2024-08-04T16:36:01.977946652Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:01.977980491Z   warnings.warn(
2024-08-04T16:36:02.415112001Z The following values were not passed to `accelerate launch` and had defaults used instead:
2024-08-04T16:36:02.415132166Z 		More than one GPU was found, enabling multi-GPU training.
2024-08-04T16:36:02.415134030Z 		If this was unintended please pass in `--num_processes=1`.
2024-08-04T16:36:02.415135457Z 	`--dynamo_backend` was set to a value of `'no'`
2024-08-04T16:36:02.415136735Z To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
2024-08-04T16:36:04.434412855Z [2024-08-04 09:36:04,434] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:04.490707809Z df: /root/.triton/autotune: No such file or directory
2024-08-04T16:36:05.278384054Z W0804 09:36:05.277000 139854548326208 torch/distributed/run.py:757] 
2024-08-04T16:36:05.278403964Z W0804 09:36:05.277000 139854548326208 torch/distributed/run.py:757] *****************************************
2024-08-04T16:36:05.278406141Z W0804 09:36:05.277000 139854548326208 torch/distributed/run.py:757] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
2024-08-04T16:36:05.278409143Z W0804 09:36:05.277000 139854548326208 torch/distributed/run.py:757] *****************************************
2024-08-04T16:36:21.843026844Z [2024-08-04 09:36:21,842] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.523012511Z [2024-08-04 09:36:22,522] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.573451092Z [2024-08-04 09:36:22,573] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.603930997Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:22.603944863Z   warnings.warn(
2024-08-04T16:36:22.621606043Z [2024-08-04 09:36:22,621] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.647211427Z [2024-08-04 09:36:22,646] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.712706895Z [2024-08-04 09:36:22,712] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.715995097Z [2024-08-04 09:36:22,715] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.749528972Z [2024-08-04 09:36:22,748] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
2024-08-04T16:36:22.913869542Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:22.913892815Z   warnings.warn(
2024-08-04T16:36:22.942232523Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:22.949389153Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:22.949414709Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:22.949419543Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:22.965623927Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:22.965635733Z   warnings.warn(
2024-08-04T16:36:23.016368224Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:23.016393387Z   warnings.warn(
2024-08-04T16:36:23.040115531Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:23.040128746Z   warnings.warn(
2024-08-04T16:36:23.103339972Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:23.103363958Z   warnings.warn(
2024-08-04T16:36:23.116012308Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:23.116017091Z   warnings.warn(
2024-08-04T16:36:23.163480250Z /opt/miniconda3/lib/python3.10/site-packages/transformers/utils/hub.py:127: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
2024-08-04T16:36:23.163502563Z   warnings.warn(
2024-08-04T16:36:23.239013259Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.246399074Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.246413636Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.246421201Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.298632074Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.306375444Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.306394970Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.306406332Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.348608104Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.356921409Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.356943389Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.356963257Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.364055203Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.371953414Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.371975588Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.371997706Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.376524833Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.376585151Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.428979753Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.436462949Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.436480930Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.436500768Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.489508030Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.497153929Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.497179744Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.497201936Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.527639461Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-04T16:36:23.535298374Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-04T16:36:23.535326042Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-04T16:36:23.535328355Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-04T16:36:23.692689820Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.692712930Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.718071713Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.718084862Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.805242315Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.805263262Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.816986264Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.816990714Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.879349080Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.879367942Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.884764438Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.885100688Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:23.932885791Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-04T16:36:23.932901495Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
2024-08-04T16:36:24.369595047Z [2024-08-04 09:36:24,369] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.457206933Z [2024-08-04 09:36:24,456] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.476300776Z [2024-08-04 09:36:24,475] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.568389915Z [2024-08-04 09:36:24,568] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.568404218Z [2024-08-04 09:36:24,568] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
2024-08-04T16:36:24.576746511Z [2024-08-04 09:36:24,576] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.590847997Z [2024-08-04 09:36:24,590] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.657164527Z [2024-08-04 09:36:24,656] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.669285434Z [2024-08-04 09:36:24,669] [INFO] [comm.py:637:init_distributed] cdb=None
2024-08-04T16:36:24.952440146Z 08/04/2024 09:36:24 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:24.952461007Z Num processes: 32
2024-08-04T16:36:24.952463100Z Process index: 7
2024-08-04T16:36:24.952465247Z Local process index: 7
2024-08-04T16:36:24.952466847Z Device: cuda:7
2024-08-04T16:36:24.952468295Z 
2024-08-04T16:36:24.952469725Z Mixed precision type: bf16
2024-08-04T16:36:24.952472213Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:24.952477236Z 
2024-08-04T16:36:24.987864734Z 08/04/2024 09:36:24 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:24.987879901Z Num processes: 32
2024-08-04T16:36:24.987882038Z Process index: 0
2024-08-04T16:36:24.987883528Z Local process index: 0
2024-08-04T16:36:24.987885175Z Device: cuda:0
2024-08-04T16:36:24.987886712Z 
2024-08-04T16:36:24.987888106Z Mixed precision type: bf16
2024-08-04T16:36:24.987890043Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:24.987893207Z 
2024-08-04T16:36:25.098113168Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.098132442Z Num processes: 32
2024-08-04T16:36:25.098134213Z Process index: 6
2024-08-04T16:36:25.098135782Z Local process index: 6
2024-08-04T16:36:25.098137108Z Device: cuda:6
2024-08-04T16:36:25.098138560Z 
2024-08-04T16:36:25.098139908Z Mixed precision type: bf16
2024-08-04T16:36:25.098150636Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.098153807Z 
2024-08-04T16:36:25.190505787Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.190516901Z Num processes: 32
2024-08-04T16:36:25.190518768Z Process index: 1
2024-08-04T16:36:25.190520002Z Local process index: 1
2024-08-04T16:36:25.190521219Z Device: cuda:1
2024-08-04T16:36:25.190522699Z 
2024-08-04T16:36:25.190524518Z Mixed precision type: bf16
2024-08-04T16:36:25.190526497Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.190530381Z 
2024-08-04T16:36:25.249541934Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.249552746Z Num processes: 32
2024-08-04T16:36:25.249554553Z Process index: 2
2024-08-04T16:36:25.249555992Z Local process index: 2
2024-08-04T16:36:25.249557367Z Device: cuda:2
2024-08-04T16:36:25.249558541Z 
2024-08-04T16:36:25.249559893Z Mixed precision type: bf16
2024-08-04T16:36:25.249561294Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.249563848Z 
2024-08-04T16:36:25.250360699Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.250362986Z Num processes: 32
2024-08-04T16:36:25.250364382Z Process index: 3
2024-08-04T16:36:25.250365514Z Local process index: 3
2024-08-04T16:36:25.250373422Z Device: cuda:3
2024-08-04T16:36:25.250374832Z 
2024-08-04T16:36:25.250376103Z Mixed precision type: bf16
2024-08-04T16:36:25.250377288Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.250379589Z 
2024-08-04T16:36:25.254804246Z jupiter-cs-aus-134:95:95 [0] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.255120824Z jupiter-cs-aus-134:95:95 [0] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.255378317Z jupiter-cs-aus-134:95:95 [0] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.255671189Z NCCL version 2.20.5+cuda12.4
2024-08-04T16:36:25.258102796Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.258104341Z Num processes: 32
2024-08-04T16:36:25.258105637Z Process index: 5
2024-08-04T16:36:25.258106758Z Local process index: 5
2024-08-04T16:36:25.258108118Z Device: cuda:5
2024-08-04T16:36:25.258109260Z 
2024-08-04T16:36:25.258110577Z Mixed precision type: bf16
2024-08-04T16:36:25.258112026Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.258114318Z 
2024-08-04T16:36:25.259792449Z 08/04/2024 09:36:25 - INFO - __main__ - Distributed environment: DEEPSPEED  Backend: nccl
2024-08-04T16:36:25.259796739Z Num processes: 32
2024-08-04T16:36:25.259798344Z Process index: 4
2024-08-04T16:36:25.259799563Z Local process index: 4
2024-08-04T16:36:25.259801035Z Device: cuda:4
2024-08-04T16:36:25.259802383Z 
2024-08-04T16:36:25.259803936Z Mixed precision type: bf16
2024-08-04T16:36:25.259805255Z ds_config: {'bf16': {'enabled': True}, 'zero_optimization': {'stage': 3, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': inf, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'fp16': {'enabled': False}}
2024-08-04T16:36:25.259819242Z 
2024-08-04T16:36:25.274352312Z jupiter-cs-aus-134:97:97 [2] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.274363666Z jupiter-cs-aus-134:98:98 [3] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.274365456Z jupiter-cs-aus-134:96:96 [1] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.274367080Z jupiter-cs-aus-134:102:102 [7] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.274594646Z jupiter-cs-aus-134:101:101 [6] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.277253940Z jupiter-cs-aus-134:98:98 [3] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.277255997Z jupiter-cs-aus-134:97:97 [2] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.277257401Z jupiter-cs-aus-134:102:102 [7] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.277258782Z jupiter-cs-aus-134:101:101 [6] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.277260216Z jupiter-cs-aus-134:96:96 [1] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.277374129Z jupiter-cs-aus-134:99:99 [4] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.277613478Z jupiter-cs-aus-134:102:102 [7] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.277621106Z jupiter-cs-aus-134:96:96 [1] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.277622760Z jupiter-cs-aus-134:97:97 [2] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.277624212Z jupiter-cs-aus-134:98:98 [3] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.277625766Z jupiter-cs-aus-134:101:101 [6] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.277877465Z jupiter-cs-aus-134:99:99 [4] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.278005424Z jupiter-cs-aus-134:100:100 [5] NCCL INFO cudaDriverVersion 12010
2024-08-04T16:36:25.278056294Z jupiter-cs-aus-134:99:99 [4] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.278612253Z jupiter-cs-aus-134:100:100 [5] NCCL INFO Bootstrap : Using ibs255:10.246.0.18<0>
2024-08-04T16:36:25.278844303Z jupiter-cs-aus-134:100:100 [5] NCCL INFO NET/Plugin : dlerror=libnccl-net.so: cannot open shared object file: No such file or directory No plugin found (libnccl-net.so), using internal implementation
2024-08-04T16:36:25.510707395Z jupiter-cs-aus-134:100:327 [5] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.510722408Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.510724500Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Using network IB
2024-08-04T16:36:25.514547760Z jupiter-cs-aus-134:95:320 [0] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.514698102Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.514700049Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Using network IB
2024-08-04T16:36:25.523246037Z jupiter-cs-aus-134:98:324 [3] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.523398746Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.523400521Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Using network IB
2024-08-04T16:36:25.527503362Z jupiter-cs-aus-134:97:323 [2] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.527659756Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.527661762Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Using network IB
2024-08-04T16:36:25.527968946Z jupiter-cs-aus-134:101:321 [6] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.528117427Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.528119439Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Using network IB
2024-08-04T16:36:25.529184543Z jupiter-cs-aus-134:102:325 [7] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.529337113Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.529338996Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Using network IB
2024-08-04T16:36:25.530283871Z jupiter-cs-aus-134:99:326 [4] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.530453325Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.530468610Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Using network IB
2024-08-04T16:36:25.569934131Z jupiter-cs-aus-134:96:322 [1] NCCL INFO NET/IB : Using [0]mlx5_0:1/IB [1]mlx5_1:1/IB [2]mlx5_bond_0:1/RoCE [3]mlx5_2:1/IB [4]mlx5_3:1/IB [5]mlx5_4:1/IB [6]mlx5_5:1/IB [7]mlx5_6:1/IB [8]mlx5_7:1/IB [RO]; OOB ibs255:10.246.0.18<0>
2024-08-04T16:36:25.569950542Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:36:25.569952648Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Using network IB
2024-08-04T16:36:26.691080618Z jupiter-cs-aus-134:97:323 [2] NCCL INFO comm 0xa822120 rank 2 nranks 32 cudaDev 2 nvmlDev 2 busId 3a000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691106366Z jupiter-cs-aus-134:96:322 [1] NCCL INFO comm 0xb484410 rank 1 nranks 32 cudaDev 1 nvmlDev 1 busId 2a000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691109649Z jupiter-cs-aus-134:95:320 [0] NCCL INFO comm 0xb8be120 rank 0 nranks 32 cudaDev 0 nvmlDev 0 busId 18000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691112546Z jupiter-cs-aus-134:98:324 [3] NCCL INFO comm 0xa0f91b0 rank 3 nranks 32 cudaDev 3 nvmlDev 3 busId 5d000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691114964Z jupiter-cs-aus-134:102:325 [7] NCCL INFO comm 0xb01b030 rank 7 nranks 32 cudaDev 7 nvmlDev 7 busId e4000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691116537Z jupiter-cs-aus-134:101:321 [6] NCCL INFO comm 0xa1944d0 rank 6 nranks 32 cudaDev 6 nvmlDev 6 busId 91000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691118091Z jupiter-cs-aus-134:100:327 [5] NCCL INFO comm 0x9e65470 rank 5 nranks 32 cudaDev 5 nvmlDev 5 busId 8b000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:26.691119843Z jupiter-cs-aus-134:99:326 [4] NCCL INFO comm 0xab6a750 rank 4 nranks 32 cudaDev 4 nvmlDev 4 busId 84000 commId 0x2621bd3530dda406 - Init START
2024-08-04T16:36:30.279132088Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:36:30.279149350Z jupiter-cs-aus-134:101:321 [6] NCCL INFO NVLS multicast support is not available on dev 6
2024-08-04T16:36:30.280676209Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Setting affinity for GPU 0 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:36:30.280678704Z jupiter-cs-aus-134:95:320 [0] NCCL INFO NVLS multicast support is not available on dev 0
2024-08-04T16:36:30.334629527Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:36:30.334673326Z jupiter-cs-aus-134:99:326 [4] NCCL INFO NVLS multicast support is not available on dev 4
2024-08-04T16:36:30.381123310Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:36:30.381125201Z jupiter-cs-aus-134:100:327 [5] NCCL INFO NVLS multicast support is not available on dev 5
2024-08-04T16:36:30.392348400Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Setting affinity for GPU 1 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:36:30.392359087Z jupiter-cs-aus-134:96:322 [1] NCCL INFO NVLS multicast support is not available on dev 1
2024-08-04T16:36:30.405764828Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:36:30.405766781Z jupiter-cs-aus-134:102:325 [7] NCCL INFO NVLS multicast support is not available on dev 7
2024-08-04T16:36:30.415224393Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Setting affinity for GPU 2 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:36:30.415469004Z jupiter-cs-aus-134:97:323 [2] NCCL INFO NVLS multicast support is not available on dev 2
2024-08-04T16:36:30.423423644Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Setting affinity for GPU 3 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:36:30.423490109Z jupiter-cs-aus-134:98:324 [3] NCCL INFO NVLS multicast support is not available on dev 3
2024-08-04T16:36:30.485004466Z jupiter-cs-aus-134:102:325 [7] NCCL INFO comm 0xb01b030 rank 7 nRanks 32 nNodes 4 localRanks 8 localRank 7 MNNVL 0
2024-08-04T16:36:30.485007659Z jupiter-cs-aus-134:101:321 [6] NCCL INFO comm 0xa1944d0 rank 6 nRanks 32 nNodes 4 localRanks 8 localRank 6 MNNVL 0
2024-08-04T16:36:30.485009058Z jupiter-cs-aus-134:100:327 [5] NCCL INFO comm 0x9e65470 rank 5 nRanks 32 nNodes 4 localRanks 8 localRank 5 MNNVL 0
2024-08-04T16:36:30.485010369Z jupiter-cs-aus-134:98:324 [3] NCCL INFO comm 0xa0f91b0 rank 3 nRanks 32 nNodes 4 localRanks 8 localRank 3 MNNVL 0
2024-08-04T16:36:30.485011647Z jupiter-cs-aus-134:99:326 [4] NCCL INFO comm 0xab6a750 rank 4 nRanks 32 nNodes 4 localRanks 8 localRank 4 MNNVL 0
2024-08-04T16:36:30.485013040Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] 0/-1/-1->7->6 [2] 0/-1/-1->7->6 [3] 0/-1/-1->7->6 [4] 0/-1/-1->7->6 [5] 0/-1/-1->7->6 [6] 0/-1/-1->7->6 [7] 0/23/-1->7->-1 [8] -1/-1/-1->7->6 [9] 0/-1/-1->7->6 [10] 0/-1/-1->7->6 [11] 0/-1/-1->7->6 [12] 0/-1/-1->7->6 [13] 0/-1/-1->7->6 [14] 0/-1/-1->7->6 [15] 0/-1/-1->7->15
2024-08-04T16:36:30.485015640Z jupiter-cs-aus-134:102:325 [7] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485017103Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/22/-1->6->-1 [7] -1/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->14 [15] -1/-1/-1->6->5
2024-08-04T16:36:30.485019431Z jupiter-cs-aus-134:101:321 [6] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485020667Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/21/-1->5->-1 [6] -1/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->13 [14] -1/-1/-1->5->4 [15] 6/-1/-1->5->4
2024-08-04T16:36:30.485024716Z jupiter-cs-aus-134:100:327 [5] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485026282Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/19/-1->3->-1 [4] -1/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->11 [12] -1/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2
2024-08-04T16:36:30.485028363Z jupiter-cs-aus-134:98:324 [3] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485029628Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/20/-1->4->-1 [5] -1/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->12 [13] -1/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3
2024-08-04T16:36:30.485031680Z jupiter-cs-aus-134:99:326 [4] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485303681Z jupiter-cs-aus-134:95:320 [0] NCCL INFO comm 0xb8be120 rank 0 nRanks 32 nNodes 4 localRanks 8 localRank 0 MNNVL 0
2024-08-04T16:36:30.485305360Z jupiter-cs-aus-134:97:323 [2] NCCL INFO comm 0xa822120 rank 2 nRanks 32 nNodes 4 localRanks 8 localRank 2 MNNVL 0
2024-08-04T16:36:30.485306882Z jupiter-cs-aus-134:96:322 [1] NCCL INFO comm 0xb484410 rank 1 nRanks 32 nNodes 4 localRanks 8 localRank 1 MNNVL 0
2024-08-04T16:36:30.485323073Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/16 :    0   7   6   5   4   3   2   1   9  10  11  12  13  14  15   8  16  23  22  21
2024-08-04T16:36:30.485324568Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 01/16 :    0   8  15  14  13  12  11  10   9  17  18  19  20  21  22  23  16  24  31  30
2024-08-04T16:36:30.485325875Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 02/16 :    0   7   6   5   4   3  11  12  13  14  15   8   9  10  18  17  16  23  22  21
2024-08-04T16:36:30.485327433Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 03/16 :    0   1   2  10   9   8  15  14  13  12  11  19  20  21  22  23  16  17  18  26
2024-08-04T16:36:30.485328726Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 04/16 :    0   7   6   5  13  14  15   8   9  10  11  12  20  19  18  17  16  23  22  21
2024-08-04T16:36:30.485330041Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 05/16 :    0   1   2   3   4  12  11  10   9   8  15  14  13  21  22  23  16  17  18  19
2024-08-04T16:36:30.485334256Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 06/16 :    0   7  15   8   9  10  11  12  13  14  22  21  20  19  18  17  16  23  31  24
2024-08-04T16:36:30.485335774Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 07/16 :    0   1   2   3   4   5   6  14  13  12  11  10   9   8  15  23  16  17  18  19
2024-08-04T16:36:30.485337403Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/18/-1->2->-1 [3] -1/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->10 [11] -1/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1
2024-08-04T16:36:30.485352945Z jupiter-cs-aus-134:97:323 [2] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485354338Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/16 :    0   7   6   5   4   3   2   1   9  10  11  12  13  14  15   8  16  23  22  21
2024-08-04T16:36:30.485355890Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 09/16 :    0   8  15  14  13  12  11  10   9  17  18  19  20  21  22  23  16  24  31  30
2024-08-04T16:36:30.485357216Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 10/16 :    0   7   6   5   4   3  11  12  13  14  15   8   9  10  18  17  16  23  22  21
2024-08-04T16:36:30.485358526Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/17/-1->1->-1 [2] -1/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->9 [10] -1/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0
2024-08-04T16:36:30.485360535Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 11/16 :    0   1   2  10   9   8  15  14  13  12  11  19  20  21  22  23  16  17  18  26
2024-08-04T16:36:30.485361850Z jupiter-cs-aus-134:96:322 [1] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.485363093Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 12/16 :    0   7   6   5  13  14  15   8   9  10  11  12  20  19  18  17  16  23  22  21
2024-08-04T16:36:30.485364409Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 13/16 :    0   1   2   3   4  12  11  10   9   8  15  14  13  21  22  23  16  17  18  19
2024-08-04T16:36:30.485368940Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 14/16 :    0   7  15   8   9  10  11  12  13  14  22  21  20  19  18  17  16  23  31  24
2024-08-04T16:36:30.485370342Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 15/16 :    0   1   2   3   4   5   6  14  13  12  11  10   9   8  15  23  16  17  18  19
2024-08-04T16:36:30.485371650Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Trees [0] 1/16/-1->0->-1 [1] -1/-1/-1->0->7 [2] 1/-1/-1->0->7 [3] 1/-1/-1->0->7 [4] 1/-1/-1->0->7 [5] 1/-1/-1->0->7 [6] 1/-1/-1->0->7 [7] 1/-1/-1->0->7 [8] 1/-1/-1->0->8 [9] -1/-1/-1->0->7 [10] 1/-1/-1->0->7 [11] 1/-1/-1->0->7 [12] 1/-1/-1->0->7 [13] 1/-1/-1->0->7 [14] 1/-1/-1->0->7 [15] 1/-1/-1->0->7
2024-08-04T16:36:30.485373754Z jupiter-cs-aus-134:95:320 [0] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:36:30.521268375Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.522338936Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.523197845Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.524040137Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.524835172Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.525623710Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.528677275Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.529253012Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.529734033Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.530201436Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.530654824Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.531093643Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.531745469Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.531780755Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.532344360Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.532397071Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.534744323Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.535204215Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.535614184Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.536036528Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.536336659Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.536601302Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.536665807Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.537005538Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.537128665Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.537415087Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.537531533Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.537816248Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.537931281Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.538214597Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.538330483Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.538608567Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.538722621Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.539002702Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.539116452Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.539405197Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.539692523Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.539725462Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.539859703Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.539906938Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.539990952Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540123425Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 02/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540202812Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.540281757Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540418523Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 04/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540496848Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.540570657Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540704411Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 06/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540780853Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.540862800Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.540997576Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.541072033Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.541153322Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.541288115Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 10/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.541534775Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 12/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.541693246Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 14/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.543500809Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 04/0 : 28[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.543585264Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 12/0 : 28[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.543654188Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.543743701Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.544901689Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 02/0 : 26[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.544965612Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 03/0 : 27[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.544967131Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 10/0 : 26[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.545015965Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.545038714Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 11/0 : 27[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.545063311Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 01/0 : 25[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.545064781Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.545107225Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.545137085Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 09/0 : 25[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.545167305Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.545206037Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.545254984Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.545344249Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.545400338Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 06/0 : 30[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.545402036Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 05/0 : 29[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.545472943Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 14/0 : 30[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.545491506Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 13/0 : 29[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.545522025Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.545523459Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.545565758Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.545593445Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.545630661Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.545792309Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.546473938Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.546712383Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/0 : 24[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.546771064Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/0 : 24[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.546820044Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.546871162Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.547059330Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 07/0 : 31[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.547115124Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.547117578Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 15/0 : 31[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.547187390Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.547255925Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.547753270Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.547949921Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.548711543Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.548846657Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.549386403Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.549458125Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.549749823Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.550232887Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.550322265Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.550840655Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.551038852Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.551125858Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.551565024Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.551670485Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.551748060Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.551814214Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.551854598Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.552202860Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.552295144Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.552407512Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.552479849Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.552509452Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.552595390Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.552917896Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.553025806Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.553135993Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.553208490Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.553238654Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.553345629Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.553638256Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.553691260Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.553805930Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.553877424Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.553933736Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.554099864Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.554237834Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.554353791Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.554440743Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.554537115Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.554559568Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.554843878Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.554994344Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.555064508Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.555198330Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.555320451Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.555579876Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.555666509Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.555763438Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.556166749Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.556783032Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.557544340Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.941917903Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Connected all rings
2024-08-04T16:36:30.941934671Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Connected all rings
2024-08-04T16:36:30.943508380Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.943717421Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.943850909Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.943922448Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.944046348Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.944160051Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.944237565Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.944371782Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.944455099Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.944543368Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Connected all rings
2024-08-04T16:36:30.944580597Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.944681811Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.944799644Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.944959815Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.945170496Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.946121686Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.946275508Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.946429611Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.946587358Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.946739306Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.946890507Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.947041915Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.947221443Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Connected all rings
2024-08-04T16:36:30.947249078Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.947629594Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.947809186Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.947968373Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.948130792Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.948284648Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.948443283Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.948598235Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.948650223Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.949001858Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.949003761Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Connected all rings
2024-08-04T16:36:30.950573532Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.950730743Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.950881163Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.951032416Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.951430981Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.951583721Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.951887928Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.951889526Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.952741208Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Connected all rings
2024-08-04T16:36:30.952788205Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Connected all rings
2024-08-04T16:36:30.952789950Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Connected all rings
2024-08-04T16:36:30.952933907Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 01/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.953353290Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 01/0 : 17[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.953371880Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 03/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.953393990Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 01/0 : 1[1] -> 17[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.953672138Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:36:30.953806320Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 05/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.954244299Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 07/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.954798102Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 09/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.955336508Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 11/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.955862338Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 13/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.956112479Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.956387403Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 15/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.956624200Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.956858430Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.957114807Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.957205525Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.957439142Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.957533455Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.957761706Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.957788182Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.957872821Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.958021106Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.958099933Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.958180164Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.958325992Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.958407147Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.958487297Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.958636819Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:36:30.958723307Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.958978388Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.958980166Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.959073261Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.959101483Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.959703315Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 03/0 : 19[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.959752446Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 03/0 : 3[3] -> 19[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.960168448Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:36:30.960720037Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.960929197Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 02/0 : 18[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.960930812Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.960975437Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 02/0 : 2[2] -> 18[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.961154662Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:36:30.961238982Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.962294515Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 06/0 : 22[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.962319172Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 04/0 : 20[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.962342718Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 06/0 : 6[6] -> 22[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.962384423Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 04/0 : 4[4] -> 20[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.962413520Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 05/0 : 21[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.962487592Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.962506085Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:36:30.962562810Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:36:30.962681180Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 05/0 : 5[5] -> 21[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.962778888Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.962818546Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:36:30.963108589Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.963110245Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.963242927Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.963650789Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.963963472Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.964108555Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.964283545Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.964381260Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.964476329Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 07/0 : 23[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.964478057Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/0 : 16[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.964524531Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 00/0 : 0[0] -> 16[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.964526091Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 07/0 : 7[7] -> 23[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.964626107Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.964685074Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:36:30.964686742Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.964989464Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:36:30.965010481Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:36:30.965076882Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.965140446Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.965710991Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.965735771Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.966058483Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.966181969Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.966287271Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.966581282Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.966774770Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.966968928Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.967563873Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.967565833Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.967841293Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:36:30.967913105Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.968348532Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:36:30.968362013Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.968612662Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.968775217Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.969107555Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.969265129Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.969649443Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.969878196Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:36:30.970586930Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.970675362Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.972616524Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.976982111Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.977006316Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.977513110Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.977604424Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.977860840Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.977880059Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.977968030Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.978229034Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:36:30.978247375Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.978381910Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.978669927Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.978781077Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.979118416Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.979290496Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.979575551Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:36:30.979755404Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.980155557Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:30.981403851Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:36:31.392219210Z jupiter-cs-aus-134:97:323 [2] NCCL INFO Connected all trees
2024-08-04T16:36:31.392236683Z jupiter-cs-aus-134:97:323 [2] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.392242692Z jupiter-cs-aus-134:97:323 [2] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.400739049Z jupiter-cs-aus-134:98:324 [3] NCCL INFO Connected all trees
2024-08-04T16:36:31.400747522Z jupiter-cs-aus-134:98:324 [3] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.400749548Z jupiter-cs-aus-134:98:324 [3] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.400822560Z jupiter-cs-aus-134:99:326 [4] NCCL INFO Connected all trees
2024-08-04T16:36:31.400855337Z jupiter-cs-aus-134:100:327 [5] NCCL INFO Connected all trees
2024-08-04T16:36:31.400857827Z jupiter-cs-aus-134:99:326 [4] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.400859399Z jupiter-cs-aus-134:99:326 [4] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.400868671Z jupiter-cs-aus-134:100:327 [5] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.400874215Z jupiter-cs-aus-134:100:327 [5] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.401600242Z jupiter-cs-aus-134:101:321 [6] NCCL INFO Connected all trees
2024-08-04T16:36:31.401607555Z jupiter-cs-aus-134:102:325 [7] NCCL INFO Connected all trees
2024-08-04T16:36:31.401609093Z jupiter-cs-aus-134:95:320 [0] NCCL INFO Connected all trees
2024-08-04T16:36:31.401610484Z jupiter-cs-aus-134:101:321 [6] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.401611744Z jupiter-cs-aus-134:101:321 [6] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.401613383Z jupiter-cs-aus-134:102:325 [7] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.401614593Z jupiter-cs-aus-134:102:325 [7] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.401616124Z jupiter-cs-aus-134:96:322 [1] NCCL INFO Connected all trees
2024-08-04T16:36:31.401617320Z jupiter-cs-aus-134:96:322 [1] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.401618772Z jupiter-cs-aus-134:96:322 [1] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.401620050Z jupiter-cs-aus-134:95:320 [0] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:36:31.401621441Z jupiter-cs-aus-134:95:320 [0] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:36:31.577174958Z jupiter-cs-aus-134:102:325 [7] NCCL INFO comm 0xb01b030 rank 7 nranks 32 cudaDev 7 nvmlDev 7 busId e4000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577197100Z jupiter-cs-aus-134:100:327 [5] NCCL INFO comm 0x9e65470 rank 5 nranks 32 cudaDev 5 nvmlDev 5 busId 8b000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577199555Z jupiter-cs-aus-134:98:324 [3] NCCL INFO comm 0xa0f91b0 rank 3 nranks 32 cudaDev 3 nvmlDev 3 busId 5d000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577201691Z jupiter-cs-aus-134:99:326 [4] NCCL INFO comm 0xab6a750 rank 4 nranks 32 cudaDev 4 nvmlDev 4 busId 84000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577203491Z jupiter-cs-aus-134:96:322 [1] NCCL INFO comm 0xb484410 rank 1 nranks 32 cudaDev 1 nvmlDev 1 busId 2a000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577205014Z jupiter-cs-aus-134:101:321 [6] NCCL INFO comm 0xa1944d0 rank 6 nranks 32 cudaDev 6 nvmlDev 6 busId 91000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577217788Z jupiter-cs-aus-134:97:323 [2] NCCL INFO comm 0xa822120 rank 2 nranks 32 cudaDev 2 nvmlDev 2 busId 3a000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:31.577643182Z jupiter-cs-aus-134:95:320 [0] NCCL INFO comm 0xb8be120 rank 0 nranks 32 cudaDev 0 nvmlDev 0 busId 18000 commId 0x2621bd3530dda406 - Init COMPLETE
2024-08-04T16:36:32.142410799Z 
Downloading readme:   0%|          | 0.00/4.46k [00:00<?, ?B/s]
Downloading readme: 100%|██████████| 4.46k/4.46k [00:00<00:00, 28.0MB/s]
2024-08-04T16:36:35.307879663Z 
Downloading data:   0%|          | 0.00/143M [00:00<?, ?B/s]
Downloading data:   7%|▋         | 10.5M/143M [00:00<00:01, 69.8MB/s]
Downloading data:  29%|██▉       | 41.9M/143M [00:00<00:00, 185MB/s] 
Downloading data:  51%|█████     | 73.4M/143M [00:00<00:00, 227MB/s]
Downloading data:  73%|███████▎  | 105M/143M [00:00<00:00, 243MB/s] 
Downloading data:  95%|█████████▌| 136M/143M [00:00<00:00, 236MB/s]
Downloading data: 100%|██████████| 143M/143M [00:00<00:00, 167MB/s]
2024-08-04T16:36:35.957580438Z 
Generating train split:   0%|          | 0/60917 [00:00<?, ? examples/s]
Generating train split:  11%|█▏        | 7000/60917 [00:00<00:00, 60715.24 examples/s]
Generating train split:  34%|███▍      | 21000/60917 [00:00<00:00, 100561.18 examples/s]
Generating train split:  54%|█████▍    | 33000/60917 [00:00<00:00, 107927.77 examples/s]
Generating train split:  79%|███████▉  | 48000/60917 [00:00<00:00, 101930.67 examples/s]
Generating train split: 100%|██████████| 60917/60917 [00:00<00:00, 91889.58 examples/s] 
Generating train split: 100%|██████████| 60917/60917 [00:00<00:00, 94110.24 examples/s]
2024-08-04T16:36:35.989903687Z loading configuration file /model/config.json
2024-08-04T16:36:35.990528739Z Model config OlmoeConfig {
2024-08-04T16:36:35.990532331Z   "_name_or_path": "/model",
2024-08-04T16:36:35.990533995Z   "architectures": [
2024-08-04T16:36:35.990535479Z     "OlmoeForCausalLM"
2024-08-04T16:36:35.990537006Z   ],
2024-08-04T16:36:35.990538572Z   "attention_bias": false,
2024-08-04T16:36:35.990540095Z   "attention_dropout": 0.0,
2024-08-04T16:36:35.990541457Z   "clip_qkv": null,
2024-08-04T16:36:35.990542887Z   "eos_token_id": 50279,
2024-08-04T16:36:35.990544080Z   "hidden_act": "silu",
2024-08-04T16:36:35.990545547Z   "hidden_size": 2048,
2024-08-04T16:36:35.990546734Z   "initializer_range": 0.02,
2024-08-04T16:36:35.990548287Z   "intermediate_size": 1024,
2024-08-04T16:36:35.990549452Z   "max_position_embeddings": 4096,
2024-08-04T16:36:35.990550839Z   "model_type": "olmoe",
2024-08-04T16:36:35.990552054Z   "norm_topk_prob": false,
2024-08-04T16:36:35.990553413Z   "num_attention_heads": 16,
2024-08-04T16:36:35.990554568Z   "num_experts": 64,
2024-08-04T16:36:35.990555874Z   "num_experts_per_tok": 8,
2024-08-04T16:36:35.990566563Z   "num_hidden_layers": 16,
2024-08-04T16:36:35.990567970Z   "num_key_value_heads": 16,
2024-08-04T16:36:35.990569179Z   "output_router_logits": true,
2024-08-04T16:36:35.990570328Z   "pad_token_id": 1,
2024-08-04T16:36:35.990571477Z   "rope_scaling": null,
2024-08-04T16:36:35.990572801Z   "rope_theta": 10000.0,
2024-08-04T16:36:35.990574041Z   "router_aux_loss_coef": 0.001,
2024-08-04T16:36:35.990575378Z   "tie_word_embeddings": false,
2024-08-04T16:36:35.990576563Z   "torch_dtype": "bfloat16",
2024-08-04T16:36:35.990577968Z   "transformers_version": "4.43.0.dev0",
2024-08-04T16:36:35.990579230Z   "use_cache": true,
2024-08-04T16:36:35.990580605Z   "vocab_size": 50304
2024-08-04T16:36:35.990581780Z }
2024-08-04T16:36:35.990583106Z 
2024-08-04T16:36:35.991027251Z loading file vocab.json
2024-08-04T16:36:35.991039783Z loading file merges.txt
2024-08-04T16:36:35.991044620Z loading file tokenizer.json
2024-08-04T16:36:35.991046777Z loading file added_tokens.json
2024-08-04T16:36:35.991048663Z loading file special_tokens_map.json
2024-08-04T16:36:35.991070986Z loading file tokenizer_config.json
2024-08-04T16:36:36.043567842Z loading weights file /model/pytorch_model.bin.index.json
2024-08-04T16:36:36.044827225Z Detected DeepSpeed ZeRO-3: activating zero.init() for this model
2024-08-04T16:36:36.046413618Z The model was loaded with use_flash_attention_2=True, which is deprecated and may be removed in a future release. Please use `attn_implementation="flash_attention_2"` instead.
2024-08-04T16:36:36.047438011Z You are attempting to use Flash Attention 2.0 without specifying a torch dtype. This might lead to unexpected behaviour
2024-08-04T16:36:36.047535890Z You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`.
2024-08-04T16:36:36.052581830Z Flash Attention 2.0 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in OlmoeForCausalLM is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `torch_dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", torch_dtype=torch.float16)`
2024-08-04T16:36:36.052991625Z Generate config GenerationConfig {
2024-08-04T16:36:36.052993451Z   "eos_token_id": 50279,
2024-08-04T16:36:36.052994959Z   "pad_token_id": 1
2024-08-04T16:36:36.052996176Z }
2024-08-04T16:36:36.052997470Z 
2024-08-04T16:36:36.054066865Z Flash Attention 2.0 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in OlmoeModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `torch_dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", torch_dtype=torch.float16)`
2024-08-04T16:36:37.169590636Z [2024-08-04 09:36:37,169] [INFO] [partition_parameters.py:345:__exit__] finished initializing model - num_params = 3219, num_elems = 6.92B
2024-08-04T16:36:51.458208155Z 
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.32s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.28s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.24s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.23s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.26s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.28s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.29s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:09,  4.61s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.35s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.33s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.38s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.34s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.33s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.34s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.34s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:09<00:04,  4.48s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.91s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.03s/it]
2024-08-04T16:36:51.470111956Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.88s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.99s/it]
2024-08-04T16:36:51.476648520Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.88s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  4.00s/it]
2024-08-04T16:36:51.488580130Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.89s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.00s/it]
2024-08-04T16:36:51.490625765Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.90s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.01s/it]
2024-08-04T16:36:51.501752960Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.90s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.01s/it]
2024-08-04T16:36:51.508075244Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.92s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.03s/it]
2024-08-04T16:36:51.707183978Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  3.96s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:12<00:00,  4.11s/it]
2024-08-04T16:36:51.707211034Z All model checkpoint weights were used when initializing OlmoeForCausalLM.
2024-08-04T16:36:51.707212843Z 
2024-08-04T16:36:51.707232449Z All the weights of OlmoeForCausalLM were initialized from the model checkpoint at /model.
2024-08-04T16:36:51.707234155Z If your task is similar to the task the model of the checkpoint was trained on, you can already use OlmoeForCausalLM for predictions without further training.
2024-08-04T16:36:51.734856946Z loading configuration file /model/generation_config.json
2024-08-04T16:36:51.735097784Z Generate config GenerationConfig {
2024-08-04T16:36:51.735099719Z   "eos_token_id": 50279,
2024-08-04T16:36:51.735101462Z   "pad_token_id": 1
2024-08-04T16:36:51.735102962Z }
2024-08-04T16:36:51.735104260Z 
2024-08-04T16:36:51.736104371Z loading weights file /model/pytorch_model.bin.index.json
2024-08-04T16:36:51.737206186Z Detected DeepSpeed ZeRO-3: activating zero.init() for this model
2024-08-04T16:36:51.742575202Z Generate config GenerationConfig {
2024-08-04T16:36:51.742578087Z   "eos_token_id": 50279,
2024-08-04T16:36:51.742579678Z   "pad_token_id": 1
2024-08-04T16:36:51.742580953Z }
2024-08-04T16:36:51.742582421Z 
2024-08-04T16:36:52.756126350Z [2024-08-04 09:36:52,755] [INFO] [partition_parameters.py:345:__exit__] finished initializing model - num_params = 6438, num_elems = 13.84B
2024-08-04T16:37:06.004137605Z 
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.90s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.96s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.98s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.02s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.93s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.90s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:03<00:07,  3.95s/it]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:04<00:08,  4.18s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:03,  3.99s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.01s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:03,  4.00s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:03,  3.99s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:04,  4.00s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:03,  3.97s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:07<00:03,  3.98s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:08<00:04,  4.07s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.60s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.71s/it]
2024-08-04T16:37:06.008150794Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.58s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.69s/it]
2024-08-04T16:37:06.016808138Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.60s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.70s/it]
2024-08-04T16:37:06.019344794Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.59s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.69s/it]
2024-08-04T16:37:06.023736572Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.58s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.69s/it]
2024-08-04T16:37:06.023839208Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.57s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.57s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.67s/it]
2024-08-04T16:37:06.023888213Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.68s/it]
2024-08-04T16:37:06.221269006Z 
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.63s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:11<00:00,  3.76s/it]
2024-08-04T16:37:06.221362007Z All model checkpoint weights were used when initializing OlmoeForCausalLM.
2024-08-04T16:37:06.221376532Z 
2024-08-04T16:37:06.221381918Z All the weights of OlmoeForCausalLM were initialized from the model checkpoint at /model.
2024-08-04T16:37:06.221384174Z If your task is similar to the task the model of the checkpoint was trained on, you can already use OlmoeForCausalLM for predictions without further training.
2024-08-04T16:37:06.250848769Z loading configuration file /model/generation_config.json
2024-08-04T16:37:06.250906743Z Generate config GenerationConfig {
2024-08-04T16:37:06.250909042Z   "eos_token_id": 50279,
2024-08-04T16:37:06.250910683Z   "pad_token_id": 1
2024-08-04T16:37:06.250912203Z }
2024-08-04T16:37:06.250913426Z 
2024-08-04T16:37:20.806654277Z 
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 0/60917 [00:00<?, ? examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 8/60917 [00:00<22:09, 45.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 148/60917 [00:00<01:35, 634.25 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   1%|          | 603/60917 [00:00<00:28, 2129.52 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   2%|▏         | 1175/60917 [00:00<00:17, 3329.41 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   3%|▎         | 1841/60917 [00:00<00:13, 4407.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   4%|▍         | 2513/60917 [00:00<00:11, 5104.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   5%|▌         | 3115/60917 [00:00<00:10, 5385.90 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   6%|▌         | 3680/60917 [00:00<00:10, 5346.13 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   7%|▋         | 4243/60917 [00:01<00:10, 5408.36 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   8%|▊         | 4844/60917 [00:01<00:10, 5579.10 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   9%|▉         | 5476/60917 [00:01<00:09, 5713.99 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  10%|▉         | 6060/60917 [00:01<00:09, 5657.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  11%|█         | 6647/60917 [00:01<00:09, 5645.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  12%|█▏        | 7215/60917 [00:01<00:09, 5596.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  13%|█▎        | 7787/60917 [00:01<00:10, 5289.99 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  14%|█▎        | 8346/60917 [00:01<00:09, 5363.98 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  15%|█▍        | 8900/60917 [00:01<00:09, 5266.26 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  16%|█▌        | 9489/60917 [00:01<00:09, 5413.86 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  16%|█▋        | 10038/60917 [00:02<00:09, 5364.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  17%|█▋        | 10588/60917 [00:02<00:09, 5377.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  18%|█▊        | 11132/60917 [00:02<00:09, 5382.20 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  19%|█▉        | 11698/60917 [00:02<00:09, 5446.84 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  20%|██        | 12261/60917 [00:02<00:08, 5433.23 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  21%|██        | 12815/60917 [00:02<00:08, 5364.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  22%|██▏       | 13361/60917 [00:02<00:08, 5386.27 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  23%|██▎       | 13908/60917 [00:02<00:09, 5210.18 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  24%|██▎       | 14431/60917 [00:02<00:08, 5177.38 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  25%|██▍       | 14958/60917 [00:02<00:08, 5194.94 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  25%|██▌       | 15479/60917 [00:03<00:08, 5097.36 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  26%|██▋       | 16005/60917 [00:03<00:09, 4771.35 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  27%|██▋       | 16487/60917 [00:03<00:09, 4677.37 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  28%|██▊       | 16989/60917 [00:03<00:09, 4738.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  29%|██▉       | 17559/60917 [00:03<00:08, 4949.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  30%|██▉       | 18112/60917 [00:03<00:08, 5043.49 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  31%|███       | 18634/60917 [00:03<00:08, 5051.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  31%|███▏      | 19158/60917 [00:03<00:08, 5067.74 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  32%|███▏      | 19676/60917 [00:03<00:08, 5053.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  33%|███▎      | 20217/60917 [00:04<00:07, 5128.03 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  34%|███▍      | 20809/60917 [00:04<00:07, 5304.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  35%|███▌      | 21352/60917 [00:04<00:07, 5277.87 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  36%|███▌      | 21936/60917 [00:04<00:07, 5392.27 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  37%|███▋      | 22495/60917 [00:04<00:07, 5433.82 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  38%|███▊      | 23040/60917 [00:04<00:07, 5400.95 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  39%|███▊      | 23593/60917 [00:04<00:06, 5412.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  40%|███▉      | 24148/60917 [00:04<00:06, 5388.16 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  41%|████      | 24717/60917 [00:04<00:06, 5476.24 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  41%|████▏     | 25276/60917 [00:04<00:06, 5364.71 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  42%|████▏     | 25825/60917 [00:05<00:06, 5300.95 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  43%|████▎     | 26409/60917 [00:05<00:06, 5313.00 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  44%|████▍     | 26971/60917 [00:05<00:06, 5109.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  45%|████▌     | 27498/60917 [00:05<00:06, 5121.44 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  46%|████▌     | 28014/60917 [00:05<00:06, 5090.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  47%|████▋     | 28606/60917 [00:05<00:06, 5252.97 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  48%|████▊     | 29168/60917 [00:05<00:05, 5318.69 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  49%|████▉     | 29705/60917 [00:05<00:05, 5235.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  50%|████▉     | 30241/60917 [00:05<00:05, 5233.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  51%|█████     | 30771/60917 [00:06<00:05, 5066.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  51%|█████▏    | 31289/60917 [00:06<00:06, 4768.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  52%|█████▏    | 31818/60917 [00:06<00:05, 4881.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  53%|█████▎    | 32310/60917 [00:06<00:05, 4885.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  54%|█████▍    | 32938/60917 [00:06<00:05, 5226.31 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  55%|█████▌    | 33541/60917 [00:06<00:05, 5438.16 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  56%|█████▌    | 34141/60917 [00:06<00:04, 5591.32 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  57%|█████▋    | 34704/60917 [00:06<00:04, 5586.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  58%|█████▊    | 35266/60917 [00:06<00:04, 5591.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  59%|█████▉    | 35869/60917 [00:06<00:04, 5695.39 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  60%|█████▉    | 36454/60917 [00:07<00:04, 5719.42 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  61%|██████    | 37079/60917 [00:07<00:04, 5871.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  62%|██████▏   | 37670/60917 [00:07<00:04, 5740.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  63%|██████▎   | 38252/60917 [00:07<00:04, 5484.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  64%|██████▍   | 38852/60917 [00:07<00:03, 5567.50 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  65%|██████▍   | 39466/60917 [00:07<00:03, 5689.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  66%|██████▌   | 40127/60917 [00:07<00:03, 5773.94 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  67%|██████▋   | 40720/60917 [00:07<00:03, 5755.32 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  68%|██████▊   | 41345/60917 [00:07<00:03, 5875.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  69%|██████▉   | 41968/60917 [00:08<00:03, 5871.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  70%|██████▉   | 42596/60917 [00:08<00:03, 5887.64 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  71%|███████   | 43191/60917 [00:08<00:03, 5820.81 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  72%|███████▏  | 43782/60917 [00:08<00:02, 5811.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  73%|███████▎  | 44376/60917 [00:08<00:02, 5656.93 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  74%|███████▍  | 44956/60917 [00:08<00:02, 5481.86 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  75%|███████▍  | 45518/60917 [00:08<00:02, 5325.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  76%|███████▌  | 46053/60917 [00:08<00:02, 5229.93 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  76%|███████▋  | 46589/60917 [00:08<00:02, 4842.41 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  77%|███████▋  | 47079/60917 [00:09<00:02, 4742.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  78%|███████▊  | 47603/60917 [00:09<00:02, 4779.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  79%|███████▉  | 48127/60917 [00:09<00:02, 4775.25 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  80%|███████▉  | 48615/60917 [00:09<00:02, 4729.87 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  81%|████████  | 49102/60917 [00:09<00:02, 4742.39 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  81%|████████▏ | 49639/60917 [00:09<00:02, 4852.01 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  82%|████████▏ | 50144/60917 [00:09<00:02, 4874.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  83%|████████▎ | 50661/60917 [00:09<00:02, 4941.13 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  84%|████████▍ | 51195/60917 [00:09<00:01, 5047.81 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  85%|████████▍ | 51706/60917 [00:09<00:01, 5013.79 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  86%|████████▌ | 52218/60917 [00:10<00:01, 4943.00 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  87%|████████▋ | 52715/60917 [00:10<00:01, 4918.56 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  87%|████████▋ | 53242/60917 [00:10<00:01, 4983.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  88%|████████▊ | 53762/60917 [00:10<00:01, 5003.51 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  89%|████████▉ | 54284/60917 [00:10<00:01, 5017.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  90%|█████████ | 54826/60917 [00:10<00:01, 5073.09 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  91%|█████████ | 55344/60917 [00:10<00:01, 5011.10 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  92%|█████████▏| 55846/60917 [00:10<00:01, 4720.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  92%|█████████▏| 56338/60917 [00:10<00:01, 4383.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  93%|█████████▎| 56786/60917 [00:11<00:00, 4289.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  94%|█████████▍| 57234/60917 [00:11<00:00, 4284.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  95%|█████████▍| 57676/60917 [00:11<00:00, 3870.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  95%|█████████▌| 58074/60917 [00:11<00:00, 3653.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  96%|█████████▌| 58461/60917 [00:11<00:00, 3302.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  97%|█████████▋| 58816/60917 [00:11<00:00, 2920.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  97%|█████████▋| 59136/60917 [00:12<00:00, 2236.40 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59402/60917 [00:12<00:00, 2018.44 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59629/60917 [00:12<00:00, 1708.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59825/60917 [00:12<00:00, 1435.75 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59987/60917 [00:12<00:00, 1313.34 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▊| 60142/60917 [00:12<00:00, 1234.15 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60280/60917 [00:13<00:00, 1153.92 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60407/60917 [00:13<00:00, 1077.50 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60525/60917 [00:13<00:00, 1037.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60629/60917 [00:13<00:00, 1036.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60734/60917 [00:13<00:00, 1027.38 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60841/60917 [00:13<00:00, 691.17 examples/s] 
Tokenizing and reformatti2024-08-04T16:37:20.806654277Z ng instruction data (num_proc=16): 100%|██████████| 60917/60917 [00:14<00:00, 4286.47 examples/s]
2024-08-04T16:37:20.806654277Z 
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 0/60917 [00:00<?, ? examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 8/60917 [00:00<22:09, 45.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   0%|          | 148/60917 [00:00<01:35, 634.25 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   1%|          | 603/60917 [00:00<00:28, 2129.52 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   2%|▏         | 1175/60917 [00:00<00:17, 3329.41 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   3%|▎         | 1841/60917 [00:00<00:13, 4407.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   4%|▍         | 2513/60917 [00:00<00:11, 5104.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   5%|▌         | 3115/60917 [00:00<00:10, 5385.90 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   6%|▌         | 3680/60917 [00:00<00:10, 5346.13 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   7%|▋         | 4243/60917 [00:01<00:10, 5408.36 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   8%|▊         | 4844/60917 [00:01<00:10, 5579.10 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):   9%|▉         | 5476/60917 [00:01<00:09, 5713.99 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  10%|▉         | 6060/60917 [00:01<00:09, 5657.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  11%|█         | 6647/60917 [00:01<00:09, 5645.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  12%|█▏        | 7215/60917 [00:01<00:09, 5596.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  13%|█▎        | 7787/60917 [00:01<00:10, 5289.99 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  14%|█▎        | 8346/60917 [00:01<00:09, 5363.98 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  15%|█▍        | 8900/60917 [00:01<00:09, 5266.26 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  16%|█▌        | 9489/60917 [00:01<00:09, 5413.86 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  16%|█▋        | 10038/60917 [00:02<00:09, 5364.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  17%|█▋        | 10588/60917 [00:02<00:09, 5377.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  18%|█▊        | 11132/60917 [00:02<00:09, 5382.20 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  19%|█▉        | 11698/60917 [00:02<00:09, 5446.84 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  20%|██        | 12261/60917 [00:02<00:08, 5433.23 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  21%|██        | 12815/60917 [00:02<00:08, 5364.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  22%|██▏       | 13361/60917 [00:02<00:08, 5386.27 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  23%|██▎       | 13908/60917 [00:02<00:09, 5210.18 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  24%|██▎       | 14431/60917 [00:02<00:08, 5177.38 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  25%|██▍       | 14958/60917 [00:02<00:08, 5194.94 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  25%|██▌       | 15479/60917 [00:03<00:08, 5097.36 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  26%|██▋       | 16005/60917 [00:03<00:09, 4771.35 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  27%|██▋       | 16487/60917 [00:03<00:09, 4677.37 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  28%|██▊       | 16989/60917 [00:03<00:09, 4738.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  29%|██▉       | 17559/60917 [00:03<00:08, 4949.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  30%|██▉       | 18112/60917 [00:03<00:08, 5043.49 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  31%|███       | 18634/60917 [00:03<00:08, 5051.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  31%|███▏      | 19158/60917 [00:03<00:08, 5067.74 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  32%|███▏      | 19676/60917 [00:03<00:08, 5053.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  33%|███▎      | 20217/60917 [00:04<00:07, 5128.03 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  34%|███▍      | 20809/60917 [00:04<00:07, 5304.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  35%|███▌      | 21352/60917 [00:04<00:07, 5277.87 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  36%|███▌      | 21936/60917 [00:04<00:07, 5392.27 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  37%|███▋      | 22495/60917 [00:04<00:07, 5433.82 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  38%|███▊      | 23040/60917 [00:04<00:07, 5400.95 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  39%|███▊      | 23593/60917 [00:04<00:06, 5412.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  40%|███▉      | 24148/60917 [00:04<00:06, 5388.16 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  41%|████      | 24717/60917 [00:04<00:06, 5476.24 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  41%|████▏     | 25276/60917 [00:04<00:06, 5364.71 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  42%|████▏     | 25825/60917 [00:05<00:06, 5300.95 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  43%|████▎     | 26409/60917 [00:05<00:06, 5313.00 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  44%|████▍     | 26971/60917 [00:05<00:06, 5109.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  45%|████▌     | 27498/60917 [00:05<00:06, 5121.44 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  46%|████▌     | 28014/60917 [00:05<00:06, 5090.91 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  47%|████▋     | 28606/60917 [00:05<00:06, 5252.97 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  48%|████▊     | 29168/60917 [00:05<00:05, 5318.69 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  49%|████▉     | 29705/60917 [00:05<00:05, 5235.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  50%|████▉     | 30241/60917 [00:05<00:05, 5233.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  51%|█████     | 30771/60917 [00:06<00:05, 5066.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  51%|█████▏    | 31289/60917 [00:06<00:06, 4768.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  52%|█████▏    | 31818/60917 [00:06<00:05, 4881.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  53%|█████▎    | 32310/60917 [00:06<00:05, 4885.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  54%|█████▍    | 32938/60917 [00:06<00:05, 5226.31 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  55%|█████▌    | 33541/60917 [00:06<00:05, 5438.16 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  56%|█████▌    | 34141/60917 [00:06<00:04, 5591.32 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  57%|█████▋    | 34704/60917 [00:06<00:04, 5586.04 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  58%|█████▊    | 35266/60917 [00:06<00:04, 5591.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  59%|█████▉    | 35869/60917 [00:06<00:04, 5695.39 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  60%|█████▉    | 36454/60917 [00:07<00:04, 5719.42 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  61%|██████    | 37079/60917 [00:07<00:04, 5871.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  62%|██████▏   | 37670/60917 [00:07<00:04, 5740.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  63%|██████▎   | 38252/60917 [00:07<00:04, 5484.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  64%|██████▍   | 38852/60917 [00:07<00:03, 5567.50 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  65%|██████▍   | 39466/60917 [00:07<00:03, 5689.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  66%|██████▌   | 40127/60917 [00:07<00:03, 5773.94 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  67%|██████▋   | 40720/60917 [00:07<00:03, 5755.32 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  68%|██████▊   | 41345/60917 [00:07<00:03, 5875.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  69%|██████▉   | 41968/60917 [00:08<00:03, 5871.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  70%|██████▉   | 42596/60917 [00:08<00:03, 5887.64 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  71%|███████   | 43191/60917 [00:08<00:03, 5820.81 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  72%|███████▏  | 43782/60917 [00:08<00:02, 5811.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  73%|███████▎  | 44376/60917 [00:08<00:02, 5656.93 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  74%|███████▍  | 44956/60917 [00:08<00:02, 5481.86 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  75%|███████▍  | 45518/60917 [00:08<00:02, 5325.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  76%|███████▌  | 46053/60917 [00:08<00:02, 5229.93 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  76%|███████▋  | 46589/60917 [00:08<00:02, 4842.41 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  77%|███████▋  | 47079/60917 [00:09<00:02, 4742.57 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  78%|███████▊  | 47603/60917 [00:09<00:02, 4779.85 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  79%|███████▉  | 48127/60917 [00:09<00:02, 4775.25 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  80%|███████▉  | 48615/60917 [00:09<00:02, 4729.87 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  81%|████████  | 49102/60917 [00:09<00:02, 4742.39 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  81%|████████▏ | 49639/60917 [00:09<00:02, 4852.01 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  82%|████████▏ | 50144/60917 [00:09<00:02, 4874.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  83%|████████▎ | 50661/60917 [00:09<00:02, 4941.13 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  84%|████████▍ | 51195/60917 [00:09<00:01, 5047.81 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  85%|████████▍ | 51706/60917 [00:09<00:01, 5013.79 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  86%|████████▌ | 52218/60917 [00:10<00:01, 4943.00 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  87%|████████▋ | 52715/60917 [00:10<00:01, 4918.56 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  87%|████████▋ | 53242/60917 [00:10<00:01, 4983.96 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  88%|████████▊ | 53762/60917 [00:10<00:01, 5003.51 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  89%|████████▉ | 54284/60917 [00:10<00:01, 5017.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  90%|█████████ | 54826/60917 [00:10<00:01, 5073.09 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  91%|█████████ | 55344/60917 [00:10<00:01, 5011.10 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  92%|█████████▏| 55846/60917 [00:10<00:01, 4720.62 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  92%|█████████▏| 56338/60917 [00:10<00:01, 4383.89 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  93%|█████████▎| 56786/60917 [00:11<00:00, 4289.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  94%|█████████▍| 57234/60917 [00:11<00:00, 4284.80 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  95%|█████████▍| 57676/60917 [00:11<00:00, 3870.12 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  95%|█████████▌| 58074/60917 [00:11<00:00, 3653.65 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  96%|█████████▌| 58461/60917 [00:11<00:00, 3302.21 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  97%|█████████▋| 58816/60917 [00:11<00:00, 2920.83 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  97%|█████████▋| 59136/60917 [00:12<00:00, 2236.40 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59402/60917 [00:12<00:00, 2018.44 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59629/60917 [00:12<00:00, 1708.28 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59825/60917 [00:12<00:00, 1435.75 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  98%|█████████▊| 59987/60917 [00:12<00:00, 1313.34 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▊| 60142/60917 [00:12<00:00, 1234.15 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60280/60917 [00:13<00:00, 1153.92 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60407/60917 [00:13<00:00, 1077.50 examples/s]
Tokenizing and reformatting instruction data (num_proc=16):  99%|█████████▉| 60525/60917 [00:13<00:00, 1037.77 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60629/60917 [00:13<00:00, 1036.17 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60734/60917 [00:13<00:00, 1027.38 examples/s]
Tokenizing and reformatting instruction data (num_proc=16): 100%|█████████▉| 60841/60917 [00:13<00:00, 691.17 examples/s] 
Tokenizing and reformatti2024-08-04T16:37:20.806654277Z ng instruction data (num_proc=16): 100%|██████████| 60917/60917 [00:14<00:00, 4286.47 examples/s]
2024-08-04T16:37:24.248969631Z 
Filter:   0%|          | 0/60917 [00:00<?, ? examples/s]
Filter:   3%|▎         | 2000/60917 [00:00<00:04, 12748.47 examples/s]
Filter:   7%|▋         | 4000/60917 [00:00<00:03, 15332.64 examples/s]
Filter:  10%|▉         | 6000/60917 [00:00<00:03, 16317.91 examples/s]
Filter:  13%|█▎        | 8000/60917 [00:00<00:03, 16959.61 examples/s]
Filter:  16%|█▋        | 10000/60917 [00:00<00:02, 17504.26 examples/s]
Filter:  20%|█▉        | 12000/60917 [00:00<00:02, 18217.41 examples/s]
Filter:  23%|██▎       | 14000/60917 [00:00<00:02, 18421.45 examples/s]
Filter:  26%|██▋       | 16000/60917 [00:00<00:02, 18185.45 examples/s]
Filter:  30%|██▉       | 18000/60917 [00:01<00:02, 18372.03 examples/s]
Filter:  33%|███▎      | 20000/60917 [00:01<00:02, 18457.94 examples/s]
Filter:  36%|███▌      | 22000/60917 [00:01<00:02, 18576.48 examples/s]
Filter:  39%|███▉      | 24000/60917 [00:01<00:01, 18535.59 examples/s]
Filter:  43%|████▎     | 26000/60917 [00:01<00:01, 18580.97 examples/s]
Filter:  46%|████▌     | 28000/60917 [00:01<00:01, 18584.38 examples/s]
Filter:  49%|████▉     | 30000/60917 [00:01<00:01, 18595.67 examples/s]
Filter:  53%|█████▎    | 32000/60917 [00:01<00:01, 18544.67 examples/s]
Filter:  56%|█████▌    | 34000/60917 [00:01<00:01, 18451.88 examples/s]
Filter:  59%|█████▉    | 36000/60917 [00:01<00:01, 18344.08 examples/s]
Filter:  62%|██████▏   | 38000/60917 [00:02<00:01, 18308.14 examples/s]
Filter:  66%|██████▌   | 40000/60917 [00:02<00:01, 18270.69 examples/s]
Filter:  69%|██████▉   | 42000/60917 [00:02<00:01, 18097.95 examples/s]
Filter:  72%|███████▏  | 44000/60917 [00:02<00:00, 18179.28 examples/s]
Filter:  76%|███████▌  | 46000/60917 [00:02<00:00, 18242.99 examples/s]
Filter:  79%|███████▉  | 48000/60917 [00:02<00:00, 18254.71 examples/s]
Filter:  82%|████████▏ | 50000/60917 [00:02<00:00, 18287.68 examples/s]
Filter:  85%|████████▌ | 52000/60917 [00:02<00:00, 18094.80 examples/s]
Filter:  89%|████████▊ | 54000/60917 [00:02<00:00, 18005.87 examples/s]
Filter:  92%|█████████▏| 56000/60917 [00:03<00:00, 18104.98 examples/s]
Filter:  95%|█████████▌| 58000/60917 [00:03<00:00, 18042.80 examples/s]
Filter:  98%|█████████▊| 60000/60917 [00:03<00:00, 18058.50 examples/s]
Filter: 100%|██████████| 60917/60917 [00:03<00:00, 18036.29 examples/s]
2024-08-04T16:37:29.029739238Z 
Filter:   0%|          | 0/60917 [00:00<?, ? examples/s]
Filter:   3%|▎         | 2000/60917 [00:00<00:04, 13570.13 examples/s]
Filter:   7%|▋         | 4000/60917 [00:00<00:04, 13593.61 examples/s]
Filter:  10%|▉         | 6000/60917 [00:00<00:07, 7492.02 examples/s] 
Filter:  13%|█▎        | 8000/60917 [00:00<00:05, 8945.97 examples/s]
Filter:  16%|█▋        | 10000/60917 [00:01<00:04, 10198.78 examples/s]
Filter:  20%|█▉        | 12000/60917 [00:01<00:04, 11258.96 examples/s]
Filter:  23%|██▎       | 14000/60917 [00:01<00:03, 11931.38 examples/s]
Filter:  26%|██▋       | 16000/60917 [00:01<00:03, 12433.05 examples/s]
Filter:  30%|██▉       | 18000/60917 [00:01<00:03, 12812.40 examples/s]
Filter:  33%|███▎      | 20000/60917 [00:01<00:03, 13054.18 examples/s]
Filter:  36%|███▌      | 22000/60917 [00:01<00:02, 13234.13 examples/s]
Filter:  39%|███▉      | 24000/60917 [00:02<00:02, 13364.88 examples/s]
Filter:  43%|████▎     | 26000/60917 [00:02<00:02, 13456.20 examples/s]
Filter:  46%|████▌     | 28000/60917 [00:02<00:02, 13512.65 examples/s]
Filter:  49%|████▉     | 30000/60917 [00:02<00:02, 13555.92 examples/s]
Filter:  53%|█████▎    | 32000/60917 [00:02<00:02, 13534.44 examples/s]
Filter:  56%|█████▌    | 34000/60917 [00:02<00:01, 13524.19 examples/s]
Filter:  59%|█████▉    | 36000/60917 [00:02<00:01, 13514.49 examples/s]
Filter:  62%|██████▏   | 38000/60917 [00:03<00:01, 13500.59 examples/s]
Filter:  66%|██████▌   | 40000/60917 [00:03<00:01, 13472.21 examples/s]
Filter:  69%|██████▉   | 42000/60917 [00:03<00:01, 13480.43 examples/s]
Filter:  72%|███████▏  | 44000/60917 [00:03<00:01, 13479.85 examples/s]
Filter:  76%|███████▌  | 46000/60917 [00:03<00:01, 13483.74 examples/s]
Filter:  79%|███████▉  | 48000/60917 [00:03<00:00, 13486.33 examples/s]
Filter:  82%|████████▏ | 50000/60917 [00:03<00:00, 13472.28 examples/s]
Filter:  85%|████████▌ | 52000/60917 [00:04<00:00, 13396.72 examples/s]
Filter:  89%|████████▊ | 54000/60917 [00:04<00:00, 13342.05 examples/s]
Filter:  92%|█████████▏| 56000/60917 [00:04<00:00, 13339.21 examples/s]
Filter:  95%|█████████▌| 58000/60917 [00:04<00:00, 13319.88 examples/s]
Filter:  98%|█████████▊| 60000/60917 [00:04<00:00, 13337.77 examples/s]
Filter: 100%|██████████| 60917/60917 [00:04<00:00, 12752.41 examples/s]
2024-08-04T16:37:29.040035292Z 08/04/2024 09:37:29 - INFO - __main__ - Sample 41905 of the training set: {'chosen_input_ids': tensor([50279,    29,    93,  ...,   187, 11202, 50279]), 'chosen_labels': tensor([ -100,  -100,  -100,  ...,   187, 11202, 50279]), 'chosen_attention_mask': tensor([1, 1, 1,  ..., 1, 1, 1]), 'rejected_input_ids': tensor([50279,    29,    93,  4537, 49651,   187,   510,   401,  6955,  2529,
2024-08-04T16:37:29.040054748Z          1840,   310,   271,  1650,   273,  6486,  1375,  3772,   682,    15,
2024-08-04T16:37:29.040057223Z          2726,   253,  1361,   273,   253, 12002,   187, 28692,  2708,    13,
2024-08-04T16:37:29.040060958Z          2794,   247,  3694,  6333,   323, 11365,   271,   401,  6955,    15,
2024-08-04T16:37:29.040062504Z           380,  8990,   273,   634,  6335,   943,   187,  1257,  4158,   323,
2024-08-04T16:37:29.040063967Z           897,   407,   643, 12259,    15,  3173,  3018,   253,  2802,  2307,
2024-08-04T16:37:29.040065420Z            14, 13524,   457,  5199,   347,   271,  1650,   275, 14741,    15,
2024-08-04T16:37:29.040068978Z          5220,  3630,  3943,  5216,   285, 28204,  5288,   187,    29,    93,
2024-08-04T16:37:29.040070557Z           515,  5567, 49651,   187,  4943,   310,   247,  2969,  7092,   273,
2024-08-04T16:37:29.040078844Z           253,   401,  6955,  5978,   285,  2634,  2307,    14, 13524,    65,
2024-08-04T16:37:29.040080354Z          5199,   275, 14741,    27,   187, 11202,  5581,   187,  2437,   401,
2024-08-04T16:37:29.040081796Z          6955,   551,   187, 50274,  9486,   370,  5478,    28,   187, 50274,
2024-08-04T16:37:29.040083288Z          9486,   370, 13017,    28,   187, 50274,  9486,   370, 21196,    28,
2024-08-04T16:37:29.040084692Z           187, 50274,  9486,   370, 40967,    28,   535, 50274,  4387,  1159,
2024-08-04T16:37:29.040088304Z          2794,  3914,   267, 24656,    13,   370,  5478,  5443,    13,   370,
2024-08-04T16:37:29.040089916Z         13017,  5443,    10,   551,   187, 50270,     5,  2520,  1168,  5478,
2024-08-04T16:37:29.040091409Z           426,   370,  5478,  5443,    28,   187, 50270,     5,  2520,  1168,
2024-08-04T16:37:29.040092829Z         13017,   426,   370, 13017,  5443,    28,   187, 50270,     5,  2520,
2024-08-04T16:37:29.040094251Z          1168, 21196,   426,  3781,  3914,  5478,  5443,  3001,  3781,  5715,
2024-08-04T16:37:29.040097928Z           370, 13017,  5443,  3001,   337,   558,   187, 50270,     5,  2520,
2024-08-04T16:37:29.040099324Z          1168,   267, 24656,   426,  1213,    64,  9148,  3914,   267, 24656,
2024-08-04T16:37:29.040100709Z           558,   187, 50270,     5,  2520,  1168, 40967,   426,  3781,  1874,
2024-08-04T16:37:29.040102459Z           535, 50270, 26966,  4816,  2520,  1168, 21196,   347,   370,  3409,
2024-08-04T16:37:29.040103900Z          3001,   370, 14764,   272,    10,   551,   187, 50266,   605,  5733,
2024-08-04T16:37:29.040107407Z           271,  5024,   323,  1016,  5502,   187, 50266, 26966,  4816,  2520,
2024-08-04T16:37:29.040108837Z          1168,   267, 24656,   347,   370, 25354,    10,   551,   187, 50262,
2024-08-04T16:37:29.040110261Z             5,  8384,  5443,   426,  9484,  1672, 11347,  3914, 25354,    13,
2024-08-04T16:37:29.040111676Z           370,  3409,    13,   370,  2520,  1168,   267, 24656,   558,   187,
2024-08-04T16:37:29.040113068Z         50262,   338,  4816,  8384,  5443, 20767,  3635,    10,   551,   187,
2024-08-04T16:37:29.040116609Z         50258,     5,  2520,  1168, 40967, 16369,  3409,  7082,     5, 25354,
2024-08-04T16:37:29.040118027Z            62,   426,   370,  8384,  5443,    28,   187, 50262,    94,   187,
2024-08-04T16:37:29.040119453Z         50266,    94,   187, 50270,    94,   187, 50274,    94,   535, 50274,
2024-08-04T16:37:29.040120850Z          4387,  1159,  1408,  3914,  5423,    10,   551,   187, 50270,     5,
2024-08-04T16:37:29.040122291Z          6259,  5443,   426,   370,  2520,  1168,  5478,    28,   187, 50270,
2024-08-04T16:37:29.040125834Z             5, 25354,   426, 29707,   535, 50270,   605, 29516,   366,   689,
2024-08-04T16:37:29.040127281Z          1016,  3280,  9484,   187, 50270,  1542,  4816,    74,   426,   470,
2024-08-04T16:37:29.040128680Z            28,   370,    74,   654, 47287,  3914,  5423,   558,   370,    74,
2024-08-04T16:37:29.040134313Z          9234,   551,   187, 50266,     5, 25354, 33750,   370,  5423, 16369,
2024-08-04T16:37:29.040135765Z            74,  2194,   187, 50266,     5,  8384,  5443,   426,   370,  2520,
2024-08-04T16:37:29.040137182Z          1168, 40967, 16369,  6259,  5443,  7082,     5, 25354,  2194,   535,
2024-08-04T16:37:29.040138584Z         50266,   605,  9423,   604,   359,   452,  4925,   247,  2457,  1375,
2024-08-04T16:37:29.040139976Z           187, 50266,   338,   313, 33915,  3914,  2520,  1168, 21196, 16369,
2024-08-04T16:37:29.040143471Z          8384,  5443,  3291,  3857,   370,  2520,  1168, 21196, 16369,  8384,
2024-08-04T16:37:29.040144899Z          5443,    62, 11013,   337,    10,   551,   187, 50262,  2309,   370,
2024-08-04T16:37:29.040146309Z          6259,  5443,    28,   187, 50266,    94,   535, 50266,     5,  6259,
2024-08-04T16:37:29.040147702Z          5443,   426,   370,  8384,  5443,    28,   187, 50270,    94,   535,
2024-08-04T16:37:29.040151138Z         50270,  2309,  3635,    28,   187, 50274,    94,   535, 50274,  9486,
2024-08-04T16:37:29.040152551Z          1159,  9484,  1672, 11347,  3914, 25354,    13,   370,  3409,    13,
2024-08-04T16:37:29.040154119Z           370,   267, 24656,    10,   551,   187, 50270,   338,  4816, 25354,
2024-08-04T16:37:29.040155565Z         11013, 45381,   551,   187, 50266,  2309,   370,  3409,    28,   187,
2024-08-04T16:37:29.040159041Z         50270,    94,   535, 50270,  2309,   310,  1178,  3914,  2520,  1168,
2024-08-04T16:37:29.040160487Z         40967, 16369,  3409,  7082,     5, 25354,  3291,  3736,   370,  2520,
2024-08-04T16:37:29.040161886Z          1168, 40967, 16369,  3409,  7082,     5, 25354,    62,  1163,  3635,
2024-08-04T16:37:29.040163273Z            28,   187, 50274,    94,   535, 50274,  9486,  1159,   823,  3996,
2024-08-04T16:37:29.040166947Z          2510,  3914, 40967,    13,   370,  3409,    13,   370, 25354,    10,
2024-08-04T16:37:29.040168469Z           551,   187, 50270,   338,  4816, 25354, 11013, 45381,   551,   187,
2024-08-04T16:37:29.040169874Z         50266,  2309,    28,   187, 50270,    94,   535, 50270,   338,  6522,
2024-08-04T16:37:29.040171283Z         33915,  3914, 40967, 16369,  3409, 27829,   551,   187, 50266,     5,
2024-08-04T16:37:29.040172702Z         40967, 16369,  3409,    62,   426,  3781,  1874,   187, 50270,    94,
2024-08-04T16:37:29.040176290Z           535, 50270,     5, 40967, 16369,  3409,  7082,     5, 25354,    62,
2024-08-04T16:37:29.040177728Z           426,   370, 25354,  1672, 11347,  3914, 25354,    13,   370,  3409,
2024-08-04T16:37:29.040179125Z            13,   370,  2520,  1168,   267, 24656,   558,   187, 50270,  2309,
2024-08-04T16:37:29.040180520Z           370, 40967, 16369,  3409,  7082,     5, 25354,  2194,   187, 50274,
2024-08-04T16:37:29.040184162Z            94,   187,    94,   187,   187,  3701,   771, 11831,  3914,  5423,
2024-08-04T16:37:29.040187664Z            10,   551,   187, 50274,     5,   267, 24656,   426,   346, 39154,
2024-08-04T16:37:29.040189088Z          1857, 43784,  3664,   535, 50274,   605, 13119,   253,   401,  6955,
2024-08-04T16:37:29.040192479Z           187, 50274,     5,  3610,   426,   747,   401,  6955,  1874,   187,
2024-08-04T16:37:29.040193980Z         50274,     5,  3610,  1168,  6953,  3914,   267, 24656,    13,   346,
2024-08-04T16:37:29.040195387Z            17,   995,   346,   740,  3287,   535, 50274,   605, 14311,   253,
2024-08-04T16:37:29.040196788Z           401,  6955,   327,   253,  3280,   187, 50274,     5,  6870,   426,
2024-08-04T16:37:29.040200345Z           370,  3610,  1168,  6321,  3914,  5423,   558,   535, 50274,   605,
2024-08-04T16:37:29.040201834Z         16140,   253,   906,   273,   253,   401,  6955,   187, 50274,  2309,
2024-08-04T16:37:29.040203244Z           370,  6870,  3736,   370,  6870,  1163,   470,    28,   187,    94,
2024-08-04T16:37:29.040204648Z           187, 11202,   187,  1898,  1060,   434,   271,  1650, 28204,  5288,
2024-08-04T16:37:29.040208352Z            27,   187,   187,  1552,   310,   271,   401,  6955,  6335,   323,
2024-08-04T16:37:29.040209781Z         11365,  6486,  1375,  3772,   682,   275, 14741,    15,   187,   187,
2024-08-04T16:37:29.040211177Z         11252,    27,   187, 11202,  5581,   187,     5,    71,  3610,   426,
2024-08-04T16:37:29.040214569Z           747,   401,  6955,  1874,   187,     5,  6870,   426,   370,    71,
2024-08-04T16:37:29.040215982Z          3610,  1168,  6321,  1587, 10768,  3287,   187, 13088,   370,  6870,
2024-08-04T16:37:29.040217382Z            28,  1380,   884,   187, 11202,   187, 16698, 43825,    27,   187,
2024-08-04T16:37:29.040218763Z         11202,  5581,   187,     5,  6870,   426,   771, 11831,  1587, 10768,
2024-08-04T16:37:29.040222155Z          3287,   187, 13088,   370,  6870,    28,  1380,   495,   187, 11202,
2024-08-04T16:37:29.040223605Z         50279]), 'rejected_labels': tensor([ -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040225075Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040226481Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040229825Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040231247Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040232635Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040234017Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040237534Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.040239155Z          -100,  -100,  -100,   187,  4943,   310,   247,  2969,  7092,   273,
2024-08-04T16:37:29.040240689Z           253,   401,  6955,  5978,   285,  2634,  2307,    14, 13524,    65,
2024-08-04T16:37:29.040245515Z          5199,   275, 14741,    27,   187, 11202,  5581,   187,  2437,   401,
2024-08-04T16:37:29.040246966Z          6955,   551,   187, 50274,  9486,   370,  5478,    28,   187, 50274,
2024-08-04T16:37:29.040249801Z          9486,   370, 13017,    28,   187, 50274,  9486,   370, 21196,    28,
2024-08-04T16:37:29.040251208Z           187, 50274,  9486,   370, 40967,    28,   535, 50274,  4387,  1159,
2024-08-04T16:37:29.040252601Z          2794,  3914,   267, 24656,    13,   370,  5478,  5443,    13,   370,
2024-08-04T16:37:29.040254000Z         13017,  5443,    10,   551,   187, 50270,     5,  2520,  1168,  5478,
2024-08-04T16:37:29.040257486Z           426,   370,  5478,  5443,    28,   187, 50270,     5,  2520,  1168,
2024-08-04T16:37:29.040258903Z         13017,   426,   370, 13017,  5443,    28,   187, 50270,     5,  2520,
2024-08-04T16:37:29.040260436Z          1168, 21196,   426,  3781,  3914,  5478,  5443,  3001,  3781,  5715,
2024-08-04T16:37:29.040261856Z           370, 13017,  5443,  3001,   337,   558,   187, 50270,     5,  2520,
2024-08-04T16:37:29.040265232Z          1168,   267, 24656,   426,  1213,    64,  9148,  3914,   267, 24656,
2024-08-04T16:37:29.040266620Z           558,   187, 50270,     5,  2520,  1168, 40967,   426,  3781,  1874,
2024-08-04T16:37:29.040268060Z           535, 50270, 26966,  4816,  2520,  1168, 21196,   347,   370,  3409,
2024-08-04T16:37:29.040270637Z          3001,   370, 14764,   272,    10,   551,   187, 50266,   605,  5733,
2024-08-04T16:37:29.040272048Z           271,  5024,   323,  1016,  5502,   187, 50266, 26966,  4816,  2520,
2024-08-04T16:37:29.040273632Z          1168,   267, 24656,   347,   370, 25354,    10,   551,   187, 50262,
2024-08-04T16:37:29.040275911Z             5,  8384,  5443,   426,  9484,  1672, 11347,  3914, 25354,    13,
2024-08-04T16:37:29.040277308Z           370,  3409,    13,   370,  2520,  1168,   267, 24656,   558,   187,
2024-08-04T16:37:29.040279646Z         50262,   338,  4816,  8384,  5443, 20767,  3635,    10,   551,   187,
2024-08-04T16:37:29.040282101Z         50258,     5,  2520,  1168, 40967, 16369,  3409,  7082,     5, 25354,
2024-08-04T16:37:29.040283512Z            62,   426,   370,  8384,  5443,    28,   187, 50262,    94,   187,
2024-08-04T16:37:29.040284897Z         50266,    94,   187, 50270,    94,   187, 50274,    94,   535, 50274,
2024-08-04T16:37:29.040287606Z          4387,  1159,  1408,  3914,  5423,    10,   551,   187, 50270,     5,
2024-08-04T16:37:29.040289206Z          6259,  5443,   426,   370,  2520,  1168,  5478,    28,   187, 50270,
2024-08-04T16:37:29.040290595Z             5, 25354,   426, 29707,   535, 50270,   605, 29516,   366,   689,
2024-08-04T16:37:29.040293073Z          1016,  3280,  9484,   187, 50270,  1542,  4816,    74,   426,   470,
2024-08-04T16:37:29.040294467Z            28,   370,    74,   654, 47287,  3914,  5423,   558,   370,    74,
2024-08-04T16:37:29.040296980Z          9234,   551,   187, 50266,     5, 25354, 33750,   370,  5423, 16369,
2024-08-04T16:37:29.040301492Z            74,  2194,   187, 50266,     5,  8384,  5443,   426,   370,  2520,
2024-08-04T16:37:29.040302899Z          1168, 40967, 16369,  6259,  5443,  7082,     5, 25354,  2194,   535,
2024-08-04T16:37:29.040305640Z         50266,   605,  9423,   604,   359,   452,  4925,   247,  2457,  1375,
2024-08-04T16:37:29.040307099Z           187, 50266,   338,   313, 33915,  3914,  2520,  1168, 21196, 16369,
2024-08-04T16:37:29.040309349Z          8384,  5443,  3291,  3857,   370,  2520,  1168, 21196, 16369,  8384,
2024-08-04T16:37:29.040310750Z          5443,    62, 11013,   337,    10,   551,   187, 50262,  2309,   370,
2024-08-04T16:37:29.040313132Z          6259,  5443,    28,   187, 50266,    94,   535, 50266,     5,  6259,
2024-08-04T16:37:29.040314659Z          5443,   426,   370,  8384,  5443,    28,   187, 50270,    94,   535,
2024-08-04T16:37:29.040317249Z         50270,  2309,  3635,    28,   187, 50274,    94,   535, 50274,  9486,
2024-08-04T16:37:29.040318663Z          1159,  9484,  1672, 11347,  3914, 25354,    13,   370,  3409,    13,
2024-08-04T16:37:29.040320079Z           370,   267, 24656,    10,   551,   187, 50270,   338,  4816, 25354,
2024-08-04T16:37:29.040323209Z         11013, 45381,   551,   187, 50266,  2309,   370,  3409,    28,   187,
2024-08-04T16:37:29.040324629Z         50270,    94,   535, 50270,  2309,   310,  1178,  3914,  2520,  1168,
2024-08-04T16:37:29.040326025Z         40967, 16369,  3409,  7082,     5, 25354,  3291,  3736,   370,  2520,
2024-08-04T16:37:29.040328878Z          1168, 40967, 16369,  3409,  7082,     5, 25354,    62,  1163,  3635,
2024-08-04T16:37:29.040330299Z            28,   187, 50274,    94,   535, 50274,  9486,  1159,   823,  3996,
2024-08-04T16:37:29.040332643Z          2510,  3914, 40967,    13,   370,  3409,    13,   370, 25354,    10,
2024-08-04T16:37:29.040334055Z           551,   187, 50270,   338,  4816, 25354, 11013, 45381,   551,   187,
2024-08-04T16:37:29.040336374Z         50266,  2309,    28,   187, 50270,    94,   535, 50270,   338,  6522,
2024-08-04T16:37:29.040337784Z         33915,  3914, 40967, 16369,  3409, 27829,   551,   187, 50266,     5,
2024-08-04T16:37:29.040340275Z         40967, 16369,  3409,    62,   426,  3781,  1874,   187, 50270,    94,
2024-08-04T16:37:29.040341660Z           535, 50270,     5, 40967, 16369,  3409,  7082,     5, 25354,    62,
2024-08-04T16:37:29.040343070Z           426,   370, 25354,  1672, 11347,  3914, 25354,    13,   370,  3409,
2024-08-04T16:37:29.040345767Z            13,   370,  2520,  1168,   267, 24656,   558,   187, 50270,  2309,
2024-08-04T16:37:29.040347176Z           370, 40967, 16369,  3409,  7082,     5, 25354,  2194,   187, 50274,
2024-08-04T16:37:29.040350192Z            94,   187,    94,   187,   187,  3701,   771, 11831,  3914,  5423,
2024-08-04T16:37:29.040351602Z            10,   551,   187, 50274,     5,   267, 24656,   426,   346, 39154,
2024-08-04T16:37:29.040355096Z          1857, 43784,  3664,   535, 50274,   605, 13119,   253,   401,  6955,
2024-08-04T16:37:29.040358584Z           187, 50274,     5,  3610,   426,   747,   401,  6955,  1874,   187,
2024-08-04T16:37:29.040359981Z         50274,     5,  3610,  1168,  6953,  3914,   267, 24656,    13,   346,
2024-08-04T16:37:29.040361366Z            17,   995,   346,   740,  3287,   535, 50274,   605, 14311,   253,
2024-08-04T16:37:29.040363789Z           401,  6955,   327,   253,  3280,   187, 50274,     5,  6870,   426,
2024-08-04T16:37:29.040365215Z           370,  3610,  1168,  6321,  3914,  5423,   558,   535, 50274,   605,
2024-08-04T16:37:29.040366756Z         16140,   253,   906,   273,   253,   401,  6955,   187, 50274,  2309,
2024-08-04T16:37:29.040369820Z           370,  6870,  3736,   370,  6870,  1163,   470,    28,   187,    94,
2024-08-04T16:37:29.040371293Z           187, 11202,   187,  1898,  1060,   434,   271,  1650, 28204,  5288,
2024-08-04T16:37:29.040372677Z            27,   187,   187,  1552,   310,   271,   401,  6955,  6335,   323,
2024-08-04T16:37:29.040375071Z         11365,  6486,  1375,  3772,   682,   275, 14741,    15,   187,   187,
2024-08-04T16:37:29.040376478Z         11252,    27,   187, 11202,  5581,   187,     5,    71,  3610,   426,
2024-08-04T16:37:29.040377875Z           747,   401,  6955,  1874,   187,     5,  6870,   426,   370,    71,
2024-08-04T16:37:29.040380902Z          3610,  1168,  6321,  1587, 10768,  3287,   187, 13088,   370,  6870,
2024-08-04T16:37:29.040382317Z            28,  1380,   884,   187, 11202,   187, 16698, 43825,    27,   187,
2024-08-04T16:37:29.040383710Z         11202,  5581,   187,     5,  6870,   426,   771, 11831,  1587, 10768,
2024-08-04T16:37:29.040385155Z          3287,   187, 13088,   370,  6870,    28,  1380,   495,   187, 11202,
2024-08-04T16:37:29.040386570Z         50279]), 'rejected_attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040390261Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040391738Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040393147Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040395542Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040396947Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040399349Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040400894Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040403697Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040405084Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040409743Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040411183Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040413351Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040414761Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040417191Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040419549Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040420985Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040423321Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040424725Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040427596Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040429016Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040430419Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040432708Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040434137Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040436915Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040438336Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040439726Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040442404Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040443807Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040446690Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040448124Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040449533Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040451984Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040454204Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.040455674Z         1, 1, 1, 1, 1])}.
2024-08-04T16:37:29.044421905Z 08/04/2024 09:37:29 - INFO - __main__ - Sample 7296 of the training set: {'chosen_input_ids': tensor([50279,    29,    93,  4537, 49651,   187,  1276,   310,   253, 26572,
2024-08-04T16:37:29.044434358Z         29317,  2127,   281,  4908,   285, 26799,   253,  3918,   434,  3908,
2024-08-04T16:37:29.044436427Z           432,   247,  3668,  3929,   670,   253, 10800, 29005,   275,   253,
2024-08-04T16:37:29.044443501Z         10515,  5791,   970, 26502,    89,   941,  5981,    32,   187,  4943,
2024-08-04T16:37:29.044445054Z           434,   271,  1650, 26572, 29317,  2127,   326,   476,  1361,   342,
2024-08-04T16:37:29.044446443Z           436,  4836,    27,   187,     6, 16676,   253,  3668,  3929,   347,
2024-08-04T16:37:29.044447873Z           247,  2876,   187, 13608,    64, 14600,   426,  1873,  1088,  2073,
2024-08-04T16:37:29.044449248Z         13608,    64, 14600,    15, 10134,  5137,   187,     6, 46685,   253,
2024-08-04T16:37:29.044450713Z          3918,   434,  3908,   970,  3963, 12091,   187, 10192,    64, 25322,
2024-08-04T16:37:29.044452059Z           426, 21165,    81,     9, 13608,    64, 14600,    13,   686, 20349,
2024-08-04T16:37:29.044453496Z          8048,    84,  5355,  5929,    32,  1572,    79,  1383,   686, 45499,
2024-08-04T16:37:29.044454886Z          5137,   187, 10192,    64, 25322,   426,   838,    64, 25322,    92,
2024-08-04T16:37:29.044456439Z            18,  1217,    18,  4718,   187,     6,  7069,  4175,   907,   253,
2024-08-04T16:37:29.044457789Z          3908,   970,   253, 10318, 34337,  5933,   187,  8774,   426,  2505,
2024-08-04T16:37:29.044459147Z         14714,     9, 10192,    64, 25322,   558,   187,     6, 18312,   253,
2024-08-04T16:37:29.044460506Z          6010,   275, 26502,    89,  5981,   187,    71, 13108,  2073,  3353,
2024-08-04T16:37:29.044461844Z         11765,    92, 20349,  4479,    84,  3908,  6010,    27,    94,  2462,
2024-08-04T16:37:29.044463215Z            84,    61,    79,  1383,  6010,   558,   187, 13325,  2119,   281,
2024-08-04T16:37:29.044464561Z          8171,   686, 13608,    64, 14600,    15, 10134,     8,   342,   253,
2024-08-04T16:37:29.044465927Z          4588,  1873,  1416,   285,  1854,   273,   253,  3668,  3929,   368,
2024-08-04T16:37:29.044467286Z           971,   281,  4908,   253,  3918,   434,  3908,   432,    15,   187,
2024-08-04T16:37:29.044468619Z            29,    93,   515,  5567, 49651,   187, 17833,    13,  1060,   434,
2024-08-04T16:37:29.044469979Z           271,  1650, 26572, 29317,  2127,   326,   476,  1361,   342,   634,
2024-08-04T16:37:29.044471544Z          4836,    27,   187,   187, 11202,  2056, 13068,   187,     6, 16676,
2024-08-04T16:37:29.044472918Z           253,  3668,  3929,   347,   247,  2876,   187, 13608,    64, 14600,
2024-08-04T16:37:29.044474705Z           426,  1873,  1088,  2073, 13608,    64, 14600,    15, 10134,  5137,
2024-08-04T16:37:29.044476125Z           187,   187,     6, 46685,   253,  3918,   434,  3908,   970,  3963,
2024-08-04T16:37:29.044477606Z         12091,   187, 10192,    64, 25322,   426, 21165,    81,     9, 13608,
2024-08-04T16:37:29.044478952Z            64, 14600,    13,   686, 20349,  8048,    84,  5355,  5929,    32,
2024-08-04T16:37:29.044480300Z          1572,    79,  1383,   686, 45499,  5137,   187, 10192,    64, 25322,
2024-08-04T16:37:29.044483453Z           426,   838,    64, 25322,    92,    18,  1217,    18,  4718,   187,
2024-08-04T16:37:29.044484868Z           187,     6,  7069,  4175,   907,   253,  3908,   970,   253, 10318,
2024-08-04T16:37:29.044486203Z         34337,  5933,   187,  8774,   426,  2505, 14714,     9, 10192,    64,
2024-08-04T16:37:29.044487582Z         25322,   558,   187,   187,     6, 18312,   253,  6010,   275, 26502,
2024-08-04T16:37:29.044489935Z            89,  5981,   187,    71, 13108,  2073,  3353, 11765,    92, 20349,
2024-08-04T16:37:29.044491442Z          4479,    84,  3908,  6010,    27,    94,  2462,    84,    61,    79,
2024-08-04T16:37:29.044492795Z          1383,  6010,   558,   187, 11202,   187,   187, 13325,  2119,   281,
2024-08-04T16:37:29.044494137Z          8171,   686, 13608,    64, 14600,    15, 10134,     8,   342,   253,
2024-08-04T16:37:29.044496498Z          4588,  1873,  1416,   285,  1854,   273,   253,  3668,  3929,   368,
2024-08-04T16:37:29.044497736Z           971,   281,  4908,   253,  3918,   434,  3908,   432,    15, 50279]), 'chosen_labels': tensor([ -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044499064Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044500243Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044501564Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044502749Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044503921Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044505135Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044506339Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044507520Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044508764Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044509969Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044511301Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044512502Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044513696Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044514883Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044516057Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044517256Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044518431Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044521587Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044522777Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044523955Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044525124Z          -100,  -100,  -100,  -100,  -100,   187, 17833,    13,  1060,   434,
2024-08-04T16:37:29.044526315Z           271,  1650, 26572, 29317,  2127,   326,   476,  1361,   342,   634,
2024-08-04T16:37:29.044527531Z          4836,    27,   187,   187, 11202,  2056, 13068,   187,     6, 16676,
2024-08-04T16:37:29.044528701Z           253,  3668,  3929,   347,   247,  2876,   187, 13608,    64, 14600,
2024-08-04T16:37:29.044529878Z           426,  1873,  1088,  2073, 13608,    64, 14600,    15, 10134,  5137,
2024-08-04T16:37:29.044531047Z           187,   187,     6, 46685,   253,  3918,   434,  3908,   970,  3963,
2024-08-04T16:37:29.044532222Z         12091,   187, 10192,    64, 25322,   426, 21165,    81,     9, 13608,
2024-08-04T16:37:29.044533403Z            64, 14600,    13,   686, 20349,  8048,    84,  5355,  5929,    32,
2024-08-04T16:37:29.044534599Z          1572,    79,  1383,   686, 45499,  5137,   187, 10192,    64, 25322,
2024-08-04T16:37:29.044535766Z           426,   838,    64, 25322,    92,    18,  1217,    18,  4718,   187,
2024-08-04T16:37:29.044536942Z           187,     6,  7069,  4175,   907,   253,  3908,   970,   253, 10318,
2024-08-04T16:37:29.044538114Z         34337,  5933,   187,  8774,   426,  2505, 14714,     9, 10192,    64,
2024-08-04T16:37:29.044539282Z         25322,   558,   187,   187,     6, 18312,   253,  6010,   275, 26502,
2024-08-04T16:37:29.044540472Z            89,  5981,   187,    71, 13108,  2073,  3353, 11765,    92, 20349,
2024-08-04T16:37:29.044541650Z          4479,    84,  3908,  6010,    27,    94,  2462,    84,    61,    79,
2024-08-04T16:37:29.044542842Z          1383,  6010,   558,   187, 11202,   187,   187, 13325,  2119,   281,
2024-08-04T16:37:29.044544173Z          8171,   686, 13608,    64, 14600,    15, 10134,     8,   342,   253,
2024-08-04T16:37:29.044545591Z          4588,  1873,  1416,   285,  1854,   273,   253,  3668,  3929,   368,
2024-08-04T16:37:29.044546791Z           971,   281,  4908,   253,  3918,   434,  3908,   432,    15, 50279]), 'chosen_attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044548139Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044549331Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044550515Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044551695Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044553013Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044555730Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044556942Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044558128Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044559311Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044560494Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044561681Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044562850Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044564069Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044565242Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044566408Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044567615Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]), 'rejected_input_ids': tensor([50279,    29,    93,  4537, 49651,   187,  1276,   310,   253, 26572,
2024-08-04T16:37:29.044568949Z         29317,  2127,   281,  4908,   285, 26799,   253,  3918,   434,  3908,
2024-08-04T16:37:29.044570128Z           432,   247,  3668,  3929,   670,   253, 10800, 29005,   275,   253,
2024-08-04T16:37:29.044571384Z         10515,  5791,   970, 26502,    89,   941,  5981,    32,   187,  4943,
2024-08-04T16:37:29.044572568Z           434,   271,  1650, 26572, 29317,  2127,   326,   476,  1361,   342,
2024-08-04T16:37:29.044573888Z           436,  4836,    27,   187,     6, 16676,   253,  3668,  3929,   347,
2024-08-04T16:37:29.044575085Z           247,  2876,   187, 13608,    64, 14600,   426,  1873,  1088,  2073,
2024-08-04T16:37:29.044576287Z         13608,    64, 14600,    15, 10134,  5137,   187,     6, 46685,   253,
2024-08-04T16:37:29.044577474Z          3918,   434,  3908,   970,  3963, 12091,   187, 10192,    64, 25322,
2024-08-04T16:37:29.044578647Z           426, 21165,    81,     9, 13608,    64, 14600,    13,   686, 20349,
2024-08-04T16:37:29.044579816Z          8048,    84,  5355,  5929,    32,  1572,    79,  1383,   686, 45499,
2024-08-04T16:37:29.044580981Z          5137,   187, 10192,    64, 25322,   426,   838,    64, 25322,    92,
2024-08-04T16:37:29.044582168Z            18,  1217,    18,  4718,   187,     6,  7069,  4175,   907,   253,
2024-08-04T16:37:29.044583359Z          3908,   970,   253, 10318, 34337,  5933,   187,  8774,   426,  2505,
2024-08-04T16:37:29.044584528Z         14714,     9, 10192,    64, 25322,   558,   187,     6, 18312,   253,
2024-08-04T16:37:29.044585702Z          6010,   275, 26502,    89,  5981,   187,    71, 13108,  2073,  3353,
2024-08-04T16:37:29.044586875Z         11765,    92, 20349,  4479,    84,  3908,  6010,    27,    94,  2462,
2024-08-04T16:37:29.044589474Z            84,    61,    79,  1383,  6010,   558,   187, 13325,  2119,   281,
2024-08-04T16:37:29.044590675Z          8171,   686, 13608,    64, 14600,    15, 10134,     8,   342,   253,
2024-08-04T16:37:29.044591854Z          4588,  1873,  1416,   285,  1854,   273,   253,  3668,  3929,   368,
2024-08-04T16:37:29.044593031Z           971,   281,  4908,   253,  3918,   434,  3908,   432,    15,   187,
2024-08-04T16:37:29.044594221Z            29,    93,   515,  5567, 49651,   187,   510,  2127,   368,  2530,
2024-08-04T16:37:29.044595405Z           943,  1361,  4908,   285, 26799,   253,  3918,   434,  3908,   432,
2024-08-04T16:37:29.044596578Z           247,  3668,  3929,   670, 10800, 29005,   275,   253, 10515,  5791,
2024-08-04T16:37:29.044597775Z           970, 26572, 29317,   285, 26502,    89,   941,  5981,    15,   733,
2024-08-04T16:37:29.044598955Z          4648,   253,  1873,  1088,  1082,  1159,   281,  3301,   253,  3668,
2024-08-04T16:37:29.044600117Z          3929,   347,   247,  2876,    13,   253, 21165,    81,  1082,  1159,
2024-08-04T16:37:29.044601298Z           281,  4908,   253,  3918,   434,  3908,   970,   247,  3963,  2048,
2024-08-04T16:37:29.044602464Z            13,   253,  2505, 14714,  1082,  1159,   281, 26799,   253,  3908,
2024-08-04T16:37:29.044603684Z           970,   253, 10318, 34337,  5933,    13,   285,   253, 43164,  1082,
2024-08-04T16:37:29.044604855Z          1159,   281,  3379,   253,  6010,   275, 26502,    89,  5981,    15,
2024-08-04T16:37:29.044606031Z          1916,   897,   436,  2127,    13,  8171,   686, 13608,    64, 14600,
2024-08-04T16:37:29.044607293Z            15, 10134,     8,   342,   253,  4588,  1873,  1416,   285,  1854,
2024-08-04T16:37:29.044608494Z           273,   253,  3668,  3929,   368,   971,   281,  4908,   253,  3918,
2024-08-04T16:37:29.044609677Z           434,  3908,   432,    15, 50279]), 'rejected_labels': tensor([ -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044610958Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044612129Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044613305Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044614499Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044615676Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044616851Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044618018Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044619202Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044620370Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044623094Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044624340Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044625528Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044626714Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044627879Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044629053Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044630246Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044631422Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044632591Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044633795Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044635019Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.044636224Z          -100,  -100,  -100,  -100,  -100,   187,   510,  2127,   368,  2530,
2024-08-04T16:37:29.044637411Z           943,  1361,  4908,   285, 26799,   253,  3918,   434,  3908,   432,
2024-08-04T16:37:29.044638657Z           247,  3668,  3929,   670, 10800, 29005,   275,   253, 10515,  5791,
2024-08-04T16:37:29.044639860Z           970, 26572, 29317,   285, 26502,    89,   941,  5981,    15,   733,
2024-08-04T16:37:29.044641065Z          4648,   253,  1873,  1088,  1082,  1159,   281,  3301,   253,  3668,
2024-08-04T16:37:29.044642242Z          3929,   347,   247,  2876,    13,   253, 21165,    81,  1082,  1159,
2024-08-04T16:37:29.044643446Z           281,  4908,   253,  3918,   434,  3908,   970,   247,  3963,  2048,
2024-08-04T16:37:29.044644639Z            13,   253,  2505, 14714,  1082,  1159,   281, 26799,   253,  3908,
2024-08-04T16:37:29.044645823Z           970,   253, 10318, 34337,  5933,    13,   285,   253, 43164,  1082,
2024-08-04T16:37:29.044647014Z          1159,   281,  3379,   253,  6010,   275, 26502,    89,  5981,    15,
2024-08-04T16:37:29.044648204Z          1916,   897,   436,  2127,    13,  8171,   686, 13608,    64, 14600,
2024-08-04T16:37:29.044649378Z            15, 10134,     8,   342,   253,  4588,  1873,  1416,   285,  1854,
2024-08-04T16:37:29.044650571Z           273,   253,  3668,  3929,   368,   971,   281,  4908,   253,  3918,
2024-08-04T16:37:29.044651759Z           434,  3908,   432,    15, 50279]), 'rejected_attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044653079Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044654266Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044655460Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044658223Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044659423Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044660619Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044661801Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044662987Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044664191Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044665368Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044666555Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044667745Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044668940Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.044670330Z         1, 1, 1, 1, 1, 1, 1, 1, 1])}.
2024-08-04T16:37:29.048334914Z 08/04/2024 09:37:29 - INFO - __main__ - Sample 1639 of the training set: {'chosen_input_ids': tensor([50279,    29,    93,  4537, 49651,   187,  4947,  1419,   253,  6197,
2024-08-04T16:37:29.048343831Z          1754,   327,  2600,    13,  3192,   715,  2395,   253,  1563,  3081,
2024-08-04T16:37:29.048345501Z         10806,    27,   209,   187,    18,    15,   380,  6197,   310,  3542,
2024-08-04T16:37:29.048347033Z           275,  9883,    15,   209,   187,    19,    15,   380,  6197,   310,
2024-08-04T16:37:29.048348367Z           629,   273,   247,  8249,  3929,   670, 27606,  2341,    15,   209,
2024-08-04T16:37:29.048349688Z           187,    20,    15,   380,  6197,   310, 29920,   407,   247,  2829,
2024-08-04T16:37:29.048351125Z          4645,   253, 16589,  3116,   273,  4076,  2341,   275,  2710,  4343,
2024-08-04T16:37:29.048352447Z           689,   253,  1735,  9976,    15,   209,   187,    21,    15,   380,
2024-08-04T16:37:29.048353756Z          6197,   310,  3560,   407,   247,  2127, 36408,  4645,   253,  7092,
2024-08-04T16:37:29.048355147Z           273,   247,  5145,  4715,  5933,   323, 21565,   253, 16253,   273,
2024-08-04T16:37:29.048356584Z          4076,  2341,   275,  1027,  4811,    15,   209,   187,    22,    15,
2024-08-04T16:37:29.048357897Z           380,  6197,   310,   247, 14430,   432,   247, 30101,  6485,   275,
2024-08-04T16:37:29.048359239Z           253,  1673,   273, 18380,  2440,    15,   209,   187, 15545,   327,
2024-08-04T16:37:29.048360553Z           841, 10806,    13,   310,   253,  6197,   247,   958,    13,   271,
2024-08-04T16:37:29.048361987Z          4743,    13,   390,   247,  2087,  3908,    32,   187,    29,    93,
2024-08-04T16:37:29.048363310Z           515,  5567, 49651,   187, 15545,   327,   253,  2530, 10806,    13,
2024-08-04T16:37:29.048368530Z           253,  6197,   310,   247,   958,    15,  2490,   187,   510,  6197,
2024-08-04T16:37:29.048369896Z           310,  2668,   432,   247,  8249,  3929,   670, 27606,  2341,    13,
2024-08-04T16:37:29.048371222Z           285,   253,  1491,  3559,   310,  4516,   407,   941,   432,   253,
2024-08-04T16:37:29.048372527Z          2829,   387,   253,  5068,   273,   253,  3929,    15,   380, 14430,
2024-08-04T16:37:29.048373830Z           432,   247, 30101,  6485,   275,   253,  1673,   273, 18380,  2440,
2024-08-04T16:37:29.048375152Z         11323, 17938,   281,   253,  1491,  3559,   285,  2007,  8525,   326,
2024-08-04T16:37:29.048376551Z           253,  6197,   310,   247,   958,    15,   187,   187, 28144,    13,
2024-08-04T16:37:29.048377860Z           253,  6197,  4620,   281,   320,  5277,  1491,   670,   253, 16253,
2024-08-04T16:37:29.048379224Z           273,  4076,  2341,   275,  1027,  4811,    13,   534,   310,   247,
2024-08-04T16:37:29.048380881Z          2336, 18397,   958,   326,   476,   320,  4516,   407,   941,   285,
2024-08-04T16:37:29.048382221Z          2561,    15,  3813,    13,   352,   476,   320, 10509,   347,   247,
2024-08-04T16:37:29.048383554Z           958,    15, 50279]), 'chosen_labels': tensor([ -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048384962Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048386304Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048387624Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048389116Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048390561Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048391957Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048393272Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048394658Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048395971Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048397296Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048398599Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048399896Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048401207Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048402537Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048403867Z          -100,  -100,  -100,   187, 15545,   327,   253,  2530, 10806,    13,
2024-08-04T16:37:29.048407008Z           253,  6197,   310,   247,   958,    15,  2490,   187,   510,  6197,
2024-08-04T16:37:29.048408340Z           310,  2668,   432,   247,  8249,  3929,   670, 27606,  2341,    13,
2024-08-04T16:37:29.048409671Z           285,   253,  1491,  3559,   310,  4516,   407,   941,   432,   253,
2024-08-04T16:37:29.048410988Z          2829,   387,   253,  5068,   273,   253,  3929,    15,   380, 14430,
2024-08-04T16:37:29.048412295Z           432,   247, 30101,  6485,   275,   253,  1673,   273, 18380,  2440,
2024-08-04T16:37:29.048413610Z         11323, 17938,   281,   253,  1491,  3559,   285,  2007,  8525,   326,
2024-08-04T16:37:29.048414954Z           253,  6197,   310,   247,   958,    15,   187,   187, 28144,    13,
2024-08-04T16:37:29.048416389Z           253,  6197,  4620,   281,   320,  5277,  1491,   670,   253, 16253,
2024-08-04T16:37:29.048417721Z           273,  4076,  2341,   275,  1027,  4811,    13,   534,   310,   247,
2024-08-04T16:37:29.048419048Z          2336, 18397,   958,   326,   476,   320,  4516,   407,   941,   285,
2024-08-04T16:37:29.048420350Z          2561,    15,  3813,    13,   352,   476,   320, 10509,   347,   247,
2024-08-04T16:37:29.048421719Z           958,    15, 50279]), 'chosen_attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048423138Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048424461Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048425801Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048427139Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048428458Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048429760Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048431081Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048432381Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048433697Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048435023Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048436377Z         1, 1, 1, 1, 1, 1, 1, 1, 1]), 'rejected_input_ids': tensor([50279,    29,    93,  4537, 49651,   187,  4947,  1419,   253,  6197,
2024-08-04T16:37:29.048437788Z          1754,   327,  2600,    13,  3192,   715,  2395,   253,  1563,  3081,
2024-08-04T16:37:29.048439115Z         10806,    27,   209,   187,    18,    15,   380,  6197,   310,  3542,
2024-08-04T16:37:29.048440436Z           275,  9883,    15,   209,   187,    19,    15,   380,  6197,   310,
2024-08-04T16:37:29.048441772Z           629,   273,   247,  8249,  3929,   670, 27606,  2341,    15,   209,
2024-08-04T16:37:29.048444753Z           187,    20,    15,   380,  6197,   310, 29920,   407,   247,  2829,
2024-08-04T16:37:29.048446075Z          4645,   253, 16589,  3116,   273,  4076,  2341,   275,  2710,  4343,
2024-08-04T16:37:29.048447371Z           689,   253,  1735,  9976,    15,   209,   187,    21,    15,   380,
2024-08-04T16:37:29.048448712Z          6197,   310,  3560,   407,   247,  2127, 36408,  4645,   253,  7092,
2024-08-04T16:37:29.048450054Z           273,   247,  5145,  4715,  5933,   323, 21565,   253, 16253,   273,
2024-08-04T16:37:29.048451539Z          4076,  2341,   275,  1027,  4811,    15,   209,   187,    22,    15,
2024-08-04T16:37:29.048452868Z           380,  6197,   310,   247, 14430,   432,   247, 30101,  6485,   275,
2024-08-04T16:37:29.048454170Z           253,  1673,   273, 18380,  2440,    15,   209,   187, 15545,   327,
2024-08-04T16:37:29.048455512Z           841, 10806,    13,   310,   253,  6197,   247,   958,    13,   271,
2024-08-04T16:37:29.048456802Z          4743,    13,   390,   247,  2087,  3908,    32,   187,    29,    93,
2024-08-04T16:37:29.048458106Z           515,  5567, 49651,   187, 15545,   327,   253,  1677, 10806,    13,
2024-08-04T16:37:29.048459446Z           253,  6197,   310,   954,  2779,   247,   958,    15,   187,   187,
2024-08-04T16:37:29.048460742Z           510,  6197,   310,  3542,   275,  9883,    13,   534,  5936,   326,
2024-08-04T16:37:29.048462041Z           352,   310,  6034,   323,   247,  9883,    14, 30777,  8446,    13,
2024-08-04T16:37:29.048463337Z           285,   352,   310,   629,   273,   247,  8249,  3929,   670, 27606,
2024-08-04T16:37:29.048464809Z          2341,    15,   831,  8018,   326,   253,  6197,   310,  2779,   281,
2024-08-04T16:37:29.048466104Z           320,   247,  3908,   273,   958,  2581,   685,   271,  4743,   390,
2024-08-04T16:37:29.048467427Z           247,  2087,  3908,    15,   187,   187, 20964,    13,   253,  6197,
2024-08-04T16:37:29.048468732Z           310, 29920,   407,   247,  2829,  4645,   253, 16589,  3116,   273,
2024-08-04T16:37:29.048470189Z          4076,  2341,   275,  2710,  4343,   689,   253,  1735,  9976,    13,
2024-08-04T16:37:29.048471489Z           534,  5936,   326,   352,   310,  5277, 15010,  1491,   670, 27606,
2024-08-04T16:37:29.048472792Z          2341,    15,  9157,    13,   253,  6197,   310,  3560,   407,   247,
2024-08-04T16:37:29.048474099Z          2127, 36408,  4645,   253,  7092,   273,   247,  5145,  4715,  5933,
2024-08-04T16:37:29.048475415Z           323, 21565,   253, 16253,   273,  4076,  2341,   275,  1027,  4811,
2024-08-04T16:37:29.048476718Z            13,   534,  2007,  8525,   253,  2934,   326,   253,  6197,   310,
2024-08-04T16:37:29.048478032Z         15250, 15010,  1491,    15,   187,   187, 10971,    13,   253,  6197,
2024-08-04T16:37:29.048479340Z           310,   247, 14430,   432,   247, 30101,  6485,   275,   253,  1673,
2024-08-04T16:37:29.048480695Z           273, 18380,  2440,    13,   534, 11323, 17938,   281,   253,  3908,
2024-08-04T16:37:29.048483695Z           285,  5936,   326,   352,   310,  1754,   327,  9630,   941,   285,
2024-08-04T16:37:29.048485068Z          2561,    15,  3813,    13,  1754,   327,   253,  1677, 10806,    13,
2024-08-04T16:37:29.048487234Z           352,   310,  2779,   326,   253,  6197,   310,   247,   958,    15,
2024-08-04T16:37:29.048488664Z         50279]), 'rejected_labels': tensor([ -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048490039Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048491347Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048492640Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048494155Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048495451Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048496747Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048498080Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048499400Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048500769Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048502247Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048503559Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048504880Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048506203Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048507502Z          -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,  -100,
2024-08-04T16:37:29.048508810Z          -100,  -100,  -100,   187, 15545,   327,   253,  1677, 10806,    13,
2024-08-04T16:37:29.048510323Z           253,  6197,   310,   954,  2779,   247,   958,    15,   187,   187,
2024-08-04T16:37:29.048511652Z           510,  6197,   310,  3542,   275,  9883,    13,   534,  5936,   326,
2024-08-04T16:37:29.048512952Z           352,   310,  6034,   323,   247,  9883,    14, 30777,  8446,    13,
2024-08-04T16:37:29.048514252Z           285,   352,   310,   629,   273,   247,  8249,  3929,   670, 27606,
2024-08-04T16:37:29.048515578Z          2341,    15,   831,  8018,   326,   253,  6197,   310,  2779,   281,
2024-08-04T16:37:29.048516872Z           320,   247,  3908,   273,   958,  2581,   685,   271,  4743,   390,
2024-08-04T16:37:29.048518199Z           247,  2087,  3908,    15,   187,   187, 20964,    13,   253,  6197,
2024-08-04T16:37:29.048519505Z           310, 29920,   407,   247,  2829,  4645,   253, 16589,  3116,   273,
2024-08-04T16:37:29.048522352Z          4076,  2341,   275,  2710,  4343,   689,   253,  1735,  9976,    13,
2024-08-04T16:37:29.048523689Z           534,  5936,   326,   352,   310,  5277, 15010,  1491,   670, 27606,
2024-08-04T16:37:29.048525184Z          2341,    15,  9157,    13,   253,  6197,   310,  3560,   407,   247,
2024-08-04T16:37:29.048526514Z          2127, 36408,  4645,   253,  7092,   273,   247,  5145,  4715,  5933,
2024-08-04T16:37:29.048527846Z           323, 21565,   253, 16253,   273,  4076,  2341,   275,  1027,  4811,
2024-08-04T16:37:29.048529166Z            13,   534,  2007,  8525,   253,  2934,   326,   253,  6197,   310,
2024-08-04T16:37:29.048530472Z         15250, 15010,  1491,    15,   187,   187, 10971,    13,   253,  6197,
2024-08-04T16:37:29.048531811Z           310,   247, 14430,   432,   247, 30101,  6485,   275,   253,  1673,
2024-08-04T16:37:29.048533127Z           273, 18380,  2440,    13,   534, 11323, 17938,   281,   253,  3908,
2024-08-04T16:37:29.048534451Z           285,  5936,   326,   352,   310,  1754,   327,  9630,   941,   285,
2024-08-04T16:37:29.048535761Z          2561,    15,  3813,    13,  1754,   327,   253,  1677, 10806,    13,
2024-08-04T16:37:29.048537069Z           352,   310,  2779,   326,   253,  6197,   310,   247,   958,    15,
2024-08-04T16:37:29.048538430Z         50279]), 'rejected_attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048540036Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048541350Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048542707Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048544025Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048545343Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048546646Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048547963Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048549448Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048550764Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048552088Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048553390Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048554716Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048556029Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048557382Z         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2024-08-04T16:37:29.048560425Z         1])}.
2024-08-04T16:37:29.089116606Z [2024-08-04 09:37:29,088] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed info: version=0.14.4, git-hash=unknown, git-branch=unknown
2024-08-04T16:37:29.165680225Z [2024-08-04 09:37:29,165] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
2024-08-04T16:37:29.174339699Z [2024-08-04 09:37:29,174] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer
2024-08-04T16:37:29.174365423Z [2024-08-04 09:37:29,174] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer
2024-08-04T16:37:30.351631625Z [2024-08-04 09:37:30,351] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = AdamW
2024-08-04T16:37:30.351655192Z [2024-08-04 09:37:30,351] [INFO] [utils.py:56:is_zero_supported_optimizer] Checking ZeRO support for optimizer=AdamW type=<class 'torch.optim.adamw.AdamW'>
2024-08-04T16:37:30.351657912Z [2024-08-04 09:37:30,351] [INFO] [logging.py:96:log_dist] [Rank 0] Creating fp16 ZeRO stage 3 optimizer, MiCS is enabled False, Hierarchical params gather False
2024-08-04T16:37:30.351659581Z [2024-08-04 09:37:30,351] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.bfloat16 ZeRO stage 3 optimizer
2024-08-04T16:37:30.556652559Z [2024-08-04 09:37:30,556] [INFO] [utils.py:781:see_memory_usage] Stage 3 initialize beginning
2024-08-04T16:37:30.557002591Z [2024-08-04 09:37:30,556] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 1.38 GB         CA 1.75 GB         Max_CA 2 GB 
2024-08-04T16:37:30.557176695Z [2024-08-04 09:37:30,557] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.67 GB, percent = 2.0%
2024-08-04T16:37:30.569410403Z [2024-08-04 09:37:30,569] [INFO] [stage3.py:130:__init__] Reduce bucket size 4194304
2024-08-04T16:37:30.569422155Z [2024-08-04 09:37:30,569] [INFO] [stage3.py:131:__init__] Prefetch bucket size 3774873
2024-08-04T16:37:30.734028444Z [2024-08-04 09:37:30,733] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [begin]
2024-08-04T16:37:30.734299069Z [2024-08-04 09:37:30,734] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 0.81 GB         CA 1.75 GB         Max_CA 2 GB 
2024-08-04T16:37:30.734451466Z [2024-08-04 09:37:30,734] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.75 GB, percent = 2.0%
2024-08-04T16:37:30.833912580Z Parameter Offload: Total persistent parameters: 133120 in 65 params
2024-08-04T16:37:31.099670160Z [2024-08-04 09:37:31,099] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [end]
2024-08-04T16:37:31.099950654Z [2024-08-04 09:37:31,099] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 0.81 GB         CA 1.75 GB         Max_CA 2 GB 
2024-08-04T16:37:31.100123422Z [2024-08-04 09:37:31,100] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.77 GB, percent = 2.0%
2024-08-04T16:37:31.301709154Z [2024-08-04 09:37:31,301] [INFO] [utils.py:781:see_memory_usage] Before creating fp16 partitions
2024-08-04T16:37:31.301975663Z [2024-08-04 09:37:31,301] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 0.81 GB         CA 1.75 GB         Max_CA 2 GB 
2024-08-04T16:37:31.302150056Z [2024-08-04 09:37:31,302] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.77 GB, percent = 2.0%
2024-08-04T16:38:05.459045024Z [2024-08-04 09:38:05,458] [INFO] [utils.py:781:see_memory_usage] After creating fp16 partitions: 1
2024-08-04T16:38:05.459486401Z [2024-08-04 09:38:05,459] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 0.81 GB         CA 1.19 GB         Max_CA 2 GB 
2024-08-04T16:38:05.459649064Z [2024-08-04 09:38:05,459] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.81 GB, percent = 2.0%
2024-08-04T16:38:05.659467859Z [2024-08-04 09:38:05,659] [INFO] [utils.py:781:see_memory_usage] Before creating fp32 partitions
2024-08-04T16:38:05.659742053Z [2024-08-04 09:38:05,659] [INFO] [utils.py:782:see_memory_usage] MA 0.81 GB         Max_MA 0.81 GB         CA 1.19 GB         Max_CA 1 GB 
2024-08-04T16:38:05.659907663Z [2024-08-04 09:38:05,659] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.81 GB, percent = 2.0%
2024-08-04T16:38:05.843261417Z [2024-08-04 09:38:05,842] [INFO] [utils.py:781:see_memory_usage] After creating fp32 partitions
2024-08-04T16:38:05.843534513Z [2024-08-04 09:38:05,843] [INFO] [utils.py:782:see_memory_usage] MA 1.61 GB         Max_MA 2.01 GB         CA 2.4 GB         Max_CA 2 GB 
2024-08-04T16:38:05.843693551Z [2024-08-04 09:38:05,843] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.81 GB, percent = 2.0%
2024-08-04T16:38:06.026224344Z [2024-08-04 09:38:06,025] [INFO] [utils.py:781:see_memory_usage] Before initializing optimizer states
2024-08-04T16:38:06.026580642Z [2024-08-04 09:38:06,026] [INFO] [utils.py:782:see_memory_usage] MA 1.61 GB         Max_MA 1.61 GB         CA 2.4 GB         Max_CA 2 GB 
2024-08-04T16:38:06.026745554Z [2024-08-04 09:38:06,026] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.81 GB, percent = 2.0%
2024-08-04T16:38:06.209282695Z [2024-08-04 09:38:06,208] [INFO] [utils.py:781:see_memory_usage] After initializing optimizer states
2024-08-04T16:38:06.209556096Z [2024-08-04 09:38:06,209] [INFO] [utils.py:782:see_memory_usage] MA 1.61 GB         Max_MA 2.42 GB         CA 3.2 GB         Max_CA 3 GB 
2024-08-04T16:38:06.209713339Z [2024-08-04 09:38:06,209] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.81 GB, percent = 2.0%
2024-08-04T16:38:06.210242087Z [2024-08-04 09:38:06,210] [INFO] [stage3.py:486:_setup_for_real_optimizer] optimizer state initialized
2024-08-04T16:38:08.051332098Z [2024-08-04 09:38:08,050] [INFO] [utils.py:781:see_memory_usage] After initializing ZeRO optimizer
2024-08-04T16:38:08.051704335Z [2024-08-04 09:38:08,051] [INFO] [utils.py:782:see_memory_usage] MA 2.02 GB         Max_MA 2.41 GB         CA 3.2 GB         Max_CA 3 GB 
2024-08-04T16:38:08.051866791Z [2024-08-04 09:38:08,051] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.86 GB, percent = 2.0%
2024-08-04T16:38:08.051963515Z [2024-08-04 09:38:08,051] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Final Optimizer = DeepSpeedZeroOptimizer_Stage3
2024-08-04T16:38:08.052067669Z [2024-08-04 09:38:08,052] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed using client LR scheduler
2024-08-04T16:38:08.052116068Z [2024-08-04 09:38:08,052] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed LR Scheduler = None
2024-08-04T16:38:08.052144230Z [2024-08-04 09:38:08,052] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0], mom=[(0.9, 0.999)]
2024-08-04T16:38:08.060068388Z [2024-08-04 09:38:08,059] [INFO] [config.py:997:print] DeepSpeedEngine configuration:
2024-08-04T16:38:08.060592977Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   activation_checkpointing_config  {
2024-08-04T16:38:08.060595561Z     "partition_activations": false, 
2024-08-04T16:38:08.060596873Z     "contiguous_memory_optimization": false, 
2024-08-04T16:38:08.060598409Z     "cpu_checkpointing": false, 
2024-08-04T16:38:08.060599718Z     "number_checkpoints": null, 
2024-08-04T16:38:08.060601147Z     "synchronize_checkpoint_boundary": false, 
2024-08-04T16:38:08.060602425Z     "profile": false
2024-08-04T16:38:08.060603805Z }
2024-08-04T16:38:08.060641878Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
2024-08-04T16:38:08.060645916Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   amp_enabled .................. False
2024-08-04T16:38:08.060649373Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   amp_params ................... False
2024-08-04T16:38:08.060838544Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   autotuning_config ............ {
2024-08-04T16:38:08.060866716Z     "enabled": false, 
2024-08-04T16:38:08.060868940Z     "start_step": null, 
2024-08-04T16:38:08.060870666Z     "end_step": null, 
2024-08-04T16:38:08.060872542Z     "metric_path": null, 
2024-08-04T16:38:08.060874471Z     "arg_mappings": null, 
2024-08-04T16:38:08.060875863Z     "metric": "throughput", 
2024-08-04T16:38:08.060877548Z     "model_info": null, 
2024-08-04T16:38:08.060879248Z     "results_dir": "autotuning_results", 
2024-08-04T16:38:08.060881064Z     "exps_dir": "autotuning_exps", 
2024-08-04T16:38:08.060882345Z     "overwrite": true, 
2024-08-04T16:38:08.060883643Z     "fast": true, 
2024-08-04T16:38:08.060884817Z     "start_profile_step": 3, 
2024-08-04T16:38:08.060886103Z     "end_profile_step": 5, 
2024-08-04T16:38:08.060887317Z     "tuner_type": "gridsearch", 
2024-08-04T16:38:08.060888690Z     "tuner_early_stopping": 5, 
2024-08-04T16:38:08.060889891Z     "tuner_num_trials": 50, 
2024-08-04T16:38:08.060891197Z     "model_info_path": null, 
2024-08-04T16:38:08.060892377Z     "mp_size": 1, 
2024-08-04T16:38:08.060911248Z     "max_train_batch_size": null, 
2024-08-04T16:38:08.060912865Z     "min_train_batch_size": 1, 
2024-08-04T16:38:08.060914217Z     "max_train_micro_batch_size_per_gpu": 1.024000e+03, 
2024-08-04T16:38:08.060915503Z     "min_train_micro_batch_size_per_gpu": 1, 
2024-08-04T16:38:08.060917681Z     "num_tuning_micro_batch_sizes": 3
2024-08-04T16:38:08.060919147Z }
2024-08-04T16:38:08.060920435Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   bfloat16_enabled ............. True
2024-08-04T16:38:08.060927567Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   bfloat16_immediate_grad_update  False
2024-08-04T16:38:08.060929045Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   checkpoint_parallel_write_pipeline  False
2024-08-04T16:38:08.060930271Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   checkpoint_tag_validation_enabled  True
2024-08-04T16:38:08.060931663Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   checkpoint_tag_validation_fail  False
2024-08-04T16:38:08.060932881Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f2f2c0818d0>
2024-08-04T16:38:08.060936470Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   communication_data_type ...... None
2024-08-04T16:38:08.060982804Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}}
2024-08-04T16:38:08.060991281Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   curriculum_enabled_legacy .... False
2024-08-04T16:38:08.061010885Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   curriculum_params_legacy ..... False
2024-08-04T16:38:08.061024893Z [2024-08-04 09:38:08,060] [INFO] [config.py:1001:print]   data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}}
2024-08-04T16:38:08.061042492Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   data_efficiency_enabled ...... False
2024-08-04T16:38:08.061046845Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   dataloader_drop_last ......... False
2024-08-04T16:38:08.061070941Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   disable_allgather ............ False
2024-08-04T16:38:08.061074684Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   dump_state ................... False
2024-08-04T16:38:08.061095449Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   dynamic_loss_scale_args ...... None
2024-08-04T16:38:08.061101298Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_enabled ........... False
2024-08-04T16:38:08.061119176Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_gas_boundary_resolution  1
2024-08-04T16:38:08.061137226Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_layer_name ........ bert.encoder.layer
2024-08-04T16:38:08.061155251Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_layer_num ......... 0
2024-08-04T16:38:08.061159230Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_max_iter .......... 100
2024-08-04T16:38:08.061180900Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_stability ......... 1e-06
2024-08-04T16:38:08.061192836Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_tol ............... 0.01
2024-08-04T16:38:08.061216286Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   eigenvalue_verbose ........... False
2024-08-04T16:38:08.061221245Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   elasticity_enabled ........... False
2024-08-04T16:38:08.061273047Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   flops_profiler_config ........ {
2024-08-04T16:38:08.061275606Z     "enabled": false, 
2024-08-04T16:38:08.061276928Z     "recompute_fwd_factor": 0.0, 
2024-08-04T16:38:08.061278161Z     "profile_step": 1, 
2024-08-04T16:38:08.061279511Z     "module_depth": -1, 
2024-08-04T16:38:08.061280694Z     "top_modules": 1, 
2024-08-04T16:38:08.061282037Z     "detailed": true, 
2024-08-04T16:38:08.061283269Z     "output_file": null
2024-08-04T16:38:08.061284486Z }
2024-08-04T16:38:08.061286818Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   fp16_auto_cast ............... None
2024-08-04T16:38:08.061293030Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   fp16_enabled ................. False
2024-08-04T16:38:08.061322702Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   fp16_master_weights_and_gradients  False
2024-08-04T16:38:08.061329411Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   global_rank .................. 0
2024-08-04T16:38:08.061352720Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   grad_accum_dtype ............. None
2024-08-04T16:38:08.061357606Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   gradient_accumulation_steps .. 1
2024-08-04T16:38:08.061372196Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   gradient_clipping ............ 1.0
2024-08-04T16:38:08.061386990Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   gradient_predivide_factor .... 1.0
2024-08-04T16:38:08.061414377Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   graph_harvesting ............. False
2024-08-04T16:38:08.061457219Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8
2024-08-04T16:38:08.061463208Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   initial_dynamic_scale ........ 1
2024-08-04T16:38:08.061472808Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   load_universal_checkpoint .... False
2024-08-04T16:38:08.061480908Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   loss_scale ................... 1.0
2024-08-04T16:38:08.061498220Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   memory_breakdown ............. False
2024-08-04T16:38:08.061513309Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   mics_hierarchial_params_gather  False
2024-08-04T16:38:08.061530943Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   mics_shard_size .............. -1
2024-08-04T16:38:08.061604443Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') comet=CometConfig(enabled=False, samples_log_interval=100, project=None, workspace=None, api_key=None, experiment_name=None, experiment_key=None, online=None, mode=None) wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False
2024-08-04T16:38:08.061647551Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   nebula_config ................ {
2024-08-04T16:38:08.061652683Z     "enabled": false, 
2024-08-04T16:38:08.061654823Z     "persistent_storage_path": null, 
2024-08-04T16:38:08.061656077Z     "persistent_time_interval": 100, 
2024-08-04T16:38:08.061657336Z     "num_of_version_in_retention": 2, 
2024-08-04T16:38:08.061658513Z     "enable_nebula_load": true, 
2024-08-04T16:38:08.061659682Z     "load_path": null
2024-08-04T16:38:08.061660891Z }
2024-08-04T16:38:08.061661998Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   optimizer_legacy_fusion ...... False
2024-08-04T16:38:08.061682494Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   optimizer_name ............... None
2024-08-04T16:38:08.061687331Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   optimizer_params ............. None
2024-08-04T16:38:08.061713514Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True}
2024-08-04T16:38:08.061719417Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   pld_enabled .................. False
2024-08-04T16:38:08.061738408Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   pld_params ................... False
2024-08-04T16:38:08.061751415Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   prescale_gradients ........... False
2024-08-04T16:38:08.061760856Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   scheduler_name ............... None
2024-08-04T16:38:08.061785248Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   scheduler_params ............. None
2024-08-04T16:38:08.061804832Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   seq_parallel_communication_data_type  torch.float32
2024-08-04T16:38:08.061807922Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   sparse_attention ............. None
2024-08-04T16:38:08.061829006Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   sparse_gradients_enabled ..... False
2024-08-04T16:38:08.061837740Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   steps_per_print .............. inf
2024-08-04T16:38:08.061862933Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   timers_config ................ enabled=True synchronized=True
2024-08-04T16:38:08.061888026Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   train_batch_size ............. 32
2024-08-04T16:38:08.061893954Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   train_micro_batch_size_per_gpu  1
2024-08-04T16:38:08.061907199Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   use_data_before_expert_parallel_  False
2024-08-04T16:38:08.061922050Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   use_node_local_storage ....... False
2024-08-04T16:38:08.061939345Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   wall_clock_breakdown ......... False
2024-08-04T16:38:08.061957599Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   weight_quantization_config ... None
2024-08-04T16:38:08.061959082Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   world_size ................... 32
2024-08-04T16:38:08.061982493Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   zero_allow_untested_optimizer  True
2024-08-04T16:38:08.062037338Z [2024-08-04 09:38:08,061] [INFO] [config.py:1001:print]   zero_config .................. stage=3 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=4194304 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=3774873 param_persistence_threshold=20480 model_persistence_threshold=sys.maxsize max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=True use_all_reduce_for_fetch_params=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True
2024-08-04T16:38:08.062042631Z [2024-08-04 09:38:08,062] [INFO] [config.py:1001:print]   zero_enabled ................. True
2024-08-04T16:38:08.062053244Z [2024-08-04 09:38:08,062] [INFO] [config.py:1001:print]   zero_force_ds_cpu_optimizer .. True
2024-08-04T16:38:08.062072771Z [2024-08-04 09:38:08,062] [INFO] [config.py:1001:print]   zero_optimization_stage ...... 3
2024-08-04T16:38:08.062169705Z [2024-08-04 09:38:08,062] [INFO] [config.py:987:print_user_config]   json = {
2024-08-04T16:38:08.062182606Z     "bf16": {
2024-08-04T16:38:08.062184690Z         "enabled": true
2024-08-04T16:38:08.062186323Z     }, 
2024-08-04T16:38:08.062187570Z     "zero_optimization": {
2024-08-04T16:38:08.062189333Z         "stage": 3, 
2024-08-04T16:38:08.062190729Z         "overlap_comm": true, 
2024-08-04T16:38:08.062197834Z         "contiguous_gradients": true, 
2024-08-04T16:38:08.062199347Z         "sub_group_size": 1.000000e+09, 
2024-08-04T16:38:08.062200896Z         "reduce_bucket_size": 4.194304e+06, 
2024-08-04T16:38:08.062202338Z         "stage3_prefetch_bucket_size": 3.774873e+06, 
2024-08-04T16:38:08.062203966Z         "stage3_param_persistence_threshold": 2.048000e+04, 
2024-08-04T16:38:08.062205334Z         "stage3_max_live_parameters": 1.000000e+09, 
2024-08-04T16:38:08.062206818Z         "stage3_max_reuse_distance": 1.000000e+09, 
2024-08-04T16:38:08.062207998Z         "stage3_gather_16bit_weights_on_model_save": true
2024-08-04T16:38:08.062209394Z     }, 
2024-08-04T16:38:08.062210489Z     "gradient_accumulation_steps": 1, 
2024-08-04T16:38:08.062211839Z     "gradient_clipping": 1.0, 
2024-08-04T16:38:08.062213047Z     "steps_per_print": inf, 
2024-08-04T16:38:08.062214359Z     "train_batch_size": 32, 
2024-08-04T16:38:08.062215538Z     "train_micro_batch_size_per_gpu": 1, 
2024-08-04T16:38:08.062216884Z     "wall_clock_breakdown": false, 
2024-08-04T16:38:08.062218095Z     "fp16": {
2024-08-04T16:38:08.062219326Z         "enabled": false
2024-08-04T16:38:08.062220530Z     }, 
2024-08-04T16:38:08.062221816Z     "zero_allow_untested_optimizer": true
2024-08-04T16:38:08.062223054Z }
2024-08-04T16:38:08.062379550Z [2024-08-04 09:38:08,062] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed info: version=0.14.4, git-hash=unknown, git-branch=unknown
2024-08-04T16:38:08.140123557Z [2024-08-04 09:38:08,139] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
2024-08-04T16:38:08.157304554Z [2024-08-04 09:38:08,157] [INFO] [logging.py:96:log_dist] [Rank 0] Creating ZeRO Offload
2024-08-04T16:38:08.365556812Z [2024-08-04 09:38:08,365] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [begin]
2024-08-04T16:38:08.365985098Z [2024-08-04 09:38:08,365] [INFO] [utils.py:782:see_memory_usage] MA 2.02 GB         Max_MA 2.02 GB         CA 3.2 GB         Max_CA 3 GB 
2024-08-04T16:38:08.366167227Z [2024-08-04 09:38:08,366] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.93 GB, percent = 2.0%
2024-08-04T16:38:08.466515224Z Parameter Offload: Total persistent parameters: 133120 in 65 params
2024-08-04T16:38:08.770561192Z [2024-08-04 09:38:08,770] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [end]
2024-08-04T16:38:08.770902694Z [2024-08-04 09:38:08,770] [INFO] [utils.py:782:see_memory_usage] MA 2.02 GB         Max_MA 2.02 GB         CA 3.2 GB         Max_CA 3 GB 
2024-08-04T16:38:08.771065433Z [2024-08-04 09:38:08,771] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 40.94 GB, percent = 2.0%
2024-08-04T16:38:08.778728448Z [2024-08-04 09:38:08,778] [INFO] [config.py:997:print] DeepSpeedEngine configuration:
2024-08-04T16:38:08.778832486Z [2024-08-04 09:38:08,778] [INFO] [config.py:1001:print]   activation_checkpointing_config  {
2024-08-04T16:38:08.778834955Z     "partition_activations": false, 
2024-08-04T16:38:08.778836515Z     "contiguous_memory_optimization": false, 
2024-08-04T16:38:08.778838152Z     "cpu_checkpointing": false, 
2024-08-04T16:38:08.778839680Z     "number_checkpoints": null, 
2024-08-04T16:38:08.778841290Z     "synchronize_checkpoint_boundary": false, 
2024-08-04T16:38:08.778842683Z     "profile": false
2024-08-04T16:38:08.778844173Z }
2024-08-04T16:38:08.778877559Z [2024-08-04 09:38:08,778] [INFO] [config.py:1001:print]   aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
2024-08-04T16:38:08.778904915Z [2024-08-04 09:38:08,778] [INFO] [config.py:1001:print]   amp_enabled .................. False
2024-08-04T16:38:08.778907139Z [2024-08-04 09:38:08,778] [INFO] [config.py:1001:print]   amp_params ................... False
2024-08-04T16:38:08.779090975Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   autotuning_config ............ {
2024-08-04T16:38:08.779099058Z     "enabled": false, 
2024-08-04T16:38:08.779100410Z     "start_step": null, 
2024-08-04T16:38:08.779102170Z     "end_step": null, 
2024-08-04T16:38:08.779103483Z     "metric_path": null, 
2024-08-04T16:38:08.779104884Z     "arg_mappings": null, 
2024-08-04T16:38:08.779106197Z     "metric": "throughput", 
2024-08-04T16:38:08.779107572Z     "model_info": null, 
2024-08-04T16:38:08.779108786Z     "results_dir": "autotuning_results", 
2024-08-04T16:38:08.779110226Z     "exps_dir": "autotuning_exps", 
2024-08-04T16:38:08.779111890Z     "overwrite": true, 
2024-08-04T16:38:08.779113229Z     "fast": true, 
2024-08-04T16:38:08.779114416Z     "start_profile_step": 3, 
2024-08-04T16:38:08.779115818Z     "end_profile_step": 5, 
2024-08-04T16:38:08.779117051Z     "tuner_type": "gridsearch", 
2024-08-04T16:38:08.779126469Z     "tuner_early_stopping": 5, 
2024-08-04T16:38:08.779127832Z     "tuner_num_trials": 50, 
2024-08-04T16:38:08.779129213Z     "model_info_path": null, 
2024-08-04T16:38:08.779130398Z     "mp_size": 1, 
2024-08-04T16:38:08.779131697Z     "max_train_batch_size": null, 
2024-08-04T16:38:08.779132886Z     "min_train_batch_size": 1, 
2024-08-04T16:38:08.779134168Z     "max_train_micro_batch_size_per_gpu": 1.024000e+03, 
2024-08-04T16:38:08.779135464Z     "min_train_micro_batch_size_per_gpu": 1, 
2024-08-04T16:38:08.779136780Z     "num_tuning_micro_batch_sizes": 3
2024-08-04T16:38:08.779138163Z }
2024-08-04T16:38:08.779139448Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   bfloat16_enabled ............. True
2024-08-04T16:38:08.779143510Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   bfloat16_immediate_grad_update  False
2024-08-04T16:38:08.779145166Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   checkpoint_parallel_write_pipeline  False
2024-08-04T16:38:08.779146405Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   checkpoint_tag_validation_enabled  True
2024-08-04T16:38:08.779148914Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   checkpoint_tag_validation_fail  False
2024-08-04T16:38:08.779175569Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f2f2c080f10>
2024-08-04T16:38:08.779181753Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   communication_data_type ...... None
2024-08-04T16:38:08.779240565Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}}
2024-08-04T16:38:08.779245607Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   curriculum_enabled_legacy .... False
2024-08-04T16:38:08.779248034Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   curriculum_params_legacy ..... False
2024-08-04T16:38:08.779273408Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}}
2024-08-04T16:38:08.779291065Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   data_efficiency_enabled ...... False
2024-08-04T16:38:08.779303150Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   dataloader_drop_last ......... False
2024-08-04T16:38:08.779311226Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   disable_allgather ............ False
2024-08-04T16:38:08.779346769Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   dump_state ................... False
2024-08-04T16:38:08.779350181Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   dynamic_loss_scale_args ...... None
2024-08-04T16:38:08.779359650Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_enabled ........... False
2024-08-04T16:38:08.779371348Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_gas_boundary_resolution  1
2024-08-04T16:38:08.779396156Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_layer_name ........ bert.encoder.layer
2024-08-04T16:38:08.779402072Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_layer_num ......... 0
2024-08-04T16:38:08.779418407Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_max_iter .......... 100
2024-08-04T16:38:08.779436886Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_stability ......... 1e-06
2024-08-04T16:38:08.779452607Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_tol ............... 0.01
2024-08-04T16:38:08.779457688Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   eigenvalue_verbose ........... False
2024-08-04T16:38:08.779484087Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   elasticity_enabled ........... False
2024-08-04T16:38:08.779515169Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   flops_profiler_config ........ {
2024-08-04T16:38:08.779516837Z     "enabled": false, 
2024-08-04T16:38:08.779518212Z     "recompute_fwd_factor": 0.0, 
2024-08-04T16:38:08.779519516Z     "profile_step": 1, 
2024-08-04T16:38:08.779520882Z     "module_depth": -1, 
2024-08-04T16:38:08.779522315Z     "top_modules": 1, 
2024-08-04T16:38:08.779523482Z     "detailed": true, 
2024-08-04T16:38:08.779525633Z     "output_file": null
2024-08-04T16:38:08.779526842Z }
2024-08-04T16:38:08.779533281Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   fp16_auto_cast ............... None
2024-08-04T16:38:08.779559541Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   fp16_enabled ................. False
2024-08-04T16:38:08.779565336Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   fp16_master_weights_and_gradients  False
2024-08-04T16:38:08.779579829Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   global_rank .................. 0
2024-08-04T16:38:08.779603600Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   grad_accum_dtype ............. None
2024-08-04T16:38:08.779608986Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   gradient_accumulation_steps .. 1
2024-08-04T16:38:08.779626058Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   gradient_clipping ............ 1.0
2024-08-04T16:38:08.779644000Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   gradient_predivide_factor .... 1.0
2024-08-04T16:38:08.779649880Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   graph_harvesting ............. False
2024-08-04T16:38:08.779694201Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8
2024-08-04T16:38:08.779708857Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   initial_dynamic_scale ........ 1
2024-08-04T16:38:08.779714942Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   load_universal_checkpoint .... False
2024-08-04T16:38:08.779731423Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   loss_scale ................... 1.0
2024-08-04T16:38:08.779751095Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   memory_breakdown ............. False
2024-08-04T16:38:08.779757297Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   mics_hierarchial_params_gather  False
2024-08-04T16:38:08.779774495Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   mics_shard_size .............. -1
2024-08-04T16:38:08.779835633Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') comet=CometConfig(enabled=False, samples_log_interval=100, project=None, workspace=None, api_key=None, experiment_name=None, experiment_key=None, online=None, mode=None) wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False
2024-08-04T16:38:08.779883123Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   nebula_config ................ {
2024-08-04T16:38:08.779886688Z     "enabled": false, 
2024-08-04T16:38:08.779888502Z     "persistent_storage_path": null, 
2024-08-04T16:38:08.779890214Z     "persistent_time_interval": 100, 
2024-08-04T16:38:08.779892034Z     "num_of_version_in_retention": 2, 
2024-08-04T16:38:08.779893537Z     "enable_nebula_load": true, 
2024-08-04T16:38:08.779894948Z     "load_path": null
2024-08-04T16:38:08.779896170Z }
2024-08-04T16:38:08.779897563Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   optimizer_legacy_fusion ...... False
2024-08-04T16:38:08.779910262Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   optimizer_name ............... None
2024-08-04T16:38:08.779922134Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   optimizer_params ............. None
2024-08-04T16:38:08.779946789Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True}
2024-08-04T16:38:08.779956696Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   pld_enabled .................. False
2024-08-04T16:38:08.779975613Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   pld_params ................... False
2024-08-04T16:38:08.779981711Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   prescale_gradients ........... False
2024-08-04T16:38:08.780007238Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   scheduler_name ............... None
2024-08-04T16:38:08.780013492Z [2024-08-04 09:38:08,779] [INFO] [config.py:1001:print]   scheduler_params ............. None
2024-08-04T16:38:08.780041071Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   seq_parallel_communication_data_type  torch.float32
2024-08-04T16:38:08.780046454Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   sparse_attention ............. None
2024-08-04T16:38:08.780071584Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   sparse_gradients_enabled ..... False
2024-08-04T16:38:08.780077441Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   steps_per_print .............. inf
2024-08-04T16:38:08.780103206Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   timers_config ................ enabled=True synchronized=True
2024-08-04T16:38:08.780113900Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   train_batch_size ............. 32
2024-08-04T16:38:08.780120930Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   train_micro_batch_size_per_gpu  1
2024-08-04T16:38:08.780152925Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   use_data_before_expert_parallel_  False
2024-08-04T16:38:08.780158874Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   use_node_local_storage ....... False
2024-08-04T16:38:08.780173696Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   wall_clock_breakdown ......... False
2024-08-04T16:38:08.780183284Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   weight_quantization_config ... None
2024-08-04T16:38:08.780207200Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   world_size ................... 32
2024-08-04T16:38:08.780213749Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   zero_allow_untested_optimizer  True
2024-08-04T16:38:08.780296057Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   zero_config .................. stage=3 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=4194304 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=3774873 param_persistence_threshold=20480 model_persistence_threshold=sys.maxsize max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=True use_all_reduce_for_fetch_params=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True
2024-08-04T16:38:08.780308286Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   zero_enabled ................. True
2024-08-04T16:38:08.780311052Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   zero_force_ds_cpu_optimizer .. True
2024-08-04T16:38:08.780331292Z [2024-08-04 09:38:08,780] [INFO] [config.py:1001:print]   zero_optimization_stage ...... 3
2024-08-04T16:38:08.780424392Z [2024-08-04 09:38:08,780] [INFO] [config.py:987:print_user_config]   json = {
2024-08-04T16:38:08.780436173Z     "bf16": {
2024-08-04T16:38:08.780437871Z         "enabled": true
2024-08-04T16:38:08.780439144Z     }, 
2024-08-04T16:38:08.780440419Z     "zero_optimization": {
2024-08-04T16:38:08.780441648Z         "stage": 3, 
2024-08-04T16:38:08.780443029Z         "overlap_comm": true, 
2024-08-04T16:38:08.780444258Z         "contiguous_gradients": true, 
2024-08-04T16:38:08.780445675Z         "sub_group_size": 1.000000e+09, 
2024-08-04T16:38:08.780446898Z         "reduce_bucket_size": 4.194304e+06, 
2024-08-04T16:38:08.780448304Z         "stage3_prefetch_bucket_size": 3.774873e+06, 
2024-08-04T16:38:08.780449485Z         "stage3_param_persistence_threshold": 2.048000e+04, 
2024-08-04T16:38:08.780450907Z         "stage3_max_live_parameters": 1.000000e+09, 
2024-08-04T16:38:08.780452074Z         "stage3_max_reuse_distance": 1.000000e+09, 
2024-08-04T16:38:08.780453470Z         "stage3_gather_16bit_weights_on_model_save": true
2024-08-04T16:38:08.780454740Z     }, 
2024-08-04T16:38:08.780456029Z     "gradient_accumulation_steps": 1, 
2024-08-04T16:38:08.780457201Z     "gradient_clipping": 1.0, 
2024-08-04T16:38:08.780458534Z     "steps_per_print": inf, 
2024-08-04T16:38:08.780459713Z     "train_batch_size": 32, 
2024-08-04T16:38:08.780460862Z     "train_micro_batch_size_per_gpu": 1, 
2024-08-04T16:38:08.780462113Z     "wall_clock_breakdown": false, 
2024-08-04T16:38:08.780463300Z     "fp16": {
2024-08-04T16:38:08.780464522Z         "enabled": false
2024-08-04T16:38:08.780465718Z     }, 
2024-08-04T16:38:08.780466804Z     "zero_allow_untested_optimizer": true, 
2024-08-04T16:38:08.780467999Z     "zero_optimization.reduce_bucket_size": 4.194304e+06, 
2024-08-04T16:38:08.780469245Z     "zero_optimization.stage3_param_persistence_threshold": 2.048000e+04, 
2024-08-04T16:38:08.780470506Z     "zero_optimization.stage3_prefetch_bucket_size": 3.774874e+06
2024-08-04T16:38:08.780471766Z }
2024-08-04T16:38:08.851749283Z 08/04/2024 09:38:08 - INFO - __main__ - ***** Running training *****
2024-08-04T16:38:08.851771303Z 08/04/2024 09:38:08 - INFO - __main__ -   Num examples = 60917
2024-08-04T16:38:08.851773665Z 08/04/2024 09:38:08 - INFO - __main__ -   Num Epochs = 3
2024-08-04T16:38:08.851775214Z 08/04/2024 09:38:08 - INFO - __main__ -   Instantaneous batch size per device = 1
2024-08-04T16:38:08.851776643Z 08/04/2024 09:38:08 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 32
2024-08-04T16:38:08.851778098Z 08/04/2024 09:38:08 - INFO - __main__ -   Gradient Accumulation steps = 1
2024-08-04T16:38:08.851779464Z 08/04/2024 09:38:08 - INFO - __main__ -   Total optimization steps = 5712
2024-08-04T16:38:08.873576615Z 
  0%|          | 0/5712 [00:00<?, ?it/s]/opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873588394Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873590613Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873592506Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873593799Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873595532Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873596933Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873598628Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873599933Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873608404Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873789939Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873798730Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873962696Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873964535Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:08.873965798Z /opt/miniconda3/lib/python3.10/site-packages/transformers/data/data_collator.py:656: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)
2024-08-04T16:38:08.873967500Z   batch["labels"] = torch.tensor(batch["labels"], dtype=torch.int64)
2024-08-04T16:38:09.135246591Z We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
2024-08-04T16:38:19.276072202Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276117218Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276119872Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Using network IB
2024-08-04T16:38:19.276122222Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Using network IB
2024-08-04T16:38:19.276124210Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276126185Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Using network IB
2024-08-04T16:38:19.276127893Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276129445Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276131180Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276132751Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Using network IB
2024-08-04T16:38:19.276134460Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Using network IB
2024-08-04T16:38:19.276135980Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Using network IB
2024-08-04T16:38:19.276137688Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276139208Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Using non-device net plugin version 0
2024-08-04T16:38:19.276141040Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Using network IB
2024-08-04T16:38:19.276142559Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Using network IB
2024-08-04T16:38:19.278479191Z jupiter-cs-aus-134:102:628 [7] NCCL INFO bootstrapSplit: comm 0x7f40e407fc60 parent 0xb01b030 rank 7 nranks 32 color 698429859 key 7 prev 6 next 8 - DONE
2024-08-04T16:38:19.278495132Z jupiter-cs-aus-134:102:628 [7] NCCL INFO comm 0x7f40e407fc60 rank 7 nranks 32 cudaDev 7 nvmlDev 7 busId e4000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278497664Z jupiter-cs-aus-134:101:626 [6] NCCL INFO bootstrapSplit: comm 0x7f0b7c07f950 parent 0xa1944d0 rank 6 nranks 32 color 698429859 key 6 prev 5 next 7 - DONE
2024-08-04T16:38:19.278499543Z jupiter-cs-aus-134:101:626 [6] NCCL INFO comm 0x7f0b7c07f950 rank 6 nranks 32 cudaDev 6 nvmlDev 6 busId 91000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278501206Z jupiter-cs-aus-134:100:630 [5] NCCL INFO bootstrapSplit: comm 0x7f6d0c07fa10 parent 0x9e65470 rank 5 nranks 32 color 698429859 key 5 prev 4 next 6 - DONE
2024-08-04T16:38:19.278503039Z jupiter-cs-aus-134:100:630 [5] NCCL INFO comm 0x7f6d0c07fa10 rank 5 nranks 32 cudaDev 5 nvmlDev 5 busId 8b000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278537328Z jupiter-cs-aus-134:98:629 [3] NCCL INFO bootstrapSplit: comm 0x7fa72007fa00 parent 0xa0f91b0 rank 3 nranks 32 color 698429859 key 3 prev 2 next 4 - DONE
2024-08-04T16:38:19.278566074Z jupiter-cs-aus-134:99:624 [4] NCCL INFO bootstrapSplit: comm 0x7fcab007fe00 parent 0xab6a750 rank 4 nranks 32 color 698429859 key 4 prev 3 next 5 - DONE
2024-08-04T16:38:19.278568543Z jupiter-cs-aus-134:97:625 [2] NCCL INFO bootstrapSplit: comm 0x7f3fd80929a0 parent 0xa822120 rank 2 nranks 32 color 698429859 key 2 prev 1 next 3 - DONE
2024-08-04T16:38:19.278570742Z jupiter-cs-aus-134:96:627 [1] NCCL INFO bootstrapSplit: comm 0x7f2284091160 parent 0xb484410 rank 1 nranks 32 color 698429859 key 1 prev 0 next 2 - DONE
2024-08-04T16:38:19.278572513Z jupiter-cs-aus-134:95:623 [0] NCCL INFO bootstrapSplit: comm 0x7f2e600806a0 parent 0xb8be120 rank 0 nranks 32 color 698429859 key 0 prev 31 next 1 - DONE
2024-08-04T16:38:19.278574001Z jupiter-cs-aus-134:98:629 [3] NCCL INFO comm 0x7fa72007fa00 rank 3 nranks 32 cudaDev 3 nvmlDev 3 busId 5d000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278575616Z jupiter-cs-aus-134:99:624 [4] NCCL INFO comm 0x7fcab007fe00 rank 4 nranks 32 cudaDev 4 nvmlDev 4 busId 84000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278577075Z jupiter-cs-aus-134:97:625 [2] NCCL INFO comm 0x7f3fd80929a0 rank 2 nranks 32 cudaDev 2 nvmlDev 2 busId 3a000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278578674Z jupiter-cs-aus-134:96:627 [1] NCCL INFO comm 0x7f2284091160 rank 1 nranks 32 cudaDev 1 nvmlDev 1 busId 2a000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:19.278580139Z jupiter-cs-aus-134:95:623 [0] NCCL INFO comm 0x7f2e600806a0 rank 0 nranks 32 cudaDev 0 nvmlDev 0 busId 18000 commId 0x39a520acc33b2a02 - Init START
2024-08-04T16:38:22.892873954Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Setting affinity for GPU 4 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:38:22.892899577Z jupiter-cs-aus-134:99:624 [4] NCCL INFO NVLS multicast support is not available on dev 4
2024-08-04T16:38:22.926864988Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Setting affinity for GPU 5 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:38:22.926875807Z jupiter-cs-aus-134:100:630 [5] NCCL INFO NVLS multicast support is not available on dev 5
2024-08-04T16:38:22.970843842Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Setting affinity for GPU 7 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:38:22.970865667Z jupiter-cs-aus-134:102:628 [7] NCCL INFO NVLS multicast support is not available on dev 7
2024-08-04T16:38:22.989254254Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Setting affinity for GPU 6 to ffffffff,fffe0000,00000000,ffffffff,fffe0000,00000000
2024-08-04T16:38:22.989265247Z jupiter-cs-aus-134:101:626 [6] NCCL INFO NVLS multicast support is not available on dev 6
2024-08-04T16:38:23.048360732Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Setting affinity for GPU 3 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:38:23.048371778Z jupiter-cs-aus-134:98:629 [3] NCCL INFO NVLS multicast support is not available on dev 3
2024-08-04T16:38:23.061128368Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Setting affinity for GPU 2 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:38:23.061139403Z jupiter-cs-aus-134:97:625 [2] NCCL INFO NVLS multicast support is not available on dev 2
2024-08-04T16:38:23.066823183Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Setting affinity for GPU 1 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:38:23.066876349Z jupiter-cs-aus-134:96:627 [1] NCCL INFO NVLS multicast support is not available on dev 1
2024-08-04T16:38:23.072449436Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Setting affinity for GPU 0 to ffff,fffffffd,00000000,0000ffff,fffffffd
2024-08-04T16:38:23.072451923Z jupiter-cs-aus-134:95:623 [0] NCCL INFO NVLS multicast support is not available on dev 0
2024-08-04T16:38:23.111635939Z jupiter-cs-aus-134:95:623 [0] NCCL INFO comm 0x7f2e600806a0 rank 0 nRanks 32 nNodes 4 localRanks 8 localRank 0 MNNVL 0
2024-08-04T16:38:23.111647401Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/16 :    0   7   6   5   4   3   2   1   9  10  11  12  13  14  15   8  16  23  22  21
2024-08-04T16:38:23.111649503Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 01/16 :    0   8  15  14  13  12  11  10   9  17  18  19  20  21  22  23  16  24  31  30
2024-08-04T16:38:23.111651188Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 02/16 :    0   7   6   5   4   3  11  12  13  14  15   8   9  10  18  17  16  23  22  21
2024-08-04T16:38:23.111652519Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 03/16 :    0   1   2  10   9   8  15  14  13  12  11  19  20  21  22  23  16  17  18  26
2024-08-04T16:38:23.111653931Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 04/16 :    0   7   6   5  13  14  15   8   9  10  11  12  20  19  18  17  16  23  22  21
2024-08-04T16:38:23.111655258Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 05/16 :    0   1   2   3   4  12  11  10   9   8  15  14  13  21  22  23  16  17  18  19
2024-08-04T16:38:23.111656956Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 06/16 :    0   7  15   8   9  10  11  12  13  14  22  21  20  19  18  17  16  23  31  24
2024-08-04T16:38:23.111658252Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 07/16 :    0   1   2   3   4   5   6  14  13  12  11  10   9   8  15  23  16  17  18  19
2024-08-04T16:38:23.111659737Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/16 :    0   7   6   5   4   3   2   1   9  10  11  12  13  14  15   8  16  23  22  21
2024-08-04T16:38:23.111667251Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 09/16 :    0   8  15  14  13  12  11  10   9  17  18  19  20  21  22  23  16  24  31  30
2024-08-04T16:38:23.111668929Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 10/16 :    0   7   6   5   4   3  11  12  13  14  15   8   9  10  18  17  16  23  22  21
2024-08-04T16:38:23.111670233Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 11/16 :    0   1   2  10   9   8  15  14  13  12  11  19  20  21  22  23  16  17  18  26
2024-08-04T16:38:23.111671707Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 12/16 :    0   7   6   5  13  14  15   8   9  10  11  12  20  19  18  17  16  23  22  21
2024-08-04T16:38:23.111673013Z jupiter-cs-aus-134:97:625 [2] NCCL INFO comm 0x7f3fd80929a0 rank 2 nRanks 32 nNodes 4 localRanks 8 localRank 2 MNNVL 0
2024-08-04T16:38:23.111675113Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 13/16 :    0   1   2   3   4  12  11  10   9   8  15  14  13  21  22  23  16  17  18  19
2024-08-04T16:38:23.111676433Z jupiter-cs-aus-134:96:627 [1] NCCL INFO comm 0x7f2284091160 rank 1 nRanks 32 nNodes 4 localRanks 8 localRank 1 MNNVL 0
2024-08-04T16:38:23.111677845Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 14/16 :    0   7  15   8   9  10  11  12  13  14  22  21  20  19  18  17  16  23  31  24
2024-08-04T16:38:23.111679151Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 15/16 :    0   1   2   3   4   5   6  14  13  12  11  10   9   8  15  23  16  17  18  19
2024-08-04T16:38:23.111680653Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Trees [0] 1/16/-1->0->-1 [1] -1/-1/-1->0->7 [2] 1/-1/-1->0->7 [3] 1/-1/-1->0->7 [4] 1/-1/-1->0->7 [5] 1/-1/-1->0->7 [6] 1/-1/-1->0->7 [7] 1/-1/-1->0->7 [8] 1/-1/-1->0->8 [9] -1/-1/-1->0->7 [10] 1/-1/-1->0->7 [11] 1/-1/-1->0->7 [12] 1/-1/-1->0->7 [13] 1/-1/-1->0->7 [14] 1/-1/-1->0->7 [15] 1/-1/-1->0->7
2024-08-04T16:38:23.111683614Z jupiter-cs-aus-134:95:623 [0] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111685011Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Trees [0] 3/-1/-1->2->1 [1] 3/-1/-1->2->1 [2] 3/18/-1->2->-1 [3] -1/-1/-1->2->1 [4] 3/-1/-1->2->1 [5] 3/-1/-1->2->1 [6] 3/-1/-1->2->1 [7] 3/-1/-1->2->1 [8] 3/-1/-1->2->1 [9] 3/-1/-1->2->1 [10] 3/-1/-1->2->10 [11] -1/-1/-1->2->1 [12] 3/-1/-1->2->1 [13] 3/-1/-1->2->1 [14] 3/-1/-1->2->1 [15] 3/-1/-1->2->1
2024-08-04T16:38:23.111687285Z jupiter-cs-aus-134:97:625 [2] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111688805Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Trees [0] 2/-1/-1->1->0 [1] 2/17/-1->1->-1 [2] -1/-1/-1->1->0 [3] 2/-1/-1->1->0 [4] 2/-1/-1->1->0 [5] 2/-1/-1->1->0 [6] 2/-1/-1->1->0 [7] 2/-1/-1->1->0 [8] 2/-1/-1->1->0 [9] 2/-1/-1->1->9 [10] -1/-1/-1->1->0 [11] 2/-1/-1->1->0 [12] 2/-1/-1->1->0 [13] 2/-1/-1->1->0 [14] 2/-1/-1->1->0 [15] 2/-1/-1->1->0
2024-08-04T16:38:23.111690808Z jupiter-cs-aus-134:96:627 [1] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111699566Z jupiter-cs-aus-134:102:628 [7] NCCL INFO comm 0x7f40e407fc60 rank 7 nRanks 32 nNodes 4 localRanks 8 localRank 7 MNNVL 0
2024-08-04T16:38:23.111703517Z jupiter-cs-aus-134:98:629 [3] NCCL INFO comm 0x7fa72007fa00 rank 3 nRanks 32 nNodes 4 localRanks 8 localRank 3 MNNVL 0
2024-08-04T16:38:23.111704978Z jupiter-cs-aus-134:100:630 [5] NCCL INFO comm 0x7f6d0c07fa10 rank 5 nRanks 32 nNodes 4 localRanks 8 localRank 5 MNNVL 0
2024-08-04T16:38:23.111706256Z jupiter-cs-aus-134:101:626 [6] NCCL INFO comm 0x7f0b7c07f950 rank 6 nRanks 32 nNodes 4 localRanks 8 localRank 6 MNNVL 0
2024-08-04T16:38:23.111707531Z jupiter-cs-aus-134:99:624 [4] NCCL INFO comm 0x7fcab007fe00 rank 4 nRanks 32 nNodes 4 localRanks 8 localRank 4 MNNVL 0
2024-08-04T16:38:23.111708846Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Trees [0] -1/-1/-1->7->6 [1] 0/-1/-1->7->6 [2] 0/-1/-1->7->6 [3] 0/-1/-1->7->6 [4] 0/-1/-1->7->6 [5] 0/-1/-1->7->6 [6] 0/-1/-1->7->6 [7] 0/23/-1->7->-1 [8] -1/-1/-1->7->6 [9] 0/-1/-1->7->6 [10] 0/-1/-1->7->6 [11] 0/-1/-1->7->6 [12] 0/-1/-1->7->6 [13] 0/-1/-1->7->6 [14] 0/-1/-1->7->6 [15] 0/-1/-1->7->15
2024-08-04T16:38:23.111710896Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Trees [0] 6/-1/-1->5->4 [1] 6/-1/-1->5->4 [2] 6/-1/-1->5->4 [3] 6/-1/-1->5->4 [4] 6/-1/-1->5->4 [5] 6/21/-1->5->-1 [6] -1/-1/-1->5->4 [7] 6/-1/-1->5->4 [8] 6/-1/-1->5->4 [9] 6/-1/-1->5->4 [10] 6/-1/-1->5->4 [11] 6/-1/-1->5->4 [12] 6/-1/-1->5->4 [13] 6/-1/-1->5->13 [14] -1/-1/-1->5->4 [15] 6/-1/-1->5->4
2024-08-04T16:38:23.111712928Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Trees [0] 5/-1/-1->4->3 [1] 5/-1/-1->4->3 [2] 5/-1/-1->4->3 [3] 5/-1/-1->4->3 [4] 5/20/-1->4->-1 [5] -1/-1/-1->4->3 [6] 5/-1/-1->4->3 [7] 5/-1/-1->4->3 [8] 5/-1/-1->4->3 [9] 5/-1/-1->4->3 [10] 5/-1/-1->4->3 [11] 5/-1/-1->4->3 [12] 5/-1/-1->4->12 [13] -1/-1/-1->4->3 [14] 5/-1/-1->4->3 [15] 5/-1/-1->4->3
2024-08-04T16:38:23.111714893Z jupiter-cs-aus-134:102:628 [7] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111716133Z jupiter-cs-aus-134:100:630 [5] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111717362Z jupiter-cs-aus-134:99:624 [4] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111718841Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Trees [0] 4/-1/-1->3->2 [1] 4/-1/-1->3->2 [2] 4/-1/-1->3->2 [3] 4/19/-1->3->-1 [4] -1/-1/-1->3->2 [5] 4/-1/-1->3->2 [6] 4/-1/-1->3->2 [7] 4/-1/-1->3->2 [8] 4/-1/-1->3->2 [9] 4/-1/-1->3->2 [10] 4/-1/-1->3->2 [11] 4/-1/-1->3->11 [12] -1/-1/-1->3->2 [13] 4/-1/-1->3->2 [14] 4/-1/-1->3->2 [15] 4/-1/-1->3->2
2024-08-04T16:38:23.111720857Z jupiter-cs-aus-134:98:629 [3] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.111722080Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Trees [0] 7/-1/-1->6->5 [1] 7/-1/-1->6->5 [2] 7/-1/-1->6->5 [3] 7/-1/-1->6->5 [4] 7/-1/-1->6->5 [5] 7/-1/-1->6->5 [6] 7/22/-1->6->-1 [7] -1/-1/-1->6->5 [8] 7/-1/-1->6->5 [9] 7/-1/-1->6->5 [10] 7/-1/-1->6->5 [11] 7/-1/-1->6->5 [12] 7/-1/-1->6->5 [13] 7/-1/-1->6->5 [14] 7/-1/-1->6->14 [15] -1/-1/-1->6->5
2024-08-04T16:38:23.111725847Z jupiter-cs-aus-134:101:626 [6] NCCL INFO P2P Chunksize set to 131072
2024-08-04T16:38:23.156468500Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 03/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.157851083Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 05/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.158850051Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 01/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.159599890Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 07/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.159983413Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 11/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.160514297Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 13/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.160989800Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 15/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.163823897Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 03/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.164569731Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 05/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.165375484Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 07/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.166111564Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 09/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.166818728Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 11/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.167823325Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 13/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.168806946Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 15/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.171498050Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 01/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.172245735Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 03/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.172991334Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 05/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.173706014Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 09/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.174475224Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 11/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.175157422Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 13/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.178206643Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 01/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.178704299Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 03/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.179340853Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 05/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.179655957Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 07/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.179928895Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 09/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.181550603Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 11/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.181857691Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 01/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.182136915Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 13/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.182329980Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 03/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.182508533Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 15/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.182872122Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 07/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.183176609Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 09/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.183462558Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 11/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.183650555Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 15/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.185591464Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 01/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.185902423Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 03/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.185945712Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 01/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.186249013Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 05/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.186270081Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 05/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.186600599Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 07/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.186622718Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 07/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.186888991Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 06/0 : 30[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.186940485Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 09/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.186942633Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 14/0 : 30[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.186961164Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 09/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.187008070Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 07/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.187064573Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 15/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.187299574Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 11/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.187320562Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 13/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.187642929Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 04/0 : 28[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.187647947Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 13/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.187664230Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 15/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.187703481Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 12/0 : 28[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.187760078Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 05/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.187821362Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 13/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.187985557Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 05/0 : 29[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.187987002Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 15/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.188047007Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 13/0 : 29[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.188104129Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 04/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.188163701Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 12/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.191821698Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 03/0 : 27[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.191880305Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 11/0 : 27[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.191936288Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 02/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.191993797Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 10/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.192043371Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 01/0 : 25[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.192064101Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 02/0 : 26[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.192106697Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 09/0 : 25[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.192132321Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 10/0 : 26[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.192153717Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 00/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.192179155Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 03/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.192199841Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 08/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.192240303Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 11/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.194196599Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.194538339Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 02/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.194743777Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 04/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.194934023Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 06/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.195127695Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.195332834Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 10/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.195529419Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 12/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.195722964Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 14/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.198977826Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 00/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.199206646Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 02/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.199432364Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 04/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.199600427Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/0 : 24[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.199649203Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 06/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.199667514Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/0 : 24[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.199719147Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 01/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.199771956Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 09/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.199883534Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 08/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.200100517Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 10/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.200330168Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 12/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.200478129Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 07/0 : 31[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.200548534Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 15/0 : 31[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.200549985Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 14/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.200605830Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 06/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.200669009Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 14/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.203582305Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 01/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.204545500Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 03/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.205200271Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 00/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.205427034Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 05/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.205633792Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 00/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.206193691Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 02/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.206714465Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 07/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.206732877Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 02/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.207161631Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 04/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.207905833Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 00/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.208265522Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 04/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.208376679Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 04/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.208663011Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 06/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.208966385Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 06/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.209024013Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 06/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.209128106Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 00/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.209451359Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 08/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.209629334Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 08/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.209793147Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 08/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.209845807Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 09/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.209916167Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 02/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.210295593Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 10/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.210389387Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 10/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.210607499Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 02/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.210650811Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 12/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.210753776Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 11/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.210806763Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 06/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.211257893Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 12/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.211409988Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 12/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.211577056Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 04/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.211594433Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 14/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.211631023Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 13/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.211761808Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 08/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.212217275Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 14/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.212338981Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 14/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.212505651Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 06/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.212564188Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 15/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.212589949Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 10/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.213233656Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 10/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.213288144Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 14/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.213377177Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 00/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.213799702Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 12/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.214077679Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 02/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.214550807Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 14/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.214865526Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 04/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.215842976Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 08/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.216198758Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 10/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.218165412Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 12/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.601721922Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Connected all rings
2024-08-04T16:38:23.601739190Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Connected all rings
2024-08-04T16:38:23.601741637Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Connected all rings
2024-08-04T16:38:23.603777487Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Connected all rings
2024-08-04T16:38:23.603780621Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Connected all rings
2024-08-04T16:38:23.603931184Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 00/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.604023262Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Connected all rings
2024-08-04T16:38:23.604028582Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.604085121Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Connected all rings
2024-08-04T16:38:23.604099027Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Connected all rings
2024-08-04T16:38:23.604915000Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 02/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.605350803Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 02/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.605436613Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 00/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.605996737Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 04/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.606066889Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 00/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.606451107Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 04/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.606517543Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 02/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.607037616Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 06/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.607094802Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 02/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.608092869Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 06/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.608255758Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 08/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.608726095Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 04/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.608888544Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 06/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.609284565Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 08/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.609465830Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 00/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.609711159Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 10/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.609957064Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 02/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.610287385Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 14/0 : 3[3] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.610502468Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 04/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.610719857Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 00/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.610944345Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 10/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.610965448Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 06/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.611288239Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 02/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.611549741Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 12/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.611647647Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 08/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.611933740Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 04/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.612163368Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 14/0 : 4[4] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.612257498Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 10/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.612425482Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 06/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.612935063Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 12/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.612983818Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 08/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.613432214Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 14/0 : 6[6] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.613459912Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 10/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.613498845Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 00/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.614079452Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 08/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.614162031Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 12/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.614181574Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 04/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.614677359Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 10/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.614770378Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 14/0 : 2[2] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.614790288Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 06/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.615604569Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.615803985Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 10/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.615992038Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 12/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.616186061Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 14/0 : 0[0] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.616187932Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 12/0 : 5[5] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.616189613Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 08/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.616787854Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 12/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.616997349Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 11/0 : 3[3] -> 11[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.617180167Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 14/0 : 1[1] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.617367394Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 12/0 : 4[4] -> 12[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.617369107Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 14/0 : 6[6] -> 14[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.617411828Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 13/0 : 5[5] -> 13[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.617516822Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 03/0 : 19[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.617541642Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 06/0 : 22[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.617563800Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 05/0 : 21[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.617565474Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 03/0 : 3[3] -> 19[3] [send] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.617588929Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 01/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.617590289Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 06/0 : 6[6] -> 22[6] [send] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.617619865Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 05/0 : 5[5] -> 21[5] [send] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.617668869Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 04/0 : 20[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.617681113Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 10/0 : 2[2] -> 10[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.617718723Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 09/0 : 1[1] -> 9[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.617724263Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 04/0 : 4[4] -> 20[4] [send] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.617857442Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 03/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.618089824Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 01/0 : 17[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.618140147Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 01/0 : 1[1] -> 17[1] [send] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.618142072Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 05/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.618143537Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 02/0 : 18[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.618210055Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 02/0 : 2[2] -> 18[2] [send] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.618416382Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 07/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.618605796Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 09/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.618809180Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 11/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.618999749Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 13/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.619044394Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 14/0 : 14[6] -> 6[6] [receive] via NET/IB/7/GDRDMA
2024-08-04T16:38:23.619892836Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 15/0 : 0[0] -> 7[7] via P2P/CUMEM
2024-08-04T16:38:23.620868834Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/0 : 0[0] -> 8[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.620873402Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 15/0 : 7[7] -> 15[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.620875119Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 13/0 : 13[5] -> 5[5] [receive] via NET/IB/6/GDRDMA
2024-08-04T16:38:23.621410255Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/0 : 16[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.621423223Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 07/0 : 23[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.621449873Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 00/0 : 0[0] -> 16[0] [send] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.621460560Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 07/0 : 7[7] -> 23[7] [send] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.621831024Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 01/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.622130254Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 03/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.622424687Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 05/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.622719597Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 07/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.623012465Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 09/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.623038437Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 01/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.623341250Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 11/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.623360768Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 03/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.623412769Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 12/0 : 12[4] -> 4[4] [receive] via NET/IB/5/GDRDMA
2024-08-04T16:38:23.623666415Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 13/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.623687768Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 04/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.624079764Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Channel 15/0 : 6[6] -> 5[5] via P2P/CUMEM
2024-08-04T16:38:23.624098233Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 07/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.624523040Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 09/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.624575566Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 15/0 : 15[7] -> 7[7] [receive] via NET/IB/8/GDRDMA
2024-08-04T16:38:23.624688246Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Channel 08/0 : 8[0] -> 0[0] [receive] via NET/IB/0/GDRDMA
2024-08-04T16:38:23.624733423Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 10/0 : 10[2] -> 2[2] [receive] via NET/IB/3/GDRDMA
2024-08-04T16:38:23.624788682Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 11/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.624793757Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 11/0 : 11[3] -> 3[3] [receive] via NET/IB/4/GDRDMA
2024-08-04T16:38:23.624848537Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 02/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.625152499Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 12/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.625174020Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 09/0 : 9[1] -> 1[1] [receive] via NET/IB/1/GDRDMA
2024-08-04T16:38:23.625242370Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 04/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.625862479Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Channel 15/0 : 5[5] -> 4[4] via P2P/CUMEM
2024-08-04T16:38:23.626049052Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 06/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.626929259Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 10/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.628001054Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 01/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.628348739Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 12/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.628673443Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 03/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.629158413Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 14/0 : 7[7] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.629432483Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 05/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.630135718Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 07/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.630186037Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 01/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.630843120Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 09/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.630897531Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 01/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.630919330Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 03/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.631517037Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 01/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.631631358Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 11/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.631650325Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 02/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.631690293Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 05/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.632105774Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 00/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.632312438Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 03/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.632444285Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 13/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.632486185Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 05/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.632526885Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 06/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.633060622Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 03/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.633218488Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 05/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.633239524Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Channel 15/0 : 4[4] -> 3[3] via P2P/CUMEM
2024-08-04T16:38:23.633392934Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 07/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.633423542Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 09/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.634000021Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 05/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.634116024Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 07/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.634170777Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 09/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.634325593Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 11/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.634850172Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 07/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.634941541Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 09/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.634961975Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 10/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.635151701Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 13/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:23.635637422Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 08/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.635658072Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 11/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.635743598Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 13/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.636404855Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 11/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.636428104Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 13/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.636482415Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Channel 15/0 : 3[3] -> 2[2] via P2P/CUMEM
2024-08-04T16:38:23.636927894Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 13/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.636947919Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Channel 15/0 : 2[2] -> 1[1] via P2P/CUMEM
2024-08-04T16:38:23.637646936Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Channel 15/0 : 1[1] -> 0[0] via P2P/CUMEM
2024-08-04T16:38:23.638895538Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Channel 14/0 : 7[7] -> 6[6] via P2P/CUMEM
2024-08-04T16:38:24.074545045Z jupiter-cs-aus-134:97:625 [2] NCCL INFO Connected all trees
2024-08-04T16:38:24.074561387Z jupiter-cs-aus-134:97:625 [2] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.074572832Z jupiter-cs-aus-134:97:625 [2] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.074574705Z jupiter-cs-aus-134:98:629 [3] NCCL INFO Connected all trees
2024-08-04T16:38:24.074576136Z jupiter-cs-aus-134:98:629 [3] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.074577777Z jupiter-cs-aus-134:98:629 [3] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077093540Z jupiter-cs-aus-134:95:623 [0] NCCL INFO Connected all trees
2024-08-04T16:38:24.077122827Z jupiter-cs-aus-134:96:627 [1] NCCL INFO Connected all trees
2024-08-04T16:38:24.077138841Z jupiter-cs-aus-134:96:627 [1] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077141116Z jupiter-cs-aus-134:96:627 [1] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077147224Z jupiter-cs-aus-134:95:623 [0] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077148878Z jupiter-cs-aus-134:95:623 [0] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077717914Z jupiter-cs-aus-134:102:628 [7] NCCL INFO Connected all trees
2024-08-04T16:38:24.077723306Z jupiter-cs-aus-134:99:624 [4] NCCL INFO Connected all trees
2024-08-04T16:38:24.077725062Z jupiter-cs-aus-134:102:628 [7] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077726906Z jupiter-cs-aus-134:99:624 [4] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077728600Z jupiter-cs-aus-134:102:628 [7] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077730447Z jupiter-cs-aus-134:99:624 [4] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077787280Z jupiter-cs-aus-134:101:626 [6] NCCL INFO Connected all trees
2024-08-04T16:38:24.077799665Z jupiter-cs-aus-134:100:630 [5] NCCL INFO Connected all trees
2024-08-04T16:38:24.077801801Z jupiter-cs-aus-134:101:626 [6] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077803926Z jupiter-cs-aus-134:101:626 [6] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.077805745Z jupiter-cs-aus-134:100:630 [5] NCCL INFO threadThresholds 8/8/64 | 256/8/64 | 512 | 512
2024-08-04T16:38:24.077807364Z jupiter-cs-aus-134:100:630 [5] NCCL INFO 16 coll channels, 0 collnet channels, 0 nvls channels, 16 p2p channels, 2 p2p channels per peer
2024-08-04T16:38:24.120389672Z jupiter-cs-aus-134:102:628 [7] NCCL INFO comm 0x7f40e407fc60 rank 7 nranks 32 cudaDev 7 nvmlDev 7 busId e4000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120413854Z jupiter-cs-aus-134:99:624 [4] NCCL INFO comm 0x7fcab007fe00 rank 4 nranks 32 cudaDev 4 nvmlDev 4 busId 84000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120434691Z jupiter-cs-aus-134:96:627 [1] NCCL INFO comm 0x7f2284091160 rank 1 nranks 32 cudaDev 1 nvmlDev 1 busId 2a000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120436932Z jupiter-cs-aus-134:98:629 [3] NCCL INFO comm 0x7fa72007fa00 rank 3 nranks 32 cudaDev 3 nvmlDev 3 busId 5d000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120438598Z jupiter-cs-aus-134:97:625 [2] NCCL INFO comm 0x7f3fd80929a0 rank 2 nranks 32 cudaDev 2 nvmlDev 2 busId 3a000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120440171Z jupiter-cs-aus-134:100:630 [5] NCCL INFO comm 0x7f6d0c07fa10 rank 5 nranks 32 cudaDev 5 nvmlDev 5 busId 8b000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120441591Z jupiter-cs-aus-134:95:623 [0] NCCL INFO comm 0x7f2e600806a0 rank 0 nranks 32 cudaDev 0 nvmlDev 0 busId 18000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:24.120443265Z jupiter-cs-aus-134:101:626 [6] NCCL INFO comm 0x7f0b7c07f950 rank 6 nranks 32 cudaDev 6 nvmlDev 6 busId 91000 commId 0x39a520acc33b2a02 - Init COMPLETE
2024-08-04T16:38:27.759318613Z 
  0%|          | 1/5712 [00:18<29:59:31, 18.91s/it]08/04/2024 09:38:27 - INFO - __main__ -   Step: 1, LR: 8.755129958960328e-10, Loss: 0.6931471824645996
2024-08-04T16:39:59.030359560Z 
  0%|          | 2/5712 [01:50<97:30:16, 61.47s/it]08/04/2024 09:39:59 - INFO - __main__ -   Step: 2, LR: 1.7510259917920655e-09, Loss: 0.6931471824645996
2024-08-04T16:40:07.021099181Z 
  0%|          | 3/5712 [01:58<58:45:32, 37.05s/it]08/04/2024 09:40:07 - INFO - __main__ -   Step: 3, LR: 2.626538987688098e-09, Loss: 0.6998361945152283
2024-08-04T16:40:14.910212465Z 
  0%|          | 4/5712 [02:06<40:29:37, 25.54s/it]08/04/2024 09:40:14 - INFO - __main__ -   Step: 4, LR: 3.502051983584131e-09, Loss: 0.6980556845664978
2024-08-04T16:40:23.152838999Z 
  0%|          | 5/5712 [02:14<30:35:55, 19.30s/it]08/04/2024 09:40:23 - INFO - __main__ -   Step: 5, LR: 4.3775649794801635e-09, Loss: 0.6707123517990112
2024-08-04T16:40:30.760576438Z 
  0%|          | 6/5712 [02:21<24:17:29, 15.33s/it]08/04/2024 09:40:30 - INFO - __main__ -   Step: 6, LR: 5.253077975376196e-09, Loss: 0.6963956356048584
2024-08-04T16:40:38.362921642Z 
  0%|          | 7/5712 [02:29<20:17:09, 12.80s/it]08/04/2024 09:40:38 - INFO - __main__ -   Step: 7, LR: 6.128590971272229e-09, Loss: 0.7120819687843323
2024-08-04T16:40:45.968939146Z 
  0%|          | 8/5712 [02:37<17:39:42, 11.15s/it]08/04/2024 09:40:45 - INFO - __main__ -   Step: 8, LR: 7.004103967168262e-09, Loss: 0.7333127856254578
2024-08-04T16:40:53.526354268Z 
  0%|          | 9/5712 [02:44<15:52:52, 10.02s/it]08/04/2024 09:40:53 - INFO - __main__ -   Step: 9, LR: 7.879616963064295e-09, Loss: 0.6828325390815735
2024-08-04T16:41:01.200728857Z 
  0%|          | 10/5712 [02:52<14:43:44,  9.30s/it]08/04/2024 09:41:01 - INFO - __main__ -   Step: 10, LR: 8.755129958960327e-09, Loss: 0.7044398784637451
2024-08-04T16:41:08.774951841Z 
  0%|          | 11/5712 [02:59<13:53:25,  8.77s/it]08/04/2024 09:41:08 - INFO - __main__ -   Step: 11, LR: 9.63064295485636e-09, Loss: 0.6861777305603027
2024-08-04T16:41:16.329347405Z 
  0%|          | 12/5712 [03:07<13:18:06,  8.40s/it]08/04/2024 09:41:16 - INFO - __main__ -   Step: 12, LR: 1.0506155950752393e-08, Loss: 0.6991897821426392
2024-08-04T16:41:24.628755157Z 
  0%|          | 13/5712 [03:15<13:15:01,  8.37s/it]08/04/2024 09:41:24 - INFO - __main__ -   Step: 13, LR: 1.1381668946648426e-08, Loss: 0.706813633441925
2024-08-04T16:41:32.142895753Z 
  0%|          | 14/5712 [03:23<12:50:20,  8.11s/it]08/04/2024 09:41:32 - INFO - __main__ -   Step: 14, LR: 1.2257181942544458e-08, Loss: 0.7107319831848145
2024-08-04T16:41:39.675957367Z 
  0%|          | 15/5712 [03:30<12:33:38,  7.94s/it]08/04/2024 09:41:39 - INFO - __main__ -   Step: 15, LR: 1.3132694938440492e-08, Loss: 0.6950780153274536
2024-08-04T16:41:47.321304009Z 
  0%|          | 16/5712 [03:38<12:25:10,  7.85s/it]08/04/2024 09:41:47 - INFO - __main__ -   Step: 16, LR: 1.4008207934336524e-08, Loss: 0.7041332125663757
2024-08-04T16:41:54.861493826Z 
  0%|          | 17/5712 [03:46<12:16:12,  7.76s/it]08/04/2024 09:41:54 - INFO - __main__ -   Step: 17, LR: 1.4883720930232558e-08, Loss: 0.6952694058418274
2024-08-04T16:42:02.412373135Z 
  0%|          | 18/5712 [03:53<12:10:13,  7.69s/it]08/04/2024 09:42:02 - INFO - __main__ -   Step: 18, LR: 1.575923392612859e-08, Loss: 0.6685059070587158
2024-08-04T16:42:09.988976786Z 
  0%|          | 19/5712 [04:01<12:06:43,  7.66s/it]08/04/2024 09:42:09 - INFO - __main__ -   Step: 19, LR: 1.663474692202462e-08, Loss: 0.698024332523346
2024-08-04T16:42:17.663697384Z 
  0%|          | 20/5712 [04:08<12:07:02,  7.66s/it]08/04/2024 09:42:17 - INFO - __main__ -   Step: 20, LR: 1.7510259917920654e-08, Loss: 0.7036696076393127
2024-08-04T16:42:26.153748173Z 
  0%|          | 21/5712 [04:17<12:30:26,  7.91s/it]08/04/2024 09:42:26 - INFO - __main__ -   Step: 21, LR: 1.838577291381669e-08, Loss: 0.6913235187530518
2024-08-04T16:42:34.183542768Z 
  0%|          | 22/5712 [04:25<12:33:40,  7.95s/it]08/04/2024 09:42:34 - INFO - __main__ -   Step: 22, LR: 1.926128590971272e-08, Loss: 0.6979995965957642
2024-08-04T16:42:41.729386747Z 
  0%|          | 23/5712 [04:32<12:22:06,  7.83s/it]08/04/2024 09:42:41 - INFO - __main__ -   Step: 23, LR: 2.0136798905608755e-08, Loss: 0.6864503622055054
2024-08-04T16:42:49.286452280Z 
  0%|          | 24/5712 [04:40<12:14:17,  7.75s/it]08/04/2024 09:42:49 - INFO - __main__ -   Step: 24, LR: 2.1012311901504785e-08, Loss: 0.701951265335083
2024-08-04T16:42:56.766663484Z 
  0%|          | 25/5712 [04:47<12:06:37,  7.67s/it]08/04/2024 09:42:56 - INFO - __main__ -   Step: 25, LR: 2.188782489740082e-08, Loss: 0.6914501190185547
2024-08-04T16:43:04.316217223Z 
  0%|          | 26/5712 [04:55<12:03:10,  7.63s/it]08/04/2024 09:43:04 - INFO - __main__ -   Step: 26, LR: 2.2763337893296853e-08, Loss: 0.6915736198425293
2024-08-04T16:43:11.844258545Z 
  0%|          | 27/5712 [05:02<12:00:07,  7.60s/it]08/04/2024 09:43:11 - INFO - __main__ -   Step: 27, LR: 2.3638850889192883e-08, Loss: 0.696486234664917
2024-08-04T16:43:19.676495356Z 
  0%|          | 28/5712 [05:10<12:06:35,  7.67s/it]08/04/2024 09:43:19 - INFO - __main__ -   Step: 28, LR: 2.4514363885088917e-08, Loss: 0.7202781438827515
2024-08-04T16:43:28.132407249Z 
  1%|          | 29/5712 [05:19<12:28:47,  7.91s/it]08/04/2024 09:43:28 - INFO - __main__ -   Step: 29, LR: 2.5389876880984954e-08, Loss: 0.6791400909423828
2024-08-04T16:43:36.206473561Z 
  1%|          | 30/5712 [05:27<12:33:27,  7.96s/it]08/04/2024 09:43:36 - INFO - __main__ -   Step: 30, LR: 2.6265389876880984e-08, Loss: 0.6964441537857056
2024-08-04T16:43:43.760358743Z 
  1%|          | 31/5712 [05:34<12:21:53,  7.84s/it]08/04/2024 09:43:43 - INFO - __main__ -   Step: 31, LR: 2.7140902872777018e-08, Loss: 0.6885902881622314
2024-08-04T16:43:51.822669148Z 
  1%|          | 32/5712 [05:42<12:28:11,  7.90s/it]08/04/2024 09:43:51 - INFO - __main__ -   Step: 32, LR: 2.801641586867305e-08, Loss: 0.6789212226867676
2024-08-04T16:43:59.359112492Z 
  1%|          | 33/5712 [05:50<12:17:38,  7.79s/it]08/04/2024 09:43:59 - INFO - __main__ -   Step: 33, LR: 2.8891928864569082e-08, Loss: 0.7085568308830261
2024-08-04T16:44:07.151298509Z 
  1%|          | 34/5712 [05:58<12:17:28,  7.79s/it]08/04/2024 09:44:07 - INFO - __main__ -   Step: 34, LR: 2.9767441860465116e-08, Loss: 0.7034270763397217
2024-08-04T16:44:14.668626666Z 
  1%|          | 35/5712 [06:05<12:09:31,  7.71s/it]08/04/2024 09:44:14 - INFO - __main__ -   Step: 35, LR: 3.0642954856361146e-08, Loss: 0.7148541808128357
2024-08-04T16:44:22.206982038Z 
  1%|          | 36/5712 [06:13<12:04:31,  7.66s/it]08/04/2024 09:44:22 - INFO - __main__ -   Step: 36, LR: 3.151846785225718e-08, Loss: 0.7137930393218994
2024-08-04T16:44:30.164628380Z 
  1%|          | 37/5712 [06:21<12:12:51,  7.75s/it]08/04/2024 09:44:30 - INFO - __main__ -   Step: 37, LR: 3.2393980848153214e-08, Loss: 0.6807165145874023
2024-08-04T16:44:38.551544966Z 
  1%|          | 38/5712 [06:29<12:30:51,  7.94s/it]08/04/2024 09:44:38 - INFO - __main__ -   Step: 38, LR: 3.326949384404924e-08, Loss: 0.6883653402328491
2024-08-04T16:44:46.081413246Z 
  1%|          | 39/5712 [06:37<12:19:05,  7.82s/it]08/04/2024 09:44:46 - INFO - __main__ -   Step: 39, LR: 3.4145006839945274e-08, Loss: 0.6968000531196594
2024-08-04T16:44:53.550874325Z 
  1%|          | 40/5712 [06:44<12:09:06,  7.71s/it]08/04/2024 09:44:53 - INFO - __main__ -   Step: 40, LR: 3.502051983584131e-08, Loss: 0.7103575468063354
2024-08-04T16:45:01.102962293Z 
  1%|          | 41/5712 [06:52<12:04:25,  7.66s/it]08/04/2024 09:45:01 - INFO - __main__ -   Step: 41, LR: 3.589603283173735e-08, Loss: 0.6894935369491577
2024-08-04T16:45:08.700674330Z 
  1%|          | 42/5712 [06:59<12:02:24,  7.64s/it]08/04/2024 09:45:08 - INFO - __main__ -   Step: 42, LR: 3.677154582763338e-08, Loss: 0.6936129927635193
2024-08-04T16:45:16.138425306Z 
  1%|          | 43/5712 [07:07<11:56:25,  7.58s/it]08/04/2024 09:45:16 - INFO - __main__ -   Step: 43, LR: 3.764705882352941e-08, Loss: 0.7069162130355835
2024-08-04T16:45:23.599365402Z 
  1%|          | 44/5712 [07:14<11:52:50,  7.55s/it]08/04/2024 09:45:23 - INFO - __main__ -   Step: 44, LR: 3.852257181942544e-08, Loss: 0.6980623006820679
2024-08-04T16:45:31.032995231Z 
  1%|          | 45/5712 [07:22<11:49:31,  7.51s/it]08/04/2024 09:45:31 - INFO - __main__ -   Step: 45, LR: 3.9398084815321476e-08, Loss: 0.6830753087997437
2024-08-04T16:45:39.443976955Z 
  1%|          | 46/5712 [07:30<12:14:52,  7.78s/it]08/04/2024 09:45:39 - INFO - __main__ -   Step: 46, LR: 4.027359781121751e-08, Loss: 0.7358903288841248
2024-08-04T16:45:47.103925965Z 
  1%|          | 47/5712 [07:38<12:11:17,  7.75s/it]08/04/2024 09:45:47 - INFO - __main__ -   Step: 47, LR: 4.1149110807113544e-08, Loss: 0.686690092086792
2024-08-04T16:45:54.650118323Z 
  1%|          | 48/5712 [07:45<12:05:31,  7.69s/it]08/04/2024 09:45:54 - INFO - __main__ -   Step: 48, LR: 4.202462380300957e-08, Loss: 0.6997710466384888
2024-08-04T16:46:02.119192602Z 
  1%|          | 49/5712 [07:53<11:59:15,  7.62s/it]08/04/2024 09:46:02 - INFO - __main__ -   Step: 49, LR: 4.2900136798905605e-08, Loss: 0.6839615702629089
2024-08-04T16:46:09.802399523Z 
  1%|          | 50/5712 [08:00<12:00:54,  7.64s/it]08/04/2024 09:46:09 - INFO - __main__ -   Step: 50, LR: 4.377564979480164e-08, Loss: 0.7200710773468018
2024-08-04T16:46:17.243273289Z 
  1%|          | 51/5712 [08:08<11:55:09,  7.58s/it]08/04/2024 09:46:17 - INFO - __main__ -   Step: 51, LR: 4.465116279069767e-08, Loss: 0.692096471786499
2024-08-04T16:46:24.721570289Z 
  1%|          | 52/5712 [08:15<11:52:09,  7.55s/it]08/04/2024 09:46:24 - INFO - __main__ -   Step: 52, LR: 4.5526675786593706e-08, Loss: 0.668211817741394
2024-08-04T16:46:32.402045642Z 
  1%|          | 53/5712 [08:23<11:55:44,  7.59s/it]08/04/2024 09:46:32 - INFO - __main__ -   Step: 53, LR: 4.640218878248973e-08, Loss: 0.7074475288391113
2024-08-04T16:46:40.914220462Z 
  1%|          | 54/5712 [08:32<12:21:44,  7.87s/it]08/04/2024 09:46:40 - INFO - __main__ -   Step: 54, LR: 4.7277701778385766e-08, Loss: 0.703402578830719
2024-08-04T16:46:49.104248555Z 
  1%|          | 55/5712 [08:40<12:30:46,  7.96s/it]08/04/2024 09:46:49 - INFO - __main__ -   Step: 55, LR: 4.81532147742818e-08, Loss: 0.7161206603050232
2024-08-04T16:46:56.691449831Z 
  1%|          | 56/5712 [08:47<12:20:00,  7.85s/it]08/04/2024 09:46:56 - INFO - __main__ -   Step: 56, LR: 4.9028727770177834e-08, Loss: 0.6990382671356201
2024-08-04T16:47:04.442923747Z 
  1%|          | 57/5712 [08:55<12:17:05,  7.82s/it]08/04/2024 09:47:04 - INFO - __main__ -   Step: 57, LR: 4.9904240766073874e-08, Loss: 0.7071866989135742
2024-08-04T16:47:12.321190851Z 
  1%|          | 58/5712 [09:03<12:18:35,  7.84s/it]08/04/2024 09:47:12 - INFO - __main__ -   Step: 58, LR: 5.077975376196991e-08, Loss: 0.6889636516571045
2024-08-04T16:47:19.848118549Z 
  1%|          | 59/5712 [09:10<12:09:40,  7.74s/it]08/04/2024 09:47:19 - INFO - __main__ -   Step: 59, LR: 5.1655266757865935e-08, Loss: 0.6912192702293396
2024-08-04T16:47:27.343766788Z 
  1%|          | 60/5712 [09:18<12:02:30,  7.67s/it]08/04/2024 09:47:27 - INFO - __main__ -   Step: 60, LR: 5.253077975376197e-08, Loss: 0.6838579177856445
2024-08-04T16:47:34.868504863Z 
  1%|          | 61/5712 [09:26<11:58:16,  7.63s/it]08/04/2024 09:47:34 - INFO - __main__ -   Step: 61, LR: 5.3406292749658e-08, Loss: 0.6795120239257812
2024-08-04T16:47:43.333514574Z 
  1%|          | 62/5712 [09:34<12:21:50,  7.88s/it]08/04/2024 09:47:43 - INFO - __main__ -   Step: 62, LR: 5.4281805745554036e-08, Loss: 0.7177343368530273
2024-08-04T16:47:51.464716265Z 
  1%|          | 63/5712 [09:42<12:28:52,  7.95s/it]08/04/2024 09:47:51 - INFO - __main__ -   Step: 63, LR: 5.515731874145007e-08, Loss: 0.728875994682312
2024-08-04T16:47:59.022388438Z 
  1%|          | 64/5712 [09:50<12:17:31,  7.83s/it]08/04/2024 09:47:59 - INFO - __main__ -   Step: 64, LR: 5.60328317373461e-08, Loss: 0.6835880279541016
2024-08-04T16:48:06.636605892Z 
  1%|          | 65/5712 [09:57<12:11:09,  7.77s/it]08/04/2024 09:48:06 - INFO - __main__ -   Step: 65, LR: 5.690834473324213e-08, Loss: 0.6993609070777893
2024-08-04T16:48:14.165185204Z 
  1%|          | 66/5712 [10:05<12:04:15,  7.70s/it]08/04/2024 09:48:14 - INFO - __main__ -   Step: 66, LR: 5.7783857729138164e-08, Loss: 0.7142348289489746
2024-08-04T16:48:21.691764280Z 
  1%|          | 67/5712 [10:12<11:59:19,  7.65s/it]08/04/2024 09:48:21 - INFO - __main__ -   Step: 67, LR: 5.86593707250342e-08, Loss: 0.7153388857841492
2024-08-04T16:48:29.141471795Z 
  1%|          | 68/5712 [10:20<11:53:40,  7.59s/it]08/04/2024 09:48:29 - INFO - __main__ -   Step: 68, LR: 5.953488372093023e-08, Loss: 0.7048372626304626
2024-08-04T16:48:36.828849324Z 
  1%|          | 69/5712 [10:27<11:56:23,  7.62s/it]08/04/2024 09:48:36 - INFO - __main__ -   Step: 69, LR: 6.041039671682627e-08, Loss: 0.7117264270782471
2024-08-04T16:48:45.392961765Z 
  1%|          | 70/5712 [10:36<12:22:58,  7.90s/it]08/04/2024 09:48:45 - INFO - __main__ -   Step: 70, LR: 6.128590971272229e-08, Loss: 0.703973650932312
2024-08-04T16:48:53.695400145Z 
  1%|          | 71/5712 [10:44<12:34:09,  8.02s/it]08/04/2024 09:48:53 - INFO - __main__ -   Step: 71, LR: 6.216142270861833e-08, Loss: 0.6923038959503174
2024-08-04T16:49:01.528377576Z 
  1%|▏         | 72/5712 [10:52<12:28:42,  7.97s/it]08/04/2024 09:49:01 - INFO - __main__ -   Step: 72, LR: 6.303693570451436e-08, Loss: 0.69292151927948
2024-08-04T16:49:09.188842350Z 
  1%|▏         | 73/5712 [11:00<12:19:59,  7.87s/it]08/04/2024 09:49:09 - INFO - __main__ -   Step: 73, LR: 6.391244870041039e-08, Loss: 0.6913508176803589
2024-08-04T16:49:16.985735498Z 
  1%|▏         | 74/5712 [11:08<12:17:41,  7.85s/it]08/04/2024 09:49:16 - INFO - __main__ -   Step: 74, LR: 6.478796169630643e-08, Loss: 0.6849799156188965
2024-08-04T16:49:24.586249212Z 
  1%|▏         | 75/5712 [11:15<12:10:30,  7.78s/it]08/04/2024 09:49:24 - INFO - __main__ -   Step: 75, LR: 6.566347469220245e-08, Loss: 0.6937519311904907
2024-08-04T16:49:32.074701991Z 
  1%|▏         | 76/5712 [11:23<12:02:18,  7.69s/it]08/04/2024 09:49:32 - INFO - __main__ -   Step: 76, LR: 6.653898768809848e-08, Loss: 0.7159361839294434
2024-08-04T16:49:39.597808827Z 
  1%|▏         | 77/5712 [11:30<11:57:28,  7.64s/it]08/04/2024 09:49:39 - INFO - __main__ -   Step: 77, LR: 6.741450068399452e-08, Loss: 0.7193236351013184
2024-08-04T16:49:47.703519545Z 
  1%|▏         | 78/5712 [11:38<12:10:29,  7.78s/it]08/04/2024 09:49:47 - INFO - __main__ -   Step: 78, LR: 6.829001367989055e-08, Loss: 0.6835300922393799
2024-08-04T16:49:56.473482245Z 
  1%|▏         | 79/5712 [11:47<12:38:15,  8.08s/it]08/04/2024 09:49:56 - INFO - __main__ -   Step: 79, LR: 6.916552667578659e-08, Loss: 0.6933463215827942
2024-08-04T16:50:04.502225176Z 
  1%|▏         | 80/5712 [11:55<12:36:45,  8.06s/it]08/04/2024 09:50:04 - INFO - __main__ -   Step: 80, LR: 7.004103967168262e-08, Loss: 0.6952735185623169
2024-08-04T16:50:12.363136252Z 
  1%|▏         | 81/5712 [12:03<12:30:58,  8.00s/it]08/04/2024 09:50:12 - INFO - __main__ -   Step: 81, LR: 7.091655266757864e-08, Loss: 0.6991236805915833
2024-08-04T16:50:20.041700617Z 
  1%|▏         | 82/5712 [12:11<12:21:44,  7.90s/it]08/04/2024 09:50:20 - INFO - __main__ -   Step: 82, LR: 7.17920656634747e-08, Loss: 0.7070008516311646
2024-08-04T16:50:27.670282424Z 
  1%|▏         | 83/5712 [12:18<12:13:50,  7.82s/it]08/04/2024 09:50:27 - INFO - __main__ -   Step: 83, LR: 7.266757865937072e-08, Loss: 0.6878722906112671
2024-08-04T16:50:35.289653590Z 
  1%|▏         | 84/5712 [12:26<12:07:59,  7.76s/it]08/04/2024 09:50:35 - INFO - __main__ -   Step: 84, LR: 7.354309165526676e-08, Loss: 0.6880051493644714
2024-08-04T16:50:42.877839252Z 
  1%|▏         | 85/5712 [12:34<12:03:00,  7.71s/it]08/04/2024 09:50:42 - INFO - __main__ -   Step: 85, LR: 7.441860465116279e-08, Loss: 0.7261626720428467
2024-08-04T16:50:50.835687388Z 
  2%|▏         | 86/5712 [12:41<12:09:52,  7.78s/it]08/04/2024 09:50:50 - INFO - __main__ -   Step: 86, LR: 7.529411764705882e-08, Loss: 0.6716941595077515
2024-08-04T16:51:00.023697097Z 
  2%|▏         | 87/5712 [12:51<12:49:13,  8.21s/it]08/04/2024 09:51:00 - INFO - __main__ -   Step: 87, LR: 7.616963064295486e-08, Loss: 0.6880806684494019
2024-08-04T16:51:08.662270263Z 
  2%|▏         | 88/5712 [12:59<13:01:16,  8.34s/it]08/04/2024 09:51:08 - INFO - __main__ -   Step: 88, LR: 7.704514363885089e-08, Loss: 0.6965017318725586
2024-08-04T16:51:16.157433041Z 
  2%|▏         | 89/5712 [13:07<12:37:31,  8.08s/it]08/04/2024 09:51:16 - INFO - __main__ -   Step: 89, LR: 7.792065663474693e-08, Loss: 0.7138015031814575
2024-08-04T16:51:23.744957485Z 
  2%|▏         | 90/5712 [13:14<12:23:27,  7.93s/it]08/04/2024 09:51:23 - INFO - __main__ -   Step: 90, LR: 7.879616963064295e-08, Loss: 0.7206392288208008
2024-08-04T16:51:31.306994459Z 
  2%|▏         | 91/5712 [13:22<12:12:51,  7.82s/it]08/04/2024 09:51:31 - INFO - __main__ -   Step: 91, LR: 7.967168262653898e-08, Loss: 0.6981893181800842
2024-08-04T16:51:38.843183378Z 
  2%|▏         | 92/5712 [13:29<12:04:40,  7.74s/it]08/04/2024 09:51:38 - INFO - __main__ -   Step: 92, LR: 8.054719562243502e-08, Loss: 0.6928083300590515
2024-08-04T16:51:46.469729838Z 
  2%|▏         | 93/5712 [13:37<12:01:27,  7.70s/it]08/04/2024 09:51:46 - INFO - __main__ -   Step: 93, LR: 8.142270861833105e-08, Loss: 0.6746349334716797
2024-08-04T16:51:54.068400146Z 
  2%|▏         | 94/5712 [13:45<11:58:21,  7.67s/it]08/04/2024 09:51:54 - INFO - __main__ -   Step: 94, LR: 8.229822161422709e-08, Loss: 0.699245810508728
2024-08-04T16:52:03.489327584Z 
  2%|▏         | 95/5712 [13:54<12:47:21,  8.20s/it]08/04/2024 09:52:03 - INFO - __main__ -   Step: 95, LR: 8.317373461012311e-08, Loss: 0.6858730912208557
2024-08-04T16:52:11.978888607Z 
  2%|▏         | 96/5712 [14:03<12:55:26,  8.28s/it]08/04/2024 09:52:11 - INFO - __main__ -   Step: 96, LR: 8.404924760601914e-08, Loss: 0.6856228113174438
2024-08-04T16:52:20.066198763Z 
  2%|▏         | 97/5712 [14:11<12:49:45,  8.23s/it]08/04/2024 09:52:20 - INFO - __main__ -   Step: 97, LR: 8.492476060191518e-08, Loss: 0.6980844736099243
2024-08-04T16:52:27.654699143Z 
  2%|▏         | 98/5712 [14:18<12:31:45,  8.03s/it]08/04/2024 09:52:27 - INFO - __main__ -   Step: 98, LR: 8.580027359781121e-08, Loss: 0.6849882006645203
2024-08-04T16:52:35.106530398Z 
  2%|▏         | 99/5712 [14:26<12:15:15,  7.86s/it]08/04/2024 09:52:35 - INFO - __main__ -   Step: 99, LR: 8.667578659370725e-08, Loss: 0.7205431461334229
2024-08-04T16:52:42.775567631Z 
  2%|▏         | 100/5712 [14:33<12:09:46,  7.80s/it]08/04/2024 09:52:42 - INFO - __main__ -   Step: 100, LR: 8.755129958960328e-08, Loss: 0.6895573139190674
2024-08-04T16:52:50.962114041Z 
  2%|▏         | 101/5712 [14:42<12:20:26,  7.92s/it]08/04/2024 09:52:50 - INFO - __main__ -   Step: 101, LR: 8.84268125854993e-08, Loss: 0.7032755613327026
2024-08-04T16:52:58.550090476Z 
  2%|▏         | 102/5712 [14:49<12:11:03,  7.82s/it]08/04/2024 09:52:58 - INFO - __main__ -   Step: 102, LR: 8.930232558139534e-08, Loss: 0.6888548731803894
2024-08-04T16:53:07.357560298Z 
  2%|▏         | 103/5712 [14:58<12:38:39,  8.12s/it]08/04/2024 09:53:07 - INFO - __main__ -   Step: 103, LR: 9.017783857729137e-08, Loss: 0.6937364339828491
2024-08-04T16:53:16.572468399Z 
  2%|▏         | 104/5712 [15:07<13:09:20,  8.45s/it]08/04/2024 09:53:16 - INFO - __main__ -   Step: 104, LR: 9.105335157318741e-08, Loss: 0.6888850927352905
2024-08-04T16:53:24.567510882Z 
  2%|▏         | 105/5712 [15:15<12:56:34,  8.31s/it]08/04/2024 09:53:24 - INFO - __main__ -   Step: 105, LR: 9.192886456908344e-08, Loss: 0.6952584981918335
2024-08-04T16:53:32.117808865Z 
  2%|▏         | 106/5712 [15:23<12:35:09,  8.08s/it]08/04/2024 09:53:32 - INFO - __main__ -   Step: 106, LR: 9.280437756497947e-08, Loss: 0.7182351350784302
2024-08-04T16:53:39.871550498Z 
  2%|▏         | 107/5712 [15:31<12:25:48,  7.98s/it]08/04/2024 09:53:39 - INFO - __main__ -   Step: 107, LR: 9.36798905608755e-08, Loss: 0.7029772996902466
2024-08-04T16:53:47.302008282Z 
  2%|▏         | 108/5712 [15:38<12:10:10,  7.82s/it]08/04/2024 09:53:47 - INFO - __main__ -   Step: 108, LR: 9.455540355677153e-08, Loss: 0.6943541765213013
2024-08-04T16:53:54.755907565Z 
  2%|▏         | 109/5712 [15:45<11:59:50,  7.71s/it]08/04/2024 09:53:54 - INFO - __main__ -   Step: 109, LR: 9.543091655266757e-08, Loss: 0.6990154981613159
2024-08-04T16:54:02.255819265Z 
  2%|▏         | 110/5712 [15:53<11:53:53,  7.65s/it]08/04/2024 09:54:02 - INFO - __main__ -   Step: 110, LR: 9.63064295485636e-08, Loss: 0.7134765386581421
2024-08-04T16:54:10.461599820Z 
  2%|▏         | 111/5712 [16:01<12:09:25,  7.81s/it]08/04/2024 09:54:10 - INFO - __main__ -   Step: 111, LR: 9.718194254445963e-08, Loss: 0.6859300136566162
2024-08-04T16:54:19.635788261Z 
  2%|▏         | 112/5712 [16:10<12:47:23,  8.22s/it]08/04/2024 09:54:19 - INFO - __main__ -   Step: 112, LR: 9.805745554035567e-08, Loss: 0.6823734045028687
2024-08-04T16:54:27.828070847Z 
  2%|▏         | 113/5712 [16:18<12:46:24,  8.21s/it]08/04/2024 09:54:27 - INFO - __main__ -   Step: 113, LR: 9.893296853625171e-08, Loss: 0.699669599533081
2024-08-04T16:54:35.876079288Z 
  2%|▏         | 114/5712 [16:27<12:41:39,  8.16s/it]08/04/2024 09:54:35 - INFO - __main__ -   Step: 114, LR: 9.980848153214775e-08, Loss: 0.6898506879806519
2024-08-04T16:54:43.369169443Z 
  2%|▏         | 115/5712 [16:34<12:22:45,  7.96s/it]08/04/2024 09:54:43 - INFO - __main__ -   Step: 115, LR: 1.0068399452804378e-07, Loss: 0.6641945838928223
2024-08-04T16:54:50.886730668Z 
  2%|▏         | 116/5712 [16:42<12:10:11,  7.83s/it]08/04/2024 09:54:50 - INFO - __main__ -   Step: 116, LR: 1.0155950752393982e-07, Loss: 0.7090247869491577
2024-08-04T16:54:58.424669696Z 
  2%|▏         | 117/5712 [16:49<12:01:54,  7.74s/it]08/04/2024 09:54:58 - INFO - __main__ -   Step: 117, LR: 1.0243502051983584e-07, Loss: 0.6823127269744873
2024-08-04T16:55:05.972849081Z 
  2%|▏         | 118/5712 [16:57<11:56:21,  7.68s/it]08/04/2024 09:55:05 - INFO - __main__ -   Step: 118, LR: 1.0331053351573187e-07, Loss: 0.6928598880767822
2024-08-04T16:55:13.866017024Z 
  2%|▏         | 119/5712 [17:05<12:02:06,  7.75s/it]08/04/2024 09:55:13 - INFO - __main__ -   Step: 119, LR: 1.0418604651162791e-07, Loss: 0.6938502788543701
2024-08-04T16:55:22.839946893Z 
  2%|▏         | 120/5712 [17:13<12:36:17,  8.11s/it]08/04/2024 09:55:22 - INFO - __main__ -   Step: 120, LR: 1.0506155950752394e-07, Loss: 0.6722677946090698
2024-08-04T16:55:31.278950830Z 
  2%|▏         | 121/5712 [17:22<12:45:13,  8.21s/it]08/04/2024 09:55:31 - INFO - __main__ -   Step: 121, LR: 1.0593707250341998e-07, Loss: 0.7166206240653992
2024-08-04T16:55:39.336216028Z 
  2%|▏         | 122/5712 [17:30<12:40:45,  8.17s/it]08/04/2024 09:55:39 - INFO - __main__ -   Step: 122, LR: 1.06812585499316e-07, Loss: 0.6893728971481323
2024-08-04T16:55:46.836508987Z 
  2%|▏         | 123/5712 [17:37<12:22:01,  7.97s/it]08/04/2024 09:55:46 - INFO - __main__ -   Step: 123, LR: 1.0768809849521203e-07, Loss: 0.7044479250907898
2024-08-04T16:55:54.266946336Z 
  2%|▏         | 124/5712 [17:45<12:06:56,  7.81s/it]08/04/2024 09:55:54 - INFO - __main__ -   Step: 124, LR: 1.0856361149110807e-07, Loss: 0.7206829786300659
2024-08-04T16:56:01.795035309Z 
  2%|▏         | 125/5712 [17:52<11:59:03,  7.72s/it]08/04/2024 09:56:01 - INFO - __main__ -   Step: 125, LR: 1.094391244870041e-07, Loss: 0.6747841238975525
2024-08-04T16:56:09.645622100Z 
  2%|▏         | 126/5712 [18:00<12:02:30,  7.76s/it]08/04/2024 09:56:09 - INFO - __main__ -   Step: 126, LR: 1.1031463748290014e-07, Loss: 0.708403468132019
2024-08-04T16:56:17.153297269Z 
  2%|▏         | 127/5712 [18:08<11:55:19,  7.68s/it]08/04/2024 09:56:17 - INFO - __main__ -   Step: 127, LR: 1.1119015047879617e-07, Loss: 0.6652869582176208
2024-08-04T16:56:25.962285543Z 
  2%|▏         | 128/5712 [18:17<12:26:35,  8.02s/it]08/04/2024 09:56:25 - INFO - __main__ -   Step: 128, LR: 1.120656634746922e-07, Loss: 0.6767797470092773
2024-08-04T16:56:34.870750982Z 
  2%|▏         | 129/5712 [18:26<12:51:11,  8.29s/it]08/04/2024 09:56:34 - INFO - __main__ -   Step: 129, LR: 1.1294117647058823e-07, Loss: 0.6842948198318481
2024-08-04T16:56:42.904267278Z 
  2%|▏         | 130/5712 [18:34<12:43:57,  8.21s/it]08/04/2024 09:56:42 - INFO - __main__ -   Step: 130, LR: 1.1381668946648426e-07, Loss: 0.6790053844451904
2024-08-04T16:56:51.094973227Z 
  2%|▏         | 131/5712 [18:42<12:43:12,  8.21s/it]08/04/2024 09:56:51 - INFO - __main__ -   Step: 131, LR: 1.146922024623803e-07, Loss: 0.6689271926879883
2024-08-04T16:56:58.766212081Z 
  2%|▏         | 132/5712 [18:49<12:28:12,  8.05s/it]08/04/2024 09:56:58 - INFO - __main__ -   Step: 132, LR: 1.1556771545827633e-07, Loss: 0.6975531578063965
2024-08-04T16:57:06.462342589Z 
  2%|▏         | 133/5712 [18:57<12:18:20,  7.94s/it]08/04/2024 09:57:06 - INFO - __main__ -   Step: 133, LR: 1.1644322845417236e-07, Loss: 0.6876901388168335
2024-08-04T16:57:14.033035483Z 
  2%|▏         | 134/5712 [19:05<12:07:53,  7.83s/it]08/04/2024 09:57:14 - INFO - __main__ -   Step: 134, LR: 1.173187414500684e-07, Loss: 0.6711536645889282
2024-08-04T16:57:21.980077202Z 
  2%|▏         | 135/5712 [19:13<12:11:02,  7.86s/it]08/04/2024 09:57:21 - INFO - __main__ -   Step: 135, LR: 1.1819425444596442e-07, Loss: 0.7035913467407227
2024-08-04T16:57:30.656003587Z 
  2%|▏         | 136/5712 [19:21<12:33:31,  8.11s/it]08/04/2024 09:57:30 - INFO - __main__ -   Step: 136, LR: 1.1906976744186046e-07, Loss: 0.6839514970779419
2024-08-04T16:57:39.573354891Z 
  2%|▏         | 137/5712 [19:30<12:55:56,  8.35s/it]08/04/2024 09:57:39 - INFO - __main__ -   Step: 137, LR: 1.199452804377565e-07, Loss: 0.6693434715270996
2024-08-04T16:57:47.768413398Z 
  2%|▏         | 138/5712 [19:38<12:51:27,  8.30s/it]08/04/2024 09:57:47 - INFO - __main__ -   Step: 138, LR: 1.2082079343365253e-07, Loss: 0.7031826972961426
2024-08-04T16:57:55.384986434Z 
  2%|▏         | 139/5712 [19:46<12:32:09,  8.10s/it]08/04/2024 09:57:55 - INFO - __main__ -   Step: 139, LR: 1.2169630642954857e-07, Loss: 0.6542238593101501
2024-08-04T16:58:03.417877466Z 
  2%|▏         | 140/5712 [19:54<12:30:12,  8.08s/it]08/04/2024 09:58:03 - INFO - __main__ -   Step: 140, LR: 1.2257181942544458e-07, Loss: 0.6909189820289612
2024-08-04T16:58:10.955281718Z 
  2%|▏         | 141/5712 [20:02<12:15:00,  7.92s/it]08/04/2024 09:58:10 - INFO - __main__ -   Step: 141, LR: 1.2344733242134062e-07, Loss: 0.6944424510002136
2024-08-04T16:58:18.468846596Z 
  2%|▏         | 142/5712 [20:09<12:03:39,  7.80s/it]08/04/2024 09:58:18 - INFO - __main__ -   Step: 142, LR: 1.2432284541723667e-07, Loss: 0.6734872460365295
2024-08-04T16:58:26.463740871Z 
  3%|▎         | 143/5712 [20:17<12:09:04,  7.86s/it]08/04/2024 09:58:26 - INFO - __main__ -   Step: 143, LR: 1.251983584131327e-07, Loss: 0.693630576133728
2024-08-04T16:58:35.059141002Z 
  3%|▎         | 144/5712 [20:26<12:29:34,  8.08s/it]08/04/2024 09:58:35 - INFO - __main__ -   Step: 144, LR: 1.2607387140902872e-07, Loss: 0.6815298795700073
2024-08-04T16:58:43.498096134Z 
  3%|▎         | 145/5712 [20:34<12:39:30,  8.19s/it]08/04/2024 09:58:43 - INFO - __main__ -   Step: 145, LR: 1.2694938440492476e-07, Loss: 0.6672689914703369
2024-08-04T16:58:52.140852304Z 
  3%|▎         | 146/5712 [20:43<12:52:05,  8.32s/it]08/04/2024 09:58:52 - INFO - __main__ -   Step: 146, LR: 1.2782489740082077e-07, Loss: 0.6978909373283386
2024-08-04T16:59:00.107110287Z 
  3%|▎         | 147/5712 [20:51<12:42:01,  8.22s/it]08/04/2024 09:59:00 - INFO - __main__ -   Step: 147, LR: 1.2870041039671681e-07, Loss: 0.7107089757919312
2024-08-04T16:59:08.095861919Z 
  3%|▎         | 148/5712 [20:59<12:35:33,  8.15s/it]08/04/2024 09:59:08 - INFO - __main__ -   Step: 148, LR: 1.2957592339261285e-07, Loss: 0.6717308759689331
2024-08-04T16:59:15.554186219Z 
  3%|▎         | 149/5712 [21:06<12:16:15,  7.94s/it]08/04/2024 09:59:15 - INFO - __main__ -   Step: 149, LR: 1.304514363885089e-07, Loss: 0.6819839477539062
2024-08-04T16:59:23.049267075Z 
  3%|▎         | 150/5712 [21:14<12:03:43,  7.81s/it]08/04/2024 09:59:23 - INFO - __main__ -   Step: 150, LR: 1.313269493844049e-07, Loss: 0.6468344926834106
2024-08-04T16:59:30.574580429Z 
  3%|▎         | 151/5712 [21:21<11:55:45,  7.72s/it]08/04/2024 09:59:30 - INFO - __main__ -   Step: 151, LR: 1.3220246238030095e-07, Loss: 0.7094814777374268
2024-08-04T16:59:39.430676430Z 
  3%|▎         | 152/5712 [21:30<12:27:07,  8.06s/it]08/04/2024 09:59:39 - INFO - __main__ -   Step: 152, LR: 1.3307797537619696e-07, Loss: 0.6980386972427368
2024-08-04T16:59:48.206977825Z 
  3%|▎         | 153/5712 [21:39<12:46:50,  8.28s/it]08/04/2024 09:59:48 - INFO - __main__ -   Step: 153, LR: 1.3395348837209303e-07, Loss: 0.7051393985748291
2024-08-04T16:59:56.661819773Z 
  3%|▎         | 154/5712 [21:47<12:51:39,  8.33s/it]08/04/2024 09:59:56 - INFO - __main__ -   Step: 154, LR: 1.3482900136798904e-07, Loss: 0.6967036128044128
2024-08-04T17:00:04.685736008Z 
  3%|▎         | 155/5712 [21:55<12:43:00,  8.24s/it]08/04/2024 10:00:04 - INFO - __main__ -   Step: 155, LR: 1.3570451436388508e-07, Loss: 0.6760322451591492
2024-08-04T17:00:12.215966004Z 
  3%|▎         | 156/5712 [22:03<12:23:11,  8.03s/it]08/04/2024 10:00:12 - INFO - __main__ -   Step: 156, LR: 1.365800273597811e-07, Loss: 0.7142356634140015
2024-08-04T17:00:20.155388527Z 
  3%|▎         | 157/5712 [22:11<12:20:39,  8.00s/it]08/04/2024 10:00:20 - INFO - __main__ -   Step: 157, LR: 1.3745554035567714e-07, Loss: 0.6866841316223145
2024-08-04T17:00:28.075689096Z 
  3%|▎         | 158/5712 [22:19<12:18:18,  7.98s/it]08/04/2024 10:00:28 - INFO - __main__ -   Step: 158, LR: 1.3833105335157318e-07, Loss: 0.6419069170951843
2024-08-04T17:00:35.657219352Z 
  3%|▎         | 159/5712 [22:26<12:07:13,  7.86s/it]08/04/2024 10:00:35 - INFO - __main__ -   Step: 159, LR: 1.3920656634746922e-07, Loss: 0.6750102043151855
2024-08-04T17:00:44.160538747Z 
  3%|▎         | 160/5712 [22:35<12:25:00,  8.05s/it]08/04/2024 10:00:44 - INFO - __main__ -   Step: 160, LR: 1.4008207934336523e-07, Loss: 0.6628997325897217
2024-08-04T17:00:53.772491195Z 
  3%|▎         | 161/5712 [22:44<13:08:12,  8.52s/it]08/04/2024 10:00:53 - INFO - __main__ -   Step: 161, LR: 1.4095759233926127e-07, Loss: 0.6583162546157837
2024-08-04T17:01:01.972992324Z 
  3%|▎         | 162/5712 [22:53<12:59:11,  8.42s/it]08/04/2024 10:01:01 - INFO - __main__ -   Step: 162, LR: 1.4183310533515729e-07, Loss: 0.681057870388031
2024-08-04T17:01:10.322926022Z 
  3%|▎         | 163/5712 [23:01<12:57:00,  8.40s/it]08/04/2024 10:01:10 - INFO - __main__ -   Step: 163, LR: 1.4270861833105335e-07, Loss: 0.6666034460067749
2024-08-04T17:01:18.294500607Z 
  3%|▎         | 164/5712 [23:09<12:44:57,  8.27s/it]08/04/2024 10:01:18 - INFO - __main__ -   Step: 164, LR: 1.435841313269494e-07, Loss: 0.6562402248382568
2024-08-04T17:01:26.310046574Z 
  3%|▎         | 165/5712 [23:17<12:37:40,  8.20s/it]08/04/2024 10:01:26 - INFO - __main__ -   Step: 165, LR: 1.444596443228454e-07, Loss: 0.6873619556427002
2024-08-04T17:01:33.832662020Z 
  3%|▎         | 166/5712 [23:24<12:18:53,  7.99s/it]08/04/2024 10:01:33 - INFO - __main__ -   Step: 166, LR: 1.4533515731874145e-07, Loss: 0.6783313751220703
2024-08-04T17:01:41.461323150Z 
  3%|▎         | 167/5712 [23:32<12:08:37,  7.88s/it]08/04/2024 10:01:41 - INFO - __main__ -   Step: 167, LR: 1.4621067031463746e-07, Loss: 0.6754315495491028
2024-08-04T17:01:48.889057447Z 
  3%|▎         | 168/5712 [23:40<11:55:50,  7.75s/it]08/04/2024 10:01:48 - INFO - __main__ -   Step: 168, LR: 1.4708618331053353e-07, Loss: 0.6721370220184326
2024-08-04T17:01:58.345894484Z 
  3%|▎         | 169/5712 [23:49<12:43:05,  8.26s/it]08/04/2024 10:01:58 - INFO - __main__ -   Step: 169, LR: 1.4796169630642954e-07, Loss: 0.7065664529800415
2024-08-04T17:02:06.982898456Z 
  3%|▎         | 170/5712 [23:58<12:53:23,  8.37s/it]08/04/2024 10:02:06 - INFO - __main__ -   Step: 170, LR: 1.4883720930232558e-07, Loss: 0.6621653437614441
2024-08-04T17:02:15.582265132Z 
  3%|▎         | 171/5712 [24:06<12:59:31,  8.44s/it]08/04/2024 10:02:15 - INFO - __main__ -   Step: 171, LR: 1.497127222982216e-07, Loss: 0.7095898985862732
2024-08-04T17:02:23.679576224Z 
  3%|▎         | 172/5712 [24:14<12:49:52,  8.34s/it]08/04/2024 10:02:23 - INFO - __main__ -   Step: 172, LR: 1.5058823529411764e-07, Loss: 0.6608048677444458
2024-08-04T17:02:31.240050404Z 
  3%|▎         | 173/5712 [24:22<12:28:12,  8.10s/it]08/04/2024 10:02:31 - INFO - __main__ -   Step: 173, LR: 1.5146374829001368e-07, Loss: 0.6799863576889038
2024-08-04T17:02:39.220442430Z 
  3%|▎         | 174/5712 [24:30<12:24:37,  8.07s/it]08/04/2024 10:02:39 - INFO - __main__ -   Step: 174, LR: 1.5233926128590972e-07, Loss: 0.6497067213058472
2024-08-04T17:02:46.958962025Z 
  3%|▎         | 175/5712 [24:38<12:15:22,  7.97s/it]08/04/2024 10:02:46 - INFO - __main__ -   Step: 175, LR: 1.5321477428180573e-07, Loss: 0.6812635064125061
2024-08-04T17:02:54.513089779Z 
  3%|▎         | 176/5712 [24:45<12:03:45,  7.84s/it]08/04/2024 10:02:54 - INFO - __main__ -   Step: 176, LR: 1.5409028727770177e-07, Loss: 0.6523261070251465
2024-08-04T17:03:03.735825229Z 
  3%|▎         | 177/5712 [24:54<12:41:44,  8.26s/it]08/04/2024 10:03:03 - INFO - __main__ -   Step: 177, LR: 1.5496580027359778e-07, Loss: 0.6702193021774292
2024-08-04T17:03:12.249451372Z 
  3%|▎         | 178/5712 [25:03<12:48:44,  8.33s/it]08/04/2024 10:03:12 - INFO - __main__ -   Step: 178, LR: 1.5584131326949385e-07, Loss: 0.6569276452064514
2024-08-04T17:03:20.954202680Z 
  3%|▎         | 179/5712 [25:12<12:58:50,  8.45s/it]08/04/2024 10:03:20 - INFO - __main__ -   Step: 179, LR: 1.5671682626538987e-07, Loss: 0.662735104560852
2024-08-04T17:03:28.896839768Z 
  3%|▎         | 180/5712 [25:20<12:44:44,  8.29s/it]08/04/2024 10:03:28 - INFO - __main__ -   Step: 180, LR: 1.575923392612859e-07, Loss: 0.6552080512046814
2024-08-04T17:03:37.075464276Z 
  3%|▎         | 181/5712 [25:28<12:41:26,  8.26s/it]08/04/2024 10:03:37 - INFO - __main__ -   Step: 181, LR: 1.5846785225718192e-07, Loss: 0.6593239903450012
2024-08-04T17:03:44.986724399Z 
  3%|▎         | 182/5712 [25:36<12:31:39,  8.16s/it]08/04/2024 10:03:44 - INFO - __main__ -   Step: 182, LR: 1.5934336525307796e-07, Loss: 0.6410896182060242
2024-08-04T17:03:52.586605142Z 
  3%|▎         | 183/5712 [25:43<12:16:09,  7.99s/it]08/04/2024 10:03:52 - INFO - __main__ -   Step: 183, LR: 1.60218878248974e-07, Loss: 0.6826082468032837
2024-08-04T17:04:00.109827567Z 
  3%|▎         | 184/5712 [25:51<12:03:09,  7.85s/it]08/04/2024 10:04:00 - INFO - __main__ -   Step: 184, LR: 1.6109439124487004e-07, Loss: 0.6416610479354858
2024-08-04T17:04:08.607398417Z 
  3%|▎         | 185/5712 [25:59<12:20:57,  8.04s/it]08/04/2024 10:04:08 - INFO - __main__ -   Step: 185, LR: 1.6196990424076605e-07, Loss: 0.6653401255607605
2024-08-04T17:04:17.619839420Z 
  3%|▎         | 186/5712 [26:08<12:47:34,  8.33s/it]08/04/2024 10:04:17 - INFO - __main__ -   Step: 186, LR: 1.628454172366621e-07, Loss: 0.6655803918838501
2024-08-04T17:04:25.770927328Z 
  3%|▎         | 187/5712 [26:16<12:42:23,  8.28s/it]08/04/2024 10:04:25 - INFO - __main__ -   Step: 187, LR: 1.637209302325581e-07, Loss: 0.6652674078941345
2024-08-04T17:04:33.879336472Z 
  3%|▎         | 188/5712 [26:25<12:37:32,  8.23s/it]08/04/2024 10:04:33 - INFO - __main__ -   Step: 188, LR: 1.6459644322845418e-07, Loss: 0.6630035638809204
2024-08-04T17:04:41.767675196Z 
  3%|▎         | 189/5712 [26:32<12:28:00,  8.13s/it]08/04/2024 10:04:41 - INFO - __main__ -   Step: 189, LR: 1.654719562243502e-07, Loss: 0.6625496745109558
2024-08-04T17:04:49.384061147Z 
  3%|▎         | 190/5712 [26:40<12:13:48,  7.97s/it]08/04/2024 10:04:49 - INFO - __main__ -   Step: 190, LR: 1.6634746922024623e-07, Loss: 0.6828669309616089
2024-08-04T17:04:57.390374076Z 
  3%|▎         | 191/5712 [26:48<12:14:34,  7.98s/it]08/04/2024 10:04:57 - INFO - __main__ -   Step: 191, LR: 1.6722298221614224e-07, Loss: 0.6521304845809937
2024-08-04T17:05:04.892981812Z 
  3%|▎         | 192/5712 [26:56<12:01:11,  7.84s/it]08/04/2024 10:05:04 - INFO - __main__ -   Step: 192, LR: 1.6809849521203828e-07, Loss: 0.6624146699905396
2024-08-04T17:05:12.792560325Z 
  3%|▎         | 193/5712 [27:03<12:02:44,  7.86s/it]08/04/2024 10:05:12 - INFO - __main__ -   Step: 193, LR: 1.6897400820793435e-07, Loss: 0.6739829778671265
2024-08-04T17:05:21.873570787Z 
  3%|▎         | 194/5712 [27:13<12:36:20,  8.22s/it]08/04/2024 10:05:21 - INFO - __main__ -   Step: 194, LR: 1.6984952120383036e-07, Loss: 0.6723450422286987
2024-08-04T17:05:30.460608023Z 
  3%|▎         | 195/5712 [27:21<12:46:14,  8.33s/it]08/04/2024 10:05:30 - INFO - __main__ -   Step: 195, LR: 1.707250341997264e-07, Loss: 0.682575523853302
2024-08-04T17:05:38.841333324Z 
  3%|▎         | 196/5712 [27:29<12:47:24,  8.35s/it]08/04/2024 10:05:38 - INFO - __main__ -   Step: 196, LR: 1.7160054719562242e-07, Loss: 0.6739901900291443
2024-08-04T17:05:46.858404002Z 
  3%|▎         | 197/5712 [27:38<12:38:09,  8.25s/it]08/04/2024 10:05:46 - INFO - __main__ -   Step: 197, LR: 1.7247606019151846e-07, Loss: 0.6443328857421875
2024-08-04T17:05:54.752432434Z 
  3%|▎         | 198/5712 [27:45<12:28:15,  8.14s/it]08/04/2024 10:05:54 - INFO - __main__ -   Step: 198, LR: 1.733515731874145e-07, Loss: 0.659956693649292
2024-08-04T17:06:02.765552319Z 
  3%|▎         | 199/5712 [27:53<12:24:34,  8.10s/it]08/04/2024 10:06:02 - INFO - __main__ -   Step: 199, LR: 1.7422708618331054e-07, Loss: 0.6357108354568481
2024-08-04T17:06:10.275856686Z 
  4%|▎         | 200/5712 [28:01<12:08:04,  7.93s/it]08/04/2024 10:06:10 - INFO - __main__ -   Step: 200, LR: 1.7510259917920655e-07, Loss: 0.6244543790817261
2024-08-04T17:06:18.196379974Z 
  4%|▎         | 201/5712 [28:09<12:07:49,  7.92s/it]08/04/2024 10:06:18 - INFO - __main__ -   Step: 201, LR: 1.759781121751026e-07, Loss: 0.6528332233428955
2024-08-04T17:06:27.143539124Z 
  4%|▎         | 202/5712 [28:18<12:35:52,  8.23s/it]08/04/2024 10:06:27 - INFO - __main__ -   Step: 202, LR: 1.768536251709986e-07, Loss: 0.6691132187843323
2024-08-04T17:06:36.449530506Z 
  4%|▎         | 203/5712 [28:27<13:05:21,  8.55s/it]08/04/2024 10:06:36 - INFO - __main__ -   Step: 203, LR: 1.7772913816689467e-07, Loss: 0.674875020980835
2024-08-04T17:06:44.508157291Z 
  4%|▎         | 204/5712 [28:35<12:51:34,  8.41s/it]08/04/2024 10:06:44 - INFO - __main__ -   Step: 204, LR: 1.786046511627907e-07, Loss: 0.6318355798721313
2024-08-04T17:06:52.651609186Z 
  4%|▎         | 205/5712 [28:43<12:44:14,  8.33s/it]08/04/2024 10:06:52 - INFO - __main__ -   Step: 205, LR: 1.7948016415868673e-07, Loss: 0.6591941118240356
2024-08-04T17:07:00.704201297Z 
  4%|▎         | 206/5712 [28:51<12:36:33,  8.24s/it]08/04/2024 10:07:00 - INFO - __main__ -   Step: 206, LR: 1.8035567715458274e-07, Loss: 0.6695451140403748
2024-08-04T17:07:08.289798575Z 
  4%|▎         | 207/5712 [28:59<12:18:17,  8.05s/it]08/04/2024 10:07:08 - INFO - __main__ -   Step: 207, LR: 1.8123119015047878e-07, Loss: 0.6681997776031494
2024-08-04T17:07:16.272793013Z 
  4%|▎         | 208/5712 [29:07<12:16:24,  8.03s/it]08/04/2024 10:07:16 - INFO - __main__ -   Step: 208, LR: 1.8210670314637482e-07, Loss: 0.6574568152427673
2024-08-04T17:07:24.366501758Z 
  4%|▎         | 209/5712 [29:15<12:18:04,  8.05s/it]08/04/2024 10:07:24 - INFO - __main__ -   Step: 209, LR: 1.8298221614227086e-07, Loss: 0.6413398385047913
2024-08-04T17:07:33.065221010Z 
  4%|▎         | 210/5712 [29:24<12:35:52,  8.24s/it]08/04/2024 10:07:33 - INFO - __main__ -   Step: 210, LR: 1.8385772913816688e-07, Loss: 0.6610806584358215
2024-08-04T17:07:42.453980255Z 
  4%|▎         | 211/5712 [29:33<13:07:12,  8.59s/it]08/04/2024 10:07:42 - INFO - __main__ -   Step: 211, LR: 1.8473324213406292e-07, Loss: 0.6755111217498779
2024-08-04T17:07:50.769798941Z 
  4%|▎         | 212/5712 [29:41<12:59:40,  8.51s/it]08/04/2024 10:07:50 - INFO - __main__ -   Step: 212, LR: 1.8560875512995893e-07, Loss: 0.6384110450744629
2024-08-04T17:07:59.357056479Z 
  4%|▎         | 213/5712 [29:50<13:01:46,  8.53s/it]08/04/2024 10:07:59 - INFO - __main__ -   Step: 213, LR: 1.86484268125855e-07, Loss: 0.6334303617477417
2024-08-04T17:08:06.899345828Z 
  4%|▎         | 214/5712 [29:58<12:34:28,  8.23s/it]08/04/2024 10:08:06 - INFO - __main__ -   Step: 214, LR: 1.87359781121751e-07, Loss: 0.6094685792922974
2024-08-04T17:08:14.927305602Z 
  4%|▍         | 215/5712 [30:06<12:28:41,  8.17s/it]08/04/2024 10:08:14 - INFO - __main__ -   Step: 215, LR: 1.8823529411764705e-07, Loss: 0.6650073528289795
2024-08-04T17:08:22.859850339Z 
  4%|▍         | 216/5712 [30:14<12:21:58,  8.10s/it]08/04/2024 10:08:22 - INFO - __main__ -   Step: 216, LR: 1.8911080711354307e-07, Loss: 0.6512043476104736
2024-08-04T17:08:30.510569068Z 
  4%|▍         | 217/5712 [30:21<12:09:29,  7.97s/it]08/04/2024 10:08:30 - INFO - __main__ -   Step: 217, LR: 1.899863201094391e-07, Loss: 0.6537736654281616
2024-08-04T17:08:38.918850805Z 
  4%|▍         | 218/5712 [30:30<12:21:31,  8.10s/it]08/04/2024 10:08:38 - INFO - __main__ -   Step: 218, LR: 1.9086183310533515e-07, Loss: 0.6882860064506531
2024-08-04T17:08:47.844293983Z 
  4%|▍         | 219/5712 [30:38<12:44:06,  8.35s/it]08/04/2024 10:08:47 - INFO - __main__ -   Step: 219, LR: 1.9173734610123119e-07, Loss: 0.6537848711013794
2024-08-04T17:08:56.677656216Z 
  4%|▍         | 220/5712 [30:47<12:57:20,  8.49s/it]08/04/2024 10:08:56 - INFO - __main__ -   Step: 220, LR: 1.926128590971272e-07, Loss: 0.6421684622764587
2024-08-04T17:09:04.673728127Z 
  4%|▍         | 221/5712 [30:55<12:43:34,  8.34s/it]08/04/2024 10:09:04 - INFO - __main__ -   Step: 221, LR: 1.9348837209302324e-07, Loss: 0.6430364847183228
2024-08-04T17:09:12.815455332Z 
  4%|▍         | 222/5712 [31:03<12:37:53,  8.28s/it]08/04/2024 10:09:12 - INFO - __main__ -   Step: 222, LR: 1.9436388508891925e-07, Loss: 0.6480622291564941
2024-08-04T17:09:20.944568247Z 
  4%|▍         | 223/5712 [31:12<12:33:32,  8.24s/it]08/04/2024 10:09:20 - INFO - __main__ -   Step: 223, LR: 1.9523939808481532e-07, Loss: 0.6460071802139282
2024-08-04T17:09:28.531124115Z 
  4%|▍         | 224/5712 [31:19<12:15:33,  8.04s/it]08/04/2024 10:09:28 - INFO - __main__ -   Step: 224, LR: 1.9611491108071134e-07, Loss: 0.6644529104232788
2024-08-04T17:09:36.515113741Z 
  4%|▍         | 225/5712 [31:27<12:13:50,  8.02s/it]08/04/2024 10:09:36 - INFO - __main__ -   Step: 225, LR: 1.9699042407660738e-07, Loss: 0.6398574709892273
2024-08-04T17:09:44.463841412Z 
  4%|▍         | 226/5712 [31:35<12:11:37,  8.00s/it]08/04/2024 10:09:44 - INFO - __main__ -   Step: 226, LR: 1.9786593707250342e-07, Loss: 0.6724584102630615
2024-08-04T17:09:53.321927192Z 
  4%|▍         | 227/5712 [31:44<12:34:58,  8.26s/it]08/04/2024 10:09:53 - INFO - __main__ -   Step: 227, LR: 1.9874145006839943e-07, Loss: 0.6608750820159912
2024-08-04T17:10:02.330637799Z 
  4%|▍         | 228/5712 [31:53<12:55:23,  8.48s/it]08/04/2024 10:10:02 - INFO - __main__ -   Step: 228, LR: 1.996169630642955e-07, Loss: 0.6376351714134216
2024-08-04T17:10:11.156559146Z 
  4%|▍         | 229/5712 [32:02<13:04:38,  8.59s/it]08/04/2024 10:10:11 - INFO - __main__ -   Step: 229, LR: 2.004924760601915e-07, Loss: 0.639093279838562
2024-08-04T17:10:19.107735093Z 
  4%|▍         | 230/5712 [32:10<12:47:05,  8.40s/it]08/04/2024 10:10:19 - INFO - __main__ -   Step: 230, LR: 2.0136798905608755e-07, Loss: 0.668329119682312
2024-08-04T17:10:26.615237511Z 
  4%|▍         | 231/5712 [32:17<12:22:36,  8.13s/it]08/04/2024 10:10:26 - INFO - __main__ -   Step: 231, LR: 2.0224350205198356e-07, Loss: 0.6387492418289185
2024-08-04T17:10:34.568019683Z 
  4%|▍         | 232/5712 [32:25<12:17:38,  8.08s/it]08/04/2024 10:10:34 - INFO - __main__ -   Step: 232, LR: 2.0311901504787963e-07, Loss: 0.6230341196060181
2024-08-04T17:10:42.596497438Z 
  4%|▍         | 233/5712 [32:33<12:16:11,  8.06s/it]08/04/2024 10:10:42 - INFO - __main__ -   Step: 233, LR: 2.0399452804377565e-07, Loss: 0.6499825119972229
2024-08-04T17:10:50.485681302Z 
  4%|▍         | 234/5712 [32:41<12:11:20,  8.01s/it]08/04/2024 10:10:50 - INFO - __main__ -   Step: 234, LR: 2.0487004103967169e-07, Loss: 0.6407041549682617
2024-08-04T17:10:59.539495193Z 
  4%|▍         | 235/5712 [32:50<12:39:45,  8.32s/it]08/04/2024 10:10:59 - INFO - __main__ -   Step: 235, LR: 2.057455540355677e-07, Loss: 0.6656381487846375
2024-08-04T17:11:08.392318430Z 
  4%|▍         | 236/5712 [32:59<12:54:08,  8.48s/it]08/04/2024 10:11:08 - INFO - __main__ -   Step: 236, LR: 2.0662106703146374e-07, Loss: 0.6400535106658936
2024-08-04T17:11:17.245297722Z 
  4%|▍         | 237/5712 [33:08<13:04:08,  8.59s/it]08/04/2024 10:11:17 - INFO - __main__ -   Step: 237, LR: 2.0749658002735978e-07, Loss: 0.6458084583282471
2024-08-04T17:11:25.880014921Z 
  4%|▍         | 238/5712 [33:17<13:05:07,  8.61s/it]08/04/2024 10:11:25 - INFO - __main__ -   Step: 238, LR: 2.0837209302325582e-07, Loss: 0.6117351055145264
2024-08-04T17:11:33.407604801Z 
  4%|▍         | 239/5712 [33:24<12:35:29,  8.28s/it]08/04/2024 10:11:33 - INFO - __main__ -   Step: 239, LR: 2.0924760601915183e-07, Loss: 0.6504044532775879
2024-08-04T17:11:41.435285459Z 
  4%|▍         | 240/5712 [33:32<12:28:22,  8.21s/it]08/04/2024 10:11:41 - INFO - __main__ -   Step: 240, LR: 2.1012311901504787e-07, Loss: 0.6741126179695129
2024-08-04T17:11:48.952526293Z 
  4%|▍         | 241/5712 [33:40<12:09:24,  8.00s/it]08/04/2024 10:11:48 - INFO - __main__ -   Step: 241, LR: 2.109986320109439e-07, Loss: 0.6062808036804199
2024-08-04T17:11:57.079148222Z 
  4%|▍         | 242/5712 [33:48<12:12:44,  8.04s/it]08/04/2024 10:11:57 - INFO - __main__ -   Step: 242, LR: 2.1187414500683995e-07, Loss: 0.6977329254150391
2024-08-04T17:12:06.034228719Z 
  4%|▍         | 243/5712 [33:57<12:37:42,  8.31s/it]08/04/2024 10:12:06 - INFO - __main__ -   Step: 243, LR: 2.1274965800273597e-07, Loss: 0.6313938498497009
2024-08-04T17:12:14.744678687Z 
  4%|▍         | 244/5712 [34:05<12:48:26,  8.43s/it]08/04/2024 10:12:14 - INFO - __main__ -   Step: 244, LR: 2.13625170998632e-07, Loss: 0.6267253160476685
2024-08-04T17:12:23.428977719Z 
  4%|▍         | 245/5712 [34:14<12:55:11,  8.51s/it]08/04/2024 10:12:23 - INFO - __main__ -   Step: 245, LR: 2.1450068399452802e-07, Loss: 0.6889384984970093
2024-08-04T17:12:31.849754261Z 
  4%|▍         | 246/5712 [34:22<12:52:41,  8.48s/it]08/04/2024 10:12:31 - INFO - __main__ -   Step: 246, LR: 2.1537619699042406e-07, Loss: 0.6702325940132141
2024-08-04T17:12:39.306553837Z 
  4%|▍         | 247/5712 [34:30<12:24:32,  8.17s/it]08/04/2024 10:12:39 - INFO - __main__ -   Step: 247, LR: 2.162517099863201e-07, Loss: 0.6444345116615295
2024-08-04T17:12:46.897962949Z 
  4%|▍         | 248/5712 [34:38<12:08:28,  8.00s/it]08/04/2024 10:12:46 - INFO - __main__ -   Step: 248, LR: 2.1712722298221614e-07, Loss: 0.6305333375930786
2024-08-04T17:12:54.870564493Z 
  4%|▍         | 249/5712 [34:46<12:07:36,  7.99s/it]08/04/2024 10:12:54 - INFO - __main__ -   Step: 249, LR: 2.1800273597811216e-07, Loss: 0.6478406190872192
2024-08-04T17:13:03.076275773Z 
  4%|▍         | 250/5712 [34:54<12:13:19,  8.06s/it]08/04/2024 10:13:03 - INFO - __main__ -   Step: 250, LR: 2.188782489740082e-07, Loss: 0.6559675931930542
2024-08-04T17:13:12.056488171Z 
  4%|▍         | 251/5712 [35:03<12:38:26,  8.33s/it]08/04/2024 10:13:12 - INFO - __main__ -   Step: 251, LR: 2.197537619699042e-07, Loss: 0.6159484386444092
2024-08-04T17:13:21.034243200Z 
  4%|▍         | 252/5712 [35:12<12:55:54,  8.53s/it]08/04/2024 10:13:21 - INFO - __main__ -   Step: 252, LR: 2.2062927496580028e-07, Loss: 0.6698729395866394
2024-08-04T17:13:29.854216700Z 
  4%|▍         | 253/5712 [35:21<13:03:46,  8.61s/it]08/04/2024 10:13:29 - INFO - __main__ -   Step: 253, LR: 2.215047879616963e-07, Loss: 0.5787590742111206
2024-08-04T17:13:38.510779590Z 
  4%|▍         | 254/5712 [35:29<13:04:46,  8.63s/it]08/04/2024 10:13:38 - INFO - __main__ -   Step: 254, LR: 2.2238030095759233e-07, Loss: 0.6775997877120972
2024-08-04T17:13:46.505685671Z 
  4%|▍         | 255/5712 [35:37<12:47:23,  8.44s/it]08/04/2024 10:13:46 - INFO - __main__ -   Step: 255, LR: 2.2325581395348835e-07, Loss: 0.6037108898162842
2024-08-04T17:13:54.221596008Z 
  4%|▍         | 256/5712 [35:45<12:27:33,  8.22s/it]08/04/2024 10:13:54 - INFO - __main__ -   Step: 256, LR: 2.241313269493844e-07, Loss: 0.6290242671966553
2024-08-04T17:14:02.300233943Z 
  4%|▍         | 257/5712 [35:53<12:23:32,  8.18s/it]08/04/2024 10:14:02 - INFO - __main__ -   Step: 257, LR: 2.2500683994528045e-07, Loss: 0.6170969009399414
2024-08-04T17:14:10.743774808Z 
  5%|▍         | 258/5712 [36:01<12:30:37,  8.26s/it]08/04/2024 10:14:10 - INFO - __main__ -   Step: 258, LR: 2.2588235294117647e-07, Loss: 0.7331872582435608
2024-08-04T17:14:19.520781073Z 
  5%|▍         | 259/5712 [36:10<12:44:38,  8.41s/it]08/04/2024 10:14:19 - INFO - __main__ -   Step: 259, LR: 2.267578659370725e-07, Loss: 0.6558274626731873
2024-08-04T17:14:27.855326197Z 
  5%|▍         | 260/5712 [36:19<12:42:21,  8.39s/it]08/04/2024 10:14:27 - INFO - __main__ -   Step: 260, LR: 2.2763337893296852e-07, Loss: 0.6144145727157593
2024-08-04T17:14:36.640269330Z 
  5%|▍         | 261/5712 [36:27<12:52:59,  8.51s/it]08/04/2024 10:14:36 - INFO - __main__ -   Step: 261, LR: 2.2850889192886456e-07, Loss: 0.6345334649085999
2024-08-04T17:14:44.994136189Z 
  5%|▍         | 262/5712 [36:36<12:48:37,  8.46s/it]08/04/2024 10:14:44 - INFO - __main__ -   Step: 262, LR: 2.293844049247606e-07, Loss: 0.6236155033111572
2024-08-04T17:14:53.147036078Z 
  5%|▍         | 263/5712 [36:44<12:40:04,  8.37s/it]08/04/2024 10:14:53 - INFO - __main__ -   Step: 263, LR: 2.3025991792065664e-07, Loss: 0.6441893577575684
2024-08-04T17:15:00.830276318Z 
  5%|▍         | 264/5712 [36:51<12:21:14,  8.16s/it]08/04/2024 10:15:00 - INFO - __main__ -   Step: 264, LR: 2.3113543091655266e-07, Loss: 0.6530382633209229
2024-08-04T17:15:08.439319229Z 
  5%|▍         | 265/5712 [36:59<12:06:00,  8.00s/it]08/04/2024 10:15:08 - INFO - __main__ -   Step: 265, LR: 2.320109439124487e-07, Loss: 0.6099665760993958
2024-08-04T17:15:16.601908643Z 
  5%|▍         | 266/5712 [37:07<12:10:22,  8.05s/it]08/04/2024 10:15:16 - INFO - __main__ -   Step: 266, LR: 2.328864569083447e-07, Loss: 0.6396051049232483
2024-08-04T17:15:25.638721132Z 
  5%|▍         | 267/5712 [37:16<12:37:11,  8.34s/it]08/04/2024 10:15:25 - INFO - __main__ -   Step: 267, LR: 2.3376196990424078e-07, Loss: 0.6322764158248901
2024-08-04T17:15:34.978239222Z 
  5%|▍         | 268/5712 [37:26<13:04:10,  8.64s/it]08/04/2024 10:15:34 - INFO - __main__ -   Step: 268, LR: 2.346374829001368e-07, Loss: 0.5881327390670776
2024-08-04T17:15:43.774645745Z 
  5%|▍         | 269/5712 [37:34<13:08:13,  8.69s/it]08/04/2024 10:15:43 - INFO - __main__ -   Step: 269, LR: 2.3551299589603283e-07, Loss: 0.5959327220916748
2024-08-04T17:15:52.797125071Z 
  5%|▍         | 270/5712 [37:43<13:17:09,  8.79s/it]08/04/2024 10:15:52 - INFO - __main__ -   Step: 270, LR: 2.3638850889192885e-07, Loss: 0.6219760775566101
2024-08-04T17:16:00.739898043Z 
  5%|▍         | 271/5712 [37:51<12:53:58,  8.53s/it]08/04/2024 10:16:00 - INFO - __main__ -   Step: 271, LR: 2.3726402188782489e-07, Loss: 0.669735312461853
2024-08-04T17:16:08.725684725Z 
  5%|▍         | 272/5712 [37:59<12:38:54,  8.37s/it]08/04/2024 10:16:08 - INFO - __main__ -   Step: 272, LR: 2.3813953488372093e-07, Loss: 0.6111117601394653
2024-08-04T17:16:16.360705248Z 
  5%|▍         | 273/5712 [38:07<12:18:46,  8.15s/it]08/04/2024 10:16:16 - INFO - __main__ -   Step: 273, LR: 2.3901504787961694e-07, Loss: 0.7274156808853149
2024-08-04T17:16:24.326188140Z 
  5%|▍         | 274/5712 [38:15<12:13:37,  8.09s/it]08/04/2024 10:16:24 - INFO - __main__ -   Step: 274, LR: 2.39890560875513e-07, Loss: 0.6497503519058228
2024-08-04T17:16:32.615814609Z 
  5%|▍         | 275/5712 [38:23<12:18:47,  8.15s/it]08/04/2024 10:16:32 - INFO - __main__ -   Step: 275, LR: 2.40766073871409e-07, Loss: 0.6043383479118347
2024-08-04T17:16:41.256850068Z 
  5%|▍         | 276/5712 [38:32<12:31:55,  8.30s/it]08/04/2024 10:16:41 - INFO - __main__ -   Step: 276, LR: 2.4164158686730506e-07, Loss: 0.652144193649292
2024-08-04T17:16:50.382241436Z 
  5%|▍         | 277/5712 [38:41<12:54:13,  8.55s/it]08/04/2024 10:16:50 - INFO - __main__ -   Step: 277, LR: 2.425170998632011e-07, Loss: 0.6392334699630737
2024-08-04T17:16:59.273000527Z 
  5%|▍         | 278/5712 [38:50<13:03:25,  8.65s/it]08/04/2024 10:16:59 - INFO - __main__ -   Step: 278, LR: 2.4339261285909714e-07, Loss: 0.6121575832366943
2024-08-04T17:17:07.595978665Z 
  5%|▍         | 279/5712 [38:58<12:54:23,  8.55s/it]08/04/2024 10:17:07 - INFO - __main__ -   Step: 279, LR: 2.4426812585499313e-07, Loss: 0.7043060064315796
2024-08-04T17:17:15.730721588Z 
  5%|▍         | 280/5712 [39:06<12:42:54,  8.43s/it]08/04/2024 10:17:15 - INFO - __main__ -   Step: 280, LR: 2.4514363885088917e-07, Loss: 0.6112699508666992
2024-08-04T17:17:23.272218408Z 
  5%|▍         | 281/5712 [39:14<12:18:43,  8.16s/it]08/04/2024 10:17:23 - INFO - __main__ -   Step: 281, LR: 2.460191518467852e-07, Loss: 0.6301665902137756
2024-08-04T17:17:30.830001635Z 
  5%|▍         | 282/5712 [39:21<12:02:12,  7.98s/it]08/04/2024 10:17:30 - INFO - __main__ -   Step: 282, LR: 2.4689466484268125e-07, Loss: 0.6184279322624207
2024-08-04T17:17:38.986807651Z 
  5%|▍         | 283/5712 [39:30<12:06:52,  8.03s/it]08/04/2024 10:17:38 - INFO - __main__ -   Step: 283, LR: 2.477701778385773e-07, Loss: 0.6893959641456604
2024-08-04T17:17:47.270779564Z 
  5%|▍         | 284/5712 [39:38<12:13:32,  8.11s/it]08/04/2024 10:17:47 - INFO - __main__ -   Step: 284, LR: 2.4864569083447333e-07, Loss: 0.617872953414917
2024-08-04T17:17:56.618954863Z 
  5%|▍         | 285/5712 [39:47<12:47:03,  8.48s/it]08/04/2024 10:17:56 - INFO - __main__ -   Step: 285, LR: 2.495212038303693e-07, Loss: 0.645554780960083
2024-08-04T17:18:05.344339688Z 
  5%|▌         | 286/5712 [39:56<12:53:33,  8.55s/it]08/04/2024 10:18:05 - INFO - __main__ -   Step: 286, LR: 2.503967168262654e-07, Loss: 0.6014817953109741
2024-08-04T17:18:13.772736230Z 
  5%|▌         | 287/5712 [40:04<12:50:01,  8.52s/it]08/04/2024 10:18:13 - INFO - __main__ -   Step: 287, LR: 2.512722298221614e-07, Loss: 0.621751070022583
2024-08-04T17:18:21.797389654Z 
  5%|▌         | 288/5712 [40:12<12:36:32,  8.37s/it]08/04/2024 10:18:21 - INFO - __main__ -   Step: 288, LR: 2.5214774281805744e-07, Loss: 0.6819450259208679
2024-08-04T17:18:29.827210295Z 
  5%|▌         | 289/5712 [40:20<12:27:12,  8.27s/it]08/04/2024 10:18:29 - INFO - __main__ -   Step: 289, LR: 2.530232558139534e-07, Loss: 0.6585075855255127
2024-08-04T17:18:37.590857688Z 
  5%|▌         | 290/5712 [40:28<12:13:24,  8.12s/it]08/04/2024 10:18:37 - INFO - __main__ -   Step: 290, LR: 2.538987688098495e-07, Loss: 0.5998355150222778
2024-08-04T17:18:45.744153671Z 
  5%|▌         | 291/5712 [40:36<12:14:18,  8.13s/it]08/04/2024 10:18:45 - INFO - __main__ -   Step: 291, LR: 2.5477428180574556e-07, Loss: 0.6087421178817749
2024-08-04T17:18:53.960765458Z 
  5%|▌         | 292/5712 [40:45<12:16:35,  8.15s/it]08/04/2024 10:18:53 - INFO - __main__ -   Step: 292, LR: 2.5564979480164155e-07, Loss: 0.6170691251754761
2024-08-04T17:19:02.521789265Z 
  5%|▌         | 293/5712 [40:53<12:27:27,  8.28s/it]08/04/2024 10:19:02 - INFO - __main__ -   Step: 293, LR: 2.5652530779753764e-07, Loss: 0.6229382753372192
2024-08-04T17:19:12.004082988Z 
  5%|▌         | 294/5712 [41:03<13:00:00,  8.64s/it]08/04/2024 10:19:12 - INFO - __main__ -   Step: 294, LR: 2.5740082079343363e-07, Loss: 0.6527327299118042
2024-08-04T17:19:20.317334453Z 
  5%|▌         | 295/5712 [41:11<12:51:04,  8.54s/it]08/04/2024 10:19:20 - INFO - __main__ -   Step: 295, LR: 2.5827633378932967e-07, Loss: 0.5699528455734253
2024-08-04T17:19:28.350534371Z 
  5%|▌         | 296/5712 [41:19<12:37:11,  8.39s/it]08/04/2024 10:19:28 - INFO - __main__ -   Step: 296, LR: 2.591518467852257e-07, Loss: 0.6812020540237427
2024-08-04T17:19:36.719226421Z 
  5%|▌         | 297/5712 [41:27<12:36:31,  8.38s/it]08/04/2024 10:19:36 - INFO - __main__ -   Step: 297, LR: 2.6002735978112175e-07, Loss: 0.6024580001831055
2024-08-04T17:19:44.418040609Z 
  5%|▌         | 298/5712 [41:35<12:17:52,  8.18s/it]08/04/2024 10:19:44 - INFO - __main__ -   Step: 298, LR: 2.609028727770178e-07, Loss: 0.651381254196167
2024-08-04T17:19:52.693035665Z 
  5%|▌         | 299/5712 [41:43<12:20:22,  8.21s/it]08/04/2024 10:19:52 - INFO - __main__ -   Step: 299, LR: 2.617783857729138e-07, Loss: 0.6282674074172974
2024-08-04T17:20:00.781936300Z 
  5%|▌         | 300/5712 [41:51<12:17:03,  8.17s/it]08/04/2024 10:20:00 - INFO - __main__ -   Step: 300, LR: 2.626538987688098e-07, Loss: 0.6393052935600281
2024-08-04T17:20:09.776273714Z 
  5%|▌         | 301/5712 [42:00<12:39:11,  8.42s/it]08/04/2024 10:20:09 - INFO - __main__ -   Step: 301, LR: 2.635294117647059e-07, Loss: 0.6473251581192017
2024-08-04T17:20:18.910835247Z 
  5%|▌         | 302/5712 [42:10<12:58:25,  8.63s/it]08/04/2024 10:20:18 - INFO - __main__ -   Step: 302, LR: 2.644049247606019e-07, Loss: 0.6011437177658081
2024-08-04T17:20:27.707505568Z 
  5%|▌         | 303/5712 [42:18<13:02:42,  8.68s/it]08/04/2024 10:20:27 - INFO - __main__ -   Step: 303, LR: 2.6528043775649794e-07, Loss: 0.6068853139877319
2024-08-04T17:20:35.726261493Z 
  5%|▌         | 304/5712 [42:26<12:44:36,  8.48s/it]08/04/2024 10:20:35 - INFO - __main__ -   Step: 304, LR: 2.661559507523939e-07, Loss: 0.6202523708343506
2024-08-04T17:20:43.709338529Z 
  5%|▌         | 305/5712 [42:34<12:30:57,  8.33s/it]08/04/2024 10:20:43 - INFO - __main__ -   Step: 305, LR: 2.6703146374829e-07, Loss: 0.5581561923027039
2024-08-04T17:20:51.598240980Z 
  5%|▌         | 306/5712 [42:42<12:18:48,  8.20s/it]08/04/2024 10:20:51 - INFO - __main__ -   Step: 306, LR: 2.6790697674418606e-07, Loss: 0.6318768858909607
2024-08-04T17:20:59.497884956Z 
  5%|▌         | 307/5712 [42:50<12:10:32,  8.11s/it]08/04/2024 10:20:59 - INFO - __main__ -   Step: 307, LR: 2.6878248974008205e-07, Loss: 0.6429945230484009
2024-08-04T17:21:08.050842399Z 
  5%|▌         | 308/5712 [42:59<12:22:23,  8.24s/it]08/04/2024 10:21:08 - INFO - __main__ -   Step: 308, LR: 2.696580027359781e-07, Loss: 0.5495636463165283
2024-08-04T17:21:16.996858235Z 
  5%|▌         | 309/5712 [43:08<12:41:15,  8.45s/it]08/04/2024 10:21:16 - INFO - __main__ -   Step: 309, LR: 2.705335157318741e-07, Loss: 0.5749790668487549
2024-08-04T17:21:26.459634327Z 
  5%|▌         | 310/5712 [43:17<13:08:22,  8.76s/it]08/04/2024 10:21:26 - INFO - __main__ -   Step: 310, LR: 2.7140902872777017e-07, Loss: 0.5997415781021118
2024-08-04T17:21:35.393505787Z 
  5%|▌         | 311/5712 [43:26<13:13:01,  8.81s/it]08/04/2024 10:21:35 - INFO - __main__ -   Step: 311, LR: 2.722845417236662e-07, Loss: 0.5998690128326416
2024-08-04T17:21:43.910888755Z 
  5%|▌         | 312/5712 [43:35<13:04:59,  8.72s/it]08/04/2024 10:21:43 - INFO - __main__ -   Step: 312, LR: 2.731600547195622e-07, Loss: 0.6140714883804321
2024-08-04T17:21:52.269980180Z 
  5%|▌         | 313/5712 [43:43<12:55:02,  8.61s/it]08/04/2024 10:21:52 - INFO - __main__ -   Step: 313, LR: 2.740355677154583e-07, Loss: 0.6304718255996704
2024-08-04T17:22:00.740245038Z 
  5%|▌         | 314/5712 [43:51<12:51:02,  8.57s/it]08/04/2024 10:22:00 - INFO - __main__ -   Step: 314, LR: 2.749110807113543e-07, Loss: 0.5259747505187988
2024-08-04T17:22:08.237174669Z 
  6%|▌         | 315/5712 [43:59<12:21:56,  8.25s/it]08/04/2024 10:22:08 - INFO - __main__ -   Step: 315, LR: 2.757865937072503e-07, Loss: 0.6122989654541016
2024-08-04T17:22:16.344090533Z 
  6%|▌         | 316/5712 [44:07<12:17:58,  8.21s/it]08/04/2024 10:22:16 - INFO - __main__ -   Step: 316, LR: 2.7666210670314636e-07, Loss: 0.6197820901870728
2024-08-04T17:22:24.779624124Z 
  6%|▌         | 317/5712 [44:15<12:24:02,  8.27s/it]08/04/2024 10:22:24 - INFO - __main__ -   Step: 317, LR: 2.775376196990424e-07, Loss: 0.6755844354629517
2024-08-04T17:22:34.349639419Z 
  6%|▌         | 318/5712 [44:25<12:58:49,  8.66s/it]08/04/2024 10:22:34 - INFO - __main__ -   Step: 318, LR: 2.7841313269493844e-07, Loss: 0.6117295622825623
2024-08-04T17:22:43.739643610Z 
  6%|▌         | 319/5712 [44:34<13:18:16,  8.88s/it]08/04/2024 10:22:43 - INFO - __main__ -   Step: 319, LR: 2.792886456908344e-07, Loss: 0.6611512303352356
2024-08-04T17:22:52.593045143Z 
  6%|▌         | 320/5712 [44:43<13:17:22,  8.87s/it]08/04/2024 10:22:52 - INFO - __main__ -   Step: 320, LR: 2.8016415868673046e-07, Loss: 0.6712731719017029
2024-08-04T17:23:00.551033644Z 
  6%|▌         | 321/5712 [44:51<12:52:34,  8.60s/it]08/04/2024 10:23:00 - INFO - __main__ -   Step: 321, LR: 2.8103967168262656e-07, Loss: 0.5846683382987976
2024-08-04T17:23:08.491039385Z 
  6%|▌         | 322/5712 [44:59<12:34:41,  8.40s/it]08/04/2024 10:23:08 - INFO - __main__ -   Step: 322, LR: 2.8191518467852254e-07, Loss: 0.6088007688522339
2024-08-04T17:23:16.542055791Z 
  6%|▌         | 323/5712 [45:07<12:25:06,  8.30s/it]08/04/2024 10:23:16 - INFO - __main__ -   Step: 323, LR: 2.827906976744186e-07, Loss: 0.5446698069572449
2024-08-04T17:23:24.513256160Z 
  6%|▌         | 324/5712 [45:15<12:16:13,  8.20s/it]08/04/2024 10:23:24 - INFO - __main__ -   Step: 324, LR: 2.8366621067031457e-07, Loss: 0.6263322830200195
2024-08-04T17:23:33.205312069Z 
  6%|▌         | 325/5712 [45:24<12:29:23,  8.35s/it]08/04/2024 10:23:33 - INFO - __main__ -   Step: 325, LR: 2.8454172366621067e-07, Loss: 0.545507550239563
2024-08-04T17:23:41.215151232Z 
  6%|▌         | 326/5712 [45:32<12:20:10,  8.25s/it]08/04/2024 10:23:41 - INFO - __main__ -   Step: 326, LR: 2.854172366621067e-07, Loss: 0.5552341938018799
2024-08-04T17:23:49.704795075Z 
  6%|▌         | 327/5712 [45:40<12:26:36,  8.32s/it]08/04/2024 10:23:49 - INFO - __main__ -   Step: 327, LR: 2.862927496580027e-07, Loss: 0.6381044387817383
2024-08-04T17:23:58.554914116Z 
  6%|▌         | 328/5712 [45:49<12:40:46,  8.48s/it]08/04/2024 10:23:58 - INFO - __main__ -   Step: 328, LR: 2.871682626538988e-07, Loss: 0.6160397529602051
2024-08-04T17:24:07.459041045Z 
  6%|▌         | 329/5712 [45:58<12:52:05,  8.61s/it]08/04/2024 10:24:07 - INFO - __main__ -   Step: 329, LR: 2.880437756497948e-07, Loss: 0.5985705256462097
2024-08-04T17:24:15.537881538Z 
  6%|▌         | 330/5712 [46:06<12:37:46,  8.45s/it]08/04/2024 10:24:15 - INFO - __main__ -   Step: 330, LR: 2.889192886456908e-07, Loss: 0.6260056495666504
2024-08-04T17:24:23.555121414Z 
  6%|▌         | 331/5712 [46:14<12:26:02,  8.32s/it]08/04/2024 10:24:23 - INFO - __main__ -   Step: 331, LR: 2.8979480164158685e-07, Loss: 0.6211012601852417
2024-08-04T17:24:31.495528017Z 
  6%|▌         | 332/5712 [46:22<12:15:43,  8.21s/it]08/04/2024 10:24:31 - INFO - __main__ -   Step: 332, LR: 2.906703146374829e-07, Loss: 0.6493300199508667
2024-08-04T17:24:39.987000131Z 
  6%|▌         | 333/5712 [46:31<12:23:17,  8.29s/it]08/04/2024 10:24:39 - INFO - __main__ -   Step: 333, LR: 2.9154582763337893e-07, Loss: 0.6066188812255859
2024-08-04T17:24:48.866276573Z 
  6%|▌         | 334/5712 [46:40<12:38:58,  8.47s/it]08/04/2024 10:24:48 - INFO - __main__ -   Step: 334, LR: 2.924213406292749e-07, Loss: 0.5767585039138794
2024-08-04T17:24:57.499646438Z 
  6%|▌         | 335/5712 [46:48<12:43:17,  8.52s/it]08/04/2024 10:24:57 - INFO - __main__ -   Step: 335, LR: 2.9329685362517096e-07, Loss: 0.6389949917793274
2024-08-04T17:25:06.147059879Z 
  6%|▌         | 336/5712 [46:57<12:46:38,  8.56s/it]08/04/2024 10:25:06 - INFO - __main__ -   Step: 336, LR: 2.9417236662106706e-07, Loss: 0.6233342885971069
2024-08-04T17:25:14.975807667Z 
  6%|▌         | 337/5712 [47:06<12:53:49,  8.64s/it]08/04/2024 10:25:14 - INFO - __main__ -   Step: 337, LR: 2.9504787961696304e-07, Loss: 0.6507999897003174
2024-08-04T17:25:23.352484278Z 
  6%|▌         | 338/5712 [47:14<12:46:39,  8.56s/it]08/04/2024 10:25:23 - INFO - __main__ -   Step: 338, LR: 2.959233926128591e-07, Loss: 0.6802621483802795
2024-08-04T17:25:30.988112122Z 
  6%|▌         | 339/5712 [47:22<12:21:41,  8.28s/it]08/04/2024 10:25:30 - INFO - __main__ -   Step: 339, LR: 2.9679890560875507e-07, Loss: 0.5918662548065186
2024-08-04T17:25:39.039823343Z 
  6%|▌         | 340/5712 [47:30<12:15:21,  8.21s/it]08/04/2024 10:25:39 - INFO - __main__ -   Step: 340, LR: 2.9767441860465116e-07, Loss: 0.5658769011497498
2024-08-04T17:25:47.339242307Z 
  6%|▌         | 341/5712 [47:38<12:17:31,  8.24s/it]08/04/2024 10:25:47 - INFO - __main__ -   Step: 341, LR: 2.985499316005472e-07, Loss: 0.5726871490478516
2024-08-04T17:25:56.614926321Z 
  6%|▌         | 342/5712 [47:47<12:45:13,  8.55s/it]08/04/2024 10:25:56 - INFO - __main__ -   Step: 342, LR: 2.994254445964432e-07, Loss: 0.6644267439842224
2024-08-04T17:26:05.397340944Z 
  6%|▌         | 343/5712 [47:56<12:51:19,  8.62s/it]08/04/2024 10:26:05 - INFO - __main__ -   Step: 343, LR: 3.0030095759233923e-07, Loss: 0.6282673478126526
2024-08-04T17:26:14.057245948Z 
  6%|▌         | 344/5712 [48:05<12:52:15,  8.63s/it]08/04/2024 10:26:14 - INFO - __main__ -   Step: 344, LR: 3.0117647058823527e-07, Loss: 0.6321090459823608
2024-08-04T17:26:22.448659177Z 
  6%|▌         | 345/5712 [48:13<12:45:39,  8.56s/it]08/04/2024 10:26:22 - INFO - __main__ -   Step: 345, LR: 3.020519835841313e-07, Loss: 0.5992746949195862
2024-08-04T17:26:30.478043165Z 
  6%|▌         | 346/5712 [48:21<12:31:17,  8.40s/it]08/04/2024 10:26:30 - INFO - __main__ -   Step: 346, LR: 3.0292749658002735e-07, Loss: 0.6612647771835327
2024-08-04T17:26:38.549540846Z 
  6%|▌         | 347/5712 [48:29<12:22:19,  8.30s/it]08/04/2024 10:26:38 - INFO - __main__ -   Step: 347, LR: 3.0380300957592334e-07, Loss: 0.5749658346176147
2024-08-04T17:26:46.526036470Z 
  6%|▌         | 348/5712 [48:37<12:13:27,  8.20s/it]08/04/2024 10:26:46 - INFO - __main__ -   Step: 348, LR: 3.0467852257181943e-07, Loss: 0.5654072761535645
2024-08-04T17:26:54.697140796Z 
  6%|▌         | 349/5712 [48:45<12:12:26,  8.19s/it]08/04/2024 10:26:54 - INFO - __main__ -   Step: 349, LR: 3.055540355677154e-07, Loss: 0.5587066411972046
2024-08-04T17:27:04.179008814Z 
  6%|▌         | 350/5712 [48:55<12:46:49,  8.58s/it]08/04/2024 10:27:04 - INFO - __main__ -   Step: 350, LR: 3.0642954856361146e-07, Loss: 0.559892475605011
2024-08-04T17:27:12.834844982Z 
  6%|▌         | 351/5712 [49:03<12:48:41,  8.60s/it]08/04/2024 10:27:12 - INFO - __main__ -   Step: 351, LR: 3.073050615595075e-07, Loss: 0.6369308233261108
2024-08-04T17:27:21.423366851Z 
  6%|▌         | 352/5712 [49:12<12:48:09,  8.60s/it]08/04/2024 10:27:21 - INFO - __main__ -   Step: 352, LR: 3.0818057455540354e-07, Loss: 0.6376659870147705
2024-08-04T17:27:30.269437903Z 
  6%|▌         | 353/5712 [49:21<12:54:38,  8.67s/it]08/04/2024 10:27:30 - INFO - __main__ -   Step: 353, LR: 3.090560875512996e-07, Loss: 0.6070417165756226
2024-08-04T17:27:38.619296690Z 
  6%|▌         | 354/5712 [49:29<12:45:50,  8.58s/it]08/04/2024 10:27:38 - INFO - __main__ -   Step: 354, LR: 3.0993160054719557e-07, Loss: 0.5562454462051392
2024-08-04T17:27:46.845224722Z 
  6%|▌         | 355/5712 [49:37<12:36:19,  8.47s/it]08/04/2024 10:27:46 - INFO - __main__ -   Step: 355, LR: 3.1080711354309166e-07, Loss: 0.6071668267250061
2024-08-04T17:27:54.468346930Z 
  6%|▌         | 356/5712 [49:45<12:13:28,  8.22s/it]08/04/2024 10:27:54 - INFO - __main__ -   Step: 356, LR: 3.116826265389877e-07, Loss: 0.6684145927429199
2024-08-04T17:28:03.042874871Z 
  6%|▋         | 357/5712 [49:54<12:22:55,  8.32s/it]08/04/2024 10:28:03 - INFO - __main__ -   Step: 357, LR: 3.125581395348837e-07, Loss: 0.5855952501296997
2024-08-04T17:28:11.023042280Z 
  6%|▋         | 358/5712 [50:02<12:13:34,  8.22s/it]08/04/2024 10:28:11 - INFO - __main__ -   Step: 358, LR: 3.1343365253077973e-07, Loss: 0.6416953206062317
2024-08-04T17:28:19.410239823Z 
  6%|▋         | 359/5712 [50:10<12:17:53,  8.27s/it]08/04/2024 10:28:19 - INFO - __main__ -   Step: 359, LR: 3.1430916552667577e-07, Loss: 0.5287169218063354
2024-08-04T17:28:28.159700751Z 
  6%|▋         | 360/5712 [50:19<12:30:33,  8.41s/it]08/04/2024 10:28:28 - INFO - __main__ -   Step: 360, LR: 3.151846785225718e-07, Loss: 0.5169386863708496
2024-08-04T17:28:36.946675111Z 
  6%|▋         | 361/5712 [50:28<12:40:23,  8.53s/it]08/04/2024 10:28:36 - INFO - __main__ -   Step: 361, LR: 3.1606019151846785e-07, Loss: 0.5686642527580261
2024-08-04T17:28:45.194080751Z 
  6%|▋         | 362/5712 [50:36<12:32:47,  8.44s/it]08/04/2024 10:28:45 - INFO - __main__ -   Step: 362, LR: 3.1693570451436384e-07, Loss: 0.5721920728683472
2024-08-04T17:28:53.477205884Z 
  6%|▋         | 363/5712 [50:44<12:28:23,  8.39s/it]08/04/2024 10:28:53 - INFO - __main__ -   Step: 363, LR: 3.1781121751025993e-07, Loss: 0.5714517831802368
2024-08-04T17:29:01.654110026Z 
  6%|▋         | 364/5712 [50:52<12:22:24,  8.33s/it]08/04/2024 10:29:01 - INFO - __main__ -   Step: 364, LR: 3.186867305061559e-07, Loss: 0.5533840656280518
2024-08-04T17:29:09.843289879Z 
  6%|▋         | 365/5712 [51:00<12:18:32,  8.29s/it]08/04/2024 10:29:09 - INFO - __main__ -   Step: 365, LR: 3.1956224350205196e-07, Loss: 0.6589789390563965
2024-08-04T17:29:17.961680942Z 
  6%|▋         | 366/5712 [51:09<12:13:53,  8.24s/it]08/04/2024 10:29:17 - INFO - __main__ -   Step: 366, LR: 3.20437756497948e-07, Loss: 0.5610512495040894
2024-08-04T17:29:26.770449665Z 
  6%|▋         | 367/5712 [51:17<12:29:01,  8.41s/it]08/04/2024 10:29:26 - INFO - __main__ -   Step: 367, LR: 3.2131326949384404e-07, Loss: 0.5728433728218079
2024-08-04T17:29:35.611862533Z 
  6%|▋         | 368/5712 [51:26<12:40:28,  8.54s/it]08/04/2024 10:29:35 - INFO - __main__ -   Step: 368, LR: 3.221887824897401e-07, Loss: 0.6275687217712402
2024-08-04T17:29:44.148524457Z 
  6%|▋         | 369/5712 [51:35<12:40:17,  8.54s/it]08/04/2024 10:29:44 - INFO - __main__ -   Step: 369, LR: 3.2306429548563607e-07, Loss: 0.6488229036331177
2024-08-04T17:29:53.014544314Z 
  6%|▋         | 370/5712 [51:44<12:48:54,  8.64s/it]08/04/2024 10:29:53 - INFO - __main__ -   Step: 370, LR: 3.239398084815321e-07, Loss: 0.6554884910583496
2024-08-04T17:30:01.388852108Z 
  6%|▋         | 371/5712 [51:52<12:41:46,  8.56s/it]08/04/2024 10:30:01 - INFO - __main__ -   Step: 371, LR: 3.248153214774282e-07, Loss: 0.5215347409248352
2024-08-04T17:30:09.562206058Z 
  7%|▋         | 372/5712 [52:00<12:31:21,  8.44s/it]08/04/2024 10:30:09 - INFO - __main__ -   Step: 372, LR: 3.256908344733242e-07, Loss: 0.6813233494758606
2024-08-04T17:30:17.443804345Z 
  7%|▋         | 373/5712 [52:08<12:16:15,  8.27s/it]08/04/2024 10:30:17 - INFO - __main__ -   Step: 373, LR: 3.2656634746922023e-07, Loss: 0.5963588953018188
2024-08-04T17:30:26.401226731Z 
  7%|▋         | 374/5712 [52:17<12:34:21,  8.48s/it]08/04/2024 10:30:26 - INFO - __main__ -   Step: 374, LR: 3.274418604651162e-07, Loss: 0.6552149057388306
2024-08-04T17:30:34.302870555Z 
  7%|▋         | 375/5712 [52:25<12:18:48,  8.31s/it]08/04/2024 10:30:34 - INFO - __main__ -   Step: 375, LR: 3.283173734610123e-07, Loss: 0.5513943433761597
2024-08-04T17:30:43.110650633Z 
  7%|▋         | 376/5712 [52:34<12:32:03,  8.46s/it]08/04/2024 10:30:43 - INFO - __main__ -   Step: 376, LR: 3.2919288645690835e-07, Loss: 0.6530282497406006
2024-08-04T17:30:51.437609949Z 
  7%|▋         | 377/5712 [52:42<12:28:27,  8.42s/it]08/04/2024 10:30:51 - INFO - __main__ -   Step: 377, LR: 3.3006839945280434e-07, Loss: 0.5343688726425171
2024-08-04T17:30:59.718673148Z 
  7%|▋         | 378/5712 [52:50<12:24:41,  8.38s/it]08/04/2024 10:30:59 - INFO - __main__ -   Step: 378, LR: 3.309439124487004e-07, Loss: 0.6055119037628174
2024-08-04T17:31:08.036918047Z 
  7%|▋         | 379/5712 [52:59<12:22:58,  8.36s/it]08/04/2024 10:31:08 - INFO - __main__ -   Step: 379, LR: 3.318194254445964e-07, Loss: 0.5770817995071411
2024-08-04T17:31:16.158817026Z 
  7%|▋         | 380/5712 [53:07<12:16:31,  8.29s/it]08/04/2024 10:31:16 - INFO - __main__ -   Step: 380, LR: 3.3269493844049246e-07, Loss: 0.48357635736465454
2024-08-04T17:31:24.413637186Z 
  7%|▋         | 381/5712 [53:15<12:15:29,  8.28s/it]08/04/2024 10:31:24 - INFO - __main__ -   Step: 381, LR: 3.335704514363885e-07, Loss: 0.5978053212165833
2024-08-04T17:31:32.645240602Z 
  7%|▋         | 382/5712 [53:23<12:14:07,  8.26s/it]08/04/2024 10:31:32 - INFO - __main__ -   Step: 382, LR: 3.344459644322845e-07, Loss: 0.516957700252533
2024-08-04T17:31:40.983607896Z 
  7%|▋         | 383/5712 [53:32<12:15:58,  8.29s/it]08/04/2024 10:31:40 - INFO - __main__ -   Step: 383, LR: 3.353214774281806e-07, Loss: 0.5920391082763672
2024-08-04T17:31:49.537359526Z 
  7%|▋         | 384/5712 [53:40<12:22:57,  8.37s/it]08/04/2024 10:31:49 - INFO - __main__ -   Step: 384, LR: 3.3619699042407657e-07, Loss: 0.5845319628715515
2024-08-04T17:31:58.042881750Z 
  7%|▋         | 385/5712 [53:49<12:26:30,  8.41s/it]08/04/2024 10:31:58 - INFO - __main__ -   Step: 385, LR: 3.370725034199726e-07, Loss: 0.5553535223007202
2024-08-04T17:32:06.960709454Z 
  7%|▋         | 386/5712 [53:58<12:39:56,  8.56s/it]08/04/2024 10:32:06 - INFO - __main__ -   Step: 386, LR: 3.379480164158687e-07, Loss: 0.5847832560539246
2024-08-04T17:32:14.883045882Z 
  7%|▋         | 387/5712 [54:06<12:22:47,  8.37s/it]08/04/2024 10:32:14 - INFO - __main__ -   Step: 387, LR: 3.388235294117647e-07, Loss: 0.5695603489875793
2024-08-04T17:32:23.487015626Z 
  7%|▋         | 388/5712 [54:14<12:28:54,  8.44s/it]08/04/2024 10:32:23 - INFO - __main__ -   Step: 388, LR: 3.3969904240766073e-07, Loss: 0.5486071109771729
2024-08-04T17:32:31.936488036Z 
  7%|▋         | 389/5712 [54:23<12:29:00,  8.44s/it]08/04/2024 10:32:31 - INFO - __main__ -   Step: 389, LR: 3.405745554035567e-07, Loss: 0.6061396598815918
2024-08-04T17:32:39.895705742Z 
  7%|▋         | 390/5712 [54:31<12:16:00,  8.30s/it]08/04/2024 10:32:39 - INFO - __main__ -   Step: 390, LR: 3.414500683994528e-07, Loss: 0.6123651266098022
2024-08-04T17:32:48.229828962Z 
  7%|▋         | 391/5712 [54:39<12:16:50,  8.31s/it]08/04/2024 10:32:48 - INFO - __main__ -   Step: 391, LR: 3.4232558139534885e-07, Loss: 0.6575480699539185
2024-08-04T17:32:56.357817787Z 
  7%|▋         | 392/5712 [54:47<12:11:54,  8.25s/it]08/04/2024 10:32:56 - INFO - __main__ -   Step: 392, LR: 3.4320109439124484e-07, Loss: 0.570633053779602
2024-08-04T17:33:05.278967018Z 
  7%|▋         | 393/5712 [54:56<12:29:29,  8.45s/it]08/04/2024 10:33:05 - INFO - __main__ -   Step: 393, LR: 3.440766073871409e-07, Loss: 0.5470979809761047
2024-08-04T17:33:13.716521591Z 
  7%|▋         | 394/5712 [55:04<12:28:53,  8.45s/it]08/04/2024 10:33:13 - INFO - __main__ -   Step: 394, LR: 3.449521203830369e-07, Loss: 0.5942845344543457
2024-08-04T17:33:22.310889417Z 
  7%|▋         | 395/5712 [55:13<12:32:36,  8.49s/it]08/04/2024 10:33:22 - INFO - __main__ -   Step: 395, LR: 3.4582763337893296e-07, Loss: 0.5349084734916687
2024-08-04T17:33:30.540675801Z 
  7%|▋         | 396/5712 [55:21<12:25:28,  8.41s/it]08/04/2024 10:33:30 - INFO - __main__ -   Step: 396, LR: 3.46703146374829e-07, Loss: 0.5416029691696167
2024-08-04T17:33:38.650167518Z 
  7%|▋         | 397/5712 [55:29<12:17:14,  8.32s/it]08/04/2024 10:33:38 - INFO - __main__ -   Step: 397, LR: 3.47578659370725e-07, Loss: 0.6365228295326233
2024-08-04T17:33:47.064657980Z 
  7%|▋         | 398/5712 [55:38<12:19:32,  8.35s/it]08/04/2024 10:33:47 - INFO - __main__ -   Step: 398, LR: 3.484541723666211e-07, Loss: 0.6054985523223877
2024-08-04T17:33:55.928947122Z 
  7%|▋         | 399/5712 [55:47<12:33:01,  8.50s/it]08/04/2024 10:33:55 - INFO - __main__ -   Step: 399, LR: 3.4932968536251707e-07, Loss: 0.6217980980873108
2024-08-04T17:34:04.501176670Z 
  7%|▋         | 400/5712 [55:55<12:34:44,  8.52s/it]08/04/2024 10:34:04 - INFO - __main__ -   Step: 400, LR: 3.502051983584131e-07, Loss: 0.5853691697120667
2024-08-04T17:34:12.909423322Z 
  7%|▋         | 401/5712 [56:04<12:31:30,  8.49s/it]08/04/2024 10:34:12 - INFO - __main__ -   Step: 401, LR: 3.5108071135430915e-07, Loss: 0.6150942444801331
2024-08-04T17:34:21.342835315Z 
  7%|▋         | 402/5712 [56:12<12:29:51,  8.47s/it]08/04/2024 10:34:21 - INFO - __main__ -   Step: 402, LR: 3.519562243502052e-07, Loss: 0.6067512035369873
2024-08-04T17:34:29.803654116Z 
  7%|▋         | 403/5712 [56:20<12:29:23,  8.47s/it]08/04/2024 10:34:29 - INFO - __main__ -   Step: 403, LR: 3.5283173734610123e-07, Loss: 0.5781203508377075
2024-08-04T17:34:38.034226997Z 
  7%|▋         | 404/5712 [56:29<12:22:55,  8.40s/it]08/04/2024 10:34:38 - INFO - __main__ -   Step: 404, LR: 3.537072503419972e-07, Loss: 0.5873045921325684
2024-08-04T17:34:45.985122331Z 
  7%|▋         | 405/5712 [56:37<12:10:55,  8.26s/it]08/04/2024 10:34:45 - INFO - __main__ -   Step: 405, LR: 3.5458276333789325e-07, Loss: 0.5233588814735413
2024-08-04T17:34:54.767097580Z 
  7%|▋         | 406/5712 [56:45<12:24:31,  8.42s/it]08/04/2024 10:34:54 - INFO - __main__ -   Step: 406, LR: 3.5545827633378935e-07, Loss: 0.5998693704605103
2024-08-04T17:35:02.854766062Z 
  7%|▋         | 407/5712 [56:54<12:15:35,  8.32s/it]08/04/2024 10:35:02 - INFO - __main__ -   Step: 407, LR: 3.5633378932968534e-07, Loss: 0.5365880727767944
2024-08-04T17:35:11.026291092Z 
  7%|▋         | 408/5712 [57:02<12:11:32,  8.28s/it]08/04/2024 10:35:11 - INFO - __main__ -   Step: 408, LR: 3.572093023255814e-07, Loss: 0.6813592910766602
2024-08-04T17:35:19.850704486Z 
  7%|▋         | 409/5712 [57:10<12:25:57,  8.44s/it]08/04/2024 10:35:19 - INFO - __main__ -   Step: 409, LR: 3.5808481532147736e-07, Loss: 0.6053766012191772
2024-08-04T17:35:28.202784375Z 
  7%|▋         | 410/5712 [57:19<12:23:29,  8.41s/it]08/04/2024 10:35:28 - INFO - __main__ -   Step: 410, LR: 3.5896032831737346e-07, Loss: 0.6175495982170105
2024-08-04T17:35:36.345153054Z 
  7%|▋         | 411/5712 [57:27<12:16:09,  8.33s/it]08/04/2024 10:35:36 - INFO - __main__ -   Step: 411, LR: 3.598358413132695e-07, Loss: 0.5280817747116089
2024-08-04T17:35:44.933896150Z 
  7%|▋         | 412/5712 [57:36<12:22:48,  8.41s/it]08/04/2024 10:35:44 - INFO - __main__ -   Step: 412, LR: 3.607113543091655e-07, Loss: 0.5837525129318237
2024-08-04T17:35:52.969487702Z 
  7%|▋         | 413/5712 [57:44<12:12:46,  8.30s/it]08/04/2024 10:35:52 - INFO - __main__ -   Step: 413, LR: 3.615868673050615e-07, Loss: 0.499787837266922
2024-08-04T17:36:01.189694408Z 
  7%|▋         | 414/5712 [57:52<12:10:36,  8.27s/it]08/04/2024 10:36:01 - INFO - __main__ -   Step: 414, LR: 3.6246238030095756e-07, Loss: 0.5318899154663086
2024-08-04T17:36:09.306867584Z 
  7%|▋         | 415/5712 [58:00<12:06:17,  8.23s/it]08/04/2024 10:36:09 - INFO - __main__ -   Step: 415, LR: 3.633378932968536e-07, Loss: 0.5810859203338623
2024-08-04T17:36:17.940263019Z 
  7%|▋         | 416/5712 [58:09<12:16:56,  8.35s/it]08/04/2024 10:36:17 - INFO - __main__ -   Step: 416, LR: 3.6421340629274965e-07, Loss: 0.6619487404823303
2024-08-04T17:36:26.574344674Z 
  7%|▋         | 417/5712 [58:17<12:24:20,  8.43s/it]08/04/2024 10:36:26 - INFO - __main__ -   Step: 417, LR: 3.6508891928864563e-07, Loss: 0.5748171806335449
2024-08-04T17:36:35.036983372Z 
  7%|▋         | 418/5712 [58:26<12:24:56,  8.44s/it]08/04/2024 10:36:35 - INFO - __main__ -   Step: 418, LR: 3.659644322845417e-07, Loss: 0.5863271951675415
2024-08-04T17:36:43.483670365Z 
  7%|▋         | 419/5712 [58:34<12:24:54,  8.44s/it]08/04/2024 10:36:43 - INFO - __main__ -   Step: 419, LR: 3.668399452804377e-07, Loss: 0.6217329502105713
2024-08-04T17:36:51.518036397Z 
  7%|▋         | 420/5712 [58:42<12:13:55,  8.32s/it]08/04/2024 10:36:51 - INFO - __main__ -   Step: 420, LR: 3.6771545827633375e-07, Loss: 0.5417925119400024
2024-08-04T17:36:59.702917623Z 
  7%|▋         | 421/5712 [58:50<12:10:10,  8.28s/it]08/04/2024 10:36:59 - INFO - __main__ -   Step: 421, LR: 3.6859097127222985e-07, Loss: 0.5854254961013794
2024-08-04T17:37:08.124539057Z 
  7%|▋         | 422/5712 [58:59<12:13:47,  8.32s/it]08/04/2024 10:37:08 - INFO - __main__ -   Step: 422, LR: 3.6946648426812583e-07, Loss: 0.5479049682617188
2024-08-04T17:37:17.049482253Z 
  7%|▋         | 423/5712 [59:08<12:29:34,  8.50s/it]08/04/2024 10:37:17 - INFO - __main__ -   Step: 423, LR: 3.703419972640219e-07, Loss: 0.5832235813140869
2024-08-04T17:37:25.127857459Z 
  7%|▋         | 424/5712 [59:16<12:18:11,  8.38s/it]08/04/2024 10:37:25 - INFO - __main__ -   Step: 424, LR: 3.7121751025991786e-07, Loss: 0.5387109518051147
2024-08-04T17:37:33.368000313Z 
  7%|▋         | 425/5712 [59:24<12:14:28,  8.34s/it]08/04/2024 10:37:33 - INFO - __main__ -   Step: 425, LR: 3.7209302325581396e-07, Loss: 0.637285053730011
2024-08-04T17:37:41.798778657Z 
  7%|▋         | 426/5712 [59:32<12:16:51,  8.36s/it]08/04/2024 10:37:41 - INFO - __main__ -   Step: 426, LR: 3.7296853625171e-07, Loss: 0.5370264053344727
2024-08-04T17:37:50.060015875Z 
  7%|▋         | 427/5712 [59:41<12:14:00,  8.33s/it]08/04/2024 10:37:50 - INFO - __main__ -   Step: 427, LR: 3.73844049247606e-07, Loss: 0.6015068292617798
2024-08-04T17:37:57.640031830Z 
  7%|▋         | 428/5712 [59:48<11:53:57,  8.11s/it]08/04/2024 10:37:57 - INFO - __main__ -   Step: 428, LR: 3.74719562243502e-07, Loss: 0.6233503818511963
2024-08-04T17:38:06.331768901Z 
  8%|▊         | 429/5712 [59:57<12:09:15,  8.28s/it]08/04/2024 10:38:06 - INFO - __main__ -   Step: 429, LR: 3.7559507523939806e-07, Loss: 0.6335545182228088
2024-08-04T17:38:14.317695085Z 
  8%|▊         | 430/5712 [1:00:05<12:01:18,  8.19s/it]08/04/2024 10:38:14 - INFO - __main__ -   Step: 430, LR: 3.764705882352941e-07, Loss: 0.5271561741828918
2024-08-04T17:38:22.500477812Z 
  8%|▊         | 431/5712 [1:00:13<12:00:53,  8.19s/it]08/04/2024 10:38:22 - INFO - __main__ -   Step: 431, LR: 3.7734610123119014e-07, Loss: 0.5955733060836792
2024-08-04T17:38:30.921982051Z 
  8%|▊         | 432/5712 [1:00:22<12:06:51,  8.26s/it]08/04/2024 10:38:30 - INFO - __main__ -   Step: 432, LR: 3.7822161422708613e-07, Loss: 0.6113295555114746
2024-08-04T17:38:39.714809216Z 
  8%|▊         | 433/5712 [1:00:30<12:20:47,  8.42s/it]08/04/2024 10:38:39 - INFO - __main__ -   Step: 433, LR: 3.790971272229822e-07, Loss: 0.6628960371017456
2024-08-04T17:38:48.461085016Z 
  8%|▊         | 434/5712 [1:00:39<12:29:16,  8.52s/it]08/04/2024 10:38:48 - INFO - __main__ -   Step: 434, LR: 3.799726402188782e-07, Loss: 0.6000419855117798
2024-08-04T17:38:56.540641110Z 
  8%|▊         | 435/5712 [1:00:47<12:17:34,  8.39s/it]08/04/2024 10:38:56 - INFO - __main__ -   Step: 435, LR: 3.8084815321477425e-07, Loss: 0.4637824296951294
2024-08-04T17:39:04.787892702Z 
  8%|▊         | 436/5712 [1:00:55<12:13:45,  8.34s/it]08/04/2024 10:39:04 - INFO - __main__ -   Step: 436, LR: 3.817236662106703e-07, Loss: 0.5500996708869934
2024-08-04T17:39:13.218029618Z 
  8%|▊         | 437/5712 [1:01:04<12:15:52,  8.37s/it]08/04/2024 10:39:13 - INFO - __main__ -   Step: 437, LR: 3.8259917920656633e-07, Loss: 0.598339319229126
2024-08-04T17:39:21.796013577Z 
  8%|▊         | 438/5712 [1:01:12<12:21:13,  8.43s/it]08/04/2024 10:39:21 - INFO - __main__ -   Step: 438, LR: 3.8347469220246237e-07, Loss: 0.5708224773406982
2024-08-04T17:39:30.358125913Z 
  8%|▊         | 439/5712 [1:01:21<12:24:30,  8.47s/it]08/04/2024 10:39:30 - INFO - __main__ -   Step: 439, LR: 3.8435020519835836e-07, Loss: 0.6250839233398438
2024-08-04T17:39:38.371554082Z 
  8%|▊         | 440/5712 [1:01:29<12:12:16,  8.33s/it]08/04/2024 10:39:38 - INFO - __main__ -   Step: 440, LR: 3.852257181942544e-07, Loss: 0.5943103432655334
2024-08-04T17:39:46.917081776Z 
  8%|▊         | 441/5712 [1:01:38<12:17:43,  8.40s/it]08/04/2024 10:39:46 - INFO - __main__ -   Step: 441, LR: 3.861012311901505e-07, Loss: 0.5109086632728577
2024-08-04T17:39:56.046889015Z 
  8%|▊         | 442/5712 [1:01:47<12:36:51,  8.62s/it]08/04/2024 10:39:56 - INFO - __main__ -   Step: 442, LR: 3.869767441860465e-07, Loss: 0.5323296785354614
2024-08-04T17:40:05.308691467Z 
  8%|▊         | 443/5712 [1:01:56<12:53:43,  8.81s/it]08/04/2024 10:40:05 - INFO - __main__ -   Step: 443, LR: 3.878522571819425e-07, Loss: 0.5438330769538879
2024-08-04T17:40:13.672545201Z 
  8%|▊         | 444/5712 [1:02:04<12:41:47,  8.68s/it]08/04/2024 10:40:13 - INFO - __main__ -   Step: 444, LR: 3.887277701778385e-07, Loss: 0.5700883865356445
2024-08-04T17:40:21.710173711Z 
  8%|▊         | 445/5712 [1:02:12<12:24:49,  8.48s/it]08/04/2024 10:40:21 - INFO - __main__ -   Step: 445, LR: 3.896032831737346e-07, Loss: 0.5197506546974182
2024-08-04T17:40:30.265775203Z 
  8%|▊         | 446/5712 [1:02:21<12:26:32,  8.51s/it]08/04/2024 10:40:30 - INFO - __main__ -   Step: 446, LR: 3.9047879616963064e-07, Loss: 0.573807954788208
2024-08-04T17:40:38.433972000Z 
  8%|▊         | 447/5712 [1:02:29<12:17:31,  8.40s/it]08/04/2024 10:40:38 - INFO - __main__ -   Step: 447, LR: 3.9135430916552663e-07, Loss: 0.5396357774734497
2024-08-04T17:40:47.013447288Z 
  8%|▊         | 448/5712 [1:02:38<12:21:58,  8.46s/it]08/04/2024 10:40:47 - INFO - __main__ -   Step: 448, LR: 3.9222982216142267e-07, Loss: 0.6065584421157837
2024-08-04T17:40:55.246530472Z 
  8%|▊         | 449/5712 [1:02:46<12:15:56,  8.39s/it]08/04/2024 10:40:55 - INFO - __main__ -   Step: 449, LR: 3.931053351573187e-07, Loss: 0.5620909929275513
2024-08-04T17:41:03.669601445Z 
  8%|▊         | 450/5712 [1:02:54<12:16:40,  8.40s/it]08/04/2024 10:41:03 - INFO - __main__ -   Step: 450, LR: 3.9398084815321475e-07, Loss: 0.5433951020240784
2024-08-04T17:41:12.121248587Z 
  8%|▊         | 451/5712 [1:03:03<12:17:53,  8.42s/it]08/04/2024 10:41:12 - INFO - __main__ -   Step: 451, LR: 3.948563611491108e-07, Loss: 0.6693275570869446
2024-08-04T17:41:20.364717465Z 
  8%|▊         | 452/5712 [1:03:11<12:13:13,  8.36s/it]08/04/2024 10:41:20 - INFO - __main__ -   Step: 452, LR: 3.9573187414500683e-07, Loss: 0.5425653457641602
2024-08-04T17:41:28.388174890Z 
  8%|▊         | 453/5712 [1:03:19<12:04:08,  8.26s/it]08/04/2024 10:41:28 - INFO - __main__ -   Step: 453, LR: 3.9660738714090287e-07, Loss: 0.5960123538970947
2024-08-04T17:41:36.661052038Z 
  8%|▊         | 454/5712 [1:03:27<12:04:17,  8.27s/it]08/04/2024 10:41:36 - INFO - __main__ -   Step: 454, LR: 3.9748290013679886e-07, Loss: 0.6515630483627319
2024-08-04T17:41:45.602915720Z 
  8%|▊         | 455/5712 [1:03:36<12:21:56,  8.47s/it]08/04/2024 10:41:45 - INFO - __main__ -   Step: 455, LR: 3.983584131326949e-07, Loss: 0.560499906539917
2024-08-04T17:41:53.764789673Z 
  8%|▊         | 456/5712 [1:03:44<12:13:45,  8.38s/it]08/04/2024 10:41:53 - INFO - __main__ -   Step: 456, LR: 3.99233926128591e-07, Loss: 0.625413715839386
2024-08-04T17:42:01.695852693Z 
  8%|▊         | 457/5712 [1:03:52<12:01:54,  8.24s/it]08/04/2024 10:42:01 - INFO - __main__ -   Step: 457, LR: 4.00109439124487e-07, Loss: 0.6007075309753418
2024-08-04T17:42:10.406336418Z 
  8%|▊         | 458/5712 [1:04:01<12:14:04,  8.38s/it]08/04/2024 10:42:10 - INFO - __main__ -   Step: 458, LR: 4.00984952120383e-07, Loss: 0.5214465856552124
2024-08-04T17:42:18.896069225Z 
  8%|▊         | 459/5712 [1:04:10<12:16:44,  8.42s/it]08/04/2024 10:42:18 - INFO - __main__ -   Step: 459, LR: 4.0186046511627906e-07, Loss: 0.5879412293434143
2024-08-04T17:42:27.361998346Z 
  8%|▊         | 460/5712 [1:04:18<12:17:56,  8.43s/it]08/04/2024 10:42:27 - INFO - __main__ -   Step: 460, LR: 4.027359781121751e-07, Loss: 0.5647162199020386
2024-08-04T17:42:35.547227065Z 
  8%|▊         | 461/5712 [1:04:26<12:11:21,  8.36s/it]08/04/2024 10:42:35 - INFO - __main__ -   Step: 461, LR: 4.0361149110807114e-07, Loss: 0.5994489789009094
2024-08-04T17:42:43.572720480Z 
  8%|▊         | 462/5712 [1:04:34<12:02:31,  8.26s/it]08/04/2024 10:42:43 - INFO - __main__ -   Step: 462, LR: 4.0448700410396713e-07, Loss: 0.6092194318771362
2024-08-04T17:42:51.986425803Z 
  8%|▊         | 463/5712 [1:04:43<12:06:28,  8.30s/it]08/04/2024 10:42:51 - INFO - __main__ -   Step: 463, LR: 4.0536251709986317e-07, Loss: 0.5545706152915955
2024-08-04T17:43:00.162930434Z 
  8%|▊         | 464/5712 [1:04:51<12:02:59,  8.27s/it]08/04/2024 10:43:00 - INFO - __main__ -   Step: 464, LR: 4.0623803009575926e-07, Loss: 0.5754927396774292
2024-08-04T17:43:08.185806573Z 
  8%|▊         | 465/5712 [1:04:59<11:56:29,  8.19s/it]08/04/2024 10:43:08 - INFO - __main__ -   Step: 465, LR: 4.0711354309165525e-07, Loss: 0.4957253336906433
2024-08-04T17:43:16.699678077Z 
  8%|▊         | 466/5712 [1:05:07<12:04:45,  8.29s/it]08/04/2024 10:43:16 - INFO - __main__ -   Step: 466, LR: 4.079890560875513e-07, Loss: 0.5817158818244934
2024-08-04T17:43:25.315381314Z 
  8%|▊         | 467/5712 [1:05:16<12:13:10,  8.39s/it]08/04/2024 10:43:25 - INFO - __main__ -   Step: 467, LR: 4.088645690834473e-07, Loss: 0.6057398319244385
2024-08-04T17:43:33.859583341Z 
  8%|▊         | 468/5712 [1:05:25<12:17:09,  8.43s/it]08/04/2024 10:43:33 - INFO - __main__ -   Step: 468, LR: 4.0974008207934337e-07, Loss: 0.6315243244171143
2024-08-04T17:43:42.147291772Z 
  8%|▊         | 469/5712 [1:05:33<12:13:10,  8.39s/it]08/04/2024 10:43:42 - INFO - __main__ -   Step: 469, LR: 4.106155950752394e-07, Loss: 0.5905681848526001
2024-08-04T17:43:50.343540831Z 
  8%|▊         | 470/5712 [1:05:41<12:07:56,  8.33s/it]08/04/2024 10:43:50 - INFO - __main__ -   Step: 470, LR: 4.114911080711354e-07, Loss: 0.5690790414810181
2024-08-04T17:43:58.948827985Z 
  8%|▊         | 471/5712 [1:05:50<12:14:57,  8.41s/it]08/04/2024 10:43:58 - INFO - __main__ -   Step: 471, LR: 4.1236662106703144e-07, Loss: 0.49280694127082825
2024-08-04T17:44:07.794804805Z 
  8%|▊         | 472/5712 [1:05:58<12:26:08,  8.54s/it]08/04/2024 10:44:07 - INFO - __main__ -   Step: 472, LR: 4.132421340629275e-07, Loss: 0.5158249139785767
2024-08-04T17:44:15.831780691Z 
  8%|▊         | 473/5712 [1:06:06<12:12:44,  8.39s/it]08/04/2024 10:44:15 - INFO - __main__ -   Step: 473, LR: 4.141176470588235e-07, Loss: 0.6448664665222168
2024-08-04T17:44:24.203525688Z 
  8%|▊         | 474/5712 [1:06:15<12:12:04,  8.39s/it]08/04/2024 10:44:24 - INFO - __main__ -   Step: 474, LR: 4.1499316005471956e-07, Loss: 0.5739168524742126
2024-08-04T17:44:32.693253956Z 
  8%|▊         | 475/5712 [1:06:23<12:14:39,  8.42s/it]08/04/2024 10:44:32 - INFO - __main__ -   Step: 475, LR: 4.1586867305061555e-07, Loss: 0.5874791145324707
2024-08-04T17:44:41.128713619Z 
  8%|▊         | 476/5712 [1:06:32<12:14:59,  8.42s/it]08/04/2024 10:44:41 - INFO - __main__ -   Step: 476, LR: 4.1674418604651164e-07, Loss: 0.5684034824371338
2024-08-04T17:44:49.285580137Z 
  8%|▊         | 477/5712 [1:06:40<12:07:54,  8.34s/it]08/04/2024 10:44:49 - INFO - __main__ -   Step: 477, LR: 4.1761969904240763e-07, Loss: 0.5831961631774902
2024-08-04T17:44:57.621247216Z 
  8%|▊         | 478/5712 [1:06:48<12:07:34,  8.34s/it]08/04/2024 10:44:57 - INFO - __main__ -   Step: 478, LR: 4.1849521203830367e-07, Loss: 0.5815247297286987
2024-08-04T17:45:05.636051790Z 
  8%|▊         | 479/5712 [1:06:56<11:58:54,  8.24s/it]08/04/2024 10:45:05 - INFO - __main__ -   Step: 479, LR: 4.1937072503419976e-07, Loss: 0.608695387840271
2024-08-04T17:45:14.229336327Z 
  8%|▊         | 480/5712 [1:07:05<12:07:57,  8.35s/it]08/04/2024 10:45:14 - INFO - __main__ -   Step: 480, LR: 4.2024623803009575e-07, Loss: 0.49775683879852295
2024-08-04T17:45:22.559138321Z 
  8%|▊         | 481/5712 [1:07:13<12:07:20,  8.34s/it]08/04/2024 10:45:22 - INFO - __main__ -   Step: 481, LR: 4.211217510259918e-07, Loss: 0.546044111251831
2024-08-04T17:45:30.736844687Z 
  8%|▊         | 482/5712 [1:07:21<12:02:53,  8.29s/it]08/04/2024 10:45:30 - INFO - __main__ -   Step: 482, LR: 4.219972640218878e-07, Loss: 0.5973384976387024
2024-08-04T17:45:39.164834058Z 
  8%|▊         | 483/5712 [1:07:30<12:06:16,  8.33s/it]08/04/2024 10:45:39 - INFO - __main__ -   Step: 483, LR: 4.2287277701778387e-07, Loss: 0.47787803411483765
2024-08-04T17:45:47.888270711Z 
  8%|▊         | 484/5712 [1:07:39<12:16:19,  8.45s/it]08/04/2024 10:45:47 - INFO - __main__ -   Step: 484, LR: 4.237482900136799e-07, Loss: 0.6267262697219849
2024-08-04T17:45:55.999220856Z 
  8%|▊         | 485/5712 [1:07:47<12:07:18,  8.35s/it]08/04/2024 10:45:55 - INFO - __main__ -   Step: 485, LR: 4.246238030095759e-07, Loss: 0.5958272814750671
2024-08-04T17:46:04.411492949Z 
  9%|▊         | 486/5712 [1:07:55<12:08:49,  8.37s/it]08/04/2024 10:46:04 - INFO - __main__ -   Step: 486, LR: 4.2549931600547194e-07, Loss: 0.5667515993118286
2024-08-04T17:46:13.017506397Z 
  9%|▊         | 487/5712 [1:08:04<12:14:55,  8.44s/it]08/04/2024 10:46:13 - INFO - __main__ -   Step: 487, LR: 4.26374829001368e-07, Loss: 0.4889776110649109
2024-08-04T17:46:21.515711662Z 
  9%|▊         | 488/5712 [1:08:12<12:16:19,  8.46s/it]08/04/2024 10:46:21 - INFO - __main__ -   Step: 488, LR: 4.27250341997264e-07, Loss: 0.5762462615966797
2024-08-04T17:46:29.950224477Z 
  9%|▊         | 489/5712 [1:08:21<12:15:35,  8.45s/it]08/04/2024 10:46:29 - INFO - __main__ -   Step: 489, LR: 4.2812585499316006e-07, Loss: 0.5369495153427124
2024-08-04T17:46:38.641152291Z 
  9%|▊         | 490/5712 [1:08:29<12:21:44,  8.52s/it]08/04/2024 10:46:38 - INFO - __main__ -   Step: 490, LR: 4.2900136798905605e-07, Loss: 0.42719370126724243
2024-08-04T17:46:47.200956062Z 
  9%|▊         | 491/5712 [1:08:38<12:22:34,  8.53s/it]08/04/2024 10:46:47 - INFO - __main__ -   Step: 491, LR: 4.2987688098495214e-07, Loss: 0.5705822706222534
2024-08-04T17:46:56.711799378Z 
  9%|▊         | 492/5712 [1:08:47<12:47:55,  8.83s/it]08/04/2024 10:46:56 - INFO - __main__ -   Step: 492, LR: 4.307523939808481e-07, Loss: 0.5603460669517517
2024-08-04T17:47:04.728572030Z 
  9%|▊         | 493/5712 [1:08:55<12:26:38,  8.58s/it]08/04/2024 10:47:04 - INFO - __main__ -   Step: 493, LR: 4.3162790697674417e-07, Loss: 0.5228695869445801
2024-08-04T17:47:12.707698249Z 
  9%|▊         | 494/5712 [1:09:03<12:10:43,  8.40s/it]08/04/2024 10:47:12 - INFO - __main__ -   Step: 494, LR: 4.325034199726402e-07, Loss: 0.5481756925582886
2024-08-04T17:47:21.048002318Z 
  9%|▊         | 495/5712 [1:09:12<12:08:58,  8.38s/it]08/04/2024 10:47:21 - INFO - __main__ -   Step: 495, LR: 4.3337893296853625e-07, Loss: 0.5323742628097534
2024-08-04T17:47:29.419364947Z 
  9%|▊         | 496/5712 [1:09:20<12:08:30,  8.38s/it]08/04/2024 10:47:29 - INFO - __main__ -   Step: 496, LR: 4.342544459644323e-07, Loss: 0.5223963260650635
2024-08-04T17:47:38.222970162Z 
  9%|▊         | 497/5712 [1:09:29<12:19:24,  8.51s/it]08/04/2024 10:47:38 - INFO - __main__ -   Step: 497, LR: 4.351299589603283e-07, Loss: 0.4942034184932709
2024-08-04T17:47:46.476304435Z 
  9%|▊         | 498/5712 [1:09:37<12:12:39,  8.43s/it]08/04/2024 10:47:46 - INFO - __main__ -   Step: 498, LR: 4.360054719562243e-07, Loss: 0.6416777968406677
2024-08-04T17:47:54.958592714Z 
  9%|▊         | 499/5712 [1:09:46<12:13:51,  8.45s/it]08/04/2024 10:47:54 - INFO - __main__ -   Step: 499, LR: 4.368809849521204e-07, Loss: 0.5878140926361084
2024-08-04T17:48:03.845894493Z 
  9%|▉         | 500/5712 [1:09:54<12:25:12,  8.58s/it]08/04/2024 10:48:03 - INFO - __main__ -   Step: 500, LR: 4.377564979480164e-07, Loss: 0.49239692091941833
2024-08-04T17:48:12.185894663Z 
  9%|▉         | 501/5712 [1:10:03<12:18:49,  8.51s/it]08/04/2024 10:48:12 - INFO - __main__ -   Step: 501, LR: 4.3863201094391244e-07, Loss: 0.542434573173523
2024-08-04T17:48:19.740788645Z 
  9%|▉         | 502/5712 [1:10:10<11:53:53,  8.22s/it]08/04/2024 10:48:19 - INFO - __main__ -   Step: 502, LR: 4.395075239398084e-07, Loss: 0.5203595161437988
2024-08-04T17:48:28.020667781Z 
  9%|▉         | 503/5712 [1:10:19<11:55:16,  8.24s/it]08/04/2024 10:48:28 - INFO - __main__ -   Step: 503, LR: 4.403830369357045e-07, Loss: 0.5560636520385742
2024-08-04T17:48:36.920927575Z 
  9%|▉         | 504/5712 [1:10:28<12:12:21,  8.44s/it]08/04/2024 10:48:36 - INFO - __main__ -   Step: 504, LR: 4.4125854993160056e-07, Loss: 0.5514079928398132
2024-08-04T17:48:45.255946702Z 
  9%|▉         | 505/5712 [1:10:36<12:09:33,  8.41s/it]08/04/2024 10:48:45 - INFO - __main__ -   Step: 505, LR: 4.4213406292749654e-07, Loss: 0.6078082323074341
2024-08-04T17:48:53.623271942Z 
  9%|▉         | 506/5712 [1:10:44<12:08:22,  8.39s/it]08/04/2024 10:48:53 - INFO - __main__ -   Step: 506, LR: 4.430095759233926e-07, Loss: 0.586963415145874
2024-08-04T17:49:02.536644206Z 
  9%|▉         | 507/5712 [1:10:53<12:21:45,  8.55s/it]08/04/2024 10:49:02 - INFO - __main__ -   Step: 507, LR: 4.438850889192886e-07, Loss: 0.47554704546928406
2024-08-04T17:49:11.234135944Z 
  9%|▉         | 508/5712 [1:11:02<12:25:26,  8.59s/it]08/04/2024 10:49:11 - INFO - __main__ -   Step: 508, LR: 4.4476060191518467e-07, Loss: 0.5804499387741089
2024-08-04T17:49:19.755084647Z 
  9%|▉         | 509/5712 [1:11:10<12:23:22,  8.57s/it]08/04/2024 10:49:19 - INFO - __main__ -   Step: 509, LR: 4.456361149110807e-07, Loss: 0.5753316879272461
2024-08-04T17:49:27.809017685Z 
  9%|▉         | 510/5712 [1:11:18<12:09:44,  8.42s/it]08/04/2024 10:49:27 - INFO - __main__ -   Step: 510, LR: 4.465116279069767e-07, Loss: 0.5809031128883362
2024-08-04T17:49:36.043728837Z 
  9%|▉         | 511/5712 [1:11:27<12:04:52,  8.36s/it]08/04/2024 10:49:36 - INFO - __main__ -   Step: 511, LR: 4.473871409028728e-07, Loss: 0.48867419362068176
2024-08-04T17:49:44.268261530Z 
  9%|▉         | 512/5712 [1:11:35<12:01:09,  8.32s/it]08/04/2024 10:49:44 - INFO - __main__ -   Step: 512, LR: 4.482626538987688e-07, Loss: 0.556084394454956
2024-08-04T17:49:52.748502001Z 
  9%|▉         | 513/5712 [1:11:43<12:05:09,  8.37s/it]08/04/2024 10:49:52 - INFO - __main__ -   Step: 513, LR: 4.491381668946648e-07, Loss: 0.5177570581436157
2024-08-04T17:50:00.970579669Z 
  9%|▉         | 514/5712 [1:11:52<12:01:11,  8.32s/it]08/04/2024 10:50:00 - INFO - __main__ -   Step: 514, LR: 4.500136798905609e-07, Loss: 0.5652565956115723
2024-08-04T17:50:09.507618029Z 
  9%|▉         | 515/5712 [1:12:00<12:06:34,  8.39s/it]08/04/2024 10:50:09 - INFO - __main__ -   Step: 515, LR: 4.508891928864569e-07, Loss: 0.5150469541549683
2024-08-04T17:50:18.140990997Z 
  9%|▉         | 516/5712 [1:12:09<12:12:48,  8.46s/it]08/04/2024 10:50:18 - INFO - __main__ -   Step: 516, LR: 4.5176470588235294e-07, Loss: 0.5422943830490112
2024-08-04T17:50:27.433541619Z 
  9%|▉         | 517/5712 [1:12:18<12:34:14,  8.71s/it]08/04/2024 10:50:27 - INFO - __main__ -   Step: 517, LR: 4.526402188782489e-07, Loss: 0.42772895097732544
2024-08-04T17:50:35.527931793Z 
  9%|▉         | 518/5712 [1:12:26<12:18:04,  8.53s/it]08/04/2024 10:50:35 - INFO - __main__ -   Step: 518, LR: 4.53515731874145e-07, Loss: 0.5221086740493774
2024-08-04T17:50:43.604761462Z 
  9%|▉         | 519/5712 [1:12:34<12:06:16,  8.39s/it]08/04/2024 10:50:43 - INFO - __main__ -   Step: 519, LR: 4.5439124487004106e-07, Loss: 0.62938392162323
2024-08-04T17:50:52.038816804Z 
  9%|▉         | 520/5712 [1:12:43<12:07:14,  8.40s/it]08/04/2024 10:50:52 - INFO - __main__ -   Step: 520, LR: 4.5526675786593704e-07, Loss: 0.5226300954818726
2024-08-04T17:51:00.781130828Z 
  9%|▉         | 521/5712 [1:12:51<12:15:52,  8.51s/it]08/04/2024 10:51:00 - INFO - __main__ -   Step: 521, LR: 4.561422708618331e-07, Loss: 0.5926859974861145
2024-08-04T17:51:09.364585224Z 
  9%|▉         | 522/5712 [1:13:00<12:17:45,  8.53s/it]08/04/2024 10:51:09 - INFO - __main__ -   Step: 522, LR: 4.570177838577291e-07, Loss: 0.5756460428237915
2024-08-04T17:51:17.680957213Z 
  9%|▉         | 523/5712 [1:13:08<12:12:04,  8.47s/it]08/04/2024 10:51:17 - INFO - __main__ -   Step: 523, LR: 4.5789329685362516e-07, Loss: 0.5429431200027466
2024-08-04T17:51:26.589942299Z 
  9%|▉         | 524/5712 [1:13:17<12:23:28,  8.60s/it]08/04/2024 10:51:26 - INFO - __main__ -   Step: 524, LR: 4.587688098495212e-07, Loss: 0.5632920265197754
2024-08-04T17:51:34.786472621Z 
  9%|▉         | 525/5712 [1:13:25<12:12:54,  8.48s/it]08/04/2024 10:51:34 - INFO - __main__ -   Step: 525, LR: 4.596443228454172e-07, Loss: 0.5086996555328369
2024-08-04T17:51:43.093590424Z 
  9%|▉         | 526/5712 [1:13:34<12:08:20,  8.43s/it]08/04/2024 10:51:43 - INFO - __main__ -   Step: 526, LR: 4.605198358413133e-07, Loss: 0.5241280794143677
2024-08-04T17:51:51.084154344Z 
  9%|▉         | 527/5712 [1:13:42<11:56:53,  8.30s/it]08/04/2024 10:51:51 - INFO - __main__ -   Step: 527, LR: 4.6139534883720927e-07, Loss: 0.5662513971328735
2024-08-04T17:51:59.136084018Z 
  9%|▉         | 528/5712 [1:13:50<11:50:26,  8.22s/it]08/04/2024 10:51:59 - INFO - __main__ -   Step: 528, LR: 4.622708618331053e-07, Loss: 0.6102088689804077
2024-08-04T17:52:07.422955305Z 
  9%|▉         | 529/5712 [1:13:58<11:51:57,  8.24s/it]08/04/2024 10:52:07 - INFO - __main__ -   Step: 529, LR: 4.6314637482900135e-07, Loss: 0.5203671455383301
2024-08-04T17:52:16.393013641Z 
  9%|▉         | 530/5712 [1:14:07<12:10:41,  8.46s/it]08/04/2024 10:52:16 - INFO - __main__ -   Step: 530, LR: 4.640218878248974e-07, Loss: 0.6066925525665283
2024-08-04T17:52:24.353261434Z 
  9%|▉         | 531/5712 [1:14:15<11:57:35,  8.31s/it]08/04/2024 10:52:24 - INFO - __main__ -   Step: 531, LR: 4.6489740082079343e-07, Loss: 0.4844663143157959
2024-08-04T17:52:33.003445753Z 
  9%|▉         | 532/5712 [1:14:24<12:06:15,  8.41s/it]08/04/2024 10:52:33 - INFO - __main__ -   Step: 532, LR: 4.657729138166894e-07, Loss: 0.5601228475570679
2024-08-04T17:52:41.648456604Z 
  9%|▉         | 533/5712 [1:14:32<12:12:06,  8.48s/it]08/04/2024 10:52:41 - INFO - __main__ -   Step: 533, LR: 4.6664842681258546e-07, Loss: 0.43285471200942993
2024-08-04T17:52:50.114949656Z 
  9%|▉         | 534/5712 [1:14:41<12:11:36,  8.48s/it]08/04/2024 10:52:50 - INFO - __main__ -   Step: 534, LR: 4.6752393980848155e-07, Loss: 0.6769249439239502
2024-08-04T17:52:57.673658864Z 
  9%|▉         | 535/5712 [1:14:48<11:47:40,  8.20s/it]08/04/2024 10:52:57 - INFO - __main__ -   Step: 535, LR: 4.6839945280437754e-07, Loss: 0.5791734457015991
2024-08-04T17:53:06.085229879Z 
  9%|▉         | 536/5712 [1:14:57<11:52:58,  8.26s/it]08/04/2024 10:53:06 - INFO - __main__ -   Step: 536, LR: 4.692749658002736e-07, Loss: 0.5157592296600342
2024-08-04T17:53:14.763516255Z 
  9%|▉         | 537/5712 [1:15:05<12:03:32,  8.39s/it]08/04/2024 10:53:14 - INFO - __main__ -   Step: 537, LR: 4.7015047879616957e-07, Loss: 0.500505805015564
2024-08-04T17:53:23.063576936Z 
  9%|▉         | 538/5712 [1:15:14<12:01:05,  8.36s/it]08/04/2024 10:53:23 - INFO - __main__ -   Step: 538, LR: 4.7102599179206566e-07, Loss: 0.5729411840438843
2024-08-04T17:53:31.537346060Z 
  9%|▉         | 539/5712 [1:15:22<12:03:51,  8.40s/it]08/04/2024 10:53:31 - INFO - __main__ -   Step: 539, LR: 4.719015047879617e-07, Loss: 0.551315188407898
2024-08-04T17:53:40.542486248Z 
  9%|▉         | 540/5712 [1:15:31<12:19:27,  8.58s/it]08/04/2024 10:53:40 - INFO - __main__ -   Step: 540, LR: 4.727770177838577e-07, Loss: 0.5078200101852417
2024-08-04T17:53:49.915542227Z 
  9%|▉         | 541/5712 [1:15:41<12:39:52,  8.82s/it]08/04/2024 10:53:49 - INFO - __main__ -   Step: 541, LR: 4.7365253077975373e-07, Loss: 0.5434361100196838
2024-08-04T17:53:58.507765953Z 
  9%|▉         | 542/5712 [1:15:49<12:33:54,  8.75s/it]08/04/2024 10:53:58 - INFO - __main__ -   Step: 542, LR: 4.7452804377564977e-07, Loss: 0.5380403399467468
2024-08-04T17:54:06.616617698Z 
 10%|▉         | 543/5712 [1:15:57<12:17:12,  8.56s/it]08/04/2024 10:54:06 - INFO - __main__ -   Step: 543, LR: 4.754035567715458e-07, Loss: 0.4445091485977173
2024-08-04T17:54:14.569913971Z 
 10%|▉         | 544/5712 [1:16:05<12:01:27,  8.38s/it]08/04/2024 10:54:14 - INFO - __main__ -   Step: 544, LR: 4.7627906976744185e-07, Loss: 0.526254415512085
2024-08-04T17:54:22.770928066Z 
 10%|▉         | 545/5712 [1:16:13<11:56:47,  8.32s/it]08/04/2024 10:54:22 - INFO - __main__ -   Step: 545, LR: 4.771545827633379e-07, Loss: 0.45492827892303467
2024-08-04T17:54:31.585135682Z 
 10%|▉         | 546/5712 [1:16:22<12:09:20,  8.47s/it]08/04/2024 10:54:31 - INFO - __main__ -   Step: 546, LR: 4.780300957592339e-07, Loss: 0.6007057428359985
2024-08-04T17:54:39.550677008Z 
 10%|▉         | 547/5712 [1:16:30<11:56:07,  8.32s/it]08/04/2024 10:54:39 - INFO - __main__ -   Step: 547, LR: 4.789056087551299e-07, Loss: 0.5543856620788574
2024-08-04T17:54:47.826644797Z 
 10%|▉         | 548/5712 [1:16:38<11:54:53,  8.31s/it]08/04/2024 10:54:47 - INFO - __main__ -   Step: 548, LR: 4.79781121751026e-07, Loss: 0.5595567226409912
2024-08-04T17:54:56.074765044Z 
 10%|▉         | 549/5712 [1:16:47<11:53:15,  8.29s/it]08/04/2024 10:54:56 - INFO - __main__ -   Step: 549, LR: 4.806566347469221e-07, Loss: 0.5216260552406311
2024-08-04T17:55:05.248052966Z 
 10%|▉         | 550/5712 [1:16:56<12:15:56,  8.55s/it]08/04/2024 10:55:05 - INFO - __main__ -   Step: 550, LR: 4.81532147742818e-07, Loss: 0.5741139054298401
2024-08-04T17:55:13.332040972Z 
 10%|▉         | 551/5712 [1:17:04<12:03:40,  8.41s/it]08/04/2024 10:55:13 - INFO - __main__ -   Step: 551, LR: 4.824076607387141e-07, Loss: 0.5264873504638672
2024-08-04T17:55:21.281268362Z 
 10%|▉         | 552/5712 [1:17:12<11:51:33,  8.27s/it]08/04/2024 10:55:21 - INFO - __main__ -   Step: 552, LR: 4.832831737346101e-07, Loss: 0.5076346397399902
2024-08-04T17:55:29.567029795Z 
 10%|▉         | 553/5712 [1:17:20<11:51:42,  8.28s/it]08/04/2024 10:55:29 - INFO - __main__ -   Step: 553, LR: 4.841586867305061e-07, Loss: 0.5241419076919556
2024-08-04T17:55:38.242500108Z 
 10%|▉         | 554/5712 [1:17:29<12:01:51,  8.40s/it]08/04/2024 10:55:38 - INFO - __main__ -   Step: 554, LR: 4.850341997264022e-07, Loss: 0.5089348554611206
2024-08-04T17:55:47.133974936Z 
 10%|▉         | 555/5712 [1:17:38<12:14:28,  8.55s/it]08/04/2024 10:55:47 - INFO - __main__ -   Step: 555, LR: 4.859097127222982e-07, Loss: 0.7059967517852783
2024-08-04T17:55:55.915407556Z 
 10%|▉         | 556/5712 [1:17:47<12:20:24,  8.62s/it]08/04/2024 10:55:55 - INFO - __main__ -   Step: 556, LR: 4.867852257181943e-07, Loss: 0.517687201499939
2024-08-04T17:56:04.279830590Z 
 10%|▉         | 557/5712 [1:17:55<12:13:46,  8.54s/it]08/04/2024 10:56:04 - INFO - __main__ -   Step: 557, LR: 4.876607387140903e-07, Loss: 0.48921793699264526
2024-08-04T17:56:12.824731132Z 
 10%|▉         | 558/5712 [1:18:03<12:13:45,  8.54s/it]08/04/2024 10:56:12 - INFO - __main__ -   Step: 558, LR: 4.885362517099863e-07, Loss: 0.6628600358963013
2024-08-04T17:56:21.173440196Z 
 10%|▉         | 559/5712 [1:18:12<12:08:38,  8.48s/it]08/04/2024 10:56:21 - INFO - __main__ -   Step: 559, LR: 4.894117647058824e-07, Loss: 0.6297732591629028
2024-08-04T17:56:29.159982488Z 
 10%|▉         | 560/5712 [1:18:20<11:55:40,  8.33s/it]08/04/2024 10:56:29 - INFO - __main__ -   Step: 560, LR: 4.902872777017783e-07, Loss: 0.4537852108478546
2024-08-04T17:56:37.021202260Z 
 10%|▉         | 561/5712 [1:18:28<11:43:20,  8.19s/it]08/04/2024 10:56:37 - INFO - __main__ -   Step: 561, LR: 4.911627906976744e-07, Loss: 0.47168201208114624
2024-08-04T17:56:45.388872701Z 
 10%|▉         | 562/5712 [1:18:36<11:47:42,  8.25s/it]08/04/2024 10:56:45 - INFO - __main__ -   Step: 562, LR: 4.920383036935704e-07, Loss: 0.5406051874160767
2024-08-04T17:56:54.152794628Z 
 10%|▉         | 563/5712 [1:18:45<12:00:55,  8.40s/it]08/04/2024 10:56:54 - INFO - __main__ -   Step: 563, LR: 4.929138166894665e-07, Loss: 0.5450577735900879
2024-08-04T17:57:03.056439882Z 
 10%|▉         | 564/5712 [1:18:54<12:13:44,  8.55s/it]08/04/2024 10:57:03 - INFO - __main__ -   Step: 564, LR: 4.937893296853625e-07, Loss: 0.5286151170730591
2024-08-04T17:57:11.252466921Z 
 10%|▉         | 565/5712 [1:19:02<12:04:26,  8.44s/it]08/04/2024 10:57:11 - INFO - __main__ -   Step: 565, LR: 4.946648426812585e-07, Loss: 0.662521243095398
2024-08-04T17:57:20.502094046Z 
 10%|▉         | 566/5712 [1:19:11<12:24:59,  8.69s/it]08/04/2024 10:57:20 - INFO - __main__ -   Step: 566, LR: 4.955403556771546e-07, Loss: 0.5281900763511658
2024-08-04T17:57:29.111739451Z 
 10%|▉         | 567/5712 [1:19:20<12:22:51,  8.66s/it]08/04/2024 10:57:29 - INFO - __main__ -   Step: 567, LR: 4.964158686730506e-07, Loss: 0.5969810485839844
2024-08-04T17:57:36.761225641Z 
 10%|▉         | 568/5712 [1:19:27<11:56:40,  8.36s/it]08/04/2024 10:57:36 - INFO - __main__ -   Step: 568, LR: 4.972913816689467e-07, Loss: 0.4642210602760315
2024-08-04T17:57:44.825051138Z 
 10%|▉         | 569/5712 [1:19:35<11:48:56,  8.27s/it]08/04/2024 10:57:44 - INFO - __main__ -   Step: 569, LR: 4.981668946648426e-07, Loss: 0.5502809882164001
2024-08-04T17:57:53.215093157Z 
 10%|▉         | 570/5712 [1:19:44<11:51:51,  8.31s/it]08/04/2024 10:57:53 - INFO - __main__ -   Step: 570, LR: 4.990424076607386e-07, Loss: 0.6569315195083618
2024-08-04T17:58:01.674856894Z 
 10%|▉         | 571/5712 [1:19:52<11:55:39,  8.35s/it]08/04/2024 10:58:01 - INFO - __main__ -   Step: 571, LR: 4.999179206566347e-07, Loss: 0.4869765639305115
2024-08-04T17:58:10.085857981Z 
 10%|█         | 572/5712 [1:20:01<11:57:02,  8.37s/it]08/04/2024 10:58:10 - INFO - __main__ -   Step: 572, LR: 4.999118412412753e-07, Loss: 0.6008196473121643
2024-08-04T17:58:18.812508397Z 
 10%|█         | 573/5712 [1:20:09<12:06:03,  8.48s/it]08/04/2024 10:58:18 - INFO - __main__ -   Step: 573, LR: 4.998145626109584e-07, Loss: 0.5713196992874146
2024-08-04T17:58:27.422373954Z 
 10%|█         | 574/5712 [1:20:18<12:09:19,  8.52s/it]08/04/2024 10:58:27 - INFO - __main__ -   Step: 574, LR: 4.997172839806416e-07, Loss: 0.626554012298584
2024-08-04T17:58:35.865944105Z 
 10%|█         | 575/5712 [1:20:27<12:07:17,  8.49s/it]08/04/2024 10:58:35 - INFO - __main__ -   Step: 575, LR: 4.996200053503247e-07, Loss: 0.5356981754302979
2024-08-04T17:58:44.018775467Z 
 10%|█         | 576/5712 [1:20:35<11:58:23,  8.39s/it]08/04/2024 10:58:44 - INFO - __main__ -   Step: 576, LR: 4.995227267200078e-07, Loss: 0.5732269883155823
2024-08-04T17:58:52.111227057Z 
 10%|█         | 577/5712 [1:20:43<11:50:32,  8.30s/it]08/04/2024 10:58:52 - INFO - __main__ -   Step: 577, LR: 4.994254480896909e-07, Loss: 0.5292621850967407
2024-08-04T17:59:00.111855206Z 
 10%|█         | 578/5712 [1:20:51<11:42:39,  8.21s/it]08/04/2024 10:59:00 - INFO - __main__ -   Step: 578, LR: 4.99328169459374e-07, Loss: 0.5201379656791687
2024-08-04T17:59:08.631016250Z 
 10%|█         | 579/5712 [1:20:59<11:50:24,  8.30s/it]08/04/2024 10:59:08 - INFO - __main__ -   Step: 579, LR: 4.992308908290572e-07, Loss: 0.5128656625747681
2024-08-04T17:59:17.168772547Z 
 10%|█         | 580/5712 [1:21:08<11:56:15,  8.37s/it]08/04/2024 10:59:17 - INFO - __main__ -   Step: 580, LR: 4.991336121987403e-07, Loss: 0.45911896228790283
2024-08-04T17:59:25.892254919Z 
 10%|█         | 581/5712 [1:21:17<12:05:05,  8.48s/it]08/04/2024 10:59:25 - INFO - __main__ -   Step: 581, LR: 4.990363335684234e-07, Loss: 0.5154577493667603
2024-08-04T17:59:34.068039425Z 
 10%|█         | 582/5712 [1:21:25<11:57:10,  8.39s/it]08/04/2024 10:59:34 - INFO - __main__ -   Step: 582, LR: 4.989390549381065e-07, Loss: 0.5341032147407532
2024-08-04T17:59:42.945085152Z 
 10%|█         | 583/5712 [1:21:34<12:09:34,  8.53s/it]08/04/2024 10:59:42 - INFO - __main__ -   Step: 583, LR: 4.988417763077896e-07, Loss: 0.5110663175582886
2024-08-04T17:59:51.291823263Z 
 10%|█         | 584/5712 [1:21:42<12:04:37,  8.48s/it]08/04/2024 10:59:51 - INFO - __main__ -   Step: 584, LR: 4.987444976774727e-07, Loss: 0.5370463132858276
2024-08-04T17:59:59.750924068Z 
 10%|█         | 585/5712 [1:21:50<12:03:58,  8.47s/it]08/04/2024 10:59:59 - INFO - __main__ -   Step: 585, LR: 4.986472190471558e-07, Loss: 0.4983524680137634
2024-08-04T18:00:07.759200341Z 
 10%|█         | 586/5712 [1:21:58<11:51:55,  8.33s/it]08/04/2024 11:00:07 - INFO - __main__ -   Step: 586, LR: 4.985499404168389e-07, Loss: 0.49336883425712585
2024-08-04T18:00:15.710355233Z 
 10%|█         | 587/5712 [1:22:06<11:42:00,  8.22s/it]08/04/2024 11:00:15 - INFO - __main__ -   Step: 587, LR: 4.984526617865221e-07, Loss: 0.4823029041290283
2024-08-04T18:00:24.573241819Z 
 10%|█         | 588/5712 [1:22:15<11:58:23,  8.41s/it]08/04/2024 11:00:24 - INFO - __main__ -   Step: 588, LR: 4.983553831562052e-07, Loss: 0.6296385526657104
2024-08-04T18:00:33.339463967Z 
 10%|█         | 589/5712 [1:22:24<12:07:19,  8.52s/it]08/04/2024 11:00:33 - INFO - __main__ -   Step: 589, LR: 4.982581045258883e-07, Loss: 0.6604604721069336
2024-08-04T18:00:42.452818154Z 
 10%|█         | 590/5712 [1:22:33<12:22:24,  8.70s/it]08/04/2024 11:00:42 - INFO - __main__ -   Step: 590, LR: 4.981608258955714e-07, Loss: 0.5521321892738342
2024-08-04T18:00:50.945945984Z 
 10%|█         | 591/5712 [1:22:42<12:17:03,  8.64s/it]08/04/2024 11:00:50 - INFO - __main__ -   Step: 591, LR: 4.980635472652545e-07, Loss: 0.5326974987983704
2024-08-04T18:00:59.102998582Z 
 10%|█         | 592/5712 [1:22:50<12:04:39,  8.49s/it]08/04/2024 11:00:59 - INFO - __main__ -   Step: 592, LR: 4.979662686349377e-07, Loss: 0.5909975171089172
2024-08-04T18:01:07.246462635Z 
 10%|█         | 593/5712 [1:22:58<11:55:35,  8.39s/it]08/04/2024 11:01:07 - INFO - __main__ -   Step: 593, LR: 4.978689900046208e-07, Loss: 0.48778197169303894
2024-08-04T18:01:15.523193846Z 
 10%|█         | 594/5712 [1:23:06<11:52:37,  8.35s/it]08/04/2024 11:01:15 - INFO - __main__ -   Step: 594, LR: 4.977717113743039e-07, Loss: 0.4043906629085541
2024-08-04T18:01:23.552210623Z 
 10%|█         | 595/5712 [1:23:14<11:44:09,  8.26s/it]08/04/2024 11:01:23 - INFO - __main__ -   Step: 595, LR: 4.97674432743987e-07, Loss: 0.49323785305023193
2024-08-04T18:01:32.020045983Z 
 10%|█         | 596/5712 [1:23:23<11:49:25,  8.32s/it]08/04/2024 11:01:32 - INFO - __main__ -   Step: 596, LR: 4.975771541136701e-07, Loss: 0.5846846103668213
2024-08-04T18:01:40.675058961Z 
 10%|█         | 597/5712 [1:23:31<11:57:50,  8.42s/it]08/04/2024 11:01:40 - INFO - __main__ -   Step: 597, LR: 4.974798754833532e-07, Loss: 0.5866923332214355
2024-08-04T18:01:49.083923761Z 
 10%|█         | 598/5712 [1:23:40<11:57:24,  8.42s/it]08/04/2024 11:01:49 - INFO - __main__ -   Step: 598, LR: 4.973825968530363e-07, Loss: 0.506955087184906
2024-08-04T18:01:57.639469689Z 
 10%|█         | 599/5712 [1:23:48<12:00:48,  8.46s/it]08/04/2024 11:01:57 - INFO - __main__ -   Step: 599, LR: 4.972853182227194e-07, Loss: 0.5747389197349548
2024-08-04T18:02:06.137869033Z 
 11%|█         | 600/5712 [1:23:57<12:01:40,  8.47s/it]08/04/2024 11:02:06 - INFO - __main__ -   Step: 600, LR: 4.971880395924026e-07, Loss: 0.5846537947654724
2024-08-04T18:02:14.546901660Z 
 11%|█         | 601/5712 [1:24:05<11:59:58,  8.45s/it]08/04/2024 11:02:14 - INFO - __main__ -   Step: 601, LR: 4.970907609620857e-07, Loss: 0.5539498329162598
2024-08-04T18:02:23.037744117Z 
 11%|█         | 602/5712 [1:24:14<12:00:49,  8.46s/it]08/04/2024 11:02:23 - INFO - __main__ -   Step: 602, LR: 4.969934823317688e-07, Loss: 0.5034406185150146
2024-08-04T18:02:31.265150133Z 
 11%|█         | 603/5712 [1:24:22<11:54:38,  8.39s/it]08/04/2024 11:02:31 - INFO - __main__ -   Step: 603, LR: 4.968962037014519e-07, Loss: 0.5567346811294556
2024-08-04T18:02:39.698398519Z 
 11%|█         | 604/5712 [1:24:30<11:55:32,  8.40s/it]08/04/2024 11:02:39 - INFO - __main__ -   Step: 604, LR: 4.96798925071135e-07, Loss: 0.41871020197868347
2024-08-04T18:02:48.549238059Z 
 11%|█         | 605/5712 [1:24:39<12:06:47,  8.54s/it]08/04/2024 11:02:48 - INFO - __main__ -   Step: 605, LR: 4.967016464408181e-07, Loss: 0.6256341338157654
2024-08-04T18:02:57.084420296Z 
 11%|█         | 606/5712 [1:24:48<12:06:33,  8.54s/it]08/04/2024 11:02:57 - INFO - __main__ -   Step: 606, LR: 4.966043678105012e-07, Loss: 0.5744068622589111
2024-08-04T18:03:05.323496530Z 
 11%|█         | 607/5712 [1:24:56<11:58:47,  8.45s/it]08/04/2024 11:03:05 - INFO - __main__ -   Step: 607, LR: 4.965070891801843e-07, Loss: 0.5319488644599915
2024-08-04T18:03:13.871421925Z 
 11%|█         | 608/5712 [1:25:05<12:01:11,  8.48s/it]08/04/2024 11:03:13 - INFO - __main__ -   Step: 608, LR: 4.964098105498675e-07, Loss: 0.4585132598876953
2024-08-04T18:03:21.863873624Z 
 11%|█         | 609/5712 [1:25:13<11:48:39,  8.33s/it]08/04/2024 11:03:21 - INFO - __main__ -   Step: 609, LR: 4.963125319195506e-07, Loss: 0.48832255601882935
2024-08-04T18:03:30.207073508Z 
 11%|█         | 610/5712 [1:25:21<11:48:48,  8.34s/it]08/04/2024 11:03:30 - INFO - __main__ -   Step: 610, LR: 4.962152532892337e-07, Loss: 0.47367119789123535
2024-08-04T18:03:38.364428380Z 
 11%|█         | 611/5712 [1:25:29<11:44:06,  8.28s/it]08/04/2024 11:03:38 - INFO - __main__ -   Step: 611, LR: 4.961179746589168e-07, Loss: 0.5047751665115356
2024-08-04T18:03:46.876184844Z 
 11%|█         | 612/5712 [1:25:38<11:49:50,  8.35s/it]08/04/2024 11:03:46 - INFO - __main__ -   Step: 612, LR: 4.960206960286e-07, Loss: 0.6165759563446045
2024-08-04T18:03:55.417005257Z 
 11%|█         | 613/5712 [1:25:46<11:54:32,  8.41s/it]08/04/2024 11:03:55 - INFO - __main__ -   Step: 613, LR: 4.959234173982831e-07, Loss: 0.40838518738746643
2024-08-04T18:04:04.408926947Z 
 11%|█         | 614/5712 [1:25:55<12:09:16,  8.58s/it]08/04/2024 11:04:04 - INFO - __main__ -   Step: 614, LR: 4.958261387679662e-07, Loss: 0.5031964778900146
2024-08-04T18:04:13.100377137Z 
 11%|█         | 615/5712 [1:26:04<12:11:54,  8.62s/it]08/04/2024 11:04:13 - INFO - __main__ -   Step: 615, LR: 4.957288601376493e-07, Loss: 0.6185152530670166
2024-08-04T18:04:21.340565008Z 
 11%|█         | 616/5712 [1:26:12<12:02:11,  8.50s/it]08/04/2024 11:04:21 - INFO - __main__ -   Step: 616, LR: 4.956315815073324e-07, Loss: 0.5302440524101257
2024-08-04T18:04:29.770514137Z 
 11%|█         | 617/5712 [1:26:20<12:00:10,  8.48s/it]08/04/2024 11:04:29 - INFO - __main__ -   Step: 617, LR: 4.955343028770155e-07, Loss: 0.4980733394622803
2024-08-04T18:04:38.384151993Z 
 11%|█         | 618/5712 [1:26:29<12:03:25,  8.52s/it]08/04/2024 11:04:38 - INFO - __main__ -   Step: 618, LR: 4.954370242466986e-07, Loss: 0.5977338552474976
2024-08-04T18:04:46.848783777Z 
 11%|█         | 619/5712 [1:26:37<12:01:50,  8.50s/it]08/04/2024 11:04:46 - INFO - __main__ -   Step: 619, LR: 4.953397456163817e-07, Loss: 0.6480767726898193
2024-08-04T18:04:54.445196383Z 
 11%|█         | 620/5712 [1:26:45<11:38:35,  8.23s/it]08/04/2024 11:04:54 - INFO - __main__ -   Step: 620, LR: 4.952424669860649e-07, Loss: 0.502300500869751
2024-08-04T18:05:03.139340960Z 
 11%|█         | 621/5712 [1:26:54<11:50:13,  8.37s/it]08/04/2024 11:05:03 - INFO - __main__ -   Step: 621, LR: 4.95145188355748e-07, Loss: 0.5416930913925171
2024-08-04T18:05:12.182319516Z 
 11%|█         | 622/5712 [1:27:03<12:07:12,  8.57s/it]08/04/2024 11:05:12 - INFO - __main__ -   Step: 622, LR: 4.950479097254311e-07, Loss: 0.4820164442062378
2024-08-04T18:05:20.651305091Z 
 11%|█         | 623/5712 [1:27:11<12:04:26,  8.54s/it]08/04/2024 11:05:20 - INFO - __main__ -   Step: 623, LR: 4.949506310951142e-07, Loss: 0.6204389929771423
2024-08-04T18:05:28.965791681Z 
 11%|█         | 624/5712 [1:27:20<11:58:32,  8.47s/it]08/04/2024 11:05:28 - INFO - __main__ -   Step: 624, LR: 4.948533524647973e-07, Loss: 0.5344556570053101
2024-08-04T18:05:37.371216222Z 
 11%|█         | 625/5712 [1:27:28<11:56:40,  8.45s/it]08/04/2024 11:05:37 - INFO - __main__ -   Step: 625, LR: 4.947560738344804e-07, Loss: 0.4694973826408386
2024-08-04T18:05:45.589441257Z 
 11%|█         | 626/5712 [1:27:36<11:50:32,  8.38s/it]08/04/2024 11:05:45 - INFO - __main__ -   Step: 626, LR: 4.946587952041635e-07, Loss: 0.4506351351737976
2024-08-04T18:05:53.985769858Z 
 11%|█         | 627/5712 [1:27:45<11:50:45,  8.39s/it]08/04/2024 11:05:53 - INFO - __main__ -   Step: 627, LR: 4.945615165738466e-07, Loss: 0.4736473560333252
2024-08-04T18:06:02.070319513Z 
 11%|█         | 628/5712 [1:27:53<11:42:57,  8.30s/it]08/04/2024 11:06:02 - INFO - __main__ -   Step: 628, LR: 4.944642379435297e-07, Loss: 0.5293459892272949
2024-08-04T18:06:10.787878832Z 
 11%|█         | 629/5712 [1:28:01<11:53:31,  8.42s/it]08/04/2024 11:06:10 - INFO - __main__ -   Step: 629, LR: 4.943669593132129e-07, Loss: 0.4743422269821167
2024-08-04T18:06:19.640512637Z 
 11%|█         | 630/5712 [1:28:10<12:04:18,  8.55s/it]08/04/2024 11:06:19 - INFO - __main__ -   Step: 630, LR: 4.94269680682896e-07, Loss: 0.5382306575775146
2024-08-04T18:06:28.130518403Z 
 11%|█         | 631/5712 [1:28:19<12:02:36,  8.53s/it]08/04/2024 11:06:28 - INFO - __main__ -   Step: 631, LR: 4.941724020525791e-07, Loss: 0.508460283279419
2024-08-04T18:06:37.249391394Z 
 11%|█         | 632/5712 [1:28:28<12:17:20,  8.71s/it]08/04/2024 11:06:37 - INFO - __main__ -   Step: 632, LR: 4.940751234222622e-07, Loss: 0.6186089515686035
2024-08-04T18:06:45.250929469Z 
 11%|█         | 633/5712 [1:28:36<11:59:14,  8.50s/it]08/04/2024 11:06:45 - INFO - __main__ -   Step: 633, LR: 4.939778447919454e-07, Loss: 0.5862351655960083
2024-08-04T18:06:54.275976401Z 
 11%|█         | 634/5712 [1:28:45<12:12:30,  8.66s/it]08/04/2024 11:06:54 - INFO - __main__ -   Step: 634, LR: 4.938805661616285e-07, Loss: 0.5878335237503052
2024-08-04T18:07:03.028993646Z 
 11%|█         | 635/5712 [1:28:54<12:14:51,  8.68s/it]08/04/2024 11:07:03 - INFO - __main__ -   Step: 635, LR: 4.937832875313116e-07, Loss: 0.555420994758606
2024-08-04T18:07:11.102520932Z 
 11%|█         | 636/5712 [1:29:02<11:59:12,  8.50s/it]08/04/2024 11:07:11 - INFO - __main__ -   Step: 636, LR: 4.936860089009947e-07, Loss: 0.49198994040489197
2024-08-04T18:07:19.239663838Z 
 11%|█         | 637/5712 [1:29:10<11:49:49,  8.39s/it]08/04/2024 11:07:19 - INFO - __main__ -   Step: 637, LR: 4.935887302706778e-07, Loss: 0.5579612851142883
2024-08-04T18:07:27.231960542Z 
 11%|█         | 638/5712 [1:29:18<11:39:32,  8.27s/it]08/04/2024 11:07:27 - INFO - __main__ -   Step: 638, LR: 4.934914516403609e-07, Loss: 0.4915567934513092
2024-08-04T18:07:37.201863850Z 
 11%|█         | 639/5712 [1:29:28<12:22:27,  8.78s/it]08/04/2024 11:07:37 - INFO - __main__ -   Step: 639, LR: 4.93394173010044e-07, Loss: 0.5238815546035767
2024-08-04T18:07:45.602887859Z 
 11%|█         | 640/5712 [1:29:36<12:12:40,  8.67s/it]08/04/2024 11:07:45 - INFO - __main__ -   Step: 640, LR: 4.932968943797271e-07, Loss: 0.4221421778202057
2024-08-04T18:07:54.081450064Z 
 11%|█         | 641/5712 [1:29:45<12:07:44,  8.61s/it]08/04/2024 11:07:54 - INFO - __main__ -   Step: 641, LR: 4.931996157494103e-07, Loss: 0.5636458992958069
2024-08-04T18:08:02.600661618Z 
 11%|█         | 642/5712 [1:29:53<12:05:16,  8.58s/it]08/04/2024 11:08:02 - INFO - __main__ -   Step: 642, LR: 4.931023371190934e-07, Loss: 0.5364160537719727
2024-08-04T18:08:11.670093938Z 
 11%|█▏        | 643/5712 [1:30:02<12:17:28,  8.73s/it]08/04/2024 11:08:11 - INFO - __main__ -   Step: 643, LR: 4.930050584887765e-07, Loss: 0.6253573298454285
2024-08-04T18:08:19.650540454Z 
 11%|█▏        | 644/5712 [1:30:10<11:58:21,  8.50s/it]08/04/2024 11:08:19 - INFO - __main__ -   Step: 644, LR: 4.929077798584596e-07, Loss: 0.48157066106796265
2024-08-04T18:08:27.945118446Z 
 11%|█▏        | 645/5712 [1:30:19<11:52:53,  8.44s/it]08/04/2024 11:08:27 - INFO - __main__ -   Step: 645, LR: 4.928105012281427e-07, Loss: 0.44807469844818115
2024-08-04T18:08:36.295865859Z 
 11%|█▏        | 646/5712 [1:30:27<11:50:26,  8.41s/it]08/04/2024 11:08:36 - INFO - __main__ -   Step: 646, LR: 4.927132225978258e-07, Loss: 0.5853579640388489
2024-08-04T18:08:44.768323838Z 
 11%|█▏        | 647/5712 [1:30:35<11:51:46,  8.43s/it]08/04/2024 11:08:44 - INFO - __main__ -   Step: 647, LR: 4.92615943967509e-07, Loss: 0.6070919036865234
2024-08-04T18:08:53.257169526Z 
 11%|█▏        | 648/5712 [1:30:44<11:53:05,  8.45s/it]08/04/2024 11:08:53 - INFO - __main__ -   Step: 648, LR: 4.925186653371921e-07, Loss: 0.49176594614982605
2024-08-04T18:09:01.571077757Z 
 11%|█▏        | 649/5712 [1:30:52<11:49:31,  8.41s/it]08/04/2024 11:09:01 - INFO - __main__ -   Step: 649, LR: 4.924213867068752e-07, Loss: 0.5648553371429443
2024-08-04T18:09:09.715193897Z 
 11%|█▏        | 650/5712 [1:31:00<11:42:41,  8.33s/it]08/04/2024 11:09:09 - INFO - __main__ -   Step: 650, LR: 4.923241080765583e-07, Loss: 0.5157528519630432
2024-08-04T18:09:18.118364879Z 
 11%|█▏        | 651/5712 [1:31:09<11:44:25,  8.35s/it]08/04/2024 11:09:18 - INFO - __main__ -   Step: 651, LR: 4.922268294462414e-07, Loss: 0.4987926781177521
2024-08-04T18:09:26.557802620Z 
 11%|█▏        | 652/5712 [1:31:17<11:46:31,  8.38s/it]08/04/2024 11:09:26 - INFO - __main__ -   Step: 652, LR: 4.921295508159245e-07, Loss: 0.5900142192840576
2024-08-04T18:09:34.562630418Z 
 11%|█▏        | 653/5712 [1:31:25<11:36:57,  8.27s/it]08/04/2024 11:09:34 - INFO - __main__ -   Step: 653, LR: 4.920322721856077e-07, Loss: 0.4475443661212921
2024-08-04T18:09:43.040086314Z 
 11%|█▏        | 654/5712 [1:31:34<11:42:09,  8.33s/it]08/04/2024 11:09:43 - INFO - __main__ -   Step: 654, LR: 4.919349935552908e-07, Loss: 0.5636831521987915
2024-08-04T18:09:51.176002930Z 
 11%|█▏        | 655/5712 [1:31:42<11:37:07,  8.27s/it]08/04/2024 11:09:51 - INFO - __main__ -   Step: 655, LR: 4.918377149249739e-07, Loss: 0.46637386083602905
2024-08-04T18:09:59.854525879Z 
 11%|█▏        | 656/5712 [1:31:51<11:47:17,  8.39s/it]08/04/2024 11:09:59 - INFO - __main__ -   Step: 656, LR: 4.91740436294657e-07, Loss: 0.6742936372756958
2024-08-04T18:10:08.111882911Z 
 12%|█▏        | 657/5712 [1:31:59<11:43:42,  8.35s/it]08/04/2024 11:10:08 - INFO - __main__ -   Step: 657, LR: 4.916431576643401e-07, Loss: 0.5274267792701721
2024-08-04T18:10:16.427020356Z 
 12%|█▏        | 658/5712 [1:32:07<11:42:37,  8.34s/it]08/04/2024 11:10:16 - INFO - __main__ -   Step: 658, LR: 4.915458790340232e-07, Loss: 0.4711121916770935
2024-08-04T18:10:25.570707781Z 
 12%|█▏        | 659/5712 [1:32:16<12:02:45,  8.58s/it]08/04/2024 11:10:25 - INFO - __main__ -   Step: 659, LR: 4.914486004037063e-07, Loss: 0.5872468948364258
2024-08-04T18:10:33.787789539Z 
 12%|█▏        | 660/5712 [1:32:24<11:53:23,  8.47s/it]08/04/2024 11:10:33 - INFO - __main__ -   Step: 660, LR: 4.913513217733894e-07, Loss: 0.5252419710159302
2024-08-04T18:10:41.709520802Z 
 12%|█▏        | 661/5712 [1:32:32<11:39:20,  8.31s/it]08/04/2024 11:10:41 - INFO - __main__ -   Step: 661, LR: 4.912540431430726e-07, Loss: 0.44252508878707886
2024-08-04T18:10:49.968431850Z 
 12%|█▏        | 662/5712 [1:32:41<11:37:58,  8.29s/it]08/04/2024 11:10:49 - INFO - __main__ -   Step: 662, LR: 4.911567645127557e-07, Loss: 0.5263016223907471
2024-08-04T18:10:58.567421874Z 
 12%|█▏        | 663/5712 [1:32:49<11:45:34,  8.38s/it]08/04/2024 11:10:58 - INFO - __main__ -   Step: 663, LR: 4.910594858824388e-07, Loss: 0.46277788281440735
2024-08-04T18:11:07.625815863Z 
 12%|█▏        | 664/5712 [1:32:58<12:02:25,  8.59s/it]08/04/2024 11:11:07 - INFO - __main__ -   Step: 664, LR: 4.909622072521219e-07, Loss: 0.5172041654586792
2024-08-04T18:11:16.041642947Z 
 12%|█▏        | 665/5712 [1:33:07<11:57:58,  8.54s/it]08/04/2024 11:11:16 - INFO - __main__ -   Step: 665, LR: 4.908649286218051e-07, Loss: 0.4276049733161926
2024-08-04T18:11:23.947863920Z 
 12%|█▏        | 666/5712 [1:33:15<11:41:57,  8.35s/it]08/04/2024 11:11:23 - INFO - __main__ -   Step: 666, LR: 4.907676499914882e-07, Loss: 0.531859278678894
2024-08-04T18:11:32.110194318Z 
 12%|█▏        | 667/5712 [1:33:23<11:37:10,  8.29s/it]08/04/2024 11:11:32 - INFO - __main__ -   Step: 667, LR: 4.906703713611713e-07, Loss: 0.448839008808136
2024-08-04T18:11:41.154168643Z 
 12%|█▏        | 668/5712 [1:33:32<11:56:00,  8.52s/it]08/04/2024 11:11:41 - INFO - __main__ -   Step: 668, LR: 4.905730927308544e-07, Loss: 0.43216222524642944
2024-08-04T18:11:50.188794867Z 
 12%|█▏        | 669/5712 [1:33:41<12:08:55,  8.67s/it]08/04/2024 11:11:50 - INFO - __main__ -   Step: 669, LR: 4.904758141005375e-07, Loss: 0.46347588300704956
2024-08-04T18:11:58.234233355Z 
 12%|█▏        | 670/5712 [1:33:49<11:52:58,  8.48s/it]08/04/2024 11:11:58 - INFO - __main__ -   Step: 670, LR: 4.903785354702206e-07, Loss: 0.5074610114097595
2024-08-04T18:12:06.640814635Z 
 12%|█▏        | 671/5712 [1:33:57<11:50:52,  8.46s/it]08/04/2024 11:12:06 - INFO - __main__ -   Step: 671, LR: 4.902812568399037e-07, Loss: 0.6086021661758423
2024-08-04T18:12:15.309983996Z 
 12%|█▏        | 672/5712 [1:34:06<11:55:58,  8.52s/it]08/04/2024 11:12:15 - INFO - __main__ -   Step: 672, LR: 4.901839782095868e-07, Loss: 0.5329370498657227
2024-08-04T18:12:24.304175492Z 
 12%|█▏        | 673/5712 [1:34:15<12:07:41,  8.66s/it]08/04/2024 11:12:24 - INFO - __main__ -   Step: 673, LR: 4.900866995792699e-07, Loss: 0.5051247477531433
2024-08-04T18:12:32.907339494Z 
 12%|█▏        | 674/5712 [1:34:24<12:05:59,  8.65s/it]08/04/2024 11:12:32 - INFO - __main__ -   Step: 674, LR: 4.899894209489531e-07, Loss: 0.4808928370475769
2024-08-04T18:12:41.097908927Z 
 12%|█▏        | 675/5712 [1:34:32<11:54:22,  8.51s/it]08/04/2024 11:12:41 - INFO - __main__ -   Step: 675, LR: 4.898921423186362e-07, Loss: 0.6359398365020752
2024-08-04T18:12:49.459351367Z 
 12%|█▏        | 676/5712 [1:34:40<11:50:30,  8.47s/it]08/04/2024 11:12:49 - INFO - __main__ -   Step: 676, LR: 4.897948636883193e-07, Loss: 0.5121116638183594
2024-08-04T18:12:57.807025362Z 
 12%|█▏        | 677/5712 [1:34:48<11:47:23,  8.43s/it]08/04/2024 11:12:57 - INFO - __main__ -   Step: 677, LR: 4.896975850580024e-07, Loss: 0.4715157151222229
2024-08-04T18:13:06.395869898Z 
 12%|█▏        | 678/5712 [1:34:57<11:51:16,  8.48s/it]08/04/2024 11:13:06 - INFO - __main__ -   Step: 678, LR: 4.896003064276855e-07, Loss: 0.47868502140045166
2024-08-04T18:13:15.016721482Z 
 12%|█▏        | 679/5712 [1:35:06<11:54:43,  8.52s/it]08/04/2024 11:13:15 - INFO - __main__ -   Step: 679, LR: 4.895030277973686e-07, Loss: 0.38547417521476746
2024-08-04T18:13:23.519374007Z 
 12%|█▏        | 680/5712 [1:35:14<11:54:08,  8.52s/it]08/04/2024 11:13:23 - INFO - __main__ -   Step: 680, LR: 4.894057491670517e-07, Loss: 0.59614098072052
2024-08-04T18:13:32.425523066Z 
 12%|█▏        | 681/5712 [1:35:23<12:03:49,  8.63s/it]08/04/2024 11:13:32 - INFO - __main__ -   Step: 681, LR: 4.893084705367347e-07, Loss: 0.6309576034545898
2024-08-04T18:13:40.396391065Z 
 12%|█▏        | 682/5712 [1:35:31<11:47:03,  8.43s/it]08/04/2024 11:13:40 - INFO - __main__ -   Step: 682, LR: 4.89211191906418e-07, Loss: 0.6418415307998657
2024-08-04T18:13:49.093266198Z 
 12%|█▏        | 683/5712 [1:35:40<11:53:31,  8.51s/it]08/04/2024 11:13:49 - INFO - __main__ -   Step: 683, LR: 4.891139132761011e-07, Loss: 0.5938323736190796
2024-08-04T18:13:57.600584403Z 
 12%|█▏        | 684/5712 [1:35:48<11:53:13,  8.51s/it]08/04/2024 11:13:57 - INFO - __main__ -   Step: 684, LR: 4.890166346457842e-07, Loss: 0.42632901668548584
2024-08-04T18:14:06.211316420Z 
 12%|█▏        | 685/5712 [1:35:57<11:55:35,  8.54s/it]08/04/2024 11:14:06 - INFO - __main__ -   Step: 685, LR: 4.889193560154673e-07, Loss: 0.5594150424003601
2024-08-04T18:14:14.743971607Z 
 12%|█▏        | 686/5712 [1:36:05<11:55:14,  8.54s/it]08/04/2024 11:14:14 - INFO - __main__ -   Step: 686, LR: 4.888220773851505e-07, Loss: 0.5729551911354065
2024-08-04T18:14:22.956594302Z 
 12%|█▏        | 687/5712 [1:36:14<11:46:55,  8.44s/it]08/04/2024 11:14:22 - INFO - __main__ -   Step: 687, LR: 4.887247987548336e-07, Loss: 0.44707390666007996
2024-08-04T18:14:32.598094051Z 
 12%|█▏        | 688/5712 [1:36:23<12:16:56,  8.80s/it]08/04/2024 11:14:32 - INFO - __main__ -   Step: 688, LR: 4.886275201245167e-07, Loss: 0.5606340169906616
2024-08-04T18:14:41.124138013Z 
 12%|█▏        | 689/5712 [1:36:32<12:09:53,  8.72s/it]08/04/2024 11:14:41 - INFO - __main__ -   Step: 689, LR: 4.885302414941998e-07, Loss: 0.5878361463546753
2024-08-04T18:14:49.699298862Z 
 12%|█▏        | 690/5712 [1:36:40<12:06:07,  8.68s/it]08/04/2024 11:14:49 - INFO - __main__ -   Step: 690, LR: 4.884329628638829e-07, Loss: 0.4762330651283264
2024-08-04T18:14:57.652102541Z 
 12%|█▏        | 691/5712 [1:36:48<11:47:50,  8.46s/it]08/04/2024 11:14:57 - INFO - __main__ -   Step: 691, LR: 4.88335684233566e-07, Loss: 0.5137606859207153
2024-08-04T18:15:06.422526527Z 
 12%|█▏        | 692/5712 [1:36:57<11:55:32,  8.55s/it]08/04/2024 11:15:06 - INFO - __main__ -   Step: 692, LR: 4.88238405603249e-07, Loss: 0.40904921293258667
2024-08-04T18:15:14.876085645Z 
 12%|█▏        | 693/5712 [1:37:06<11:52:55,  8.52s/it]08/04/2024 11:15:14 - INFO - __main__ -   Step: 693, LR: 4.881411269729321e-07, Loss: 0.6444311738014221
2024-08-04T18:15:23.446262559Z 
 12%|█▏        | 694/5712 [1:37:14<11:53:57,  8.54s/it]08/04/2024 11:15:23 - INFO - __main__ -   Step: 694, LR: 4.880438483426154e-07, Loss: 0.48083019256591797
2024-08-04T18:15:32.371855678Z 
 12%|█▏        | 695/5712 [1:37:23<12:03:35,  8.65s/it]08/04/2024 11:15:32 - INFO - __main__ -   Step: 695, LR: 4.879465697122985e-07, Loss: 0.54356849193573
2024-08-04T18:15:40.956616790Z 
 12%|█▏        | 696/5712 [1:37:32<12:01:42,  8.63s/it]08/04/2024 11:15:40 - INFO - __main__ -   Step: 696, LR: 4.878492910819816e-07, Loss: 0.6534260511398315
2024-08-04T18:15:49.506052472Z 
 12%|█▏        | 697/5712 [1:37:40<11:59:28,  8.61s/it]08/04/2024 11:15:49 - INFO - __main__ -   Step: 697, LR: 4.877520124516647e-07, Loss: 0.5050735473632812
2024-08-04T18:15:57.811437710Z 
 12%|█▏        | 698/5712 [1:37:48<11:51:44,  8.52s/it]08/04/2024 11:15:57 - INFO - __main__ -   Step: 698, LR: 4.876547338213478e-07, Loss: 0.46537885069847107
2024-08-04T18:16:06.008748225Z 
 12%|█▏        | 699/5712 [1:37:57<11:43:35,  8.42s/it]08/04/2024 11:16:06 - INFO - __main__ -   Step: 699, LR: 4.875574551910308e-07, Loss: 0.5754173994064331
2024-08-04T18:16:13.968875230Z 
 12%|█▏        | 700/5712 [1:38:05<11:31:53,  8.28s/it]08/04/2024 11:16:13 - INFO - __main__ -   Step: 700, LR: 4.87460176560714e-07, Loss: 0.5776852965354919
2024-08-04T18:16:22.296437769Z 
 12%|█▏        | 701/5712 [1:38:13<11:32:52,  8.30s/it]08/04/2024 11:16:22 - INFO - __main__ -   Step: 701, LR: 4.873628979303972e-07, Loss: 0.5089195370674133
2024-08-04T18:16:30.841517967Z 
 12%|█▏        | 702/5712 [1:38:21<11:38:58,  8.37s/it]08/04/2024 11:16:30 - INFO - __main__ -   Step: 702, LR: 4.872656193000803e-07, Loss: 0.5351481437683105
2024-08-04T18:16:39.057138530Z 
 12%|█▏        | 703/5712 [1:38:30<11:34:56,  8.32s/it]08/04/2024 11:16:39 - INFO - __main__ -   Step: 703, LR: 4.871683406697634e-07, Loss: 0.49041759967803955
2024-08-04T18:16:47.454206319Z 
 12%|█▏        | 704/5712 [1:38:38<11:36:37,  8.35s/it]08/04/2024 11:16:47 - INFO - __main__ -   Step: 704, LR: 4.870710620394465e-07, Loss: 0.4276914596557617
2024-08-04T18:16:56.247582914Z 
 12%|█▏        | 705/5712 [1:38:47<11:47:40,  8.48s/it]08/04/2024 11:16:56 - INFO - __main__ -   Step: 705, LR: 4.869737834091296e-07, Loss: 0.4472646117210388
2024-08-04T18:17:04.680578817Z 
 12%|█▏        | 706/5712 [1:38:55<11:46:21,  8.47s/it]08/04/2024 11:17:04 - INFO - __main__ -   Step: 706, LR: 4.868765047788128e-07, Loss: 0.41542530059814453
2024-08-04T18:17:13.343006843Z 
 12%|█▏        | 707/5712 [1:39:04<11:51:07,  8.52s/it]08/04/2024 11:17:13 - INFO - __main__ -   Step: 707, LR: 4.867792261484959e-07, Loss: 0.5407804250717163
2024-08-04T18:17:21.575812972Z 
 12%|█▏        | 708/5712 [1:39:12<11:43:40,  8.44s/it]08/04/2024 11:17:21 - INFO - __main__ -   Step: 708, LR: 4.86681947518179e-07, Loss: 0.5226699113845825
2024-08-04T18:17:29.801863311Z 
 12%|█▏        | 709/5712 [1:39:20<11:38:14,  8.37s/it]08/04/2024 11:17:29 - INFO - __main__ -   Step: 709, LR: 4.86584668887862e-07, Loss: 0.4749296307563782
2024-08-04T18:17:38.665798477Z 
 12%|█▏        | 710/5712 [1:39:29<11:50:21,  8.52s/it]08/04/2024 11:17:38 - INFO - __main__ -   Step: 710, LR: 4.864873902575452e-07, Loss: 0.46954208612442017
2024-08-04T18:17:47.315527980Z 
 12%|█▏        | 711/5712 [1:39:38<11:53:26,  8.56s/it]08/04/2024 11:17:47 - INFO - __main__ -   Step: 711, LR: 4.863901116272283e-07, Loss: 0.5993322730064392
2024-08-04T18:17:55.769624916Z 
 12%|█▏        | 712/5712 [1:39:46<11:50:40,  8.53s/it]08/04/2024 11:17:55 - INFO - __main__ -   Step: 712, LR: 4.862928329969113e-07, Loss: 0.49651020765304565
2024-08-04T18:18:04.455493228Z 
 12%|█▏        | 713/5712 [1:39:55<11:54:27,  8.58s/it]08/04/2024 11:18:04 - INFO - __main__ -   Step: 713, LR: 4.861955543665944e-07, Loss: 0.4549102783203125
2024-08-04T18:18:12.693454948Z 
 12%|█▎        | 714/5712 [1:40:03<11:45:53,  8.47s/it]08/04/2024 11:18:12 - INFO - __main__ -   Step: 714, LR: 4.860982757362775e-07, Loss: 0.450594961643219
2024-08-04T18:18:21.262051289Z 
 13%|█▎        | 715/5712 [1:40:12<11:48:06,  8.50s/it]08/04/2024 11:18:21 - INFO - __main__ -   Step: 715, LR: 4.860009971059608e-07, Loss: 0.48679468035697937
2024-08-04T18:18:29.656944164Z 
 13%|█▎        | 716/5712 [1:40:20<11:45:16,  8.47s/it]08/04/2024 11:18:29 - INFO - __main__ -   Step: 716, LR: 4.859037184756439e-07, Loss: 0.439552903175354
2024-08-04T18:18:38.135985405Z 
 13%|█▎        | 717/5712 [1:40:29<11:45:21,  8.47s/it]08/04/2024 11:18:38 - INFO - __main__ -   Step: 717, LR: 4.85806439845327e-07, Loss: 0.3824918866157532
2024-08-04T18:18:46.454814681Z 
 13%|█▎        | 718/5712 [1:40:37<11:41:22,  8.43s/it]08/04/2024 11:18:46 - INFO - __main__ -   Step: 718, LR: 4.8570916121501e-07, Loss: 0.4965572655200958
2024-08-04T18:18:54.875422729Z 
 13%|█▎        | 719/5712 [1:40:46<11:41:05,  8.42s/it]08/04/2024 11:18:54 - INFO - __main__ -   Step: 719, LR: 4.856118825846933e-07, Loss: 0.506646454334259
2024-08-04T18:19:03.537043803Z 
 13%|█▎        | 720/5712 [1:40:54<11:46:51,  8.50s/it]08/04/2024 11:19:03 - INFO - __main__ -   Step: 720, LR: 4.855146039543764e-07, Loss: 0.4232723116874695
2024-08-04T18:19:11.608800824Z 
 13%|█▎        | 721/5712 [1:41:02<11:36:08,  8.37s/it]08/04/2024 11:19:11 - INFO - __main__ -   Step: 721, LR: 4.854173253240595e-07, Loss: 0.48185238242149353
2024-08-04T18:19:20.358836746Z 
 13%|█▎        | 722/5712 [1:41:11<11:45:30,  8.48s/it]08/04/2024 11:19:20 - INFO - __main__ -   Step: 722, LR: 4.853200466937426e-07, Loss: 0.40683525800704956
2024-08-04T18:19:29.139127548Z 
 13%|█▎        | 723/5712 [1:41:20<11:52:46,  8.57s/it]08/04/2024 11:19:29 - INFO - __main__ -   Step: 723, LR: 4.852227680634257e-07, Loss: 0.5555527210235596
2024-08-04T18:19:37.352569420Z 
 13%|█▎        | 724/5712 [1:41:28<11:43:40,  8.46s/it]08/04/2024 11:19:37 - INFO - __main__ -   Step: 724, LR: 4.851254894331087e-07, Loss: 0.6366521120071411
2024-08-04T18:19:45.567038628Z 
 13%|█▎        | 725/5712 [1:41:36<11:37:18,  8.39s/it]08/04/2024 11:19:45 - INFO - __main__ -   Step: 725, LR: 4.850282108027918e-07, Loss: 0.3755643665790558
2024-08-04T18:19:53.870782097Z 
 13%|█▎        | 726/5712 [1:41:45<11:35:01,  8.36s/it]08/04/2024 11:19:53 - INFO - __main__ -   Step: 726, LR: 4.84930932172475e-07, Loss: 0.5138546228408813
2024-08-04T18:20:02.271086268Z 
 13%|█▎        | 727/5712 [1:41:53<11:35:48,  8.37s/it]08/04/2024 11:20:02 - INFO - __main__ -   Step: 727, LR: 4.848336535421582e-07, Loss: 0.3890896737575531
2024-08-04T18:20:10.975637270Z 
 13%|█▎        | 728/5712 [1:42:02<11:43:52,  8.47s/it]08/04/2024 11:20:10 - INFO - __main__ -   Step: 728, LR: 4.847363749118413e-07, Loss: 0.6396610736846924
2024-08-04T18:20:18.971845694Z 
 13%|█▎        | 729/5712 [1:42:10<11:31:50,  8.33s/it]08/04/2024 11:20:18 - INFO - __main__ -   Step: 729, LR: 4.846390962815244e-07, Loss: 0.48041728138923645
2024-08-04T18:20:27.899945309Z 
 13%|█▎        | 730/5712 [1:42:19<11:46:35,  8.51s/it]08/04/2024 11:20:27 - INFO - __main__ -   Step: 730, LR: 4.845418176512074e-07, Loss: 0.4367157816886902
2024-08-04T18:20:36.551517282Z 
 13%|█▎        | 731/5712 [1:42:27<11:49:59,  8.55s/it]08/04/2024 11:20:36 - INFO - __main__ -   Step: 731, LR: 4.844445390208905e-07, Loss: 0.40585243701934814
2024-08-04T18:20:45.702863410Z 
 13%|█▎        | 732/5712 [1:42:36<12:04:44,  8.73s/it]08/04/2024 11:20:45 - INFO - __main__ -   Step: 732, LR: 4.843472603905736e-07, Loss: 0.44666218757629395
2024-08-04T18:20:53.983841468Z 
 13%|█▎        | 733/5712 [1:42:45<11:53:22,  8.60s/it]08/04/2024 11:20:53 - INFO - __main__ -   Step: 733, LR: 4.842499817602567e-07, Loss: 0.5274958610534668
2024-08-04T18:21:02.561644526Z 
 13%|█▎        | 734/5712 [1:42:53<11:52:46,  8.59s/it]08/04/2024 11:21:02 - INFO - __main__ -   Step: 734, LR: 4.841527031299398e-07, Loss: 0.4564253091812134
2024-08-04T18:21:10.497089232Z 
 13%|█▎        | 735/5712 [1:43:01<11:36:18,  8.39s/it]08/04/2024 11:21:10 - INFO - __main__ -   Step: 735, LR: 4.84055424499623e-07, Loss: 0.4969336986541748
2024-08-04T18:21:19.314072633Z 
 13%|█▎        | 736/5712 [1:43:10<11:46:41,  8.52s/it]08/04/2024 11:21:19 - INFO - __main__ -   Step: 736, LR: 4.839581458693061e-07, Loss: 0.5502418279647827
2024-08-04T18:21:28.475895971Z 
 13%|█▎        | 737/5712 [1:43:19<12:02:28,  8.71s/it]08/04/2024 11:21:28 - INFO - __main__ -   Step: 737, LR: 4.838608672389892e-07, Loss: 0.5337332487106323
2024-08-04T18:21:36.956725316Z 
 13%|█▎        | 738/5712 [1:43:28<11:56:33,  8.64s/it]08/04/2024 11:21:36 - INFO - __main__ -   Step: 738, LR: 4.837635886086723e-07, Loss: 0.43623048067092896
2024-08-04T18:21:45.186171878Z 
 13%|█▎        | 739/5712 [1:43:36<11:46:06,  8.52s/it]08/04/2024 11:21:45 - INFO - __main__ -   Step: 739, LR: 4.836663099783556e-07, Loss: 0.4626461863517761
2024-08-04T18:21:53.683760332Z 
 13%|█▎        | 740/5712 [1:43:44<11:45:25,  8.51s/it]08/04/2024 11:21:53 - INFO - __main__ -   Step: 740, LR: 4.835690313480387e-07, Loss: 0.48147058486938477
2024-08-04T18:22:02.409534028Z 
 13%|█▎        | 741/5712 [1:43:53<11:50:35,  8.58s/it]08/04/2024 11:22:02 - INFO - __main__ -   Step: 741, LR: 4.834717527177218e-07, Loss: 0.46921372413635254
2024-08-04T18:22:11.086662829Z 
 13%|█▎        | 742/5712 [1:44:02<11:52:54,  8.61s/it]08/04/2024 11:22:11 - INFO - __main__ -   Step: 742, LR: 4.833744740874049e-07, Loss: 0.6143388748168945
2024-08-04T18:22:19.058172870Z 
 13%|█▎        | 743/5712 [1:44:10<11:37:01,  8.42s/it]08/04/2024 11:22:19 - INFO - __main__ -   Step: 743, LR: 4.83277195457088e-07, Loss: 0.5777302384376526
2024-08-04T18:22:27.823182787Z 
 13%|█▎        | 744/5712 [1:44:18<11:45:31,  8.52s/it]08/04/2024 11:22:27 - INFO - __main__ -   Step: 744, LR: 4.83179916826771e-07, Loss: 0.5344483852386475
2024-08-04T18:22:36.231096406Z 
 13%|█▎        | 745/5712 [1:44:27<11:42:34,  8.49s/it]08/04/2024 11:22:36 - INFO - __main__ -   Step: 745, LR: 4.830826381964541e-07, Loss: 0.4976078271865845
2024-08-04T18:22:44.948074013Z 
 13%|█▎        | 746/5712 [1:44:36<11:48:09,  8.56s/it]08/04/2024 11:22:44 - INFO - __main__ -   Step: 746, LR: 4.829853595661372e-07, Loss: 0.5552849769592285
2024-08-04T18:22:53.184479753Z 
 13%|█▎        | 747/5712 [1:44:44<11:40:04,  8.46s/it]08/04/2024 11:22:53 - INFO - __main__ -   Step: 747, LR: 4.828880809358203e-07, Loss: 0.5011114478111267
2024-08-04T18:23:01.429506590Z 
 13%|█▎        | 748/5712 [1:44:52<11:34:36,  8.40s/it]08/04/2024 11:23:01 - INFO - __main__ -   Step: 748, LR: 4.827908023055036e-07, Loss: 0.4709899127483368
2024-08-04T18:23:09.990877820Z 
 13%|█▎        | 749/5712 [1:45:01<11:38:34,  8.45s/it]08/04/2024 11:23:09 - INFO - __main__ -   Step: 749, LR: 4.826935236751866e-07, Loss: 0.4204264283180237
2024-08-04T18:23:18.434513109Z 
 13%|█▎        | 750/5712 [1:45:09<11:38:23,  8.44s/it]08/04/2024 11:23:18 - INFO - __main__ -   Step: 750, LR: 4.825962450448697e-07, Loss: 0.4703771471977234
2024-08-04T18:23:26.731296739Z 
 13%|█▎        | 751/5712 [1:45:17<11:34:34,  8.40s/it]08/04/2024 11:23:26 - INFO - __main__ -   Step: 751, LR: 4.824989664145528e-07, Loss: 0.5393639206886292
2024-08-04T18:23:35.382362716Z 
 13%|█▎        | 752/5712 [1:45:26<11:40:39,  8.48s/it]08/04/2024 11:23:35 - INFO - __main__ -   Step: 752, LR: 4.824016877842359e-07, Loss: 0.49181067943573
2024-08-04T18:23:44.260179483Z 
 13%|█▎        | 753/5712 [1:45:35<11:50:28,  8.60s/it]08/04/2024 11:23:44 - INFO - __main__ -   Step: 753, LR: 4.82304409153919e-07, Loss: 0.47245845198631287
2024-08-04T18:23:52.436371298Z 
 13%|█▎        | 754/5712 [1:45:43<11:39:55,  8.47s/it]08/04/2024 11:23:52 - INFO - __main__ -   Step: 754, LR: 4.822071305236021e-07, Loss: 0.44888660311698914
2024-08-04T18:24:00.981918630Z 
 13%|█▎        | 755/5712 [1:45:52<11:41:38,  8.49s/it]08/04/2024 11:24:00 - INFO - __main__ -   Step: 755, LR: 4.821098518932853e-07, Loss: 0.573062539100647
2024-08-04T18:24:09.228221781Z 
 13%|█▎        | 756/5712 [1:46:00<11:35:24,  8.42s/it]08/04/2024 11:24:09 - INFO - __main__ -   Step: 756, LR: 4.820125732629684e-07, Loss: 0.4315025806427002
2024-08-04T18:24:17.745796050Z 
 13%|█▎        | 757/5712 [1:46:08<11:37:42,  8.45s/it]08/04/2024 11:24:17 - INFO - __main__ -   Step: 757, LR: 4.819152946326515e-07, Loss: 0.5142350792884827
2024-08-04T18:24:26.358161912Z 
 13%|█▎        | 758/5712 [1:46:17<11:41:37,  8.50s/it]08/04/2024 11:24:26 - INFO - __main__ -   Step: 758, LR: 4.818180160023346e-07, Loss: 0.4913644790649414
2024-08-04T18:24:34.891831282Z 
 13%|█▎        | 759/5712 [1:46:26<11:42:21,  8.51s/it]08/04/2024 11:24:34 - INFO - __main__ -   Step: 759, LR: 4.817207373720177e-07, Loss: 0.5699934363365173
2024-08-04T18:24:43.390033708Z 
 13%|█▎        | 760/5712 [1:46:34<11:41:58,  8.51s/it]08/04/2024 11:24:43 - INFO - __main__ -   Step: 760, LR: 4.81623458741701e-07, Loss: 0.513388991355896
2024-08-04T18:24:51.905453020Z 
 13%|█▎        | 761/5712 [1:46:43<11:42:04,  8.51s/it]08/04/2024 11:24:51 - INFO - __main__ -   Step: 761, LR: 4.81526180111384e-07, Loss: 0.5530635118484497
2024-08-04T18:25:00.201823616Z 
 13%|█▎        | 762/5712 [1:46:51<11:36:41,  8.44s/it]08/04/2024 11:25:00 - INFO - __main__ -   Step: 762, LR: 4.814289014810671e-07, Loss: 0.5683826208114624
2024-08-04T18:25:09.132889760Z 
 13%|█▎        | 763/5712 [1:47:00<11:48:34,  8.59s/it]08/04/2024 11:25:09 - INFO - __main__ -   Step: 763, LR: 4.813316228507502e-07, Loss: 0.4703017473220825
2024-08-04T18:25:17.668752923Z 
 13%|█▎        | 764/5712 [1:47:08<11:47:05,  8.57s/it]08/04/2024 11:25:17 - INFO - __main__ -   Step: 764, LR: 4.812343442204333e-07, Loss: 0.5374124050140381
2024-08-04T18:25:25.851371033Z 
 13%|█▎        | 765/5712 [1:47:16<11:37:15,  8.46s/it]08/04/2024 11:25:25 - INFO - __main__ -   Step: 765, LR: 4.811370655901164e-07, Loss: 0.6303085684776306
2024-08-04T18:25:34.668592533Z 
 13%|█▎        | 766/5712 [1:47:25<11:46:01,  8.56s/it]08/04/2024 11:25:34 - INFO - __main__ -   Step: 766, LR: 4.810397869597995e-07, Loss: 0.573055624961853
2024-08-04T18:25:42.756640754Z 
 13%|█▎        | 767/5712 [1:47:33<11:34:05,  8.42s/it]08/04/2024 11:25:42 - INFO - __main__ -   Step: 767, LR: 4.809425083294826e-07, Loss: 0.5434346199035645
2024-08-04T18:25:51.282570239Z 
 13%|█▎        | 768/5712 [1:47:42<11:36:31,  8.45s/it]08/04/2024 11:25:51 - INFO - __main__ -   Step: 768, LR: 4.808452296991658e-07, Loss: 0.5326634645462036
2024-08-04T18:26:00.112983023Z 
 13%|█▎        | 769/5712 [1:47:51<11:45:43,  8.57s/it]08/04/2024 11:26:00 - INFO - __main__ -   Step: 769, LR: 4.80747951068849e-07, Loss: 0.4731677174568176
2024-08-04T18:26:08.294630186Z 
 13%|█▎        | 770/5712 [1:47:59<11:36:04,  8.45s/it]08/04/2024 11:26:08 - INFO - __main__ -   Step: 770, LR: 4.80650672438532e-07, Loss: 0.6476494073867798
2024-08-04T18:26:16.639914243Z 
 13%|█▎        | 771/5712 [1:48:07<11:33:19,  8.42s/it]08/04/2024 11:26:16 - INFO - __main__ -   Step: 771, LR: 4.805533938082151e-07, Loss: 0.4323786795139313
2024-08-04T18:26:25.020219007Z 
 14%|█▎        | 772/5712 [1:48:16<11:32:13,  8.41s/it]08/04/2024 11:26:25 - INFO - __main__ -   Step: 772, LR: 4.804561151778982e-07, Loss: 0.6206437349319458
2024-08-04T18:26:33.363723520Z 
 14%|█▎        | 773/5712 [1:48:24<11:30:30,  8.39s/it]08/04/2024 11:26:33 - INFO - __main__ -   Step: 773, LR: 4.803588365475814e-07, Loss: 0.3663034737110138
2024-08-04T18:26:41.996779141Z 
 14%|█▎        | 774/5712 [1:48:33<11:36:23,  8.46s/it]08/04/2024 11:26:41 - INFO - __main__ -   Step: 774, LR: 4.802615579172645e-07, Loss: 0.4003424346446991
2024-08-04T18:26:50.616562223Z 
 14%|█▎        | 775/5712 [1:48:41<11:40:09,  8.51s/it]08/04/2024 11:26:50 - INFO - __main__ -   Step: 775, LR: 4.801642792869476e-07, Loss: 0.5210422277450562
2024-08-04T18:26:59.090042457Z 
 14%|█▎        | 776/5712 [1:48:50<11:39:06,  8.50s/it]08/04/2024 11:26:59 - INFO - __main__ -   Step: 776, LR: 4.800670006566307e-07, Loss: 0.46239936351776123
2024-08-04T18:27:08.164900489Z 
 14%|█▎        | 777/5712 [1:48:59<11:53:13,  8.67s/it]08/04/2024 11:27:08 - INFO - __main__ -   Step: 777, LR: 4.799697220263138e-07, Loss: 0.4110376238822937
2024-08-04T18:27:16.410351969Z 
 14%|█▎        | 778/5712 [1:49:07<11:42:34,  8.54s/it]08/04/2024 11:27:16 - INFO - __main__ -   Step: 778, LR: 4.798724433959969e-07, Loss: 0.44686952233314514
2024-08-04T18:27:24.801491644Z 
 14%|█▎        | 779/5712 [1:49:15<11:38:40,  8.50s/it]08/04/2024 11:27:24 - INFO - __main__ -   Step: 779, LR: 4.7977516476568e-07, Loss: 0.45763272047042847
2024-08-04T18:27:33.858704798Z 
 14%|█▎        | 780/5712 [1:49:25<11:52:19,  8.67s/it]08/04/2024 11:27:33 - INFO - __main__ -   Step: 780, LR: 4.796778861353632e-07, Loss: 0.6854270696640015
2024-08-04T18:27:41.793387933Z 
 14%|█▎        | 781/5712 [1:49:32<11:34:09,  8.45s/it]08/04/2024 11:27:41 - INFO - __main__ -   Step: 781, LR: 4.795806075050463e-07, Loss: 0.5105180740356445
2024-08-04T18:27:50.013794675Z 
 14%|█▎        | 782/5712 [1:49:41<11:28:26,  8.38s/it]08/04/2024 11:27:50 - INFO - __main__ -   Step: 782, LR: 4.794833288747294e-07, Loss: 0.46688807010650635
2024-08-04T18:27:58.370935764Z 
 14%|█▎        | 783/5712 [1:49:49<11:27:45,  8.37s/it]08/04/2024 11:27:58 - INFO - __main__ -   Step: 783, LR: 4.793860502444125e-07, Loss: 0.47831952571868896
2024-08-04T18:28:06.475892098Z 
 14%|█▎        | 784/5712 [1:49:57<11:21:03,  8.29s/it]08/04/2024 11:28:06 - INFO - __main__ -   Step: 784, LR: 4.792887716140956e-07, Loss: 0.47498977184295654
2024-08-04T18:28:15.097697071Z 
 14%|█▎        | 785/5712 [1:50:06<11:29:02,  8.39s/it]08/04/2024 11:28:15 - INFO - __main__ -   Step: 785, LR: 4.791914929837787e-07, Loss: 0.3660803437232971
2024-08-04T18:28:23.767945700Z 
 14%|█▍        | 786/5712 [1:50:14<11:35:46,  8.47s/it]08/04/2024 11:28:23 - INFO - __main__ -   Step: 786, LR: 4.790942143534618e-07, Loss: 0.5336408615112305
2024-08-04T18:28:32.142418821Z 
 14%|█▍        | 787/5712 [1:50:23<11:33:09,  8.44s/it]08/04/2024 11:28:32 - INFO - __main__ -   Step: 787, LR: 4.789969357231449e-07, Loss: 0.5286176204681396
2024-08-04T18:28:40.500900824Z 
 14%|█▍        | 788/5712 [1:50:31<11:30:54,  8.42s/it]08/04/2024 11:28:40 - INFO - __main__ -   Step: 788, LR: 4.78899657092828e-07, Loss: 0.4323102831840515
2024-08-04T18:28:48.915713973Z 
 14%|█▍        | 789/5712 [1:50:40<11:30:40,  8.42s/it]08/04/2024 11:28:48 - INFO - __main__ -   Step: 789, LR: 4.788023784625112e-07, Loss: 0.5449865460395813
2024-08-04T18:28:57.632003406Z 
 14%|█▍        | 790/5712 [1:50:48<11:37:52,  8.51s/it]08/04/2024 11:28:57 - INFO - __main__ -   Step: 790, LR: 4.787050998321943e-07, Loss: 0.4611559808254242
2024-08-04T18:29:06.062667200Z 
 14%|█▍        | 791/5712 [1:50:57<11:35:50,  8.48s/it]08/04/2024 11:29:06 - INFO - __main__ -   Step: 791, LR: 4.786078212018774e-07, Loss: 0.553341269493103
2024-08-04T18:29:14.292924521Z 
 14%|█▍        | 792/5712 [1:51:05<11:29:27,  8.41s/it]08/04/2024 11:29:14 - INFO - __main__ -   Step: 792, LR: 4.785105425715605e-07, Loss: 0.4748588800430298
2024-08-04T18:29:23.035218306Z 
 14%|█▍        | 793/5712 [1:51:14<11:37:30,  8.51s/it]08/04/2024 11:29:23 - INFO - __main__ -   Step: 793, LR: 4.784132639412437e-07, Loss: 0.5154297351837158
2024-08-04T18:29:31.990176284Z 
 14%|█▍        | 794/5712 [1:51:23<11:48:23,  8.64s/it]08/04/2024 11:29:31 - INFO - __main__ -   Step: 794, LR: 4.783159853109268e-07, Loss: 0.47541528940200806
2024-08-04T18:29:40.493740994Z 
 14%|█▍        | 795/5712 [1:51:31<11:44:50,  8.60s/it]08/04/2024 11:29:40 - INFO - __main__ -   Step: 795, LR: 4.782187066806099e-07, Loss: 0.4304894208908081
2024-08-04T18:29:48.959959069Z 
 14%|█▍        | 796/5712 [1:51:40<11:41:22,  8.56s/it]08/04/2024 11:29:48 - INFO - __main__ -   Step: 796, LR: 4.78121428050293e-07, Loss: 0.4002964198589325
2024-08-04T18:29:57.403250801Z 
 14%|█▍        | 797/5712 [1:51:48<11:38:21,  8.53s/it]08/04/2024 11:29:57 - INFO - __main__ -   Step: 797, LR: 4.780241494199761e-07, Loss: 0.3670874238014221
2024-08-04T18:30:06.009711718Z 
 14%|█▍        | 798/5712 [1:51:57<11:40:12,  8.55s/it]08/04/2024 11:30:06 - INFO - __main__ -   Step: 798, LR: 4.779268707896592e-07, Loss: 0.5167096853256226
2024-08-04T18:30:14.517068313Z 
 14%|█▍        | 799/5712 [1:52:05<11:39:01,  8.54s/it]08/04/2024 11:30:14 - INFO - __main__ -   Step: 799, LR: 4.778295921593423e-07, Loss: 0.5400388240814209
2024-08-04T18:30:23.032494484Z 
 14%|█▍        | 800/5712 [1:52:14<11:38:21,  8.53s/it]08/04/2024 11:30:23 - INFO - __main__ -   Step: 800, LR: 4.777323135290254e-07, Loss: 0.32858073711395264
2024-08-04T18:30:31.930820135Z 
 14%|█▍        | 801/5712 [1:52:23<11:47:14,  8.64s/it]08/04/2024 11:30:31 - INFO - __main__ -   Step: 801, LR: 4.776350348987086e-07, Loss: 0.600475549697876
2024-08-04T18:30:40.670591617Z 
 14%|█▍        | 802/5712 [1:52:31<11:49:32,  8.67s/it]08/04/2024 11:30:40 - INFO - __main__ -   Step: 802, LR: 4.775377562683917e-07, Loss: 0.420413076877594
2024-08-04T18:30:48.682187095Z 
 14%|█▍        | 803/5712 [1:52:39<11:33:13,  8.47s/it]08/04/2024 11:30:48 - INFO - __main__ -   Step: 803, LR: 4.774404776380748e-07, Loss: 0.40958869457244873
2024-08-04T18:30:57.224891888Z 
 14%|█▍        | 804/5712 [1:52:48<11:34:47,  8.49s/it]08/04/2024 11:30:57 - INFO - __main__ -   Step: 804, LR: 4.773431990077579e-07, Loss: 0.6468698978424072
2024-08-04T18:31:05.962845660Z 
 14%|█▍        | 805/5712 [1:52:57<11:40:38,  8.57s/it]08/04/2024 11:31:05 - INFO - __main__ -   Step: 805, LR: 4.77245920377441e-07, Loss: 0.42705342173576355
2024-08-04T18:31:14.528248344Z 
 14%|█▍        | 806/5712 [1:53:05<11:40:27,  8.57s/it]08/04/2024 11:31:14 - INFO - __main__ -   Step: 806, LR: 4.771486417471241e-07, Loss: 0.5452877283096313
2024-08-04T18:31:22.776799801Z 
 14%|█▍        | 807/5712 [1:53:13<11:32:31,  8.47s/it]08/04/2024 11:31:22 - INFO - __main__ -   Step: 807, LR: 4.770513631168072e-07, Loss: 0.5227884650230408
2024-08-04T18:31:31.054911701Z 
 14%|█▍        | 808/5712 [1:53:22<11:27:38,  8.41s/it]08/04/2024 11:31:31 - INFO - __main__ -   Step: 808, LR: 4.769540844864903e-07, Loss: 0.5035861730575562
2024-08-04T18:31:39.906865316Z 
 14%|█▍        | 809/5712 [1:53:31<11:38:15,  8.54s/it]08/04/2024 11:31:39 - INFO - __main__ -   Step: 809, LR: 4.768568058561735e-07, Loss: 0.4318178594112396
2024-08-04T18:31:48.715825660Z 
 14%|█▍        | 810/5712 [1:53:39<11:44:33,  8.62s/it]08/04/2024 11:31:48 - INFO - __main__ -   Step: 810, LR: 4.7675952722585664e-07, Loss: 0.47834643721580505
2024-08-04T18:31:56.733286387Z 
 14%|█▍        | 811/5712 [1:53:47<11:29:35,  8.44s/it]08/04/2024 11:31:56 - INFO - __main__ -   Step: 811, LR: 4.766622485955398e-07, Loss: 0.4051315486431122
2024-08-04T18:32:05.305131088Z 
 14%|█▍        | 812/5712 [1:53:56<11:32:37,  8.48s/it]08/04/2024 11:32:05 - INFO - __main__ -   Step: 812, LR: 4.765649699652229e-07, Loss: 0.43497979640960693
2024-08-04T18:32:13.566603453Z 
 14%|█▍        | 813/5712 [1:54:04<11:27:05,  8.42s/it]08/04/2024 11:32:13 - INFO - __main__ -   Step: 813, LR: 4.76467691334906e-07, Loss: 0.39152470231056213
2024-08-04T18:32:22.232502997Z 
 14%|█▍        | 814/5712 [1:54:13<11:33:06,  8.49s/it]08/04/2024 11:32:22 - INFO - __main__ -   Step: 814, LR: 4.763704127045891e-07, Loss: 0.6487880349159241
2024-08-04T18:32:30.662472806Z 
 14%|█▍        | 815/5712 [1:54:21<11:31:28,  8.47s/it]08/04/2024 11:32:30 - INFO - __main__ -   Step: 815, LR: 4.7627313407427225e-07, Loss: 0.5322000980377197
2024-08-04T18:32:38.774447280Z 
 14%|█▍        | 816/5712 [1:54:29<11:22:31,  8.36s/it]08/04/2024 11:32:38 - INFO - __main__ -   Step: 816, LR: 4.7617585544395534e-07, Loss: 0.43219509720802307
2024-08-04T18:32:47.566028248Z 
 14%|█▍        | 817/5712 [1:54:38<11:32:49,  8.49s/it]08/04/2024 11:32:47 - INFO - __main__ -   Step: 817, LR: 4.7607857681363844e-07, Loss: 0.37394416332244873
2024-08-04T18:32:56.069609129Z 
 14%|█▍        | 818/5712 [1:54:47<11:32:58,  8.50s/it]08/04/2024 11:32:56 - INFO - __main__ -   Step: 818, LR: 4.7598129818332154e-07, Loss: 0.39579954743385315
2024-08-04T18:33:04.373783072Z 
 14%|█▍        | 819/5712 [1:54:55<11:28:08,  8.44s/it]08/04/2024 11:33:04 - INFO - __main__ -   Step: 819, LR: 4.7588401955300464e-07, Loss: 0.4718399941921234
2024-08-04T18:33:12.320573867Z 
 14%|█▍        | 820/5712 [1:55:03<11:15:58,  8.29s/it]08/04/2024 11:33:12 - INFO - __main__ -   Step: 820, LR: 4.757867409226878e-07, Loss: 0.5471855401992798
2024-08-04T18:33:20.858865803Z 
 14%|█▍        | 821/5712 [1:55:12<11:21:53,  8.37s/it]08/04/2024 11:33:20 - INFO - __main__ -   Step: 821, LR: 4.756894622923709e-07, Loss: 0.673158586025238
2024-08-04T18:33:28.992240608Z 
 14%|█▍        | 822/5712 [1:55:20<11:16:05,  8.30s/it]08/04/2024 11:33:28 - INFO - __main__ -   Step: 822, LR: 4.75592183662054e-07, Loss: 0.4043310880661011
2024-08-04T18:33:37.860394448Z 
 14%|█▍        | 823/5712 [1:55:29<11:29:57,  8.47s/it]08/04/2024 11:33:37 - INFO - __main__ -   Step: 823, LR: 4.754949050317371e-07, Loss: 0.47057583928108215
2024-08-04T18:33:45.608197211Z 
 14%|█▍        | 824/5712 [1:55:36<11:12:13,  8.25s/it]08/04/2024 11:33:45 - INFO - __main__ -   Step: 824, LR: 4.7539762640142024e-07, Loss: 0.5511079430580139
2024-08-04T18:33:54.524762551Z 
 14%|█▍        | 825/5712 [1:55:45<11:28:19,  8.45s/it]08/04/2024 11:33:54 - INFO - __main__ -   Step: 825, LR: 4.7530034777110334e-07, Loss: 0.5061519742012024
2024-08-04T18:34:03.901133347Z 
 14%|█▍        | 826/5712 [1:55:55<11:50:47,  8.73s/it]08/04/2024 11:34:03 - INFO - __main__ -   Step: 826, LR: 4.7520306914078644e-07, Loss: 0.4663449227809906
2024-08-04T18:34:12.547899003Z 
 14%|█▍        | 827/5712 [1:56:03<11:48:39,  8.70s/it]08/04/2024 11:34:12 - INFO - __main__ -   Step: 827, LR: 4.751057905104696e-07, Loss: 0.47178906202316284
2024-08-04T18:34:20.518807574Z 
 14%|█▍        | 828/5712 [1:56:11<11:30:36,  8.48s/it]08/04/2024 11:34:20 - INFO - __main__ -   Step: 828, LR: 4.7500851188015274e-07, Loss: 0.4551115036010742
2024-08-04T18:34:29.615835247Z 
 15%|█▍        | 829/5712 [1:56:20<11:45:25,  8.67s/it]08/04/2024 11:34:29 - INFO - __main__ -   Step: 829, LR: 4.7491123324983584e-07, Loss: 0.5802196860313416
2024-08-04T18:34:38.002775588Z 
 15%|█▍        | 830/5712 [1:56:29<11:38:25,  8.58s/it]08/04/2024 11:34:38 - INFO - __main__ -   Step: 830, LR: 4.7481395461951894e-07, Loss: 0.5270017385482788
2024-08-04T18:34:46.271907630Z 
 15%|█▍        | 831/5712 [1:56:37<11:30:36,  8.49s/it]08/04/2024 11:34:46 - INFO - __main__ -   Step: 831, LR: 4.7471667598920204e-07, Loss: 0.6224126815795898
2024-08-04T18:34:54.721740362Z 
 15%|█▍        | 832/5712 [1:56:45<11:29:29,  8.48s/it]08/04/2024 11:34:54 - INFO - __main__ -   Step: 832, LR: 4.746193973588852e-07, Loss: 0.35764026641845703
2024-08-04T18:35:02.906641845Z 
 15%|█▍        | 833/5712 [1:56:54<11:22:13,  8.39s/it]08/04/2024 11:35:02 - INFO - __main__ -   Step: 833, LR: 4.745221187285683e-07, Loss: 0.49396729469299316
2024-08-04T18:35:11.574700859Z 
 15%|█▍        | 834/5712 [1:57:02<11:28:52,  8.47s/it]08/04/2024 11:35:11 - INFO - __main__ -   Step: 834, LR: 4.744248400982514e-07, Loss: 0.5487620234489441
2024-08-04T18:35:20.431872905Z 
 15%|█▍        | 835/5712 [1:57:11<11:38:06,  8.59s/it]08/04/2024 11:35:20 - INFO - __main__ -   Step: 835, LR: 4.743275614679345e-07, Loss: 0.5128715634346008
2024-08-04T18:35:28.733081215Z 
 15%|█▍        | 836/5712 [1:57:19<11:30:57,  8.50s/it]08/04/2024 11:35:28 - INFO - __main__ -   Step: 836, LR: 4.7423028283761764e-07, Loss: 0.45090141892433167
2024-08-04T18:35:37.215348393Z 
 15%|█▍        | 837/5712 [1:57:28<11:30:19,  8.50s/it]08/04/2024 11:35:37 - INFO - __main__ -   Step: 837, LR: 4.7413300420730074e-07, Loss: 0.3928508162498474
2024-08-04T18:35:45.501633309Z 
 15%|█▍        | 838/5712 [1:57:36<11:25:03,  8.43s/it]08/04/2024 11:35:45 - INFO - __main__ -   Step: 838, LR: 4.7403572557698384e-07, Loss: 0.5369244813919067
2024-08-04T18:35:54.116354520Z 
 15%|█▍        | 839/5712 [1:57:45<11:29:20,  8.49s/it]08/04/2024 11:35:54 - INFO - __main__ -   Step: 839, LR: 4.7393844694666694e-07, Loss: 0.5187257528305054
2024-08-04T18:36:02.918762789Z 
 15%|█▍        | 840/5712 [1:57:54<11:36:52,  8.58s/it]08/04/2024 11:36:02 - INFO - __main__ -   Step: 840, LR: 4.738411683163501e-07, Loss: 0.5868971347808838
2024-08-04T18:36:11.026114937Z 
 15%|█▍        | 841/5712 [1:58:02<11:25:09,  8.44s/it]08/04/2024 11:36:11 - INFO - __main__ -   Step: 841, LR: 4.737438896860332e-07, Loss: 0.44875356554985046
2024-08-04T18:36:19.588570423Z 
 15%|█▍        | 842/5712 [1:58:10<11:28:00,  8.48s/it]08/04/2024 11:36:19 - INFO - __main__ -   Step: 842, LR: 4.736466110557163e-07, Loss: 0.5159563422203064
2024-08-04T18:36:28.121586822Z 
 15%|█▍        | 843/5712 [1:58:19<11:29:14,  8.49s/it]08/04/2024 11:36:28 - INFO - __main__ -   Step: 843, LR: 4.735493324253994e-07, Loss: 0.49142763018608093
2024-08-04T18:36:36.302909729Z 
 15%|█▍        | 844/5712 [1:58:27<11:21:30,  8.40s/it]08/04/2024 11:36:36 - INFO - __main__ -   Step: 844, LR: 4.7345205379508254e-07, Loss: 0.6526056528091431
2024-08-04T18:36:44.718614676Z 
 15%|█▍        | 845/5712 [1:58:35<11:21:45,  8.40s/it]08/04/2024 11:36:44 - INFO - __main__ -   Step: 845, LR: 4.733547751647657e-07, Loss: 0.5272318124771118
2024-08-04T18:36:53.201286909Z 
 15%|█▍        | 846/5712 [1:58:44<11:23:30,  8.43s/it]08/04/2024 11:36:53 - INFO - __main__ -   Step: 846, LR: 4.732574965344488e-07, Loss: 0.5102174878120422
2024-08-04T18:37:01.410279317Z 
 15%|█▍        | 847/5712 [1:58:52<11:18:02,  8.36s/it]08/04/2024 11:37:01 - INFO - __main__ -   Step: 847, LR: 4.731602179041319e-07, Loss: 0.5626832246780396
2024-08-04T18:37:09.979554920Z 
 15%|█▍        | 848/5712 [1:59:01<11:22:56,  8.42s/it]08/04/2024 11:37:09 - INFO - __main__ -   Step: 848, LR: 4.7306293927381504e-07, Loss: 0.5218780636787415
2024-08-04T18:37:18.282101022Z 
 15%|█▍        | 849/5712 [1:59:09<11:19:50,  8.39s/it]08/04/2024 11:37:18 - INFO - __main__ -   Step: 849, LR: 4.7296566064349814e-07, Loss: 0.47134241461753845
2024-08-04T18:37:27.465655085Z 
 15%|█▍        | 850/5712 [1:59:18<11:38:58,  8.63s/it]08/04/2024 11:37:27 - INFO - __main__ -   Step: 850, LR: 4.7286838201318124e-07, Loss: 0.5287876129150391
2024-08-04T18:37:36.498206193Z 
 15%|█▍        | 851/5712 [1:59:27<11:48:47,  8.75s/it]08/04/2024 11:37:36 - INFO - __main__ -   Step: 851, LR: 4.7277110338286434e-07, Loss: 0.4839198589324951
2024-08-04T18:37:44.648396958Z 
 15%|█▍        | 852/5712 [1:59:35<11:34:05,  8.57s/it]08/04/2024 11:37:44 - INFO - __main__ -   Step: 852, LR: 4.726738247525475e-07, Loss: 0.44493305683135986
2024-08-04T18:37:52.600082598Z 
 15%|█▍        | 853/5712 [1:59:43<11:18:57,  8.38s/it]08/04/2024 11:37:52 - INFO - __main__ -   Step: 853, LR: 4.725765461222306e-07, Loss: 0.6293322443962097
2024-08-04T18:38:01.202257522Z 
 15%|█▍        | 854/5712 [1:59:52<11:24:06,  8.45s/it]08/04/2024 11:38:01 - INFO - __main__ -   Step: 854, LR: 4.724792674919137e-07, Loss: 0.43368837237358093
2024-08-04T18:38:09.573149900Z 
 15%|█▍        | 855/5712 [2:00:00<11:22:03,  8.43s/it]08/04/2024 11:38:09 - INFO - __main__ -   Step: 855, LR: 4.723819888615968e-07, Loss: 0.6412473917007446
2024-08-04T18:38:18.185595097Z 
 15%|█▍        | 856/5712 [2:00:09<11:26:27,  8.48s/it]08/04/2024 11:38:18 - INFO - __main__ -   Step: 856, LR: 4.7228471023127994e-07, Loss: 0.4612157940864563
2024-08-04T18:38:26.866363444Z 
 15%|█▌        | 857/5712 [2:00:18<11:31:09,  8.54s/it]08/04/2024 11:38:26 - INFO - __main__ -   Step: 857, LR: 4.7218743160096304e-07, Loss: 0.3848063051700592
2024-08-04T18:38:35.336952943Z 
 15%|█▌        | 858/5712 [2:00:26<11:29:17,  8.52s/it]08/04/2024 11:38:35 - INFO - __main__ -   Step: 858, LR: 4.7209015297064614e-07, Loss: 0.33562713861465454
2024-08-04T18:38:44.042504154Z 
 15%|█▌        | 859/5712 [2:00:35<11:33:38,  8.58s/it]08/04/2024 11:38:44 - INFO - __main__ -   Step: 859, LR: 4.7199287434032924e-07, Loss: 0.5870088338851929
2024-08-04T18:38:52.670553343Z 
 15%|█▌        | 860/5712 [2:00:43<11:34:45,  8.59s/it]08/04/2024 11:38:52 - INFO - __main__ -   Step: 860, LR: 4.7189559571001234e-07, Loss: 0.4781061112880707
2024-08-04T18:39:00.623103307Z 
 15%|█▌        | 861/5712 [2:00:51<11:19:07,  8.40s/it]08/04/2024 11:39:00 - INFO - __main__ -   Step: 861, LR: 4.717983170796955e-07, Loss: 0.39383000135421753
2024-08-04T18:39:08.879542062Z 
 15%|█▌        | 862/5712 [2:01:00<11:15:30,  8.36s/it]08/04/2024 11:39:08 - INFO - __main__ -   Step: 862, LR: 4.717010384493786e-07, Loss: 0.4384312033653259
2024-08-04T18:39:17.307203078Z 
 15%|█▌        | 863/5712 [2:01:08<11:17:05,  8.38s/it]08/04/2024 11:39:17 - INFO - __main__ -   Step: 863, LR: 4.7160375981906174e-07, Loss: 0.44554945826530457
2024-08-04T18:39:26.012485293Z 
 15%|█▌        | 864/5712 [2:01:17<11:24:52,  8.48s/it]08/04/2024 11:39:26 - INFO - __main__ -   Step: 864, LR: 4.7150648118874484e-07, Loss: 0.5550566911697388
2024-08-04T18:39:34.963395473Z 
 15%|█▌        | 865/5712 [2:01:26<11:36:14,  8.62s/it]08/04/2024 11:39:34 - INFO - __main__ -   Step: 865, LR: 4.71409202558428e-07, Loss: 0.5597822666168213
2024-08-04T18:39:43.241035441Z 
 15%|█▌        | 866/5712 [2:01:34<11:27:50,  8.52s/it]08/04/2024 11:39:43 - INFO - __main__ -   Step: 866, LR: 4.713119239281111e-07, Loss: 0.43139755725860596
2024-08-04T18:39:51.709044695Z 
 15%|█▌        | 867/5712 [2:01:42<11:26:31,  8.50s/it]08/04/2024 11:39:51 - INFO - __main__ -   Step: 867, LR: 4.712146452977942e-07, Loss: 0.4166613221168518
2024-08-04T18:40:00.169263495Z 
 15%|█▌        | 868/5712 [2:01:51<11:25:22,  8.49s/it]08/04/2024 11:40:00 - INFO - __main__ -   Step: 868, LR: 4.711173666674773e-07, Loss: 0.4489865303039551
2024-08-04T18:40:08.668689055Z 
 15%|█▌        | 869/5712 [2:01:59<11:25:28,  8.49s/it]08/04/2024 11:40:08 - INFO - __main__ -   Step: 869, LR: 4.7102008803716044e-07, Loss: 0.6049953699111938
2024-08-04T18:40:16.672904016Z 
 15%|█▌        | 870/5712 [2:02:07<11:13:31,  8.35s/it]08/04/2024 11:40:16 - INFO - __main__ -   Step: 870, LR: 4.7092280940684354e-07, Loss: 0.5864989757537842
2024-08-04T18:40:24.979881987Z 
 15%|█▌        | 871/5712 [2:02:16<11:12:26,  8.33s/it]08/04/2024 11:40:24 - INFO - __main__ -   Step: 871, LR: 4.7082553077652664e-07, Loss: 0.5157974362373352
2024-08-04T18:40:33.020937551Z 
 15%|█▌        | 872/5712 [2:02:24<11:05:12,  8.25s/it]08/04/2024 11:40:33 - INFO - __main__ -   Step: 872, LR: 4.7072825214620974e-07, Loss: 0.4575114846229553
2024-08-04T18:40:41.863306809Z 
 15%|█▌        | 873/5712 [2:02:33<11:19:28,  8.43s/it]08/04/2024 11:40:41 - INFO - __main__ -   Step: 873, LR: 4.706309735158929e-07, Loss: 0.44009754061698914
2024-08-04T18:40:50.070670197Z 
 15%|█▌        | 874/5712 [2:02:41<11:14:04,  8.36s/it]08/04/2024 11:40:50 - INFO - __main__ -   Step: 874, LR: 4.70533694885576e-07, Loss: 0.5093951225280762
2024-08-04T18:40:58.611971197Z 
 15%|█▌        | 875/5712 [2:02:49<11:18:19,  8.41s/it]08/04/2024 11:40:58 - INFO - __main__ -   Step: 875, LR: 4.704364162552591e-07, Loss: 0.4840465784072876
2024-08-04T18:41:07.006001902Z 
 15%|█▌        | 876/5712 [2:02:58<11:17:41,  8.41s/it]08/04/2024 11:41:07 - INFO - __main__ -   Step: 876, LR: 4.703391376249422e-07, Loss: 0.5171695947647095
2024-08-04T18:41:15.446047836Z 
 15%|█▌        | 877/5712 [2:03:06<11:18:19,  8.42s/it]08/04/2024 11:41:15 - INFO - __main__ -   Step: 877, LR: 4.7024185899462534e-07, Loss: 0.37624281644821167
2024-08-04T18:41:24.098046083Z 
 15%|█▌        | 878/5712 [2:03:15<11:23:51,  8.49s/it]08/04/2024 11:41:24 - INFO - __main__ -   Step: 878, LR: 4.7014458036430844e-07, Loss: 0.6536757349967957
2024-08-04T18:41:32.100249895Z 
 15%|█▌        | 879/5712 [2:03:23<11:11:58,  8.34s/it]08/04/2024 11:41:32 - INFO - __main__ -   Step: 879, LR: 4.7004730173399154e-07, Loss: 0.5238350629806519
2024-08-04T18:41:40.729166288Z 
 15%|█▌        | 880/5712 [2:03:31<11:18:45,  8.43s/it]08/04/2024 11:41:40 - INFO - __main__ -   Step: 880, LR: 4.6995002310367464e-07, Loss: 0.5508901476860046
2024-08-04T18:41:49.358545854Z 
 15%|█▌        | 881/5712 [2:03:40<11:23:28,  8.49s/it]08/04/2024 11:41:49 - INFO - __main__ -   Step: 881, LR: 4.6985274447335784e-07, Loss: 0.48142382502555847
2024-08-04T18:41:58.217917712Z 
 15%|█▌        | 882/5712 [2:03:49<11:32:17,  8.60s/it]08/04/2024 11:41:58 - INFO - __main__ -   Step: 882, LR: 4.6975546584304094e-07, Loss: 0.5025988221168518
2024-08-04T18:42:06.909098022Z 
 15%|█▌        | 883/5712 [2:03:58<11:34:20,  8.63s/it]08/04/2024 11:42:06 - INFO - __main__ -   Step: 883, LR: 4.6965818721272404e-07, Loss: 0.5227470397949219
2024-08-04T18:42:16.235980162Z 
 15%|█▌        | 884/5712 [2:04:07<11:51:05,  8.84s/it]08/04/2024 11:42:16 - INFO - __main__ -   Step: 884, LR: 4.6956090858240714e-07, Loss: 0.5220957398414612
2024-08-04T18:42:24.886302771Z 
 15%|█▌        | 885/5712 [2:04:16<11:46:26,  8.78s/it]08/04/2024 11:42:24 - INFO - __main__ -   Step: 885, LR: 4.694636299520903e-07, Loss: 0.35517215728759766
2024-08-04T18:42:32.397031806Z 
 16%|█▌        | 886/5712 [2:04:23<11:15:38,  8.40s/it]08/04/2024 11:42:32 - INFO - __main__ -   Step: 886, LR: 4.693663513217734e-07, Loss: 0.5333852767944336
2024-08-04T18:42:40.473093427Z 
 16%|█▌        | 887/5712 [2:04:31<11:07:41,  8.30s/it]08/04/2024 11:42:40 - INFO - __main__ -   Step: 887, LR: 4.692690726914565e-07, Loss: 0.38637256622314453
2024-08-04T18:42:48.926512934Z 
 16%|█▌        | 888/5712 [2:04:40<11:11:10,  8.35s/it]08/04/2024 11:42:48 - INFO - __main__ -   Step: 888, LR: 4.691717940611396e-07, Loss: 0.36434683203697205
2024-08-04T18:42:57.760377155Z 
 16%|█▌        | 889/5712 [2:04:48<11:22:45,  8.49s/it]08/04/2024 11:42:57 - INFO - __main__ -   Step: 889, LR: 4.6907451543082274e-07, Loss: 0.3745298385620117
2024-08-04T18:43:06.477076046Z 
 16%|█▌        | 890/5712 [2:04:57<11:27:59,  8.56s/it]08/04/2024 11:43:06 - INFO - __main__ -   Step: 890, LR: 4.6897723680050584e-07, Loss: 0.6342778205871582
2024-08-04T18:43:14.944578510Z 
 16%|█▌        | 891/5712 [2:05:06<11:25:36,  8.53s/it]08/04/2024 11:43:14 - INFO - __main__ -   Step: 891, LR: 4.6887995817018894e-07, Loss: 0.4957921802997589
2024-08-04T18:43:23.286518178Z 
 16%|█▌        | 892/5712 [2:05:14<11:20:51,  8.48s/it]08/04/2024 11:43:23 - INFO - __main__ -   Step: 892, LR: 4.6878267953987204e-07, Loss: 0.5717752575874329
2024-08-04T18:43:32.094361912Z 
 16%|█▌        | 893/5712 [2:05:23<11:28:43,  8.58s/it]08/04/2024 11:43:32 - INFO - __main__ -   Step: 893, LR: 4.686854009095552e-07, Loss: 0.3862774968147278
2024-08-04T18:43:40.026847030Z 
 16%|█▌        | 894/5712 [2:05:31<11:13:05,  8.38s/it]08/04/2024 11:43:40 - INFO - __main__ -   Step: 894, LR: 4.685881222792383e-07, Loss: 0.46583062410354614
2024-08-04T18:43:48.200654546Z 
 16%|█▌        | 895/5712 [2:05:39<11:07:56,  8.32s/it]08/04/2024 11:43:48 - INFO - __main__ -   Step: 895, LR: 4.684908436489214e-07, Loss: 0.3913290500640869
2024-08-04T18:43:56.333312965Z 
 16%|█▌        | 896/5712 [2:05:47<11:03:18,  8.26s/it]08/04/2024 11:43:56 - INFO - __main__ -   Step: 896, LR: 4.683935650186045e-07, Loss: 0.5057452321052551
2024-08-04T18:44:05.015079300Z 
 16%|█▌        | 897/5712 [2:05:56<11:13:13,  8.39s/it]08/04/2024 11:44:05 - INFO - __main__ -   Step: 897, LR: 4.682962863882876e-07, Loss: 0.46229109168052673
2024-08-04T18:44:13.442358306Z 
 16%|█▌        | 898/5712 [2:06:04<11:14:00,  8.40s/it]08/04/2024 11:44:13 - INFO - __main__ -   Step: 898, LR: 4.6819900775797074e-07, Loss: 0.5128359794616699
2024-08-04T18:44:21.895577186Z 
 16%|█▌        | 899/5712 [2:06:13<11:15:07,  8.42s/it]08/04/2024 11:44:21 - INFO - __main__ -   Step: 899, LR: 4.681017291276539e-07, Loss: 0.45548099279403687
2024-08-04T18:44:30.340001120Z 
 16%|█▌        | 900/5712 [2:06:21<11:15:39,  8.42s/it]08/04/2024 11:44:30 - INFO - __main__ -   Step: 900, LR: 4.68004450497337e-07, Loss: 0.3945050835609436
2024-08-04T18:44:39.136472058Z 
 16%|█▌        | 901/5712 [2:06:30<11:24:27,  8.54s/it]08/04/2024 11:44:39 - INFO - __main__ -   Step: 901, LR: 4.679071718670201e-07, Loss: 0.47443437576293945
2024-08-04T18:44:47.394718325Z 
 16%|█▌        | 902/5712 [2:06:38<11:17:38,  8.45s/it]08/04/2024 11:44:47 - INFO - __main__ -   Step: 902, LR: 4.6780989323670324e-07, Loss: 0.5360714197158813
2024-08-04T18:44:55.731789178Z 
 16%|█▌        | 903/5712 [2:06:46<11:14:42,  8.42s/it]08/04/2024 11:44:55 - INFO - __main__ -   Step: 903, LR: 4.6771261460638634e-07, Loss: 0.5184863805770874
2024-08-04T18:45:03.795875779Z 
 16%|█▌        | 904/5712 [2:06:54<11:06:04,  8.31s/it]08/04/2024 11:45:03 - INFO - __main__ -   Step: 904, LR: 4.6761533597606944e-07, Loss: 0.6101195216178894
2024-08-04T18:45:12.662959691Z 
 16%|█▌        | 905/5712 [2:07:03<11:19:16,  8.48s/it]08/04/2024 11:45:12 - INFO - __main__ -   Step: 905, LR: 4.6751805734575254e-07, Loss: 0.5085436105728149
2024-08-04T18:45:21.121867118Z 
 16%|█▌        | 906/5712 [2:07:12<11:18:39,  8.47s/it]08/04/2024 11:45:21 - INFO - __main__ -   Step: 906, LR: 4.674207787154357e-07, Loss: 0.5380767583847046
2024-08-04T18:45:29.373607302Z 
 16%|█▌        | 907/5712 [2:07:20<11:13:12,  8.41s/it]08/04/2024 11:45:29 - INFO - __main__ -   Step: 907, LR: 4.673235000851188e-07, Loss: 0.5228704214096069
2024-08-04T18:45:38.170054683Z 
 16%|█▌        | 908/5712 [2:07:29<11:22:26,  8.52s/it]08/04/2024 11:45:38 - INFO - __main__ -   Step: 908, LR: 4.672262214548019e-07, Loss: 0.6163492202758789
2024-08-04T18:45:46.789145906Z 
 16%|█▌        | 909/5712 [2:07:37<11:24:35,  8.55s/it]08/04/2024 11:45:46 - INFO - __main__ -   Step: 909, LR: 4.67128942824485e-07, Loss: 0.5858283638954163
2024-08-04T18:45:55.208296082Z 
 16%|█▌        | 910/5712 [2:07:46<11:21:15,  8.51s/it]08/04/2024 11:45:55 - INFO - __main__ -   Step: 910, LR: 4.6703166419416814e-07, Loss: 0.5466699004173279
2024-08-04T18:46:03.279829963Z 
 16%|█▌        | 911/5712 [2:07:54<11:10:32,  8.38s/it]08/04/2024 11:46:03 - INFO - __main__ -   Step: 911, LR: 4.6693438556385124e-07, Loss: 0.5682449340820312
2024-08-04T18:46:11.312935474Z 
 16%|█▌        | 912/5712 [2:08:02<11:02:04,  8.28s/it]08/04/2024 11:46:11 - INFO - __main__ -   Step: 912, LR: 4.6683710693353433e-07, Loss: 0.46861356496810913
2024-08-04T18:46:19.521149663Z 
 16%|█▌        | 913/5712 [2:08:10<11:00:18,  8.26s/it]08/04/2024 11:46:19 - INFO - __main__ -   Step: 913, LR: 4.6673982830321743e-07, Loss: 0.4372231364250183
2024-08-04T18:46:27.807715740Z 
 16%|█▌        | 914/5712 [2:08:18<11:00:55,  8.26s/it]08/04/2024 11:46:27 - INFO - __main__ -   Step: 914, LR: 4.666425496729006e-07, Loss: 0.5712223052978516
2024-08-04T18:46:36.907535609Z 
 16%|█▌        | 915/5712 [2:08:28<11:20:48,  8.52s/it]08/04/2024 11:46:36 - INFO - __main__ -   Step: 915, LR: 4.665452710425837e-07, Loss: 0.6187443733215332
2024-08-04T18:46:45.335113570Z 
 16%|█▌        | 916/5712 [2:08:36<11:18:33,  8.49s/it]08/04/2024 11:46:45 - INFO - __main__ -   Step: 916, LR: 4.664479924122668e-07, Loss: 0.5223791599273682
2024-08-04T18:46:54.335041082Z 
 16%|█▌        | 917/5712 [2:08:45<11:30:38,  8.64s/it]08/04/2024 11:46:54 - INFO - __main__ -   Step: 917, LR: 4.6635071378194994e-07, Loss: 0.4878905415534973
2024-08-04T18:47:03.496142139Z 
 16%|█▌        | 918/5712 [2:08:54<11:42:56,  8.80s/it]08/04/2024 11:47:03 - INFO - __main__ -   Step: 918, LR: 4.662534351516331e-07, Loss: 0.4336944818496704
2024-08-04T18:47:11.048174772Z 
 16%|█▌        | 919/5712 [2:09:02<11:12:57,  8.42s/it]08/04/2024 11:47:11 - INFO - __main__ -   Step: 919, LR: 4.661561565213162e-07, Loss: 0.5226459503173828
2024-08-04T18:47:19.392735283Z 
 16%|█▌        | 920/5712 [2:09:10<11:10:54,  8.40s/it]08/04/2024 11:47:19 - INFO - __main__ -   Step: 920, LR: 4.660588778909993e-07, Loss: 0.42966240644454956
2024-08-04T18:47:27.613041625Z 
 16%|█▌        | 921/5712 [2:09:18<11:06:27,  8.35s/it]08/04/2024 11:47:27 - INFO - __main__ -   Step: 921, LR: 4.659615992606824e-07, Loss: 0.49067437648773193
2024-08-04T18:47:36.524226163Z 
 16%|█▌        | 922/5712 [2:09:27<11:19:50,  8.52s/it]08/04/2024 11:47:36 - INFO - __main__ -   Step: 922, LR: 4.6586432063036554e-07, Loss: 0.49433714151382446
2024-08-04T18:47:44.688541726Z 
 16%|█▌        | 923/5712 [2:09:35<11:11:17,  8.41s/it]08/04/2024 11:47:44 - INFO - __main__ -   Step: 923, LR: 4.6576704200004864e-07, Loss: 0.5625520944595337
2024-08-04T18:47:53.835087296Z 
 16%|█▌        | 924/5712 [2:09:44<11:28:45,  8.63s/it]08/04/2024 11:47:53 - INFO - __main__ -   Step: 924, LR: 4.6566976336973174e-07, Loss: 0.7260754704475403
2024-08-04T18:48:02.460336298Z 
 16%|█▌        | 925/5712 [2:09:53<11:28:29,  8.63s/it]08/04/2024 11:48:02 - INFO - __main__ -   Step: 925, LR: 4.6557248473941483e-07, Loss: 0.40457883477211
2024-08-04T18:48:11.463550328Z 
 16%|█▌        | 926/5712 [2:10:02<11:37:17,  8.74s/it]08/04/2024 11:48:11 - INFO - __main__ -   Step: 926, LR: 4.65475206109098e-07, Loss: 0.5818695425987244
2024-08-04T18:48:19.631569292Z 
 16%|█▌        | 927/5712 [2:10:10<11:23:25,  8.57s/it]08/04/2024 11:48:19 - INFO - __main__ -   Step: 927, LR: 4.653779274787811e-07, Loss: 0.6196050643920898
2024-08-04T18:48:27.919237768Z 
 16%|█▌        | 928/5712 [2:10:19<11:16:31,  8.48s/it]08/04/2024 11:48:27 - INFO - __main__ -   Step: 928, LR: 4.652806488484642e-07, Loss: 0.40801358222961426
2024-08-04T18:48:35.870310710Z 
 16%|█▋        | 929/5712 [2:10:27<11:03:37,  8.32s/it]08/04/2024 11:48:35 - INFO - __main__ -   Step: 929, LR: 4.651833702181473e-07, Loss: 0.4520929455757141
2024-08-04T18:48:44.315577326Z 
 16%|█▋        | 930/5712 [2:10:35<11:06:22,  8.36s/it]08/04/2024 11:48:44 - INFO - __main__ -   Step: 930, LR: 4.6508609158783044e-07, Loss: 0.5012038946151733
2024-08-04T18:48:52.673895028Z 
 16%|█▋        | 931/5712 [2:10:43<11:06:09,  8.36s/it]08/04/2024 11:48:52 - INFO - __main__ -   Step: 931, LR: 4.6498881295751353e-07, Loss: 0.39207789301872253
2024-08-04T18:49:01.117467175Z 
 16%|█▋        | 932/5712 [2:10:52<11:08:01,  8.39s/it]08/04/2024 11:49:01 - INFO - __main__ -   Step: 932, LR: 4.6489153432719663e-07, Loss: 0.5923444032669067
2024-08-04T18:49:10.304833798Z 
 16%|█▋        | 933/5712 [2:11:01<11:27:02,  8.63s/it]08/04/2024 11:49:10 - INFO - __main__ -   Step: 933, LR: 4.6479425569687973e-07, Loss: 0.5756037831306458
2024-08-04T18:49:19.225968848Z 
 16%|█▋        | 934/5712 [2:11:10<11:33:57,  8.71s/it]08/04/2024 11:49:19 - INFO - __main__ -   Step: 934, LR: 4.6469697706656283e-07, Loss: 0.5387276411056519
2024-08-04T18:49:27.819969427Z 
 16%|█▋        | 935/5712 [2:11:18<11:30:56,  8.68s/it]08/04/2024 11:49:27 - INFO - __main__ -   Step: 935, LR: 4.6459969843624604e-07, Loss: 0.49529606103897095
2024-08-04T18:49:35.833093719Z 
 16%|█▋        | 936/5712 [2:11:26<11:14:54,  8.48s/it]08/04/2024 11:49:35 - INFO - __main__ -   Step: 936, LR: 4.6450241980592914e-07, Loss: 0.4141952395439148
2024-08-04T18:49:43.802409352Z 
 16%|█▋        | 937/5712 [2:11:34<11:02:36,  8.33s/it]08/04/2024 11:49:43 - INFO - __main__ -   Step: 937, LR: 4.6440514117561223e-07, Loss: 0.36215415596961975
2024-08-04T18:49:52.086611531Z 
 16%|█▋        | 938/5712 [2:11:43<11:01:27,  8.31s/it]08/04/2024 11:49:52 - INFO - __main__ -   Step: 938, LR: 4.6430786254529533e-07, Loss: 0.481653094291687
2024-08-04T18:50:00.782252572Z 
 16%|█▋        | 939/5712 [2:11:51<11:10:27,  8.43s/it]08/04/2024 11:50:00 - INFO - __main__ -   Step: 939, LR: 4.642105839149785e-07, Loss: 0.39577436447143555
2024-08-04T18:50:09.284489783Z 
 16%|█▋        | 940/5712 [2:12:00<11:12:05,  8.45s/it]08/04/2024 11:50:09 - INFO - __main__ -   Step: 940, LR: 4.641133052846616e-07, Loss: 0.35996851325035095
2024-08-04T18:50:17.573937820Z 
 16%|█▋        | 941/5712 [2:12:08<11:08:05,  8.40s/it]08/04/2024 11:50:17 - INFO - __main__ -   Step: 941, LR: 4.640160266543447e-07, Loss: 0.46053504943847656
2024-08-04T18:50:26.612868590Z 
 16%|█▋        | 942/5712 [2:12:17<11:23:09,  8.59s/it]08/04/2024 11:50:26 - INFO - __main__ -   Step: 942, LR: 4.639187480240278e-07, Loss: 0.4917849898338318
2024-08-04T18:50:34.988565569Z 
 17%|█▋        | 943/5712 [2:12:26<11:17:49,  8.53s/it]08/04/2024 11:50:34 - INFO - __main__ -   Step: 943, LR: 4.6382146939371093e-07, Loss: 0.42823725938796997
2024-08-04T18:50:43.464059366Z 
 17%|█▋        | 944/5712 [2:12:34<11:16:26,  8.51s/it]08/04/2024 11:50:43 - INFO - __main__ -   Step: 944, LR: 4.6372419076339403e-07, Loss: 0.4927898943424225
2024-08-04T18:50:51.430219479Z 
 17%|█▋        | 945/5712 [2:12:42<11:03:16,  8.35s/it]08/04/2024 11:50:51 - INFO - __main__ -   Step: 945, LR: 4.6362691213307713e-07, Loss: 0.4183047115802765
2024-08-04T18:50:59.624105732Z 
 17%|█▋        | 946/5712 [2:12:50<10:59:27,  8.30s/it]08/04/2024 11:50:59 - INFO - __main__ -   Step: 946, LR: 4.6352963350276023e-07, Loss: 0.4755142331123352
2024-08-04T18:51:07.985971239Z 
 17%|█▋        | 947/5712 [2:12:59<11:00:44,  8.32s/it]08/04/2024 11:51:07 - INFO - __main__ -   Step: 947, LR: 4.634323548724434e-07, Loss: 0.48441365361213684
2024-08-04T18:51:16.535522376Z 
 17%|█▋        | 948/5712 [2:13:07<11:06:04,  8.39s/it]08/04/2024 11:51:16 - INFO - __main__ -   Step: 948, LR: 4.633350762421265e-07, Loss: 0.496381551027298
2024-08-04T18:51:25.426599056Z 
 17%|█▋        | 949/5712 [2:13:16<11:17:54,  8.54s/it]08/04/2024 11:51:25 - INFO - __main__ -   Step: 949, LR: 4.632377976118096e-07, Loss: 0.6983351111412048
2024-08-04T18:51:33.633801301Z 
 17%|█▋        | 950/5712 [2:13:24<11:09:50,  8.44s/it]08/04/2024 11:51:33 - INFO - __main__ -   Step: 950, LR: 4.631405189814927e-07, Loss: 0.4298906922340393
2024-08-04T18:51:42.202254841Z 
 17%|█▋        | 951/5712 [2:13:33<11:12:45,  8.48s/it]08/04/2024 11:51:42 - INFO - __main__ -   Step: 951, LR: 4.6304324035117583e-07, Loss: 0.470673143863678
2024-08-04T18:51:50.413068697Z 
 17%|█▋        | 952/5712 [2:13:41<11:06:15,  8.40s/it]08/04/2024 11:51:50 - INFO - __main__ -   Step: 952, LR: 4.6294596172085893e-07, Loss: 0.4227328598499298
2024-08-04T18:51:58.590642364Z 
 17%|█▋        | 953/5712 [2:13:49<11:00:51,  8.33s/it]08/04/2024 11:51:58 - INFO - __main__ -   Step: 953, LR: 4.628486830905421e-07, Loss: 0.5610753893852234
2024-08-04T18:52:06.923763795Z 
 17%|█▋        | 954/5712 [2:13:58<11:00:45,  8.33s/it]08/04/2024 11:52:06 - INFO - __main__ -   Step: 954, LR: 4.627514044602252e-07, Loss: 0.5199134945869446
2024-08-04T18:52:15.111448050Z 
 17%|█▋        | 955/5712 [2:14:06<10:57:10,  8.29s/it]08/04/2024 11:52:15 - INFO - __main__ -   Step: 955, LR: 4.6265412582990833e-07, Loss: 0.42818883061408997
2024-08-04T18:52:23.742264897Z 
 17%|█▋        | 956/5712 [2:14:14<11:05:09,  8.39s/it]08/04/2024 11:52:23 - INFO - __main__ -   Step: 956, LR: 4.6255684719959143e-07, Loss: 0.6492371559143066
2024-08-04T18:52:32.164919037Z 
 17%|█▋        | 957/5712 [2:14:23<11:05:46,  8.40s/it]08/04/2024 11:52:32 - INFO - __main__ -   Step: 957, LR: 4.6245956856927453e-07, Loss: 0.5932766199111938
2024-08-04T18:52:40.369145876Z 
 17%|█▋        | 958/5712 [2:14:31<11:00:57,  8.34s/it]08/04/2024 11:52:40 - INFO - __main__ -   Step: 958, LR: 4.6236228993895763e-07, Loss: 0.3923206627368927
2024-08-04T18:52:49.546121704Z 
 17%|█▋        | 959/5712 [2:14:40<11:20:39,  8.59s/it]08/04/2024 11:52:49 - INFO - __main__ -   Step: 959, LR: 4.622650113086408e-07, Loss: 0.44480428099632263
2024-08-04T18:52:57.490541899Z 
 17%|█▋        | 960/5712 [2:14:48<11:05:07,  8.40s/it]08/04/2024 11:52:57 - INFO - __main__ -   Step: 960, LR: 4.621677326783239e-07, Loss: 0.6015544533729553
2024-08-04T18:53:05.860892764Z 
 17%|█▋        | 961/5712 [2:14:57<11:04:19,  8.39s/it]08/04/2024 11:53:05 - INFO - __main__ -   Step: 961, LR: 4.62070454048007e-07, Loss: 0.4659741520881653
2024-08-04T18:53:14.022064456Z 
 17%|█▋        | 962/5712 [2:15:05<10:58:45,  8.32s/it]08/04/2024 11:53:14 - INFO - __main__ -   Step: 962, LR: 4.619731754176901e-07, Loss: 0.49939700961112976
2024-08-04T18:53:22.208742100Z 
 17%|█▋        | 963/5712 [2:15:13<10:55:25,  8.28s/it]08/04/2024 11:53:22 - INFO - __main__ -   Step: 963, LR: 4.6187589678737323e-07, Loss: 0.540049135684967
2024-08-04T18:53:30.669450736Z 
 17%|█▋        | 964/5712 [2:15:21<10:59:33,  8.33s/it]08/04/2024 11:53:30 - INFO - __main__ -   Step: 964, LR: 4.6177861815705633e-07, Loss: 0.37110021710395813
2024-08-04T18:53:39.605732326Z 
 17%|█▋        | 965/5712 [2:15:30<11:13:40,  8.51s/it]08/04/2024 11:53:39 - INFO - __main__ -   Step: 965, LR: 4.6168133952673943e-07, Loss: 0.5627899765968323
2024-08-04T18:53:48.104899456Z 
 17%|█▋        | 966/5712 [2:15:39<11:13:10,  8.51s/it]08/04/2024 11:53:48 - INFO - __main__ -   Step: 966, LR: 4.6158406089642253e-07, Loss: 0.5989804267883301
2024-08-04T18:53:56.839033604Z 
 17%|█▋        | 967/5712 [2:15:47<11:18:20,  8.58s/it]08/04/2024 11:53:56 - INFO - __main__ -   Step: 967, LR: 4.614867822661057e-07, Loss: 0.5941121578216553
2024-08-04T18:54:05.217655554Z 
 17%|█▋        | 968/5712 [2:15:56<11:13:28,  8.52s/it]08/04/2024 11:54:05 - INFO - __main__ -   Step: 968, LR: 4.613895036357888e-07, Loss: 0.5308588743209839
2024-08-04T18:54:13.713553639Z 
 17%|█▋        | 969/5712 [2:16:04<11:12:48,  8.51s/it]08/04/2024 11:54:13 - INFO - __main__ -   Step: 969, LR: 4.612922250054719e-07, Loss: 0.5236661434173584
2024-08-04T18:54:21.222903960Z 
 17%|█▋        | 970/5712 [2:16:12<10:48:55,  8.21s/it]08/04/2024 11:54:21 - INFO - __main__ -   Step: 970, LR: 4.61194946375155e-07, Loss: 0.26160699129104614
2024-08-04T18:54:29.616422509Z 
 17%|█▋        | 971/5712 [2:16:20<10:53:06,  8.27s/it]08/04/2024 11:54:29 - INFO - __main__ -   Step: 971, LR: 4.610976677448382e-07, Loss: 0.6914523839950562
2024-08-04T18:54:37.955706565Z 
 17%|█▋        | 972/5712 [2:16:29<10:54:44,  8.29s/it]08/04/2024 11:54:37 - INFO - __main__ -   Step: 972, LR: 4.610003891145213e-07, Loss: 0.5094825625419617
2024-08-04T18:54:46.085983225Z 
 17%|█▋        | 973/5712 [2:16:37<10:50:51,  8.24s/it]08/04/2024 11:54:46 - INFO - __main__ -   Step: 973, LR: 4.609031104842044e-07, Loss: 0.5613354444503784
2024-08-04T18:54:54.548507494Z 
 17%|█▋        | 974/5712 [2:16:45<10:55:58,  8.31s/it]08/04/2024 11:54:54 - INFO - __main__ -   Step: 974, LR: 4.608058318538875e-07, Loss: 0.42907142639160156
2024-08-04T18:55:03.549985791Z 
 17%|█▋        | 975/5712 [2:16:54<11:12:17,  8.52s/it]08/04/2024 11:55:03 - INFO - __main__ -   Step: 975, LR: 4.607085532235706e-07, Loss: 0.5124320983886719
2024-08-04T18:55:12.064778367Z 
 17%|█▋        | 976/5712 [2:17:03<11:12:07,  8.52s/it]08/04/2024 11:55:12 - INFO - __main__ -   Step: 976, LR: 4.6061127459325373e-07, Loss: 0.5757675170898438
2024-08-04T18:55:20.221797063Z 
 17%|█▋        | 977/5712 [2:17:11<11:03:28,  8.41s/it]08/04/2024 11:55:20 - INFO - __main__ -   Step: 977, LR: 4.6051399596293683e-07, Loss: 0.3766654133796692
2024-08-04T18:55:28.175102442Z 
 17%|█▋        | 978/5712 [2:17:19<10:52:37,  8.27s/it]08/04/2024 11:55:28 - INFO - __main__ -   Step: 978, LR: 4.6041671733261993e-07, Loss: 0.4626377820968628
2024-08-04T18:55:36.985158973Z 
 17%|█▋        | 979/5712 [2:17:28<11:05:13,  8.43s/it]08/04/2024 11:55:36 - INFO - __main__ -   Step: 979, LR: 4.6031943870230303e-07, Loss: 0.4969235062599182
2024-08-04T18:55:45.248386861Z 
 17%|█▋        | 980/5712 [2:17:36<11:01:02,  8.38s/it]08/04/2024 11:55:45 - INFO - __main__ -   Step: 980, LR: 4.602221600719862e-07, Loss: 0.5928167104721069
2024-08-04T18:55:53.467812177Z 
 17%|█▋        | 981/5712 [2:17:44<10:57:05,  8.33s/it]08/04/2024 11:55:53 - INFO - __main__ -   Step: 981, LR: 4.601248814416693e-07, Loss: 0.42073529958724976
2024-08-04T18:56:02.573991151Z 
 17%|█▋        | 982/5712 [2:17:53<11:15:14,  8.57s/it]08/04/2024 11:56:02 - INFO - __main__ -   Step: 982, LR: 4.600276028113524e-07, Loss: 0.5165738463401794
2024-08-04T18:56:11.130091405Z 
 17%|█▋        | 983/5712 [2:18:02<11:14:52,  8.56s/it]08/04/2024 11:56:11 - INFO - __main__ -   Step: 983, LR: 4.599303241810355e-07, Loss: 0.3871650993824005
2024-08-04T18:56:20.028586967Z 
 17%|█▋        | 984/5712 [2:18:11<11:22:39,  8.66s/it]08/04/2024 11:56:20 - INFO - __main__ -   Step: 984, LR: 4.5983304555071863e-07, Loss: 0.40001189708709717
2024-08-04T18:56:28.006688018Z 
 17%|█▋        | 985/5712 [2:18:19<11:06:19,  8.46s/it]08/04/2024 11:56:28 - INFO - __main__ -   Step: 985, LR: 4.5973576692040173e-07, Loss: 0.4993523061275482
2024-08-04T18:56:36.571739198Z 
 17%|█▋        | 986/5712 [2:18:27<11:08:43,  8.49s/it]08/04/2024 11:56:36 - INFO - __main__ -   Step: 986, LR: 4.5963848829008483e-07, Loss: 0.5420629382133484
2024-08-04T18:56:45.021051072Z 
 17%|█▋        | 987/5712 [2:18:36<11:07:37,  8.48s/it]08/04/2024 11:56:45 - INFO - __main__ -   Step: 987, LR: 4.5954120965976793e-07, Loss: 0.4270557165145874
2024-08-04T18:56:53.379681652Z 
 17%|█▋        | 988/5712 [2:18:44<11:04:39,  8.44s/it]08/04/2024 11:56:53 - INFO - __main__ -   Step: 988, LR: 4.594439310294511e-07, Loss: 0.37224605679512024
2024-08-04T18:57:01.957128547Z 
 17%|█▋        | 989/5712 [2:18:53<11:07:43,  8.48s/it]08/04/2024 11:57:01 - INFO - __main__ -   Step: 989, LR: 4.5934665239913423e-07, Loss: 0.42318275570869446
2024-08-04T18:57:10.046143385Z 
 17%|█▋        | 990/5712 [2:19:01<10:58:17,  8.36s/it]08/04/2024 11:57:10 - INFO - __main__ -   Step: 990, LR: 4.5924937376881733e-07, Loss: 0.4581736922264099
2024-08-04T18:57:18.637994655Z 
 17%|█▋        | 991/5712 [2:19:09<11:03:31,  8.43s/it]08/04/2024 11:57:18 - INFO - __main__ -   Step: 991, LR: 4.5915209513850043e-07, Loss: 0.5468622446060181
2024-08-04T18:57:27.243426272Z 
 17%|█▋        | 992/5712 [2:19:18<11:07:27,  8.48s/it]08/04/2024 11:57:27 - INFO - __main__ -   Step: 992, LR: 4.590548165081836e-07, Loss: 0.5248154997825623
2024-08-04T18:57:35.569537975Z 
 17%|█▋        | 993/5712 [2:19:26<11:03:34,  8.44s/it]08/04/2024 11:57:35 - INFO - __main__ -   Step: 993, LR: 4.589575378778667e-07, Loss: 0.5057516098022461
2024-08-04T18:57:43.665072536Z 
 17%|█▋        | 994/5712 [2:19:34<10:55:22,  8.33s/it]08/04/2024 11:57:43 - INFO - __main__ -   Step: 994, LR: 4.588602592475498e-07, Loss: 0.5360745787620544
2024-08-04T18:57:52.408876430Z 
 17%|█▋        | 995/5712 [2:19:43<11:04:53,  8.46s/it]08/04/2024 11:57:52 - INFO - __main__ -   Step: 995, LR: 4.587629806172329e-07, Loss: 0.46875494718551636
2024-08-04T18:58:01.505781833Z 
 17%|█▋        | 996/5712 [2:19:52<11:19:49,  8.65s/it]08/04/2024 11:58:01 - INFO - __main__ -   Step: 996, LR: 4.5866570198691603e-07, Loss: 0.4842796325683594
2024-08-04T18:58:09.683314412Z 
 17%|█▋        | 997/5712 [2:20:00<11:08:33,  8.51s/it]08/04/2024 11:58:09 - INFO - __main__ -   Step: 997, LR: 4.5856842335659913e-07, Loss: 0.5464831590652466
2024-08-04T18:58:17.855944079Z 
 17%|█▋        | 998/5712 [2:20:09<11:00:31,  8.41s/it]08/04/2024 11:58:17 - INFO - __main__ -   Step: 998, LR: 4.5847114472628223e-07, Loss: 0.4040023386478424
2024-08-04T18:58:26.733483420Z 
 17%|█▋        | 999/5712 [2:20:17<11:11:28,  8.55s/it]08/04/2024 11:58:26 - INFO - __main__ -   Step: 999, LR: 4.5837386609596533e-07, Loss: 0.4489770531654358
2024-08-04T18:58:35.033190404Z 
 18%|█▊        | 1000/5712 [2:20:26<11:05:28,  8.47s/it]08/04/2024 11:58:35 - INFO - __main__ -   Step: 1000, LR: 4.582765874656485e-07, Loss: 0.5320388078689575
2024-08-04T18:58:43.310882414Z 
 18%|█▊        | 1001/5712 [2:20:34<11:00:42,  8.41s/it]08/04/2024 11:58:43 - INFO - __main__ -   Step: 1001, LR: 4.581793088353316e-07, Loss: 0.5332425832748413
2024-08-04T18:58:51.599555439Z 
 18%|█▊        | 1002/5712 [2:20:42<10:57:35,  8.38s/it]08/04/2024 11:58:51 - INFO - __main__ -   Step: 1002, LR: 4.580820302050147e-07, Loss: 0.442247211933136
2024-08-04T18:58:59.626153535Z 
 18%|█▊        | 1003/5712 [2:20:50<10:49:12,  8.27s/it]08/04/2024 11:58:59 - INFO - __main__ -   Step: 1003, LR: 4.579847515746978e-07, Loss: 0.4891858696937561
2024-08-04T18:59:08.372835390Z 
 18%|█▊        | 1004/5712 [2:20:59<11:00:14,  8.41s/it]08/04/2024 11:59:08 - INFO - __main__ -   Step: 1004, LR: 4.5788747294438093e-07, Loss: 0.47298967838287354
2024-08-04T18:59:17.082029271Z 
 18%|█▊        | 1005/5712 [2:21:08<11:07:02,  8.50s/it]08/04/2024 11:59:17 - INFO - __main__ -   Step: 1005, LR: 4.5779019431406403e-07, Loss: 0.5492095947265625
2024-08-04T18:59:25.071958618Z 
 18%|█▊        | 1006/5712 [2:21:16<10:54:49,  8.35s/it]08/04/2024 11:59:25 - INFO - __main__ -   Step: 1006, LR: 4.5769291568374713e-07, Loss: 0.47813427448272705
2024-08-04T18:59:33.574178599Z 
 18%|█▊        | 1007/5712 [2:21:24<10:58:17,  8.39s/it]08/04/2024 11:59:33 - INFO - __main__ -   Step: 1007, LR: 4.575956370534303e-07, Loss: 0.5568544864654541
2024-08-04T18:59:42.362086099Z 
 18%|█▊        | 1008/5712 [2:21:33<11:07:24,  8.51s/it]08/04/2024 11:59:42 - INFO - __main__ -   Step: 1008, LR: 4.5749835842311343e-07, Loss: 0.4371045231819153
2024-08-04T18:59:50.766964217Z 
 18%|█▊        | 1009/5712 [2:21:41<11:04:43,  8.48s/it]08/04/2024 11:59:50 - INFO - __main__ -   Step: 1009, LR: 4.5740107979279653e-07, Loss: 0.451604962348938
2024-08-04T18:59:59.292698702Z 
 18%|█▊        | 1010/5712 [2:21:50<11:05:38,  8.49s/it]08/04/2024 11:59:59 - INFO - __main__ -   Step: 1010, LR: 4.5730380116247963e-07, Loss: 0.5660213232040405
2024-08-04T19:00:07.275089186Z 
 18%|█▊        | 1011/5712 [2:21:58<10:53:29,  8.34s/it]08/04/2024 12:00:07 - INFO - __main__ -   Step: 1011, LR: 4.5720652253216273e-07, Loss: 0.47094082832336426
2024-08-04T19:00:15.471556663Z 
 18%|█▊        | 1012/5712 [2:22:06<10:49:57,  8.30s/it]08/04/2024 12:00:15 - INFO - __main__ -   Step: 1012, LR: 4.5710924390184583e-07, Loss: 0.6146266460418701
2024-08-04T19:00:24.710757929Z 
 18%|█▊        | 1013/5712 [2:22:15<11:11:56,  8.58s/it]08/04/2024 12:00:24 - INFO - __main__ -   Step: 1013, LR: 4.57011965271529e-07, Loss: 0.3735337555408478
2024-08-04T19:00:32.813968189Z 
 18%|█▊        | 1014/5712 [2:22:23<11:00:36,  8.44s/it]08/04/2024 12:00:32 - INFO - __main__ -   Step: 1014, LR: 4.569146866412121e-07, Loss: 0.46071964502334595
2024-08-04T19:00:41.243014193Z 
 18%|█▊        | 1015/5712 [2:22:32<11:00:16,  8.43s/it]08/04/2024 12:00:41 - INFO - __main__ -   Step: 1015, LR: 4.568174080108952e-07, Loss: 0.4740959107875824
2024-08-04T19:00:50.303226652Z 
 18%|█▊        | 1016/5712 [2:22:41<11:14:49,  8.62s/it]08/04/2024 12:00:50 - INFO - __main__ -   Step: 1016, LR: 4.567201293805783e-07, Loss: 0.5875611305236816
2024-08-04T19:00:58.800740587Z 
 18%|█▊        | 1017/5712 [2:22:49<11:11:45,  8.58s/it]08/04/2024 12:00:58 - INFO - __main__ -   Step: 1017, LR: 4.5662285075026143e-07, Loss: 0.4439693093299866
2024-08-04T19:01:07.017236318Z 
 18%|█▊        | 1018/5712 [2:22:58<11:02:58,  8.47s/it]08/04/2024 12:01:07 - INFO - __main__ -   Step: 1018, LR: 4.5652557211994453e-07, Loss: 0.5725501775741577
2024-08-04T19:01:15.633443781Z 
 18%|█▊        | 1019/5712 [2:23:06<11:06:09,  8.52s/it]08/04/2024 12:01:15 - INFO - __main__ -   Step: 1019, LR: 4.5642829348962763e-07, Loss: 0.457312673330307
2024-08-04T19:01:24.059425148Z 
 18%|█▊        | 1020/5712 [2:23:15<11:03:53,  8.49s/it]08/04/2024 12:01:24 - INFO - __main__ -   Step: 1020, LR: 4.563310148593107e-07, Loss: 0.630122184753418
2024-08-04T19:01:32.167328575Z 
 18%|█▊        | 1021/5712 [2:23:23<10:54:47,  8.38s/it]08/04/2024 12:01:32 - INFO - __main__ -   Step: 1021, LR: 4.562337362289939e-07, Loss: 0.5277221202850342
2024-08-04T19:01:40.564736744Z 
 18%|█▊        | 1022/5712 [2:23:31<10:55:10,  8.38s/it]08/04/2024 12:01:40 - INFO - __main__ -   Step: 1022, LR: 4.56136457598677e-07, Loss: 0.4409753382205963
2024-08-04T19:01:48.594516647Z 
 18%|█▊        | 1023/5712 [2:23:39<10:46:47,  8.28s/it]08/04/2024 12:01:48 - INFO - __main__ -   Step: 1023, LR: 4.560391789683601e-07, Loss: 0.434196799993515
2024-08-04T19:01:57.772073232Z 
 18%|█▊        | 1024/5712 [2:23:48<11:07:46,  8.55s/it]08/04/2024 12:01:57 - INFO - __main__ -   Step: 1024, LR: 4.559419003380432e-07, Loss: 0.5307304859161377
2024-08-04T19:02:06.509220203Z 
 18%|█▊        | 1025/5712 [2:23:57<11:12:06,  8.60s/it]08/04/2024 12:02:06 - INFO - __main__ -   Step: 1025, LR: 4.558446217077264e-07, Loss: 0.45358699560165405
2024-08-04T19:02:14.709290491Z 
 18%|█▊        | 1026/5712 [2:24:05<11:02:29,  8.48s/it]08/04/2024 12:02:14 - INFO - __main__ -   Step: 1026, LR: 4.557473430774095e-07, Loss: 0.6306108236312866
2024-08-04T19:02:23.112456669Z 
 18%|█▊        | 1027/5712 [2:24:14<11:00:29,  8.46s/it]08/04/2024 12:02:23 - INFO - __main__ -   Step: 1027, LR: 4.556500644470926e-07, Loss: 0.39856189489364624
2024-08-04T19:02:31.343667116Z 
 18%|█▊        | 1028/5712 [2:24:22<10:55:01,  8.39s/it]08/04/2024 12:02:31 - INFO - __main__ -   Step: 1028, LR: 4.555527858167757e-07, Loss: 0.49801796674728394
2024-08-04T19:02:39.524317567Z 
 18%|█▊        | 1029/5712 [2:24:30<10:49:57,  8.33s/it]08/04/2024 12:02:39 - INFO - __main__ -   Step: 1029, LR: 4.5545550718645883e-07, Loss: 0.43855738639831543
2024-08-04T19:02:47.908809425Z 
 18%|█▊        | 1030/5712 [2:24:39<10:51:09,  8.34s/it]08/04/2024 12:02:47 - INFO - __main__ -   Step: 1030, LR: 4.5535822855614193e-07, Loss: 0.635666012763977
2024-08-04T19:02:56.131060241Z 
 18%|█▊        | 1031/5712 [2:24:47<10:48:09,  8.31s/it]08/04/2024 12:02:56 - INFO - __main__ -   Step: 1031, LR: 4.5526094992582503e-07, Loss: 0.4918268322944641
2024-08-04T19:03:05.162798872Z 
 18%|█▊        | 1032/5712 [2:24:56<11:04:57,  8.53s/it]08/04/2024 12:03:05 - INFO - __main__ -   Step: 1032, LR: 4.551636712955081e-07, Loss: 0.425851970911026
2024-08-04T19:03:13.725801103Z 
 18%|█▊        | 1033/5712 [2:25:04<11:05:41,  8.54s/it]08/04/2024 12:03:13 - INFO - __main__ -   Step: 1033, LR: 4.550663926651913e-07, Loss: 0.5506389141082764
2024-08-04T19:03:22.220201581Z 
 18%|█▊        | 1034/5712 [2:25:13<11:04:34,  8.52s/it]08/04/2024 12:03:22 - INFO - __main__ -   Step: 1034, LR: 4.549691140348744e-07, Loss: 0.6226696968078613
2024-08-04T19:03:30.679345913Z 
 18%|█▊        | 1035/5712 [2:25:21<11:02:55,  8.50s/it]08/04/2024 12:03:30 - INFO - __main__ -   Step: 1035, LR: 4.548718354045575e-07, Loss: 0.41301092505455017
2024-08-04T19:03:38.798503696Z 
 18%|█▊        | 1036/5712 [2:25:29<10:53:46,  8.39s/it]08/04/2024 12:03:38 - INFO - __main__ -   Step: 1036, LR: 4.547745567742406e-07, Loss: 0.32244884967803955
2024-08-04T19:03:47.050924108Z 
 18%|█▊        | 1037/5712 [2:25:38<10:50:26,  8.35s/it]08/04/2024 12:03:47 - INFO - __main__ -   Step: 1037, LR: 4.5467727814392373e-07, Loss: 0.33380401134490967
2024-08-04T19:03:55.625364441Z 
 18%|█▊        | 1038/5712 [2:25:46<10:55:36,  8.42s/it]08/04/2024 12:03:55 - INFO - __main__ -   Step: 1038, LR: 4.545799995136068e-07, Loss: 0.4248761534690857
2024-08-04T19:04:04.062777529Z 
 18%|█▊        | 1039/5712 [2:25:55<10:55:57,  8.42s/it]08/04/2024 12:04:04 - INFO - __main__ -   Step: 1039, LR: 4.544827208832899e-07, Loss: 0.401248574256897
2024-08-04T19:04:12.485888148Z 
 18%|█▊        | 1040/5712 [2:26:03<10:55:50,  8.42s/it]08/04/2024 12:04:12 - INFO - __main__ -   Step: 1040, LR: 4.54385442252973e-07, Loss: 0.4179862141609192
2024-08-04T19:04:21.247531207Z 
 18%|█▊        | 1041/5712 [2:26:12<11:03:36,  8.52s/it]08/04/2024 12:04:21 - INFO - __main__ -   Step: 1041, LR: 4.542881636226562e-07, Loss: 0.7343630194664001
2024-08-04T19:04:30.072605651Z 
 18%|█▊        | 1042/5712 [2:26:21<11:10:29,  8.61s/it]08/04/2024 12:04:30 - INFO - __main__ -   Step: 1042, LR: 4.541908849923393e-07, Loss: 0.45278313755989075
2024-08-04T19:04:38.166451637Z 
 18%|█▊        | 1043/5712 [2:26:29<10:58:11,  8.46s/it]08/04/2024 12:04:38 - INFO - __main__ -   Step: 1043, LR: 4.540936063620224e-07, Loss: 0.6260176301002502
2024-08-04T19:04:46.898331173Z 
 18%|█▊        | 1044/5712 [2:26:38<11:04:26,  8.54s/it]08/04/2024 12:04:46 - INFO - __main__ -   Step: 1044, LR: 4.539963277317055e-07, Loss: 0.44367629289627075
2024-08-04T19:04:54.927601868Z 
 18%|█▊        | 1045/5712 [2:26:46<10:52:22,  8.39s/it]08/04/2024 12:04:54 - INFO - __main__ -   Step: 1045, LR: 4.538990491013887e-07, Loss: 0.44719409942626953
2024-08-04T19:05:03.357507150Z 
 18%|█▊        | 1046/5712 [2:26:54<10:53:14,  8.40s/it]08/04/2024 12:05:03 - INFO - __main__ -   Step: 1046, LR: 4.538017704710718e-07, Loss: 0.5570873022079468
2024-08-04T19:05:11.864672460Z 
 18%|█▊        | 1047/5712 [2:27:03<10:55:35,  8.43s/it]08/04/2024 12:05:11 - INFO - __main__ -   Step: 1047, LR: 4.537044918407549e-07, Loss: 0.6745177507400513
2024-08-04T19:05:20.035228674Z 
 18%|█▊        | 1048/5712 [2:27:11<10:49:21,  8.35s/it]08/04/2024 12:05:20 - INFO - __main__ -   Step: 1048, LR: 4.53607213210438e-07, Loss: 0.5016213655471802
2024-08-04T19:05:28.484137086Z 
 18%|█▊        | 1049/5712 [2:27:19<10:51:26,  8.38s/it]08/04/2024 12:05:28 - INFO - __main__ -   Step: 1049, LR: 4.535099345801211e-07, Loss: 0.40396827459335327
2024-08-04T19:05:37.400569903Z 
 18%|█▊        | 1050/5712 [2:27:28<11:03:44,  8.54s/it]08/04/2024 12:05:37 - INFO - __main__ -   Step: 1050, LR: 4.5341265594980423e-07, Loss: 0.5284316539764404
2024-08-04T19:05:45.853587755Z 
 18%|█▊        | 1051/5712 [2:27:37<11:01:31,  8.52s/it]08/04/2024 12:05:45 - INFO - __main__ -   Step: 1051, LR: 4.533153773194873e-07, Loss: 0.4895188808441162
2024-08-04T19:05:54.964281777Z 
 18%|█▊        | 1052/5712 [2:27:46<11:15:14,  8.69s/it]08/04/2024 12:05:54 - INFO - __main__ -   Step: 1052, LR: 4.532180986891704e-07, Loss: 0.4074745774269104
2024-08-04T19:06:03.751827971Z 
 18%|█▊        | 1053/5712 [2:27:54<11:17:17,  8.72s/it]08/04/2024 12:06:03 - INFO - __main__ -   Step: 1053, LR: 4.531208200588535e-07, Loss: 0.5133497714996338
2024-08-04T19:06:11.747567712Z 
 18%|█▊        | 1054/5712 [2:28:02<11:00:12,  8.50s/it]08/04/2024 12:06:11 - INFO - __main__ -   Step: 1054, LR: 4.530235414285367e-07, Loss: 0.4552915394306183
2024-08-04T19:06:20.188793359Z 
 18%|█▊        | 1055/5712 [2:28:11<10:58:36,  8.49s/it]08/04/2024 12:06:20 - INFO - __main__ -   Step: 1055, LR: 4.529262627982198e-07, Loss: 0.49524739384651184
2024-08-04T19:06:28.830686990Z 
 18%|█▊        | 1056/5712 [2:28:19<11:02:06,  8.53s/it]08/04/2024 12:06:28 - INFO - __main__ -   Step: 1056, LR: 4.528289841679029e-07, Loss: 0.4727800488471985
2024-08-04T19:06:37.119493460Z 
 19%|█▊        | 1057/5712 [2:28:28<10:56:17,  8.46s/it]08/04/2024 12:06:37 - INFO - __main__ -   Step: 1057, LR: 4.5273170553758597e-07, Loss: 0.3631315529346466
2024-08-04T19:06:45.681415657Z 
 19%|█▊        | 1058/5712 [2:28:36<10:58:32,  8.49s/it]08/04/2024 12:06:45 - INFO - __main__ -   Step: 1058, LR: 4.526344269072691e-07, Loss: 0.35819223523139954
2024-08-04T19:06:54.534931162Z 
 19%|█▊        | 1059/5712 [2:28:45<11:06:51,  8.60s/it]08/04/2024 12:06:54 - INFO - __main__ -   Step: 1059, LR: 4.525371482769522e-07, Loss: 0.46473586559295654
2024-08-04T19:07:02.740522987Z 
 19%|█▊        | 1060/5712 [2:28:53<10:57:33,  8.48s/it]08/04/2024 12:07:02 - INFO - __main__ -   Step: 1060, LR: 4.524398696466353e-07, Loss: 0.47548502683639526
2024-08-04T19:07:11.294393007Z 
 19%|█▊        | 1061/5712 [2:29:02<10:59:06,  8.50s/it]08/04/2024 12:07:11 - INFO - __main__ -   Step: 1061, LR: 4.523425910163184e-07, Loss: 0.4061735272407532
2024-08-04T19:07:19.663289753Z 
 19%|█▊        | 1062/5712 [2:29:10<10:55:51,  8.46s/it]08/04/2024 12:07:19 - INFO - __main__ -   Step: 1062, LR: 4.5224531238600163e-07, Loss: 0.41640564799308777
2024-08-04T19:07:27.797056688Z 
 19%|█▊        | 1063/5712 [2:29:18<10:48:04,  8.36s/it]08/04/2024 12:07:27 - INFO - __main__ -   Step: 1063, LR: 4.521480337556847e-07, Loss: 0.5553367137908936
2024-08-04T19:07:36.436276011Z 
 19%|█▊        | 1064/5712 [2:29:27<10:54:19,  8.45s/it]08/04/2024 12:07:36 - INFO - __main__ -   Step: 1064, LR: 4.520507551253678e-07, Loss: 0.5648025274276733
2024-08-04T19:07:44.984204169Z 
 19%|█▊        | 1065/5712 [2:29:36<10:56:32,  8.48s/it]08/04/2024 12:07:44 - INFO - __main__ -   Step: 1065, LR: 4.519534764950509e-07, Loss: 0.45587581396102905
2024-08-04T19:07:53.715333555Z 
 19%|█▊        | 1066/5712 [2:29:44<11:02:18,  8.55s/it]08/04/2024 12:07:53 - INFO - __main__ -   Step: 1066, LR: 4.518561978647341e-07, Loss: 0.5265212655067444
2024-08-04T19:08:02.828093431Z 
 19%|█▊        | 1067/5712 [2:29:53<11:15:09,  8.72s/it]08/04/2024 12:08:02 - INFO - __main__ -   Step: 1067, LR: 4.517589192344172e-07, Loss: 0.475923091173172
2024-08-04T19:08:11.584696482Z 
 19%|█▊        | 1068/5712 [2:30:02<11:15:50,  8.73s/it]08/04/2024 12:08:11 - INFO - __main__ -   Step: 1068, LR: 4.516616406041003e-07, Loss: 0.46019935607910156
2024-08-04T19:08:20.387358098Z 
 19%|█▊        | 1069/5712 [2:30:11<11:17:20,  8.75s/it]08/04/2024 12:08:20 - INFO - __main__ -   Step: 1069, LR: 4.5156436197378337e-07, Loss: 0.39703044295310974
2024-08-04T19:08:28.429202734Z 
 19%|█▊        | 1070/5712 [2:30:19<11:00:41,  8.54s/it]08/04/2024 12:08:28 - INFO - __main__ -   Step: 1070, LR: 4.514670833434665e-07, Loss: 0.5396270751953125
2024-08-04T19:08:36.406024268Z 
 19%|█▉        | 1071/5712 [2:30:27<10:47:28,  8.37s/it]08/04/2024 12:08:36 - INFO - __main__ -   Step: 1071, LR: 4.513698047131496e-07, Loss: 0.48673492670059204
2024-08-04T19:08:44.935720481Z 
 19%|█▉        | 1072/5712 [2:30:36<10:51:01,  8.42s/it]08/04/2024 12:08:44 - INFO - __main__ -   Step: 1072, LR: 4.512725260828327e-07, Loss: 0.6081031560897827
2024-08-04T19:08:53.513566225Z 
 19%|█▉        | 1073/5712 [2:30:44<10:54:35,  8.47s/it]08/04/2024 12:08:53 - INFO - __main__ -   Step: 1073, LR: 4.511752474525158e-07, Loss: 0.5700291991233826
2024-08-04T19:09:02.300719254Z 
 19%|█▉        | 1074/5712 [2:30:53<11:01:53,  8.56s/it]08/04/2024 12:09:02 - INFO - __main__ -   Step: 1074, LR: 4.51077968822199e-07, Loss: 0.5471363067626953
2024-08-04T19:09:10.791020655Z 
 19%|█▉        | 1075/5712 [2:31:01<11:00:03,  8.54s/it]08/04/2024 12:09:10 - INFO - __main__ -   Step: 1075, LR: 4.5098069019188207e-07, Loss: 0.5245060324668884
2024-08-04T19:09:19.297508854Z 
 19%|█▉        | 1076/5712 [2:31:10<10:59:07,  8.53s/it]08/04/2024 12:09:19 - INFO - __main__ -   Step: 1076, LR: 4.5088341156156517e-07, Loss: 0.44515514373779297
2024-08-04T19:09:27.759827615Z 
 19%|█▉        | 1077/5712 [2:31:18<10:57:23,  8.51s/it]08/04/2024 12:09:27 - INFO - __main__ -   Step: 1077, LR: 4.5078613293124827e-07, Loss: 0.44303882122039795
2024-08-04T19:09:36.074050102Z 
 19%|█▉        | 1078/5712 [2:31:27<10:52:43,  8.45s/it]08/04/2024 12:09:36 - INFO - __main__ -   Step: 1078, LR: 4.506888543009314e-07, Loss: 0.4289257526397705
2024-08-04T19:09:44.098480109Z 
 19%|█▉        | 1079/5712 [2:31:35<10:42:41,  8.32s/it]08/04/2024 12:09:44 - INFO - __main__ -   Step: 1079, LR: 4.505915756706145e-07, Loss: 0.4366121292114258
2024-08-04T19:09:51.998825409Z 
 19%|█▉        | 1080/5712 [2:31:43<10:32:45,  8.20s/it]08/04/2024 12:09:51 - INFO - __main__ -   Step: 1080, LR: 4.504942970402977e-07, Loss: 0.5083414912223816
2024-08-04T19:10:00.396074741Z 
 19%|█▉        | 1081/5712 [2:31:51<10:37:16,  8.26s/it]08/04/2024 12:10:00 - INFO - __main__ -   Step: 1081, LR: 4.5039701840998077e-07, Loss: 0.5381654500961304
2024-08-04T19:10:08.811900573Z 
 19%|█▉        | 1082/5712 [2:31:59<10:40:49,  8.30s/it]08/04/2024 12:10:08 - INFO - __main__ -   Step: 1082, LR: 4.502997397796639e-07, Loss: 0.5180544853210449
2024-08-04T19:10:17.112649019Z 
 19%|█▉        | 1083/5712 [2:32:08<10:40:36,  8.30s/it]08/04/2024 12:10:17 - INFO - __main__ -   Step: 1083, LR: 4.50202461149347e-07, Loss: 0.4402507543563843
2024-08-04T19:10:26.229734198Z 
 19%|█▉        | 1084/5712 [2:32:17<10:59:17,  8.55s/it]08/04/2024 12:10:26 - INFO - __main__ -   Step: 1084, LR: 4.501051825190301e-07, Loss: 0.5062817335128784
2024-08-04T19:10:35.129299076Z 
 19%|█▉        | 1085/5712 [2:32:26<11:07:17,  8.65s/it]08/04/2024 12:10:35 - INFO - __main__ -   Step: 1085, LR: 4.500079038887132e-07, Loss: 0.43525660037994385
2024-08-04T19:10:43.698209706Z 
 19%|█▉        | 1086/5712 [2:32:34<11:05:12,  8.63s/it]08/04/2024 12:10:43 - INFO - __main__ -   Step: 1086, LR: 4.499106252583963e-07, Loss: 0.42378103733062744
2024-08-04T19:10:51.889448970Z 
 19%|█▉        | 1087/5712 [2:32:43<10:54:58,  8.50s/it]08/04/2024 12:10:51 - INFO - __main__ -   Step: 1087, LR: 4.498133466280795e-07, Loss: 0.49574732780456543
2024-08-04T19:10:59.938791414Z 
 19%|█▉        | 1088/5712 [2:32:51<10:44:28,  8.36s/it]08/04/2024 12:10:59 - INFO - __main__ -   Step: 1088, LR: 4.4971606799776257e-07, Loss: 0.544055700302124
2024-08-04T19:11:08.178098431Z 
 19%|█▉        | 1089/5712 [2:32:59<10:41:29,  8.33s/it]08/04/2024 12:11:08 - INFO - __main__ -   Step: 1089, LR: 4.4961878936744567e-07, Loss: 0.549127459526062
2024-08-04T19:11:16.915725597Z 
 19%|█▉        | 1090/5712 [2:33:08<10:50:52,  8.45s/it]08/04/2024 12:11:16 - INFO - __main__ -   Step: 1090, LR: 4.4952151073712877e-07, Loss: 0.578109622001648
2024-08-04T19:11:25.332885984Z 
 19%|█▉        | 1091/5712 [2:33:16<10:49:59,  8.44s/it]08/04/2024 12:11:25 - INFO - __main__ -   Step: 1091, LR: 4.494242321068119e-07, Loss: 0.48727965354919434
2024-08-04T19:11:33.575159476Z 
 19%|█▉        | 1092/5712 [2:33:24<10:45:17,  8.38s/it]08/04/2024 12:11:33 - INFO - __main__ -   Step: 1092, LR: 4.49326953476495e-07, Loss: 0.46786147356033325
2024-08-04T19:11:42.242560487Z 
 19%|█▉        | 1093/5712 [2:33:33<10:51:46,  8.47s/it]08/04/2024 12:11:42 - INFO - __main__ -   Step: 1093, LR: 4.492296748461781e-07, Loss: 0.4266982674598694
2024-08-04T19:11:50.817271420Z 
 19%|█▉        | 1094/5712 [2:33:41<10:54:07,  8.50s/it]08/04/2024 12:11:50 - INFO - __main__ -   Step: 1094, LR: 4.491323962158612e-07, Loss: 0.3893929719924927
2024-08-04T19:11:58.922500832Z 
 19%|█▉        | 1095/5712 [2:33:50<10:44:54,  8.38s/it]08/04/2024 12:11:58 - INFO - __main__ -   Step: 1095, LR: 4.4903511758554437e-07, Loss: 0.45580214262008667
2024-08-04T19:12:06.855140589Z 
 19%|█▉        | 1096/5712 [2:33:58<10:34:25,  8.25s/it]08/04/2024 12:12:06 - INFO - __main__ -   Step: 1096, LR: 4.4893783895522747e-07, Loss: 0.5318378210067749
2024-08-04T19:12:15.045122347Z 
 19%|█▉        | 1097/5712 [2:34:06<10:32:59,  8.23s/it]08/04/2024 12:12:15 - INFO - __main__ -   Step: 1097, LR: 4.4884056032491057e-07, Loss: 0.32681265473365784
2024-08-04T19:12:23.880371620Z 
 19%|█▉        | 1098/5712 [2:34:15<10:46:49,  8.41s/it]08/04/2024 12:12:23 - INFO - __main__ -   Step: 1098, LR: 4.487432816945937e-07, Loss: 0.4147000014781952
2024-08-04T19:12:32.185902961Z 
 19%|█▉        | 1099/5712 [2:34:23<10:44:14,  8.38s/it]08/04/2024 12:12:32 - INFO - __main__ -   Step: 1099, LR: 4.486460030642769e-07, Loss: 0.3474687337875366
2024-08-04T19:12:40.359643974Z 
 19%|█▉        | 1100/5712 [2:34:31<10:39:21,  8.32s/it]08/04/2024 12:12:40 - INFO - __main__ -   Step: 1100, LR: 4.4854872443395997e-07, Loss: 0.5626079440116882
2024-08-04T19:12:49.044360842Z 
 19%|█▉        | 1101/5712 [2:34:40<10:47:40,  8.43s/it]08/04/2024 12:12:49 - INFO - __main__ -   Step: 1101, LR: 4.4845144580364307e-07, Loss: 0.4323890209197998
2024-08-04T19:12:58.428355905Z 
 19%|█▉        | 1102/5712 [2:34:49<11:09:34,  8.71s/it]08/04/2024 12:12:58 - INFO - __main__ -   Step: 1102, LR: 4.4835416717332617e-07, Loss: 0.37529653310775757
2024-08-04T19:13:06.893419724Z 
 19%|█▉        | 1103/5712 [2:34:58<11:03:40,  8.64s/it]08/04/2024 12:13:06 - INFO - __main__ -   Step: 1103, LR: 4.482568885430093e-07, Loss: 0.42471522092819214
2024-08-04T19:13:14.847305561Z 
 19%|█▉        | 1104/5712 [2:35:05<10:47:44,  8.43s/it]08/04/2024 12:13:14 - INFO - __main__ -   Step: 1104, LR: 4.481596099126924e-07, Loss: 0.40241143107414246
2024-08-04T19:13:23.163242542Z 
 19%|█▉        | 1105/5712 [2:35:14<10:44:52,  8.40s/it]08/04/2024 12:13:23 - INFO - __main__ -   Step: 1105, LR: 4.480623312823755e-07, Loss: 0.4600847363471985
2024-08-04T19:13:31.738120582Z 
 19%|█▉        | 1106/5712 [2:35:22<10:48:47,  8.45s/it]08/04/2024 12:13:31 - INFO - __main__ -   Step: 1106, LR: 4.479650526520586e-07, Loss: 0.5697449445724487
2024-08-04T19:13:40.416191228Z 
 19%|█▉        | 1107/5712 [2:35:31<10:53:51,  8.52s/it]08/04/2024 12:13:40 - INFO - __main__ -   Step: 1107, LR: 4.4786777402174177e-07, Loss: 0.6026787757873535
2024-08-04T19:13:49.112497887Z 
 19%|█▉        | 1108/5712 [2:35:40<10:57:48,  8.57s/it]08/04/2024 12:13:49 - INFO - __main__ -   Step: 1108, LR: 4.4777049539142487e-07, Loss: 0.38066062331199646
2024-08-04T19:13:57.552124652Z 
 19%|█▉        | 1109/5712 [2:35:48<10:54:35,  8.53s/it]08/04/2024 12:13:57 - INFO - __main__ -   Step: 1109, LR: 4.4767321676110797e-07, Loss: 0.5625531673431396
2024-08-04T19:14:06.329782862Z 
 19%|█▉        | 1110/5712 [2:35:57<11:00:05,  8.61s/it]08/04/2024 12:14:06 - INFO - __main__ -   Step: 1110, LR: 4.4757593813079107e-07, Loss: 0.3580433130264282
2024-08-04T19:14:14.648553797Z 
 19%|█▉        | 1111/5712 [2:36:05<10:53:20,  8.52s/it]08/04/2024 12:14:14 - INFO - __main__ -   Step: 1111, LR: 4.474786595004742e-07, Loss: 0.43517062067985535
2024-08-04T19:14:23.031325089Z 
 19%|█▉        | 1112/5712 [2:36:14<10:50:02,  8.48s/it]08/04/2024 12:14:23 - INFO - __main__ -   Step: 1112, LR: 4.473813808701573e-07, Loss: 0.5500366687774658
2024-08-04T19:14:30.798020579Z 
 19%|█▉        | 1113/5712 [2:36:21<10:33:31,  8.27s/it]08/04/2024 12:14:30 - INFO - __main__ -   Step: 1113, LR: 4.472841022398404e-07, Loss: 0.41513025760650635
2024-08-04T19:14:39.389883475Z 
 20%|█▉        | 1114/5712 [2:36:30<10:40:53,  8.36s/it]08/04/2024 12:14:39 - INFO - __main__ -   Step: 1114, LR: 4.471868236095235e-07, Loss: 0.4482072591781616
2024-08-04T19:14:48.149380194Z 
 20%|█▉        | 1115/5712 [2:36:39<10:49:52,  8.48s/it]08/04/2024 12:14:48 - INFO - __main__ -   Step: 1115, LR: 4.4708954497920667e-07, Loss: 0.45147255063056946
2024-08-04T19:14:56.830870419Z 
 20%|█▉        | 1116/5712 [2:36:47<10:54:18,  8.54s/it]08/04/2024 12:14:56 - INFO - __main__ -   Step: 1116, LR: 4.469922663488898e-07, Loss: 0.4647566080093384
2024-08-04T19:15:05.337341667Z 
 20%|█▉        | 1117/5712 [2:36:56<10:53:21,  8.53s/it]08/04/2024 12:15:05 - INFO - __main__ -   Step: 1117, LR: 4.468949877185729e-07, Loss: 0.4666735827922821
2024-08-04T19:15:14.455824896Z 
 20%|█▉        | 1118/5712 [2:37:05<11:06:41,  8.71s/it]08/04/2024 12:15:14 - INFO - __main__ -   Step: 1118, LR: 4.46797709088256e-07, Loss: 0.38571426272392273
2024-08-04T19:15:23.291083524Z 
 20%|█▉        | 1119/5712 [2:37:14<11:09:29,  8.75s/it]08/04/2024 12:15:23 - INFO - __main__ -   Step: 1119, LR: 4.4670043045793917e-07, Loss: 0.5735300183296204
2024-08-04T19:15:31.557372147Z 
 20%|█▉        | 1120/5712 [2:37:22<10:58:19,  8.60s/it]08/04/2024 12:15:31 - INFO - __main__ -   Step: 1120, LR: 4.4660315182762227e-07, Loss: 0.38798317313194275
2024-08-04T19:15:39.286588769Z 
 20%|█▉        | 1121/5712 [2:37:30<10:38:09,  8.34s/it]08/04/2024 12:15:39 - INFO - __main__ -   Step: 1121, LR: 4.4650587319730537e-07, Loss: 0.4855273962020874
2024-08-04T19:15:47.633923680Z 
 20%|█▉        | 1122/5712 [2:37:38<10:38:11,  8.34s/it]08/04/2024 12:15:47 - INFO - __main__ -   Step: 1122, LR: 4.4640859456698847e-07, Loss: 0.3739365041255951
2024-08-04T19:15:57.238840628Z 
 20%|█▉        | 1123/5712 [2:37:48<11:07:00,  8.72s/it]08/04/2024 12:15:57 - INFO - __main__ -   Step: 1123, LR: 4.463113159366716e-07, Loss: 0.41312241554260254
2024-08-04T19:16:05.996714282Z 
 20%|█▉        | 1124/5712 [2:37:57<11:07:42,  8.73s/it]08/04/2024 12:16:05 - INFO - __main__ -   Step: 1124, LR: 4.462140373063547e-07, Loss: 0.5041690468788147
2024-08-04T19:16:14.819989372Z 
 20%|█▉        | 1125/5712 [2:38:05<11:09:39,  8.76s/it]08/04/2024 12:16:14 - INFO - __main__ -   Step: 1125, LR: 4.461167586760378e-07, Loss: 0.5322942733764648
2024-08-04T19:16:23.125763988Z 
 20%|█▉        | 1126/5712 [2:38:14<10:59:06,  8.62s/it]08/04/2024 12:16:23 - INFO - __main__ -   Step: 1126, LR: 4.460194800457209e-07, Loss: 0.499949187040329
2024-08-04T19:16:31.901492739Z 
 20%|█▉        | 1127/5712 [2:38:23<11:02:27,  8.67s/it]08/04/2024 12:16:31 - INFO - __main__ -   Step: 1127, LR: 4.45922201415404e-07, Loss: 0.5860180258750916
2024-08-04T19:16:40.170565673Z 
 20%|█▉        | 1128/5712 [2:38:31<10:53:08,  8.55s/it]08/04/2024 12:16:40 - INFO - __main__ -   Step: 1128, LR: 4.4582492278508717e-07, Loss: 0.4658941626548767
2024-08-04T19:16:48.435533045Z 
 20%|█▉        | 1129/5712 [2:38:39<10:46:29,  8.46s/it]08/04/2024 12:16:48 - INFO - __main__ -   Step: 1129, LR: 4.4572764415477027e-07, Loss: 0.383683979511261
2024-08-04T19:16:56.464040793Z 
 20%|█▉        | 1130/5712 [2:38:47<10:36:22,  8.33s/it]08/04/2024 12:16:56 - INFO - __main__ -   Step: 1130, LR: 4.4563036552445337e-07, Loss: 0.43837153911590576
2024-08-04T19:17:05.068902312Z 
 20%|█▉        | 1131/5712 [2:38:56<10:42:28,  8.41s/it]08/04/2024 12:17:05 - INFO - __main__ -   Step: 1131, LR: 4.4553308689413647e-07, Loss: 0.4364449679851532
2024-08-04T19:17:13.573265809Z 
 20%|█▉        | 1132/5712 [2:39:04<10:44:22,  8.44s/it]08/04/2024 12:17:13 - INFO - __main__ -   Step: 1132, LR: 4.454358082638196e-07, Loss: 0.3770013451576233
2024-08-04T19:17:21.945575371Z 
 20%|█▉        | 1133/5712 [2:39:13<10:42:39,  8.42s/it]08/04/2024 12:17:21 - INFO - __main__ -   Step: 1133, LR: 4.453385296335027e-07, Loss: 0.5550633072853088
2024-08-04T19:17:30.466472810Z 
 20%|█▉        | 1134/5712 [2:39:21<10:44:48,  8.45s/it]08/04/2024 12:17:30 - INFO - __main__ -   Step: 1134, LR: 4.4524125100318587e-07, Loss: 0.46564343571662903
2024-08-04T19:17:39.168253547Z 
 20%|█▉        | 1135/5712 [2:39:30<10:50:24,  8.53s/it]08/04/2024 12:17:39 - INFO - __main__ -   Step: 1135, LR: 4.4514397237286897e-07, Loss: 0.5953593254089355
2024-08-04T19:17:47.753361125Z 
 20%|█▉        | 1136/5712 [2:39:38<10:51:36,  8.54s/it]08/04/2024 12:17:47 - INFO - __main__ -   Step: 1136, LR: 4.450466937425521e-07, Loss: 0.44643256068229675
2024-08-04T19:17:56.082933529Z 
 20%|█▉        | 1137/5712 [2:39:47<10:46:33,  8.48s/it]08/04/2024 12:17:56 - INFO - __main__ -   Step: 1137, LR: 4.449494151122352e-07, Loss: 0.3715411424636841
2024-08-04T19:18:04.046942688Z 
 20%|█▉        | 1138/5712 [2:39:55<10:34:38,  8.32s/it]08/04/2024 12:18:04 - INFO - __main__ -   Step: 1138, LR: 4.448521364819183e-07, Loss: 0.386152982711792
2024-08-04T19:18:12.603189880Z 
 20%|█▉        | 1139/5712 [2:40:03<10:39:45,  8.39s/it]08/04/2024 12:18:12 - INFO - __main__ -   Step: 1139, LR: 4.447548578516014e-07, Loss: 0.4724491238594055
2024-08-04T19:18:22.114269453Z 
 20%|█▉        | 1140/5712 [2:40:13<11:05:10,  8.73s/it]08/04/2024 12:18:22 - INFO - __main__ -   Step: 1140, LR: 4.4465757922128457e-07, Loss: 0.5850918292999268
2024-08-04T19:18:30.596288919Z 
 20%|█▉        | 1141/5712 [2:40:21<10:59:22,  8.66s/it]08/04/2024 12:18:30 - INFO - __main__ -   Step: 1141, LR: 4.4456030059096767e-07, Loss: 0.46557432413101196
2024-08-04T19:18:39.247756934Z 
 20%|█▉        | 1142/5712 [2:40:30<10:59:09,  8.65s/it]08/04/2024 12:18:39 - INFO - __main__ -   Step: 1142, LR: 4.4446302196065077e-07, Loss: 0.4908575415611267
2024-08-04T19:18:47.410709978Z 
 20%|██        | 1143/5712 [2:40:38<10:47:47,  8.51s/it]08/04/2024 12:18:47 - INFO - __main__ -   Step: 1143, LR: 4.4436574333033387e-07, Loss: 0.4587612748146057
2024-08-04T19:18:56.082386555Z 
 20%|██        | 1144/5712 [2:40:47<10:51:24,  8.56s/it]08/04/2024 12:18:56 - INFO - __main__ -   Step: 1144, LR: 4.44268464700017e-07, Loss: 0.5327097177505493
2024-08-04T19:19:04.427758074Z 
 20%|██        | 1145/5712 [2:40:55<10:46:27,  8.49s/it]08/04/2024 12:19:04 - INFO - __main__ -   Step: 1145, LR: 4.441711860697001e-07, Loss: 0.7033630013465881
2024-08-04T19:19:12.552216399Z 
 20%|██        | 1146/5712 [2:41:03<10:37:54,  8.38s/it]08/04/2024 12:19:12 - INFO - __main__ -   Step: 1146, LR: 4.440739074393832e-07, Loss: 0.40007203817367554
2024-08-04T19:19:20.712652454Z 
 20%|██        | 1147/5712 [2:41:11<10:32:42,  8.32s/it]08/04/2024 12:19:20 - INFO - __main__ -   Step: 1147, LR: 4.439766288090663e-07, Loss: 0.48652634024620056
2024-08-04T19:19:29.042345444Z 
 20%|██        | 1148/5712 [2:41:20<10:32:52,  8.32s/it]08/04/2024 12:19:29 - INFO - __main__ -   Step: 1148, LR: 4.4387935017874947e-07, Loss: 0.4753405749797821
2024-08-04T19:19:37.607548587Z 
 20%|██        | 1149/5712 [2:41:28<10:38:19,  8.39s/it]08/04/2024 12:19:37 - INFO - __main__ -   Step: 1149, LR: 4.4378207154843257e-07, Loss: 0.40956294536590576
2024-08-04T19:19:46.080051095Z 
 20%|██        | 1150/5712 [2:41:37<10:39:59,  8.42s/it]08/04/2024 12:19:46 - INFO - __main__ -   Step: 1150, LR: 4.4368479291811567e-07, Loss: 0.40692245960235596
2024-08-04T19:19:54.540047697Z 
 20%|██        | 1151/5712 [2:41:45<10:40:49,  8.43s/it]08/04/2024 12:19:54 - INFO - __main__ -   Step: 1151, LR: 4.4358751428779877e-07, Loss: 0.46255141496658325
2024-08-04T19:20:03.043954017Z 
 20%|██        | 1152/5712 [2:41:54<10:42:22,  8.45s/it]08/04/2024 12:20:03 - INFO - __main__ -   Step: 1152, LR: 4.4349023565748197e-07, Loss: 0.33290237188339233
2024-08-04T19:20:11.827574038Z 
 20%|██        | 1153/5712 [2:42:02<10:49:47,  8.55s/it]08/04/2024 12:20:11 - INFO - __main__ -   Step: 1153, LR: 4.4339295702716507e-07, Loss: 0.43512803316116333
2024-08-04T19:20:19.976053240Z 
 20%|██        | 1154/5712 [2:42:11<10:40:27,  8.43s/it]08/04/2024 12:20:19 - INFO - __main__ -   Step: 1154, LR: 4.4329567839684817e-07, Loss: 0.46484237909317017
2024-08-04T19:20:27.893965859Z 
 20%|██        | 1155/5712 [2:42:19<10:28:37,  8.28s/it]08/04/2024 12:20:27 - INFO - __main__ -   Step: 1155, LR: 4.4319839976653127e-07, Loss: 0.41862353682518005
2024-08-04T19:20:36.152973265Z 
 20%|██        | 1156/5712 [2:42:27<10:28:04,  8.27s/it]08/04/2024 12:20:36 - INFO - __main__ -   Step: 1156, LR: 4.431011211362144e-07, Loss: 0.37738755345344543
2024-08-04T19:20:44.982133515Z 
 20%|██        | 1157/5712 [2:42:36<10:40:38,  8.44s/it]08/04/2024 12:20:44 - INFO - __main__ -   Step: 1157, LR: 4.430038425058975e-07, Loss: 0.4924071431159973
2024-08-04T19:20:53.649774499Z 
 20%|██        | 1158/5712 [2:42:44<10:45:42,  8.51s/it]08/04/2024 12:20:53 - INFO - __main__ -   Step: 1158, LR: 4.429065638755806e-07, Loss: 0.44886064529418945
2024-08-04T19:21:02.603844540Z 
 20%|██        | 1159/5712 [2:42:53<10:55:44,  8.64s/it]08/04/2024 12:21:02 - INFO - __main__ -   Step: 1159, LR: 4.428092852452637e-07, Loss: 0.5441542267799377
2024-08-04T19:21:10.661398066Z 
 20%|██        | 1160/5712 [2:43:01<10:42:18,  8.47s/it]08/04/2024 12:21:10 - INFO - __main__ -   Step: 1160, LR: 4.4271200661494687e-07, Loss: 0.45149296522140503
2024-08-04T19:21:19.014064017Z 
 20%|██        | 1161/5712 [2:43:10<10:39:34,  8.43s/it]08/04/2024 12:21:19 - INFO - __main__ -   Step: 1161, LR: 4.4261472798462997e-07, Loss: 0.41993510723114014
2024-08-04T19:21:27.300254879Z 
 20%|██        | 1162/5712 [2:43:18<10:36:07,  8.39s/it]08/04/2024 12:21:27 - INFO - __main__ -   Step: 1162, LR: 4.4251744935431307e-07, Loss: 0.43514013290405273
2024-08-04T19:21:35.463424636Z 
 20%|██        | 1163/5712 [2:43:26<10:30:51,  8.32s/it]08/04/2024 12:21:35 - INFO - __main__ -   Step: 1163, LR: 4.4242017072399617e-07, Loss: 0.4936995506286621
2024-08-04T19:21:43.666608768Z 
 20%|██        | 1164/5712 [2:43:34<10:28:02,  8.29s/it]08/04/2024 12:21:43 - INFO - __main__ -   Step: 1164, LR: 4.4232289209367926e-07, Loss: 0.40096038579940796
2024-08-04T19:21:52.243852924Z 
 20%|██        | 1165/5712 [2:43:43<10:34:32,  8.37s/it]08/04/2024 12:21:52 - INFO - __main__ -   Step: 1165, LR: 4.422256134633624e-07, Loss: 0.47535496950149536
2024-08-04T19:22:01.037640873Z 
 20%|██        | 1166/5712 [2:43:52<10:43:57,  8.50s/it]08/04/2024 12:22:01 - INFO - __main__ -   Step: 1166, LR: 4.421283348330455e-07, Loss: 0.3831076920032501
2024-08-04T19:22:09.757344002Z 
 20%|██        | 1167/5712 [2:44:00<10:48:49,  8.57s/it]08/04/2024 12:22:09 - INFO - __main__ -   Step: 1167, LR: 4.420310562027286e-07, Loss: 0.4251733124256134
2024-08-04T19:22:18.371968937Z 
 20%|██        | 1168/5712 [2:44:09<10:49:48,  8.58s/it]08/04/2024 12:22:18 - INFO - __main__ -   Step: 1168, LR: 4.419337775724117e-07, Loss: 0.46816515922546387
2024-08-04T19:22:27.416055606Z 
 20%|██        | 1169/5712 [2:44:18<11:00:11,  8.72s/it]08/04/2024 12:22:27 - INFO - __main__ -   Step: 1169, LR: 4.4183649894209487e-07, Loss: 0.5770300626754761
2024-08-04T19:22:35.433396793Z 
 20%|██        | 1170/5712 [2:44:26<10:44:06,  8.51s/it]08/04/2024 12:22:35 - INFO - __main__ -   Step: 1170, LR: 4.41739220311778e-07, Loss: 0.41868728399276733
2024-08-04T19:22:43.654640975Z 
 21%|██        | 1171/5712 [2:44:34<10:37:26,  8.42s/it]08/04/2024 12:22:43 - INFO - __main__ -   Step: 1171, LR: 4.416419416814611e-07, Loss: 0.5741405487060547
2024-08-04T19:22:52.009826483Z 
 21%|██        | 1172/5712 [2:44:43<10:35:46,  8.40s/it]08/04/2024 12:22:52 - INFO - __main__ -   Step: 1172, LR: 4.415446630511442e-07, Loss: 0.3536036014556885
2024-08-04T19:23:00.668011112Z 
 21%|██        | 1173/5712 [2:44:51<10:41:26,  8.48s/it]08/04/2024 12:23:00 - INFO - __main__ -   Step: 1173, LR: 4.4144738442082737e-07, Loss: 0.36774754524230957
2024-08-04T19:23:09.692172331Z 
 21%|██        | 1174/5712 [2:45:00<10:53:39,  8.64s/it]08/04/2024 12:23:09 - INFO - __main__ -   Step: 1174, LR: 4.4135010579051047e-07, Loss: 0.45409703254699707
2024-08-04T19:23:18.321468994Z 
 21%|██        | 1175/5712 [2:45:09<10:53:13,  8.64s/it]08/04/2024 12:23:18 - INFO - __main__ -   Step: 1175, LR: 4.4125282716019357e-07, Loss: 0.4446480870246887
2024-08-04T19:23:26.938360253Z 
 21%|██        | 1176/5712 [2:45:18<10:52:35,  8.63s/it]08/04/2024 12:23:26 - INFO - __main__ -   Step: 1176, LR: 4.4115554852987667e-07, Loss: 0.4730621874332428
2024-08-04T19:23:35.773283867Z 
 21%|██        | 1177/5712 [2:45:26<10:57:02,  8.69s/it]08/04/2024 12:23:35 - INFO - __main__ -   Step: 1177, LR: 4.410582698995598e-07, Loss: 0.5312955975532532
2024-08-04T19:23:44.046951552Z 
 21%|██        | 1178/5712 [2:45:35<10:47:23,  8.57s/it]08/04/2024 12:23:44 - INFO - __main__ -   Step: 1178, LR: 4.409609912692429e-07, Loss: 0.4827496111392975
2024-08-04T19:23:52.179829216Z 
 21%|██        | 1179/5712 [2:45:43<10:37:24,  8.44s/it]08/04/2024 12:23:52 - INFO - __main__ -   Step: 1179, LR: 4.40863712638926e-07, Loss: 0.44995731115341187
2024-08-04T19:24:00.245580947Z 
 21%|██        | 1180/5712 [2:45:51<10:28:51,  8.33s/it]08/04/2024 12:24:00 - INFO - __main__ -   Step: 1180, LR: 4.407664340086091e-07, Loss: 0.43581604957580566
2024-08-04T19:24:08.630155603Z 
 21%|██        | 1181/5712 [2:45:59<10:30:03,  8.34s/it]08/04/2024 12:24:08 - INFO - __main__ -   Step: 1181, LR: 4.4066915537829227e-07, Loss: 0.6569856405258179
2024-08-04T19:24:17.438375740Z 
 21%|██        | 1182/5712 [2:46:08<10:40:26,  8.48s/it]08/04/2024 12:24:17 - INFO - __main__ -   Step: 1182, LR: 4.4057187674797537e-07, Loss: 0.4420267343521118
2024-08-04T19:24:25.828898861Z 
 21%|██        | 1183/5712 [2:46:16<10:38:13,  8.46s/it]08/04/2024 12:24:25 - INFO - __main__ -   Step: 1183, LR: 4.4047459811765846e-07, Loss: 0.5215536952018738
2024-08-04T19:24:34.329328320Z 
 21%|██        | 1184/5712 [2:46:25<10:39:06,  8.47s/it]08/04/2024 12:24:34 - INFO - __main__ -   Step: 1184, LR: 4.4037731948734156e-07, Loss: 0.5287324786186218
2024-08-04T19:24:42.863038763Z 
 21%|██        | 1185/5712 [2:46:34<10:40:24,  8.49s/it]08/04/2024 12:24:42 - INFO - __main__ -   Step: 1185, LR: 4.402800408570247e-07, Loss: 0.3954736590385437
2024-08-04T19:24:51.232029172Z 
 21%|██        | 1186/5712 [2:46:42<10:37:35,  8.45s/it]08/04/2024 12:24:51 - INFO - __main__ -   Step: 1186, LR: 4.401827622267078e-07, Loss: 0.5297212600708008
2024-08-04T19:24:58.743242303Z 
 21%|██        | 1187/5712 [2:46:49<10:16:10,  8.17s/it]08/04/2024 12:24:58 - INFO - __main__ -   Step: 1187, LR: 4.400854835963909e-07, Loss: 0.2946222126483917
2024-08-04T19:25:06.992645514Z 
 21%|██        | 1188/5712 [2:46:58<10:17:49,  8.19s/it]08/04/2024 12:25:06 - INFO - __main__ -   Step: 1188, LR: 4.3998820496607407e-07, Loss: 0.5064386129379272
2024-08-04T19:25:15.214033537Z 
 21%|██        | 1189/5712 [2:47:06<10:18:18,  8.20s/it]08/04/2024 12:25:15 - INFO - __main__ -   Step: 1189, LR: 4.398909263357572e-07, Loss: 0.45954638719558716
2024-08-04T19:25:23.873279500Z 
 21%|██        | 1190/5712 [2:47:15<10:28:30,  8.34s/it]08/04/2024 12:25:23 - INFO - __main__ -   Step: 1190, LR: 4.397936477054403e-07, Loss: 0.38837963342666626
2024-08-04T19:25:32.486785654Z 
 21%|██        | 1191/5712 [2:47:23<10:34:33,  8.42s/it]08/04/2024 12:25:32 - INFO - __main__ -   Step: 1191, LR: 4.396963690751234e-07, Loss: 0.5199315547943115
2024-08-04T19:25:40.999314967Z 
 21%|██        | 1192/5712 [2:47:32<10:36:28,  8.45s/it]08/04/2024 12:25:40 - INFO - __main__ -   Step: 1192, LR: 4.395990904448065e-07, Loss: 0.3354353904724121
2024-08-04T19:25:49.582824513Z 
 21%|██        | 1193/5712 [2:47:40<10:39:22,  8.49s/it]08/04/2024 12:25:49 - INFO - __main__ -   Step: 1193, LR: 4.3950181181448967e-07, Loss: 0.5012173652648926
2024-08-04T19:25:58.256263091Z 
 21%|██        | 1194/5712 [2:47:49<10:43:23,  8.54s/it]08/04/2024 12:25:58 - INFO - __main__ -   Step: 1194, LR: 4.3940453318417277e-07, Loss: 0.3974619507789612
2024-08-04T19:26:06.479047406Z 
 21%|██        | 1195/5712 [2:47:57<10:35:59,  8.45s/it]08/04/2024 12:26:06 - INFO - __main__ -   Step: 1195, LR: 4.3930725455385586e-07, Loss: 0.4009496867656708
2024-08-04T19:26:14.473089736Z 
 21%|██        | 1196/5712 [2:48:05<10:25:35,  8.31s/it]08/04/2024 12:26:14 - INFO - __main__ -   Step: 1196, LR: 4.3920997592353896e-07, Loss: 0.3776454031467438
2024-08-04T19:26:23.491180284Z 
 21%|██        | 1197/5712 [2:48:14<10:41:24,  8.52s/it]08/04/2024 12:26:23 - INFO - __main__ -   Step: 1197, LR: 4.391126972932221e-07, Loss: 0.39855000376701355
2024-08-04T19:26:31.968640979Z 
 21%|██        | 1198/5712 [2:48:23<10:40:13,  8.51s/it]08/04/2024 12:26:31 - INFO - __main__ -   Step: 1198, LR: 4.390154186629052e-07, Loss: 0.4142402410507202
2024-08-04T19:26:40.333724585Z 
 21%|██        | 1199/5712 [2:48:31<10:36:49,  8.47s/it]08/04/2024 12:26:40 - INFO - __main__ -   Step: 1199, LR: 4.389181400325883e-07, Loss: 0.48279058933258057
2024-08-04T19:26:49.126033283Z 
 21%|██        | 1200/5712 [2:48:40<10:44:01,  8.56s/it]08/04/2024 12:26:49 - INFO - __main__ -   Step: 1200, LR: 4.388208614022714e-07, Loss: 0.48427385091781616
2024-08-04T19:26:57.406691907Z 
 21%|██        | 1201/5712 [2:48:48<10:37:29,  8.48s/it]08/04/2024 12:26:57 - INFO - __main__ -   Step: 1201, LR: 4.387235827719545e-07, Loss: 0.5463540554046631
2024-08-04T19:27:06.226894930Z 
 21%|██        | 1202/5712 [2:48:57<10:45:00,  8.58s/it]08/04/2024 12:27:06 - INFO - __main__ -   Step: 1202, LR: 4.3862630414163766e-07, Loss: 0.5378645658493042
2024-08-04T19:27:14.980222737Z 
 21%|██        | 1203/5712 [2:49:06<10:48:46,  8.63s/it]08/04/2024 12:27:14 - INFO - __main__ -   Step: 1203, LR: 4.3852902551132076e-07, Loss: 0.4883776903152466
2024-08-04T19:27:22.527692491Z 
 21%|██        | 1204/5712 [2:49:13<10:24:09,  8.31s/it]08/04/2024 12:27:22 - INFO - __main__ -   Step: 1204, LR: 4.3843174688100386e-07, Loss: 0.5269876718521118
2024-08-04T19:27:30.810668242Z 
 21%|██        | 1205/5712 [2:49:21<10:23:27,  8.30s/it]08/04/2024 12:27:30 - INFO - __main__ -   Step: 1205, LR: 4.3833446825068696e-07, Loss: 0.4666014313697815
2024-08-04T19:27:39.740412250Z 
 21%|██        | 1206/5712 [2:49:30<10:37:31,  8.49s/it]08/04/2024 12:27:39 - INFO - __main__ -   Step: 1206, LR: 4.3823718962037017e-07, Loss: 0.5878154635429382
2024-08-04T19:27:48.059312839Z 
 21%|██        | 1207/5712 [2:49:39<10:33:32,  8.44s/it]08/04/2024 12:27:48 - INFO - __main__ -   Step: 1207, LR: 4.3813991099005326e-07, Loss: 0.5163589715957642
2024-08-04T19:27:56.846521261Z 
 21%|██        | 1208/5712 [2:49:47<10:41:16,  8.54s/it]08/04/2024 12:27:56 - INFO - __main__ -   Step: 1208, LR: 4.3804263235973636e-07, Loss: 0.486659973859787
2024-08-04T19:28:04.886211786Z 
 21%|██        | 1209/5712 [2:49:56<10:29:48,  8.39s/it]08/04/2024 12:28:04 - INFO - __main__ -   Step: 1209, LR: 4.3794535372941946e-07, Loss: 0.4823366403579712
2024-08-04T19:28:13.442955078Z 
 21%|██        | 1210/5712 [2:50:04<10:33:22,  8.44s/it]08/04/2024 12:28:13 - INFO - __main__ -   Step: 1210, LR: 4.378480750991026e-07, Loss: 0.38402247428894043
2024-08-04T19:28:21.987189700Z 
 21%|██        | 1211/5712 [2:50:13<10:35:33,  8.47s/it]08/04/2024 12:28:21 - INFO - __main__ -   Step: 1211, LR: 4.377507964687857e-07, Loss: 0.5069898366928101
2024-08-04T19:28:30.166107079Z 
 21%|██        | 1212/5712 [2:50:21<10:28:48,  8.38s/it]08/04/2024 12:28:30 - INFO - __main__ -   Step: 1212, LR: 4.376535178384688e-07, Loss: 0.5600451827049255
2024-08-04T19:28:38.303215289Z 
 21%|██        | 1213/5712 [2:50:29<10:23:07,  8.31s/it]08/04/2024 12:28:38 - INFO - __main__ -   Step: 1213, LR: 4.375562392081519e-07, Loss: 0.425642728805542
2024-08-04T19:28:46.857834174Z 
 21%|██▏       | 1214/5712 [2:50:38<10:28:28,  8.38s/it]08/04/2024 12:28:46 - INFO - __main__ -   Step: 1214, LR: 4.3745896057783506e-07, Loss: 0.6216930150985718
2024-08-04T19:28:55.407822210Z 
 21%|██▏       | 1215/5712 [2:50:46<10:32:04,  8.43s/it]08/04/2024 12:28:55 - INFO - __main__ -   Step: 1215, LR: 4.3736168194751816e-07, Loss: 0.3764880895614624
2024-08-04T19:29:03.860348102Z 
 21%|██▏       | 1216/5712 [2:50:55<10:32:22,  8.44s/it]08/04/2024 12:29:03 - INFO - __main__ -   Step: 1216, LR: 4.3726440331720126e-07, Loss: 0.43812403082847595
2024-08-04T19:29:12.834501094Z 
 21%|██▏       | 1217/5712 [2:51:03<10:44:15,  8.60s/it]08/04/2024 12:29:12 - INFO - __main__ -   Step: 1217, LR: 4.3716712468688436e-07, Loss: 0.5504474639892578
2024-08-04T19:29:20.739685784Z 
 21%|██▏       | 1218/5712 [2:51:11<10:28:30,  8.39s/it]08/04/2024 12:29:20 - INFO - __main__ -   Step: 1218, LR: 4.370698460565675e-07, Loss: 0.4850391745567322
2024-08-04T19:29:29.478311259Z 
 21%|██▏       | 1219/5712 [2:51:20<10:36:10,  8.50s/it]08/04/2024 12:29:29 - INFO - __main__ -   Step: 1219, LR: 4.369725674262506e-07, Loss: 0.5662564039230347
2024-08-04T19:29:37.703658066Z 
 21%|██▏       | 1220/5712 [2:51:28<10:29:57,  8.41s/it]08/04/2024 12:29:37 - INFO - __main__ -   Step: 1220, LR: 4.368752887959337e-07, Loss: 0.41917040944099426
2024-08-04T19:29:45.222667858Z 
 21%|██▏       | 1221/5712 [2:51:36<10:09:43,  8.15s/it]08/04/2024 12:29:45 - INFO - __main__ -   Step: 1221, LR: 4.367780101656168e-07, Loss: 0.5205846428871155
2024-08-04T19:29:53.399577312Z 
 21%|██▏       | 1222/5712 [2:51:44<10:10:16,  8.16s/it]08/04/2024 12:29:53 - INFO - __main__ -   Step: 1222, LR: 4.3668073153529996e-07, Loss: 0.580093502998352
2024-08-04T19:30:02.077224375Z 
 21%|██▏       | 1223/5712 [2:51:53<10:21:52,  8.31s/it]08/04/2024 12:30:02 - INFO - __main__ -   Step: 1223, LR: 4.3658345290498306e-07, Loss: 0.4208398461341858
2024-08-04T19:30:11.055792338Z 
 21%|██▏       | 1224/5712 [2:52:02<10:36:41,  8.51s/it]08/04/2024 12:30:11 - INFO - __main__ -   Step: 1224, LR: 4.364861742746662e-07, Loss: 0.4325268864631653
2024-08-04T19:30:19.525281491Z 
 21%|██▏       | 1225/5712 [2:52:10<10:35:36,  8.50s/it]08/04/2024 12:30:19 - INFO - __main__ -   Step: 1225, LR: 4.363888956443493e-07, Loss: 0.39758896827697754
2024-08-04T19:30:27.705495622Z 
 21%|██▏       | 1226/5712 [2:52:18<10:28:18,  8.40s/it]08/04/2024 12:30:27 - INFO - __main__ -   Step: 1226, LR: 4.3629161701403246e-07, Loss: 0.486270010471344
2024-08-04T19:30:36.677218279Z 
 21%|██▏       | 1227/5712 [2:52:27<10:40:54,  8.57s/it]08/04/2024 12:30:36 - INFO - __main__ -   Step: 1227, LR: 4.3619433838371556e-07, Loss: 0.5270284414291382
2024-08-04T19:30:44.942606005Z 
 21%|██▏       | 1228/5712 [2:52:36<10:33:50,  8.48s/it]08/04/2024 12:30:44 - INFO - __main__ -   Step: 1228, LR: 4.3609705975339866e-07, Loss: 0.43462979793548584
2024-08-04T19:30:53.004441113Z 
 22%|██▏       | 1229/5712 [2:52:44<10:24:17,  8.36s/it]08/04/2024 12:30:53 - INFO - __main__ -   Step: 1229, LR: 4.3599978112308176e-07, Loss: 0.5123759508132935
2024-08-04T19:31:01.502239074Z 
 22%|██▏       | 1230/5712 [2:52:52<10:27:21,  8.40s/it]08/04/2024 12:31:01 - INFO - __main__ -   Step: 1230, LR: 4.359025024927649e-07, Loss: 0.6463040709495544
2024-08-04T19:31:10.184779440Z 
 22%|██▏       | 1231/5712 [2:53:01<10:33:34,  8.48s/it]08/04/2024 12:31:10 - INFO - __main__ -   Step: 1231, LR: 4.35805223862448e-07, Loss: 0.3505772054195404
2024-08-04T19:31:18.350631902Z 
 22%|██▏       | 1232/5712 [2:53:09<10:26:19,  8.39s/it]08/04/2024 12:31:18 - INFO - __main__ -   Step: 1232, LR: 4.357079452321311e-07, Loss: 0.7779916524887085
2024-08-04T19:31:27.082227927Z 
 22%|██▏       | 1233/5712 [2:53:18<10:33:52,  8.49s/it]08/04/2024 12:31:27 - INFO - __main__ -   Step: 1233, LR: 4.356106666018142e-07, Loss: 0.5413523316383362
2024-08-04T19:31:35.797400284Z 
 22%|██▏       | 1234/5712 [2:53:26<10:38:44,  8.56s/it]08/04/2024 12:31:35 - INFO - __main__ -   Step: 1234, LR: 4.3551338797149736e-07, Loss: 0.6076477766036987
2024-08-04T19:31:44.123214880Z 
 22%|██▏       | 1235/5712 [2:53:35<10:33:23,  8.49s/it]08/04/2024 12:31:44 - INFO - __main__ -   Step: 1235, LR: 4.3541610934118046e-07, Loss: 0.5748226642608643
2024-08-04T19:31:52.465478654Z 
 22%|██▏       | 1236/5712 [2:53:43<10:29:58,  8.44s/it]08/04/2024 12:31:52 - INFO - __main__ -   Step: 1236, LR: 4.3531883071086356e-07, Loss: 0.35866183042526245
2024-08-04T19:32:00.667993723Z 
 22%|██▏       | 1237/5712 [2:53:51<10:24:24,  8.37s/it]08/04/2024 12:32:00 - INFO - __main__ -   Step: 1237, LR: 4.3522155208054666e-07, Loss: 0.4457637667655945
2024-08-04T19:32:08.348974934Z 
 22%|██▏       | 1238/5712 [2:53:59<10:08:49,  8.16s/it]08/04/2024 12:32:08 - INFO - __main__ -   Step: 1238, LR: 4.3512427345022976e-07, Loss: 0.5532411336898804
2024-08-04T19:32:17.677592043Z 
 22%|██▏       | 1239/5712 [2:54:08<10:34:42,  8.51s/it]08/04/2024 12:32:17 - INFO - __main__ -   Step: 1239, LR: 4.350269948199129e-07, Loss: 0.37670934200286865
2024-08-04T19:32:26.343583203Z 
 22%|██▏       | 1240/5712 [2:54:17<10:37:58,  8.56s/it]08/04/2024 12:32:26 - INFO - __main__ -   Step: 1240, LR: 4.34929716189596e-07, Loss: 0.43350541591644287
2024-08-04T19:32:35.056403873Z 
 22%|██▏       | 1241/5712 [2:54:26<10:41:15,  8.61s/it]08/04/2024 12:32:35 - INFO - __main__ -   Step: 1241, LR: 4.348324375592791e-07, Loss: 0.43566110730171204
2024-08-04T19:32:43.801816744Z 
 22%|██▏       | 1242/5712 [2:54:34<10:44:14,  8.65s/it]08/04/2024 12:32:43 - INFO - __main__ -   Step: 1242, LR: 4.3473515892896226e-07, Loss: 0.5872617959976196
2024-08-04T19:32:52.251865262Z 
 22%|██▏       | 1243/5712 [2:54:43<10:39:41,  8.59s/it]08/04/2024 12:32:52 - INFO - __main__ -   Step: 1243, LR: 4.346378802986454e-07, Loss: 0.5304259061813354
2024-08-04T19:33:00.874226068Z 
 22%|██▏       | 1244/5712 [2:54:52<10:40:17,  8.60s/it]08/04/2024 12:33:00 - INFO - __main__ -   Step: 1244, LR: 4.345406016683285e-07, Loss: 0.5036659836769104
2024-08-04T19:33:09.138650548Z 
 22%|██▏       | 1245/5712 [2:55:00<10:32:41,  8.50s/it]08/04/2024 12:33:09 - INFO - __main__ -   Step: 1245, LR: 4.344433230380116e-07, Loss: 0.49150753021240234
2024-08-04T19:33:17.376548155Z 
 22%|██▏       | 1246/5712 [2:55:08<10:26:44,  8.42s/it]08/04/2024 12:33:17 - INFO - __main__ -   Step: 1246, LR: 4.343460444076947e-07, Loss: 0.6764144897460938
2024-08-04T19:33:25.755940317Z 
 22%|██▏       | 1247/5712 [2:55:16<10:25:41,  8.41s/it]08/04/2024 12:33:25 - INFO - __main__ -   Step: 1247, LR: 4.3424876577737786e-07, Loss: 0.5351294279098511
2024-08-04T19:33:34.616823065Z 
 22%|██▏       | 1248/5712 [2:55:25<10:35:39,  8.54s/it]08/04/2024 12:33:34 - INFO - __main__ -   Step: 1248, LR: 4.3415148714706096e-07, Loss: 0.5648245811462402
2024-08-04T19:33:43.461630992Z 
 22%|██▏       | 1249/5712 [2:55:34<10:42:13,  8.63s/it]08/04/2024 12:33:43 - INFO - __main__ -   Step: 1249, LR: 4.3405420851674406e-07, Loss: 0.5057581663131714
2024-08-04T19:33:52.097515663Z 
 22%|██▏       | 1250/5712 [2:55:43<10:42:07,  8.63s/it]08/04/2024 12:33:52 - INFO - __main__ -   Step: 1250, LR: 4.3395692988642716e-07, Loss: 0.4539191722869873
2024-08-04T19:34:01.144996335Z 
 22%|██▏       | 1251/5712 [2:55:52<10:51:11,  8.76s/it]08/04/2024 12:34:01 - INFO - __main__ -   Step: 1251, LR: 4.338596512561103e-07, Loss: 0.49884945154190063
2024-08-04T19:34:09.367281734Z 
 22%|██▏       | 1252/5712 [2:56:00<10:39:05,  8.60s/it]08/04/2024 12:34:09 - INFO - __main__ -   Step: 1252, LR: 4.337623726257934e-07, Loss: 0.4233141541481018
2024-08-04T19:34:17.655425194Z 
 22%|██▏       | 1253/5712 [2:56:08<10:32:02,  8.50s/it]08/04/2024 12:34:17 - INFO - __main__ -   Step: 1253, LR: 4.336650939954765e-07, Loss: 0.48254749178886414
2024-08-04T19:34:25.813043118Z 
 22%|██▏       | 1254/5712 [2:56:16<10:24:08,  8.40s/it]08/04/2024 12:34:25 - INFO - __main__ -   Step: 1254, LR: 4.335678153651596e-07, Loss: 0.4987484812736511
2024-08-04T19:34:34.277071121Z 
 22%|██▏       | 1255/5712 [2:56:25<10:25:26,  8.42s/it]08/04/2024 12:34:34 - INFO - __main__ -   Step: 1255, LR: 4.3347053673484276e-07, Loss: 0.4962860345840454
2024-08-04T19:34:42.561514265Z 
 22%|██▏       | 1256/5712 [2:56:33<10:22:17,  8.38s/it]08/04/2024 12:34:42 - INFO - __main__ -   Step: 1256, LR: 4.3337325810452586e-07, Loss: 0.34945106506347656
2024-08-04T19:34:50.754349138Z 
 22%|██▏       | 1257/5712 [2:56:41<10:18:00,  8.32s/it]08/04/2024 12:34:50 - INFO - __main__ -   Step: 1257, LR: 4.3327597947420896e-07, Loss: 0.45383477210998535
2024-08-04T19:34:59.240193802Z 
 22%|██▏       | 1258/5712 [2:56:50<10:21:28,  8.37s/it]08/04/2024 12:34:59 - INFO - __main__ -   Step: 1258, LR: 4.3317870084389206e-07, Loss: 0.4273945689201355
2024-08-04T19:35:08.206007725Z 
 22%|██▏       | 1259/5712 [2:56:59<10:34:33,  8.55s/it]08/04/2024 12:35:08 - INFO - __main__ -   Step: 1259, LR: 4.330814222135752e-07, Loss: 0.35632872581481934
2024-08-04T19:35:16.700816984Z 
 22%|██▏       | 1260/5712 [2:57:07<10:33:11,  8.53s/it]08/04/2024 12:35:16 - INFO - __main__ -   Step: 1260, LR: 4.3298414358325836e-07, Loss: 0.6513011455535889
2024-08-04T19:35:25.282796402Z 
 22%|██▏       | 1261/5712 [2:57:16<10:34:07,  8.55s/it]08/04/2024 12:35:25 - INFO - __main__ -   Step: 1261, LR: 4.3288686495294146e-07, Loss: 0.5709840655326843
2024-08-04T19:35:33.282246863Z 
 22%|██▏       | 1262/5712 [2:57:24<10:21:46,  8.38s/it]08/04/2024 12:35:33 - INFO - __main__ -   Step: 1262, LR: 4.3278958632262456e-07, Loss: 0.5157867074012756
2024-08-04T19:35:41.678366000Z 
 22%|██▏       | 1263/5712 [2:57:32<10:21:54,  8.39s/it]08/04/2024 12:35:41 - INFO - __main__ -   Step: 1263, LR: 4.326923076923077e-07, Loss: 0.4334721267223358
2024-08-04T19:35:50.393590809Z 
 22%|██▏       | 1264/5712 [2:57:41<10:29:03,  8.49s/it]08/04/2024 12:35:50 - INFO - __main__ -   Step: 1264, LR: 4.325950290619908e-07, Loss: 0.3703903257846832
2024-08-04T19:35:58.871048493Z 
 22%|██▏       | 1265/5712 [2:57:50<10:28:44,  8.48s/it]08/04/2024 12:35:58 - INFO - __main__ -   Step: 1265, LR: 4.324977504316739e-07, Loss: 0.47269096970558167
2024-08-04T19:36:07.504726372Z 
 22%|██▏       | 1266/5712 [2:57:58<10:31:56,  8.53s/it]08/04/2024 12:36:07 - INFO - __main__ -   Step: 1266, LR: 4.32400471801357e-07, Loss: 0.37957635521888733
2024-08-04T19:36:16.286487316Z 
 22%|██▏       | 1267/5712 [2:58:07<10:37:26,  8.60s/it]08/04/2024 12:36:16 - INFO - __main__ -   Step: 1267, LR: 4.3230319317104016e-07, Loss: 0.5247370004653931
2024-08-04T19:36:24.724083103Z 
 22%|██▏       | 1268/5712 [2:58:15<10:33:35,  8.55s/it]08/04/2024 12:36:24 - INFO - __main__ -   Step: 1268, LR: 4.3220591454072326e-07, Loss: 0.527716338634491
2024-08-04T19:36:32.955379043Z 
 22%|██▏       | 1269/5712 [2:58:24<10:26:16,  8.46s/it]08/04/2024 12:36:32 - INFO - __main__ -   Step: 1269, LR: 4.3210863591040636e-07, Loss: 0.457508385181427
2024-08-04T19:36:41.311459344Z 
 22%|██▏       | 1270/5712 [2:58:32<10:23:52,  8.43s/it]08/04/2024 12:36:41 - INFO - __main__ -   Step: 1270, LR: 4.3201135728008946e-07, Loss: 0.36064714193344116
2024-08-04T19:36:49.570793549Z 
 22%|██▏       | 1271/5712 [2:58:40<10:20:01,  8.38s/it]08/04/2024 12:36:49 - INFO - __main__ -   Step: 1271, LR: 4.319140786497726e-07, Loss: 0.4522439241409302
2024-08-04T19:36:58.488186685Z 
 22%|██▏       | 1272/5712 [2:58:49<10:31:52,  8.54s/it]08/04/2024 12:36:58 - INFO - __main__ -   Step: 1272, LR: 4.318168000194557e-07, Loss: 0.5318208932876587
2024-08-04T19:37:06.744500597Z 
 22%|██▏       | 1273/5712 [2:58:57<10:25:27,  8.45s/it]08/04/2024 12:37:06 - INFO - __main__ -   Step: 1273, LR: 4.317195213891388e-07, Loss: 0.5021662712097168
2024-08-04T19:37:15.268879301Z 
 22%|██▏       | 1274/5712 [2:59:06<10:26:52,  8.48s/it]08/04/2024 12:37:15 - INFO - __main__ -   Step: 1274, LR: 4.316222427588219e-07, Loss: 0.4270781874656677
2024-08-04T19:37:23.777790828Z 
 22%|██▏       | 1275/5712 [2:59:14<10:27:29,  8.49s/it]08/04/2024 12:37:23 - INFO - __main__ -   Step: 1275, LR: 4.31524964128505e-07, Loss: 0.5077680349349976
2024-08-04T19:37:32.187359369Z 
 22%|██▏       | 1276/5712 [2:59:23<10:25:40,  8.46s/it]08/04/2024 12:37:32 - INFO - __main__ -   Step: 1276, LR: 4.3142768549818816e-07, Loss: 0.5124433040618896
2024-08-04T19:37:40.168032135Z 
 22%|██▏       | 1277/5712 [2:59:31<10:14:50,  8.32s/it]08/04/2024 12:37:40 - INFO - __main__ -   Step: 1277, LR: 4.3133040686787126e-07, Loss: 0.5254279971122742
2024-08-04T19:37:48.698430373Z 
 22%|██▏       | 1278/5712 [2:59:39<10:19:24,  8.38s/it]08/04/2024 12:37:48 - INFO - __main__ -   Step: 1278, LR: 4.312331282375544e-07, Loss: 0.42479264736175537
2024-08-04T19:37:56.655870957Z 
 22%|██▏       | 1279/5712 [2:59:47<10:09:51,  8.25s/it]08/04/2024 12:37:56 - INFO - __main__ -   Step: 1279, LR: 4.311358496072375e-07, Loss: 0.5718003511428833
2024-08-04T19:38:05.160639458Z 
 22%|██▏       | 1280/5712 [2:59:56<10:15:16,  8.33s/it]08/04/2024 12:38:05 - INFO - __main__ -   Step: 1280, LR: 4.3103857097692066e-07, Loss: 0.6504590511322021
2024-08-04T19:38:13.540201887Z 
 22%|██▏       | 1281/5712 [3:00:04<10:16:14,  8.34s/it]08/04/2024 12:38:13 - INFO - __main__ -   Step: 1281, LR: 4.3094129234660376e-07, Loss: 0.4854855537414551
2024-08-04T19:38:22.176216341Z 
 22%|██▏       | 1282/5712 [3:00:13<10:22:33,  8.43s/it]08/04/2024 12:38:22 - INFO - __main__ -   Step: 1282, LR: 4.3084401371628686e-07, Loss: 0.4087821841239929
2024-08-04T19:38:30.982532688Z 
 22%|██▏       | 1283/5712 [3:00:22<10:30:42,  8.54s/it]08/04/2024 12:38:30 - INFO - __main__ -   Step: 1283, LR: 4.3074673508596996e-07, Loss: 0.408025324344635
2024-08-04T19:38:39.506799435Z 
 22%|██▏       | 1284/5712 [3:00:30<10:30:07,  8.54s/it]08/04/2024 12:38:39 - INFO - __main__ -   Step: 1284, LR: 4.306494564556531e-07, Loss: 0.6077375411987305
2024-08-04T19:38:47.712853774Z 
 22%|██▏       | 1285/5712 [3:00:38<10:22:37,  8.44s/it]08/04/2024 12:38:47 - INFO - __main__ -   Step: 1285, LR: 4.305521778253362e-07, Loss: 0.37404680252075195
2024-08-04T19:38:55.689399558Z 
 23%|██▎       | 1286/5712 [3:00:46<10:12:16,  8.30s/it]08/04/2024 12:38:55 - INFO - __main__ -   Step: 1286, LR: 4.304548991950193e-07, Loss: 0.4028453230857849
2024-08-04T19:39:04.139911844Z 
 23%|██▎       | 1287/5712 [3:00:55<10:15:27,  8.35s/it]08/04/2024 12:39:04 - INFO - __main__ -   Step: 1287, LR: 4.303576205647024e-07, Loss: 0.5165712833404541
2024-08-04T19:39:13.039875652Z 
 23%|██▎       | 1288/5712 [3:01:04<10:27:35,  8.51s/it]08/04/2024 12:39:13 - INFO - __main__ -   Step: 1288, LR: 4.3026034193438556e-07, Loss: 0.35945847630500793
2024-08-04T19:39:21.697443027Z 
 23%|██▎       | 1289/5712 [3:01:12<10:30:40,  8.56s/it]08/04/2024 12:39:21 - INFO - __main__ -   Step: 1289, LR: 4.3016306330406866e-07, Loss: 0.40349698066711426
2024-08-04T19:39:29.864999132Z 
 23%|██▎       | 1290/5712 [3:01:21<10:21:57,  8.44s/it]08/04/2024 12:39:29 - INFO - __main__ -   Step: 1290, LR: 4.3006578467375176e-07, Loss: 0.42325007915496826
2024-08-04T19:39:38.221501037Z 
 23%|██▎       | 1291/5712 [3:01:29<10:19:59,  8.41s/it]08/04/2024 12:39:38 - INFO - __main__ -   Step: 1291, LR: 4.2996850604343486e-07, Loss: 0.560645341873169
2024-08-04T19:39:47.090740998Z 
 23%|██▎       | 1292/5712 [3:01:38<10:29:54,  8.55s/it]08/04/2024 12:39:47 - INFO - __main__ -   Step: 1292, LR: 4.29871227413118e-07, Loss: 0.42332378029823303
2024-08-04T19:39:55.792468014Z 
 23%|██▎       | 1293/5712 [3:01:46<10:33:03,  8.60s/it]08/04/2024 12:39:55 - INFO - __main__ -   Step: 1293, LR: 4.297739487828011e-07, Loss: 0.45473378896713257
2024-08-04T19:40:03.778373429Z 
 23%|██▎       | 1294/5712 [3:01:54<10:19:29,  8.41s/it]08/04/2024 12:40:03 - INFO - __main__ -   Step: 1294, LR: 4.296766701524842e-07, Loss: 0.3529524803161621
2024-08-04T19:40:11.856020963Z 
 23%|██▎       | 1295/5712 [3:02:03<10:11:56,  8.31s/it]08/04/2024 12:40:11 - INFO - __main__ -   Step: 1295, LR: 4.295793915221673e-07, Loss: 0.4099034070968628
2024-08-04T19:40:21.173634163Z 
 23%|██▎       | 1296/5712 [3:02:12<10:33:59,  8.61s/it]08/04/2024 12:40:21 - INFO - __main__ -   Step: 1296, LR: 4.294821128918505e-07, Loss: 0.5506497621536255
2024-08-04T19:40:30.278045190Z 
 23%|██▎       | 1297/5712 [3:02:21<10:44:40,  8.76s/it]08/04/2024 12:40:30 - INFO - __main__ -   Step: 1297, LR: 4.293848342615336e-07, Loss: 0.23426389694213867
2024-08-04T19:40:39.387214171Z 
 23%|██▎       | 1298/5712 [3:02:30<10:52:12,  8.87s/it]08/04/2024 12:40:39 - INFO - __main__ -   Step: 1298, LR: 4.292875556312167e-07, Loss: 0.4148409068584442
2024-08-04T19:40:47.686561640Z 
 23%|██▎       | 1299/5712 [3:02:38<10:39:34,  8.70s/it]08/04/2024 12:40:47 - INFO - __main__ -   Step: 1299, LR: 4.291902770008998e-07, Loss: 0.47585010528564453
2024-08-04T19:40:56.297075414Z 
 23%|██▎       | 1300/5712 [3:02:47<10:37:32,  8.67s/it]08/04/2024 12:40:56 - INFO - __main__ -   Step: 1300, LR: 4.2909299837058296e-07, Loss: 0.4491281509399414
2024-08-04T19:41:05.033172741Z 
 23%|██▎       | 1301/5712 [3:02:56<10:38:51,  8.69s/it]08/04/2024 12:41:05 - INFO - __main__ -   Step: 1301, LR: 4.2899571974026606e-07, Loss: 0.5004178881645203
2024-08-04T19:41:13.206043664Z 
 23%|██▎       | 1302/5712 [3:03:04<10:27:18,  8.53s/it]08/04/2024 12:41:13 - INFO - __main__ -   Step: 1302, LR: 4.2889844110994916e-07, Loss: 0.5329164862632751
2024-08-04T19:41:21.345276726Z 
 23%|██▎       | 1303/5712 [3:03:12<10:18:26,  8.42s/it]08/04/2024 12:41:21 - INFO - __main__ -   Step: 1303, LR: 4.2880116247963226e-07, Loss: 0.5061220526695251
2024-08-04T19:41:30.456125952Z 
 23%|██▎       | 1304/5712 [3:03:21<10:33:36,  8.62s/it]08/04/2024 12:41:30 - INFO - __main__ -   Step: 1304, LR: 4.287038838493154e-07, Loss: 0.4888707995414734
2024-08-04T19:41:38.712206055Z 
 23%|██▎       | 1305/5712 [3:03:29<10:25:20,  8.51s/it]08/04/2024 12:41:38 - INFO - __main__ -   Step: 1305, LR: 4.286066052189985e-07, Loss: 0.47094500064849854
2024-08-04T19:41:47.416786606Z 
 23%|██▎       | 1306/5712 [3:03:38<10:29:24,  8.57s/it]08/04/2024 12:41:47 - INFO - __main__ -   Step: 1306, LR: 4.285093265886816e-07, Loss: 0.36911314725875854
2024-08-04T19:41:55.712219373Z 
 23%|██▎       | 1307/5712 [3:03:46<10:23:11,  8.49s/it]08/04/2024 12:41:55 - INFO - __main__ -   Step: 1307, LR: 4.284120479583647e-07, Loss: 0.4175068140029907
2024-08-04T19:42:03.690467227Z 
 23%|██▎       | 1308/5712 [3:03:54<10:11:49,  8.34s/it]08/04/2024 12:42:03 - INFO - __main__ -   Step: 1308, LR: 4.2831476932804786e-07, Loss: 0.5567611455917358
2024-08-04T19:42:12.290161925Z 
 23%|██▎       | 1309/5712 [3:04:03<10:17:29,  8.41s/it]08/04/2024 12:42:12 - INFO - __main__ -   Step: 1309, LR: 4.2821749069773096e-07, Loss: 0.4288061559200287
2024-08-04T19:42:20.616906946Z 
 23%|██▎       | 1310/5712 [3:04:11<10:15:25,  8.39s/it]08/04/2024 12:42:20 - INFO - __main__ -   Step: 1310, LR: 4.2812021206741405e-07, Loss: 0.46934452652931213
2024-08-04T19:42:28.574337124Z 
 23%|██▎       | 1311/5712 [3:04:19<10:05:48,  8.26s/it]08/04/2024 12:42:28 - INFO - __main__ -   Step: 1311, LR: 4.2802293343709715e-07, Loss: 0.38566529750823975
2024-08-04T19:42:37.347174836Z 
 23%|██▎       | 1312/5712 [3:04:28<10:16:58,  8.41s/it]08/04/2024 12:42:37 - INFO - __main__ -   Step: 1312, LR: 4.2792565480678025e-07, Loss: 0.5874204039573669
2024-08-04T19:42:45.837181866Z 
 23%|██▎       | 1313/5712 [3:04:36<10:18:30,  8.44s/it]08/04/2024 12:42:45 - INFO - __main__ -   Step: 1313, LR: 4.278283761764634e-07, Loss: 0.4413014352321625
2024-08-04T19:42:54.665418628Z 
 23%|██▎       | 1314/5712 [3:04:45<10:26:59,  8.55s/it]08/04/2024 12:42:54 - INFO - __main__ -   Step: 1314, LR: 4.2773109754614656e-07, Loss: 0.48335036635398865
2024-08-04T19:43:03.167372011Z 
 23%|██▎       | 1315/5712 [3:04:54<10:25:42,  8.54s/it]08/04/2024 12:43:03 - INFO - __main__ -   Step: 1315, LR: 4.2763381891582966e-07, Loss: 0.48435139656066895
2024-08-04T19:43:11.977611727Z 
 23%|██▎       | 1316/5712 [3:05:03<10:31:33,  8.62s/it]08/04/2024 12:43:11 - INFO - __main__ -   Step: 1316, LR: 4.2753654028551275e-07, Loss: 0.3693159818649292
2024-08-04T19:43:20.737047734Z 
 23%|██▎       | 1317/5712 [3:05:11<10:34:27,  8.66s/it]08/04/2024 12:43:20 - INFO - __main__ -   Step: 1317, LR: 4.274392616551959e-07, Loss: 0.4174986481666565
2024-08-04T19:43:29.154799752Z 
 23%|██▎       | 1318/5712 [3:05:20<10:28:58,  8.59s/it]08/04/2024 12:43:29 - INFO - __main__ -   Step: 1318, LR: 4.27341983024879e-07, Loss: 0.4794144630432129
2024-08-04T19:43:37.070143445Z 
 23%|██▎       | 1319/5712 [3:05:28<10:14:02,  8.39s/it]08/04/2024 12:43:37 - INFO - __main__ -   Step: 1319, LR: 4.272447043945621e-07, Loss: 0.6135917901992798
2024-08-04T19:43:45.216789213Z 
 23%|██▎       | 1320/5712 [3:05:36<10:08:37,  8.31s/it]08/04/2024 12:43:45 - INFO - __main__ -   Step: 1320, LR: 4.271474257642452e-07, Loss: 0.45169496536254883
2024-08-04T19:43:54.629077769Z 
 23%|██▎       | 1321/5712 [3:05:45<10:32:35,  8.64s/it]08/04/2024 12:43:54 - INFO - __main__ -   Step: 1321, LR: 4.2705014713392836e-07, Loss: 0.5698064565658569
2024-08-04T19:44:03.154054157Z 
 23%|██▎       | 1322/5712 [3:05:54<10:29:50,  8.61s/it]08/04/2024 12:44:03 - INFO - __main__ -   Step: 1322, LR: 4.2695286850361146e-07, Loss: 0.6921486854553223
2024-08-04T19:44:11.359208793Z 
 23%|██▎       | 1323/5712 [3:06:02<10:20:50,  8.49s/it]08/04/2024 12:44:11 - INFO - __main__ -   Step: 1323, LR: 4.2685558987329455e-07, Loss: 0.42100024223327637
2024-08-04T19:44:19.545852209Z 
 23%|██▎       | 1324/5712 [3:06:10<10:14:06,  8.40s/it]08/04/2024 12:44:19 - INFO - __main__ -   Step: 1324, LR: 4.2675831124297765e-07, Loss: 0.5015518069267273
2024-08-04T19:44:28.133949793Z 
 23%|██▎       | 1325/5712 [3:06:19<10:18:09,  8.45s/it]08/04/2024 12:44:28 - INFO - __main__ -   Step: 1325, LR: 4.266610326126608e-07, Loss: 0.5881726145744324
2024-08-04T19:44:36.546424621Z 
 23%|██▎       | 1326/5712 [3:06:27<10:17:05,  8.44s/it]08/04/2024 12:44:36 - INFO - __main__ -   Step: 1326, LR: 4.265637539823439e-07, Loss: 0.43619704246520996
2024-08-04T19:44:44.942274215Z 
 23%|██▎       | 1327/5712 [3:06:36<10:15:57,  8.43s/it]08/04/2024 12:44:44 - INFO - __main__ -   Step: 1327, LR: 4.26466475352027e-07, Loss: 0.41166356205940247
2024-08-04T19:44:52.516214080Z 
 23%|██▎       | 1328/5712 [3:06:43<9:57:05,  8.17s/it] 08/04/2024 12:44:52 - INFO - __main__ -   Step: 1328, LR: 4.263691967217101e-07, Loss: 0.4065856337547302
2024-08-04T19:45:00.913827949Z 
 23%|██▎       | 1329/5712 [3:06:52<10:01:53,  8.24s/it]08/04/2024 12:45:00 - INFO - __main__ -   Step: 1329, LR: 4.2627191809139325e-07, Loss: 0.49607184529304504
2024-08-04T19:45:09.231767332Z 
 23%|██▎       | 1330/5712 [3:07:00<10:03:28,  8.26s/it]08/04/2024 12:45:09 - INFO - __main__ -   Step: 1330, LR: 4.2617463946107635e-07, Loss: 0.46338486671447754
2024-08-04T19:45:17.792146107Z 
 23%|██▎       | 1331/5712 [3:07:08<10:09:51,  8.35s/it]08/04/2024 12:45:17 - INFO - __main__ -   Step: 1331, LR: 4.2607736083075945e-07, Loss: 0.4262819290161133
2024-08-04T19:45:26.162626555Z 
 23%|██▎       | 1332/5712 [3:07:17<10:10:06,  8.36s/it]08/04/2024 12:45:26 - INFO - __main__ -   Step: 1332, LR: 4.259800822004426e-07, Loss: 0.6015307307243347
2024-08-04T19:45:34.723841507Z 
 23%|██▎       | 1333/5712 [3:07:25<10:14:25,  8.42s/it]08/04/2024 12:45:34 - INFO - __main__ -   Step: 1333, LR: 4.2588280357012576e-07, Loss: 0.3653448224067688
2024-08-04T19:45:42.985439885Z 
 23%|██▎       | 1334/5712 [3:07:34<10:10:51,  8.37s/it]08/04/2024 12:45:42 - INFO - __main__ -   Step: 1334, LR: 4.2578552493980886e-07, Loss: 0.40260326862335205
2024-08-04T19:45:51.651455623Z 
 23%|██▎       | 1335/5712 [3:07:42<10:17:09,  8.46s/it]08/04/2024 12:45:51 - INFO - __main__ -   Step: 1335, LR: 4.2568824630949195e-07, Loss: 0.3782956600189209
2024-08-04T19:45:59.142343679Z 
 23%|██▎       | 1336/5712 [3:07:50<9:55:48,  8.17s/it] 08/04/2024 12:45:59 - INFO - __main__ -   Step: 1336, LR: 4.2559096767917505e-07, Loss: 0.3721836805343628
2024-08-04T19:46:08.041022839Z 
 23%|██▎       | 1337/5712 [3:07:59<10:11:37,  8.39s/it]08/04/2024 12:46:08 - INFO - __main__ -   Step: 1337, LR: 4.254936890488582e-07, Loss: 0.3374864161014557
2024-08-04T19:46:16.885112450Z 
 23%|██▎       | 1338/5712 [3:08:08<10:21:27,  8.52s/it]08/04/2024 12:46:16 - INFO - __main__ -   Step: 1338, LR: 4.253964104185413e-07, Loss: 0.3957570791244507
2024-08-04T19:46:25.699433922Z 
 23%|██▎       | 1339/5712 [3:08:16<10:27:38,  8.61s/it]08/04/2024 12:46:25 - INFO - __main__ -   Step: 1339, LR: 4.252991317882244e-07, Loss: 0.5360139608383179
2024-08-04T19:46:33.886842507Z 
 23%|██▎       | 1340/5712 [3:08:25<10:18:13,  8.48s/it]08/04/2024 12:46:33 - INFO - __main__ -   Step: 1340, LR: 4.252018531579075e-07, Loss: 0.48839956521987915
2024-08-04T19:46:42.377309779Z 
 23%|██▎       | 1341/5712 [3:08:33<10:18:13,  8.49s/it]08/04/2024 12:46:42 - INFO - __main__ -   Step: 1341, LR: 4.2510457452759065e-07, Loss: 0.4817492961883545
2024-08-04T19:46:51.040647797Z 
 23%|██▎       | 1342/5712 [3:08:42<10:21:56,  8.54s/it]08/04/2024 12:46:51 - INFO - __main__ -   Step: 1342, LR: 4.2500729589727375e-07, Loss: 0.3750213384628296
2024-08-04T19:46:59.006578376Z 
 24%|██▎       | 1343/5712 [3:08:50<10:09:14,  8.37s/it]08/04/2024 12:46:59 - INFO - __main__ -   Step: 1343, LR: 4.2491001726695685e-07, Loss: 0.4224497675895691
2024-08-04T19:47:07.327674901Z 
 24%|██▎       | 1344/5712 [3:08:58<10:08:09,  8.35s/it]08/04/2024 12:47:07 - INFO - __main__ -   Step: 1344, LR: 4.2481273863663995e-07, Loss: 0.5511361360549927
2024-08-04T19:47:15.691474828Z 
 24%|██▎       | 1345/5712 [3:09:06<10:08:13,  8.36s/it]08/04/2024 12:47:15 - INFO - __main__ -   Step: 1345, LR: 4.247154600063231e-07, Loss: 0.5301439166069031
2024-08-04T19:47:24.786642525Z 
 24%|██▎       | 1346/5712 [3:09:15<10:24:12,  8.58s/it]08/04/2024 12:47:24 - INFO - __main__ -   Step: 1346, LR: 4.246181813760062e-07, Loss: 0.5946285724639893
2024-08-04T19:47:33.467842867Z 
 24%|██▎       | 1347/5712 [3:09:24<10:26:18,  8.61s/it]08/04/2024 12:47:33 - INFO - __main__ -   Step: 1347, LR: 4.245209027456893e-07, Loss: 0.26009348034858704
2024-08-04T19:47:41.797299306Z 
 24%|██▎       | 1348/5712 [3:09:32<10:20:04,  8.53s/it]08/04/2024 12:47:41 - INFO - __main__ -   Step: 1348, LR: 4.244236241153724e-07, Loss: 0.4410768151283264
2024-08-04T19:47:50.292055120Z 
 24%|██▎       | 1349/5712 [3:09:41<10:19:15,  8.52s/it]08/04/2024 12:47:50 - INFO - __main__ -   Step: 1349, LR: 4.243263454850555e-07, Loss: 0.4889821410179138
2024-08-04T19:47:58.970452438Z 
 24%|██▎       | 1350/5712 [3:09:50<10:22:39,  8.56s/it]08/04/2024 12:47:58 - INFO - __main__ -   Step: 1350, LR: 4.242290668547387e-07, Loss: 0.5222707390785217
2024-08-04T19:48:07.002592436Z 
 24%|██▎       | 1351/5712 [3:09:58<10:10:53,  8.40s/it]08/04/2024 12:48:07 - INFO - __main__ -   Step: 1351, LR: 4.241317882244218e-07, Loss: 0.4667397141456604
2024-08-04T19:48:15.318682983Z 
 24%|██▎       | 1352/5712 [3:10:06<10:08:49,  8.38s/it]08/04/2024 12:48:15 - INFO - __main__ -   Step: 1352, LR: 4.240345095941049e-07, Loss: 0.5267198085784912
2024-08-04T19:48:23.250277516Z 
 24%|██▎       | 1353/5712 [3:10:14<9:58:57,  8.24s/it] 08/04/2024 12:48:23 - INFO - __main__ -   Step: 1353, LR: 4.23937230963788e-07, Loss: 0.4402313828468323
2024-08-04T19:48:32.036671171Z 
 24%|██▎       | 1354/5712 [3:10:23<10:10:36,  8.41s/it]08/04/2024 12:48:32 - INFO - __main__ -   Step: 1354, LR: 4.2383995233347115e-07, Loss: 0.4584064781665802
2024-08-04T19:48:40.432669591Z 
 24%|██▎       | 1355/5712 [3:10:31<10:10:14,  8.40s/it]08/04/2024 12:48:40 - INFO - __main__ -   Step: 1355, LR: 4.2374267370315425e-07, Loss: 0.5174750089645386
2024-08-04T19:48:49.282882057Z 
 24%|██▎       | 1356/5712 [3:10:40<10:19:49,  8.54s/it]08/04/2024 12:48:49 - INFO - __main__ -   Step: 1356, LR: 4.2364539507283735e-07, Loss: 0.37817084789276123
2024-08-04T19:48:57.201843744Z 
 24%|██▍       | 1357/5712 [3:10:48<10:06:13,  8.35s/it]08/04/2024 12:48:57 - INFO - __main__ -   Step: 1357, LR: 4.2354811644252045e-07, Loss: 0.42566046118736267
2024-08-04T19:49:05.643444682Z 
 24%|██▍       | 1358/5712 [3:10:56<10:08:01,  8.38s/it]08/04/2024 12:49:05 - INFO - __main__ -   Step: 1358, LR: 4.234508378122036e-07, Loss: 0.5898356437683105
2024-08-04T19:49:13.979687123Z 
 24%|██▍       | 1359/5712 [3:11:05<10:06:57,  8.37s/it]08/04/2024 12:49:13 - INFO - __main__ -   Step: 1359, LR: 4.233535591818867e-07, Loss: 0.4057539403438568
2024-08-04T19:49:22.248143112Z 
 24%|██▍       | 1360/5712 [3:11:13<10:04:41,  8.34s/it]08/04/2024 12:49:22 - INFO - __main__ -   Step: 1360, LR: 4.232562805515698e-07, Loss: 0.5210781097412109
2024-08-04T19:49:30.145986924Z 
 24%|██▍       | 1361/5712 [3:11:21<9:55:00,  8.21s/it] 08/04/2024 12:49:30 - INFO - __main__ -   Step: 1361, LR: 4.231590019212529e-07, Loss: 0.3942303955554962
2024-08-04T19:49:38.601564605Z 
 24%|██▍       | 1362/5712 [3:11:29<10:00:18,  8.28s/it]08/04/2024 12:49:38 - INFO - __main__ -   Step: 1362, LR: 4.2306172329093605e-07, Loss: 0.3585587739944458
2024-08-04T19:49:46.986197488Z 
 24%|██▍       | 1363/5712 [3:11:38<10:02:27,  8.31s/it]08/04/2024 12:49:46 - INFO - __main__ -   Step: 1363, LR: 4.2296444466061915e-07, Loss: 0.5562061667442322
2024-08-04T19:49:55.218114736Z 
 24%|██▍       | 1364/5712 [3:11:46<10:00:34,  8.29s/it]08/04/2024 12:49:55 - INFO - __main__ -   Step: 1364, LR: 4.2286716603030225e-07, Loss: 0.7204241752624512
2024-08-04T19:50:03.598034367Z 
 24%|██▍       | 1365/5712 [3:11:54<10:02:27,  8.32s/it]08/04/2024 12:50:03 - INFO - __main__ -   Step: 1365, LR: 4.2276988739998535e-07, Loss: 0.3769396245479584
2024-08-04T19:50:11.696582862Z 
 24%|██▍       | 1366/5712 [3:12:02<9:57:35,  8.25s/it] 08/04/2024 12:50:11 - INFO - __main__ -   Step: 1366, LR: 4.226726087696685e-07, Loss: 0.5971437096595764
2024-08-04T19:50:20.549210182Z 
 24%|██▍       | 1367/5712 [3:12:11<10:10:32,  8.43s/it]08/04/2024 12:50:20 - INFO - __main__ -   Step: 1367, LR: 4.225753301393516e-07, Loss: 0.400752454996109
2024-08-04T19:50:28.862473152Z 
 24%|██▍       | 1368/5712 [3:12:20<10:07:51,  8.40s/it]08/04/2024 12:50:28 - INFO - __main__ -   Step: 1368, LR: 4.2247805150903475e-07, Loss: 0.4926277697086334
2024-08-04T19:50:37.493138076Z 
 24%|██▍       | 1369/5712 [3:12:28<10:12:49,  8.47s/it]08/04/2024 12:50:37 - INFO - __main__ -   Step: 1369, LR: 4.2238077287871785e-07, Loss: 0.33378395438194275
2024-08-04T19:50:46.074039121Z 
 24%|██▍       | 1370/5712 [3:12:37<10:15:09,  8.50s/it]08/04/2024 12:50:46 - INFO - __main__ -   Step: 1370, LR: 4.22283494248401e-07, Loss: 0.3716922402381897
2024-08-04T19:50:55.057960387Z 
 24%|██▍       | 1371/5712 [3:12:46<10:25:30,  8.65s/it]08/04/2024 12:50:55 - INFO - __main__ -   Step: 1371, LR: 4.221862156180841e-07, Loss: 0.5618255734443665
2024-08-04T19:51:03.659621470Z 
 24%|██▍       | 1372/5712 [3:12:54<10:24:24,  8.63s/it]08/04/2024 12:51:03 - INFO - __main__ -   Step: 1372, LR: 4.220889369877672e-07, Loss: 0.355972558259964
2024-08-04T19:51:12.433955173Z 
 24%|██▍       | 1373/5712 [3:13:03<10:27:20,  8.67s/it]08/04/2024 12:51:12 - INFO - __main__ -   Step: 1373, LR: 4.219916583574503e-07, Loss: 0.4635741710662842
2024-08-04T19:51:20.585235521Z 
 24%|██▍       | 1374/5712 [3:13:11<10:15:50,  8.52s/it]08/04/2024 12:51:20 - INFO - __main__ -   Step: 1374, LR: 4.2189437972713345e-07, Loss: 0.48831313848495483
2024-08-04T19:51:29.065189320Z 
 24%|██▍       | 1375/5712 [3:13:20<10:14:52,  8.51s/it]08/04/2024 12:51:29 - INFO - __main__ -   Step: 1375, LR: 4.2179710109681655e-07, Loss: 0.38867002725601196
2024-08-04T19:51:37.419803846Z 
 24%|██▍       | 1376/5712 [3:13:28<10:11:26,  8.46s/it]08/04/2024 12:51:37 - INFO - __main__ -   Step: 1376, LR: 4.2169982246649965e-07, Loss: 0.3332293629646301
2024-08-04T19:51:45.461687515Z 
 24%|██▍       | 1377/5712 [3:13:36<10:02:12,  8.34s/it]08/04/2024 12:51:45 - INFO - __main__ -   Step: 1377, LR: 4.2160254383618275e-07, Loss: 0.5711705088615417
2024-08-04T19:51:53.966559961Z 
 24%|██▍       | 1378/5712 [3:13:45<10:05:45,  8.39s/it]08/04/2024 12:51:53 - INFO - __main__ -   Step: 1378, LR: 4.215052652058659e-07, Loss: 0.37468796968460083
2024-08-04T19:52:03.077769236Z 
 24%|██▍       | 1379/5712 [3:13:54<10:21:19,  8.60s/it]08/04/2024 12:52:03 - INFO - __main__ -   Step: 1379, LR: 4.21407986575549e-07, Loss: 0.4815002679824829
2024-08-04T19:52:11.353977255Z 
 24%|██▍       | 1380/5712 [3:14:02<10:14:04,  8.51s/it]08/04/2024 12:52:11 - INFO - __main__ -   Step: 1380, LR: 4.213107079452321e-07, Loss: 0.5138961672782898
2024-08-04T19:52:19.594123398Z 
 24%|██▍       | 1381/5712 [3:14:10<10:08:12,  8.43s/it]08/04/2024 12:52:19 - INFO - __main__ -   Step: 1381, LR: 4.212134293149152e-07, Loss: 0.472388356924057
2024-08-04T19:52:28.231544272Z 
 24%|██▍       | 1382/5712 [3:14:19<10:12:38,  8.49s/it]08/04/2024 12:52:28 - INFO - __main__ -   Step: 1382, LR: 4.2111615068459835e-07, Loss: 0.40787309408187866
2024-08-04T19:52:36.847682219Z 
 24%|██▍       | 1383/5712 [3:14:27<10:15:15,  8.53s/it]08/04/2024 12:52:36 - INFO - __main__ -   Step: 1383, LR: 4.2101887205428145e-07, Loss: 0.44878607988357544
2024-08-04T19:52:44.997907412Z 
 24%|██▍       | 1384/5712 [3:14:36<10:06:56,  8.41s/it]08/04/2024 12:52:44 - INFO - __main__ -   Step: 1384, LR: 4.2092159342396455e-07, Loss: 0.44420045614242554
2024-08-04T19:52:53.244209052Z 
 24%|██▍       | 1385/5712 [3:14:44<10:03:10,  8.36s/it]08/04/2024 12:52:53 - INFO - __main__ -   Step: 1385, LR: 4.2082431479364765e-07, Loss: 0.47636282444000244
2024-08-04T19:53:02.176860015Z 
 24%|██▍       | 1386/5712 [3:14:53<10:15:19,  8.53s/it]08/04/2024 12:53:02 - INFO - __main__ -   Step: 1386, LR: 4.2072703616333085e-07, Loss: 0.501265287399292
2024-08-04T19:53:10.517168079Z 
 24%|██▍       | 1387/5712 [3:15:01<10:10:59,  8.48s/it]08/04/2024 12:53:10 - INFO - __main__ -   Step: 1387, LR: 4.2062975753301395e-07, Loss: 0.5583250522613525
2024-08-04T19:53:19.375428396Z 
 24%|██▍       | 1388/5712 [3:15:10<10:19:06,  8.59s/it]08/04/2024 12:53:19 - INFO - __main__ -   Step: 1388, LR: 4.2053247890269705e-07, Loss: 0.5349081754684448
2024-08-04T19:53:27.553617339Z 
 24%|██▍       | 1389/5712 [3:15:18<10:10:03,  8.47s/it]08/04/2024 12:53:27 - INFO - __main__ -   Step: 1389, LR: 4.2043520027238015e-07, Loss: 0.6739494800567627
2024-08-04T19:53:36.376431719Z 
 24%|██▍       | 1390/5712 [3:15:27<10:17:35,  8.57s/it]08/04/2024 12:53:36 - INFO - __main__ -   Step: 1390, LR: 4.203379216420633e-07, Loss: 0.4997996985912323
2024-08-04T19:53:44.877094450Z 
 24%|██▍       | 1391/5712 [3:15:36<10:15:52,  8.55s/it]08/04/2024 12:53:44 - INFO - __main__ -   Step: 1391, LR: 4.202406430117464e-07, Loss: 0.41339772939682007
2024-08-04T19:53:53.225882224Z 
 24%|██▍       | 1392/5712 [3:15:44<10:11:21,  8.49s/it]08/04/2024 12:53:53 - INFO - __main__ -   Step: 1392, LR: 4.201433643814295e-07, Loss: 0.5327155590057373
2024-08-04T19:54:01.440893401Z 
 24%|██▍       | 1393/5712 [3:15:52<10:05:14,  8.41s/it]08/04/2024 12:54:01 - INFO - __main__ -   Step: 1393, LR: 4.200460857511126e-07, Loss: 0.33411696553230286
2024-08-04T19:54:09.570582063Z 
 24%|██▍       | 1394/5712 [3:16:00<9:59:05,  8.32s/it] 08/04/2024 12:54:09 - INFO - __main__ -   Step: 1394, LR: 4.199488071207957e-07, Loss: 0.4044884741306305
2024-08-04T19:54:18.477486938Z 
 24%|██▍       | 1395/5712 [3:16:09<10:11:31,  8.50s/it]08/04/2024 12:54:18 - INFO - __main__ -   Step: 1395, LR: 4.1985152849047885e-07, Loss: 0.663477897644043
2024-08-04T19:54:27.087945115Z 
 24%|██▍       | 1396/5712 [3:16:18<10:13:46,  8.53s/it]08/04/2024 12:54:27 - INFO - __main__ -   Step: 1396, LR: 4.1975424986016195e-07, Loss: 0.36805960536003113
2024-08-04T19:54:35.655118731Z 
 24%|██▍       | 1397/5712 [3:16:26<10:14:23,  8.54s/it]08/04/2024 12:54:35 - INFO - __main__ -   Step: 1397, LR: 4.1965697122984505e-07, Loss: 0.3620568513870239
2024-08-04T19:54:44.556867118Z 
 24%|██▍       | 1398/5712 [3:16:35<10:21:58,  8.65s/it]08/04/2024 12:54:44 - INFO - __main__ -   Step: 1398, LR: 4.1955969259952815e-07, Loss: 0.46108728647232056
2024-08-04T19:54:52.730548374Z 
 24%|██▍       | 1399/5712 [3:16:43<10:11:33,  8.51s/it]08/04/2024 12:54:52 - INFO - __main__ -   Step: 1399, LR: 4.194624139692113e-07, Loss: 0.49273917078971863
2024-08-04T19:55:01.207650053Z 
 25%|██▍       | 1400/5712 [3:16:52<10:10:45,  8.50s/it]08/04/2024 12:55:01 - INFO - __main__ -   Step: 1400, LR: 4.193651353388944e-07, Loss: 0.4467790722846985
2024-08-04T19:55:09.115234610Z 
 25%|██▍       | 1401/5712 [3:17:00<9:57:52,  8.32s/it] 08/04/2024 12:55:09 - INFO - __main__ -   Step: 1401, LR: 4.192678567085775e-07, Loss: 0.40447038412094116
2024-08-04T19:55:17.987753741Z 
 25%|██▍       | 1402/5712 [3:17:09<10:09:37,  8.49s/it]08/04/2024 12:55:17 - INFO - __main__ -   Step: 1402, LR: 4.191705780782606e-07, Loss: 0.4732065796852112
2024-08-04T19:55:26.356030728Z 
 25%|██▍       | 1403/5712 [3:17:17<10:06:55,  8.45s/it]08/04/2024 12:55:26 - INFO - __main__ -   Step: 1403, LR: 4.1907329944794375e-07, Loss: 0.39274072647094727
2024-08-04T19:55:35.177900126Z 
 25%|██▍       | 1404/5712 [3:17:26<10:14:46,  8.56s/it]08/04/2024 12:55:35 - INFO - __main__ -   Step: 1404, LR: 4.189760208176269e-07, Loss: 0.4645819365978241
2024-08-04T19:55:43.605878922Z 
 25%|██▍       | 1405/5712 [3:17:34<10:11:44,  8.52s/it]08/04/2024 12:55:43 - INFO - __main__ -   Step: 1405, LR: 4.1887874218731e-07, Loss: 0.5385018587112427
2024-08-04T19:55:52.248783471Z 
 25%|██▍       | 1406/5712 [3:17:43<10:14:11,  8.56s/it]08/04/2024 12:55:52 - INFO - __main__ -   Step: 1406, LR: 4.187814635569931e-07, Loss: 0.43530234694480896
2024-08-04T19:56:01.139403070Z 
 25%|██▍       | 1407/5712 [3:17:52<10:21:12,  8.66s/it]08/04/2024 12:56:01 - INFO - __main__ -   Step: 1407, LR: 4.1868418492667625e-07, Loss: 0.509485125541687
2024-08-04T19:56:09.588053919Z 
 25%|██▍       | 1408/5712 [3:18:00<10:16:33,  8.60s/it]08/04/2024 12:56:09 - INFO - __main__ -   Step: 1408, LR: 4.1858690629635935e-07, Loss: 0.4818713366985321
2024-08-04T19:56:17.735665558Z 
 25%|██▍       | 1409/5712 [3:18:08<10:06:47,  8.46s/it]08/04/2024 12:56:17 - INFO - __main__ -   Step: 1409, LR: 4.1848962766604245e-07, Loss: 0.5644978284835815
2024-08-04T19:56:26.099854096Z 
 25%|██▍       | 1410/5712 [3:18:17<10:04:33,  8.43s/it]08/04/2024 12:56:26 - INFO - __main__ -   Step: 1410, LR: 4.1839234903572555e-07, Loss: 0.36138132214546204
2024-08-04T19:56:34.893544292Z 
 25%|██▍       | 1411/5712 [3:18:26<10:12:12,  8.54s/it]08/04/2024 12:56:34 - INFO - __main__ -   Step: 1411, LR: 4.182950704054087e-07, Loss: 0.28470802307128906
2024-08-04T19:56:43.418820213Z 
 25%|██▍       | 1412/5712 [3:18:34<10:11:44,  8.54s/it]08/04/2024 12:56:43 - INFO - __main__ -   Step: 1412, LR: 4.181977917750918e-07, Loss: 0.41737285256385803
2024-08-04T19:56:52.069788195Z 
 25%|██▍       | 1413/5712 [3:18:43<10:14:04,  8.57s/it]08/04/2024 12:56:52 - INFO - __main__ -   Step: 1413, LR: 4.181005131447749e-07, Loss: 0.5602813959121704
2024-08-04T19:57:00.401891342Z 
 25%|██▍       | 1414/5712 [3:18:51<10:08:48,  8.50s/it]08/04/2024 12:57:00 - INFO - __main__ -   Step: 1414, LR: 4.18003234514458e-07, Loss: 0.5247436761856079
2024-08-04T19:57:08.790735253Z 
 25%|██▍       | 1415/5712 [3:18:59<10:06:17,  8.47s/it]08/04/2024 12:57:08 - INFO - __main__ -   Step: 1415, LR: 4.1790595588414115e-07, Loss: 0.4449537992477417
2024-08-04T19:57:17.057917053Z 
 25%|██▍       | 1416/5712 [3:19:08<10:01:53,  8.41s/it]08/04/2024 12:57:17 - INFO - __main__ -   Step: 1416, LR: 4.1780867725382425e-07, Loss: 0.2938637137413025
2024-08-04T19:57:25.237585381Z 
 25%|██▍       | 1417/5712 [3:19:16<9:56:53,  8.34s/it] 08/04/2024 12:57:25 - INFO - __main__ -   Step: 1417, LR: 4.1771139862350735e-07, Loss: 0.41485512256622314
2024-08-04T19:57:33.492472195Z 
 25%|██▍       | 1418/5712 [3:19:24<9:54:57,  8.31s/it]08/04/2024 12:57:33 - INFO - __main__ -   Step: 1418, LR: 4.1761411999319045e-07, Loss: 0.5281916856765747
2024-08-04T19:57:42.302610005Z 
 25%|██▍       | 1419/5712 [3:19:33<10:05:28,  8.46s/it]08/04/2024 12:57:42 - INFO - __main__ -   Step: 1419, LR: 4.175168413628736e-07, Loss: 0.587932825088501
2024-08-04T19:57:51.657044289Z 
 25%|██▍       | 1420/5712 [3:19:42<10:24:28,  8.73s/it]08/04/2024 12:57:51 - INFO - __main__ -   Step: 1420, LR: 4.174195627325567e-07, Loss: 0.5924131870269775
2024-08-04T19:58:00.251092834Z 
 25%|██▍       | 1421/5712 [3:19:51<10:21:25,  8.69s/it]08/04/2024 12:58:00 - INFO - __main__ -   Step: 1421, LR: 4.173222841022398e-07, Loss: 0.2857930660247803
2024-08-04T19:58:08.626434761Z 
 25%|██▍       | 1422/5712 [3:19:59<10:14:33,  8.60s/it]08/04/2024 12:58:08 - INFO - __main__ -   Step: 1422, LR: 4.1722500547192295e-07, Loss: 0.5060341358184814
2024-08-04T19:58:17.163601367Z 
 25%|██▍       | 1423/5712 [3:20:08<10:13:09,  8.58s/it]08/04/2024 12:58:17 - INFO - __main__ -   Step: 1423, LR: 4.171277268416061e-07, Loss: 0.5013213157653809
2024-08-04T19:58:25.843408723Z 
 25%|██▍       | 1424/5712 [3:20:16<10:15:12,  8.61s/it]08/04/2024 12:58:25 - INFO - __main__ -   Step: 1424, LR: 4.170304482112892e-07, Loss: 0.46308058500289917
2024-08-04T19:58:34.506382203Z 
 25%|██▍       | 1425/5712 [3:20:25<10:16:14,  8.62s/it]08/04/2024 12:58:34 - INFO - __main__ -   Step: 1425, LR: 4.169331695809723e-07, Loss: 0.446530818939209
2024-08-04T19:58:42.045558441Z 
 25%|██▍       | 1426/5712 [3:20:33<9:52:49,  8.30s/it] 08/04/2024 12:58:42 - INFO - __main__ -   Step: 1426, LR: 4.168358909506554e-07, Loss: 0.4400273263454437
2024-08-04T19:58:50.751096056Z 
 25%|██▍       | 1427/5712 [3:20:41<10:01:23,  8.42s/it]08/04/2024 12:58:50 - INFO - __main__ -   Step: 1427, LR: 4.1673861232033855e-07, Loss: 0.43662530183792114
2024-08-04T19:58:59.117614687Z 
 25%|██▌       | 1428/5712 [3:20:50<10:00:05,  8.40s/it]08/04/2024 12:58:59 - INFO - __main__ -   Step: 1428, LR: 4.1664133369002165e-07, Loss: 0.40560322999954224
2024-08-04T19:59:07.529566340Z 
 25%|██▌       | 1429/5712 [3:20:58<10:00:06,  8.41s/it]08/04/2024 12:59:07 - INFO - __main__ -   Step: 1429, LR: 4.1654405505970475e-07, Loss: 0.5316140651702881
2024-08-04T19:59:15.753044899Z 
 25%|██▌       | 1430/5712 [3:21:06<9:56:02,  8.35s/it] 08/04/2024 12:59:15 - INFO - __main__ -   Step: 1430, LR: 4.1644677642938785e-07, Loss: 0.36938753724098206
2024-08-04T19:59:24.181792921Z 
 25%|██▌       | 1431/5712 [3:21:15<9:57:33,  8.37s/it]08/04/2024 12:59:24 - INFO - __main__ -   Step: 1431, LR: 4.1634949779907095e-07, Loss: 0.40187257528305054
2024-08-04T19:59:32.455530227Z 
 25%|██▌       | 1432/5712 [3:21:23<9:55:14,  8.34s/it]08/04/2024 12:59:32 - INFO - __main__ -   Step: 1432, LR: 4.162522191687541e-07, Loss: 0.34725892543792725
2024-08-04T19:59:40.641677309Z 
 25%|██▌       | 1433/5712 [3:21:31<9:51:43,  8.30s/it]08/04/2024 12:59:40 - INFO - __main__ -   Step: 1433, LR: 4.161549405384372e-07, Loss: 0.41220253705978394
2024-08-04T19:59:48.621244966Z 
 25%|██▌       | 1434/5712 [3:21:39<9:44:47,  8.20s/it]08/04/2024 12:59:48 - INFO - __main__ -   Step: 1434, LR: 4.160576619081203e-07, Loss: 0.4393323063850403
2024-08-04T19:59:57.571029096Z 
 25%|██▌       | 1435/5712 [3:21:48<10:00:38,  8.43s/it]08/04/2024 12:59:57 - INFO - __main__ -   Step: 1435, LR: 4.159603832778034e-07, Loss: 0.3449641764163971
2024-08-04T20:00:06.174049293Z 
 25%|██▌       | 1436/5712 [3:21:57<10:04:17,  8.48s/it]08/04/2024 13:00:06 - INFO - __main__ -   Step: 1436, LR: 4.1586310464748655e-07, Loss: 0.32437896728515625
2024-08-04T20:00:15.329830027Z 
 25%|██▌       | 1437/5712 [3:22:06<10:18:36,  8.68s/it]08/04/2024 13:00:15 - INFO - __main__ -   Step: 1437, LR: 4.1576582601716965e-07, Loss: 0.5433025360107422
2024-08-04T20:00:23.305546103Z 
 25%|██▌       | 1438/5712 [3:22:14<10:03:22,  8.47s/it]08/04/2024 13:00:23 - INFO - __main__ -   Step: 1438, LR: 4.1566854738685274e-07, Loss: 0.47188055515289307
2024-08-04T20:00:31.964210521Z 
 25%|██▌       | 1439/5712 [3:22:23<10:07:14,  8.53s/it]08/04/2024 13:00:31 - INFO - __main__ -   Step: 1439, LR: 4.1557126875653584e-07, Loss: 0.5907316207885742
2024-08-04T20:00:40.783453386Z 
 25%|██▌       | 1440/5712 [3:22:31<10:13:21,  8.61s/it]08/04/2024 13:00:40 - INFO - __main__ -   Step: 1440, LR: 4.1547399012621905e-07, Loss: 0.39795148372650146
2024-08-04T20:00:49.196790782Z 
 25%|██▌       | 1441/5712 [3:22:40<10:08:54,  8.55s/it]08/04/2024 13:00:49 - INFO - __main__ -   Step: 1441, LR: 4.1537671149590215e-07, Loss: 0.4140205383300781
2024-08-04T20:00:57.297675431Z 
 25%|██▌       | 1442/5712 [3:22:48<9:59:05,  8.42s/it] 08/04/2024 13:00:57 - INFO - __main__ -   Step: 1442, LR: 4.1527943286558525e-07, Loss: 0.48710402846336365
2024-08-04T20:01:05.234623214Z 
 25%|██▌       | 1443/5712 [3:22:56<9:48:40,  8.27s/it]08/04/2024 13:01:05 - INFO - __main__ -   Step: 1443, LR: 4.1518215423526835e-07, Loss: 0.451826274394989
2024-08-04T20:01:14.965427544Z 
 25%|██▌       | 1444/5712 [3:23:06<10:19:36,  8.71s/it]08/04/2024 13:01:14 - INFO - __main__ -   Step: 1444, LR: 4.150848756049515e-07, Loss: 0.5045484304428101
2024-08-04T20:01:23.675351607Z 
 25%|██▌       | 1445/5712 [3:23:14<10:19:28,  8.71s/it]08/04/2024 13:01:23 - INFO - __main__ -   Step: 1445, LR: 4.149875969746346e-07, Loss: 0.5299533009529114
2024-08-04T20:01:31.605184463Z 
 25%|██▌       | 1446/5712 [3:23:22<10:02:40,  8.48s/it]08/04/2024 13:01:31 - INFO - __main__ -   Step: 1446, LR: 4.148903183443177e-07, Loss: 0.3601831793785095
2024-08-04T20:01:40.707578796Z 
 25%|██▌       | 1447/5712 [3:23:31<10:15:53,  8.66s/it]08/04/2024 13:01:40 - INFO - __main__ -   Step: 1447, LR: 4.147930397140008e-07, Loss: 0.6356285810470581
2024-08-04T20:01:49.252402733Z 
 25%|██▌       | 1448/5712 [3:23:40<10:13:11,  8.63s/it]08/04/2024 13:01:49 - INFO - __main__ -   Step: 1448, LR: 4.1469576108368395e-07, Loss: 0.3624383211135864
2024-08-04T20:01:57.532312417Z 
 25%|██▌       | 1449/5712 [3:23:48<10:05:37,  8.52s/it]08/04/2024 13:01:57 - INFO - __main__ -   Step: 1449, LR: 4.1459848245336705e-07, Loss: 0.564295768737793
2024-08-04T20:02:05.845460256Z 
 25%|██▌       | 1450/5712 [3:23:56<10:00:59,  8.46s/it]08/04/2024 13:02:05 - INFO - __main__ -   Step: 1450, LR: 4.1450120382305014e-07, Loss: 0.5058873891830444
2024-08-04T20:02:14.768132019Z 
 25%|██▌       | 1451/5712 [3:24:05<10:10:41,  8.60s/it]08/04/2024 13:02:14 - INFO - __main__ -   Step: 1451, LR: 4.1440392519273324e-07, Loss: 0.5054488182067871
2024-08-04T20:02:22.941319234Z 
 25%|██▌       | 1452/5712 [3:24:14<10:01:28,  8.47s/it]08/04/2024 13:02:22 - INFO - __main__ -   Step: 1452, LR: 4.143066465624164e-07, Loss: 0.3071328103542328
2024-08-04T20:02:31.436803489Z 
 25%|██▌       | 1453/5712 [3:24:22<10:01:50,  8.48s/it]08/04/2024 13:02:31 - INFO - __main__ -   Step: 1453, LR: 4.142093679320995e-07, Loss: 0.45483657717704773
2024-08-04T20:02:40.082513991Z 
 25%|██▌       | 1454/5712 [3:24:31<10:05:15,  8.53s/it]08/04/2024 13:02:40 - INFO - __main__ -   Step: 1454, LR: 4.141120893017826e-07, Loss: 0.4419999122619629
2024-08-04T20:02:48.474540992Z 
 25%|██▌       | 1455/5712 [3:24:39<10:02:12,  8.49s/it]08/04/2024 13:02:48 - INFO - __main__ -   Step: 1455, LR: 4.140148106714657e-07, Loss: 0.5824868679046631
2024-08-04T20:02:57.207195895Z 
 25%|██▌       | 1456/5712 [3:24:48<10:07:16,  8.56s/it]08/04/2024 13:02:57 - INFO - __main__ -   Step: 1456, LR: 4.1391753204114884e-07, Loss: 0.5421218872070312
2024-08-04T20:03:05.636402549Z 
 26%|██▌       | 1457/5712 [3:24:56<10:04:18,  8.52s/it]08/04/2024 13:03:05 - INFO - __main__ -   Step: 1457, LR: 4.1382025341083194e-07, Loss: 0.3923560082912445
2024-08-04T20:03:14.189199102Z 
 26%|██▌       | 1458/5712 [3:25:05<10:04:50,  8.53s/it]08/04/2024 13:03:14 - INFO - __main__ -   Step: 1458, LR: 4.137229747805151e-07, Loss: 0.4578348398208618
2024-08-04T20:03:22.113630336Z 
 26%|██▌       | 1459/5712 [3:25:13<9:51:48,  8.35s/it] 08/04/2024 13:03:22 - INFO - __main__ -   Step: 1459, LR: 4.136256961501982e-07, Loss: 0.3838646411895752
2024-08-04T20:03:30.295322156Z 
 26%|██▌       | 1460/5712 [3:25:21<9:48:06,  8.30s/it]08/04/2024 13:03:30 - INFO - __main__ -   Step: 1460, LR: 4.1352841751988135e-07, Loss: 0.3605305850505829
2024-08-04T20:03:39.894476084Z 
 26%|██▌       | 1461/5712 [3:25:31<10:15:34,  8.69s/it]08/04/2024 13:03:39 - INFO - __main__ -   Step: 1461, LR: 4.1343113888956445e-07, Loss: 0.3656999468803406
2024-08-04T20:03:48.331019729Z 
 26%|██▌       | 1462/5712 [3:25:39<10:10:06,  8.61s/it]08/04/2024 13:03:48 - INFO - __main__ -   Step: 1462, LR: 4.1333386025924754e-07, Loss: 0.4399302005767822
2024-08-04T20:03:56.834248849Z 
 26%|██▌       | 1463/5712 [3:25:47<10:07:37,  8.58s/it]08/04/2024 13:03:56 - INFO - __main__ -   Step: 1463, LR: 4.1323658162893064e-07, Loss: 0.5475634932518005
2024-08-04T20:04:05.184924997Z 
 26%|██▌       | 1464/5712 [3:25:56<10:02:36,  8.51s/it]08/04/2024 13:04:05 - INFO - __main__ -   Step: 1464, LR: 4.131393029986138e-07, Loss: 0.4052552282810211
2024-08-04T20:04:13.451642579Z 
 26%|██▌       | 1465/5712 [3:26:04<9:57:16,  8.44s/it] 08/04/2024 13:04:13 - INFO - __main__ -   Step: 1465, LR: 4.130420243682969e-07, Loss: 0.38195210695266724
2024-08-04T20:04:21.729067144Z 
 26%|██▌       | 1466/5712 [3:26:12<9:53:43,  8.39s/it]08/04/2024 13:04:21 - INFO - __main__ -   Step: 1466, LR: 4.1294474573798e-07, Loss: 0.3513931930065155
2024-08-04T20:04:29.807818349Z 
 26%|██▌       | 1467/5712 [3:26:20<9:46:58,  8.30s/it]08/04/2024 13:04:29 - INFO - __main__ -   Step: 1467, LR: 4.128474671076631e-07, Loss: 0.3475147485733032
2024-08-04T20:04:38.350067938Z 
 26%|██▌       | 1468/5712 [3:26:29<9:52:03,  8.37s/it]08/04/2024 13:04:38 - INFO - __main__ -   Step: 1468, LR: 4.127501884773462e-07, Loss: 0.38624995946884155
2024-08-04T20:04:46.589110755Z 
 26%|██▌       | 1469/5712 [3:26:37<9:49:08,  8.33s/it]08/04/2024 13:04:46 - INFO - __main__ -   Step: 1469, LR: 4.1265290984702934e-07, Loss: 0.34831368923187256
2024-08-04T20:04:55.368640074Z 
 26%|██▌       | 1470/5712 [3:26:46<9:58:30,  8.47s/it]08/04/2024 13:04:55 - INFO - __main__ -   Step: 1470, LR: 4.1255563121671244e-07, Loss: 0.3685414791107178
2024-08-04T20:05:03.434861147Z 
 26%|██▌       | 1471/5712 [3:26:54<9:49:53,  8.35s/it]08/04/2024 13:05:03 - INFO - __main__ -   Step: 1471, LR: 4.1245835258639554e-07, Loss: 0.4021332859992981
2024-08-04T20:05:12.205516881Z 
 26%|██▌       | 1472/5712 [3:27:03<9:58:46,  8.47s/it]08/04/2024 13:05:12 - INFO - __main__ -   Step: 1472, LR: 4.1236107395607864e-07, Loss: 0.3551819324493408
2024-08-04T20:05:20.589132101Z 
 26%|██▌       | 1473/5712 [3:27:11<9:56:43,  8.45s/it]08/04/2024 13:05:20 - INFO - __main__ -   Step: 1473, LR: 4.122637953257618e-07, Loss: 0.37340524792671204
2024-08-04T20:05:28.763132150Z 
 26%|██▌       | 1474/5712 [3:27:19<9:50:49,  8.36s/it]08/04/2024 13:05:28 - INFO - __main__ -   Step: 1474, LR: 4.121665166954449e-07, Loss: 0.378603458404541
2024-08-04T20:05:37.210972620Z 
 26%|██▌       | 1475/5712 [3:27:28<9:52:26,  8.39s/it]08/04/2024 13:05:37 - INFO - __main__ -   Step: 1475, LR: 4.12069238065128e-07, Loss: 0.42563289403915405
2024-08-04T20:05:46.376636433Z 
 26%|██▌       | 1476/5712 [3:27:37<10:08:43,  8.62s/it]08/04/2024 13:05:46 - INFO - __main__ -   Step: 1476, LR: 4.119719594348111e-07, Loss: 0.29001516103744507
2024-08-04T20:05:54.981957840Z 
 26%|██▌       | 1477/5712 [3:27:46<10:08:13,  8.62s/it]08/04/2024 13:05:54 - INFO - __main__ -   Step: 1477, LR: 4.118746808044943e-07, Loss: 0.35516786575317383
2024-08-04T20:06:04.284476855Z 
 26%|██▌       | 1478/5712 [3:27:55<10:22:36,  8.82s/it]08/04/2024 13:06:04 - INFO - __main__ -   Step: 1478, LR: 4.117774021741774e-07, Loss: 0.47496724128723145
2024-08-04T20:06:12.931918501Z 
 26%|██▌       | 1479/5712 [3:28:04<10:18:44,  8.77s/it]08/04/2024 13:06:12 - INFO - __main__ -   Step: 1479, LR: 4.116801235438605e-07, Loss: 0.4866997003555298
2024-08-04T20:06:21.380042870Z 
 26%|██▌       | 1480/5712 [3:28:12<10:11:46,  8.67s/it]08/04/2024 13:06:21 - INFO - __main__ -   Step: 1480, LR: 4.115828449135436e-07, Loss: 0.37245333194732666
2024-08-04T20:06:29.699696415Z 
 26%|██▌       | 1481/5712 [3:28:20<10:04:08,  8.57s/it]08/04/2024 13:06:29 - INFO - __main__ -   Step: 1481, LR: 4.1148556628322674e-07, Loss: 0.42707791924476624
2024-08-04T20:06:38.014440077Z 
 26%|██▌       | 1482/5712 [3:28:29<9:58:39,  8.49s/it] 08/04/2024 13:06:38 - INFO - __main__ -   Step: 1482, LR: 4.1138828765290984e-07, Loss: 0.31368058919906616
2024-08-04T20:06:46.091445678Z 
 26%|██▌       | 1483/5712 [3:28:37<9:49:45,  8.37s/it]08/04/2024 13:06:46 - INFO - __main__ -   Step: 1483, LR: 4.1129100902259294e-07, Loss: 0.5406844615936279
2024-08-04T20:06:54.860561126Z 
 26%|██▌       | 1484/5712 [3:28:46<9:58:06,  8.49s/it]08/04/2024 13:06:54 - INFO - __main__ -   Step: 1484, LR: 4.1119373039227604e-07, Loss: 0.4569413661956787
2024-08-04T20:07:03.171706839Z 
 26%|██▌       | 1485/5712 [3:28:54<9:54:13,  8.43s/it]08/04/2024 13:07:03 - INFO - __main__ -   Step: 1485, LR: 4.110964517619592e-07, Loss: 0.3699609041213989
2024-08-04T20:07:11.766224204Z 
 26%|██▌       | 1486/5712 [3:29:02<9:57:28,  8.48s/it]08/04/2024 13:07:11 - INFO - __main__ -   Step: 1486, LR: 4.109991731316423e-07, Loss: 0.5288591384887695
2024-08-04T20:07:20.840444211Z 
 26%|██▌       | 1487/5712 [3:29:11<10:09:49,  8.66s/it]08/04/2024 13:07:20 - INFO - __main__ -   Step: 1487, LR: 4.109018945013254e-07, Loss: 0.5998779535293579
2024-08-04T20:07:29.800925521Z 
 26%|██▌       | 1488/5712 [3:29:20<10:16:01,  8.75s/it]08/04/2024 13:07:29 - INFO - __main__ -   Step: 1488, LR: 4.108046158710085e-07, Loss: 0.5053390860557556
2024-08-04T20:07:38.695795861Z 
 26%|██▌       | 1489/5712 [3:29:29<10:18:55,  8.79s/it]08/04/2024 13:07:38 - INFO - __main__ -   Step: 1489, LR: 4.1070733724069164e-07, Loss: 0.5797622203826904
2024-08-04T20:07:46.902759757Z 
 26%|██▌       | 1490/5712 [3:29:38<10:06:23,  8.62s/it]08/04/2024 13:07:46 - INFO - __main__ -   Step: 1490, LR: 4.1061005861037474e-07, Loss: 0.6565227508544922
2024-08-04T20:07:55.075891160Z 
 26%|██▌       | 1491/5712 [3:29:46<9:56:52,  8.48s/it] 08/04/2024 13:07:55 - INFO - __main__ -   Step: 1491, LR: 4.1051277998005784e-07, Loss: 0.7082456350326538
2024-08-04T20:08:03.395998818Z 
 26%|██▌       | 1492/5712 [3:29:54<9:53:15,  8.44s/it]08/04/2024 13:08:03 - INFO - __main__ -   Step: 1492, LR: 4.1041550134974094e-07, Loss: 0.4322707951068878
2024-08-04T20:08:12.843391774Z 
 26%|██▌       | 1493/5712 [3:30:03<10:14:27,  8.74s/it]08/04/2024 13:08:12 - INFO - __main__ -   Step: 1493, LR: 4.103182227194241e-07, Loss: 0.4514777362346649
2024-08-04T20:08:21.068311997Z 
 26%|██▌       | 1494/5712 [3:30:12<10:03:30,  8.58s/it]08/04/2024 13:08:21 - INFO - __main__ -   Step: 1494, LR: 4.102209440891072e-07, Loss: 0.54939204454422
2024-08-04T20:08:30.675008200Z 
 26%|██▌       | 1495/5712 [3:30:21<10:24:53,  8.89s/it]08/04/2024 13:08:30 - INFO - __main__ -   Step: 1495, LR: 4.1012366545879034e-07, Loss: 0.4609702527523041
2024-08-04T20:08:40.097062721Z 
 26%|██▌       | 1496/5712 [3:30:31<10:35:57,  9.05s/it]08/04/2024 13:08:40 - INFO - __main__ -   Step: 1496, LR: 4.1002638682847344e-07, Loss: 0.5673117637634277
2024-08-04T20:08:48.355871432Z 
 26%|██▌       | 1497/5712 [3:30:39<10:19:06,  8.81s/it]08/04/2024 13:08:48 - INFO - __main__ -   Step: 1497, LR: 4.099291081981566e-07, Loss: 0.3770902454853058
2024-08-04T20:08:57.037583809Z 
 26%|██▌       | 1498/5712 [3:30:48<10:16:12,  8.77s/it]08/04/2024 13:08:57 - INFO - __main__ -   Step: 1498, LR: 4.098318295678397e-07, Loss: 0.31928738951683044
2024-08-04T20:09:05.053041013Z 
 26%|██▌       | 1499/5712 [3:30:56<10:00:05,  8.55s/it]08/04/2024 13:09:05 - INFO - __main__ -   Step: 1499, LR: 4.097345509375228e-07, Loss: 0.6209104061126709
2024-08-04T20:09:13.407026492Z 
 26%|██▋       | 1500/5712 [3:31:04<9:55:53,  8.49s/it] 08/04/2024 13:09:13 - INFO - __main__ -   Step: 1500, LR: 4.096372723072059e-07, Loss: 0.4867144525051117
2024-08-04T20:09:21.974207028Z 
 26%|██▋       | 1501/5712 [3:31:13<9:57:24,  8.51s/it]08/04/2024 13:09:21 - INFO - __main__ -   Step: 1501, LR: 4.0953999367688904e-07, Loss: 0.36260202527046204
2024-08-04T20:09:30.674542322Z 
 26%|██▋       | 1502/5712 [3:31:21<10:01:13,  8.57s/it]08/04/2024 13:09:30 - INFO - __main__ -   Step: 1502, LR: 4.0944271504657214e-07, Loss: 0.5005570650100708
2024-08-04T20:09:39.065728146Z 
 26%|██▋       | 1503/5712 [3:31:30<9:57:21,  8.52s/it] 08/04/2024 13:09:39 - INFO - __main__ -   Step: 1503, LR: 4.0934543641625524e-07, Loss: 0.5196996927261353
2024-08-04T20:09:47.656255574Z 
 26%|██▋       | 1504/5712 [3:31:38<9:58:47,  8.54s/it]08/04/2024 13:09:47 - INFO - __main__ -   Step: 1504, LR: 4.0924815778593834e-07, Loss: 0.4083406329154968
2024-08-04T20:09:56.301267082Z 
 26%|██▋       | 1505/5712 [3:31:47<10:00:54,  8.57s/it]08/04/2024 13:09:56 - INFO - __main__ -   Step: 1505, LR: 4.0915087915562144e-07, Loss: 0.43990135192871094
2024-08-04T20:10:04.616765198Z 
 26%|██▋       | 1506/5712 [3:31:55<9:55:24,  8.49s/it] 08/04/2024 13:10:04 - INFO - __main__ -   Step: 1506, LR: 4.090536005253046e-07, Loss: 0.5399394035339355
2024-08-04T20:10:12.560396030Z 
 26%|██▋       | 1507/5712 [3:32:03<9:43:41,  8.33s/it]08/04/2024 13:10:12 - INFO - __main__ -   Step: 1507, LR: 4.089563218949877e-07, Loss: 0.5100506544113159
2024-08-04T20:10:20.840263465Z 
 26%|██▋       | 1508/5712 [3:32:11<9:42:32,  8.31s/it]08/04/2024 13:10:20 - INFO - __main__ -   Step: 1508, LR: 4.088590432646708e-07, Loss: 0.5448251962661743
2024-08-04T20:10:29.585411756Z 
 26%|██▋       | 1509/5712 [3:32:20<9:51:27,  8.44s/it]08/04/2024 13:10:29 - INFO - __main__ -   Step: 1509, LR: 4.087617646343539e-07, Loss: 0.45091360807418823
2024-08-04T20:10:38.533964178Z 
 26%|██▋       | 1510/5712 [3:32:29<10:01:54,  8.59s/it]08/04/2024 13:10:38 - INFO - __main__ -   Step: 1510, LR: 4.0866448600403704e-07, Loss: 0.406914621591568
2024-08-04T20:10:47.055671563Z 
 26%|██▋       | 1511/5712 [3:32:38<10:00:15,  8.57s/it]08/04/2024 13:10:47 - INFO - __main__ -   Step: 1511, LR: 4.0856720737372014e-07, Loss: 0.46250250935554504
2024-08-04T20:10:56.054939359Z 
 26%|██▋       | 1512/5712 [3:32:47<10:09:02,  8.70s/it]08/04/2024 13:10:56 - INFO - __main__ -   Step: 1512, LR: 4.0846992874340324e-07, Loss: 0.6318696737289429
2024-08-04T20:11:04.406871644Z 
 26%|██▋       | 1513/5712 [3:32:55<10:01:35,  8.60s/it]08/04/2024 13:11:04 - INFO - __main__ -   Step: 1513, LR: 4.083726501130864e-07, Loss: 0.46694183349609375
2024-08-04T20:11:13.219819115Z 
 27%|██▋       | 1514/5712 [3:33:04<10:06:00,  8.66s/it]08/04/2024 13:11:13 - INFO - __main__ -   Step: 1514, LR: 4.0827537148276954e-07, Loss: 0.31187981367111206
2024-08-04T20:11:21.174315599Z 
 27%|██▋       | 1515/5712 [3:33:12<9:51:01,  8.45s/it] 08/04/2024 13:11:21 - INFO - __main__ -   Step: 1515, LR: 4.0817809285245264e-07, Loss: 0.5087100863456726
2024-08-04T20:11:29.134613545Z 
 27%|██▋       | 1516/5712 [3:33:20<9:40:37,  8.30s/it]08/04/2024 13:11:29 - INFO - __main__ -   Step: 1516, LR: 4.0808081422213574e-07, Loss: 0.5137172341346741
2024-08-04T20:11:37.327037432Z 
 27%|██▋       | 1517/5712 [3:33:28<9:38:10,  8.27s/it]08/04/2024 13:11:37 - INFO - __main__ -   Step: 1517, LR: 4.0798353559181884e-07, Loss: 0.4898602366447449
2024-08-04T20:11:45.893588399Z 
 27%|██▋       | 1518/5712 [3:33:37<9:44:16,  8.36s/it]08/04/2024 13:11:45 - INFO - __main__ -   Step: 1518, LR: 4.07886256961502e-07, Loss: 0.421187162399292
2024-08-04T20:11:55.066149575Z 
 27%|██▋       | 1519/5712 [3:33:46<10:01:11,  8.60s/it]08/04/2024 13:11:55 - INFO - __main__ -   Step: 1519, LR: 4.077889783311851e-07, Loss: 0.5055192708969116
2024-08-04T20:12:03.727179575Z 
 27%|██▋       | 1520/5712 [3:33:54<10:02:16,  8.62s/it]08/04/2024 13:12:03 - INFO - __main__ -   Step: 1520, LR: 4.076916997008682e-07, Loss: 0.48795363306999207
2024-08-04T20:12:11.923317692Z 
 27%|██▋       | 1521/5712 [3:34:03<9:53:12,  8.49s/it] 08/04/2024 13:12:11 - INFO - __main__ -   Step: 1521, LR: 4.075944210705513e-07, Loss: 0.39252257347106934
2024-08-04T20:12:20.335823666Z 
 27%|██▋       | 1522/5712 [3:34:11<9:51:25,  8.47s/it]08/04/2024 13:12:20 - INFO - __main__ -   Step: 1522, LR: 4.0749714244023444e-07, Loss: 0.5145844221115112
2024-08-04T20:12:28.299698434Z 
 27%|██▋       | 1523/5712 [3:34:19<9:40:42,  8.32s/it]08/04/2024 13:12:28 - INFO - __main__ -   Step: 1523, LR: 4.0739986380991754e-07, Loss: 0.38957810401916504
2024-08-04T20:12:36.396850893Z 
 27%|██▋       | 1524/5712 [3:34:27<9:35:56,  8.25s/it]08/04/2024 13:12:36 - INFO - __main__ -   Step: 1524, LR: 4.0730258517960064e-07, Loss: 0.47559118270874023
2024-08-04T20:12:44.582504883Z 
 27%|██▋       | 1525/5712 [3:34:35<9:34:25,  8.23s/it]08/04/2024 13:12:44 - INFO - __main__ -   Step: 1525, LR: 4.0720530654928374e-07, Loss: 0.42755305767059326
2024-08-04T20:12:53.104994136Z 
 27%|██▋       | 1526/5712 [3:34:44<9:40:22,  8.32s/it]08/04/2024 13:12:53 - INFO - __main__ -   Step: 1526, LR: 4.071080279189669e-07, Loss: 0.4733302891254425
2024-08-04T20:13:01.785150936Z 
 27%|██▋       | 1527/5712 [3:34:52<9:47:47,  8.43s/it]08/04/2024 13:13:01 - INFO - __main__ -   Step: 1527, LR: 4.0701074928865e-07, Loss: 0.35103654861450195
2024-08-04T20:13:10.120819396Z 
 27%|██▋       | 1528/5712 [3:35:01<9:45:45,  8.40s/it]08/04/2024 13:13:10 - INFO - __main__ -   Step: 1528, LR: 4.069134706583331e-07, Loss: 0.6556864976882935
2024-08-04T20:13:18.776283875Z 
 27%|██▋       | 1529/5712 [3:35:09<9:50:57,  8.48s/it]08/04/2024 13:13:18 - INFO - __main__ -   Step: 1529, LR: 4.068161920280162e-07, Loss: 0.43897518515586853
2024-08-04T20:13:26.950567359Z 
 27%|██▋       | 1530/5712 [3:35:18<9:44:29,  8.39s/it]08/04/2024 13:13:26 - INFO - __main__ -   Step: 1530, LR: 4.0671891339769934e-07, Loss: 0.5110478401184082
2024-08-04T20:13:35.134423225Z 
 27%|██▋       | 1531/5712 [3:35:26<9:40:07,  8.33s/it]08/04/2024 13:13:35 - INFO - __main__ -   Step: 1531, LR: 4.066216347673825e-07, Loss: 0.4766284227371216
2024-08-04T20:13:43.337403862Z 
 27%|██▋       | 1532/5712 [3:35:34<9:37:26,  8.29s/it]08/04/2024 13:13:43 - INFO - __main__ -   Step: 1532, LR: 4.065243561370656e-07, Loss: 0.459431529045105
2024-08-04T20:13:51.430298318Z 
 27%|██▋       | 1533/5712 [3:35:42<9:33:12,  8.23s/it]08/04/2024 13:13:51 - INFO - __main__ -   Step: 1533, LR: 4.064270775067487e-07, Loss: 0.4716070890426636
2024-08-04T20:13:59.730699698Z 
 27%|██▋       | 1534/5712 [3:35:50<9:34:32,  8.25s/it]08/04/2024 13:13:59 - INFO - __main__ -   Step: 1534, LR: 4.0632979887643184e-07, Loss: 0.44464704394340515
2024-08-04T20:14:07.708854751Z 
 27%|██▋       | 1535/5712 [3:35:58<9:28:42,  8.17s/it]08/04/2024 13:14:07 - INFO - __main__ -   Step: 1535, LR: 4.0623252024611494e-07, Loss: 0.3560905456542969
2024-08-04T20:14:16.381891584Z 
 27%|██▋       | 1536/5712 [3:36:07<9:39:05,  8.32s/it]08/04/2024 13:14:16 - INFO - __main__ -   Step: 1536, LR: 4.0613524161579804e-07, Loss: 0.3603562116622925
2024-08-04T20:14:25.248916419Z 
 27%|██▋       | 1537/5712 [3:36:16<9:50:22,  8.48s/it]08/04/2024 13:14:25 - INFO - __main__ -   Step: 1537, LR: 4.0603796298548114e-07, Loss: 0.38894954323768616
2024-08-04T20:14:34.075270199Z 
 27%|██▋       | 1538/5712 [3:36:25<9:57:21,  8.59s/it]08/04/2024 13:14:34 - INFO - __main__ -   Step: 1538, LR: 4.059406843551643e-07, Loss: 0.5840731859207153
2024-08-04T20:14:42.521105426Z 
 27%|██▋       | 1539/5712 [3:36:33<9:54:16,  8.54s/it]08/04/2024 13:14:42 - INFO - __main__ -   Step: 1539, LR: 4.058434057248474e-07, Loss: 0.372442364692688
2024-08-04T20:14:50.901833648Z 
 27%|██▋       | 1540/5712 [3:36:42<9:50:43,  8.50s/it]08/04/2024 13:14:50 - INFO - __main__ -   Step: 1540, LR: 4.057461270945305e-07, Loss: 0.5001888871192932
2024-08-04T20:14:58.907270954Z 
 27%|██▋       | 1541/5712 [3:36:50<9:40:20,  8.35s/it]08/04/2024 13:14:58 - INFO - __main__ -   Step: 1541, LR: 4.056488484642136e-07, Loss: 0.3645561635494232
2024-08-04T20:15:07.916954920Z 
 27%|██▋       | 1542/5712 [3:36:59<9:54:00,  8.55s/it]08/04/2024 13:15:07 - INFO - __main__ -   Step: 1542, LR: 4.055515698338967e-07, Loss: 0.3587580919265747
2024-08-04T20:15:16.024045666Z 
 27%|██▋       | 1543/5712 [3:37:07<9:44:41,  8.41s/it]08/04/2024 13:15:16 - INFO - __main__ -   Step: 1543, LR: 4.0545429120357984e-07, Loss: 0.41898417472839355
2024-08-04T20:15:25.260274557Z 
 27%|██▋       | 1544/5712 [3:37:16<10:01:39,  8.66s/it]08/04/2024 13:15:25 - INFO - __main__ -   Step: 1544, LR: 4.0535701257326294e-07, Loss: 0.3336066007614136
2024-08-04T20:15:34.058623133Z 
 27%|██▋       | 1545/5712 [3:37:25<10:04:23,  8.70s/it]08/04/2024 13:15:34 - INFO - __main__ -   Step: 1545, LR: 4.0525973394294604e-07, Loss: 0.34868037700653076
2024-08-04T20:15:42.756099529Z 
 27%|██▋       | 1546/5712 [3:37:33<10:04:08,  8.70s/it]08/04/2024 13:15:42 - INFO - __main__ -   Step: 1546, LR: 4.0516245531262914e-07, Loss: 0.5618324279785156
2024-08-04T20:15:51.617626625Z 
 27%|██▋       | 1547/5712 [3:37:42<10:07:20,  8.75s/it]08/04/2024 13:15:51 - INFO - __main__ -   Step: 1547, LR: 4.050651766823123e-07, Loss: 0.5066295266151428
2024-08-04T20:15:59.731436379Z 
 27%|██▋       | 1548/5712 [3:37:50<9:53:57,  8.56s/it] 08/04/2024 13:15:59 - INFO - __main__ -   Step: 1548, LR: 4.049678980519954e-07, Loss: 0.4155408442020416
2024-08-04T20:16:08.077716682Z 
 27%|██▋       | 1549/5712 [3:37:59<9:49:24,  8.49s/it]08/04/2024 13:16:08 - INFO - __main__ -   Step: 1549, LR: 4.0487061942167854e-07, Loss: 0.41097474098205566
2024-08-04T20:16:16.334296929Z 
 27%|██▋       | 1550/5712 [3:38:07<9:44:18,  8.42s/it]08/04/2024 13:16:16 - INFO - __main__ -   Step: 1550, LR: 4.0477334079136164e-07, Loss: 0.3509766459465027
2024-08-04T20:16:24.570501833Z 
 27%|██▋       | 1551/5712 [3:38:15<9:40:15,  8.37s/it]08/04/2024 13:16:24 - INFO - __main__ -   Step: 1551, LR: 4.046760621610448e-07, Loss: 0.4339051842689514
2024-08-04T20:16:32.824893746Z 
 27%|██▋       | 1552/5712 [3:38:23<9:37:46,  8.33s/it]08/04/2024 13:16:32 - INFO - __main__ -   Step: 1552, LR: 4.045787835307279e-07, Loss: 0.36665260791778564
2024-08-04T20:16:41.556924881Z 
 27%|██▋       | 1553/5712 [3:38:32<9:45:55,  8.45s/it]08/04/2024 13:16:41 - INFO - __main__ -   Step: 1553, LR: 4.04481504900411e-07, Loss: 0.43994542956352234
2024-08-04T20:16:50.143843755Z 
 27%|██▋       | 1554/5712 [3:38:41<9:48:34,  8.49s/it]08/04/2024 13:16:50 - INFO - __main__ -   Step: 1554, LR: 4.043842262700941e-07, Loss: 0.44278812408447266
2024-08-04T20:16:58.609677545Z 
 27%|██▋       | 1555/5712 [3:38:49<9:47:51,  8.48s/it]08/04/2024 13:16:58 - INFO - __main__ -   Step: 1555, LR: 4.0428694763977724e-07, Loss: 0.5191446542739868
2024-08-04T20:17:07.373266094Z 
 27%|██▋       | 1556/5712 [3:38:58<9:53:30,  8.57s/it]08/04/2024 13:17:07 - INFO - __main__ -   Step: 1556, LR: 4.0418966900946034e-07, Loss: 0.5478249788284302
2024-08-04T20:17:15.626990794Z 
 27%|██▋       | 1557/5712 [3:39:06<9:46:50,  8.47s/it]08/04/2024 13:17:15 - INFO - __main__ -   Step: 1557, LR: 4.0409239037914344e-07, Loss: 0.3587421476840973
2024-08-04T20:17:23.774273916Z 
 27%|██▋       | 1558/5712 [3:39:14<9:39:54,  8.38s/it]08/04/2024 13:17:23 - INFO - __main__ -   Step: 1558, LR: 4.0399511174882654e-07, Loss: 0.35396459698677063
2024-08-04T20:17:32.572784723Z 
 27%|██▋       | 1559/5712 [3:39:23<9:48:32,  8.50s/it]08/04/2024 13:17:32 - INFO - __main__ -   Step: 1559, LR: 4.038978331185097e-07, Loss: 0.4974899888038635
2024-08-04T20:17:41.038954600Z 
 27%|██▋       | 1560/5712 [3:39:32<9:47:37,  8.49s/it]08/04/2024 13:17:41 - INFO - __main__ -   Step: 1560, LR: 4.038005544881928e-07, Loss: 0.48936983942985535
2024-08-04T20:17:49.884196796Z 
 27%|██▋       | 1561/5712 [3:39:41<9:54:48,  8.60s/it]08/04/2024 13:17:49 - INFO - __main__ -   Step: 1561, LR: 4.037032758578759e-07, Loss: 0.38698485493659973
2024-08-04T20:17:58.255833112Z 
 27%|██▋       | 1562/5712 [3:39:49<9:49:59,  8.53s/it]08/04/2024 13:17:58 - INFO - __main__ -   Step: 1562, LR: 4.03605997227559e-07, Loss: 0.33044111728668213
2024-08-04T20:18:06.636974478Z 
 27%|██▋       | 1563/5712 [3:39:57<9:46:45,  8.49s/it]08/04/2024 13:18:06 - INFO - __main__ -   Step: 1563, LR: 4.0350871859724214e-07, Loss: 0.44063279032707214
2024-08-04T20:18:15.052500581Z 
 27%|██▋       | 1564/5712 [3:40:06<9:45:09,  8.46s/it]08/04/2024 13:18:15 - INFO - __main__ -   Step: 1564, LR: 4.0341143996692524e-07, Loss: 0.3808923363685608
2024-08-04T20:18:23.101549026Z 
 27%|██▋       | 1565/5712 [3:40:14<9:36:25,  8.34s/it]08/04/2024 13:18:23 - INFO - __main__ -   Step: 1565, LR: 4.0331416133660833e-07, Loss: 0.6739251613616943
2024-08-04T20:18:31.111312762Z 
 27%|██▋       | 1566/5712 [3:40:22<9:29:26,  8.24s/it]08/04/2024 13:18:31 - INFO - __main__ -   Step: 1566, LR: 4.0321688270629143e-07, Loss: 0.5320742130279541
2024-08-04T20:18:39.596693629Z 
 27%|██▋       | 1567/5712 [3:40:30<9:34:22,  8.31s/it]08/04/2024 13:18:39 - INFO - __main__ -   Step: 1567, LR: 4.0311960407597464e-07, Loss: 0.5753113031387329
2024-08-04T20:18:48.012189422Z 
 27%|██▋       | 1568/5712 [3:40:39<9:36:19,  8.34s/it]08/04/2024 13:18:48 - INFO - __main__ -   Step: 1568, LR: 4.0302232544565774e-07, Loss: 0.44184431433677673
2024-08-04T20:18:56.418891903Z 
 27%|██▋       | 1569/5712 [3:40:47<9:37:29,  8.36s/it]08/04/2024 13:18:56 - INFO - __main__ -   Step: 1569, LR: 4.0292504681534084e-07, Loss: 0.3879234194755554
2024-08-04T20:19:04.945684385Z 
 27%|██▋       | 1570/5712 [3:40:56<9:40:43,  8.41s/it]08/04/2024 13:19:04 - INFO - __main__ -   Step: 1570, LR: 4.0282776818502394e-07, Loss: 0.43448030948638916
2024-08-04T20:19:13.387335703Z 
 28%|██▊       | 1571/5712 [3:41:04<9:41:12,  8.42s/it]08/04/2024 13:19:13 - INFO - __main__ -   Step: 1571, LR: 4.027304895547071e-07, Loss: 0.6341633796691895
2024-08-04T20:19:21.917037050Z 
 28%|██▊       | 1572/5712 [3:41:13<9:43:18,  8.45s/it]08/04/2024 13:19:21 - INFO - __main__ -   Step: 1572, LR: 4.026332109243902e-07, Loss: 0.5184012651443481
2024-08-04T20:19:30.686196582Z 
 28%|██▊       | 1573/5712 [3:41:21<9:49:41,  8.55s/it]08/04/2024 13:19:30 - INFO - __main__ -   Step: 1573, LR: 4.025359322940733e-07, Loss: 0.5342108011245728
2024-08-04T20:19:38.693491714Z 
 28%|██▊       | 1574/5712 [3:41:29<9:38:21,  8.39s/it]08/04/2024 13:19:38 - INFO - __main__ -   Step: 1574, LR: 4.024386536637564e-07, Loss: 0.4968835711479187
2024-08-04T20:19:47.365866890Z 
 28%|██▊       | 1575/5712 [3:41:38<9:44:08,  8.47s/it]08/04/2024 13:19:47 - INFO - __main__ -   Step: 1575, LR: 4.0234137503343954e-07, Loss: 0.3816290497779846
2024-08-04T20:19:55.696189971Z 
 28%|██▊       | 1576/5712 [3:41:46<9:41:04,  8.43s/it]08/04/2024 13:19:55 - INFO - __main__ -   Step: 1576, LR: 4.0224409640312264e-07, Loss: 0.5128181576728821
2024-08-04T20:20:04.638154045Z 
 28%|██▊       | 1577/5712 [3:41:55<9:51:31,  8.58s/it]08/04/2024 13:20:04 - INFO - __main__ -   Step: 1577, LR: 4.0214681777280574e-07, Loss: 0.5750458240509033
2024-08-04T20:20:13.310502326Z 
 28%|██▊       | 1578/5712 [3:42:04<9:53:10,  8.61s/it]08/04/2024 13:20:13 - INFO - __main__ -   Step: 1578, LR: 4.0204953914248883e-07, Loss: 0.5672752261161804
2024-08-04T20:20:21.723583840Z 
 28%|██▊       | 1579/5712 [3:42:12<9:49:01,  8.55s/it]08/04/2024 13:20:21 - INFO - __main__ -   Step: 1579, LR: 4.0195226051217193e-07, Loss: 0.42708420753479004
2024-08-04T20:20:31.190903338Z 
 28%|██▊       | 1580/5712 [3:42:22<10:07:49,  8.83s/it]08/04/2024 13:20:31 - INFO - __main__ -   Step: 1580, LR: 4.018549818818551e-07, Loss: 0.44720470905303955
2024-08-04T20:20:39.422557166Z 
 28%|██▊       | 1581/5712 [3:42:30<9:55:23,  8.65s/it] 08/04/2024 13:20:39 - INFO - __main__ -   Step: 1581, LR: 4.017577032515382e-07, Loss: 0.4153091311454773
2024-08-04T20:20:47.551066391Z 
 28%|██▊       | 1582/5712 [3:42:38<9:44:31,  8.49s/it]08/04/2024 13:20:47 - INFO - __main__ -   Step: 1582, LR: 4.016604246212213e-07, Loss: 0.5102968215942383
2024-08-04T20:20:55.546466735Z 
 28%|██▊       | 1583/5712 [3:42:46<9:34:08,  8.34s/it]08/04/2024 13:20:55 - INFO - __main__ -   Step: 1583, LR: 4.015631459909044e-07, Loss: 0.418973445892334
2024-08-04T20:21:04.031608932Z 
 28%|██▊       | 1584/5712 [3:42:55<9:36:56,  8.39s/it]08/04/2024 13:21:04 - INFO - __main__ -   Step: 1584, LR: 4.0146586736058753e-07, Loss: 0.2779921293258667
2024-08-04T20:21:12.449829268Z 
 28%|██▊       | 1585/5712 [3:43:03<9:37:27,  8.40s/it]08/04/2024 13:21:12 - INFO - __main__ -   Step: 1585, LR: 4.013685887302707e-07, Loss: 0.5602825284004211
2024-08-04T20:21:21.095162811Z 
 28%|██▊       | 1586/5712 [3:43:12<9:42:28,  8.47s/it]08/04/2024 13:21:21 - INFO - __main__ -   Step: 1586, LR: 4.012713100999538e-07, Loss: 0.4540593922138214
2024-08-04T20:21:30.203972495Z 
 28%|██▊       | 1587/5712 [3:43:21<9:55:30,  8.66s/it]08/04/2024 13:21:30 - INFO - __main__ -   Step: 1587, LR: 4.011740314696369e-07, Loss: 0.561642050743103
2024-08-04T20:21:38.723005447Z 
 28%|██▊       | 1588/5712 [3:43:29<9:52:24,  8.62s/it]08/04/2024 13:21:38 - INFO - __main__ -   Step: 1588, LR: 4.0107675283932004e-07, Loss: 0.42786407470703125
2024-08-04T20:21:47.378354942Z 
 28%|██▊       | 1589/5712 [3:43:38<9:53:01,  8.63s/it]08/04/2024 13:21:47 - INFO - __main__ -   Step: 1589, LR: 4.0097947420900314e-07, Loss: 0.5334518551826477
2024-08-04T20:21:55.711070826Z 
 28%|██▊       | 1590/5712 [3:43:46<9:46:44,  8.54s/it]08/04/2024 13:21:55 - INFO - __main__ -   Step: 1590, LR: 4.0088219557868623e-07, Loss: 0.35742607712745667
2024-08-04T20:22:03.789271982Z 
 28%|██▊       | 1591/5712 [3:43:54<9:37:04,  8.40s/it]08/04/2024 13:22:03 - INFO - __main__ -   Step: 1591, LR: 4.0078491694836933e-07, Loss: 0.7443352937698364
2024-08-04T20:22:12.217128877Z 
 28%|██▊       | 1592/5712 [3:44:03<9:37:28,  8.41s/it]08/04/2024 13:22:12 - INFO - __main__ -   Step: 1592, LR: 4.006876383180525e-07, Loss: 0.4241202175617218
2024-08-04T20:22:20.613182701Z 
 28%|██▊       | 1593/5712 [3:44:11<9:37:02,  8.41s/it]08/04/2024 13:22:20 - INFO - __main__ -   Step: 1593, LR: 4.005903596877356e-07, Loss: 0.40420979261398315
2024-08-04T20:22:29.768300646Z 
 28%|██▊       | 1594/5712 [3:44:20<9:52:20,  8.63s/it]08/04/2024 13:22:29 - INFO - __main__ -   Step: 1594, LR: 4.004930810574187e-07, Loss: 0.5282067060470581
2024-08-04T20:22:38.679724671Z 
 28%|██▊       | 1595/5712 [3:44:29<9:57:56,  8.71s/it]08/04/2024 13:22:38 - INFO - __main__ -   Step: 1595, LR: 4.003958024271018e-07, Loss: 0.509063720703125
2024-08-04T20:22:47.157666638Z 
 28%|██▊       | 1596/5712 [3:44:38<9:52:58,  8.64s/it]08/04/2024 13:22:47 - INFO - __main__ -   Step: 1596, LR: 4.0029852379678493e-07, Loss: 0.2718537449836731
2024-08-04T20:22:55.712430103Z 
 28%|██▊       | 1597/5712 [3:44:46<9:50:59,  8.62s/it]08/04/2024 13:22:55 - INFO - __main__ -   Step: 1597, LR: 4.0020124516646803e-07, Loss: 0.528881311416626
2024-08-04T20:23:04.698163873Z 
 28%|██▊       | 1598/5712 [3:44:55<9:58:25,  8.73s/it]08/04/2024 13:23:04 - INFO - __main__ -   Step: 1598, LR: 4.0010396653615113e-07, Loss: 0.41194552183151245
2024-08-04T20:23:12.280989207Z 
 28%|██▊       | 1599/5712 [3:45:03<9:34:43,  8.38s/it]08/04/2024 13:23:12 - INFO - __main__ -   Step: 1599, LR: 4.0000668790583423e-07, Loss: 0.46907883882522583
2024-08-04T20:23:20.516260041Z 
 28%|██▊       | 1600/5712 [3:45:11<9:31:31,  8.34s/it]08/04/2024 13:23:20 - INFO - __main__ -   Step: 1600, LR: 3.999094092755174e-07, Loss: 0.4597998261451721
2024-08-04T20:23:28.834149029Z 
 28%|██▊       | 1601/5712 [3:45:19<9:30:57,  8.33s/it]08/04/2024 13:23:28 - INFO - __main__ -   Step: 1601, LR: 3.998121306452005e-07, Loss: 0.3536412715911865
2024-08-04T20:23:37.042515891Z 
 28%|██▊       | 1602/5712 [3:45:28<9:28:15,  8.30s/it]08/04/2024 13:23:37 - INFO - __main__ -   Step: 1602, LR: 3.997148520148836e-07, Loss: 0.5092437863349915
2024-08-04T20:23:45.407689251Z 
 28%|██▊       | 1603/5712 [3:45:36<9:29:32,  8.32s/it]08/04/2024 13:23:45 - INFO - __main__ -   Step: 1603, LR: 3.9961757338456673e-07, Loss: 0.5423394441604614
2024-08-04T20:23:54.234237131Z 
 28%|██▊       | 1604/5712 [3:45:45<9:39:52,  8.47s/it]08/04/2024 13:23:54 - INFO - __main__ -   Step: 1604, LR: 3.995202947542499e-07, Loss: 0.41397279500961304
2024-08-04T20:24:02.590361916Z 
 28%|██▊       | 1605/5712 [3:45:53<9:37:24,  8.44s/it]08/04/2024 13:24:02 - INFO - __main__ -   Step: 1605, LR: 3.99423016123933e-07, Loss: 0.5155191421508789
2024-08-04T20:24:11.221859747Z 
 28%|██▊       | 1606/5712 [3:46:02<9:41:17,  8.49s/it]08/04/2024 13:24:11 - INFO - __main__ -   Step: 1606, LR: 3.993257374936161e-07, Loss: 0.3130892515182495
2024-08-04T20:24:19.489925942Z 
 28%|██▊       | 1607/5712 [3:46:10<9:36:30,  8.43s/it]08/04/2024 13:24:19 - INFO - __main__ -   Step: 1607, LR: 3.992284588632992e-07, Loss: 0.5121350288391113
2024-08-04T20:24:28.093700124Z 
 28%|██▊       | 1608/5712 [3:46:19<9:40:00,  8.48s/it]08/04/2024 13:24:28 - INFO - __main__ -   Step: 1608, LR: 3.9913118023298233e-07, Loss: 0.46475210785865784
2024-08-04T20:24:36.491374042Z 
 28%|██▊       | 1609/5712 [3:46:27<9:38:11,  8.46s/it]08/04/2024 13:24:36 - INFO - __main__ -   Step: 1609, LR: 3.9903390160266543e-07, Loss: 0.3437001407146454
2024-08-04T20:24:45.206784685Z 
 28%|██▊       | 1610/5712 [3:46:36<9:43:23,  8.53s/it]08/04/2024 13:24:45 - INFO - __main__ -   Step: 1610, LR: 3.9893662297234853e-07, Loss: 0.3951162099838257
2024-08-04T20:24:54.163642890Z 
 28%|██▊       | 1611/5712 [3:46:45<9:51:56,  8.66s/it]08/04/2024 13:24:54 - INFO - __main__ -   Step: 1611, LR: 3.9883934434203163e-07, Loss: 0.4289310872554779
2024-08-04T20:25:03.323044631Z 
 28%|██▊       | 1612/5712 [3:46:54<10:02:00,  8.81s/it]08/04/2024 13:25:03 - INFO - __main__ -   Step: 1612, LR: 3.987420657117148e-07, Loss: 0.49020034074783325
2024-08-04T20:25:11.578571745Z 
 28%|██▊       | 1613/5712 [3:47:02<9:50:30,  8.64s/it] 08/04/2024 13:25:11 - INFO - __main__ -   Step: 1613, LR: 3.986447870813979e-07, Loss: 0.4558716416358948
2024-08-04T20:25:19.783004395Z 
 28%|██▊       | 1614/5712 [3:47:10<9:41:21,  8.51s/it]08/04/2024 13:25:19 - INFO - __main__ -   Step: 1614, LR: 3.98547508451081e-07, Loss: 0.5277255773544312
2024-08-04T20:25:28.045088379Z 
 28%|██▊       | 1615/5712 [3:47:19<9:36:06,  8.44s/it]08/04/2024 13:25:28 - INFO - __main__ -   Step: 1615, LR: 3.984502298207641e-07, Loss: 0.5502753257751465
2024-08-04T20:25:36.206687370Z 
 28%|██▊       | 1616/5712 [3:47:27<9:30:19,  8.35s/it]08/04/2024 13:25:36 - INFO - __main__ -   Step: 1616, LR: 3.983529511904472e-07, Loss: 0.4882928133010864
2024-08-04T20:25:44.765529610Z 
 28%|██▊       | 1617/5712 [3:47:35<9:34:22,  8.42s/it]08/04/2024 13:25:44 - INFO - __main__ -   Step: 1617, LR: 3.9825567256013033e-07, Loss: 0.4910355806350708
2024-08-04T20:25:52.982616919Z 
 28%|██▊       | 1618/5712 [3:47:44<9:30:09,  8.36s/it]08/04/2024 13:25:52 - INFO - __main__ -   Step: 1618, LR: 3.9815839392981343e-07, Loss: 0.5627648830413818
2024-08-04T20:26:01.127723116Z 
 28%|██▊       | 1619/5712 [3:47:52<9:25:42,  8.29s/it]08/04/2024 13:26:01 - INFO - __main__ -   Step: 1619, LR: 3.9806111529949653e-07, Loss: 0.35953062772750854
2024-08-04T20:26:09.718553332Z 
 28%|██▊       | 1620/5712 [3:48:00<9:31:39,  8.38s/it]08/04/2024 13:26:09 - INFO - __main__ -   Step: 1620, LR: 3.9796383666917963e-07, Loss: 0.40373992919921875
2024-08-04T20:26:18.145911036Z 
 28%|██▊       | 1621/5712 [3:48:09<9:32:27,  8.40s/it]08/04/2024 13:26:18 - INFO - __main__ -   Step: 1621, LR: 3.9786655803886283e-07, Loss: 0.3796813488006592
2024-08-04T20:26:26.931425240Z 
 28%|██▊       | 1622/5712 [3:48:18<9:40:16,  8.51s/it]08/04/2024 13:26:26 - INFO - __main__ -   Step: 1622, LR: 3.9776927940854593e-07, Loss: 0.4522516131401062
2024-08-04T20:26:35.006170095Z 
 28%|██▊       | 1623/5712 [3:48:26<9:31:11,  8.38s/it]08/04/2024 13:26:35 - INFO - __main__ -   Step: 1623, LR: 3.9767200077822903e-07, Loss: 0.348815381526947
2024-08-04T20:26:43.453487801Z 
 28%|██▊       | 1624/5712 [3:48:34<9:32:23,  8.40s/it]08/04/2024 13:26:43 - INFO - __main__ -   Step: 1624, LR: 3.9757472214791213e-07, Loss: 0.365764319896698
2024-08-04T20:26:51.884310081Z 
 28%|██▊       | 1625/5712 [3:48:43<9:32:51,  8.41s/it]08/04/2024 13:26:51 - INFO - __main__ -   Step: 1625, LR: 3.974774435175953e-07, Loss: 0.4104406237602234
2024-08-04T20:27:00.183420342Z 
 28%|██▊       | 1626/5712 [3:48:51<9:30:27,  8.38s/it]08/04/2024 13:27:00 - INFO - __main__ -   Step: 1626, LR: 3.973801648872784e-07, Loss: 0.4018302857875824
2024-08-04T20:27:08.400401078Z 
 28%|██▊       | 1627/5712 [3:48:59<9:27:03,  8.33s/it]08/04/2024 13:27:08 - INFO - __main__ -   Step: 1627, LR: 3.972828862569615e-07, Loss: 0.4371700882911682
2024-08-04T20:27:17.102489374Z 
 29%|██▊       | 1628/5712 [3:49:08<9:34:32,  8.44s/it]08/04/2024 13:27:17 - INFO - __main__ -   Step: 1628, LR: 3.971856076266446e-07, Loss: 0.5637667775154114
2024-08-04T20:27:25.735976683Z 
 29%|██▊       | 1629/5712 [3:49:16<9:38:18,  8.50s/it]08/04/2024 13:27:25 - INFO - __main__ -   Step: 1629, LR: 3.9708832899632773e-07, Loss: 0.38933366537094116
2024-08-04T20:27:34.023849093Z 
 29%|██▊       | 1630/5712 [3:49:25<9:33:53,  8.44s/it]08/04/2024 13:27:34 - INFO - __main__ -   Step: 1630, LR: 3.9699105036601083e-07, Loss: 0.6487078070640564
2024-08-04T20:27:42.777272703Z 
 29%|██▊       | 1631/5712 [3:49:33<9:40:14,  8.53s/it]08/04/2024 13:27:42 - INFO - __main__ -   Step: 1631, LR: 3.9689377173569393e-07, Loss: 0.3513079881668091
2024-08-04T20:27:51.176937608Z 
 29%|██▊       | 1632/5712 [3:49:42<9:37:25,  8.49s/it]08/04/2024 13:27:51 - INFO - __main__ -   Step: 1632, LR: 3.9679649310537703e-07, Loss: 0.3945481777191162
2024-08-04T20:27:59.531983985Z 
 29%|██▊       | 1633/5712 [3:49:50<9:34:29,  8.45s/it]08/04/2024 13:27:59 - INFO - __main__ -   Step: 1633, LR: 3.966992144750602e-07, Loss: 0.5974397659301758
2024-08-04T20:28:07.763517606Z 
 29%|██▊       | 1634/5712 [3:49:58<9:29:53,  8.38s/it]08/04/2024 13:28:07 - INFO - __main__ -   Step: 1634, LR: 3.966019358447433e-07, Loss: 0.48111510276794434
2024-08-04T20:28:16.399739783Z 
 29%|██▊       | 1635/5712 [3:50:07<9:34:52,  8.46s/it]08/04/2024 13:28:16 - INFO - __main__ -   Step: 1635, LR: 3.965046572144264e-07, Loss: 0.37746208906173706
2024-08-04T20:28:25.159210086Z 
 29%|██▊       | 1636/5712 [3:50:16<9:40:49,  8.55s/it]08/04/2024 13:28:25 - INFO - __main__ -   Step: 1636, LR: 3.964073785841095e-07, Loss: 0.421048641204834
2024-08-04T20:28:33.807012121Z 
 29%|██▊       | 1637/5712 [3:50:24<9:42:40,  8.58s/it]08/04/2024 13:28:33 - INFO - __main__ -   Step: 1637, LR: 3.9631009995379263e-07, Loss: 0.5708435773849487
2024-08-04T20:28:42.120334959Z 
 29%|██▊       | 1638/5712 [3:50:33<9:37:07,  8.50s/it]08/04/2024 13:28:42 - INFO - __main__ -   Step: 1638, LR: 3.9621282132347573e-07, Loss: 0.38347965478897095
2024-08-04T20:28:50.568979968Z 
 29%|██▊       | 1639/5712 [3:50:41<9:35:56,  8.48s/it]08/04/2024 13:28:50 - INFO - __main__ -   Step: 1639, LR: 3.961155426931589e-07, Loss: 0.4850011169910431
2024-08-04T20:28:59.595177378Z 
 29%|██▊       | 1640/5712 [3:50:50<9:46:50,  8.65s/it]08/04/2024 13:28:59 - INFO - __main__ -   Step: 1640, LR: 3.96018264062842e-07, Loss: 0.4546769857406616
2024-08-04T20:29:08.600459245Z 
 29%|██▊       | 1641/5712 [3:50:59<9:53:58,  8.75s/it]08/04/2024 13:29:08 - INFO - __main__ -   Step: 1641, LR: 3.9592098543252513e-07, Loss: 0.49387428164482117
2024-08-04T20:29:16.641480105Z 
 29%|██▊       | 1642/5712 [3:51:07<9:39:19,  8.54s/it]08/04/2024 13:29:16 - INFO - __main__ -   Step: 1642, LR: 3.9582370680220823e-07, Loss: 0.44821256399154663
2024-08-04T20:29:25.725961303Z 
 29%|██▉       | 1643/5712 [3:51:16<9:50:15,  8.70s/it]08/04/2024 13:29:25 - INFO - __main__ -   Step: 1643, LR: 3.9572642817189133e-07, Loss: 0.4931752383708954
2024-08-04T20:29:33.784117707Z 
 29%|██▉       | 1644/5712 [3:51:24<9:36:58,  8.51s/it]08/04/2024 13:29:33 - INFO - __main__ -   Step: 1644, LR: 3.9562914954157443e-07, Loss: 0.5222876071929932
2024-08-04T20:29:42.707018443Z 
 29%|██▉       | 1645/5712 [3:51:33<9:45:13,  8.63s/it]08/04/2024 13:29:42 - INFO - __main__ -   Step: 1645, LR: 3.955318709112576e-07, Loss: 0.41450074315071106
2024-08-04T20:29:51.559431530Z 
 29%|██▉       | 1646/5712 [3:51:42<9:49:29,  8.70s/it]08/04/2024 13:29:51 - INFO - __main__ -   Step: 1646, LR: 3.954345922809407e-07, Loss: 0.5315996408462524
2024-08-04T20:30:00.260283709Z 
 29%|██▉       | 1647/5712 [3:51:51<9:49:25,  8.70s/it]08/04/2024 13:30:00 - INFO - __main__ -   Step: 1647, LR: 3.953373136506238e-07, Loss: 0.38098713755607605
2024-08-04T20:30:08.518035403Z 
 29%|██▉       | 1648/5712 [3:51:59<9:40:17,  8.57s/it]08/04/2024 13:30:08 - INFO - __main__ -   Step: 1648, LR: 3.952400350203069e-07, Loss: 0.4629509747028351
2024-08-04T20:30:16.972500877Z 
 29%|██▉       | 1649/5712 [3:52:08<9:37:51,  8.53s/it]08/04/2024 13:30:16 - INFO - __main__ -   Step: 1649, LR: 3.9514275638999003e-07, Loss: 0.5310045480728149
2024-08-04T20:30:25.544984413Z 
 29%|██▉       | 1650/5712 [3:52:16<9:38:30,  8.55s/it]08/04/2024 13:30:25 - INFO - __main__ -   Step: 1650, LR: 3.9504547775967313e-07, Loss: 0.5585455894470215
2024-08-04T20:30:33.872474311Z 
 29%|██▉       | 1651/5712 [3:52:25<9:33:56,  8.48s/it]08/04/2024 13:30:33 - INFO - __main__ -   Step: 1651, LR: 3.9494819912935623e-07, Loss: 0.4841310679912567
2024-08-04T20:30:42.067264191Z 
 29%|██▉       | 1652/5712 [3:52:33<9:28:01,  8.39s/it]08/04/2024 13:30:42 - INFO - __main__ -   Step: 1652, LR: 3.9485092049903933e-07, Loss: 0.5296535491943359
2024-08-04T20:30:51.339776538Z 
 29%|██▉       | 1653/5712 [3:52:42<9:45:41,  8.66s/it]08/04/2024 13:30:51 - INFO - __main__ -   Step: 1653, LR: 3.9475364186872243e-07, Loss: 0.5043636560440063
2024-08-04T20:30:59.810565989Z 
 29%|██▉       | 1654/5712 [3:52:50<9:41:45,  8.60s/it]08/04/2024 13:30:59 - INFO - __main__ -   Step: 1654, LR: 3.946563632384056e-07, Loss: 0.4380631744861603
2024-08-04T20:31:08.387063727Z 
 29%|██▉       | 1655/5712 [3:52:59<9:41:06,  8.59s/it]08/04/2024 13:31:08 - INFO - __main__ -   Step: 1655, LR: 3.945590846080887e-07, Loss: 0.4247840642929077
2024-08-04T20:31:16.585172456Z 
 29%|██▉       | 1656/5712 [3:53:07<9:32:55,  8.48s/it]08/04/2024 13:31:16 - INFO - __main__ -   Step: 1656, LR: 3.944618059777718e-07, Loss: 0.5075296759605408
2024-08-04T20:31:24.912706778Z 
 29%|██▉       | 1657/5712 [3:53:16<9:29:47,  8.43s/it]08/04/2024 13:31:24 - INFO - __main__ -   Step: 1657, LR: 3.94364527347455e-07, Loss: 0.4027748703956604
2024-08-04T20:31:33.558529215Z 
 29%|██▉       | 1658/5712 [3:53:24<9:34:00,  8.50s/it]08/04/2024 13:31:33 - INFO - __main__ -   Step: 1658, LR: 3.942672487171381e-07, Loss: 0.3205803334712982
2024-08-04T20:31:41.795296064Z 
 29%|██▉       | 1659/5712 [3:53:32<9:28:37,  8.42s/it]08/04/2024 13:31:41 - INFO - __main__ -   Step: 1659, LR: 3.941699700868212e-07, Loss: 0.41319823265075684
2024-08-04T20:31:50.029985883Z 
 29%|██▉       | 1660/5712 [3:53:41<9:24:46,  8.36s/it]08/04/2024 13:31:50 - INFO - __main__ -   Step: 1660, LR: 3.940726914565043e-07, Loss: 0.4761565923690796
2024-08-04T20:31:58.777388690Z 
 29%|██▉       | 1661/5712 [3:53:49<9:32:25,  8.48s/it]08/04/2024 13:31:58 - INFO - __main__ -   Step: 1661, LR: 3.939754128261874e-07, Loss: 0.35632920265197754
2024-08-04T20:32:06.858883476Z 
 29%|██▉       | 1662/5712 [3:53:58<9:24:15,  8.36s/it]08/04/2024 13:32:06 - INFO - __main__ -   Step: 1662, LR: 3.9387813419587053e-07, Loss: 0.6402902603149414
2024-08-04T20:32:15.539907138Z 
 29%|██▉       | 1663/5712 [3:54:06<9:30:35,  8.46s/it]08/04/2024 13:32:15 - INFO - __main__ -   Step: 1663, LR: 3.9378085556555363e-07, Loss: 0.38251012563705444
2024-08-04T20:32:23.801895344Z 
 29%|██▉       | 1664/5712 [3:54:14<9:26:33,  8.40s/it]08/04/2024 13:32:23 - INFO - __main__ -   Step: 1664, LR: 3.9368357693523673e-07, Loss: 0.40534707903862
2024-08-04T20:32:32.348034400Z 
 29%|██▉       | 1665/5712 [3:54:23<9:29:26,  8.44s/it]08/04/2024 13:32:32 - INFO - __main__ -   Step: 1665, LR: 3.9358629830491983e-07, Loss: 0.4301159679889679
2024-08-04T20:32:40.966064161Z 
 29%|██▉       | 1666/5712 [3:54:32<9:32:51,  8.50s/it]08/04/2024 13:32:40 - INFO - __main__ -   Step: 1666, LR: 3.93489019674603e-07, Loss: 0.4136395752429962
2024-08-04T20:32:49.028348637Z 
 29%|██▉       | 1667/5712 [3:54:40<9:23:56,  8.37s/it]08/04/2024 13:32:49 - INFO - __main__ -   Step: 1667, LR: 3.933917410442861e-07, Loss: 0.5019915699958801
2024-08-04T20:32:57.266245256Z 
 29%|██▉       | 1668/5712 [3:54:48<9:21:14,  8.33s/it]08/04/2024 13:32:57 - INFO - __main__ -   Step: 1668, LR: 3.932944624139692e-07, Loss: 0.4486168622970581
2024-08-04T20:33:06.484944247Z 
 29%|██▉       | 1669/5712 [3:54:57<9:39:07,  8.59s/it]08/04/2024 13:33:06 - INFO - __main__ -   Step: 1669, LR: 3.931971837836523e-07, Loss: 0.4697216749191284
2024-08-04T20:33:15.232315154Z 
 29%|██▉       | 1670/5712 [3:55:06<9:42:04,  8.64s/it]08/04/2024 13:33:15 - INFO - __main__ -   Step: 1670, LR: 3.9309990515333543e-07, Loss: 0.44838809967041016
2024-08-04T20:33:23.664228232Z 
 29%|██▉       | 1671/5712 [3:55:14<9:37:42,  8.58s/it]08/04/2024 13:33:23 - INFO - __main__ -   Step: 1671, LR: 3.9300262652301853e-07, Loss: 0.3974345326423645
2024-08-04T20:33:31.998171985Z 
 29%|██▉       | 1672/5712 [3:55:23<9:32:38,  8.50s/it]08/04/2024 13:33:31 - INFO - __main__ -   Step: 1672, LR: 3.9290534789270163e-07, Loss: 0.4649760127067566
2024-08-04T20:33:40.338041364Z 
 29%|██▉       | 1673/5712 [3:55:31<9:29:10,  8.46s/it]08/04/2024 13:33:40 - INFO - __main__ -   Step: 1673, LR: 3.928080692623847e-07, Loss: 0.4261101484298706
2024-08-04T20:33:48.670058537Z 
 29%|██▉       | 1674/5712 [3:55:39<9:26:33,  8.42s/it]08/04/2024 13:33:48 - INFO - __main__ -   Step: 1674, LR: 3.927107906320679e-07, Loss: 0.5429715514183044
2024-08-04T20:33:57.326397863Z 
 29%|██▉       | 1675/5712 [3:55:48<9:31:12,  8.49s/it]08/04/2024 13:33:57 - INFO - __main__ -   Step: 1675, LR: 3.9261351200175103e-07, Loss: 0.7186638116836548
2024-08-04T20:34:05.586007594Z 
 29%|██▉       | 1676/5712 [3:55:56<9:26:25,  8.42s/it]08/04/2024 13:34:05 - INFO - __main__ -   Step: 1676, LR: 3.9251623337143413e-07, Loss: 0.464421808719635
2024-08-04T20:34:13.852409108Z 
 29%|██▉       | 1677/5712 [3:56:04<9:23:10,  8.37s/it]08/04/2024 13:34:13 - INFO - __main__ -   Step: 1677, LR: 3.9241895474111723e-07, Loss: 0.40927955508232117
2024-08-04T20:34:22.273118035Z 
 29%|██▉       | 1678/5712 [3:56:13<9:23:58,  8.39s/it]08/04/2024 13:34:22 - INFO - __main__ -   Step: 1678, LR: 3.923216761108004e-07, Loss: 0.4257625937461853
2024-08-04T20:34:30.987354805Z 
 29%|██▉       | 1679/5712 [3:56:22<9:30:22,  8.49s/it]08/04/2024 13:34:30 - INFO - __main__ -   Step: 1679, LR: 3.922243974804835e-07, Loss: 0.5733299255371094
2024-08-04T20:34:39.863785558Z 
 29%|██▉       | 1680/5712 [3:56:31<9:38:06,  8.60s/it]08/04/2024 13:34:39 - INFO - __main__ -   Step: 1680, LR: 3.921271188501666e-07, Loss: 0.5938208103179932
2024-08-04T20:34:48.268468816Z 
 29%|██▉       | 1681/5712 [3:56:39<9:34:00,  8.54s/it]08/04/2024 13:34:48 - INFO - __main__ -   Step: 1681, LR: 3.920298402198497e-07, Loss: 0.467143714427948
2024-08-04T20:34:56.498086106Z 
 29%|██▉       | 1682/5712 [3:56:47<9:27:31,  8.45s/it]08/04/2024 13:34:56 - INFO - __main__ -   Step: 1682, LR: 3.9193256158953283e-07, Loss: 0.38661015033721924
2024-08-04T20:35:05.110938788Z 
 29%|██▉       | 1683/5712 [3:56:56<9:30:40,  8.50s/it]08/04/2024 13:35:05 - INFO - __main__ -   Step: 1683, LR: 3.9183528295921593e-07, Loss: 0.5695636868476868
2024-08-04T20:35:13.662512946Z 
 29%|██▉       | 1684/5712 [3:57:04<9:31:36,  8.51s/it]08/04/2024 13:35:13 - INFO - __main__ -   Step: 1684, LR: 3.9173800432889903e-07, Loss: 0.40617525577545166
2024-08-04T20:35:22.131660719Z 
 29%|██▉       | 1685/5712 [3:57:13<9:30:32,  8.50s/it]08/04/2024 13:35:22 - INFO - __main__ -   Step: 1685, LR: 3.916407256985821e-07, Loss: 0.4078672528266907
2024-08-04T20:35:30.543545425Z 
 30%|██▉       | 1686/5712 [3:57:21<9:28:37,  8.47s/it]08/04/2024 13:35:30 - INFO - __main__ -   Step: 1686, LR: 3.915434470682653e-07, Loss: 0.44202619791030884
2024-08-04T20:35:39.108033605Z 
 30%|██▉       | 1687/5712 [3:57:30<9:30:17,  8.50s/it]08/04/2024 13:35:39 - INFO - __main__ -   Step: 1687, LR: 3.914461684379484e-07, Loss: 0.45745357871055603
2024-08-04T20:35:48.336192311Z 
 30%|██▉       | 1688/5712 [3:57:39<9:44:46,  8.72s/it]08/04/2024 13:35:48 - INFO - __main__ -   Step: 1688, LR: 3.913488898076315e-07, Loss: 0.3854818344116211
2024-08-04T20:35:56.935195299Z 
 30%|██▉       | 1689/5712 [3:57:48<9:42:12,  8.68s/it]08/04/2024 13:35:56 - INFO - __main__ -   Step: 1689, LR: 3.912516111773146e-07, Loss: 0.3297371566295624
2024-08-04T20:36:04.952022824Z 
 30%|██▉       | 1690/5712 [3:57:56<9:28:40,  8.48s/it]08/04/2024 13:36:04 - INFO - __main__ -   Step: 1690, LR: 3.911543325469977e-07, Loss: 0.5332331657409668
2024-08-04T20:36:13.946038908Z 
 30%|██▉       | 1691/5712 [3:58:05<9:38:47,  8.64s/it]08/04/2024 13:36:13 - INFO - __main__ -   Step: 1691, LR: 3.910570539166808e-07, Loss: 0.502192497253418
2024-08-04T20:36:22.651487204Z 
 30%|██▉       | 1692/5712 [3:58:13<9:40:01,  8.66s/it]08/04/2024 13:36:22 - INFO - __main__ -   Step: 1692, LR: 3.909597752863639e-07, Loss: 0.32567381858825684
2024-08-04T20:36:30.964608363Z 
 30%|██▉       | 1693/5712 [3:58:22<9:32:58,  8.55s/it]08/04/2024 13:36:30 - INFO - __main__ -   Step: 1693, LR: 3.908624966560471e-07, Loss: 0.27111944556236267
2024-08-04T20:36:39.441804597Z 
 30%|██▉       | 1694/5712 [3:58:30<9:31:17,  8.53s/it]08/04/2024 13:36:39 - INFO - __main__ -   Step: 1694, LR: 3.9076521802573023e-07, Loss: 0.553472101688385
2024-08-04T20:36:47.526879799Z 
 30%|██▉       | 1695/5712 [3:58:38<9:22:11,  8.40s/it]08/04/2024 13:36:47 - INFO - __main__ -   Step: 1695, LR: 3.9066793939541333e-07, Loss: 0.6652116775512695
2024-08-04T20:36:56.236643592Z 
 30%|██▉       | 1696/5712 [3:58:47<9:28:19,  8.49s/it]08/04/2024 13:36:56 - INFO - __main__ -   Step: 1696, LR: 3.9057066076509643e-07, Loss: 0.45494696497917175
2024-08-04T20:37:05.240572461Z 
 30%|██▉       | 1697/5712 [3:58:56<9:38:28,  8.64s/it]08/04/2024 13:37:05 - INFO - __main__ -   Step: 1697, LR: 3.904733821347795e-07, Loss: 0.5186598300933838
2024-08-04T20:37:14.115966427Z 
 30%|██▉       | 1698/5712 [3:59:05<9:42:58,  8.71s/it]08/04/2024 13:37:14 - INFO - __main__ -   Step: 1698, LR: 3.903761035044626e-07, Loss: 0.32727670669555664
2024-08-04T20:37:22.431673170Z 
 30%|██▉       | 1699/5712 [3:59:13<9:34:49,  8.59s/it]08/04/2024 13:37:22 - INFO - __main__ -   Step: 1699, LR: 3.902788248741458e-07, Loss: 0.25568532943725586
2024-08-04T20:37:30.874849870Z 
 30%|██▉       | 1700/5712 [3:59:22<9:31:39,  8.55s/it]08/04/2024 13:37:30 - INFO - __main__ -   Step: 1700, LR: 3.901815462438289e-07, Loss: 0.34522566199302673
2024-08-04T20:37:39.182486943Z 
 30%|██▉       | 1701/5712 [3:59:30<9:26:39,  8.48s/it]08/04/2024 13:37:39 - INFO - __main__ -   Step: 1701, LR: 3.90084267613512e-07, Loss: 0.45923495292663574
2024-08-04T20:37:48.105640543Z 
 30%|██▉       | 1702/5712 [3:59:39<9:35:28,  8.61s/it]08/04/2024 13:37:48 - INFO - __main__ -   Step: 1702, LR: 3.899869889831951e-07, Loss: 0.369329035282135
2024-08-04T20:37:56.155461174Z 
 30%|██▉       | 1703/5712 [3:59:47<9:24:05,  8.44s/it]08/04/2024 13:37:56 - INFO - __main__ -   Step: 1703, LR: 3.8988971035287823e-07, Loss: 0.5760840177536011
2024-08-04T20:38:04.429765733Z 
 30%|██▉       | 1704/5712 [3:59:55<9:20:35,  8.39s/it]08/04/2024 13:38:04 - INFO - __main__ -   Step: 1704, LR: 3.897924317225613e-07, Loss: 0.5180075168609619
2024-08-04T20:38:12.978439331Z 
 30%|██▉       | 1705/5712 [4:00:04<9:23:34,  8.44s/it]08/04/2024 13:38:12 - INFO - __main__ -   Step: 1705, LR: 3.896951530922444e-07, Loss: 0.42310112714767456
2024-08-04T20:38:21.461494131Z 
 30%|██▉       | 1706/5712 [4:00:12<9:24:19,  8.45s/it]08/04/2024 13:38:21 - INFO - __main__ -   Step: 1706, LR: 3.895978744619275e-07, Loss: 0.23582567274570465
2024-08-04T20:38:29.591344763Z 
 30%|██▉       | 1707/5712 [4:00:20<9:17:44,  8.36s/it]08/04/2024 13:38:29 - INFO - __main__ -   Step: 1707, LR: 3.895005958316107e-07, Loss: 0.3983592987060547
2024-08-04T20:38:38.059899973Z 
 30%|██▉       | 1708/5712 [4:00:29<9:19:51,  8.39s/it]08/04/2024 13:38:38 - INFO - __main__ -   Step: 1708, LR: 3.894033172012938e-07, Loss: 0.3922826647758484
2024-08-04T20:38:46.183215831Z 
 30%|██▉       | 1709/5712 [4:00:37<9:14:23,  8.31s/it]08/04/2024 13:38:46 - INFO - __main__ -   Step: 1709, LR: 3.893060385709769e-07, Loss: 0.5165262222290039
2024-08-04T20:38:55.537295889Z 
 30%|██▉       | 1710/5712 [4:00:46<9:35:09,  8.62s/it]08/04/2024 13:38:55 - INFO - __main__ -   Step: 1710, LR: 3.8920875994065997e-07, Loss: 0.4372158348560333
2024-08-04T20:39:04.363866712Z 
 30%|██▉       | 1711/5712 [4:00:55<9:39:04,  8.68s/it]08/04/2024 13:39:04 - INFO - __main__ -   Step: 1711, LR: 3.891114813103432e-07, Loss: 0.5204850435256958
2024-08-04T20:39:12.625239178Z 
 30%|██▉       | 1712/5712 [4:01:03<9:30:28,  8.56s/it]08/04/2024 13:39:12 - INFO - __main__ -   Step: 1712, LR: 3.890142026800263e-07, Loss: 0.47212183475494385
2024-08-04T20:39:21.054879554Z 
 30%|██▉       | 1713/5712 [4:01:12<9:27:47,  8.52s/it]08/04/2024 13:39:21 - INFO - __main__ -   Step: 1713, LR: 3.889169240497094e-07, Loss: 0.4932882785797119
2024-08-04T20:39:29.731676048Z 
 30%|███       | 1714/5712 [4:01:20<9:30:44,  8.57s/it]08/04/2024 13:39:29 - INFO - __main__ -   Step: 1714, LR: 3.888196454193925e-07, Loss: 0.3395712971687317
2024-08-04T20:39:38.370684838Z 
 30%|███       | 1715/5712 [4:01:29<9:32:07,  8.59s/it]08/04/2024 13:39:38 - INFO - __main__ -   Step: 1715, LR: 3.8872236678907563e-07, Loss: 0.5225158333778381
2024-08-04T20:39:47.223935881Z 
 30%|███       | 1716/5712 [4:01:38<9:37:16,  8.67s/it]08/04/2024 13:39:47 - INFO - __main__ -   Step: 1716, LR: 3.886250881587587e-07, Loss: 0.3908744156360626
2024-08-04T20:39:55.499326836Z 
 30%|███       | 1717/5712 [4:01:46<9:29:17,  8.55s/it]08/04/2024 13:39:55 - INFO - __main__ -   Step: 1717, LR: 3.885278095284418e-07, Loss: 0.5485193729400635
2024-08-04T20:40:03.604101212Z 
 30%|███       | 1718/5712 [4:01:54<9:20:15,  8.42s/it]08/04/2024 13:40:03 - INFO - __main__ -   Step: 1718, LR: 3.884305308981249e-07, Loss: 0.515190839767456
2024-08-04T20:40:11.964914332Z 
 30%|███       | 1719/5712 [4:02:03<9:19:00,  8.40s/it]08/04/2024 13:40:11 - INFO - __main__ -   Step: 1719, LR: 3.883332522678081e-07, Loss: 0.5051310062408447
2024-08-04T20:40:20.842413123Z 
 30%|███       | 1720/5712 [4:02:11<9:28:23,  8.54s/it]08/04/2024 13:40:20 - INFO - __main__ -   Step: 1720, LR: 3.882359736374912e-07, Loss: 0.6777635216712952
2024-08-04T20:40:29.043662266Z 
 30%|███       | 1721/5712 [4:02:20<9:21:26,  8.44s/it]08/04/2024 13:40:29 - INFO - __main__ -   Step: 1721, LR: 3.881386950071743e-07, Loss: 0.4428384602069855
2024-08-04T20:40:37.543381162Z 
 30%|███       | 1722/5712 [4:02:28<9:22:28,  8.46s/it]08/04/2024 13:40:37 - INFO - __main__ -   Step: 1722, LR: 3.8804141637685737e-07, Loss: 0.25016671419143677
2024-08-04T20:40:46.225818502Z 
 30%|███       | 1723/5712 [4:02:37<9:26:48,  8.53s/it]08/04/2024 13:40:46 - INFO - __main__ -   Step: 1723, LR: 3.879441377465405e-07, Loss: 0.4638242721557617
2024-08-04T20:40:54.519060155Z 
 30%|███       | 1724/5712 [4:02:45<9:22:01,  8.46s/it]08/04/2024 13:40:54 - INFO - __main__ -   Step: 1724, LR: 3.878468591162236e-07, Loss: 0.6350066661834717
2024-08-04T20:41:03.112209981Z 
 30%|███       | 1725/5712 [4:02:54<9:24:37,  8.50s/it]08/04/2024 13:41:03 - INFO - __main__ -   Step: 1725, LR: 3.877495804859067e-07, Loss: 0.4194624722003937
2024-08-04T20:41:11.546649947Z 
 30%|███       | 1726/5712 [4:03:02<9:23:14,  8.48s/it]08/04/2024 13:41:11 - INFO - __main__ -   Step: 1726, LR: 3.876523018555898e-07, Loss: 0.5552204251289368
2024-08-04T20:41:20.326197562Z 
 30%|███       | 1727/5712 [4:03:11<9:29:04,  8.57s/it]08/04/2024 13:41:20 - INFO - __main__ -   Step: 1727, LR: 3.87555023225273e-07, Loss: 0.41554325819015503
2024-08-04T20:41:28.825126961Z 
 30%|███       | 1728/5712 [4:03:19<9:27:34,  8.55s/it]08/04/2024 13:41:28 - INFO - __main__ -   Step: 1728, LR: 3.8745774459495607e-07, Loss: 0.3676612973213196
2024-08-04T20:41:37.142372008Z 
 30%|███       | 1729/5712 [4:03:28<9:22:50,  8.48s/it]08/04/2024 13:41:37 - INFO - __main__ -   Step: 1729, LR: 3.873604659646392e-07, Loss: 0.46484628319740295
2024-08-04T20:41:45.949944806Z 
 30%|███       | 1730/5712 [4:03:37<9:29:15,  8.58s/it]08/04/2024 13:41:45 - INFO - __main__ -   Step: 1730, LR: 3.872631873343223e-07, Loss: 0.2325107753276825
2024-08-04T20:41:54.613643184Z 
 30%|███       | 1731/5712 [4:03:45<9:30:47,  8.60s/it]08/04/2024 13:41:54 - INFO - __main__ -   Step: 1731, LR: 3.871659087040055e-07, Loss: 0.5669807195663452
2024-08-04T20:42:03.288988088Z 
 30%|███       | 1732/5712 [4:03:54<9:32:07,  8.63s/it]08/04/2024 13:42:03 - INFO - __main__ -   Step: 1732, LR: 3.870686300736886e-07, Loss: 0.4307456910610199
2024-08-04T20:42:12.063612872Z 
 30%|███       | 1733/5712 [4:04:03<9:34:57,  8.67s/it]08/04/2024 13:42:12 - INFO - __main__ -   Step: 1733, LR: 3.869713514433717e-07, Loss: 0.4979579448699951
2024-08-04T20:42:20.289196508Z 
 30%|███       | 1734/5712 [4:04:11<9:25:58,  8.54s/it]08/04/2024 13:42:20 - INFO - __main__ -   Step: 1734, LR: 3.8687407281305477e-07, Loss: 0.39547228813171387
2024-08-04T20:42:29.309166804Z 
 30%|███       | 1735/5712 [4:04:20<9:35:26,  8.68s/it]08/04/2024 13:42:29 - INFO - __main__ -   Step: 1735, LR: 3.8677679418273787e-07, Loss: 0.47394898533821106
2024-08-04T20:42:37.732684588Z 
 30%|███       | 1736/5712 [4:04:28<9:30:10,  8.60s/it]08/04/2024 13:42:37 - INFO - __main__ -   Step: 1736, LR: 3.86679515552421e-07, Loss: 0.4788399338722229
2024-08-04T20:42:46.154695396Z 
 30%|███       | 1737/5712 [4:04:37<9:26:24,  8.55s/it]08/04/2024 13:42:46 - INFO - __main__ -   Step: 1737, LR: 3.865822369221041e-07, Loss: 0.4565478563308716
2024-08-04T20:42:54.469856806Z 
 30%|███       | 1738/5712 [4:04:45<9:21:36,  8.48s/it]08/04/2024 13:42:54 - INFO - __main__ -   Step: 1738, LR: 3.864849582917872e-07, Loss: 0.6841663122177124
2024-08-04T20:43:03.655242458Z 
 30%|███       | 1739/5712 [4:04:54<9:35:29,  8.69s/it]08/04/2024 13:43:03 - INFO - __main__ -   Step: 1739, LR: 3.863876796614703e-07, Loss: 0.37328529357910156
2024-08-04T20:43:11.571362785Z 
 30%|███       | 1740/5712 [4:05:02<9:19:57,  8.46s/it]08/04/2024 13:43:11 - INFO - __main__ -   Step: 1740, LR: 3.862904010311535e-07, Loss: 0.7010242938995361
2024-08-04T20:43:20.271468467Z 
 30%|███       | 1741/5712 [4:05:11<9:24:36,  8.53s/it]08/04/2024 13:43:20 - INFO - __main__ -   Step: 1741, LR: 3.8619312240083657e-07, Loss: 0.31031352281570435
2024-08-04T20:43:28.508059299Z 
 30%|███       | 1742/5712 [4:05:19<9:18:37,  8.44s/it]08/04/2024 13:43:28 - INFO - __main__ -   Step: 1742, LR: 3.8609584377051967e-07, Loss: 0.5576202273368835
2024-08-04T20:43:37.425249647Z 
 31%|███       | 1743/5712 [4:05:28<9:27:53,  8.58s/it]08/04/2024 13:43:37 - INFO - __main__ -   Step: 1743, LR: 3.8599856514020277e-07, Loss: 0.38227564096450806
2024-08-04T20:43:46.447016172Z 
 31%|███       | 1744/5712 [4:05:37<9:36:25,  8.72s/it]08/04/2024 13:43:46 - INFO - __main__ -   Step: 1744, LR: 3.859012865098859e-07, Loss: 0.5698205232620239
2024-08-04T20:43:55.314747412Z 
 31%|███       | 1745/5712 [4:05:46<9:39:17,  8.76s/it]08/04/2024 13:43:55 - INFO - __main__ -   Step: 1745, LR: 3.85804007879569e-07, Loss: 0.5016617178916931
2024-08-04T20:44:03.830951020Z 
 31%|███       | 1746/5712 [4:05:54<9:34:16,  8.69s/it]08/04/2024 13:44:03 - INFO - __main__ -   Step: 1746, LR: 3.857067292492521e-07, Loss: 0.36240294575691223
2024-08-04T20:44:12.467420522Z 
 31%|███       | 1747/5712 [4:06:03<9:33:06,  8.67s/it]08/04/2024 13:44:12 - INFO - __main__ -   Step: 1747, LR: 3.8560945061893527e-07, Loss: 0.5109128355979919
2024-08-04T20:44:21.385738958Z 
 31%|███       | 1748/5712 [4:06:12<9:37:49,  8.75s/it]08/04/2024 13:44:21 - INFO - __main__ -   Step: 1748, LR: 3.855121719886184e-07, Loss: 0.5184873342514038
2024-08-04T20:44:29.843316008Z 
 31%|███       | 1749/5712 [4:06:20<9:31:58,  8.66s/it]08/04/2024 13:44:29 - INFO - __main__ -   Step: 1749, LR: 3.854148933583015e-07, Loss: 0.3384994864463806
2024-08-04T20:44:38.372535986Z 
 31%|███       | 1750/5712 [4:06:29<9:29:14,  8.62s/it]08/04/2024 13:44:38 - INFO - __main__ -   Step: 1750, LR: 3.853176147279846e-07, Loss: 0.42973315715789795
2024-08-04T20:44:46.774803716Z 
 31%|███       | 1751/5712 [4:06:37<9:24:46,  8.56s/it]08/04/2024 13:44:46 - INFO - __main__ -   Step: 1751, LR: 3.852203360976677e-07, Loss: 0.40990713238716125
2024-08-04T20:44:55.124337020Z 
 31%|███       | 1752/5712 [4:06:46<9:20:34,  8.49s/it]08/04/2024 13:44:55 - INFO - __main__ -   Step: 1752, LR: 3.851230574673509e-07, Loss: 0.3703499436378479
2024-08-04T20:45:03.465919122Z 
 31%|███       | 1753/5712 [4:06:54<9:17:24,  8.45s/it]08/04/2024 13:45:03 - INFO - __main__ -   Step: 1753, LR: 3.8502577883703397e-07, Loss: 0.4544873535633087
2024-08-04T20:45:11.672692581Z 
 31%|███       | 1754/5712 [4:07:02<9:12:30,  8.38s/it]08/04/2024 13:45:11 - INFO - __main__ -   Step: 1754, LR: 3.8492850020671707e-07, Loss: 0.42043617367744446
2024-08-04T20:45:20.014098605Z 
 31%|███       | 1755/5712 [4:07:11<9:11:41,  8.37s/it]08/04/2024 13:45:20 - INFO - __main__ -   Step: 1755, LR: 3.8483122157640017e-07, Loss: 0.42304420471191406
2024-08-04T20:45:28.858345004Z 
 31%|███       | 1756/5712 [4:07:20<9:21:01,  8.51s/it]08/04/2024 13:45:28 - INFO - __main__ -   Step: 1756, LR: 3.847339429460833e-07, Loss: 0.5632600784301758
2024-08-04T20:45:36.905111841Z 
 31%|███       | 1757/5712 [4:07:28<9:11:44,  8.37s/it]08/04/2024 13:45:36 - INFO - __main__ -   Step: 1757, LR: 3.846366643157664e-07, Loss: 0.4829936623573303
2024-08-04T20:45:45.400186872Z 
 31%|███       | 1758/5712 [4:07:36<9:14:04,  8.41s/it]08/04/2024 13:45:45 - INFO - __main__ -   Step: 1758, LR: 3.845393856854495e-07, Loss: 0.4669373631477356
2024-08-04T20:45:54.406518137Z 
 31%|███       | 1759/5712 [4:07:45<9:25:45,  8.59s/it]08/04/2024 13:45:54 - INFO - __main__ -   Step: 1759, LR: 3.844421070551326e-07, Loss: 0.4049301743507385
2024-08-04T20:46:02.746814040Z 
 31%|███       | 1760/5712 [4:07:53<9:20:44,  8.51s/it]08/04/2024 13:46:02 - INFO - __main__ -   Step: 1760, LR: 3.8434482842481577e-07, Loss: 0.3297666907310486
2024-08-04T20:46:11.631182841Z 
 31%|███       | 1761/5712 [4:08:02<9:27:55,  8.62s/it]08/04/2024 13:46:11 - INFO - __main__ -   Step: 1761, LR: 3.8424754979449887e-07, Loss: 0.29166945815086365
2024-08-04T20:46:20.190494326Z 
 31%|███       | 1762/5712 [4:08:11<9:26:30,  8.61s/it]08/04/2024 13:46:20 - INFO - __main__ -   Step: 1762, LR: 3.8415027116418197e-07, Loss: 0.3028990626335144
2024-08-04T20:46:28.397296597Z 
 31%|███       | 1763/5712 [4:08:19<9:18:29,  8.49s/it]08/04/2024 13:46:28 - INFO - __main__ -   Step: 1763, LR: 3.8405299253386507e-07, Loss: 0.38254353404045105
2024-08-04T20:46:37.224335509Z 
 31%|███       | 1764/5712 [4:08:28<9:25:05,  8.59s/it]08/04/2024 13:46:37 - INFO - __main__ -   Step: 1764, LR: 3.839557139035482e-07, Loss: 0.539505660533905
2024-08-04T20:46:45.928356478Z 
 31%|███       | 1765/5712 [4:08:37<9:27:13,  8.62s/it]08/04/2024 13:46:45 - INFO - __main__ -   Step: 1765, LR: 3.8385843527323137e-07, Loss: 0.45167607069015503
2024-08-04T20:46:53.915936471Z 
 31%|███       | 1766/5712 [4:08:45<9:14:34,  8.43s/it]08/04/2024 13:46:53 - INFO - __main__ -   Step: 1766, LR: 3.8376115664291447e-07, Loss: 0.44875815510749817
2024-08-04T20:47:02.181966516Z 
 31%|███       | 1767/5712 [4:08:53<9:11:08,  8.38s/it]08/04/2024 13:47:02 - INFO - __main__ -   Step: 1767, LR: 3.8366387801259757e-07, Loss: 0.4356416165828705
2024-08-04T20:47:11.080058677Z 
 31%|███       | 1768/5712 [4:09:02<9:21:09,  8.54s/it]08/04/2024 13:47:11 - INFO - __main__ -   Step: 1768, LR: 3.835665993822807e-07, Loss: 0.36691880226135254
2024-08-04T20:47:19.031788762Z 
 31%|███       | 1769/5712 [4:09:10<9:09:29,  8.36s/it]08/04/2024 13:47:19 - INFO - __main__ -   Step: 1769, LR: 3.834693207519638e-07, Loss: 0.4212644398212433
2024-08-04T20:47:27.486526642Z 
 31%|███       | 1770/5712 [4:09:18<9:11:11,  8.39s/it]08/04/2024 13:47:27 - INFO - __main__ -   Step: 1770, LR: 3.833720421216469e-07, Loss: 0.5391236543655396
2024-08-04T20:47:35.657712562Z 
 31%|███       | 1771/5712 [4:09:26<9:06:44,  8.32s/it]08/04/2024 13:47:35 - INFO - __main__ -   Step: 1771, LR: 3.8327476349133e-07, Loss: 0.33390238881111145
2024-08-04T20:47:44.480196974Z 
 31%|███       | 1772/5712 [4:09:35<9:16:25,  8.47s/it]08/04/2024 13:47:44 - INFO - __main__ -   Step: 1772, LR: 3.831774848610131e-07, Loss: 0.6201679706573486
2024-08-04T20:47:53.155920370Z 
 31%|███       | 1773/5712 [4:09:44<9:20:16,  8.53s/it]08/04/2024 13:47:53 - INFO - __main__ -   Step: 1773, LR: 3.8308020623069627e-07, Loss: 0.2874899208545685
2024-08-04T20:48:01.495053055Z 
 31%|███       | 1774/5712 [4:09:52<9:16:17,  8.48s/it]08/04/2024 13:48:01 - INFO - __main__ -   Step: 1774, LR: 3.8298292760037937e-07, Loss: 0.4979677200317383
2024-08-04T20:48:09.561159380Z 
 31%|███       | 1775/5712 [4:10:00<9:08:04,  8.35s/it]08/04/2024 13:48:09 - INFO - __main__ -   Step: 1775, LR: 3.8288564897006247e-07, Loss: 0.44773370027542114
2024-08-04T20:48:17.871691696Z 
 31%|███       | 1776/5712 [4:10:09<9:07:07,  8.34s/it]08/04/2024 13:48:17 - INFO - __main__ -   Step: 1776, LR: 3.8278837033974557e-07, Loss: 0.4016759395599365
2024-08-04T20:48:26.438159969Z 
 31%|███       | 1777/5712 [4:10:17<9:11:24,  8.41s/it]08/04/2024 13:48:26 - INFO - __main__ -   Step: 1777, LR: 3.826910917094287e-07, Loss: 0.5656307935714722
2024-08-04T20:48:35.208906296Z 
 31%|███       | 1778/5712 [4:10:26<9:18:25,  8.52s/it]08/04/2024 13:48:35 - INFO - __main__ -   Step: 1778, LR: 3.825938130791118e-07, Loss: 0.4376620054244995
2024-08-04T20:48:43.631349921Z 
 31%|███       | 1779/5712 [4:10:34<9:16:25,  8.49s/it]08/04/2024 13:48:43 - INFO - __main__ -   Step: 1779, LR: 3.824965344487949e-07, Loss: 0.3682916760444641
2024-08-04T20:48:52.015590980Z 
 31%|███       | 1780/5712 [4:10:43<9:14:14,  8.46s/it]08/04/2024 13:48:52 - INFO - __main__ -   Step: 1780, LR: 3.82399255818478e-07, Loss: 0.47998231649398804
2024-08-04T20:49:00.806151732Z 
 31%|███       | 1781/5712 [4:10:51<9:20:39,  8.56s/it]08/04/2024 13:49:00 - INFO - __main__ -   Step: 1781, LR: 3.8230197718816117e-07, Loss: 0.4980793595314026
2024-08-04T20:49:09.898075195Z 
 31%|███       | 1782/5712 [4:11:01<9:30:59,  8.72s/it]08/04/2024 13:49:09 - INFO - __main__ -   Step: 1782, LR: 3.8220469855784427e-07, Loss: 0.5594751834869385
2024-08-04T20:49:18.176390442Z 
 31%|███       | 1783/5712 [4:11:09<9:22:13,  8.59s/it]08/04/2024 13:49:18 - INFO - __main__ -   Step: 1783, LR: 3.821074199275274e-07, Loss: 0.5759562253952026
2024-08-04T20:49:27.134571126Z 
 31%|███       | 1784/5712 [4:11:18<9:29:24,  8.70s/it]08/04/2024 13:49:27 - INFO - __main__ -   Step: 1784, LR: 3.820101412972105e-07, Loss: 0.5122122764587402
2024-08-04T20:49:35.641938279Z 
 31%|███▏      | 1785/5712 [4:11:26<9:25:31,  8.64s/it]08/04/2024 13:49:35 - INFO - __main__ -   Step: 1785, LR: 3.8191286266689367e-07, Loss: 0.4431819021701813
2024-08-04T20:49:43.767206557Z 
 31%|███▏      | 1786/5712 [4:11:34<9:15:15,  8.49s/it]08/04/2024 13:49:43 - INFO - __main__ -   Step: 1786, LR: 3.8181558403657677e-07, Loss: 0.4708600640296936
2024-08-04T20:49:51.889837594Z 
 31%|███▏      | 1787/5712 [4:11:43<9:08:00,  8.38s/it]08/04/2024 13:49:51 - INFO - __main__ -   Step: 1787, LR: 3.8171830540625987e-07, Loss: 0.5128360986709595
2024-08-04T20:50:00.860806476Z 
 31%|███▏      | 1788/5712 [4:11:52<9:19:30,  8.56s/it]08/04/2024 13:50:00 - INFO - __main__ -   Step: 1788, LR: 3.8162102677594297e-07, Loss: 0.334214448928833
2024-08-04T20:50:09.737212622Z 
 31%|███▏      | 1789/5712 [4:12:00<9:25:39,  8.65s/it]08/04/2024 13:50:09 - INFO - __main__ -   Step: 1789, LR: 3.815237481456261e-07, Loss: 0.348993718624115
2024-08-04T20:50:18.189005388Z 
 31%|███▏      | 1790/5712 [4:12:09<9:21:35,  8.59s/it]08/04/2024 13:50:18 - INFO - __main__ -   Step: 1790, LR: 3.814264695153092e-07, Loss: 0.42755597829818726
2024-08-04T20:50:27.484201862Z 
 31%|███▏      | 1791/5712 [4:12:18<9:35:15,  8.80s/it]08/04/2024 13:50:27 - INFO - __main__ -   Step: 1791, LR: 3.813291908849923e-07, Loss: 0.2901759445667267
2024-08-04T20:50:35.463611330Z 
 31%|███▏      | 1792/5712 [4:12:26<9:18:58,  8.56s/it]08/04/2024 13:50:35 - INFO - __main__ -   Step: 1792, LR: 3.812319122546754e-07, Loss: 0.39206206798553467
2024-08-04T20:50:43.759204323Z 
 31%|███▏      | 1793/5712 [4:12:34<9:13:43,  8.48s/it]08/04/2024 13:50:43 - INFO - __main__ -   Step: 1793, LR: 3.8113463362435857e-07, Loss: 0.5372929573059082
2024-08-04T20:50:52.614549473Z 
 31%|███▏      | 1794/5712 [4:12:43<9:20:59,  8.59s/it]08/04/2024 13:50:52 - INFO - __main__ -   Step: 1794, LR: 3.8103735499404167e-07, Loss: 0.32562118768692017
2024-08-04T20:51:00.863132575Z 
 31%|███▏      | 1795/5712 [4:12:52<9:14:08,  8.49s/it]08/04/2024 13:51:00 - INFO - __main__ -   Step: 1795, LR: 3.8094007636372477e-07, Loss: 0.5713762044906616
2024-08-04T20:51:09.426909241Z 
 31%|███▏      | 1796/5712 [4:13:00<9:15:28,  8.51s/it]08/04/2024 13:51:09 - INFO - __main__ -   Step: 1796, LR: 3.8084279773340787e-07, Loss: 0.44132447242736816
2024-08-04T20:51:18.522831142Z 
 31%|███▏      | 1797/5712 [4:13:09<9:26:47,  8.69s/it]08/04/2024 13:51:18 - INFO - __main__ -   Step: 1797, LR: 3.80745519103091e-07, Loss: 0.47882992029190063
2024-08-04T20:51:26.997410782Z 
 31%|███▏      | 1798/5712 [4:13:18<9:22:30,  8.62s/it]08/04/2024 13:51:26 - INFO - __main__ -   Step: 1798, LR: 3.806482404727741e-07, Loss: 0.3544285297393799
2024-08-04T20:51:35.662019001Z 
 31%|███▏      | 1799/5712 [4:13:26<9:23:10,  8.64s/it]08/04/2024 13:51:35 - INFO - __main__ -   Step: 1799, LR: 3.805509618424572e-07, Loss: 0.4209253191947937
2024-08-04T20:51:44.203106379Z 
 32%|███▏      | 1800/5712 [4:13:35<9:21:10,  8.61s/it]08/04/2024 13:51:44 - INFO - __main__ -   Step: 1800, LR: 3.804536832121403e-07, Loss: 0.331926554441452
2024-08-04T20:51:52.841728744Z 
 32%|███▏      | 1801/5712 [4:13:43<9:21:39,  8.62s/it]08/04/2024 13:51:52 - INFO - __main__ -   Step: 1801, LR: 3.803564045818235e-07, Loss: 0.3831339478492737
2024-08-04T20:52:01.261626979Z 
 32%|███▏      | 1802/5712 [4:13:52<9:17:40,  8.56s/it]08/04/2024 13:52:01 - INFO - __main__ -   Step: 1802, LR: 3.802591259515066e-07, Loss: 0.43408429622650146
2024-08-04T20:52:09.428023635Z 
 32%|███▏      | 1803/5712 [4:14:00<9:09:52,  8.44s/it]08/04/2024 13:52:09 - INFO - __main__ -   Step: 1803, LR: 3.801618473211897e-07, Loss: 0.6472364664077759
2024-08-04T20:52:17.384283446Z 
 32%|███▏      | 1804/5712 [4:14:08<9:00:16,  8.29s/it]08/04/2024 13:52:17 - INFO - __main__ -   Step: 1804, LR: 3.800645686908728e-07, Loss: 0.39432764053344727
2024-08-04T20:52:26.299625799Z 
 32%|███▏      | 1805/5712 [4:14:17<9:12:16,  8.48s/it]08/04/2024 13:52:26 - INFO - __main__ -   Step: 1805, LR: 3.7996729006055597e-07, Loss: 0.36872613430023193
2024-08-04T20:52:34.996486794Z 
 32%|███▏      | 1806/5712 [4:14:26<9:16:19,  8.55s/it]08/04/2024 13:52:34 - INFO - __main__ -   Step: 1806, LR: 3.7987001143023907e-07, Loss: 0.45859259366989136
2024-08-04T20:52:43.035730665Z 
 32%|███▏      | 1807/5712 [4:14:34<9:06:18,  8.39s/it]08/04/2024 13:52:43 - INFO - __main__ -   Step: 1807, LR: 3.7977273279992217e-07, Loss: 0.4402168393135071
2024-08-04T20:52:52.002331760Z 
 32%|███▏      | 1808/5712 [4:14:43<9:17:20,  8.57s/it]08/04/2024 13:52:52 - INFO - __main__ -   Step: 1808, LR: 3.7967545416960527e-07, Loss: 0.3996492624282837
2024-08-04T20:53:00.199570728Z 
 32%|███▏      | 1809/5712 [4:14:51<9:10:00,  8.46s/it]08/04/2024 13:53:00 - INFO - __main__ -   Step: 1809, LR: 3.7957817553928837e-07, Loss: 0.5194212794303894
2024-08-04T20:53:09.088319516Z 
 32%|███▏      | 1810/5712 [4:15:00<9:18:19,  8.59s/it]08/04/2024 13:53:09 - INFO - __main__ -   Step: 1810, LR: 3.794808969089715e-07, Loss: 0.35408204793930054
2024-08-04T20:53:17.800027657Z 
 32%|███▏      | 1811/5712 [4:15:08<9:20:38,  8.62s/it]08/04/2024 13:53:17 - INFO - __main__ -   Step: 1811, LR: 3.793836182786546e-07, Loss: 0.5447285175323486
2024-08-04T20:53:25.995341772Z 
 32%|███▏      | 1812/5712 [4:15:17<9:12:09,  8.49s/it]08/04/2024 13:53:25 - INFO - __main__ -   Step: 1812, LR: 3.792863396483377e-07, Loss: 0.5019943118095398
2024-08-04T20:53:34.929305325Z 
 32%|███▏      | 1813/5712 [4:15:26<9:20:35,  8.63s/it]08/04/2024 13:53:34 - INFO - __main__ -   Step: 1813, LR: 3.791890610180208e-07, Loss: 0.4139699935913086
2024-08-04T20:53:43.346953430Z 
 32%|███▏      | 1814/5712 [4:15:34<9:16:22,  8.56s/it]08/04/2024 13:53:43 - INFO - __main__ -   Step: 1814, LR: 3.7909178238770397e-07, Loss: 0.4623377323150635
2024-08-04T20:53:51.780550503Z 
 32%|███▏      | 1815/5712 [4:15:42<9:13:41,  8.52s/it]08/04/2024 13:53:51 - INFO - __main__ -   Step: 1815, LR: 3.7899450375738707e-07, Loss: 0.5266963243484497
2024-08-04T20:54:00.021476355Z 
 32%|███▏      | 1816/5712 [4:15:51<9:08:00,  8.44s/it]08/04/2024 13:54:00 - INFO - __main__ -   Step: 1816, LR: 3.7889722512707017e-07, Loss: 0.4133438766002655
2024-08-04T20:54:08.228685232Z 
 32%|███▏      | 1817/5712 [4:15:59<9:03:20,  8.37s/it]08/04/2024 13:54:08 - INFO - __main__ -   Step: 1817, LR: 3.7879994649675326e-07, Loss: 0.49936097860336304
2024-08-04T20:54:16.567834383Z 
 32%|███▏      | 1818/5712 [4:16:07<9:02:36,  8.36s/it]08/04/2024 13:54:16 - INFO - __main__ -   Step: 1818, LR: 3.787026678664364e-07, Loss: 0.19775420427322388
2024-08-04T20:54:25.002896145Z 
 32%|███▏      | 1819/5712 [4:16:16<9:03:55,  8.38s/it]08/04/2024 13:54:25 - INFO - __main__ -   Step: 1819, LR: 3.7860538923611957e-07, Loss: 0.4887753129005432
2024-08-04T20:54:33.127697641Z 
 32%|███▏      | 1820/5712 [4:16:24<8:58:44,  8.31s/it]08/04/2024 13:54:33 - INFO - __main__ -   Step: 1820, LR: 3.7850811060580267e-07, Loss: 0.38859647512435913
2024-08-04T20:54:42.402912585Z 
 32%|███▏      | 1821/5712 [4:16:33<9:17:28,  8.60s/it]08/04/2024 13:54:42 - INFO - __main__ -   Step: 1821, LR: 3.7841083197548577e-07, Loss: 0.7206271886825562
2024-08-04T20:54:50.687141436Z 
 32%|███▏      | 1822/5712 [4:16:41<9:11:15,  8.50s/it]08/04/2024 13:54:50 - INFO - __main__ -   Step: 1822, LR: 3.783135533451689e-07, Loss: 0.3901849389076233
2024-08-04T20:54:59.388558128Z 
 32%|███▏      | 1823/5712 [4:16:50<9:14:58,  8.56s/it]08/04/2024 13:54:59 - INFO - __main__ -   Step: 1823, LR: 3.78216274714852e-07, Loss: 0.3519699275493622
2024-08-04T20:55:07.449928087Z 
 32%|███▏      | 1824/5712 [4:16:58<9:05:06,  8.41s/it]08/04/2024 13:55:07 - INFO - __main__ -   Step: 1824, LR: 3.781189960845351e-07, Loss: 0.43193861842155457
2024-08-04T20:55:16.090799769Z 
 32%|███▏      | 1825/5712 [4:17:07<9:09:24,  8.48s/it]08/04/2024 13:55:16 - INFO - __main__ -   Step: 1825, LR: 3.780217174542182e-07, Loss: 0.656257152557373
2024-08-04T20:55:24.159924914Z 
 32%|███▏      | 1826/5712 [4:17:15<9:01:16,  8.36s/it]08/04/2024 13:55:24 - INFO - __main__ -   Step: 1826, LR: 3.7792443882390137e-07, Loss: 0.30789902806282043
2024-08-04T20:55:32.626755354Z 
 32%|███▏      | 1827/5712 [4:17:23<9:03:15,  8.39s/it]08/04/2024 13:55:32 - INFO - __main__ -   Step: 1827, LR: 3.7782716019358447e-07, Loss: 0.4221155643463135
2024-08-04T20:55:41.376118465Z 
 32%|███▏      | 1828/5712 [4:17:32<9:10:05,  8.50s/it]08/04/2024 13:55:41 - INFO - __main__ -   Step: 1828, LR: 3.7772988156326757e-07, Loss: 0.30370962619781494
2024-08-04T20:55:49.524073140Z 
 32%|███▏      | 1829/5712 [4:17:40<9:03:09,  8.39s/it]08/04/2024 13:55:49 - INFO - __main__ -   Step: 1829, LR: 3.7763260293295067e-07, Loss: 0.4797208607196808
2024-08-04T20:55:57.913883076Z 
 32%|███▏      | 1830/5712 [4:17:49<9:02:57,  8.39s/it]08/04/2024 13:55:57 - INFO - __main__ -   Step: 1830, LR: 3.775353243026338e-07, Loss: 0.41581547260284424
2024-08-04T20:56:06.407844225Z 
 32%|███▏      | 1831/5712 [4:17:57<9:04:47,  8.42s/it]08/04/2024 13:56:06 - INFO - __main__ -   Step: 1831, LR: 3.774380456723169e-07, Loss: 0.4094751477241516
2024-08-04T20:56:15.094745040Z 
 32%|███▏      | 1832/5712 [4:18:06<9:09:46,  8.50s/it]08/04/2024 13:56:15 - INFO - __main__ -   Step: 1832, LR: 3.77340767042e-07, Loss: 0.4471767544746399
2024-08-04T20:56:24.145319966Z 
 32%|███▏      | 1833/5712 [4:18:15<9:20:17,  8.67s/it]08/04/2024 13:56:24 - INFO - __main__ -   Step: 1833, LR: 3.772434884116831e-07, Loss: 0.35459697246551514
2024-08-04T20:56:32.205299413Z 
 32%|███▏      | 1834/5712 [4:18:23<9:08:23,  8.48s/it]08/04/2024 13:56:32 - INFO - __main__ -   Step: 1834, LR: 3.7714620978136627e-07, Loss: 0.3705059289932251
2024-08-04T20:56:40.973525165Z 
 32%|███▏      | 1835/5712 [4:18:32<9:13:44,  8.57s/it]08/04/2024 13:56:40 - INFO - __main__ -   Step: 1835, LR: 3.7704893115104937e-07, Loss: 0.44407981634140015
2024-08-04T20:56:49.175496431Z 
 32%|███▏      | 1836/5712 [4:18:40<9:06:26,  8.46s/it]08/04/2024 13:56:49 - INFO - __main__ -   Step: 1836, LR: 3.7695165252073246e-07, Loss: 0.5862250328063965
2024-08-04T20:56:57.264229705Z 
 32%|███▏      | 1837/5712 [4:18:48<8:59:09,  8.35s/it]08/04/2024 13:56:57 - INFO - __main__ -   Step: 1837, LR: 3.768543738904156e-07, Loss: 0.3595375418663025
2024-08-04T20:57:05.776115794Z 
 32%|███▏      | 1838/5712 [4:18:56<9:02:11,  8.40s/it]08/04/2024 13:57:05 - INFO - __main__ -   Step: 1838, LR: 3.7675709526009877e-07, Loss: 0.42582929134368896
2024-08-04T20:57:14.871425945Z 
 32%|███▏      | 1839/5712 [4:19:06<9:15:33,  8.61s/it]08/04/2024 13:57:14 - INFO - __main__ -   Step: 1839, LR: 3.7665981662978187e-07, Loss: 0.33302974700927734
2024-08-04T20:57:23.125341359Z 
 32%|███▏      | 1840/5712 [4:19:14<9:08:35,  8.50s/it]08/04/2024 13:57:23 - INFO - __main__ -   Step: 1840, LR: 3.7656253799946497e-07, Loss: 0.48025673627853394
2024-08-04T20:57:31.821378591Z 
 32%|███▏      | 1841/5712 [4:19:22<9:12:13,  8.56s/it]08/04/2024 13:57:31 - INFO - __main__ -   Step: 1841, LR: 3.7646525936914807e-07, Loss: 0.5666114091873169
2024-08-04T20:57:40.154803095Z 
 32%|███▏      | 1842/5712 [4:19:31<9:07:42,  8.49s/it]08/04/2024 13:57:40 - INFO - __main__ -   Step: 1842, LR: 3.763679807388312e-07, Loss: 0.5630534887313843
2024-08-04T20:57:48.817845986Z 
 32%|███▏      | 1843/5712 [4:19:39<9:10:53,  8.54s/it]08/04/2024 13:57:48 - INFO - __main__ -   Step: 1843, LR: 3.762707021085143e-07, Loss: 0.6223087906837463
2024-08-04T20:57:56.956459857Z 
 32%|███▏      | 1844/5712 [4:19:48<9:02:55,  8.42s/it]08/04/2024 13:57:56 - INFO - __main__ -   Step: 1844, LR: 3.761734234781974e-07, Loss: 0.5149213075637817
2024-08-04T20:58:05.532266510Z 
 32%|███▏      | 1845/5712 [4:19:56<9:05:45,  8.47s/it]08/04/2024 13:58:05 - INFO - __main__ -   Step: 1845, LR: 3.760761448478805e-07, Loss: 0.42140188813209534
2024-08-04T20:58:14.055929747Z 
 32%|███▏      | 1846/5712 [4:20:05<9:06:42,  8.48s/it]08/04/2024 13:58:14 - INFO - __main__ -   Step: 1846, LR: 3.759788662175636e-07, Loss: 0.27732038497924805
2024-08-04T20:58:22.943325570Z 
 32%|███▏      | 1847/5712 [4:20:14<9:14:20,  8.61s/it]08/04/2024 13:58:22 - INFO - __main__ -   Step: 1847, LR: 3.7588158758724677e-07, Loss: 0.3605404496192932
2024-08-04T20:58:31.383058713Z 
 32%|███▏      | 1848/5712 [4:20:22<9:10:58,  8.56s/it]08/04/2024 13:58:31 - INFO - __main__ -   Step: 1848, LR: 3.7578430895692986e-07, Loss: 0.6534078121185303
2024-08-04T20:58:39.785949022Z 
 32%|███▏      | 1849/5712 [4:20:30<9:07:53,  8.51s/it]08/04/2024 13:58:39 - INFO - __main__ -   Step: 1849, LR: 3.7568703032661296e-07, Loss: 0.40132489800453186
2024-08-04T20:58:48.274080227Z 
 32%|███▏      | 1850/5712 [4:20:39<9:07:20,  8.50s/it]08/04/2024 13:58:48 - INFO - __main__ -   Step: 1850, LR: 3.7558975169629606e-07, Loss: 0.5518103837966919
2024-08-04T20:58:56.421322343Z 
 32%|███▏      | 1851/5712 [4:20:47<9:00:19,  8.40s/it]08/04/2024 13:58:56 - INFO - __main__ -   Step: 1851, LR: 3.754924730659792e-07, Loss: 0.4099072217941284
2024-08-04T20:59:05.106807610Z 
 32%|███▏      | 1852/5712 [4:20:56<9:05:45,  8.48s/it]08/04/2024 13:59:05 - INFO - __main__ -   Step: 1852, LR: 3.753951944356623e-07, Loss: 0.4840105175971985
2024-08-04T20:59:13.627167175Z 
 32%|███▏      | 1853/5712 [4:21:04<9:06:19,  8.49s/it]08/04/2024 13:59:13 - INFO - __main__ -   Step: 1853, LR: 3.752979158053454e-07, Loss: 0.3857969045639038
2024-08-04T20:59:21.928740252Z 
 32%|███▏      | 1854/5712 [4:21:13<9:02:28,  8.44s/it]08/04/2024 13:59:21 - INFO - __main__ -   Step: 1854, LR: 3.752006371750285e-07, Loss: 0.39469459652900696
2024-08-04T20:59:30.262363210Z 
 32%|███▏      | 1855/5712 [4:21:21<9:00:20,  8.41s/it]08/04/2024 13:59:30 - INFO - __main__ -   Step: 1855, LR: 3.751033585447117e-07, Loss: 0.5331222414970398
2024-08-04T20:59:38.603239917Z 
 32%|███▏      | 1856/5712 [4:21:29<8:58:57,  8.39s/it]08/04/2024 13:59:38 - INFO - __main__ -   Step: 1856, LR: 3.750060799143948e-07, Loss: 0.6406978964805603
2024-08-04T20:59:47.059077584Z 
 33%|███▎      | 1857/5712 [4:21:38<9:00:09,  8.41s/it]08/04/2024 13:59:47 - INFO - __main__ -   Step: 1857, LR: 3.749088012840779e-07, Loss: 0.5428181886672974
2024-08-04T20:59:55.771986997Z 
 33%|███▎      | 1858/5712 [4:21:46<9:05:54,  8.50s/it]08/04/2024 13:59:55 - INFO - __main__ -   Step: 1858, LR: 3.74811522653761e-07, Loss: 0.4140826463699341
2024-08-04T21:00:04.214442754Z 
 33%|███▎      | 1859/5712 [4:21:55<9:04:41,  8.48s/it]08/04/2024 14:00:04 - INFO - __main__ -   Step: 1859, LR: 3.7471424402344417e-07, Loss: 0.425872266292572
2024-08-04T21:00:12.228579224Z 
 33%|███▎      | 1860/5712 [4:22:03<8:55:31,  8.34s/it]08/04/2024 14:00:12 - INFO - __main__ -   Step: 1860, LR: 3.7461696539312726e-07, Loss: 0.45161673426628113
2024-08-04T21:00:20.581520191Z 
 33%|███▎      | 1861/5712 [4:22:11<8:55:36,  8.35s/it]08/04/2024 14:00:20 - INFO - __main__ -   Step: 1861, LR: 3.7451968676281036e-07, Loss: 0.4306682348251343
2024-08-04T21:00:29.500833259Z 
 33%|███▎      | 1862/5712 [4:22:20<9:06:31,  8.52s/it]08/04/2024 14:00:29 - INFO - __main__ -   Step: 1862, LR: 3.7442240813249346e-07, Loss: 0.49253928661346436
2024-08-04T21:00:38.247266872Z 
 33%|███▎      | 1863/5712 [4:22:29<9:10:47,  8.59s/it]08/04/2024 14:00:38 - INFO - __main__ -   Step: 1863, LR: 3.743251295021766e-07, Loss: 0.5271954536437988
2024-08-04T21:00:46.936739262Z 
 33%|███▎      | 1864/5712 [4:22:38<9:12:38,  8.62s/it]08/04/2024 14:00:46 - INFO - __main__ -   Step: 1864, LR: 3.742278508718597e-07, Loss: 0.465115487575531
2024-08-04T21:00:55.622790883Z 
 33%|███▎      | 1865/5712 [4:22:46<9:13:49,  8.64s/it]08/04/2024 14:00:55 - INFO - __main__ -   Step: 1865, LR: 3.741305722415428e-07, Loss: 0.32175320386886597
2024-08-04T21:01:03.998717987Z 
 33%|███▎      | 1866/5712 [4:22:55<9:08:38,  8.56s/it]08/04/2024 14:01:03 - INFO - __main__ -   Step: 1866, LR: 3.740332936112259e-07, Loss: 0.3976632356643677
2024-08-04T21:01:12.950896970Z 
 33%|███▎      | 1867/5712 [4:23:04<9:16:03,  8.68s/it]08/04/2024 14:01:12 - INFO - __main__ -   Step: 1867, LR: 3.7393601498090906e-07, Loss: 0.5469416379928589
2024-08-04T21:01:21.190741728Z 
 33%|███▎      | 1868/5712 [4:23:12<9:07:30,  8.55s/it]08/04/2024 14:01:21 - INFO - __main__ -   Step: 1868, LR: 3.7383873635059216e-07, Loss: 0.4756421446800232
2024-08-04T21:01:29.873792501Z 
 33%|███▎      | 1869/5712 [4:23:21<9:10:00,  8.59s/it]08/04/2024 14:01:29 - INFO - __main__ -   Step: 1869, LR: 3.7374145772027526e-07, Loss: 0.26708436012268066
2024-08-04T21:01:38.513208436Z 
 33%|███▎      | 1870/5712 [4:23:29<9:10:51,  8.60s/it]08/04/2024 14:01:38 - INFO - __main__ -   Step: 1870, LR: 3.7364417908995836e-07, Loss: 0.3505009114742279
2024-08-04T21:01:47.303949882Z 
 33%|███▎      | 1871/5712 [4:23:38<9:14:19,  8.66s/it]08/04/2024 14:01:47 - INFO - __main__ -   Step: 1871, LR: 3.735469004596415e-07, Loss: 0.42240601778030396
2024-08-04T21:01:56.379807546Z 
 33%|███▎      | 1872/5712 [4:23:47<9:22:11,  8.78s/it]08/04/2024 14:01:56 - INFO - __main__ -   Step: 1872, LR: 3.734496218293246e-07, Loss: 0.4686826467514038
2024-08-04T21:02:04.550729648Z 
 33%|███▎      | 1873/5712 [4:23:55<9:10:16,  8.60s/it]08/04/2024 14:02:04 - INFO - __main__ -   Step: 1873, LR: 3.7335234319900776e-07, Loss: 0.42675238847732544
2024-08-04T21:02:13.255124157Z 
 33%|███▎      | 1874/5712 [4:24:04<9:12:08,  8.63s/it]08/04/2024 14:02:13 - INFO - __main__ -   Step: 1874, LR: 3.7325506456869086e-07, Loss: 0.34879910945892334
2024-08-04T21:02:21.620975818Z 
 33%|███▎      | 1875/5712 [4:24:12<9:06:52,  8.55s/it]08/04/2024 14:02:21 - INFO - __main__ -   Step: 1875, LR: 3.73157785938374e-07, Loss: 0.46444663405418396
2024-08-04T21:02:29.990684788Z 
 33%|███▎      | 1876/5712 [4:24:21<9:03:14,  8.50s/it]08/04/2024 14:02:29 - INFO - __main__ -   Step: 1876, LR: 3.730605073080571e-07, Loss: 0.24094389379024506
2024-08-04T21:02:38.018421741Z 
 33%|███▎      | 1877/5712 [4:24:29<8:54:06,  8.36s/it]08/04/2024 14:02:38 - INFO - __main__ -   Step: 1877, LR: 3.729632286777402e-07, Loss: 0.45091891288757324
2024-08-04T21:02:46.623145040Z 
 33%|███▎      | 1878/5712 [4:24:37<8:58:43,  8.43s/it]08/04/2024 14:02:46 - INFO - __main__ -   Step: 1878, LR: 3.728659500474233e-07, Loss: 0.46139854192733765
2024-08-04T21:02:55.179935799Z 
 33%|███▎      | 1879/5712 [4:24:46<9:01:00,  8.47s/it]08/04/2024 14:02:55 - INFO - __main__ -   Step: 1879, LR: 3.7276867141710646e-07, Loss: 0.3680674433708191
2024-08-04T21:03:04.333495507Z 
 33%|███▎      | 1880/5712 [4:24:55<9:13:59,  8.67s/it]08/04/2024 14:03:04 - INFO - __main__ -   Step: 1880, LR: 3.7267139278678956e-07, Loss: 0.5404201149940491
2024-08-04T21:03:12.617656080Z 
 33%|███▎      | 1881/5712 [4:25:03<9:06:22,  8.56s/it]08/04/2024 14:03:12 - INFO - __main__ -   Step: 1881, LR: 3.7257411415647266e-07, Loss: 0.5313871502876282
2024-08-04T21:03:21.435940769Z 
 33%|███▎      | 1882/5712 [4:25:12<9:11:14,  8.64s/it]08/04/2024 14:03:21 - INFO - __main__ -   Step: 1882, LR: 3.7247683552615576e-07, Loss: 0.7781704664230347
2024-08-04T21:03:29.830338134Z 
 33%|███▎      | 1883/5712 [4:25:20<9:06:28,  8.56s/it]08/04/2024 14:03:29 - INFO - __main__ -   Step: 1883, LR: 3.7237955689583886e-07, Loss: 0.29669666290283203
2024-08-04T21:03:37.893400299Z 
 33%|███▎      | 1884/5712 [4:25:29<8:56:45,  8.41s/it]08/04/2024 14:03:37 - INFO - __main__ -   Step: 1884, LR: 3.72282278265522e-07, Loss: 0.35347020626068115
2024-08-04T21:03:45.952362600Z 
 33%|███▎      | 1885/5712 [4:25:37<8:49:50,  8.31s/it]08/04/2024 14:03:45 - INFO - __main__ -   Step: 1885, LR: 3.721849996352051e-07, Loss: 0.5501530766487122
2024-08-04T21:03:54.491635927Z 
 33%|███▎      | 1886/5712 [4:25:45<8:54:08,  8.38s/it]08/04/2024 14:03:54 - INFO - __main__ -   Step: 1886, LR: 3.720877210048882e-07, Loss: 0.35985279083251953
2024-08-04T21:04:03.061022055Z 
 33%|███▎      | 1887/5712 [4:25:54<8:57:41,  8.43s/it]08/04/2024 14:04:03 - INFO - __main__ -   Step: 1887, LR: 3.719904423745713e-07, Loss: 0.544109582901001
2024-08-04T21:04:11.628554705Z 
 33%|███▎      | 1888/5712 [4:26:02<9:00:06,  8.47s/it]08/04/2024 14:04:11 - INFO - __main__ -   Step: 1888, LR: 3.7189316374425446e-07, Loss: 0.4430655241012573
2024-08-04T21:04:19.941965628Z 
 33%|███▎      | 1889/5712 [4:26:11<8:56:52,  8.43s/it]08/04/2024 14:04:19 - INFO - __main__ -   Step: 1889, LR: 3.7179588511393756e-07, Loss: 0.29828375577926636
2024-08-04T21:04:28.467065150Z 
 33%|███▎      | 1890/5712 [4:26:19<8:58:38,  8.46s/it]08/04/2024 14:04:28 - INFO - __main__ -   Step: 1890, LR: 3.7169860648362066e-07, Loss: 0.3949531316757202
2024-08-04T21:04:37.489466044Z 
 33%|███▎      | 1891/5712 [4:26:28<9:09:19,  8.63s/it]08/04/2024 14:04:37 - INFO - __main__ -   Step: 1891, LR: 3.7160132785330376e-07, Loss: 0.4311774969100952
2024-08-04T21:04:45.630492529Z 
 33%|███▎      | 1892/5712 [4:26:36<8:59:55,  8.48s/it]08/04/2024 14:04:45 - INFO - __main__ -   Step: 1892, LR: 3.7150404922298696e-07, Loss: 0.40293648838996887
2024-08-04T21:04:53.655686224Z 
 33%|███▎      | 1893/5712 [4:26:44<8:51:04,  8.34s/it]08/04/2024 14:04:53 - INFO - __main__ -   Step: 1893, LR: 3.7140677059267006e-07, Loss: 0.5303330421447754
2024-08-04T21:05:02.087804045Z 
 33%|███▎      | 1894/5712 [4:26:53<8:52:37,  8.37s/it]08/04/2024 14:05:02 - INFO - __main__ -   Step: 1894, LR: 3.7130949196235316e-07, Loss: 0.5302605628967285
2024-08-04T21:05:10.855382291Z 
 33%|███▎      | 1895/5712 [4:27:02<9:00:04,  8.49s/it]08/04/2024 14:05:10 - INFO - __main__ -   Step: 1895, LR: 3.7121221333203626e-07, Loss: 0.5915209054946899
2024-08-04T21:05:19.231903589Z 
 33%|███▎      | 1896/5712 [4:27:10<8:57:46,  8.46s/it]08/04/2024 14:05:19 - INFO - __main__ -   Step: 1896, LR: 3.711149347017194e-07, Loss: 0.4090646505355835
2024-08-04T21:05:27.633269188Z 
 33%|███▎      | 1897/5712 [4:27:18<8:56:35,  8.44s/it]08/04/2024 14:05:27 - INFO - __main__ -   Step: 1897, LR: 3.710176560714025e-07, Loss: 0.5898357629776001
2024-08-04T21:05:36.257136447Z 
 33%|███▎      | 1898/5712 [4:27:27<8:59:58,  8.49s/it]08/04/2024 14:05:36 - INFO - __main__ -   Step: 1898, LR: 3.709203774410856e-07, Loss: 0.6873318552970886
2024-08-04T21:05:44.619955670Z 
 33%|███▎      | 1899/5712 [4:27:35<8:57:19,  8.46s/it]08/04/2024 14:05:44 - INFO - __main__ -   Step: 1899, LR: 3.708230988107687e-07, Loss: 0.5488651990890503
2024-08-04T21:05:52.997503341Z 
 33%|███▎      | 1900/5712 [4:27:44<8:55:42,  8.43s/it]08/04/2024 14:05:52 - INFO - __main__ -   Step: 1900, LR: 3.7072582018045186e-07, Loss: 0.39109206199645996
2024-08-04T21:06:00.645789655Z 
 33%|███▎      | 1901/5712 [4:27:51<8:40:38,  8.20s/it]08/04/2024 14:06:00 - INFO - __main__ -   Step: 1901, LR: 3.7062854155013496e-07, Loss: 0.3968377709388733
2024-08-04T21:06:08.970433606Z 
 33%|███▎      | 1902/5712 [4:28:00<8:42:55,  8.24s/it]08/04/2024 14:06:08 - INFO - __main__ -   Step: 1902, LR: 3.7053126291981806e-07, Loss: 0.49555808305740356
2024-08-04T21:06:17.423083453Z 
 33%|███▎      | 1903/5712 [4:28:08<8:46:56,  8.30s/it]08/04/2024 14:06:17 - INFO - __main__ -   Step: 1903, LR: 3.7043398428950116e-07, Loss: 0.44832944869995117
2024-08-04T21:06:26.493233771Z 
 33%|███▎      | 1904/5712 [4:28:17<9:01:27,  8.53s/it]08/04/2024 14:06:26 - INFO - __main__ -   Step: 1904, LR: 3.703367056591843e-07, Loss: 0.5210217237472534
2024-08-04T21:06:35.613188213Z Configuration saved in /output/epoch_0/config.json
2024-08-04T21:06:35.613284661Z Configuration saved in /output/epoch_0/generation_config.json
2024-08-04T21:06:46.176812927Z The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at /output/epoch_0/pytorch_model.bin.index.json.
2024-08-04T21:06:54.867151368Z 
 33%|███▎      | 1905/5712 [4:28:46<15:19:01, 14.48s/it]08/04/2024 14:06:54 - INFO - __main__ -   Step: 1905, LR: 3.702394270288674e-07, Loss: 0.27736949920654297
2024-08-04T21:07:03.061383088Z 
 33%|███▎      | 1906/5712 [4:28:54<13:19:04, 12.60s/it]08/04/2024 14:07:03 - INFO - __main__ -   Step: 1906, LR: 3.701421483985505e-07, Loss: 0.1621360331773758
2024-08-04T21:07:12.073725196Z 
 33%|███▎      | 1907/5712 [4:29:03<12:10:40, 11.52s/it]08/04/2024 14:07:12 - INFO - __main__ -   Step: 1907, LR: 3.700448697682336e-07, Loss: 0.2022683322429657
2024-08-04T21:07:20.785128310Z 
 33%|███▎      | 1908/5712 [4:29:11<11:17:01, 10.68s/it]08/04/2024 14:07:20 - INFO - __main__ -   Step: 1908, LR: 3.6994759113791676e-07, Loss: 0.1737179458141327
2024-08-04T21:07:28.954658965Z 
 33%|███▎      | 1909/5712 [4:29:20<10:29:08,  9.93s/it]08/04/2024 14:07:28 - INFO - __main__ -   Step: 1909, LR: 3.6985031250759986e-07, Loss: 0.18525071442127228
2024-08-04T21:07:36.928357233Z 
 33%|███▎      | 1910/5712 [4:29:28<9:51:51,  9.34s/it] 08/04/2024 14:07:36 - INFO - __main__ -   Step: 1910, LR: 3.69753033877283e-07, Loss: 0.2858694791793823
2024-08-04T21:07:46.036354803Z 
 33%|███▎      | 1911/5712 [4:29:37<9:47:17,  9.27s/it]08/04/2024 14:07:46 - INFO - __main__ -   Step: 1911, LR: 3.696557552469661e-07, Loss: 0.20561052858829498
2024-08-04T21:07:54.982796155Z 
 33%|███▎      | 1912/5712 [4:29:46<9:40:58,  9.17s/it]08/04/2024 14:07:54 - INFO - __main__ -   Step: 1912, LR: 3.6955847661664926e-07, Loss: 0.2895287573337555
2024-08-04T21:08:03.708966636Z 
 33%|███▎      | 1913/5712 [4:29:54<9:32:19,  9.04s/it]08/04/2024 14:08:03 - INFO - __main__ -   Step: 1913, LR: 3.6946119798633236e-07, Loss: 0.1730615794658661
2024-08-04T21:08:12.343142422Z 
 34%|███▎      | 1914/5712 [4:30:03<9:24:29,  8.92s/it]08/04/2024 14:08:12 - INFO - __main__ -   Step: 1914, LR: 3.6936391935601546e-07, Loss: 0.24684607982635498
2024-08-04T21:08:21.316893170Z 
 34%|███▎      | 1915/5712 [4:30:12<9:25:24,  8.93s/it]08/04/2024 14:08:21 - INFO - __main__ -   Step: 1915, LR: 3.6926664072569856e-07, Loss: 0.19628089666366577
2024-08-04T21:08:29.625913437Z 
 34%|███▎      | 1916/5712 [4:30:20<9:13:22,  8.75s/it]08/04/2024 14:08:29 - INFO - __main__ -   Step: 1916, LR: 3.691693620953817e-07, Loss: 0.2927337884902954
2024-08-04T21:08:37.865954203Z 
 34%|███▎      | 1917/5712 [4:30:29<9:03:37,  8.59s/it]08/04/2024 14:08:37 - INFO - __main__ -   Step: 1917, LR: 3.690720834650648e-07, Loss: 0.2540285587310791
2024-08-04T21:08:45.589614888Z 
 34%|███▎      | 1918/5712 [4:30:36<8:46:56,  8.33s/it]08/04/2024 14:08:45 - INFO - __main__ -   Step: 1918, LR: 3.689748048347479e-07, Loss: 0.19817037880420685
2024-08-04T21:08:53.978679012Z 
 34%|███▎      | 1919/5712 [4:30:45<8:47:51,  8.35s/it]08/04/2024 14:08:53 - INFO - __main__ -   Step: 1919, LR: 3.68877526204431e-07, Loss: 0.2013353556394577
2024-08-04T21:09:03.016797233Z 
 34%|███▎      | 1920/5712 [4:30:54<9:00:46,  8.56s/it]08/04/2024 14:09:03 - INFO - __main__ -   Step: 1920, LR: 3.687802475741141e-07, Loss: 0.2514387369155884
2024-08-04T21:09:11.764941408Z 
 34%|███▎      | 1921/5712 [4:31:02<9:04:15,  8.61s/it]08/04/2024 14:09:11 - INFO - __main__ -   Step: 1921, LR: 3.6868296894379726e-07, Loss: 0.1877399981021881
2024-08-04T21:09:20.536570900Z 
 34%|███▎      | 1922/5712 [4:31:11<9:07:06,  8.66s/it]08/04/2024 14:09:20 - INFO - __main__ -   Step: 1922, LR: 3.6858569031348036e-07, Loss: 0.2743479907512665
2024-08-04T21:09:29.059420849Z 
 34%|███▎      | 1923/5712 [4:31:20<9:04:20,  8.62s/it]08/04/2024 14:09:29 - INFO - __main__ -   Step: 1923, LR: 3.6848841168316346e-07, Loss: 0.1713678240776062
2024-08-04T21:09:37.409444961Z 
 34%|███▎      | 1924/5712 [4:31:28<8:59:05,  8.54s/it]08/04/2024 14:09:37 - INFO - __main__ -   Step: 1924, LR: 3.6839113305284656e-07, Loss: 0.15773916244506836
2024-08-04T21:09:46.560761424Z 
 34%|███▎      | 1925/5712 [4:31:37<9:10:32,  8.72s/it]08/04/2024 14:09:46 - INFO - __main__ -   Step: 1925, LR: 3.682938544225297e-07, Loss: 0.23038998246192932
2024-08-04T21:09:54.607311145Z 
 34%|███▎      | 1926/5712 [4:31:45<8:57:35,  8.52s/it]08/04/2024 14:09:54 - INFO - __main__ -   Step: 1926, LR: 3.681965757922128e-07, Loss: 0.1138637363910675
2024-08-04T21:10:03.215127946Z 
 34%|███▎      | 1927/5712 [4:31:54<8:59:07,  8.55s/it]08/04/2024 14:10:03 - INFO - __main__ -   Step: 1927, LR: 3.680992971618959e-07, Loss: 0.23923015594482422
2024-08-04T21:10:12.371063626Z 
 34%|███▍      | 1928/5712 [4:32:03<9:10:31,  8.73s/it]08/04/2024 14:10:12 - INFO - __main__ -   Step: 1928, LR: 3.6800201853157906e-07, Loss: 0.3160479664802551
2024-08-04T21:10:20.576910639Z 
 34%|███▍      | 1929/5712 [4:32:11<9:00:28,  8.57s/it]08/04/2024 14:10:20 - INFO - __main__ -   Step: 1929, LR: 3.679047399012622e-07, Loss: 0.23568478226661682
2024-08-04T21:10:29.051508211Z 
 34%|███▍      | 1930/5712 [4:32:20<8:58:28,  8.54s/it]08/04/2024 14:10:29 - INFO - __main__ -   Step: 1930, LR: 3.678074612709453e-07, Loss: 0.1503438949584961
2024-08-04T21:10:37.633127618Z 
 34%|███▍      | 1931/5712 [4:32:28<8:59:01,  8.55s/it]08/04/2024 14:10:37 - INFO - __main__ -   Step: 1931, LR: 3.677101826406284e-07, Loss: 0.18696030974388123
2024-08-04T21:10:46.207080634Z 
 34%|███▍      | 1932/5712 [4:32:37<8:59:19,  8.56s/it]08/04/2024 14:10:46 - INFO - __main__ -   Step: 1932, LR: 3.676129040103115e-07, Loss: 0.17758211493492126
2024-08-04T21:10:54.836626454Z 
 34%|███▍      | 1933/5712 [4:32:45<9:00:28,  8.58s/it]08/04/2024 14:10:54 - INFO - __main__ -   Step: 1933, LR: 3.6751562537999466e-07, Loss: 0.21983420848846436
2024-08-04T21:11:03.013250111Z 
 34%|███▍      | 1934/5712 [4:32:54<8:52:41,  8.46s/it]08/04/2024 14:11:03 - INFO - __main__ -   Step: 1934, LR: 3.6741834674967776e-07, Loss: 0.14973007142543793
2024-08-04T21:11:11.005768699Z 
 34%|███▍      | 1935/5712 [4:33:02<8:43:43,  8.32s/it]08/04/2024 14:11:11 - INFO - __main__ -   Step: 1935, LR: 3.6732106811936086e-07, Loss: 0.24981406331062317
2024-08-04T21:11:19.130916772Z 
 34%|███▍      | 1936/5712 [4:33:10<8:39:54,  8.26s/it]08/04/2024 14:11:19 - INFO - __main__ -   Step: 1936, LR: 3.6722378948904396e-07, Loss: 0.1485058218240738
2024-08-04T21:11:28.314575773Z 
 34%|███▍      | 1937/5712 [4:33:19<8:57:10,  8.54s/it]08/04/2024 14:11:28 - INFO - __main__ -   Step: 1937, LR: 3.671265108587271e-07, Loss: 0.17212167382240295
2024-08-04T21:11:36.781507241Z 
 34%|███▍      | 1938/5712 [4:33:27<8:55:42,  8.52s/it]08/04/2024 14:11:36 - INFO - __main__ -   Step: 1938, LR: 3.670292322284102e-07, Loss: 0.15584474802017212
2024-08-04T21:11:45.436891536Z 
 34%|███▍      | 1939/5712 [4:33:36<8:58:10,  8.56s/it]08/04/2024 14:11:45 - INFO - __main__ -   Step: 1939, LR: 3.669319535980933e-07, Loss: 0.16937875747680664
2024-08-04T21:11:54.283297521Z 
 34%|███▍      | 1940/5712 [4:33:45<9:03:27,  8.64s/it]08/04/2024 14:11:54 - INFO - __main__ -   Step: 1940, LR: 3.668346749677764e-07, Loss: 0.2431279420852661
2024-08-04T21:12:02.990007406Z 
 34%|███▍      | 1941/5712 [4:33:54<9:04:29,  8.66s/it]08/04/2024 14:12:02 - INFO - __main__ -   Step: 1941, LR: 3.6673739633745956e-07, Loss: 0.23600724339485168
2024-08-04T21:12:11.395681338Z 
 34%|███▍      | 1942/5712 [4:34:02<8:59:28,  8.59s/it]08/04/2024 14:12:11 - INFO - __main__ -   Step: 1942, LR: 3.6664011770714266e-07, Loss: 0.15526053309440613
2024-08-04T21:12:18.977013207Z 
 34%|███▍      | 1943/5712 [4:34:10<8:40:23,  8.28s/it]08/04/2024 14:12:18 - INFO - __main__ -   Step: 1943, LR: 3.6654283907682576e-07, Loss: 0.20736804604530334
2024-08-04T21:12:27.463075015Z 
 34%|███▍      | 1944/5712 [4:34:18<8:44:04,  8.35s/it]08/04/2024 14:12:27 - INFO - __main__ -   Step: 1944, LR: 3.6644556044650886e-07, Loss: 0.21730144321918488
2024-08-04T21:12:36.781894197Z 
 34%|███▍      | 1945/5712 [4:34:27<9:02:16,  8.64s/it]08/04/2024 14:12:36 - INFO - __main__ -   Step: 1945, LR: 3.66348281816192e-07, Loss: 0.23438677191734314
2024-08-04T21:12:45.464708470Z 
 34%|███▍      | 1946/5712 [4:34:36<9:02:59,  8.65s/it]08/04/2024 14:12:45 - INFO - __main__ -   Step: 1946, LR: 3.6625100318587516e-07, Loss: 0.19662682712078094
2024-08-04T21:12:53.927861306Z 
 34%|███▍      | 1947/5712 [4:34:45<8:59:18,  8.59s/it]08/04/2024 14:12:53 - INFO - __main__ -   Step: 1947, LR: 3.6615372455555826e-07, Loss: 0.20241104066371918
2024-08-04T21:13:02.673101584Z 
 34%|███▍      | 1948/5712 [4:34:53<9:01:58,  8.64s/it]08/04/2024 14:13:02 - INFO - __main__ -   Step: 1948, LR: 3.6605644592524136e-07, Loss: 0.23788851499557495
2024-08-04T21:13:11.609722642Z 
 34%|███▍      | 1949/5712 [4:35:02<9:07:27,  8.73s/it]08/04/2024 14:13:11 - INFO - __main__ -   Step: 1949, LR: 3.659591672949245e-07, Loss: 0.2651084065437317
2024-08-04T21:13:19.680432441Z 
 34%|███▍      | 1950/5712 [4:35:10<8:54:55,  8.53s/it]08/04/2024 14:13:19 - INFO - __main__ -   Step: 1950, LR: 3.658618886646076e-07, Loss: 0.17589712142944336
2024-08-04T21:13:27.816802838Z 
 34%|███▍      | 1951/5712 [4:35:18<8:47:21,  8.41s/it]08/04/2024 14:13:27 - INFO - __main__ -   Step: 1951, LR: 3.657646100342907e-07, Loss: 0.18653807044029236
2024-08-04T21:13:36.010167519Z 
 34%|███▍      | 1952/5712 [4:35:27<8:43:05,  8.35s/it]08/04/2024 14:13:36 - INFO - __main__ -   Step: 1952, LR: 3.656673314039738e-07, Loss: 0.18214035034179688
2024-08-04T21:13:44.512580014Z 
 34%|███▍      | 1953/5712 [4:35:35<8:45:51,  8.39s/it]08/04/2024 14:13:44 - INFO - __main__ -   Step: 1953, LR: 3.6557005277365696e-07, Loss: 0.22576750814914703
2024-08-04T21:13:53.413461439Z 
 34%|███▍      | 1954/5712 [4:35:44<8:55:15,  8.55s/it]08/04/2024 14:13:53 - INFO - __main__ -   Step: 1954, LR: 3.6547277414334006e-07, Loss: 0.16929569840431213
2024-08-04T21:14:02.310077676Z 
 34%|███▍      | 1955/5712 [4:35:53<9:01:42,  8.65s/it]08/04/2024 14:14:02 - INFO - __main__ -   Step: 1955, LR: 3.6537549551302316e-07, Loss: 0.2583381235599518
2024-08-04T21:14:10.503811636Z 
 34%|███▍      | 1956/5712 [4:36:01<8:52:58,  8.51s/it]08/04/2024 14:14:10 - INFO - __main__ -   Step: 1956, LR: 3.6527821688270626e-07, Loss: 0.23662206530570984
2024-08-04T21:14:18.932815557Z 
 34%|███▍      | 1957/5712 [4:36:10<8:51:13,  8.49s/it]08/04/2024 14:14:18 - INFO - __main__ -   Step: 1957, LR: 3.6518093825238935e-07, Loss: 0.19108328223228455
2024-08-04T21:14:27.518611079Z 
 34%|███▍      | 1958/5712 [4:36:18<8:52:55,  8.52s/it]08/04/2024 14:14:27 - INFO - __main__ -   Step: 1958, LR: 3.650836596220725e-07, Loss: 0.1837230771780014
2024-08-04T21:14:35.571291187Z 
 34%|███▍      | 1959/5712 [4:36:26<8:44:03,  8.38s/it]08/04/2024 14:14:35 - INFO - __main__ -   Step: 1959, LR: 3.649863809917556e-07, Loss: 0.2764347195625305
2024-08-04T21:14:43.916038563Z 
 34%|███▍      | 1960/5712 [4:36:35<8:43:17,  8.37s/it]08/04/2024 14:14:43 - INFO - __main__ -   Step: 1960, LR: 3.648891023614387e-07, Loss: 0.16083642840385437
2024-08-04T21:14:52.665642784Z 
 34%|███▍      | 1961/5712 [4:36:43<8:50:18,  8.48s/it]08/04/2024 14:14:52 - INFO - __main__ -   Step: 1961, LR: 3.647918237311218e-07, Loss: 0.18455666303634644
2024-08-04T21:15:01.955283927Z 
 34%|███▍      | 1962/5712 [4:36:53<9:05:16,  8.72s/it]08/04/2024 14:15:01 - INFO - __main__ -   Step: 1962, LR: 3.6469454510080496e-07, Loss: 0.20442506670951843
2024-08-04T21:15:10.709207098Z 
 34%|███▍      | 1963/5712 [4:37:01<9:05:41,  8.73s/it]08/04/2024 14:15:10 - INFO - __main__ -   Step: 1963, LR: 3.6459726647048805e-07, Loss: 0.2465789020061493
2024-08-04T21:15:18.943793637Z 
 34%|███▍      | 1964/5712 [4:37:10<8:56:12,  8.58s/it]08/04/2024 14:15:18 - INFO - __main__ -   Step: 1964, LR: 3.644999878401712e-07, Loss: 0.19541501998901367
2024-08-04T21:15:27.786932345Z 
 34%|███▍      | 1965/5712 [4:37:18<9:00:53,  8.66s/it]08/04/2024 14:15:27 - INFO - __main__ -   Step: 1965, LR: 3.644027092098543e-07, Loss: 0.26543280482292175
2024-08-04T21:15:36.417727584Z 
 34%|███▍      | 1966/5712 [4:37:27<9:00:12,  8.65s/it]08/04/2024 14:15:36 - INFO - __main__ -   Step: 1966, LR: 3.6430543057953746e-07, Loss: 0.19024242460727692
2024-08-04T21:15:44.686869000Z 
 34%|███▍      | 1967/5712 [4:37:35<8:52:52,  8.54s/it]08/04/2024 14:15:44 - INFO - __main__ -   Step: 1967, LR: 3.6420815194922056e-07, Loss: 0.25175148248672485
2024-08-04T21:15:52.965637100Z 
 34%|███▍      | 1968/5712 [4:37:44<8:47:53,  8.46s/it]08/04/2024 14:15:52 - INFO - __main__ -   Step: 1968, LR: 3.6411087331890366e-07, Loss: 0.22465452551841736
2024-08-04T21:16:01.450185160Z 
 34%|███▍      | 1969/5712 [4:37:52<8:48:12,  8.47s/it]08/04/2024 14:16:01 - INFO - __main__ -   Step: 1969, LR: 3.6401359468858675e-07, Loss: 0.18514293432235718
2024-08-04T21:16:10.422930892Z 
 34%|███▍      | 1970/5712 [4:38:01<8:57:31,  8.62s/it]08/04/2024 14:16:10 - INFO - __main__ -   Step: 1970, LR: 3.639163160582699e-07, Loss: 0.2769058644771576
2024-08-04T21:16:19.590457131Z 
 35%|███▍      | 1971/5712 [4:38:10<9:07:39,  8.78s/it]08/04/2024 14:16:19 - INFO - __main__ -   Step: 1971, LR: 3.63819037427953e-07, Loss: 0.2176961749792099
2024-08-04T21:16:28.315977446Z 
 35%|███▍      | 1972/5712 [4:38:19<9:06:24,  8.77s/it]08/04/2024 14:16:28 - INFO - __main__ -   Step: 1972, LR: 3.637217587976361e-07, Loss: 0.19512970745563507
2024-08-04T21:16:36.822389731Z 
 35%|███▍      | 1973/5712 [4:38:27<9:01:25,  8.69s/it]08/04/2024 14:16:36 - INFO - __main__ -   Step: 1973, LR: 3.636244801673192e-07, Loss: 0.25638818740844727
2024-08-04T21:16:45.283467379Z 
 35%|███▍      | 1974/5712 [4:38:36<8:57:02,  8.62s/it]08/04/2024 14:16:45 - INFO - __main__ -   Step: 1974, LR: 3.6352720153700236e-07, Loss: 0.23006436228752136
2024-08-04T21:16:54.118406613Z 
 35%|███▍      | 1975/5712 [4:38:45<9:00:53,  8.68s/it]08/04/2024 14:16:54 - INFO - __main__ -   Step: 1975, LR: 3.6342992290668546e-07, Loss: 0.13423027098178864
2024-08-04T21:17:02.590108887Z 
 35%|███▍      | 1976/5712 [4:38:53<8:56:46,  8.62s/it]08/04/2024 14:17:02 - INFO - __main__ -   Step: 1976, LR: 3.6333264427636855e-07, Loss: 0.21096894145011902
2024-08-04T21:17:10.531362638Z 
 35%|███▍      | 1977/5712 [4:39:01<8:43:56,  8.42s/it]08/04/2024 14:17:10 - INFO - __main__ -   Step: 1977, LR: 3.6323536564605165e-07, Loss: 0.19741666316986084
2024-08-04T21:17:19.289090345Z 
 35%|███▍      | 1978/5712 [4:39:10<8:50:10,  8.52s/it]08/04/2024 14:17:19 - INFO - __main__ -   Step: 1978, LR: 3.631380870157348e-07, Loss: 0.13357913494110107
2024-08-04T21:17:29.074095409Z 
 35%|███▍      | 1979/5712 [4:39:20<9:13:38,  8.90s/it]08/04/2024 14:17:29 - INFO - __main__ -   Step: 1979, LR: 3.630408083854179e-07, Loss: 0.2808229923248291
2024-08-04T21:17:37.492025832Z 
 35%|███▍      | 1980/5712 [4:39:28<9:04:32,  8.75s/it]08/04/2024 14:17:37 - INFO - __main__ -   Step: 1980, LR: 3.62943529755101e-07, Loss: 0.1620747596025467
2024-08-04T21:17:45.592523461Z 
 35%|███▍      | 1981/5712 [4:39:36<8:52:11,  8.56s/it]08/04/2024 14:17:45 - INFO - __main__ -   Step: 1981, LR: 3.628462511247841e-07, Loss: 0.15832605957984924
2024-08-04T21:17:54.296666707Z 
 35%|███▍      | 1982/5712 [4:39:45<8:54:44,  8.60s/it]08/04/2024 14:17:54 - INFO - __main__ -   Step: 1982, LR: 3.627489724944673e-07, Loss: 0.15598657727241516
2024-08-04T21:18:02.471575131Z 
 35%|███▍      | 1983/5712 [4:39:53<8:46:39,  8.47s/it]08/04/2024 14:18:02 - INFO - __main__ -   Step: 1983, LR: 3.626516938641504e-07, Loss: 0.2741719186306
2024-08-04T21:18:10.725690811Z 
 35%|███▍      | 1984/5712 [4:40:01<8:42:25,  8.41s/it]08/04/2024 14:18:10 - INFO - __main__ -   Step: 1984, LR: 3.625544152338335e-07, Loss: 0.30445343255996704
2024-08-04T21:18:18.958473648Z 
 35%|███▍      | 1985/5712 [4:40:10<8:39:00,  8.36s/it]08/04/2024 14:18:18 - INFO - __main__ -   Step: 1985, LR: 3.624571366035166e-07, Loss: 0.18825799226760864
2024-08-04T21:18:27.656691934Z 
 35%|███▍      | 1986/5712 [4:40:18<8:45:15,  8.46s/it]08/04/2024 14:18:27 - INFO - __main__ -   Step: 1986, LR: 3.6235985797319976e-07, Loss: 0.2165517807006836
2024-08-04T21:18:37.076450195Z 
 35%|███▍      | 1987/5712 [4:40:28<9:03:00,  8.75s/it]08/04/2024 14:18:37 - INFO - __main__ -   Step: 1987, LR: 3.6226257934288286e-07, Loss: 0.3289634883403778
2024-08-04T21:18:45.508031538Z 
 35%|███▍      | 1988/5712 [4:40:36<8:57:00,  8.65s/it]08/04/2024 14:18:45 - INFO - __main__ -   Step: 1988, LR: 3.6216530071256595e-07, Loss: 0.21347171068191528
2024-08-04T21:18:54.983583576Z 
 35%|███▍      | 1989/5712 [4:40:46<9:12:11,  8.90s/it]08/04/2024 14:18:54 - INFO - __main__ -   Step: 1989, LR: 3.6206802208224905e-07, Loss: 0.2303375005722046
2024-08-04T21:19:03.477096446Z 
 35%|███▍      | 1990/5712 [4:40:54<9:04:30,  8.78s/it]08/04/2024 14:19:03 - INFO - __main__ -   Step: 1990, LR: 3.619707434519322e-07, Loss: 0.29738354682922363
2024-08-04T21:19:12.192741801Z 
 35%|███▍      | 1991/5712 [4:41:03<9:03:12,  8.76s/it]08/04/2024 14:19:12 - INFO - __main__ -   Step: 1991, LR: 3.618734648216153e-07, Loss: 0.2753898501396179
2024-08-04T21:19:20.247535867Z 
 35%|███▍      | 1992/5712 [4:41:11<8:49:57,  8.55s/it]08/04/2024 14:19:20 - INFO - __main__ -   Step: 1992, LR: 3.617761861912984e-07, Loss: 0.16971367597579956
2024-08-04T21:19:29.287548267Z 
 35%|███▍      | 1993/5712 [4:41:20<8:58:58,  8.70s/it]08/04/2024 14:19:29 - INFO - __main__ -   Step: 1993, LR: 3.616789075609815e-07, Loss: 0.17450211942195892
2024-08-04T21:19:37.756390309Z 
 35%|███▍      | 1994/5712 [4:41:28<8:54:36,  8.63s/it]08/04/2024 14:19:37 - INFO - __main__ -   Step: 1994, LR: 3.6158162893066465e-07, Loss: 0.2090698927640915
2024-08-04T21:19:46.488914597Z 
 35%|███▍      | 1995/5712 [4:41:37<8:56:25,  8.66s/it]08/04/2024 14:19:46 - INFO - __main__ -   Step: 1995, LR: 3.6148435030034775e-07, Loss: 0.17778365314006805
2024-08-04T21:19:55.673426632Z 
 35%|███▍      | 1996/5712 [4:41:46<9:06:01,  8.82s/it]08/04/2024 14:19:55 - INFO - __main__ -   Step: 1996, LR: 3.6138707167003085e-07, Loss: 0.22216863930225372
2024-08-04T21:20:03.678497056Z 
 35%|███▍      | 1997/5712 [4:41:54<8:50:49,  8.57s/it]08/04/2024 14:20:03 - INFO - __main__ -   Step: 1997, LR: 3.6128979303971395e-07, Loss: 0.1546754539012909
2024-08-04T21:20:12.301935223Z 
 35%|███▍      | 1998/5712 [4:42:03<8:51:37,  8.59s/it]08/04/2024 14:20:12 - INFO - __main__ -   Step: 1998, LR: 3.6119251440939705e-07, Loss: 0.23470738530158997
2024-08-04T21:20:21.195398542Z 
 35%|███▍      | 1999/5712 [4:42:12<8:57:07,  8.68s/it]08/04/2024 14:20:21 - INFO - __main__ -   Step: 1999, LR: 3.610952357790802e-07, Loss: 0.2055879533290863
2024-08-04T21:20:29.197490691Z 
 35%|███▌      | 2000/5712 [4:42:20<8:44:25,  8.48s/it]08/04/2024 14:20:29 - INFO - __main__ -   Step: 2000, LR: 3.6099795714876335e-07, Loss: 0.21618467569351196
2024-08-04T21:20:38.185470602Z 
 35%|███▌      | 2001/5712 [4:42:29<8:53:45,  8.63s/it]08/04/2024 14:20:38 - INFO - __main__ -   Step: 2001, LR: 3.6090067851844645e-07, Loss: 0.25496676564216614
2024-08-04T21:20:46.265521794Z 
 35%|███▌      | 2002/5712 [4:42:37<8:43:25,  8.47s/it]08/04/2024 14:20:46 - INFO - __main__ -   Step: 2002, LR: 3.6080339988812955e-07, Loss: 0.23321948945522308
2024-08-04T21:20:55.170124169Z 
 35%|███▌      | 2003/5712 [4:42:46<8:51:26,  8.60s/it]08/04/2024 14:20:55 - INFO - __main__ -   Step: 2003, LR: 3.607061212578127e-07, Loss: 0.18666517734527588
2024-08-04T21:21:04.221753469Z 
 35%|███▌      | 2004/5712 [4:42:55<8:59:43,  8.73s/it]08/04/2024 14:21:04 - INFO - __main__ -   Step: 2004, LR: 3.606088426274958e-07, Loss: 0.3018369972705841
2024-08-04T21:21:12.725030735Z 
 35%|███▌      | 2005/5712 [4:43:03<8:55:18,  8.66s/it]08/04/2024 14:21:12 - INFO - __main__ -   Step: 2005, LR: 3.605115639971789e-07, Loss: 0.1443633884191513
2024-08-04T21:21:20.928689057Z 
 35%|███▌      | 2006/5712 [4:43:12<8:46:37,  8.53s/it]08/04/2024 14:21:20 - INFO - __main__ -   Step: 2006, LR: 3.60414285366862e-07, Loss: 0.23991945385932922
2024-08-04T21:21:29.333534471Z 
 35%|███▌      | 2007/5712 [4:43:20<8:44:14,  8.49s/it]08/04/2024 14:21:29 - INFO - __main__ -   Step: 2007, LR: 3.6031700673654515e-07, Loss: 0.30618396401405334
2024-08-04T21:21:38.263609749Z 
 35%|███▌      | 2008/5712 [4:43:29<8:52:15,  8.62s/it]08/04/2024 14:21:38 - INFO - __main__ -   Step: 2008, LR: 3.6021972810622825e-07, Loss: 0.2684161067008972
2024-08-04T21:21:46.232972955Z 
 35%|███▌      | 2009/5712 [4:43:37<8:40:02,  8.43s/it]08/04/2024 14:21:46 - INFO - __main__ -   Step: 2009, LR: 3.6012244947591135e-07, Loss: 0.27547168731689453
2024-08-04T21:21:54.577662483Z 
 35%|███▌      | 2010/5712 [4:43:45<8:38:22,  8.40s/it]08/04/2024 14:21:54 - INFO - __main__ -   Step: 2010, LR: 3.6002517084559445e-07, Loss: 0.21677812933921814
2024-08-04T21:22:03.141509816Z 
 35%|███▌      | 2011/5712 [4:43:54<8:41:14,  8.45s/it]08/04/2024 14:22:03 - INFO - __main__ -   Step: 2011, LR: 3.599278922152776e-07, Loss: 0.22331205010414124
2024-08-04T21:22:11.961394529Z 
 35%|███▌      | 2012/5712 [4:44:03<8:47:56,  8.56s/it]08/04/2024 14:22:11 - INFO - __main__ -   Step: 2012, LR: 3.598306135849607e-07, Loss: 0.1697598695755005
2024-08-04T21:22:20.978830603Z 
 35%|███▌      | 2013/5712 [4:44:12<8:56:11,  8.70s/it]08/04/2024 14:22:20 - INFO - __main__ -   Step: 2013, LR: 3.597333349546438e-07, Loss: 0.18572261929512024
2024-08-04T21:22:29.274286275Z 
 35%|███▌      | 2014/5712 [4:44:20<8:48:39,  8.58s/it]08/04/2024 14:22:29 - INFO - __main__ -   Step: 2014, LR: 3.596360563243269e-07, Loss: 0.19594591856002808
2024-08-04T21:22:37.475100425Z 
 35%|███▌      | 2015/5712 [4:44:28<8:41:33,  8.46s/it]08/04/2024 14:22:37 - INFO - __main__ -   Step: 2015, LR: 3.5953877769401005e-07, Loss: 0.15559224784374237
2024-08-04T21:22:46.624791179Z 
 35%|███▌      | 2016/5712 [4:44:37<8:54:03,  8.67s/it]08/04/2024 14:22:46 - INFO - __main__ -   Step: 2016, LR: 3.5944149906369315e-07, Loss: 0.13964372873306274
2024-08-04T21:22:54.812263005Z 
 35%|███▌      | 2017/5712 [4:44:45<8:45:01,  8.53s/it]08/04/2024 14:22:54 - INFO - __main__ -   Step: 2017, LR: 3.5934422043337625e-07, Loss: 0.20171456038951874
2024-08-04T21:23:03.733195471Z 
 35%|███▌      | 2018/5712 [4:44:54<8:52:11,  8.64s/it]08/04/2024 14:23:03 - INFO - __main__ -   Step: 2018, LR: 3.592469418030594e-07, Loss: 0.25914329290390015
2024-08-04T21:23:11.673316182Z 
 35%|███▌      | 2019/5712 [4:45:02<8:39:02,  8.43s/it]08/04/2024 14:23:11 - INFO - __main__ -   Step: 2019, LR: 3.5914966317274255e-07, Loss: 0.25625383853912354
2024-08-04T21:23:20.349831734Z 
 35%|███▌      | 2020/5712 [4:45:11<8:43:23,  8.51s/it]08/04/2024 14:23:20 - INFO - __main__ -   Step: 2020, LR: 3.5905238454242565e-07, Loss: 0.23598836362361908
2024-08-04T21:23:28.914088877Z 
 35%|███▌      | 2021/5712 [4:45:20<8:44:19,  8.52s/it]08/04/2024 14:23:28 - INFO - __main__ -   Step: 2021, LR: 3.5895510591210875e-07, Loss: 0.25793713331222534
2024-08-04T21:23:37.161875261Z 
 35%|███▌      | 2022/5712 [4:45:28<8:39:06,  8.44s/it]08/04/2024 14:23:37 - INFO - __main__ -   Step: 2022, LR: 3.5885782728179185e-07, Loss: 0.20799702405929565
2024-08-04T21:23:45.339612028Z 
 35%|███▌      | 2023/5712 [4:45:36<8:34:07,  8.36s/it]08/04/2024 14:23:45 - INFO - __main__ -   Step: 2023, LR: 3.58760548651475e-07, Loss: 0.2674406170845032
2024-08-04T21:23:53.829078476Z 
 35%|███▌      | 2024/5712 [4:45:44<8:36:19,  8.40s/it]08/04/2024 14:23:53 - INFO - __main__ -   Step: 2024, LR: 3.586632700211581e-07, Loss: 0.3528451919555664
2024-08-04T21:24:02.669426725Z 
 35%|███▌      | 2025/5712 [4:45:53<8:44:18,  8.53s/it]08/04/2024 14:24:02 - INFO - __main__ -   Step: 2025, LR: 3.585659913908412e-07, Loss: 0.1977279931306839
2024-08-04T21:24:10.658051624Z 
 35%|███▌      | 2026/5712 [4:46:01<8:34:08,  8.37s/it]08/04/2024 14:24:10 - INFO - __main__ -   Step: 2026, LR: 3.584687127605243e-07, Loss: 0.16199904680252075
2024-08-04T21:24:19.668614133Z 
 35%|███▌      | 2027/5712 [4:46:10<8:45:49,  8.56s/it]08/04/2024 14:24:19 - INFO - __main__ -   Step: 2027, LR: 3.5837143413020745e-07, Loss: 0.22731880843639374
2024-08-04T21:24:28.103031061Z 
 36%|███▌      | 2028/5712 [4:46:19<8:43:19,  8.52s/it]08/04/2024 14:24:28 - INFO - __main__ -   Step: 2028, LR: 3.5827415549989055e-07, Loss: 0.2656831741333008
2024-08-04T21:24:36.847505505Z 
 36%|███▌      | 2029/5712 [4:46:27<8:47:16,  8.59s/it]08/04/2024 14:24:36 - INFO - __main__ -   Step: 2029, LR: 3.5817687686957365e-07, Loss: 0.16705214977264404
2024-08-04T21:24:45.507410285Z 
 36%|███▌      | 2030/5712 [4:46:36<8:48:23,  8.61s/it]08/04/2024 14:24:45 - INFO - __main__ -   Step: 2030, LR: 3.5807959823925675e-07, Loss: 0.1998826265335083
2024-08-04T21:24:53.634838718Z 
 36%|███▌      | 2031/5712 [4:46:44<8:39:22,  8.47s/it]08/04/2024 14:24:53 - INFO - __main__ -   Step: 2031, LR: 3.579823196089399e-07, Loss: 0.21329808235168457
2024-08-04T21:25:02.111202441Z 
 36%|███▌      | 2032/5712 [4:46:53<8:39:25,  8.47s/it]08/04/2024 14:25:02 - INFO - __main__ -   Step: 2032, LR: 3.57885040978623e-07, Loss: 0.17982015013694763
2024-08-04T21:25:11.268581759Z 
 36%|███▌      | 2033/5712 [4:47:02<8:51:56,  8.68s/it]08/04/2024 14:25:11 - INFO - __main__ -   Step: 2033, LR: 3.577877623483061e-07, Loss: 0.1829565316438675
2024-08-04T21:25:19.309637007Z 
 36%|███▌      | 2034/5712 [4:47:10<8:40:08,  8.49s/it]08/04/2024 14:25:19 - INFO - __main__ -   Step: 2034, LR: 3.576904837179892e-07, Loss: 0.1467355340719223
2024-08-04T21:25:27.601402640Z 
 36%|███▌      | 2035/5712 [4:47:18<8:36:27,  8.43s/it]08/04/2024 14:25:27 - INFO - __main__ -   Step: 2035, LR: 3.575932050876723e-07, Loss: 0.233341246843338
2024-08-04T21:25:36.353527076Z 
 36%|███▌      | 2036/5712 [4:47:27<8:42:16,  8.52s/it]08/04/2024 14:25:36 - INFO - __main__ -   Step: 2036, LR: 3.574959264573555e-07, Loss: 0.29087504744529724
2024-08-04T21:25:44.900168422Z 
 36%|███▌      | 2037/5712 [4:47:36<8:42:32,  8.53s/it]08/04/2024 14:25:44 - INFO - __main__ -   Step: 2037, LR: 3.573986478270386e-07, Loss: 0.19081133604049683
2024-08-04T21:25:53.746231238Z 
 36%|███▌      | 2038/5712 [4:47:44<8:48:10,  8.63s/it]08/04/2024 14:25:53 - INFO - __main__ -   Step: 2038, LR: 3.573013691967217e-07, Loss: 0.31505173444747925
2024-08-04T21:26:02.091706609Z 
 36%|███▌      | 2039/5712 [4:47:53<8:42:53,  8.54s/it]08/04/2024 14:26:02 - INFO - __main__ -   Step: 2039, LR: 3.572040905664048e-07, Loss: 0.27103543281555176
2024-08-04T21:26:10.083245798Z 
 36%|███▌      | 2040/5712 [4:48:01<8:32:38,  8.38s/it]08/04/2024 14:26:10 - INFO - __main__ -   Step: 2040, LR: 3.5710681193608795e-07, Loss: 0.14764627814292908
2024-08-04T21:26:18.411908778Z 
 36%|███▌      | 2041/5712 [4:48:09<8:31:37,  8.36s/it]08/04/2024 14:26:18 - INFO - __main__ -   Step: 2041, LR: 3.5700953330577105e-07, Loss: 0.19220750033855438
2024-08-04T21:26:26.878936849Z 
 36%|███▌      | 2042/5712 [4:48:18<8:33:24,  8.39s/it]08/04/2024 14:26:26 - INFO - __main__ -   Step: 2042, LR: 3.5691225467545415e-07, Loss: 0.20041102170944214
2024-08-04T21:26:35.348825128Z 
 36%|███▌      | 2043/5712 [4:48:26<8:34:40,  8.42s/it]08/04/2024 14:26:35 - INFO - __main__ -   Step: 2043, LR: 3.5681497604513725e-07, Loss: 0.2492709457874298
2024-08-04T21:26:44.138259650Z 
 36%|███▌      | 2044/5712 [4:48:35<8:41:22,  8.53s/it]08/04/2024 14:26:44 - INFO - __main__ -   Step: 2044, LR: 3.567176974148204e-07, Loss: 0.32603585720062256
2024-08-04T21:26:52.939181015Z 
 36%|███▌      | 2045/5712 [4:48:44<8:46:13,  8.61s/it]08/04/2024 14:26:52 - INFO - __main__ -   Step: 2045, LR: 3.566204187845035e-07, Loss: 0.1770179271697998
2024-08-04T21:27:01.218105685Z 
 36%|███▌      | 2046/5712 [4:48:52<8:40:00,  8.51s/it]08/04/2024 14:27:01 - INFO - __main__ -   Step: 2046, LR: 3.565231401541866e-07, Loss: 0.13600444793701172
2024-08-04T21:27:10.013763088Z 
 36%|███▌      | 2047/5712 [4:49:01<8:45:03,  8.60s/it]08/04/2024 14:27:10 - INFO - __main__ -   Step: 2047, LR: 3.564258615238697e-07, Loss: 0.1925843060016632
2024-08-04T21:27:17.687326413Z 
 36%|███▌      | 2048/5712 [4:49:08<8:28:02,  8.32s/it]08/04/2024 14:27:17 - INFO - __main__ -   Step: 2048, LR: 3.5632858289355285e-07, Loss: 0.23657837510108948
2024-08-04T21:27:26.020578291Z 
 36%|███▌      | 2049/5712 [4:49:17<8:28:09,  8.32s/it]08/04/2024 14:27:26 - INFO - __main__ -   Step: 2049, LR: 3.5623130426323595e-07, Loss: 0.28110000491142273
2024-08-04T21:27:34.404741356Z 
 36%|███▌      | 2050/5712 [4:49:25<8:29:07,  8.34s/it]08/04/2024 14:27:34 - INFO - __main__ -   Step: 2050, LR: 3.5613402563291905e-07, Loss: 0.20151546597480774
2024-08-04T21:27:42.848396355Z 
 36%|███▌      | 2051/5712 [4:49:33<8:30:51,  8.37s/it]08/04/2024 14:27:42 - INFO - __main__ -   Step: 2051, LR: 3.5603674700260215e-07, Loss: 0.31156498193740845
2024-08-04T21:27:51.321573406Z 
 36%|███▌      | 2052/5712 [4:49:42<8:32:33,  8.40s/it]08/04/2024 14:27:51 - INFO - __main__ -   Step: 2052, LR: 3.559394683722853e-07, Loss: 0.2076590657234192
2024-08-04T21:28:00.403245302Z 
 36%|███▌      | 2053/5712 [4:49:51<8:44:50,  8.61s/it]08/04/2024 14:28:00 - INFO - __main__ -   Step: 2053, LR: 3.558421897419684e-07, Loss: 0.20220348238945007
2024-08-04T21:28:09.298527485Z 
 36%|███▌      | 2054/5712 [4:50:00<8:49:59,  8.69s/it]08/04/2024 14:28:09 - INFO - __main__ -   Step: 2054, LR: 3.5574491111165155e-07, Loss: 0.15994992852210999
2024-08-04T21:28:17.649452866Z 
 36%|███▌      | 2055/5712 [4:50:08<8:43:34,  8.59s/it]08/04/2024 14:28:17 - INFO - __main__ -   Step: 2055, LR: 3.5564763248133465e-07, Loss: 0.230902299284935
2024-08-04T21:28:25.640217741Z 
 36%|███▌      | 2056/5712 [4:50:16<8:32:28,  8.41s/it]08/04/2024 14:28:25 - INFO - __main__ -   Step: 2056, LR: 3.555503538510178e-07, Loss: 0.19855831563472748
2024-08-04T21:28:34.154306916Z 
 36%|███▌      | 2057/5712 [4:50:25<8:34:14,  8.44s/it]08/04/2024 14:28:34 - INFO - __main__ -   Step: 2057, LR: 3.554530752207009e-07, Loss: 0.16405799984931946
2024-08-04T21:28:42.372443974Z 
 36%|███▌      | 2058/5712 [4:50:33<8:30:00,  8.37s/it]08/04/2024 14:28:42 - INFO - __main__ -   Step: 2058, LR: 3.55355796590384e-07, Loss: 0.16300427913665771
2024-08-04T21:28:50.900129586Z 
 36%|███▌      | 2059/5712 [4:50:42<8:32:40,  8.42s/it]08/04/2024 14:28:50 - INFO - __main__ -   Step: 2059, LR: 3.552585179600671e-07, Loss: 0.14157605171203613
2024-08-04T21:28:58.911063596Z 
 36%|███▌      | 2060/5712 [4:50:50<8:25:02,  8.30s/it]08/04/2024 14:28:58 - INFO - __main__ -   Step: 2060, LR: 3.5516123932975025e-07, Loss: 0.23530204594135284
2024-08-04T21:29:07.330015254Z 
 36%|███▌      | 2061/5712 [4:50:58<8:27:07,  8.33s/it]08/04/2024 14:29:07 - INFO - __main__ -   Step: 2061, LR: 3.5506396069943335e-07, Loss: 0.22918592393398285
2024-08-04T21:29:16.712062727Z 
 36%|███▌      | 2062/5712 [4:51:07<8:46:06,  8.65s/it]08/04/2024 14:29:16 - INFO - __main__ -   Step: 2062, LR: 3.5496668206911645e-07, Loss: 0.21880623698234558
2024-08-04T21:29:25.310894781Z 
 36%|███▌      | 2063/5712 [4:51:16<8:45:03,  8.63s/it]08/04/2024 14:29:25 - INFO - __main__ -   Step: 2063, LR: 3.5486940343879955e-07, Loss: 0.2127048671245575
2024-08-04T21:29:33.947195005Z 
 36%|███▌      | 2064/5712 [4:51:25<8:44:56,  8.63s/it]08/04/2024 14:29:33 - INFO - __main__ -   Step: 2064, LR: 3.547721248084827e-07, Loss: 0.22325220704078674
2024-08-04T21:29:41.956373294Z 
 36%|███▌      | 2065/5712 [4:51:33<8:33:26,  8.45s/it]08/04/2024 14:29:41 - INFO - __main__ -   Step: 2065, LR: 3.546748461781658e-07, Loss: 0.20964176952838898
2024-08-04T21:29:50.288060026Z 
 36%|███▌      | 2066/5712 [4:51:41<8:31:11,  8.41s/it]08/04/2024 14:29:50 - INFO - __main__ -   Step: 2066, LR: 3.545775675478489e-07, Loss: 0.1496063768863678
2024-08-04T21:29:59.078117102Z 
 36%|███▌      | 2067/5712 [4:51:50<8:37:56,  8.53s/it]08/04/2024 14:29:59 - INFO - __main__ -   Step: 2067, LR: 3.54480288917532e-07, Loss: 0.1951524019241333
2024-08-04T21:30:07.584796388Z 
 36%|███▌      | 2068/5712 [4:51:58<8:37:26,  8.52s/it]08/04/2024 14:30:07 - INFO - __main__ -   Step: 2068, LR: 3.5438301028721515e-07, Loss: 0.21551597118377686
2024-08-04T21:30:16.456999749Z 
 36%|███▌      | 2069/5712 [4:52:07<8:43:43,  8.63s/it]08/04/2024 14:30:16 - INFO - __main__ -   Step: 2069, LR: 3.5428573165689825e-07, Loss: 0.2334294319152832
2024-08-04T21:30:24.878053465Z 
 36%|███▌      | 2070/5712 [4:52:16<8:39:51,  8.56s/it]08/04/2024 14:30:24 - INFO - __main__ -   Step: 2070, LR: 3.5418845302658135e-07, Loss: 0.2723274827003479
2024-08-04T21:30:33.676786383Z 
 36%|███▋      | 2071/5712 [4:52:24<8:43:58,  8.63s/it]08/04/2024 14:30:33 - INFO - __main__ -   Step: 2071, LR: 3.5409117439626445e-07, Loss: 0.15306733548641205
2024-08-04T21:30:41.967377249Z 
 36%|███▋      | 2072/5712 [4:52:33<8:37:34,  8.53s/it]08/04/2024 14:30:41 - INFO - __main__ -   Step: 2072, LR: 3.5399389576594765e-07, Loss: 0.29481232166290283
2024-08-04T21:30:50.270535061Z 
 36%|███▋      | 2073/5712 [4:52:41<8:33:16,  8.46s/it]08/04/2024 14:30:50 - INFO - __main__ -   Step: 2073, LR: 3.5389661713563075e-07, Loss: 0.19622105360031128
2024-08-04T21:30:58.929677160Z 
 36%|███▋      | 2074/5712 [4:52:50<8:36:42,  8.52s/it]08/04/2024 14:30:58 - INFO - __main__ -   Step: 2074, LR: 3.5379933850531385e-07, Loss: 0.2645936608314514
2024-08-04T21:31:07.145595417Z 
 36%|███▋      | 2075/5712 [4:52:58<8:30:59,  8.43s/it]08/04/2024 14:31:07 - INFO - __main__ -   Step: 2075, LR: 3.5370205987499695e-07, Loss: 0.20087170600891113
2024-08-04T21:31:15.509708390Z 
 36%|███▋      | 2076/5712 [4:53:06<8:29:39,  8.41s/it]08/04/2024 14:31:15 - INFO - __main__ -   Step: 2076, LR: 3.5360478124468005e-07, Loss: 0.22830545902252197
2024-08-04T21:31:24.368890237Z 
 36%|███▋      | 2077/5712 [4:53:15<8:37:40,  8.54s/it]08/04/2024 14:31:24 - INFO - __main__ -   Step: 2077, LR: 3.535075026143632e-07, Loss: 0.2686956524848938
2024-08-04T21:31:32.860583925Z 
 36%|███▋      | 2078/5712 [4:53:24<8:36:34,  8.53s/it]08/04/2024 14:31:32 - INFO - __main__ -   Step: 2078, LR: 3.534102239840463e-07, Loss: 0.2294008731842041
2024-08-04T21:31:41.243187731Z 
 36%|███▋      | 2079/5712 [4:53:32<8:33:46,  8.49s/it]08/04/2024 14:31:41 - INFO - __main__ -   Step: 2079, LR: 3.533129453537294e-07, Loss: 0.2123306542634964
2024-08-04T21:31:49.268306443Z 
 36%|███▋      | 2080/5712 [4:53:40<8:25:16,  8.35s/it]08/04/2024 14:31:49 - INFO - __main__ -   Step: 2080, LR: 3.532156667234125e-07, Loss: 0.3210131824016571
2024-08-04T21:31:58.329830933Z 
 36%|███▋      | 2081/5712 [4:53:49<8:38:06,  8.56s/it]08/04/2024 14:31:58 - INFO - __main__ -   Step: 2081, LR: 3.5311838809309565e-07, Loss: 0.12362708151340485
2024-08-04T21:32:06.364362802Z 
 36%|███▋      | 2082/5712 [4:53:57<8:28:24,  8.40s/it]08/04/2024 14:32:06 - INFO - __main__ -   Step: 2082, LR: 3.5302110946277875e-07, Loss: 0.18873146176338196
2024-08-04T21:32:14.964829481Z 
 36%|███▋      | 2083/5712 [4:54:06<8:31:50,  8.46s/it]08/04/2024 14:32:14 - INFO - __main__ -   Step: 2083, LR: 3.5292383083246185e-07, Loss: 0.16905461251735687
2024-08-04T21:32:23.740517890Z 
 36%|███▋      | 2084/5712 [4:54:14<8:37:22,  8.56s/it]08/04/2024 14:32:23 - INFO - __main__ -   Step: 2084, LR: 3.5282655220214495e-07, Loss: 0.2610122561454773
2024-08-04T21:32:31.752633712Z 
 37%|███▋      | 2085/5712 [4:54:22<8:27:21,  8.39s/it]08/04/2024 14:32:31 - INFO - __main__ -   Step: 2085, LR: 3.527292735718281e-07, Loss: 0.12647762894630432
2024-08-04T21:32:40.269594884Z 
 37%|███▋      | 2086/5712 [4:54:31<8:29:28,  8.43s/it]08/04/2024 14:32:40 - INFO - __main__ -   Step: 2086, LR: 3.526319949415112e-07, Loss: 0.29374560713768005
2024-08-04T21:32:49.103352954Z 
 37%|███▋      | 2087/5712 [4:54:40<8:36:38,  8.55s/it]08/04/2024 14:32:49 - INFO - __main__ -   Step: 2087, LR: 3.525347163111943e-07, Loss: 0.22150132060050964
2024-08-04T21:32:57.372965286Z 
 37%|███▋      | 2088/5712 [4:54:48<8:31:23,  8.47s/it]08/04/2024 14:32:57 - INFO - __main__ -   Step: 2088, LR: 3.524374376808774e-07, Loss: 0.1596466451883316
2024-08-04T21:33:05.554997822Z 
 37%|███▋      | 2089/5712 [4:54:56<8:26:05,  8.38s/it]08/04/2024 14:33:05 - INFO - __main__ -   Step: 2089, LR: 3.5234015905056055e-07, Loss: 0.24689547717571259
2024-08-04T21:33:14.268572879Z 
 37%|███▋      | 2090/5712 [4:55:05<8:31:58,  8.48s/it]08/04/2024 14:33:14 - INFO - __main__ -   Step: 2090, LR: 3.522428804202437e-07, Loss: 0.3033357858657837
2024-08-04T21:33:22.592945563Z 
 37%|███▋      | 2091/5712 [4:55:13<8:28:59,  8.43s/it]08/04/2024 14:33:22 - INFO - __main__ -   Step: 2091, LR: 3.521456017899268e-07, Loss: 0.27364063262939453
2024-08-04T21:33:31.170095462Z 
 37%|███▋      | 2092/5712 [4:55:22<8:31:26,  8.48s/it]08/04/2024 14:33:31 - INFO - __main__ -   Step: 2092, LR: 3.520483231596099e-07, Loss: 0.22968819737434387
2024-08-04T21:33:39.202675134Z 
 37%|███▋      | 2093/5712 [4:55:30<8:23:15,  8.34s/it]08/04/2024 14:33:39 - INFO - __main__ -   Step: 2093, LR: 3.5195104452929305e-07, Loss: 0.2524434030056
2024-08-04T21:33:47.632602345Z 
 37%|███▋      | 2094/5712 [4:55:38<8:24:41,  8.37s/it]08/04/2024 14:33:47 - INFO - __main__ -   Step: 2094, LR: 3.5185376589897615e-07, Loss: 0.19922079145908356
2024-08-04T21:33:56.321146772Z 
 37%|███▋      | 2095/5712 [4:55:47<8:30:18,  8.47s/it]08/04/2024 14:33:56 - INFO - __main__ -   Step: 2095, LR: 3.5175648726865925e-07, Loss: 0.2287634015083313
2024-08-04T21:34:04.484773358Z 
 37%|███▋      | 2096/5712 [4:55:55<8:24:43,  8.37s/it]08/04/2024 14:34:04 - INFO - __main__ -   Step: 2096, LR: 3.5165920863834235e-07, Loss: 0.16021187603473663
2024-08-04T21:34:12.596079461Z 
 37%|███▋      | 2097/5712 [4:56:03<8:19:49,  8.30s/it]08/04/2024 14:34:12 - INFO - __main__ -   Step: 2097, LR: 3.515619300080255e-07, Loss: 0.22862748801708221
2024-08-04T21:34:20.708845254Z 
 37%|███▋      | 2098/5712 [4:56:11<8:16:22,  8.24s/it]08/04/2024 14:34:20 - INFO - __main__ -   Step: 2098, LR: 3.514646513777086e-07, Loss: 0.27426499128341675
2024-08-04T21:34:29.132202499Z 
 37%|███▋      | 2099/5712 [4:56:20<8:19:32,  8.30s/it]08/04/2024 14:34:29 - INFO - __main__ -   Step: 2099, LR: 3.513673727473917e-07, Loss: 0.15546120703220367
2024-08-04T21:34:37.570969082Z 
 37%|███▋      | 2100/5712 [4:56:28<8:21:58,  8.34s/it]08/04/2024 14:34:37 - INFO - __main__ -   Step: 2100, LR: 3.512700941170748e-07, Loss: 0.1876952350139618
2024-08-04T21:34:45.727933719Z 
 37%|███▋      | 2101/5712 [4:56:36<8:18:33,  8.28s/it]08/04/2024 14:34:45 - INFO - __main__ -   Step: 2101, LR: 3.5117281548675795e-07, Loss: 0.19047850370407104
2024-08-04T21:34:55.402353938Z 
 37%|███▋      | 2102/5712 [4:56:46<8:43:31,  8.70s/it]08/04/2024 14:34:55 - INFO - __main__ -   Step: 2102, LR: 3.5107553685644105e-07, Loss: 0.2789306342601776
2024-08-04T21:35:04.117406365Z 
 37%|███▋      | 2103/5712 [4:56:55<8:43:37,  8.71s/it]08/04/2024 14:35:04 - INFO - __main__ -   Step: 2103, LR: 3.5097825822612414e-07, Loss: 0.2610408067703247
2024-08-04T21:35:12.778867621Z 
 37%|███▋      | 2104/5712 [4:57:03<8:42:41,  8.69s/it]08/04/2024 14:35:12 - INFO - __main__ -   Step: 2104, LR: 3.5088097959580724e-07, Loss: 0.28441137075424194
2024-08-04T21:35:20.723996789Z 
 37%|███▋      | 2105/5712 [4:57:11<8:29:04,  8.47s/it]08/04/2024 14:35:20 - INFO - __main__ -   Step: 2105, LR: 3.507837009654904e-07, Loss: 0.2546660602092743
2024-08-04T21:35:29.074124269Z 
 37%|███▋      | 2106/5712 [4:57:20<8:26:48,  8.43s/it]08/04/2024 14:35:29 - INFO - __main__ -   Step: 2106, LR: 3.506864223351735e-07, Loss: 0.2234288454055786
2024-08-04T21:35:37.875674696Z 
 37%|███▋      | 2107/5712 [4:57:29<8:33:19,  8.54s/it]08/04/2024 14:35:37 - INFO - __main__ -   Step: 2107, LR: 3.505891437048566e-07, Loss: 0.13046550750732422
2024-08-04T21:35:46.080113263Z 
 37%|███▋      | 2108/5712 [4:57:37<8:27:03,  8.44s/it]08/04/2024 14:35:46 - INFO - __main__ -   Step: 2108, LR: 3.5049186507453975e-07, Loss: 0.2075677514076233
2024-08-04T21:35:54.131048502Z 
 37%|███▋      | 2109/5712 [4:57:45<8:19:52,  8.32s/it]08/04/2024 14:35:54 - INFO - __main__ -   Step: 2109, LR: 3.503945864442229e-07, Loss: 0.2070452868938446
2024-08-04T21:36:02.570002509Z 
 37%|███▋      | 2110/5712 [4:57:53<8:21:48,  8.36s/it]08/04/2024 14:36:02 - INFO - __main__ -   Step: 2110, LR: 3.50297307813906e-07, Loss: 0.2012740969657898
2024-08-04T21:36:11.137575982Z 
 37%|███▋      | 2111/5712 [4:58:02<8:25:25,  8.42s/it]08/04/2024 14:36:11 - INFO - __main__ -   Step: 2111, LR: 3.502000291835891e-07, Loss: 0.2898789346218109
2024-08-04T21:36:19.319810846Z 
 37%|███▋      | 2112/5712 [4:58:10<8:20:58,  8.35s/it]08/04/2024 14:36:19 - INFO - __main__ -   Step: 2112, LR: 3.501027505532722e-07, Loss: 0.1895928829908371
2024-08-04T21:36:27.301081561Z 
 37%|███▋      | 2113/5712 [4:58:18<8:14:12,  8.24s/it]08/04/2024 14:36:27 - INFO - __main__ -   Step: 2113, LR: 3.500054719229553e-07, Loss: 0.1498507857322693
2024-08-04T21:36:35.423909387Z 
 37%|███▋      | 2114/5712 [4:58:26<8:11:58,  8.20s/it]08/04/2024 14:36:35 - INFO - __main__ -   Step: 2114, LR: 3.4990819329263845e-07, Loss: 0.17582640051841736
2024-08-04T21:36:43.639105622Z 
 37%|███▋      | 2115/5712 [4:58:34<8:12:02,  8.21s/it]08/04/2024 14:36:43 - INFO - __main__ -   Step: 2115, LR: 3.4981091466232154e-07, Loss: 0.2465439736843109
2024-08-04T21:36:52.072528933Z 
 37%|███▋      | 2116/5712 [4:58:43<8:15:58,  8.28s/it]08/04/2024 14:36:52 - INFO - __main__ -   Step: 2116, LR: 3.4971363603200464e-07, Loss: 0.20994232594966888
2024-08-04T21:37:00.082894028Z 
 37%|███▋      | 2117/5712 [4:58:51<8:11:03,  8.20s/it]08/04/2024 14:37:00 - INFO - __main__ -   Step: 2117, LR: 3.4961635740168774e-07, Loss: 0.14577412605285645
2024-08-04T21:37:08.682660547Z 
 37%|███▋      | 2118/5712 [4:58:59<8:18:11,  8.32s/it]08/04/2024 14:37:08 - INFO - __main__ -   Step: 2118, LR: 3.495190787713709e-07, Loss: 0.3232062757015228
2024-08-04T21:37:17.256198300Z 
 37%|███▋      | 2119/5712 [4:59:08<8:22:39,  8.39s/it]08/04/2024 14:37:17 - INFO - __main__ -   Step: 2119, LR: 3.49421800141054e-07, Loss: 0.13974949717521667
2024-08-04T21:37:25.725101499Z 
 37%|███▋      | 2120/5712 [4:59:16<8:23:51,  8.42s/it]08/04/2024 14:37:25 - INFO - __main__ -   Step: 2120, LR: 3.493245215107371e-07, Loss: 0.1821686327457428
2024-08-04T21:37:33.929064945Z 
 37%|███▋      | 2121/5712 [4:59:25<8:19:54,  8.35s/it]08/04/2024 14:37:33 - INFO - __main__ -   Step: 2121, LR: 3.492272428804202e-07, Loss: 0.22558274865150452
2024-08-04T21:37:42.352765731Z 
 37%|███▋      | 2122/5712 [4:59:33<8:21:02,  8.37s/it]08/04/2024 14:37:42 - INFO - __main__ -   Step: 2122, LR: 3.4912996425010334e-07, Loss: 0.25914818048477173
2024-08-04T21:37:50.581415575Z 
 37%|███▋      | 2123/5712 [4:59:41<8:18:17,  8.33s/it]08/04/2024 14:37:50 - INFO - __main__ -   Step: 2123, LR: 3.4903268561978644e-07, Loss: 0.20744547247886658
2024-08-04T21:37:59.084318092Z 
 37%|███▋      | 2124/5712 [4:59:50<8:21:14,  8.38s/it]08/04/2024 14:37:59 - INFO - __main__ -   Step: 2124, LR: 3.4893540698946954e-07, Loss: 0.13359341025352478
2024-08-04T21:38:07.005659573Z 
 37%|███▋      | 2125/5712 [4:59:58<8:12:50,  8.24s/it]08/04/2024 14:38:07 - INFO - __main__ -   Step: 2125, LR: 3.4883812835915264e-07, Loss: 0.21433773636817932
2024-08-04T21:38:15.689587520Z 
 37%|███▋      | 2126/5712 [5:00:06<8:20:35,  8.38s/it]08/04/2024 14:38:15 - INFO - __main__ -   Step: 2126, LR: 3.4874084972883585e-07, Loss: 0.26241305470466614
2024-08-04T21:38:24.206190744Z 
 37%|███▋      | 2127/5712 [5:00:15<8:22:58,  8.42s/it]08/04/2024 14:38:24 - INFO - __main__ -   Step: 2127, LR: 3.4864357109851895e-07, Loss: 0.24105557799339294
2024-08-04T21:38:33.086967274Z 
 37%|███▋      | 2128/5712 [5:00:24<8:31:08,  8.56s/it]08/04/2024 14:38:33 - INFO - __main__ -   Step: 2128, LR: 3.4854629246820204e-07, Loss: 0.29434439539909363
2024-08-04T21:38:41.166831595Z 
 37%|███▋      | 2129/5712 [5:00:32<8:22:26,  8.41s/it]08/04/2024 14:38:41 - INFO - __main__ -   Step: 2129, LR: 3.4844901383788514e-07, Loss: 0.1892879754304886
2024-08-04T21:38:50.290178114Z 
 37%|███▋      | 2130/5712 [5:00:41<8:35:00,  8.63s/it]08/04/2024 14:38:50 - INFO - __main__ -   Step: 2130, LR: 3.483517352075683e-07, Loss: 0.2554038166999817
2024-08-04T21:38:59.642235809Z 
 37%|███▋      | 2131/5712 [5:00:50<8:47:51,  8.84s/it]08/04/2024 14:38:59 - INFO - __main__ -   Step: 2131, LR: 3.482544565772514e-07, Loss: 0.19121024012565613
2024-08-04T21:39:08.418321293Z 
 37%|███▋      | 2132/5712 [5:00:59<8:46:29,  8.82s/it]08/04/2024 14:39:08 - INFO - __main__ -   Step: 2132, LR: 3.481571779469345e-07, Loss: 0.11365844309329987
2024-08-04T21:39:16.862621173Z 
 37%|███▋      | 2133/5712 [5:01:08<8:39:32,  8.71s/it]08/04/2024 14:39:16 - INFO - __main__ -   Step: 2133, LR: 3.480598993166176e-07, Loss: 0.15742428600788116
2024-08-04T21:39:25.395413311Z 
 37%|███▋      | 2134/5712 [5:01:16<8:36:14,  8.66s/it]08/04/2024 14:39:25 - INFO - __main__ -   Step: 2134, LR: 3.4796262068630074e-07, Loss: 0.23626147210597992
2024-08-04T21:39:34.247555205Z 
 37%|███▋      | 2135/5712 [5:01:25<8:39:35,  8.72s/it]08/04/2024 14:39:34 - INFO - __main__ -   Step: 2135, LR: 3.4786534205598384e-07, Loss: 0.217006117105484
2024-08-04T21:39:42.624963514Z 
 37%|███▋      | 2136/5712 [5:01:33<8:33:23,  8.61s/it]08/04/2024 14:39:42 - INFO - __main__ -   Step: 2136, LR: 3.4776806342566694e-07, Loss: 0.20423202216625214
2024-08-04T21:39:51.265370606Z 
 37%|███▋      | 2137/5712 [5:01:42<8:33:42,  8.62s/it]08/04/2024 14:39:51 - INFO - __main__ -   Step: 2137, LR: 3.4767078479535004e-07, Loss: 0.268083781003952
2024-08-04T21:39:59.543526348Z 
 37%|███▋      | 2138/5712 [5:01:50<8:27:26,  8.52s/it]08/04/2024 14:39:59 - INFO - __main__ -   Step: 2138, LR: 3.475735061650332e-07, Loss: 0.16462184488773346
2024-08-04T21:40:08.988639612Z 
 37%|███▋      | 2139/5712 [5:02:00<8:43:50,  8.80s/it]08/04/2024 14:40:08 - INFO - __main__ -   Step: 2139, LR: 3.474762275347163e-07, Loss: 0.23991137742996216
2024-08-04T21:40:17.763791749Z 
 37%|███▋      | 2140/5712 [5:02:08<8:43:18,  8.79s/it]08/04/2024 14:40:17 - INFO - __main__ -   Step: 2140, LR: 3.473789489043994e-07, Loss: 0.14305955171585083
2024-08-04T21:40:25.914978912Z 
 37%|███▋      | 2141/5712 [5:02:17<8:31:45,  8.60s/it]08/04/2024 14:40:25 - INFO - __main__ -   Step: 2141, LR: 3.472816702740825e-07, Loss: 0.2668973505496979
2024-08-04T21:40:33.901618828Z 
 38%|███▊      | 2142/5712 [5:02:25<8:20:41,  8.41s/it]08/04/2024 14:40:33 - INFO - __main__ -   Step: 2142, LR: 3.4718439164376564e-07, Loss: 0.223131000995636
2024-08-04T21:40:42.398669962Z 
 38%|███▊      | 2143/5712 [5:02:33<8:22:00,  8.44s/it]08/04/2024 14:40:42 - INFO - __main__ -   Step: 2143, LR: 3.4708711301344874e-07, Loss: 0.21367387473583221
2024-08-04T21:40:50.672353149Z 
 38%|███▊      | 2144/5712 [5:02:41<8:18:55,  8.39s/it]08/04/2024 14:40:50 - INFO - __main__ -   Step: 2144, LR: 3.469898343831319e-07, Loss: 0.11427807807922363
2024-08-04T21:40:58.942106173Z 
 38%|███▊      | 2145/5712 [5:02:50<8:16:37,  8.35s/it]08/04/2024 14:40:58 - INFO - __main__ -   Step: 2145, LR: 3.46892555752815e-07, Loss: 0.08178466558456421
2024-08-04T21:41:06.901645026Z 
 38%|███▊      | 2146/5712 [5:02:58<8:09:28,  8.24s/it]08/04/2024 14:41:06 - INFO - __main__ -   Step: 2146, LR: 3.4679527712249814e-07, Loss: 0.2831636071205139
2024-08-04T21:41:15.675693318Z 
 38%|███▊      | 2147/5712 [5:03:06<8:18:55,  8.40s/it]08/04/2024 14:41:15 - INFO - __main__ -   Step: 2147, LR: 3.4669799849218124e-07, Loss: 0.32881051301956177
2024-08-04T21:41:24.097617488Z 
 38%|███▊      | 2148/5712 [5:03:15<8:19:13,  8.40s/it]08/04/2024 14:41:24 - INFO - __main__ -   Step: 2148, LR: 3.4660071986186434e-07, Loss: 0.3190675377845764
2024-08-04T21:41:32.295367169Z 
 38%|███▊      | 2149/5712 [5:03:23<8:15:24,  8.34s/it]08/04/2024 14:41:32 - INFO - __main__ -   Step: 2149, LR: 3.4650344123154744e-07, Loss: 0.151408389210701
2024-08-04T21:41:39.789337106Z 
 38%|███▊      | 2150/5712 [5:03:30<8:00:09,  8.09s/it]08/04/2024 14:41:39 - INFO - __main__ -   Step: 2150, LR: 3.4640616260123054e-07, Loss: 0.20236165821552277
2024-08-04T21:41:48.821761570Z 
 38%|███▊      | 2151/5712 [5:03:39<8:16:50,  8.37s/it]08/04/2024 14:41:48 - INFO - __main__ -   Step: 2151, LR: 3.463088839709137e-07, Loss: 0.2148466557264328
2024-08-04T21:41:57.440682030Z 
 38%|███▊      | 2152/5712 [5:03:48<8:21:05,  8.45s/it]08/04/2024 14:41:57 - INFO - __main__ -   Step: 2152, LR: 3.462116053405968e-07, Loss: 0.2562307119369507
2024-08-04T21:42:06.678721011Z 
 38%|███▊      | 2153/5712 [5:03:57<8:35:03,  8.68s/it]08/04/2024 14:42:06 - INFO - __main__ -   Step: 2153, LR: 3.461143267102799e-07, Loss: 0.18879130482673645
2024-08-04T21:42:14.672098306Z 
 38%|███▊      | 2154/5712 [5:04:05<8:22:38,  8.48s/it]08/04/2024 14:42:14 - INFO - __main__ -   Step: 2154, LR: 3.46017048079963e-07, Loss: 0.23557767271995544
2024-08-04T21:42:23.103842467Z 
 38%|███▊      | 2155/5712 [5:04:14<8:21:42,  8.46s/it]08/04/2024 14:42:23 - INFO - __main__ -   Step: 2155, LR: 3.4591976944964614e-07, Loss: 0.21384978294372559
2024-08-04T21:42:31.975941769Z 
 38%|███▊      | 2156/5712 [5:04:23<8:28:50,  8.59s/it]08/04/2024 14:42:31 - INFO - __main__ -   Step: 2156, LR: 3.4582249081932924e-07, Loss: 0.16294191777706146
2024-08-04T21:42:40.241514972Z 
 38%|███▊      | 2157/5712 [5:04:31<8:23:00,  8.49s/it]08/04/2024 14:42:40 - INFO - __main__ -   Step: 2157, LR: 3.4572521218901234e-07, Loss: 0.24228417873382568
2024-08-04T21:42:47.912836113Z 
 38%|███▊      | 2158/5712 [5:04:39<8:08:19,  8.24s/it]08/04/2024 14:42:47 - INFO - __main__ -   Step: 2158, LR: 3.4562793355869544e-07, Loss: 0.2260245978832245
2024-08-04T21:42:56.032487875Z 
 38%|███▊      | 2159/5712 [5:04:47<8:05:58,  8.21s/it]08/04/2024 14:42:56 - INFO - __main__ -   Step: 2159, LR: 3.455306549283786e-07, Loss: 0.16124647855758667
2024-08-04T21:43:04.225254539Z 
 38%|███▊      | 2160/5712 [5:04:55<8:05:35,  8.20s/it]08/04/2024 14:43:04 - INFO - __main__ -   Step: 2160, LR: 3.454333762980617e-07, Loss: 0.22195354104042053
2024-08-04T21:43:13.104193094Z 
 38%|███▊      | 2161/5712 [5:05:04<8:17:27,  8.41s/it]08/04/2024 14:43:13 - INFO - __main__ -   Step: 2161, LR: 3.453360976677448e-07, Loss: 0.18903528153896332
2024-08-04T21:43:21.823332694Z 
 38%|███▊      | 2162/5712 [5:05:12<8:22:53,  8.50s/it]08/04/2024 14:43:21 - INFO - __main__ -   Step: 2162, LR: 3.4523881903742794e-07, Loss: 0.24702481925487518
2024-08-04T21:43:29.984215332Z 
 38%|███▊      | 2163/5712 [5:05:21<8:16:44,  8.40s/it]08/04/2024 14:43:29 - INFO - __main__ -   Step: 2163, LR: 3.451415404071111e-07, Loss: 0.14000432193279266
2024-08-04T21:43:38.203605829Z 
 38%|███▊      | 2164/5712 [5:05:29<8:13:25,  8.34s/it]08/04/2024 14:43:38 - INFO - __main__ -   Step: 2164, LR: 3.450442617767942e-07, Loss: 0.14092376828193665
2024-08-04T21:43:47.116874437Z 
 38%|███▊      | 2165/5712 [5:05:38<8:23:22,  8.52s/it]08/04/2024 14:43:47 - INFO - __main__ -   Step: 2165, LR: 3.449469831464773e-07, Loss: 0.3193901777267456
2024-08-04T21:43:55.114444273Z 
 38%|███▊      | 2166/5712 [5:05:46<8:14:03,  8.36s/it]08/04/2024 14:43:55 - INFO - __main__ -   Step: 2166, LR: 3.448497045161604e-07, Loss: 0.16839441657066345
2024-08-04T21:44:03.549265581Z 
 38%|███▊      | 2167/5712 [5:05:54<8:15:15,  8.38s/it]08/04/2024 14:44:03 - INFO - __main__ -   Step: 2167, LR: 3.4475242588584354e-07, Loss: 0.283679336309433
2024-08-04T21:44:11.844140607Z 
 38%|███▊      | 2168/5712 [5:06:02<8:13:33,  8.36s/it]08/04/2024 14:44:11 - INFO - __main__ -   Step: 2168, LR: 3.4465514725552664e-07, Loss: 0.26868242025375366
2024-08-04T21:44:20.635556290Z 
 38%|███▊      | 2169/5712 [5:06:11<8:21:08,  8.49s/it]08/04/2024 14:44:20 - INFO - __main__ -   Step: 2169, LR: 3.4455786862520974e-07, Loss: 0.283427357673645
2024-08-04T21:44:28.956024094Z 
 38%|███▊      | 2170/5712 [5:06:20<8:18:03,  8.44s/it]08/04/2024 14:44:28 - INFO - __main__ -   Step: 2170, LR: 3.4446058999489284e-07, Loss: 0.161868155002594
2024-08-04T21:44:37.094505349Z 
 38%|███▊      | 2171/5712 [5:06:28<8:12:37,  8.35s/it]08/04/2024 14:44:37 - INFO - __main__ -   Step: 2171, LR: 3.44363311364576e-07, Loss: 0.16737020015716553
2024-08-04T21:44:45.535563425Z 
 38%|███▊      | 2172/5712 [5:06:36<8:14:08,  8.38s/it]08/04/2024 14:44:45 - INFO - __main__ -   Step: 2172, LR: 3.442660327342591e-07, Loss: 0.31243470311164856
2024-08-04T21:44:54.173889210Z 
 38%|███▊      | 2173/5712 [5:06:45<8:18:39,  8.45s/it]08/04/2024 14:44:54 - INFO - __main__ -   Step: 2173, LR: 3.441687541039422e-07, Loss: 0.20586007833480835
2024-08-04T21:45:02.586101568Z 
 38%|███▊      | 2174/5712 [5:06:53<8:17:46,  8.44s/it]08/04/2024 14:45:02 - INFO - __main__ -   Step: 2174, LR: 3.440714754736253e-07, Loss: 0.20267179608345032
2024-08-04T21:45:11.136480893Z 
 38%|███▊      | 2175/5712 [5:07:02<8:19:33,  8.47s/it]08/04/2024 14:45:11 - INFO - __main__ -   Step: 2175, LR: 3.4397419684330844e-07, Loss: 0.18441033363342285
2024-08-04T21:45:20.160899841Z 
 38%|███▊      | 2176/5712 [5:07:11<8:29:08,  8.64s/it]08/04/2024 14:45:20 - INFO - __main__ -   Step: 2176, LR: 3.4387691821299154e-07, Loss: 0.2632128894329071
2024-08-04T21:45:28.546794794Z 
 38%|███▊      | 2177/5712 [5:07:19<8:24:31,  8.56s/it]08/04/2024 14:45:28 - INFO - __main__ -   Step: 2177, LR: 3.4377963958267464e-07, Loss: 0.18038469552993774
2024-08-04T21:45:37.132415276Z 
 38%|███▊      | 2178/5712 [5:07:28<8:24:46,  8.57s/it]08/04/2024 14:45:37 - INFO - __main__ -   Step: 2178, LR: 3.4368236095235774e-07, Loss: 0.2632625699043274
2024-08-04T21:45:45.921356028Z 
 38%|███▊      | 2179/5712 [5:07:37<8:28:29,  8.64s/it]08/04/2024 14:45:45 - INFO - __main__ -   Step: 2179, LR: 3.435850823220409e-07, Loss: 0.17077559232711792
2024-08-04T21:45:54.895788129Z 
 38%|███▊      | 2180/5712 [5:07:46<8:34:20,  8.74s/it]08/04/2024 14:45:54 - INFO - __main__ -   Step: 2180, LR: 3.4348780369172404e-07, Loss: 0.16862185299396515
2024-08-04T21:46:03.359644254Z 
 38%|███▊      | 2181/5712 [5:07:54<8:29:21,  8.66s/it]08/04/2024 14:46:03 - INFO - __main__ -   Step: 2181, LR: 3.4339052506140714e-07, Loss: 0.22372370958328247
2024-08-04T21:46:11.489478960Z 
 38%|███▊      | 2182/5712 [5:08:02<8:19:56,  8.50s/it]08/04/2024 14:46:11 - INFO - __main__ -   Step: 2182, LR: 3.4329324643109024e-07, Loss: 0.29081395268440247
2024-08-04T21:46:19.461279762Z 
 38%|███▊      | 2183/5712 [5:08:10<8:10:31,  8.34s/it]08/04/2024 14:46:19 - INFO - __main__ -   Step: 2183, LR: 3.431959678007734e-07, Loss: 0.19469888508319855
2024-08-04T21:46:27.942961042Z 
 38%|███▊      | 2184/5712 [5:08:19<8:12:52,  8.38s/it]08/04/2024 14:46:27 - INFO - __main__ -   Step: 2184, LR: 3.430986891704565e-07, Loss: 0.1423795074224472
2024-08-04T21:46:36.249360802Z 
 38%|███▊      | 2185/5712 [5:08:27<8:11:24,  8.36s/it]08/04/2024 14:46:36 - INFO - __main__ -   Step: 2185, LR: 3.430014105401396e-07, Loss: 0.23226210474967957
2024-08-04T21:46:44.448342211Z 
 38%|███▊      | 2186/5712 [5:08:35<8:08:25,  8.31s/it]08/04/2024 14:46:44 - INFO - __main__ -   Step: 2186, LR: 3.429041319098227e-07, Loss: 0.18160928785800934
2024-08-04T21:46:53.239140829Z 
 38%|███▊      | 2187/5712 [5:08:44<8:16:44,  8.46s/it]08/04/2024 14:46:53 - INFO - __main__ -   Step: 2187, LR: 3.428068532795058e-07, Loss: 0.10327981412410736
2024-08-04T21:47:02.069497038Z 
 38%|███▊      | 2188/5712 [5:08:53<8:23:12,  8.57s/it]08/04/2024 14:47:02 - INFO - __main__ -   Step: 2188, LR: 3.4270957464918894e-07, Loss: 0.22147053480148315
2024-08-04T21:47:10.824396334Z 
 38%|███▊      | 2189/5712 [5:09:01<8:26:22,  8.62s/it]08/04/2024 14:47:10 - INFO - __main__ -   Step: 2189, LR: 3.4261229601887204e-07, Loss: 0.18951274454593658
2024-08-04T21:47:18.942690049Z 
 38%|███▊      | 2190/5712 [5:09:10<8:17:19,  8.47s/it]08/04/2024 14:47:18 - INFO - __main__ -   Step: 2190, LR: 3.4251501738855514e-07, Loss: 0.12962165474891663
2024-08-04T21:47:27.046243709Z 
 38%|███▊      | 2191/5712 [5:09:18<8:10:41,  8.36s/it]08/04/2024 14:47:27 - INFO - __main__ -   Step: 2191, LR: 3.4241773875823824e-07, Loss: 0.15758930146694183
2024-08-04T21:47:35.350821539Z 
 38%|███▊      | 2192/5712 [5:09:26<8:09:32,  8.34s/it]08/04/2024 14:47:35 - INFO - __main__ -   Step: 2192, LR: 3.423204601279214e-07, Loss: 0.16054871678352356
2024-08-04T21:47:44.426901333Z 
 38%|███▊      | 2193/5712 [5:09:35<8:22:16,  8.56s/it]08/04/2024 14:47:44 - INFO - __main__ -   Step: 2193, LR: 3.422231814976045e-07, Loss: 0.2649267911911011
2024-08-04T21:47:53.023047477Z 
 38%|███▊      | 2194/5712 [5:09:44<8:22:42,  8.57s/it]08/04/2024 14:47:53 - INFO - __main__ -   Step: 2194, LR: 3.421259028672876e-07, Loss: 0.2429426610469818
2024-08-04T21:48:01.664883791Z 
 38%|███▊      | 2195/5712 [5:09:52<8:23:45,  8.59s/it]08/04/2024 14:48:01 - INFO - __main__ -   Step: 2195, LR: 3.420286242369707e-07, Loss: 0.1872236430644989
2024-08-04T21:48:10.034781819Z 
 38%|███▊      | 2196/5712 [5:10:01<8:19:40,  8.53s/it]08/04/2024 14:48:10 - INFO - __main__ -   Step: 2196, LR: 3.4193134560665384e-07, Loss: 0.18750062584877014
2024-08-04T21:48:18.392644622Z 
 38%|███▊      | 2197/5712 [5:10:09<8:16:33,  8.48s/it]08/04/2024 14:48:18 - INFO - __main__ -   Step: 2197, LR: 3.4183406697633694e-07, Loss: 0.23233294486999512
2024-08-04T21:48:27.050541743Z 
 38%|███▊      | 2198/5712 [5:10:18<8:19:36,  8.53s/it]08/04/2024 14:48:27 - INFO - __main__ -   Step: 2198, LR: 3.417367883460201e-07, Loss: 0.20057162642478943
2024-08-04T21:48:35.103253744Z 
 38%|███▊      | 2199/5712 [5:10:26<8:11:04,  8.39s/it]08/04/2024 14:48:35 - INFO - __main__ -   Step: 2199, LR: 3.416395097157032e-07, Loss: 0.21387796103954315
2024-08-04T21:48:43.790714276Z 
 39%|███▊      | 2200/5712 [5:10:34<8:16:12,  8.48s/it]08/04/2024 14:48:43 - INFO - __main__ -   Step: 2200, LR: 3.4154223108538634e-07, Loss: 0.14525841176509857
2024-08-04T21:48:52.202428504Z 
 39%|███▊      | 2201/5712 [5:10:43<8:14:54,  8.46s/it]08/04/2024 14:48:52 - INFO - __main__ -   Step: 2201, LR: 3.4144495245506944e-07, Loss: 0.18814663589000702
2024-08-04T21:49:01.061489511Z 
 39%|███▊      | 2202/5712 [5:10:52<8:21:48,  8.58s/it]08/04/2024 14:49:01 - INFO - __main__ -   Step: 2202, LR: 3.4134767382475254e-07, Loss: 0.20273038744926453
2024-08-04T21:49:09.623899698Z 
 39%|███▊      | 2203/5712 [5:11:00<8:21:23,  8.57s/it]08/04/2024 14:49:09 - INFO - __main__ -   Step: 2203, LR: 3.4125039519443564e-07, Loss: 0.27345165610313416
2024-08-04T21:49:17.803072088Z 
 39%|███▊      | 2204/5712 [5:11:08<8:14:20,  8.46s/it]08/04/2024 14:49:17 - INFO - __main__ -   Step: 2204, LR: 3.411531165641188e-07, Loss: 0.23318512737751007
2024-08-04T21:49:26.252973745Z 
 39%|███▊      | 2205/5712 [5:11:17<8:14:06,  8.45s/it]08/04/2024 14:49:26 - INFO - __main__ -   Step: 2205, LR: 3.410558379338019e-07, Loss: 0.18356090784072876
2024-08-04T21:49:34.860281778Z 
 39%|███▊      | 2206/5712 [5:11:26<8:16:40,  8.50s/it]08/04/2024 14:49:34 - INFO - __main__ -   Step: 2206, LR: 3.40958559303485e-07, Loss: 0.22853350639343262
2024-08-04T21:49:43.256114416Z 
 39%|███▊      | 2207/5712 [5:11:34<8:14:42,  8.47s/it]08/04/2024 14:49:43 - INFO - __main__ -   Step: 2207, LR: 3.408612806731681e-07, Loss: 0.2702981233596802
2024-08-04T21:49:51.846997173Z 
 39%|███▊      | 2208/5712 [5:11:42<8:16:42,  8.51s/it]08/04/2024 14:49:51 - INFO - __main__ -   Step: 2208, LR: 3.4076400204285124e-07, Loss: 0.18233637511730194
2024-08-04T21:50:00.127349477Z 
 39%|███▊      | 2209/5712 [5:11:51<8:12:37,  8.44s/it]08/04/2024 14:50:00 - INFO - __main__ -   Step: 2209, LR: 3.4066672341253434e-07, Loss: 0.18173331022262573
2024-08-04T21:50:08.624723470Z 
 39%|███▊      | 2210/5712 [5:11:59<8:13:31,  8.46s/it]08/04/2024 14:50:08 - INFO - __main__ -   Step: 2210, LR: 3.4056944478221744e-07, Loss: 0.17788997292518616
2024-08-04T21:50:16.802488883Z 
 39%|███▊      | 2211/5712 [5:12:07<8:08:31,  8.37s/it]08/04/2024 14:50:16 - INFO - __main__ -   Step: 2211, LR: 3.4047216615190054e-07, Loss: 0.2671422064304352
2024-08-04T21:50:25.249259597Z 
 39%|███▊      | 2212/5712 [5:12:16<8:09:41,  8.39s/it]08/04/2024 14:50:25 - INFO - __main__ -   Step: 2212, LR: 3.403748875215837e-07, Loss: 0.2759336829185486
2024-08-04T21:50:34.225915687Z 
 39%|███▊      | 2213/5712 [5:12:25<8:19:43,  8.57s/it]08/04/2024 14:50:34 - INFO - __main__ -   Step: 2213, LR: 3.402776088912668e-07, Loss: 0.17420955002307892
2024-08-04T21:50:42.729346422Z 
 39%|███▉      | 2214/5712 [5:12:33<8:18:26,  8.55s/it]08/04/2024 14:50:42 - INFO - __main__ -   Step: 2214, LR: 3.401803302609499e-07, Loss: 0.21944573521614075
2024-08-04T21:50:51.119258321Z 
 39%|███▉      | 2215/5712 [5:12:42<8:15:30,  8.50s/it]08/04/2024 14:50:51 - INFO - __main__ -   Step: 2215, LR: 3.40083051630633e-07, Loss: 0.12208384275436401
2024-08-04T21:50:59.596314164Z 
 39%|███▉      | 2216/5712 [5:12:50<8:14:55,  8.49s/it]08/04/2024 14:50:59 - INFO - __main__ -   Step: 2216, LR: 3.399857730003162e-07, Loss: 0.13502013683319092
2024-08-04T21:51:07.746808067Z 
 39%|███▉      | 2217/5712 [5:12:58<8:08:47,  8.39s/it]08/04/2024 14:51:07 - INFO - __main__ -   Step: 2217, LR: 3.398884943699993e-07, Loss: 0.3043860197067261
2024-08-04T21:51:15.928600669Z 
 39%|███▉      | 2218/5712 [5:13:07<8:04:59,  8.33s/it]08/04/2024 14:51:15 - INFO - __main__ -   Step: 2218, LR: 3.397912157396824e-07, Loss: 0.18819953501224518
2024-08-04T21:51:24.530663015Z 
 39%|███▉      | 2219/5712 [5:13:15<8:09:37,  8.41s/it]08/04/2024 14:51:24 - INFO - __main__ -   Step: 2219, LR: 3.396939371093655e-07, Loss: 0.16068969666957855
2024-08-04T21:51:32.929912574Z 
 39%|███▉      | 2220/5712 [5:13:24<8:09:17,  8.41s/it]08/04/2024 14:51:32 - INFO - __main__ -   Step: 2220, LR: 3.3959665847904864e-07, Loss: 0.1671753227710724
2024-08-04T21:51:41.331386006Z 
 39%|███▉      | 2221/5712 [5:13:32<8:09:03,  8.41s/it]08/04/2024 14:51:41 - INFO - __main__ -   Step: 2221, LR: 3.3949937984873174e-07, Loss: 0.2495352178812027
2024-08-04T21:51:49.999709579Z 
 39%|███▉      | 2222/5712 [5:13:41<8:13:29,  8.48s/it]08/04/2024 14:51:49 - INFO - __main__ -   Step: 2222, LR: 3.3940210121841484e-07, Loss: 0.21513795852661133
2024-08-04T21:51:58.666778160Z 
 39%|███▉      | 2223/5712 [5:13:49<8:16:32,  8.54s/it]08/04/2024 14:51:58 - INFO - __main__ -   Step: 2223, LR: 3.3930482258809794e-07, Loss: 0.18213795125484467
2024-08-04T21:52:06.691106742Z 
 39%|███▉      | 2224/5712 [5:13:57<8:07:25,  8.38s/it]08/04/2024 14:52:06 - INFO - __main__ -   Step: 2224, LR: 3.392075439577811e-07, Loss: 0.18330144882202148
2024-08-04T21:52:15.357114894Z 
 39%|███▉      | 2225/5712 [5:14:06<8:12:11,  8.47s/it]08/04/2024 14:52:15 - INFO - __main__ -   Step: 2225, LR: 3.391102653274642e-07, Loss: 0.1343357115983963
2024-08-04T21:52:23.676376412Z 
 39%|███▉      | 2226/5712 [5:14:14<8:09:26,  8.42s/it]08/04/2024 14:52:23 - INFO - __main__ -   Step: 2226, LR: 3.390129866971473e-07, Loss: 0.17160120606422424
2024-08-04T21:52:32.346083551Z 
 39%|███▉      | 2227/5712 [5:14:23<8:13:34,  8.50s/it]08/04/2024 14:52:32 - INFO - __main__ -   Step: 2227, LR: 3.389157080668304e-07, Loss: 0.18689271807670593
2024-08-04T21:52:41.029910930Z 
 39%|███▉      | 2228/5712 [5:14:32<8:16:40,  8.55s/it]08/04/2024 14:52:41 - INFO - __main__ -   Step: 2228, LR: 3.388184294365135e-07, Loss: 0.13125848770141602
2024-08-04T21:52:49.570949996Z 
 39%|███▉      | 2229/5712 [5:14:40<8:16:18,  8.55s/it]08/04/2024 14:52:49 - INFO - __main__ -   Step: 2229, LR: 3.3872115080619664e-07, Loss: 0.2528360188007355
2024-08-04T21:52:57.851868101Z 
 39%|███▉      | 2230/5712 [5:14:48<8:11:29,  8.47s/it]08/04/2024 14:52:57 - INFO - __main__ -   Step: 2230, LR: 3.3862387217587974e-07, Loss: 0.15493696928024292
2024-08-04T21:53:06.085458636Z 
 39%|███▉      | 2231/5712 [5:14:57<8:07:15,  8.40s/it]08/04/2024 14:53:06 - INFO - __main__ -   Step: 2231, LR: 3.3852659354556283e-07, Loss: 0.185995951294899
2024-08-04T21:53:14.164161539Z 
 39%|███▉      | 2232/5712 [5:15:05<8:01:32,  8.30s/it]08/04/2024 14:53:14 - INFO - __main__ -   Step: 2232, LR: 3.3842931491524593e-07, Loss: 0.11963506042957306
2024-08-04T21:53:22.831263946Z 
 39%|███▉      | 2233/5712 [5:15:13<8:07:45,  8.41s/it]08/04/2024 14:53:22 - INFO - __main__ -   Step: 2233, LR: 3.383320362849291e-07, Loss: 0.22866836190223694
2024-08-04T21:53:31.596390573Z 
 39%|███▉      | 2234/5712 [5:15:22<8:13:45,  8.52s/it]08/04/2024 14:53:31 - INFO - __main__ -   Step: 2234, LR: 3.3823475765461224e-07, Loss: 0.11191272735595703
2024-08-04T21:53:39.563247000Z 
 39%|███▉      | 2235/5712 [5:15:30<8:04:02,  8.35s/it]08/04/2024 14:53:39 - INFO - __main__ -   Step: 2235, LR: 3.3813747902429534e-07, Loss: 0.1474093347787857
2024-08-04T21:53:48.064539129Z 
 39%|███▉      | 2236/5712 [5:15:39<8:06:28,  8.40s/it]08/04/2024 14:53:48 - INFO - __main__ -   Step: 2236, LR: 3.3804020039397844e-07, Loss: 0.22478173673152924
2024-08-04T21:53:56.478409760Z 
 39%|███▉      | 2237/5712 [5:15:47<8:06:37,  8.40s/it]08/04/2024 14:53:56 - INFO - __main__ -   Step: 2237, LR: 3.379429217636616e-07, Loss: 0.28772205114364624
2024-08-04T21:54:05.317723439Z 
 39%|███▉      | 2238/5712 [5:15:56<8:14:05,  8.53s/it]08/04/2024 14:54:05 - INFO - __main__ -   Step: 2238, LR: 3.378456431333447e-07, Loss: 0.24036571383476257
2024-08-04T21:54:13.670041949Z 
 39%|███▉      | 2239/5712 [5:16:04<8:10:47,  8.48s/it]08/04/2024 14:54:13 - INFO - __main__ -   Step: 2239, LR: 3.377483645030278e-07, Loss: 0.21057315170764923
2024-08-04T21:54:22.289850718Z 
 39%|███▉      | 2240/5712 [5:16:13<8:13:05,  8.52s/it]08/04/2024 14:54:22 - INFO - __main__ -   Step: 2240, LR: 3.376510858727109e-07, Loss: 0.17319080233573914
2024-08-04T21:54:30.535885405Z 
 39%|███▉      | 2241/5712 [5:16:21<8:08:10,  8.44s/it]08/04/2024 14:54:30 - INFO - __main__ -   Step: 2241, LR: 3.3755380724239404e-07, Loss: 0.18688678741455078
2024-08-04T21:54:40.055746155Z 
 39%|███▉      | 2242/5712 [5:16:31<8:26:47,  8.76s/it]08/04/2024 14:54:40 - INFO - __main__ -   Step: 2242, LR: 3.3745652861207714e-07, Loss: 0.14938980340957642
2024-08-04T21:54:48.050911060Z 
 39%|███▉      | 2243/5712 [5:16:39<8:13:19,  8.53s/it]08/04/2024 14:54:48 - INFO - __main__ -   Step: 2243, LR: 3.3735924998176023e-07, Loss: 0.17403611540794373
2024-08-04T21:54:56.149271696Z 
 39%|███▉      | 2244/5712 [5:16:47<8:05:39,  8.40s/it]08/04/2024 14:54:56 - INFO - __main__ -   Step: 2244, LR: 3.3726197135144333e-07, Loss: 0.21726420521736145
2024-08-04T21:55:04.331447507Z 
 39%|███▉      | 2245/5712 [5:16:55<8:01:42,  8.34s/it]08/04/2024 14:55:04 - INFO - __main__ -   Step: 2245, LR: 3.371646927211265e-07, Loss: 0.23804834485054016
2024-08-04T21:55:12.690828419Z 
 39%|███▉      | 2246/5712 [5:17:03<8:01:57,  8.34s/it]08/04/2024 14:55:12 - INFO - __main__ -   Step: 2246, LR: 3.370674140908096e-07, Loss: 0.2657448351383209
2024-08-04T21:55:21.218952256Z 
 39%|███▉      | 2247/5712 [5:17:12<8:05:01,  8.40s/it]08/04/2024 14:55:21 - INFO - __main__ -   Step: 2247, LR: 3.369701354604927e-07, Loss: 0.24062266945838928
2024-08-04T21:55:29.269749667Z 
 39%|███▉      | 2248/5712 [5:17:20<7:58:51,  8.29s/it]08/04/2024 14:55:29 - INFO - __main__ -   Step: 2248, LR: 3.368728568301758e-07, Loss: 0.1910882443189621
2024-08-04T21:55:37.981285028Z 
 39%|███▉      | 2249/5712 [5:17:29<8:05:56,  8.42s/it]08/04/2024 14:55:37 - INFO - __main__ -   Step: 2249, LR: 3.3677557819985893e-07, Loss: 0.1964847892522812
2024-08-04T21:55:46.790292785Z 
 39%|███▉      | 2250/5712 [5:17:37<8:12:32,  8.54s/it]08/04/2024 14:55:46 - INFO - __main__ -   Step: 2250, LR: 3.3667829956954203e-07, Loss: 0.23803631961345673
2024-08-04T21:55:55.958544649Z 
 39%|███▉      | 2251/5712 [5:17:47<8:23:20,  8.73s/it]08/04/2024 14:55:55 - INFO - __main__ -   Step: 2251, LR: 3.3658102093922513e-07, Loss: 0.2930510640144348
2024-08-04T21:56:04.076796650Z 
 39%|███▉      | 2252/5712 [5:17:55<8:12:39,  8.54s/it]08/04/2024 14:56:04 - INFO - __main__ -   Step: 2252, LR: 3.364837423089083e-07, Loss: 0.2999480664730072
2024-08-04T21:56:12.375917086Z 
 39%|███▉      | 2253/5712 [5:18:03<8:08:18,  8.47s/it]08/04/2024 14:56:12 - INFO - __main__ -   Step: 2253, LR: 3.3638646367859144e-07, Loss: 0.25199857354164124
2024-08-04T21:56:20.718715296Z 
 39%|███▉      | 2254/5712 [5:18:11<8:05:58,  8.43s/it]08/04/2024 14:56:20 - INFO - __main__ -   Step: 2254, LR: 3.3628918504827454e-07, Loss: 0.24058833718299866
2024-08-04T21:56:29.589857193Z 
 39%|███▉      | 2255/5712 [5:18:20<8:13:24,  8.56s/it]08/04/2024 14:56:29 - INFO - __main__ -   Step: 2255, LR: 3.3619190641795763e-07, Loss: 0.22002048790454865
2024-08-04T21:56:37.700766806Z 
 39%|███▉      | 2256/5712 [5:18:28<8:05:26,  8.43s/it]08/04/2024 14:56:37 - INFO - __main__ -   Step: 2256, LR: 3.3609462778764073e-07, Loss: 0.2192247360944748
2024-08-04T21:56:45.969049940Z 
 40%|███▉      | 2257/5712 [5:18:37<8:02:33,  8.38s/it]08/04/2024 14:56:45 - INFO - __main__ -   Step: 2257, LR: 3.359973491573239e-07, Loss: 0.18210512399673462
2024-08-04T21:56:54.016547737Z 
 40%|███▉      | 2258/5712 [5:18:45<7:56:40,  8.28s/it]08/04/2024 14:56:54 - INFO - __main__ -   Step: 2258, LR: 3.35900070527007e-07, Loss: 0.18406112492084503
2024-08-04T21:57:02.918899197Z 
 40%|███▉      | 2259/5712 [5:18:54<8:07:15,  8.47s/it]08/04/2024 14:57:02 - INFO - __main__ -   Step: 2259, LR: 3.358027918966901e-07, Loss: 0.2297564297914505
2024-08-04T21:57:11.134245571Z 
 40%|███▉      | 2260/5712 [5:19:02<8:02:47,  8.39s/it]08/04/2024 14:57:11 - INFO - __main__ -   Step: 2260, LR: 3.357055132663732e-07, Loss: 0.1632036715745926
2024-08-04T21:57:19.227820198Z 
 40%|███▉      | 2261/5712 [5:19:10<7:57:30,  8.30s/it]08/04/2024 14:57:19 - INFO - __main__ -   Step: 2261, LR: 3.3560823463605634e-07, Loss: 0.15844520926475525
2024-08-04T21:57:27.669356257Z 
 40%|███▉      | 2262/5712 [5:19:18<7:59:46,  8.34s/it]08/04/2024 14:57:27 - INFO - __main__ -   Step: 2262, LR: 3.3551095600573943e-07, Loss: 0.181045264005661
2024-08-04T21:57:36.465964152Z 
 40%|███▉      | 2263/5712 [5:19:27<8:07:26,  8.48s/it]08/04/2024 14:57:36 - INFO - __main__ -   Step: 2263, LR: 3.3541367737542253e-07, Loss: 0.15452635288238525
2024-08-04T21:57:44.796332681Z 
 40%|███▉      | 2264/5712 [5:19:35<8:04:43,  8.43s/it]08/04/2024 14:57:44 - INFO - __main__ -   Step: 2264, LR: 3.3531639874510563e-07, Loss: 0.1720852553844452
2024-08-04T21:57:53.335823939Z 
 40%|███▉      | 2265/5712 [5:19:44<8:06:23,  8.47s/it]08/04/2024 14:57:53 - INFO - __main__ -   Step: 2265, LR: 3.3521912011478873e-07, Loss: 0.43131497502326965
2024-08-04T21:58:01.933864631Z 
 40%|███▉      | 2266/5712 [5:19:53<8:08:30,  8.51s/it]08/04/2024 14:58:01 - INFO - __main__ -   Step: 2266, LR: 3.351218414844719e-07, Loss: 0.2188010811805725
2024-08-04T21:58:10.509237699Z 
 40%|███▉      | 2267/5712 [5:20:01<8:09:34,  8.53s/it]08/04/2024 14:58:10 - INFO - __main__ -   Step: 2267, LR: 3.35024562854155e-07, Loss: 0.23028358817100525
2024-08-04T21:58:19.021350802Z 
 40%|███▉      | 2268/5712 [5:20:10<8:09:10,  8.52s/it]08/04/2024 14:58:19 - INFO - __main__ -   Step: 2268, LR: 3.349272842238381e-07, Loss: 0.18955451250076294
2024-08-04T21:58:27.218815046Z 
 40%|███▉      | 2269/5712 [5:20:18<8:03:26,  8.42s/it]08/04/2024 14:58:27 - INFO - __main__ -   Step: 2269, LR: 3.348300055935212e-07, Loss: 0.2894948124885559
2024-08-04T21:58:35.810647025Z 
 40%|███▉      | 2270/5712 [5:20:26<8:06:10,  8.47s/it]08/04/2024 14:58:35 - INFO - __main__ -   Step: 2270, LR: 3.347327269632044e-07, Loss: 0.2604382038116455
2024-08-04T21:58:43.989357058Z 
 40%|███▉      | 2271/5712 [5:20:35<8:00:56,  8.39s/it]08/04/2024 14:58:43 - INFO - __main__ -   Step: 2271, LR: 3.346354483328875e-07, Loss: 0.142909437417984
2024-08-04T21:58:52.341529581Z 
 40%|███▉      | 2272/5712 [5:20:43<8:00:12,  8.38s/it]08/04/2024 14:58:52 - INFO - __main__ -   Step: 2272, LR: 3.345381697025706e-07, Loss: 0.15852856636047363
2024-08-04T21:59:00.927253412Z 
 40%|███▉      | 2273/5712 [5:20:52<8:03:41,  8.44s/it]08/04/2024 14:59:00 - INFO - __main__ -   Step: 2273, LR: 3.344408910722537e-07, Loss: 0.14514577388763428
2024-08-04T21:59:09.257853070Z 
 40%|███▉      | 2274/5712 [5:21:00<8:01:41,  8.41s/it]08/04/2024 14:59:09 - INFO - __main__ -   Step: 2274, LR: 3.3434361244193683e-07, Loss: 0.13163715600967407
2024-08-04T21:59:17.421912465Z 
 40%|███▉      | 2275/5712 [5:21:08<7:57:22,  8.33s/it]08/04/2024 14:59:17 - INFO - __main__ -   Step: 2275, LR: 3.3424633381161993e-07, Loss: 0.23503313958644867
2024-08-04T21:59:26.119293919Z 
 40%|███▉      | 2276/5712 [5:21:17<8:03:28,  8.44s/it]08/04/2024 14:59:26 - INFO - __main__ -   Step: 2276, LR: 3.3414905518130303e-07, Loss: 0.15258684754371643
2024-08-04T21:59:34.552641587Z 
 40%|███▉      | 2277/5712 [5:21:25<8:03:11,  8.44s/it]08/04/2024 14:59:34 - INFO - __main__ -   Step: 2277, LR: 3.3405177655098613e-07, Loss: 0.21548999845981598
2024-08-04T21:59:43.245394807Z 
 40%|███▉      | 2278/5712 [5:21:34<8:07:23,  8.52s/it]08/04/2024 14:59:43 - INFO - __main__ -   Step: 2278, LR: 3.339544979206693e-07, Loss: 0.1769440770149231
2024-08-04T21:59:51.711715347Z 
 40%|███▉      | 2279/5712 [5:21:42<8:06:23,  8.50s/it]08/04/2024 14:59:51 - INFO - __main__ -   Step: 2279, LR: 3.338572192903524e-07, Loss: 0.16879144310951233
2024-08-04T21:59:59.820740002Z 
 40%|███▉      | 2280/5712 [5:21:50<7:59:31,  8.38s/it]08/04/2024 14:59:59 - INFO - __main__ -   Step: 2280, LR: 3.337599406600355e-07, Loss: 0.18282143771648407
2024-08-04T22:00:08.449546270Z 
 40%|███▉      | 2281/5712 [5:21:59<8:03:35,  8.46s/it]08/04/2024 15:00:08 - INFO - __main__ -   Step: 2281, LR: 3.336626620297186e-07, Loss: 0.13000962138175964
2024-08-04T22:00:16.693349201Z 
 40%|███▉      | 2282/5712 [5:22:07<7:59:48,  8.39s/it]08/04/2024 15:00:16 - INFO - __main__ -   Step: 2282, LR: 3.3356538339940173e-07, Loss: 0.18948814272880554
2024-08-04T22:00:25.198973863Z 
 40%|███▉      | 2283/5712 [5:22:16<8:01:35,  8.43s/it]08/04/2024 15:00:25 - INFO - __main__ -   Step: 2283, LR: 3.3346810476908483e-07, Loss: 0.1494593322277069
2024-08-04T22:00:33.328140760Z 
 40%|███▉      | 2284/5712 [5:22:24<7:56:21,  8.34s/it]08/04/2024 15:00:33 - INFO - __main__ -   Step: 2284, LR: 3.3337082613876793e-07, Loss: 0.18929460644721985
2024-08-04T22:00:41.341607734Z 
 40%|████      | 2285/5712 [5:22:32<7:50:39,  8.24s/it]08/04/2024 15:00:41 - INFO - __main__ -   Step: 2285, LR: 3.3327354750845103e-07, Loss: 0.22233684360980988
2024-08-04T22:00:49.716268389Z 
 40%|████      | 2286/5712 [5:22:40<7:52:48,  8.28s/it]08/04/2024 15:00:49 - INFO - __main__ -   Step: 2286, LR: 3.331762688781342e-07, Loss: 0.20979581773281097
2024-08-04T22:00:58.340975429Z 
 40%|████      | 2287/5712 [5:22:49<7:58:34,  8.38s/it]08/04/2024 15:00:58 - INFO - __main__ -   Step: 2287, LR: 3.330789902478173e-07, Loss: 0.19943606853485107
2024-08-04T22:01:06.836643411Z 
 40%|████      | 2288/5712 [5:22:57<8:00:19,  8.42s/it]08/04/2024 15:01:06 - INFO - __main__ -   Step: 2288, LR: 3.3298171161750043e-07, Loss: 0.21213501691818237
2024-08-04T22:01:15.253888356Z 
 40%|████      | 2289/5712 [5:23:06<8:00:13,  8.42s/it]08/04/2024 15:01:15 - INFO - __main__ -   Step: 2289, LR: 3.3288443298718353e-07, Loss: 0.1806793510913849
2024-08-04T22:01:23.996290240Z 
 40%|████      | 2290/5712 [5:23:15<8:05:38,  8.51s/it]08/04/2024 15:01:23 - INFO - __main__ -   Step: 2290, LR: 3.327871543568667e-07, Loss: 0.2205006629228592
2024-08-04T22:01:32.440135627Z 
 40%|████      | 2291/5712 [5:23:23<8:04:16,  8.49s/it]08/04/2024 15:01:32 - INFO - __main__ -   Step: 2291, LR: 3.326898757265498e-07, Loss: 0.12322761863470078
2024-08-04T22:01:41.074610985Z 
 40%|████      | 2292/5712 [5:23:32<8:06:32,  8.54s/it]08/04/2024 15:01:41 - INFO - __main__ -   Step: 2292, LR: 3.325925970962329e-07, Loss: 0.23380286991596222
2024-08-04T22:01:49.773021724Z 
 40%|████      | 2293/5712 [5:23:40<8:09:10,  8.58s/it]08/04/2024 15:01:49 - INFO - __main__ -   Step: 2293, LR: 3.32495318465916e-07, Loss: 0.20477384328842163
2024-08-04T22:01:58.056597912Z 
 40%|████      | 2294/5712 [5:23:49<8:03:53,  8.49s/it]08/04/2024 15:01:58 - INFO - __main__ -   Step: 2294, LR: 3.3239803983559913e-07, Loss: 0.1982140839099884
2024-08-04T22:02:06.471112867Z 
 40%|████      | 2295/5712 [5:23:57<8:02:23,  8.47s/it]08/04/2024 15:02:06 - INFO - __main__ -   Step: 2295, LR: 3.3230076120528223e-07, Loss: 0.17437222599983215
2024-08-04T22:02:15.203095480Z 
 40%|████      | 2296/5712 [5:24:06<8:06:42,  8.55s/it]08/04/2024 15:02:15 - INFO - __main__ -   Step: 2296, LR: 3.3220348257496533e-07, Loss: 0.12437790632247925
2024-08-04T22:02:23.404008512Z 
 40%|████      | 2297/5712 [5:24:14<8:00:37,  8.44s/it]08/04/2024 15:02:23 - INFO - __main__ -   Step: 2297, LR: 3.3210620394464843e-07, Loss: 0.18289661407470703
2024-08-04T22:02:31.800316748Z 
 40%|████      | 2298/5712 [5:24:22<7:59:40,  8.43s/it]08/04/2024 15:02:31 - INFO - __main__ -   Step: 2298, LR: 3.320089253143316e-07, Loss: 0.26753705739974976
2024-08-04T22:02:40.626133795Z 
 40%|████      | 2299/5712 [5:24:31<8:06:16,  8.55s/it]08/04/2024 15:02:40 - INFO - __main__ -   Step: 2299, LR: 3.319116466840147e-07, Loss: 0.3556196093559265
2024-08-04T22:02:50.156003532Z 
 40%|████      | 2300/5712 [5:24:41<8:22:52,  8.84s/it]08/04/2024 15:02:50 - INFO - __main__ -   Step: 2300, LR: 3.318143680536978e-07, Loss: 0.21904751658439636
2024-08-04T22:02:58.628106951Z 
 40%|████      | 2301/5712 [5:24:49<8:16:24,  8.73s/it]08/04/2024 15:02:58 - INFO - __main__ -   Step: 2301, LR: 3.317170894233809e-07, Loss: 0.29876208305358887
2024-08-04T22:03:07.343008913Z 
 40%|████      | 2302/5712 [5:24:58<8:15:57,  8.73s/it]08/04/2024 15:03:07 - INFO - __main__ -   Step: 2302, LR: 3.31619810793064e-07, Loss: 0.18217244744300842
2024-08-04T22:03:15.718004279Z 
 40%|████      | 2303/5712 [5:25:06<8:09:49,  8.62s/it]08/04/2024 15:03:15 - INFO - __main__ -   Step: 2303, LR: 3.3152253216274713e-07, Loss: 0.1841811090707779
2024-08-04T22:03:24.281026007Z 
 40%|████      | 2304/5712 [5:25:15<8:08:41,  8.60s/it]08/04/2024 15:03:24 - INFO - __main__ -   Step: 2304, LR: 3.3142525353243023e-07, Loss: 0.14653989672660828
2024-08-04T22:03:33.142213423Z 
 40%|████      | 2305/5712 [5:25:24<8:12:56,  8.68s/it]08/04/2024 15:03:33 - INFO - __main__ -   Step: 2305, LR: 3.3132797490211333e-07, Loss: 0.19840215146541595
2024-08-04T22:03:41.675703546Z 
 40%|████      | 2306/5712 [5:25:32<8:10:16,  8.64s/it]08/04/2024 15:03:41 - INFO - __main__ -   Step: 2306, LR: 3.312306962717965e-07, Loss: 0.11128617823123932
2024-08-04T22:03:50.101767640Z 
 40%|████      | 2307/5712 [5:25:41<8:06:33,  8.57s/it]08/04/2024 15:03:50 - INFO - __main__ -   Step: 2307, LR: 3.3113341764147963e-07, Loss: 0.20266468822956085
2024-08-04T22:03:58.410215490Z 
 40%|████      | 2308/5712 [5:25:49<8:01:53,  8.49s/it]08/04/2024 15:03:58 - INFO - __main__ -   Step: 2308, LR: 3.3103613901116273e-07, Loss: 0.283189594745636
2024-08-04T22:04:06.739750269Z 
 40%|████      | 2309/5712 [5:25:57<7:58:57,  8.44s/it]08/04/2024 15:04:06 - INFO - __main__ -   Step: 2309, LR: 3.3093886038084583e-07, Loss: 0.1797773391008377
2024-08-04T22:04:14.803356567Z 
 40%|████      | 2310/5712 [5:26:05<7:52:19,  8.33s/it]08/04/2024 15:04:14 - INFO - __main__ -   Step: 2310, LR: 3.3084158175052893e-07, Loss: 0.13622966408729553
2024-08-04T22:04:23.932140199Z 
 40%|████      | 2311/5712 [5:26:15<8:05:45,  8.57s/it]08/04/2024 15:04:23 - INFO - __main__ -   Step: 2311, LR: 3.307443031202121e-07, Loss: 0.3246161937713623
2024-08-04T22:04:31.939865626Z 
 40%|████      | 2312/5712 [5:26:23<7:56:04,  8.40s/it]08/04/2024 15:04:31 - INFO - __main__ -   Step: 2312, LR: 3.306470244898952e-07, Loss: 0.21501044929027557
2024-08-04T22:04:40.820085343Z 
 40%|████      | 2313/5712 [5:26:31<8:04:04,  8.54s/it]08/04/2024 15:04:40 - INFO - __main__ -   Step: 2313, LR: 3.305497458595783e-07, Loss: 0.1742304116487503
2024-08-04T22:04:49.646084793Z 
 41%|████      | 2314/5712 [5:26:40<8:08:41,  8.63s/it]08/04/2024 15:04:49 - INFO - __main__ -   Step: 2314, LR: 3.304524672292614e-07, Loss: 0.1982453316450119
2024-08-04T22:04:57.980888554Z 
 41%|████      | 2315/5712 [5:26:49<8:03:33,  8.54s/it]08/04/2024 15:04:57 - INFO - __main__ -   Step: 2315, LR: 3.3035518859894453e-07, Loss: 0.22763091325759888
2024-08-04T22:05:06.162669296Z 
 41%|████      | 2316/5712 [5:26:57<7:57:19,  8.43s/it]08/04/2024 15:05:06 - INFO - __main__ -   Step: 2316, LR: 3.3025790996862763e-07, Loss: 0.23468215763568878
2024-08-04T22:05:15.425281676Z 
 41%|████      | 2317/5712 [5:27:06<8:11:15,  8.68s/it]08/04/2024 15:05:15 - INFO - __main__ -   Step: 2317, LR: 3.3016063133831073e-07, Loss: 0.23408706486225128
2024-08-04T22:05:23.608652854Z 
 41%|████      | 2318/5712 [5:27:14<8:02:38,  8.53s/it]08/04/2024 15:05:23 - INFO - __main__ -   Step: 2318, LR: 3.3006335270799383e-07, Loss: 0.189426988363266
2024-08-04T22:05:32.932661056Z 
 41%|████      | 2319/5712 [5:27:24<8:15:53,  8.77s/it]08/04/2024 15:05:32 - INFO - __main__ -   Step: 2319, LR: 3.29966074077677e-07, Loss: 0.13283798098564148
2024-08-04T22:05:41.122788349Z 
 41%|████      | 2320/5712 [5:27:32<8:05:58,  8.60s/it]08/04/2024 15:05:41 - INFO - __main__ -   Step: 2320, LR: 3.298687954473601e-07, Loss: 0.16929826140403748
2024-08-04T22:05:49.976431155Z 
 41%|████      | 2321/5712 [5:27:41<8:10:11,  8.67s/it]08/04/2024 15:05:49 - INFO - __main__ -   Step: 2321, LR: 3.297715168170432e-07, Loss: 0.137675940990448
2024-08-04T22:05:58.531408127Z 
 41%|████      | 2322/5712 [5:27:49<8:08:02,  8.64s/it]08/04/2024 15:05:58 - INFO - __main__ -   Step: 2322, LR: 3.296742381867263e-07, Loss: 0.2949145436286926
2024-08-04T22:06:07.184944806Z 
 41%|████      | 2323/5712 [5:27:58<8:08:10,  8.64s/it]08/04/2024 15:06:07 - INFO - __main__ -   Step: 2323, LR: 3.2957695955640943e-07, Loss: 0.17030584812164307
2024-08-04T22:06:15.829385179Z 
 41%|████      | 2324/5712 [5:28:06<8:08:02,  8.64s/it]08/04/2024 15:06:15 - INFO - __main__ -   Step: 2324, LR: 3.2947968092609253e-07, Loss: 0.19439998269081116
2024-08-04T22:06:24.748279462Z 
 41%|████      | 2325/5712 [5:28:15<8:12:34,  8.73s/it]08/04/2024 15:06:24 - INFO - __main__ -   Step: 2325, LR: 3.293824022957757e-07, Loss: 0.13180100917816162
2024-08-04T22:06:33.471528107Z 
 41%|████      | 2326/5712 [5:28:24<8:12:22,  8.72s/it]08/04/2024 15:06:33 - INFO - __main__ -   Step: 2326, LR: 3.292851236654588e-07, Loss: 0.16680866479873657
2024-08-04T22:06:41.390742463Z 
 41%|████      | 2327/5712 [5:28:32<7:58:36,  8.48s/it]08/04/2024 15:06:41 - INFO - __main__ -   Step: 2327, LR: 3.2918784503514193e-07, Loss: 0.24836070835590363
2024-08-04T22:06:49.921627038Z 
 41%|████      | 2328/5712 [5:28:41<7:59:15,  8.50s/it]08/04/2024 15:06:49 - INFO - __main__ -   Step: 2328, LR: 3.2909056640482503e-07, Loss: 0.2773215174674988
2024-08-04T22:06:58.357241707Z 
 41%|████      | 2329/5712 [5:28:49<7:58:04,  8.48s/it]08/04/2024 15:06:58 - INFO - __main__ -   Step: 2329, LR: 3.2899328777450813e-07, Loss: 0.16162428259849548
2024-08-04T22:07:07.606111591Z 
 41%|████      | 2330/5712 [5:28:58<8:10:57,  8.71s/it]08/04/2024 15:07:07 - INFO - __main__ -   Step: 2330, LR: 3.2889600914419123e-07, Loss: 0.1977241337299347
2024-08-04T22:07:16.063641757Z 
 41%|████      | 2331/5712 [5:29:07<8:06:32,  8.63s/it]08/04/2024 15:07:16 - INFO - __main__ -   Step: 2331, LR: 3.287987305138744e-07, Loss: 0.14404451847076416
2024-08-04T22:07:24.522026427Z 
 41%|████      | 2332/5712 [5:29:15<8:03:25,  8.58s/it]08/04/2024 15:07:24 - INFO - __main__ -   Step: 2332, LR: 3.287014518835575e-07, Loss: 0.15540039539337158
2024-08-04T22:07:32.877916852Z 
 41%|████      | 2333/5712 [5:29:24<7:59:27,  8.51s/it]08/04/2024 15:07:32 - INFO - __main__ -   Step: 2333, LR: 3.286041732532406e-07, Loss: 0.26706433296203613
2024-08-04T22:07:41.304935249Z 
 41%|████      | 2334/5712 [5:29:32<7:57:51,  8.49s/it]08/04/2024 15:07:41 - INFO - __main__ -   Step: 2334, LR: 3.285068946229237e-07, Loss: 0.13867731392383575
2024-08-04T22:07:50.025867001Z 
 41%|████      | 2335/5712 [5:29:41<8:01:39,  8.56s/it]08/04/2024 15:07:50 - INFO - __main__ -   Step: 2335, LR: 3.2840961599260683e-07, Loss: 0.1764277219772339
2024-08-04T22:07:58.483922084Z 
 41%|████      | 2336/5712 [5:29:49<7:59:48,  8.53s/it]08/04/2024 15:07:58 - INFO - __main__ -   Step: 2336, LR: 3.2831233736228993e-07, Loss: 0.25700920820236206
2024-08-04T22:08:07.107230219Z 
 41%|████      | 2337/5712 [5:29:58<8:01:18,  8.56s/it]08/04/2024 15:08:07 - INFO - __main__ -   Step: 2337, LR: 3.2821505873197303e-07, Loss: 0.12009507417678833
2024-08-04T22:08:15.402328555Z 
 41%|████      | 2338/5712 [5:30:06<7:56:45,  8.48s/it]08/04/2024 15:08:15 - INFO - __main__ -   Step: 2338, LR: 3.281177801016561e-07, Loss: 0.19008620083332062
2024-08-04T22:08:23.810733675Z 
 41%|████      | 2339/5712 [5:30:14<7:55:26,  8.46s/it]08/04/2024 15:08:23 - INFO - __main__ -   Step: 2339, LR: 3.280205014713392e-07, Loss: 0.25050830841064453
2024-08-04T22:08:33.294419499Z 
 41%|████      | 2340/5712 [5:30:24<8:12:36,  8.77s/it]08/04/2024 15:08:33 - INFO - __main__ -   Step: 2340, LR: 3.279232228410224e-07, Loss: 0.24924640357494354
2024-08-04T22:08:41.791559277Z 
 41%|████      | 2341/5712 [5:30:32<8:07:56,  8.68s/it]08/04/2024 15:08:41 - INFO - __main__ -   Step: 2341, LR: 3.278259442107055e-07, Loss: 0.19115331768989563
2024-08-04T22:08:50.304207055Z 
 41%|████      | 2342/5712 [5:30:41<8:04:53,  8.63s/it]08/04/2024 15:08:50 - INFO - __main__ -   Step: 2342, LR: 3.277286655803886e-07, Loss: 0.17506858706474304
2024-08-04T22:08:58.936833594Z 
 41%|████      | 2343/5712 [5:30:50<8:04:43,  8.63s/it]08/04/2024 15:08:58 - INFO - __main__ -   Step: 2343, LR: 3.2763138695007173e-07, Loss: 0.1858888566493988
2024-08-04T22:09:06.996969677Z 
 41%|████      | 2344/5712 [5:30:58<7:54:57,  8.46s/it]08/04/2024 15:09:06 - INFO - __main__ -   Step: 2344, LR: 3.275341083197549e-07, Loss: 0.15508051216602325
2024-08-04T22:09:16.177037991Z 
 41%|████      | 2345/5712 [5:31:07<8:06:54,  8.68s/it]08/04/2024 15:09:16 - INFO - __main__ -   Step: 2345, LR: 3.27436829689438e-07, Loss: 0.1818494200706482
2024-08-04T22:09:24.546948147Z 
 41%|████      | 2346/5712 [5:31:15<8:01:36,  8.58s/it]08/04/2024 15:09:24 - INFO - __main__ -   Step: 2346, LR: 3.273395510591211e-07, Loss: 0.1334429234266281
2024-08-04T22:09:33.395686841Z 
 41%|████      | 2347/5712 [5:31:24<8:05:53,  8.66s/it]08/04/2024 15:09:33 - INFO - __main__ -   Step: 2347, LR: 3.272422724288042e-07, Loss: 0.12382113933563232
2024-08-04T22:09:40.952696491Z 
 41%|████      | 2348/5712 [5:31:32<7:47:08,  8.33s/it]08/04/2024 15:09:40 - INFO - __main__ -   Step: 2348, LR: 3.2714499379848733e-07, Loss: 0.13710859417915344
2024-08-04T22:09:50.220205429Z 
 41%|████      | 2349/5712 [5:31:41<8:02:44,  8.61s/it]08/04/2024 15:09:50 - INFO - __main__ -   Step: 2349, LR: 3.2704771516817043e-07, Loss: 0.16644200682640076
2024-08-04T22:09:59.384408863Z 
 41%|████      | 2350/5712 [5:31:50<8:11:51,  8.78s/it]08/04/2024 15:09:59 - INFO - __main__ -   Step: 2350, LR: 3.2695043653785353e-07, Loss: 0.22634711861610413
2024-08-04T22:10:07.698747391Z 
 41%|████      | 2351/5712 [5:31:58<8:03:55,  8.64s/it]08/04/2024 15:10:07 - INFO - __main__ -   Step: 2351, LR: 3.268531579075366e-07, Loss: 0.1606854349374771
2024-08-04T22:10:15.895986629Z 
 41%|████      | 2352/5712 [5:32:07<7:56:20,  8.51s/it]08/04/2024 15:10:15 - INFO - __main__ -   Step: 2352, LR: 3.267558792772198e-07, Loss: 0.171513631939888
2024-08-04T22:10:24.445168739Z 
 41%|████      | 2353/5712 [5:32:15<7:56:54,  8.52s/it]08/04/2024 15:10:24 - INFO - __main__ -   Step: 2353, LR: 3.266586006469029e-07, Loss: 0.17145979404449463
2024-08-04T22:10:32.913754830Z 
 41%|████      | 2354/5712 [5:32:24<7:55:57,  8.50s/it]08/04/2024 15:10:32 - INFO - __main__ -   Step: 2354, LR: 3.26561322016586e-07, Loss: 0.31043708324432373
2024-08-04T22:10:41.482311785Z 
 41%|████      | 2355/5712 [5:32:32<7:56:53,  8.52s/it]08/04/2024 15:10:41 - INFO - __main__ -   Step: 2355, LR: 3.264640433862691e-07, Loss: 0.30233991146087646
2024-08-04T22:10:49.624349887Z 
 41%|████      | 2356/5712 [5:32:40<7:50:20,  8.41s/it]08/04/2024 15:10:49 - INFO - __main__ -   Step: 2356, LR: 3.2636676475595223e-07, Loss: 0.2689003348350525
2024-08-04T22:10:58.196428581Z 
 41%|████▏     | 2357/5712 [5:32:49<7:52:56,  8.46s/it]08/04/2024 15:10:58 - INFO - __main__ -   Step: 2357, LR: 3.262694861256353e-07, Loss: 0.21359217166900635
2024-08-04T22:11:07.284677732Z 
 41%|████▏     | 2358/5712 [5:32:58<8:03:22,  8.65s/it]08/04/2024 15:11:07 - INFO - __main__ -   Step: 2358, LR: 3.261722074953184e-07, Loss: 0.11854994297027588
2024-08-04T22:11:15.795163607Z 
 41%|████▏     | 2359/5712 [5:33:06<8:00:56,  8.61s/it]08/04/2024 15:11:15 - INFO - __main__ -   Step: 2359, LR: 3.260749288650015e-07, Loss: 0.2065303921699524
2024-08-04T22:11:24.426574378Z 
 41%|████▏     | 2360/5712 [5:33:15<8:01:12,  8.61s/it]08/04/2024 15:11:24 - INFO - __main__ -   Step: 2360, LR: 3.259776502346847e-07, Loss: 0.24035832285881042
2024-08-04T22:11:32.568307168Z 
 41%|████▏     | 2361/5712 [5:33:23<7:53:10,  8.47s/it]08/04/2024 15:11:32 - INFO - __main__ -   Step: 2361, LR: 3.2588037160436783e-07, Loss: 0.1635049730539322
2024-08-04T22:11:40.902013571Z 
 41%|████▏     | 2362/5712 [5:33:32<7:50:42,  8.43s/it]08/04/2024 15:11:40 - INFO - __main__ -   Step: 2362, LR: 3.2578309297405093e-07, Loss: 0.24622538685798645
2024-08-04T22:11:49.441019318Z 
 41%|████▏     | 2363/5712 [5:33:40<7:52:23,  8.46s/it]08/04/2024 15:11:49 - INFO - __main__ -   Step: 2363, LR: 3.25685814343734e-07, Loss: 0.20293354988098145
2024-08-04T22:11:57.920292703Z 
 41%|████▏     | 2364/5712 [5:33:49<7:52:30,  8.47s/it]08/04/2024 15:11:57 - INFO - __main__ -   Step: 2364, LR: 3.255885357134172e-07, Loss: 0.13731127977371216
2024-08-04T22:12:06.331910742Z 
 41%|████▏     | 2365/5712 [5:33:57<7:51:25,  8.45s/it]08/04/2024 15:12:06 - INFO - __main__ -   Step: 2365, LR: 3.254912570831003e-07, Loss: 0.19610047340393066
2024-08-04T22:12:15.114395447Z 
 41%|████▏     | 2366/5712 [5:34:06<7:56:49,  8.55s/it]08/04/2024 15:12:15 - INFO - __main__ -   Step: 2366, LR: 3.253939784527834e-07, Loss: 0.2759305238723755
2024-08-04T22:12:23.867413881Z 
 41%|████▏     | 2367/5712 [5:34:15<8:00:04,  8.61s/it]08/04/2024 15:12:23 - INFO - __main__ -   Step: 2367, LR: 3.252966998224665e-07, Loss: 0.2553558945655823
2024-08-04T22:12:32.392169658Z 
 41%|████▏     | 2368/5712 [5:34:23<7:58:29,  8.59s/it]08/04/2024 15:12:32 - INFO - __main__ -   Step: 2368, LR: 3.2519942119214963e-07, Loss: 0.2255374789237976
2024-08-04T22:12:40.929806561Z 
 41%|████▏     | 2369/5712 [5:34:32<7:57:32,  8.57s/it]08/04/2024 15:12:40 - INFO - __main__ -   Step: 2369, LR: 3.251021425618327e-07, Loss: 0.23156549036502838
2024-08-04T22:12:50.322065541Z 
 41%|████▏     | 2370/5712 [5:34:41<8:11:06,  8.82s/it]08/04/2024 15:12:50 - INFO - __main__ -   Step: 2370, LR: 3.250048639315158e-07, Loss: 0.22866716980934143
2024-08-04T22:12:58.504878873Z 
 42%|████▏     | 2371/5712 [5:34:49<8:00:23,  8.63s/it]08/04/2024 15:12:58 - INFO - __main__ -   Step: 2371, LR: 3.249075853011989e-07, Loss: 0.20391647517681122
2024-08-04T22:13:06.919782983Z 
 42%|████▏     | 2372/5712 [5:34:58<7:56:41,  8.56s/it]08/04/2024 15:13:06 - INFO - __main__ -   Step: 2372, LR: 3.248103066708821e-07, Loss: 0.1758365035057068
2024-08-04T22:13:15.096206840Z 
 42%|████▏     | 2373/5712 [5:35:06<7:50:05,  8.45s/it]08/04/2024 15:13:15 - INFO - __main__ -   Step: 2373, LR: 3.247130280405652e-07, Loss: 0.17022880911827087
2024-08-04T22:13:23.598079956Z 
 42%|████▏     | 2374/5712 [5:35:14<7:50:51,  8.46s/it]08/04/2024 15:13:23 - INFO - __main__ -   Step: 2374, LR: 3.246157494102483e-07, Loss: 0.23030027747154236
2024-08-04T22:13:32.534240701Z 
 42%|████▏     | 2375/5712 [5:35:23<7:58:36,  8.61s/it]08/04/2024 15:13:32 - INFO - __main__ -   Step: 2375, LR: 3.2451847077993137e-07, Loss: 0.12171265482902527
2024-08-04T22:13:40.831581564Z 
 42%|████▏     | 2376/5712 [5:35:31<7:53:19,  8.51s/it]08/04/2024 15:13:40 - INFO - __main__ -   Step: 2376, LR: 3.2442119214961447e-07, Loss: 0.1666274517774582
2024-08-04T22:13:49.354042095Z 
 42%|████▏     | 2377/5712 [5:35:40<7:53:20,  8.52s/it]08/04/2024 15:13:49 - INFO - __main__ -   Step: 2377, LR: 3.243239135192976e-07, Loss: 0.18906639516353607
2024-08-04T22:13:57.943346880Z 
 42%|████▏     | 2378/5712 [5:35:49<7:54:25,  8.54s/it]08/04/2024 15:13:57 - INFO - __main__ -   Step: 2378, LR: 3.242266348889807e-07, Loss: 0.19833531975746155
2024-08-04T22:14:06.703413657Z 
 42%|████▏     | 2379/5712 [5:35:57<7:57:58,  8.60s/it]08/04/2024 15:14:06 - INFO - __main__ -   Step: 2379, LR: 3.241293562586639e-07, Loss: 0.25340360403060913
2024-08-04T22:14:14.700049955Z 
 42%|████▏     | 2380/5712 [5:36:05<7:47:42,  8.42s/it]08/04/2024 15:14:14 - INFO - __main__ -   Step: 2380, LR: 3.24032077628347e-07, Loss: 0.14300782978534698
2024-08-04T22:14:23.103451030Z 
 42%|████▏     | 2381/5712 [5:36:14<7:47:15,  8.42s/it]08/04/2024 15:14:23 - INFO - __main__ -   Step: 2381, LR: 3.239347989980301e-07, Loss: 0.18964165449142456
2024-08-04T22:14:31.303899921Z 
 42%|████▏     | 2382/5712 [5:36:22<7:43:31,  8.35s/it]08/04/2024 15:14:31 - INFO - __main__ -   Step: 2382, LR: 3.238375203677132e-07, Loss: 0.12749701738357544
2024-08-04T22:14:40.286371020Z 
 42%|████▏     | 2383/5712 [5:36:31<7:53:52,  8.54s/it]08/04/2024 15:14:40 - INFO - __main__ -   Step: 2383, LR: 3.237402417373963e-07, Loss: 0.22454771399497986
2024-08-04T22:14:48.835654200Z 
 42%|████▏     | 2384/5712 [5:36:39<7:53:52,  8.54s/it]08/04/2024 15:14:48 - INFO - __main__ -   Step: 2384, LR: 3.236429631070794e-07, Loss: 0.16646674275398254
2024-08-04T22:14:57.254331858Z 
 42%|████▏     | 2385/5712 [5:36:48<7:51:39,  8.51s/it]08/04/2024 15:14:57 - INFO - __main__ -   Step: 2385, LR: 3.235456844767626e-07, Loss: 0.12795206904411316
2024-08-04T22:15:05.715953138Z 
 42%|████▏     | 2386/5712 [5:36:56<7:50:46,  8.49s/it]08/04/2024 15:15:05 - INFO - __main__ -   Step: 2386, LR: 3.234484058464457e-07, Loss: 0.20234590768814087
2024-08-04T22:15:15.023101526Z 
 42%|████▏     | 2387/5712 [5:37:06<8:04:09,  8.74s/it]08/04/2024 15:15:15 - INFO - __main__ -   Step: 2387, LR: 3.2335112721612877e-07, Loss: 0.17966130375862122
2024-08-04T22:15:23.251312998Z 
 42%|████▏     | 2388/5712 [5:37:14<7:55:34,  8.58s/it]08/04/2024 15:15:23 - INFO - __main__ -   Step: 2388, LR: 3.2325384858581187e-07, Loss: 0.13562700152397156
2024-08-04T22:15:32.040070038Z 
 42%|████▏     | 2389/5712 [5:37:23<7:58:50,  8.65s/it]08/04/2024 15:15:32 - INFO - __main__ -   Step: 2389, LR: 3.23156569955495e-07, Loss: 0.1759318709373474
2024-08-04T22:15:40.597020655Z 
 42%|████▏     | 2390/5712 [5:37:31<7:57:12,  8.62s/it]08/04/2024 15:15:40 - INFO - __main__ -   Step: 2390, LR: 3.230592913251781e-07, Loss: 0.17396453022956848
2024-08-04T22:15:48.766161659Z 
 42%|████▏     | 2391/5712 [5:37:39<7:49:35,  8.48s/it]08/04/2024 15:15:48 - INFO - __main__ -   Step: 2391, LR: 3.229620126948612e-07, Loss: 0.21644048392772675
2024-08-04T22:15:57.822222854Z 
 42%|████▏     | 2392/5712 [5:37:48<7:58:56,  8.66s/it]08/04/2024 15:15:57 - INFO - __main__ -   Step: 2392, LR: 3.228647340645443e-07, Loss: 0.24264901876449585
2024-08-04T22:16:06.687546801Z 
 42%|████▏     | 2393/5712 [5:37:57<8:02:17,  8.72s/it]08/04/2024 15:16:06 - INFO - __main__ -   Step: 2393, LR: 3.227674554342275e-07, Loss: 0.1460534632205963
2024-08-04T22:16:15.355557764Z 
 42%|████▏     | 2394/5712 [5:38:06<8:01:18,  8.70s/it]08/04/2024 15:16:15 - INFO - __main__ -   Step: 2394, LR: 3.2267017680391057e-07, Loss: 0.2170659601688385
2024-08-04T22:16:24.258365571Z 
 42%|████▏     | 2395/5712 [5:38:15<8:04:27,  8.76s/it]08/04/2024 15:16:24 - INFO - __main__ -   Step: 2395, LR: 3.2257289817359367e-07, Loss: 0.24235817790031433
2024-08-04T22:16:32.601900250Z 
 42%|████▏     | 2396/5712 [5:38:23<7:57:21,  8.64s/it]08/04/2024 15:16:32 - INFO - __main__ -   Step: 2396, LR: 3.2247561954327677e-07, Loss: 0.13020575046539307
2024-08-04T22:16:40.548333535Z 
 42%|████▏     | 2397/5712 [5:38:31<7:45:45,  8.43s/it]08/04/2024 15:16:40 - INFO - __main__ -   Step: 2397, LR: 3.2237834091296e-07, Loss: 0.16540448367595673
2024-08-04T22:16:49.854128812Z 
 42%|████▏     | 2398/5712 [5:38:41<8:00:07,  8.69s/it]08/04/2024 15:16:49 - INFO - __main__ -   Step: 2398, LR: 3.222810622826431e-07, Loss: 0.2853015959262848
2024-08-04T22:16:57.618087542Z 
 42%|████▏     | 2399/5712 [5:38:48<7:44:35,  8.41s/it]08/04/2024 15:16:57 - INFO - __main__ -   Step: 2399, LR: 3.221837836523262e-07, Loss: 0.17230285704135895
2024-08-04T22:17:06.192503915Z 
 42%|████▏     | 2400/5712 [5:38:57<7:47:06,  8.46s/it]08/04/2024 15:17:06 - INFO - __main__ -   Step: 2400, LR: 3.2208650502200927e-07, Loss: 0.173697829246521
2024-08-04T22:17:14.614444809Z 
 42%|████▏     | 2401/5712 [5:39:05<7:46:18,  8.45s/it]08/04/2024 15:17:14 - INFO - __main__ -   Step: 2401, LR: 3.219892263916924e-07, Loss: 0.16736453771591187
2024-08-04T22:17:22.792962967Z 
 42%|████▏     | 2402/5712 [5:39:13<7:41:40,  8.37s/it]08/04/2024 15:17:22 - INFO - __main__ -   Step: 2402, LR: 3.218919477613755e-07, Loss: 0.1864512860774994
2024-08-04T22:17:31.535334799Z 
 42%|████▏     | 2403/5712 [5:39:22<7:47:42,  8.48s/it]08/04/2024 15:17:31 - INFO - __main__ -   Step: 2403, LR: 3.217946691310586e-07, Loss: 0.20027892291545868
2024-08-04T22:17:40.486210126Z 
 42%|████▏     | 2404/5712 [5:39:31<7:55:19,  8.62s/it]08/04/2024 15:17:40 - INFO - __main__ -   Step: 2404, LR: 3.216973905007417e-07, Loss: 0.23971670866012573
2024-08-04T22:17:48.740545043Z 
 42%|████▏     | 2405/5712 [5:39:39<7:49:08,  8.51s/it]08/04/2024 15:17:48 - INFO - __main__ -   Step: 2405, LR: 3.216001118704249e-07, Loss: 0.2092464566230774
2024-08-04T22:17:57.091392918Z 
 42%|████▏     | 2406/5712 [5:39:48<7:46:20,  8.46s/it]08/04/2024 15:17:57 - INFO - __main__ -   Step: 2406, LR: 3.2150283324010797e-07, Loss: 0.16496197879314423
2024-08-04T22:18:05.568432942Z 
 42%|████▏     | 2407/5712 [5:39:56<7:46:25,  8.47s/it]08/04/2024 15:18:05 - INFO - __main__ -   Step: 2407, LR: 3.2140555460979107e-07, Loss: 0.23584836721420288
2024-08-04T22:18:14.543235953Z 
 42%|████▏     | 2408/5712 [5:40:05<7:54:39,  8.62s/it]08/04/2024 15:18:14 - INFO - __main__ -   Step: 2408, LR: 3.2130827597947417e-07, Loss: 0.17636214196681976
2024-08-04T22:18:23.191456629Z 
 42%|████▏     | 2409/5712 [5:40:14<7:54:58,  8.63s/it]08/04/2024 15:18:23 - INFO - __main__ -   Step: 2409, LR: 3.212109973491573e-07, Loss: 0.1820063292980194
2024-08-04T22:18:31.900653664Z 
 42%|████▏     | 2410/5712 [5:40:23<7:56:10,  8.65s/it]08/04/2024 15:18:31 - INFO - __main__ -   Step: 2410, LR: 3.211137187188404e-07, Loss: 0.1667221188545227
2024-08-04T22:18:40.299954245Z 
 42%|████▏     | 2411/5712 [5:40:31<7:51:51,  8.58s/it]08/04/2024 15:18:40 - INFO - __main__ -   Step: 2411, LR: 3.210164400885235e-07, Loss: 0.21704384684562683
2024-08-04T22:18:48.894015133Z 
 42%|████▏     | 2412/5712 [5:40:40<7:52:00,  8.58s/it]08/04/2024 15:18:48 - INFO - __main__ -   Step: 2412, LR: 3.209191614582066e-07, Loss: 0.14587312936782837
2024-08-04T22:18:57.140925196Z 
 42%|████▏     | 2413/5712 [5:40:48<7:46:20,  8.48s/it]08/04/2024 15:18:57 - INFO - __main__ -   Step: 2413, LR: 3.208218828278897e-07, Loss: 0.24540764093399048
2024-08-04T22:19:05.177896071Z 
 42%|████▏     | 2414/5712 [5:40:56<7:38:51,  8.35s/it]08/04/2024 15:19:05 - INFO - __main__ -   Step: 2414, LR: 3.2072460419757287e-07, Loss: 0.16055147349834442
2024-08-04T22:19:13.889134100Z 
 42%|████▏     | 2415/5712 [5:41:05<7:44:42,  8.46s/it]08/04/2024 15:19:13 - INFO - __main__ -   Step: 2415, LR: 3.20627325567256e-07, Loss: 0.2174513339996338
2024-08-04T22:19:21.879558093Z 
 42%|████▏     | 2416/5712 [5:41:13<7:36:52,  8.32s/it]08/04/2024 15:19:21 - INFO - __main__ -   Step: 2416, LR: 3.205300469369391e-07, Loss: 0.1668567955493927
2024-08-04T22:19:30.212170844Z 
 42%|████▏     | 2417/5712 [5:41:21<7:36:59,  8.32s/it]08/04/2024 15:19:30 - INFO - __main__ -   Step: 2417, LR: 3.204327683066222e-07, Loss: 0.13299645483493805
2024-08-04T22:19:39.024206660Z 
 42%|████▏     | 2418/5712 [5:41:30<7:44:56,  8.47s/it]08/04/2024 15:19:39 - INFO - __main__ -   Step: 2418, LR: 3.2033548967630537e-07, Loss: 0.2425815463066101
2024-08-04T22:19:47.661185712Z 
 42%|████▏     | 2419/5712 [5:41:38<7:47:33,  8.52s/it]08/04/2024 15:19:47 - INFO - __main__ -   Step: 2419, LR: 3.2023821104598847e-07, Loss: 0.1912599503993988
2024-08-04T22:19:55.938553609Z 
 42%|████▏     | 2420/5712 [5:41:47<7:43:26,  8.45s/it]08/04/2024 15:19:55 - INFO - __main__ -   Step: 2420, LR: 3.2014093241567157e-07, Loss: 0.19750577211380005
2024-08-04T22:20:04.850572391Z 
 42%|████▏     | 2421/5712 [5:41:55<7:50:56,  8.59s/it]08/04/2024 15:20:04 - INFO - __main__ -   Step: 2421, LR: 3.2004365378535467e-07, Loss: 0.2435193955898285
2024-08-04T22:20:12.866008987Z 
 42%|████▏     | 2422/5712 [5:42:04<7:41:25,  8.42s/it]08/04/2024 15:20:12 - INFO - __main__ -   Step: 2422, LR: 3.199463751550378e-07, Loss: 0.21138286590576172
2024-08-04T22:20:21.553313273Z 
 42%|████▏     | 2423/5712 [5:42:12<7:45:45,  8.50s/it]08/04/2024 15:20:21 - INFO - __main__ -   Step: 2423, LR: 3.198490965247209e-07, Loss: 0.14141103625297546
2024-08-04T22:20:29.798298245Z 
 42%|████▏     | 2424/5712 [5:42:20<7:41:29,  8.42s/it]08/04/2024 15:20:29 - INFO - __main__ -   Step: 2424, LR: 3.19751817894404e-07, Loss: 0.2972582280635834
2024-08-04T22:20:38.045474946Z 
 42%|████▏     | 2425/5712 [5:42:29<7:38:29,  8.37s/it]08/04/2024 15:20:38 - INFO - __main__ -   Step: 2425, LR: 3.196545392640871e-07, Loss: 0.1786554455757141
2024-08-04T22:20:46.748255176Z 
 42%|████▏     | 2426/5712 [5:42:37<7:43:49,  8.47s/it]08/04/2024 15:20:46 - INFO - __main__ -   Step: 2426, LR: 3.1955726063377027e-07, Loss: 0.24115128815174103
2024-08-04T22:20:55.816506058Z 
 42%|████▏     | 2427/5712 [5:42:46<7:53:31,  8.65s/it]08/04/2024 15:20:55 - INFO - __main__ -   Step: 2427, LR: 3.1945998200345337e-07, Loss: 0.18112416565418243
2024-08-04T22:21:04.215615870Z 
 43%|████▎     | 2428/5712 [5:42:55<7:49:16,  8.57s/it]08/04/2024 15:21:04 - INFO - __main__ -   Step: 2428, LR: 3.1936270337313647e-07, Loss: 0.16097405552864075
2024-08-04T22:21:13.273484634Z 
 43%|████▎     | 2429/5712 [5:43:04<7:57:04,  8.72s/it]08/04/2024 15:21:13 - INFO - __main__ -   Step: 2429, LR: 3.1926542474281957e-07, Loss: 0.11700750142335892
2024-08-04T22:21:21.531022117Z 
 43%|████▎     | 2430/5712 [5:43:12<7:49:21,  8.58s/it]08/04/2024 15:21:21 - INFO - __main__ -   Step: 2430, LR: 3.191681461125027e-07, Loss: 0.20484715700149536
2024-08-04T22:21:29.717361815Z 
 43%|████▎     | 2431/5712 [5:43:20<7:42:44,  8.46s/it]08/04/2024 15:21:29 - INFO - __main__ -   Step: 2431, LR: 3.190708674821858e-07, Loss: 0.2993631362915039
2024-08-04T22:21:38.638637237Z 
 43%|████▎     | 2432/5712 [5:43:29<7:50:07,  8.60s/it]08/04/2024 15:21:38 - INFO - __main__ -   Step: 2432, LR: 3.189735888518689e-07, Loss: 0.10961765050888062
2024-08-04T22:21:46.925509060Z 
 43%|████▎     | 2433/5712 [5:43:38<7:44:51,  8.51s/it]08/04/2024 15:21:46 - INFO - __main__ -   Step: 2433, LR: 3.1887631022155207e-07, Loss: 0.18617641925811768
2024-08-04T22:21:55.992414181Z 
 43%|████▎     | 2434/5712 [5:43:47<7:53:54,  8.67s/it]08/04/2024 15:21:55 - INFO - __main__ -   Step: 2434, LR: 3.187790315912352e-07, Loss: 0.20904608070850372
2024-08-04T22:22:04.927290271Z 
 43%|████▎     | 2435/5712 [5:43:56<7:58:01,  8.75s/it]08/04/2024 15:22:04 - INFO - __main__ -   Step: 2435, LR: 3.186817529609183e-07, Loss: 0.14303919672966003
2024-08-04T22:22:13.167469224Z 
 43%|████▎     | 2436/5712 [5:44:04<7:49:29,  8.60s/it]08/04/2024 15:22:13 - INFO - __main__ -   Step: 2436, LR: 3.185844743306014e-07, Loss: 0.2460325062274933
2024-08-04T22:22:21.843965745Z 
 43%|████▎     | 2437/5712 [5:44:12<7:50:37,  8.62s/it]08/04/2024 15:22:21 - INFO - __main__ -   Step: 2437, LR: 3.184871957002845e-07, Loss: 0.1103929802775383
2024-08-04T22:22:31.171189496Z 
 43%|████▎     | 2438/5712 [5:44:22<8:02:00,  8.83s/it]08/04/2024 15:22:31 - INFO - __main__ -   Step: 2438, LR: 3.1838991706996767e-07, Loss: 0.1318519562482834
2024-08-04T22:22:39.221619965Z 
 43%|████▎     | 2439/5712 [5:44:30<7:49:03,  8.60s/it]08/04/2024 15:22:39 - INFO - __main__ -   Step: 2439, LR: 3.1829263843965077e-07, Loss: 0.23903602361679077
2024-08-04T22:22:47.410552422Z 
 43%|████▎     | 2440/5712 [5:44:38<7:42:12,  8.48s/it]08/04/2024 15:22:47 - INFO - __main__ -   Step: 2440, LR: 3.1819535980933387e-07, Loss: 0.18927001953125
2024-08-04T22:22:55.838543806Z 
 43%|████▎     | 2441/5712 [5:44:46<7:41:17,  8.46s/it]08/04/2024 15:22:55 - INFO - __main__ -   Step: 2441, LR: 3.1809808117901697e-07, Loss: 0.19362428784370422
2024-08-04T22:23:04.026685859Z 
 43%|████▎     | 2442/5712 [5:44:55<7:36:40,  8.38s/it]08/04/2024 15:23:04 - INFO - __main__ -   Step: 2442, LR: 3.180008025487001e-07, Loss: 0.21056334674358368
2024-08-04T22:23:13.020694320Z 
 43%|████▎     | 2443/5712 [5:45:04<7:46:35,  8.56s/it]08/04/2024 15:23:13 - INFO - __main__ -   Step: 2443, LR: 3.179035239183832e-07, Loss: 0.13567626476287842
2024-08-04T22:23:21.604628282Z 
 43%|████▎     | 2444/5712 [5:45:12<7:46:46,  8.57s/it]08/04/2024 15:23:21 - INFO - __main__ -   Step: 2444, LR: 3.178062452880663e-07, Loss: 0.17342627048492432
2024-08-04T22:23:30.072226899Z 
 43%|████▎     | 2445/5712 [5:45:21<7:44:57,  8.54s/it]08/04/2024 15:23:30 - INFO - __main__ -   Step: 2445, LR: 3.177089666577494e-07, Loss: 0.1675395369529724
2024-08-04T22:23:38.221554481Z 
 43%|████▎     | 2446/5712 [5:45:29<7:38:26,  8.42s/it]08/04/2024 15:23:38 - INFO - __main__ -   Step: 2446, LR: 3.1761168802743257e-07, Loss: 0.3734467625617981
2024-08-04T22:23:47.378569810Z 
 43%|████▎     | 2447/5712 [5:45:38<7:50:18,  8.64s/it]08/04/2024 15:23:47 - INFO - __main__ -   Step: 2447, LR: 3.1751440939711567e-07, Loss: 0.21909451484680176
2024-08-04T22:23:55.515978613Z 
 43%|████▎     | 2448/5712 [5:45:46<7:41:54,  8.49s/it]08/04/2024 15:23:55 - INFO - __main__ -   Step: 2448, LR: 3.1741713076679877e-07, Loss: 0.19433599710464478
2024-08-04T22:24:04.136921566Z 
 43%|████▎     | 2449/5712 [5:45:55<7:43:53,  8.53s/it]08/04/2024 15:24:04 - INFO - __main__ -   Step: 2449, LR: 3.1731985213648187e-07, Loss: 0.2238977998495102
2024-08-04T22:24:12.082746976Z 
 43%|████▎     | 2450/5712 [5:46:03<7:34:13,  8.35s/it]08/04/2024 15:24:12 - INFO - __main__ -   Step: 2450, LR: 3.1722257350616497e-07, Loss: 0.16836191713809967
2024-08-04T22:24:21.047318613Z 
 43%|████▎     | 2451/5712 [5:46:12<7:44:01,  8.54s/it]08/04/2024 15:24:21 - INFO - __main__ -   Step: 2451, LR: 3.1712529487584817e-07, Loss: 0.25658249855041504
2024-08-04T22:24:30.426211091Z 
 43%|████▎     | 2452/5712 [5:46:21<7:57:35,  8.79s/it]08/04/2024 15:24:30 - INFO - __main__ -   Step: 2452, LR: 3.1702801624553127e-07, Loss: 0.23099340498447418
2024-08-04T22:24:38.518609043Z 
 43%|████▎     | 2453/5712 [5:46:29<7:46:04,  8.58s/it]08/04/2024 15:24:38 - INFO - __main__ -   Step: 2453, LR: 3.1693073761521437e-07, Loss: 0.13184651732444763
2024-08-04T22:24:46.963820866Z 
 43%|████▎     | 2454/5712 [5:46:38<7:43:43,  8.54s/it]08/04/2024 15:24:46 - INFO - __main__ -   Step: 2454, LR: 3.1683345898489747e-07, Loss: 0.16527804732322693
2024-08-04T22:24:55.639964853Z 
 43%|████▎     | 2455/5712 [5:46:46<7:45:46,  8.58s/it]08/04/2024 15:24:55 - INFO - __main__ -   Step: 2455, LR: 3.167361803545806e-07, Loss: 0.20455443859100342
2024-08-04T22:25:03.664639518Z 
 43%|████▎     | 2456/5712 [5:46:54<7:36:36,  8.41s/it]08/04/2024 15:25:03 - INFO - __main__ -   Step: 2456, LR: 3.166389017242637e-07, Loss: 0.16677787899971008
2024-08-04T22:25:11.999147856Z 
 43%|████▎     | 2457/5712 [5:47:03<7:35:10,  8.39s/it]08/04/2024 15:25:11 - INFO - __main__ -   Step: 2457, LR: 3.165416230939468e-07, Loss: 0.1797390729188919
2024-08-04T22:25:20.564072058Z 
 43%|████▎     | 2458/5712 [5:47:11<7:37:52,  8.44s/it]08/04/2024 15:25:20 - INFO - __main__ -   Step: 2458, LR: 3.164443444636299e-07, Loss: 0.29769834876060486
2024-08-04T22:25:28.817137452Z 
 43%|████▎     | 2459/5712 [5:47:19<7:34:38,  8.39s/it]08/04/2024 15:25:28 - INFO - __main__ -   Step: 2459, LR: 3.1634706583331307e-07, Loss: 0.23209862411022186
2024-08-04T22:25:37.825031098Z 
 43%|████▎     | 2460/5712 [5:47:28<7:44:37,  8.57s/it]08/04/2024 15:25:37 - INFO - __main__ -   Step: 2460, LR: 3.1624978720299617e-07, Loss: 0.17306935787200928
2024-08-04T22:25:46.302196543Z 
 43%|████▎     | 2461/5712 [5:47:37<7:42:56,  8.54s/it]08/04/2024 15:25:46 - INFO - __main__ -   Step: 2461, LR: 3.1615250857267927e-07, Loss: 0.17595167458057404
2024-08-04T22:25:54.494200688Z 
 43%|████▎     | 2462/5712 [5:47:45<7:37:04,  8.44s/it]08/04/2024 15:25:54 - INFO - __main__ -   Step: 2462, LR: 3.1605522994236237e-07, Loss: 0.11207963526248932
2024-08-04T22:26:02.865668662Z 
 43%|████▎     | 2463/5712 [5:47:54<7:35:50,  8.42s/it]08/04/2024 15:26:02 - INFO - __main__ -   Step: 2463, LR: 3.159579513120455e-07, Loss: 0.18749797344207764
2024-08-04T22:26:11.103987459Z 
 43%|████▎     | 2464/5712 [5:48:02<7:32:46,  8.36s/it]08/04/2024 15:26:11 - INFO - __main__ -   Step: 2464, LR: 3.158606726817286e-07, Loss: 0.17922040820121765
2024-08-04T22:26:19.138666323Z 
 43%|████▎     | 2465/5712 [5:48:10<7:27:17,  8.27s/it]08/04/2024 15:26:19 - INFO - __main__ -   Step: 2465, LR: 3.157633940514117e-07, Loss: 0.3154815137386322
2024-08-04T22:26:27.571780248Z 
 43%|████▎     | 2466/5712 [5:48:18<7:29:52,  8.32s/it]08/04/2024 15:26:27 - INFO - __main__ -   Step: 2466, LR: 3.156661154210948e-07, Loss: 0.13315418362617493
2024-08-04T22:26:35.859658203Z 
 43%|████▎     | 2467/5712 [5:48:27<7:29:17,  8.31s/it]08/04/2024 15:26:35 - INFO - __main__ -   Step: 2467, LR: 3.1556883679077797e-07, Loss: 0.30956751108169556
2024-08-04T22:26:44.328667772Z 
 43%|████▎     | 2468/5712 [5:48:35<7:31:46,  8.36s/it]08/04/2024 15:26:44 - INFO - __main__ -   Step: 2468, LR: 3.1547155816046107e-07, Loss: 0.1780211627483368
2024-08-04T22:26:53.295374864Z 
 43%|████▎     | 2469/5712 [5:48:44<7:41:32,  8.54s/it]08/04/2024 15:26:53 - INFO - __main__ -   Step: 2469, LR: 3.153742795301442e-07, Loss: 0.2881819009780884
2024-08-04T22:27:01.433839299Z 
 43%|████▎     | 2470/5712 [5:48:52<7:34:54,  8.42s/it]08/04/2024 15:27:01 - INFO - __main__ -   Step: 2470, LR: 3.152770008998273e-07, Loss: 0.2202291190624237
2024-08-04T22:27:09.927527137Z 
 43%|████▎     | 2471/5712 [5:49:01<7:35:58,  8.44s/it]08/04/2024 15:27:09 - INFO - __main__ -   Step: 2471, LR: 3.1517972226951047e-07, Loss: 0.18931668996810913
2024-08-04T22:27:18.930933372Z 
 43%|████▎     | 2472/5712 [5:49:10<7:44:55,  8.61s/it]08/04/2024 15:27:18 - INFO - __main__ -   Step: 2472, LR: 3.1508244363919357e-07, Loss: 0.0666949599981308
2024-08-04T22:27:26.890774264Z 
 43%|████▎     | 2473/5712 [5:49:18<7:34:16,  8.42s/it]08/04/2024 15:27:26 - INFO - __main__ -   Step: 2473, LR: 3.1498516500887667e-07, Loss: 0.27566003799438477
2024-08-04T22:27:35.008747592Z 
 43%|████▎     | 2474/5712 [5:49:26<7:29:19,  8.33s/it]08/04/2024 15:27:35 - INFO - __main__ -   Step: 2474, LR: 3.1488788637855977e-07, Loss: 0.26383787393569946
2024-08-04T22:27:43.410410775Z 
 43%|████▎     | 2475/5712 [5:49:34<7:30:24,  8.35s/it]08/04/2024 15:27:43 - INFO - __main__ -   Step: 2475, LR: 3.147906077482429e-07, Loss: 0.2106059491634369
2024-08-04T22:27:51.746819251Z 
 43%|████▎     | 2476/5712 [5:49:42<7:30:04,  8.35s/it]08/04/2024 15:27:51 - INFO - __main__ -   Step: 2476, LR: 3.14693329117926e-07, Loss: 0.1617114245891571
2024-08-04T22:28:00.302443727Z 
 43%|████▎     | 2477/5712 [5:49:51<7:33:20,  8.41s/it]08/04/2024 15:28:00 - INFO - __main__ -   Step: 2477, LR: 3.145960504876091e-07, Loss: 0.10912639647722244
2024-08-04T22:28:08.769611941Z 
 43%|████▎     | 2478/5712 [5:49:59<7:34:09,  8.43s/it]08/04/2024 15:28:08 - INFO - __main__ -   Step: 2478, LR: 3.144987718572922e-07, Loss: 0.20781108736991882
2024-08-04T22:28:17.047897874Z 
 43%|████▎     | 2479/5712 [5:50:08<7:31:37,  8.38s/it]08/04/2024 15:28:17 - INFO - __main__ -   Step: 2479, LR: 3.1440149322697537e-07, Loss: 0.14337578415870667
2024-08-04T22:28:25.229471899Z 
 43%|████▎     | 2480/5712 [5:50:16<7:28:15,  8.32s/it]08/04/2024 15:28:25 - INFO - __main__ -   Step: 2480, LR: 3.1430421459665847e-07, Loss: 0.12313159555196762
2024-08-04T22:28:33.867777152Z 
 43%|████▎     | 2481/5712 [5:50:25<7:33:14,  8.42s/it]08/04/2024 15:28:33 - INFO - __main__ -   Step: 2481, LR: 3.1420693596634157e-07, Loss: 0.1848590224981308
2024-08-04T22:28:41.431730511Z 
 43%|████▎     | 2482/5712 [5:50:32<7:19:19,  8.16s/it]08/04/2024 15:28:41 - INFO - __main__ -   Step: 2482, LR: 3.1410965733602467e-07, Loss: 0.18280456960201263
2024-08-04T22:28:50.171546522Z 
 43%|████▎     | 2483/5712 [5:50:41<7:28:32,  8.33s/it]08/04/2024 15:28:50 - INFO - __main__ -   Step: 2483, LR: 3.140123787057078e-07, Loss: 0.2050008922815323
2024-08-04T22:28:58.598021897Z 
 43%|████▎     | 2484/5712 [5:50:49<7:29:53,  8.36s/it]08/04/2024 15:28:58 - INFO - __main__ -   Step: 2484, LR: 3.139151000753909e-07, Loss: 0.1690610647201538
2024-08-04T22:29:06.982750423Z 
 44%|████▎     | 2485/5712 [5:50:58<7:30:06,  8.37s/it]08/04/2024 15:29:06 - INFO - __main__ -   Step: 2485, LR: 3.13817821445074e-07, Loss: 0.13400615751743317
2024-08-04T22:29:16.138299379Z 
 44%|████▎     | 2486/5712 [5:51:07<7:42:39,  8.60s/it]08/04/2024 15:29:16 - INFO - __main__ -   Step: 2486, LR: 3.137205428147571e-07, Loss: 0.17086689174175262
2024-08-04T22:29:24.878062431Z 
 44%|████▎     | 2487/5712 [5:51:16<7:44:41,  8.65s/it]08/04/2024 15:29:24 - INFO - __main__ -   Step: 2487, LR: 3.136232641844403e-07, Loss: 0.17846059799194336
2024-08-04T22:29:33.210911858Z 
 44%|████▎     | 2488/5712 [5:51:24<7:39:30,  8.55s/it]08/04/2024 15:29:33 - INFO - __main__ -   Step: 2488, LR: 3.135259855541234e-07, Loss: 0.3505544066429138
2024-08-04T22:29:42.025231886Z 
 44%|████▎     | 2489/5712 [5:51:33<7:43:34,  8.63s/it]08/04/2024 15:29:42 - INFO - __main__ -   Step: 2489, LR: 3.134287069238065e-07, Loss: 0.22649089992046356
2024-08-04T22:29:50.110092575Z 
 44%|████▎     | 2490/5712 [5:51:41<7:34:40,  8.47s/it]08/04/2024 15:29:50 - INFO - __main__ -   Step: 2490, LR: 3.133314282934896e-07, Loss: 0.1484520435333252
2024-08-04T22:29:58.556300004Z 
 44%|████▎     | 2491/5712 [5:51:49<7:34:11,  8.46s/it]08/04/2024 15:29:58 - INFO - __main__ -   Step: 2491, LR: 3.1323414966317277e-07, Loss: 0.2703506350517273
2024-08-04T22:30:07.206548287Z 
 44%|████▎     | 2492/5712 [5:51:58<7:37:06,  8.52s/it]08/04/2024 15:30:07 - INFO - __main__ -   Step: 2492, LR: 3.1313687103285587e-07, Loss: 0.24013619124889374
2024-08-04T22:30:16.117524691Z 
 44%|████▎     | 2493/5712 [5:52:07<7:43:18,  8.64s/it]08/04/2024 15:30:16 - INFO - __main__ -   Step: 2493, LR: 3.1303959240253897e-07, Loss: 0.12848111987113953
2024-08-04T22:30:24.522113692Z 
 44%|████▎     | 2494/5712 [5:52:15<7:39:26,  8.57s/it]08/04/2024 15:30:24 - INFO - __main__ -   Step: 2494, LR: 3.1294231377222207e-07, Loss: 0.23875200748443604
2024-08-04T22:30:32.747797469Z 
 44%|████▎     | 2495/5712 [5:52:23<7:33:48,  8.46s/it]08/04/2024 15:30:32 - INFO - __main__ -   Step: 2495, LR: 3.1284503514190516e-07, Loss: 0.1544211059808731
2024-08-04T22:30:41.421637669Z 
 44%|████▎     | 2496/5712 [5:52:32<7:37:02,  8.53s/it]08/04/2024 15:30:41 - INFO - __main__ -   Step: 2496, LR: 3.127477565115883e-07, Loss: 0.11476684361696243
2024-08-04T22:30:49.676900826Z 
 44%|████▎     | 2497/5712 [5:52:40<7:32:31,  8.45s/it]08/04/2024 15:30:49 - INFO - __main__ -   Step: 2497, LR: 3.126504778812714e-07, Loss: 0.1667034924030304
2024-08-04T22:30:57.869527630Z 
 44%|████▎     | 2498/5712 [5:52:49<7:28:20,  8.37s/it]08/04/2024 15:30:57 - INFO - __main__ -   Step: 2498, LR: 3.125531992509545e-07, Loss: 0.16061432659626007
2024-08-04T22:31:05.919389442Z 
 44%|████▍     | 2499/5712 [5:52:57<7:23:03,  8.27s/it]08/04/2024 15:31:05 - INFO - __main__ -   Step: 2499, LR: 3.124559206206376e-07, Loss: 0.1466299295425415
2024-08-04T22:31:14.293395529Z 
 44%|████▍     | 2500/5712 [5:53:05<7:24:31,  8.30s/it]08/04/2024 15:31:14 - INFO - __main__ -   Step: 2500, LR: 3.1235864199032077e-07, Loss: 0.10755354911088943
2024-08-04T22:31:23.638887907Z 
 44%|████▍     | 2501/5712 [5:53:14<7:41:06,  8.62s/it]08/04/2024 15:31:23 - INFO - __main__ -   Step: 2501, LR: 3.1226136336000386e-07, Loss: 0.15701928734779358
2024-08-04T22:31:32.210736771Z 
 44%|████▍     | 2502/5712 [5:53:23<7:40:15,  8.60s/it]08/04/2024 15:31:32 - INFO - __main__ -   Step: 2502, LR: 3.1216408472968696e-07, Loss: 0.2163403332233429
2024-08-04T22:31:41.108070687Z 
 44%|████▍     | 2503/5712 [5:53:32<7:44:50,  8.69s/it]08/04/2024 15:31:41 - INFO - __main__ -   Step: 2503, LR: 3.1206680609937006e-07, Loss: 0.11352173984050751
2024-08-04T22:31:49.758063151Z 
 44%|████▍     | 2504/5712 [5:53:40<7:44:01,  8.68s/it]08/04/2024 15:31:49 - INFO - __main__ -   Step: 2504, LR: 3.119695274690532e-07, Loss: 0.18777450919151306
2024-08-04T22:31:58.170769974Z 
 44%|████▍     | 2505/5712 [5:53:49<7:39:36,  8.60s/it]08/04/2024 15:31:58 - INFO - __main__ -   Step: 2505, LR: 3.1187224883873637e-07, Loss: 0.2674807012081146
2024-08-04T22:32:06.902892914Z 
 44%|████▍     | 2506/5712 [5:53:58<7:41:35,  8.64s/it]08/04/2024 15:32:06 - INFO - __main__ -   Step: 2506, LR: 3.1177497020841947e-07, Loss: 0.20334815979003906
2024-08-04T22:32:14.423199801Z 
 44%|████▍     | 2507/5712 [5:54:05<7:23:32,  8.30s/it]08/04/2024 15:32:14 - INFO - __main__ -   Step: 2507, LR: 3.1167769157810256e-07, Loss: 0.2560237646102905
2024-08-04T22:32:22.592564540Z 
 44%|████▍     | 2508/5712 [5:54:13<7:21:15,  8.26s/it]08/04/2024 15:32:22 - INFO - __main__ -   Step: 2508, LR: 3.115804129477857e-07, Loss: 0.17778818309307098
2024-08-04T22:32:31.052551710Z 
 44%|████▍     | 2509/5712 [5:54:22<7:24:16,  8.32s/it]08/04/2024 15:32:31 - INFO - __main__ -   Step: 2509, LR: 3.114831343174688e-07, Loss: 0.28158214688301086
2024-08-04T22:32:39.792319718Z 
 44%|████▍     | 2510/5712 [5:54:30<7:30:47,  8.45s/it]08/04/2024 15:32:39 - INFO - __main__ -   Step: 2510, LR: 3.113858556871519e-07, Loss: 0.22216464579105377
2024-08-04T22:32:48.165048997Z 
 44%|████▍     | 2511/5712 [5:54:39<7:29:29,  8.43s/it]08/04/2024 15:32:48 - INFO - __main__ -   Step: 2511, LR: 3.11288577056835e-07, Loss: 0.19637420773506165
2024-08-04T22:32:56.584986000Z 
 44%|████▍     | 2512/5712 [5:54:47<7:29:15,  8.42s/it]08/04/2024 15:32:56 - INFO - __main__ -   Step: 2512, LR: 3.1119129842651817e-07, Loss: 0.18823954463005066
2024-08-04T22:33:04.744078091Z 
 44%|████▍     | 2513/5712 [5:54:55<7:24:53,  8.34s/it]08/04/2024 15:33:04 - INFO - __main__ -   Step: 2513, LR: 3.1109401979620126e-07, Loss: 0.2486676573753357
2024-08-04T22:33:13.137097844Z 
 44%|████▍     | 2514/5712 [5:55:04<7:25:31,  8.36s/it]08/04/2024 15:33:13 - INFO - __main__ -   Step: 2514, LR: 3.1099674116588436e-07, Loss: 0.21108999848365784
2024-08-04T22:33:21.220324918Z 
 44%|████▍     | 2515/5712 [5:55:12<7:20:58,  8.28s/it]08/04/2024 15:33:21 - INFO - __main__ -   Step: 2515, LR: 3.1089946253556746e-07, Loss: 0.38759803771972656
2024-08-04T22:33:29.524327119Z 
 44%|████▍     | 2516/5712 [5:55:20<7:21:17,  8.28s/it]08/04/2024 15:33:29 - INFO - __main__ -   Step: 2516, LR: 3.108021839052506e-07, Loss: 0.19240181148052216
2024-08-04T22:33:38.144028457Z 
 44%|████▍     | 2517/5712 [5:55:29<7:26:30,  8.39s/it]08/04/2024 15:33:38 - INFO - __main__ -   Step: 2517, LR: 3.107049052749337e-07, Loss: 0.30257707834243774
2024-08-04T22:33:47.234417981Z 
 44%|████▍     | 2518/5712 [5:55:38<7:37:37,  8.60s/it]08/04/2024 15:33:47 - INFO - __main__ -   Step: 2518, LR: 3.106076266446168e-07, Loss: 0.2135753333568573
2024-08-04T22:33:55.478562004Z 
 44%|████▍     | 2519/5712 [5:55:46<7:31:51,  8.49s/it]08/04/2024 15:33:55 - INFO - __main__ -   Step: 2519, LR: 3.105103480142999e-07, Loss: 0.18206021189689636
2024-08-04T22:34:04.587072461Z 
 44%|████▍     | 2520/5712 [5:55:55<7:41:34,  8.68s/it]08/04/2024 15:34:04 - INFO - __main__ -   Step: 2520, LR: 3.1041306938398306e-07, Loss: 0.18381136655807495
2024-08-04T22:34:13.025459923Z 
 44%|████▍     | 2521/5712 [5:56:04<7:37:38,  8.60s/it]08/04/2024 15:34:13 - INFO - __main__ -   Step: 2521, LR: 3.1031579075366616e-07, Loss: 0.16403937339782715
2024-08-04T22:34:21.247970266Z 
 44%|████▍     | 2522/5712 [5:56:12<7:31:23,  8.49s/it]08/04/2024 15:34:21 - INFO - __main__ -   Step: 2522, LR: 3.1021851212334926e-07, Loss: 0.1529630571603775
2024-08-04T22:34:29.753911389Z 
 44%|████▍     | 2523/5712 [5:56:20<7:31:28,  8.49s/it]08/04/2024 15:34:29 - INFO - __main__ -   Step: 2523, LR: 3.101212334930324e-07, Loss: 0.14270281791687012
2024-08-04T22:34:37.817080238Z 
 44%|████▍     | 2524/5712 [5:56:28<7:24:29,  8.37s/it]08/04/2024 15:34:37 - INFO - __main__ -   Step: 2524, LR: 3.1002395486271557e-07, Loss: 0.2121947854757309
2024-08-04T22:34:46.102501479Z 
 44%|████▍     | 2525/5712 [5:56:37<7:23:04,  8.34s/it]08/04/2024 15:34:46 - INFO - __main__ -   Step: 2525, LR: 3.0992667623239867e-07, Loss: 0.15846778452396393
2024-08-04T22:34:54.661455530Z 
 44%|████▍     | 2526/5712 [5:56:45<7:26:23,  8.41s/it]08/04/2024 15:34:54 - INFO - __main__ -   Step: 2526, LR: 3.0982939760208176e-07, Loss: 0.20465491712093353
2024-08-04T22:35:03.179315910Z 
 44%|████▍     | 2527/5712 [5:56:54<7:28:01,  8.44s/it]08/04/2024 15:35:03 - INFO - __main__ -   Step: 2527, LR: 3.0973211897176486e-07, Loss: 0.19357579946517944
2024-08-04T22:35:11.561852815Z 
 44%|████▍     | 2528/5712 [5:57:02<7:26:58,  8.42s/it]08/04/2024 15:35:11 - INFO - __main__ -   Step: 2528, LR: 3.09634840341448e-07, Loss: 0.12612944841384888
2024-08-04T22:35:19.961491549Z 
 44%|████▍     | 2529/5712 [5:57:11<7:26:27,  8.42s/it]08/04/2024 15:35:19 - INFO - __main__ -   Step: 2529, LR: 3.095375617111311e-07, Loss: 0.21559616923332214
2024-08-04T22:35:28.893278538Z 
 44%|████▍     | 2530/5712 [5:57:20<7:34:32,  8.57s/it]08/04/2024 15:35:28 - INFO - __main__ -   Step: 2530, LR: 3.094402830808142e-07, Loss: 0.146846204996109
2024-08-04T22:35:36.977215178Z 
 44%|████▍     | 2531/5712 [5:57:28<7:26:38,  8.42s/it]08/04/2024 15:35:36 - INFO - __main__ -   Step: 2531, LR: 3.093430044504973e-07, Loss: 0.14924553036689758
2024-08-04T22:35:45.752486485Z 
 44%|████▍     | 2532/5712 [5:57:36<7:32:04,  8.53s/it]08/04/2024 15:35:45 - INFO - __main__ -   Step: 2532, LR: 3.092457258201804e-07, Loss: 0.11261548846960068
2024-08-04T22:35:53.901415998Z 
 44%|████▍     | 2533/5712 [5:57:45<7:25:52,  8.42s/it]08/04/2024 15:35:53 - INFO - __main__ -   Step: 2533, LR: 3.0914844718986356e-07, Loss: 0.15736888349056244
2024-08-04T22:36:02.394231156Z 
 44%|████▍     | 2534/5712 [5:57:53<7:26:58,  8.44s/it]08/04/2024 15:36:02 - INFO - __main__ -   Step: 2534, LR: 3.0905116855954666e-07, Loss: 0.17337936162948608
2024-08-04T22:36:10.957605034Z 
 44%|████▍     | 2535/5712 [5:58:02<7:28:48,  8.48s/it]08/04/2024 15:36:10 - INFO - __main__ -   Step: 2535, LR: 3.0895388992922976e-07, Loss: 0.1421298384666443
2024-08-04T22:36:19.707863507Z 
 44%|████▍     | 2536/5712 [5:58:10<7:33:00,  8.56s/it]08/04/2024 15:36:19 - INFO - __main__ -   Step: 2536, LR: 3.0885661129891286e-07, Loss: 0.16711542010307312
2024-08-04T22:36:28.862860880Z 
 44%|████▍     | 2537/5712 [5:58:20<7:42:21,  8.74s/it]08/04/2024 15:36:28 - INFO - __main__ -   Step: 2537, LR: 3.08759332668596e-07, Loss: 0.1201280802488327
2024-08-04T22:36:36.944388985Z 
 44%|████▍     | 2538/5712 [5:58:28<7:31:48,  8.54s/it]08/04/2024 15:36:36 - INFO - __main__ -   Step: 2538, LR: 3.086620540382791e-07, Loss: 0.16653241217136383
2024-08-04T22:36:45.220639906Z 
 44%|████▍     | 2539/5712 [5:58:36<7:27:27,  8.46s/it]08/04/2024 15:36:45 - INFO - __main__ -   Step: 2539, LR: 3.085647754079622e-07, Loss: 0.2145105004310608
2024-08-04T22:36:53.893710962Z 
 44%|████▍     | 2540/5712 [5:58:45<7:30:39,  8.52s/it]08/04/2024 15:36:53 - INFO - __main__ -   Step: 2540, LR: 3.084674967776453e-07, Loss: 0.16827920079231262
2024-08-04T22:37:02.333405406Z 
 44%|████▍     | 2541/5712 [5:58:53<7:29:11,  8.50s/it]08/04/2024 15:37:02 - INFO - __main__ -   Step: 2541, LR: 3.083702181473285e-07, Loss: 0.3111814260482788
2024-08-04T22:37:11.012020568Z 
 45%|████▍     | 2542/5712 [5:59:02<7:31:53,  8.55s/it]08/04/2024 15:37:11 - INFO - __main__ -   Step: 2542, LR: 3.082729395170116e-07, Loss: 0.2486644983291626
2024-08-04T22:37:19.983697703Z 
 45%|████▍     | 2543/5712 [5:59:11<7:38:22,  8.68s/it]08/04/2024 15:37:19 - INFO - __main__ -   Step: 2543, LR: 3.081756608866947e-07, Loss: 0.15735356509685516
2024-08-04T22:37:28.427430955Z 
 45%|████▍     | 2544/5712 [5:59:19<7:34:31,  8.61s/it]08/04/2024 15:37:28 - INFO - __main__ -   Step: 2544, LR: 3.080783822563778e-07, Loss: 0.10061638057231903
2024-08-04T22:37:37.355900999Z 
 45%|████▍     | 2545/5712 [5:59:28<7:39:26,  8.70s/it]08/04/2024 15:37:37 - INFO - __main__ -   Step: 2545, LR: 3.0798110362606096e-07, Loss: 0.2140914797782898
2024-08-04T22:37:45.517601074Z 
 45%|████▍     | 2546/5712 [5:59:36<7:30:42,  8.54s/it]08/04/2024 15:37:45 - INFO - __main__ -   Step: 2546, LR: 3.0788382499574406e-07, Loss: 0.23092347383499146
2024-08-04T22:37:53.956000458Z 
 45%|████▍     | 2547/5712 [5:59:45<7:28:56,  8.51s/it]08/04/2024 15:37:53 - INFO - __main__ -   Step: 2547, LR: 3.0778654636542716e-07, Loss: 0.203178271651268
2024-08-04T22:38:02.094598243Z 
 45%|████▍     | 2548/5712 [5:59:53<7:22:54,  8.40s/it]08/04/2024 15:38:02 - INFO - __main__ -   Step: 2548, LR: 3.0768926773511026e-07, Loss: 0.13728070259094238
2024-08-04T22:38:10.498496456Z 
 45%|████▍     | 2549/5712 [6:00:01<7:22:50,  8.40s/it]08/04/2024 15:38:10 - INFO - __main__ -   Step: 2549, LR: 3.075919891047934e-07, Loss: 0.15872713923454285
2024-08-04T22:38:19.646273796Z 
 45%|████▍     | 2550/5712 [6:00:10<7:34:30,  8.62s/it]08/04/2024 15:38:19 - INFO - __main__ -   Step: 2550, LR: 3.074947104744765e-07, Loss: 0.24797183275222778
2024-08-04T22:38:27.829923564Z 
 45%|████▍     | 2551/5712 [6:00:18<7:27:24,  8.49s/it]08/04/2024 15:38:27 - INFO - __main__ -   Step: 2551, LR: 3.073974318441596e-07, Loss: 0.21261397004127502
2024-08-04T22:38:36.156484508Z 
 45%|████▍     | 2552/5712 [6:00:27<7:24:38,  8.44s/it]08/04/2024 15:38:36 - INFO - __main__ -   Step: 2552, LR: 3.073001532138427e-07, Loss: 0.16525745391845703
2024-08-04T22:38:44.578317857Z 
 45%|████▍     | 2553/5712 [6:00:35<7:24:10,  8.44s/it]08/04/2024 15:38:44 - INFO - __main__ -   Step: 2553, LR: 3.0720287458352586e-07, Loss: 0.2224268615245819
2024-08-04T22:38:53.458366009Z 
 45%|████▍     | 2554/5712 [6:00:44<7:31:02,  8.57s/it]08/04/2024 15:38:53 - INFO - __main__ -   Step: 2554, LR: 3.0710559595320896e-07, Loss: 0.2803317904472351
2024-08-04T22:39:02.115112376Z 
 45%|████▍     | 2555/5712 [6:00:53<7:32:16,  8.60s/it]08/04/2024 15:39:02 - INFO - __main__ -   Step: 2555, LR: 3.0700831732289206e-07, Loss: 0.1519569307565689
2024-08-04T22:39:10.178531618Z 
 45%|████▍     | 2556/5712 [6:01:01<7:23:44,  8.44s/it]08/04/2024 15:39:10 - INFO - __main__ -   Step: 2556, LR: 3.0691103869257516e-07, Loss: 0.13943248987197876
2024-08-04T22:39:19.095851399Z 
 45%|████▍     | 2557/5712 [6:01:10<7:31:10,  8.58s/it]08/04/2024 15:39:19 - INFO - __main__ -   Step: 2557, LR: 3.068137600622583e-07, Loss: 0.18950004875659943
2024-08-04T22:39:27.542995134Z 
 45%|████▍     | 2558/5712 [6:01:18<7:28:56,  8.54s/it]08/04/2024 15:39:27 - INFO - __main__ -   Step: 2558, LR: 3.067164814319414e-07, Loss: 0.23275180160999298
2024-08-04T22:39:36.688950467Z 
 45%|████▍     | 2559/5712 [6:01:27<7:38:20,  8.72s/it]08/04/2024 15:39:36 - INFO - __main__ -   Step: 2559, LR: 3.0661920280162456e-07, Loss: 0.15866237878799438
2024-08-04T22:39:45.239328149Z 
 45%|████▍     | 2560/5712 [6:01:36<7:35:29,  8.67s/it]08/04/2024 15:39:45 - INFO - __main__ -   Step: 2560, LR: 3.0652192417130766e-07, Loss: 0.1650824248790741
2024-08-04T22:39:53.554578455Z 
 45%|████▍     | 2561/5712 [6:01:44<7:29:45,  8.56s/it]08/04/2024 15:39:53 - INFO - __main__ -   Step: 2561, LR: 3.064246455409908e-07, Loss: 0.1157156229019165
2024-08-04T22:40:02.855026952Z 
 45%|████▍     | 2562/5712 [6:01:54<7:41:12,  8.79s/it]08/04/2024 15:40:02 - INFO - __main__ -   Step: 2562, LR: 3.063273669106739e-07, Loss: 0.08818168938159943
2024-08-04T22:40:11.852226601Z 
 45%|████▍     | 2563/5712 [6:02:02<7:44:24,  8.85s/it]08/04/2024 15:40:11 - INFO - __main__ -   Step: 2563, LR: 3.06230088280357e-07, Loss: 0.1944017857313156
2024-08-04T22:40:20.038325085Z 
 45%|████▍     | 2564/5712 [6:02:11<7:33:49,  8.65s/it]08/04/2024 15:40:20 - INFO - __main__ -   Step: 2564, LR: 3.061328096500401e-07, Loss: 0.1867198944091797
2024-08-04T22:40:28.617868875Z 
 45%|████▍     | 2565/5712 [6:02:19<7:32:34,  8.63s/it]08/04/2024 15:40:28 - INFO - __main__ -   Step: 2565, LR: 3.0603553101972326e-07, Loss: 0.16265085339546204
2024-08-04T22:40:36.901032773Z 
 45%|████▍     | 2566/5712 [6:02:28<7:27:00,  8.53s/it]08/04/2024 15:40:36 - INFO - __main__ -   Step: 2566, LR: 3.0593825238940636e-07, Loss: 0.18686825037002563
2024-08-04T22:40:45.278830479Z 
 45%|████▍     | 2567/5712 [6:02:36<7:24:32,  8.48s/it]08/04/2024 15:40:45 - INFO - __main__ -   Step: 2567, LR: 3.0584097375908946e-07, Loss: 0.12234267592430115
2024-08-04T22:40:53.715390200Z 
 45%|████▍     | 2568/5712 [6:02:44<7:23:42,  8.47s/it]08/04/2024 15:40:53 - INFO - __main__ -   Step: 2568, LR: 3.0574369512877256e-07, Loss: 0.16775935888290405
2024-08-04T22:41:02.386641054Z 
 45%|████▍     | 2569/5712 [6:02:53<7:26:45,  8.53s/it]08/04/2024 15:41:02 - INFO - __main__ -   Step: 2569, LR: 3.0564641649845566e-07, Loss: 0.1725935935974121
2024-08-04T22:41:10.738226100Z 
 45%|████▍     | 2570/5712 [6:03:01<7:23:50,  8.48s/it]08/04/2024 15:41:10 - INFO - __main__ -   Step: 2570, LR: 3.055491378681388e-07, Loss: 0.083103708922863
2024-08-04T22:41:19.302295617Z 
 45%|████▌     | 2571/5712 [6:03:10<7:25:05,  8.50s/it]08/04/2024 15:41:19 - INFO - __main__ -   Step: 2571, LR: 3.054518592378219e-07, Loss: 0.20052532851696014
2024-08-04T22:41:27.920635691Z 
 45%|████▌     | 2572/5712 [6:03:19<7:26:46,  8.54s/it]08/04/2024 15:41:27 - INFO - __main__ -   Step: 2572, LR: 3.05354580607505e-07, Loss: 0.11297633498907089
2024-08-04T22:41:36.071650935Z 
 45%|████▌     | 2573/5712 [6:03:27<7:20:33,  8.42s/it]08/04/2024 15:41:36 - INFO - __main__ -   Step: 2573, LR: 3.052573019771881e-07, Loss: 0.1340388059616089
2024-08-04T22:41:45.005696970Z 
 45%|████▌     | 2574/5712 [6:03:36<7:28:28,  8.57s/it]08/04/2024 15:41:45 - INFO - __main__ -   Step: 2574, LR: 3.0516002334687126e-07, Loss: 0.08440946787595749
2024-08-04T22:41:53.891896451Z 
 45%|████▌     | 2575/5712 [6:03:45<7:33:13,  8.67s/it]08/04/2024 15:41:53 - INFO - __main__ -   Step: 2575, LR: 3.0506274471655436e-07, Loss: 0.2766702175140381
2024-08-04T22:42:02.110220311Z 
 45%|████▌     | 2576/5712 [6:03:53<7:26:00,  8.53s/it]08/04/2024 15:42:02 - INFO - __main__ -   Step: 2576, LR: 3.0496546608623746e-07, Loss: 0.22115132212638855
2024-08-04T22:42:10.293703752Z 
 45%|████▌     | 2577/5712 [6:04:01<7:20:23,  8.43s/it]08/04/2024 15:42:10 - INFO - __main__ -   Step: 2577, LR: 3.048681874559206e-07, Loss: 0.1380932480096817
2024-08-04T22:42:18.345460359Z 
 45%|████▌     | 2578/5712 [6:04:09<7:14:20,  8.32s/it]08/04/2024 15:42:18 - INFO - __main__ -   Step: 2578, LR: 3.0477090882560376e-07, Loss: 0.21406595408916473
2024-08-04T22:42:27.125536034Z 
 45%|████▌     | 2579/5712 [6:04:18<7:21:29,  8.45s/it]08/04/2024 15:42:27 - INFO - __main__ -   Step: 2579, LR: 3.0467363019528686e-07, Loss: 0.18006004393100739
2024-08-04T22:42:35.473363879Z 
 45%|████▌     | 2580/5712 [6:04:26<7:19:39,  8.42s/it]08/04/2024 15:42:35 - INFO - __main__ -   Step: 2580, LR: 3.0457635156496996e-07, Loss: 0.15412306785583496
2024-08-04T22:42:44.046357634Z 
 45%|████▌     | 2581/5712 [6:04:35<7:21:52,  8.47s/it]08/04/2024 15:42:44 - INFO - __main__ -   Step: 2581, LR: 3.0447907293465306e-07, Loss: 0.14438579976558685
2024-08-04T22:42:52.669322603Z 
 45%|████▌     | 2582/5712 [6:04:43<7:24:10,  8.51s/it]08/04/2024 15:42:52 - INFO - __main__ -   Step: 2582, LR: 3.043817943043362e-07, Loss: 0.1526774764060974
2024-08-04T22:43:00.891638816Z 
 45%|████▌     | 2583/5712 [6:04:52<7:19:26,  8.43s/it]08/04/2024 15:43:00 - INFO - __main__ -   Step: 2583, LR: 3.042845156740193e-07, Loss: 0.24093014001846313
2024-08-04T22:43:09.286278473Z 
 45%|████▌     | 2584/5712 [6:05:00<7:18:48,  8.42s/it]08/04/2024 15:43:09 - INFO - __main__ -   Step: 2584, LR: 3.041872370437024e-07, Loss: 0.17282366752624512
2024-08-04T22:43:18.304704013Z 
 45%|████▌     | 2585/5712 [6:05:09<7:28:04,  8.60s/it]08/04/2024 15:43:18 - INFO - __main__ -   Step: 2585, LR: 3.040899584133855e-07, Loss: 0.06462790817022324
2024-08-04T22:43:26.696781563Z 
 45%|████▌     | 2586/5712 [6:05:17<7:24:43,  8.54s/it]08/04/2024 15:43:26 - INFO - __main__ -   Step: 2586, LR: 3.0399267978306866e-07, Loss: 0.21834540367126465
2024-08-04T22:43:35.648437463Z 
 45%|████▌     | 2587/5712 [6:05:26<7:31:04,  8.66s/it]08/04/2024 15:43:35 - INFO - __main__ -   Step: 2587, LR: 3.0389540115275176e-07, Loss: 0.17389659583568573
2024-08-04T22:43:43.932056928Z 
 45%|████▌     | 2588/5712 [6:05:35<7:25:02,  8.55s/it]08/04/2024 15:43:43 - INFO - __main__ -   Step: 2588, LR: 3.0379812252243486e-07, Loss: 0.24021756649017334
2024-08-04T22:43:52.003087799Z 
 45%|████▌     | 2589/5712 [6:05:43<7:17:27,  8.40s/it]08/04/2024 15:43:52 - INFO - __main__ -   Step: 2589, LR: 3.0370084389211796e-07, Loss: 0.17086908221244812
2024-08-04T22:44:00.867793601Z 
 45%|████▌     | 2590/5712 [6:05:52<7:24:29,  8.54s/it]08/04/2024 15:44:00 - INFO - __main__ -   Step: 2590, LR: 3.036035652618011e-07, Loss: 0.2234041690826416
2024-08-04T22:44:09.613439963Z 
 45%|████▌     | 2591/5712 [6:06:00<7:27:31,  8.60s/it]08/04/2024 15:44:09 - INFO - __main__ -   Step: 2591, LR: 3.035062866314842e-07, Loss: 0.18863099813461304
2024-08-04T22:44:17.891165478Z 
 45%|████▌     | 2592/5712 [6:06:09<7:22:17,  8.51s/it]08/04/2024 15:44:17 - INFO - __main__ -   Step: 2592, LR: 3.034090080011673e-07, Loss: 0.1413162648677826
2024-08-04T22:44:26.749463310Z 
 45%|████▌     | 2593/5712 [6:06:17<7:27:39,  8.61s/it]08/04/2024 15:44:26 - INFO - __main__ -   Step: 2593, LR: 3.033117293708504e-07, Loss: 0.2931935489177704
2024-08-04T22:44:35.505365644Z 
 45%|████▌     | 2594/5712 [6:06:26<7:29:45,  8.65s/it]08/04/2024 15:44:35 - INFO - __main__ -   Step: 2594, LR: 3.0321445074053356e-07, Loss: 0.21660655736923218
2024-08-04T22:44:43.795031510Z 
 45%|████▌     | 2595/5712 [6:06:34<7:23:55,  8.55s/it]08/04/2024 15:44:43 - INFO - __main__ -   Step: 2595, LR: 3.031171721102167e-07, Loss: 0.12645483016967773
2024-08-04T22:44:52.635185572Z 
 45%|████▌     | 2596/5712 [6:06:43<7:28:22,  8.63s/it]08/04/2024 15:44:52 - INFO - __main__ -   Step: 2596, LR: 3.030198934798998e-07, Loss: 0.22828684747219086
2024-08-04T22:45:00.681888200Z 
 45%|████▌     | 2597/5712 [6:06:51<7:19:05,  8.46s/it]08/04/2024 15:45:00 - INFO - __main__ -   Step: 2597, LR: 3.029226148495829e-07, Loss: 0.19846844673156738
2024-08-04T22:45:09.246511351Z 
 45%|████▌     | 2598/5712 [6:07:00<7:20:36,  8.49s/it]08/04/2024 15:45:09 - INFO - __main__ -   Step: 2598, LR: 3.0282533621926606e-07, Loss: 0.17290976643562317
2024-08-04T22:45:18.479807682Z 
 46%|████▌     | 2599/5712 [6:07:09<7:32:03,  8.71s/it]08/04/2024 15:45:18 - INFO - __main__ -   Step: 2599, LR: 3.0272805758894916e-07, Loss: 0.13107909262180328
2024-08-04T22:45:26.762868219Z 
 46%|████▌     | 2600/5712 [6:07:17<7:25:13,  8.58s/it]08/04/2024 15:45:26 - INFO - __main__ -   Step: 2600, LR: 3.0263077895863226e-07, Loss: 0.32751911878585815
2024-08-04T22:45:34.983050758Z 
 46%|████▌     | 2601/5712 [6:07:26<7:19:25,  8.47s/it]08/04/2024 15:45:34 - INFO - __main__ -   Step: 2601, LR: 3.0253350032831536e-07, Loss: 0.11182647943496704
2024-08-04T22:45:43.807348593Z 
 46%|████▌     | 2602/5712 [6:07:34<7:24:42,  8.58s/it]08/04/2024 15:45:43 - INFO - __main__ -   Step: 2602, LR: 3.024362216979985e-07, Loss: 0.170063316822052
2024-08-04T22:45:52.307452756Z 
 46%|████▌     | 2603/5712 [6:07:43<7:23:19,  8.56s/it]08/04/2024 15:45:52 - INFO - __main__ -   Step: 2603, LR: 3.023389430676816e-07, Loss: 0.13197456300258636
2024-08-04T22:46:01.303667416Z 
 46%|████▌     | 2604/5712 [6:07:52<7:30:01,  8.69s/it]08/04/2024 15:46:01 - INFO - __main__ -   Step: 2604, LR: 3.022416644373647e-07, Loss: 0.16777995228767395
2024-08-04T22:46:09.721254101Z 
 46%|████▌     | 2605/5712 [6:08:00<7:25:41,  8.61s/it]08/04/2024 15:46:09 - INFO - __main__ -   Step: 2605, LR: 3.021443858070478e-07, Loss: 0.17209398746490479
2024-08-04T22:46:17.886431779Z 
 46%|████▌     | 2606/5712 [6:08:09<7:18:41,  8.47s/it]08/04/2024 15:46:17 - INFO - __main__ -   Step: 2606, LR: 3.020471071767309e-07, Loss: 0.2413630485534668
2024-08-04T22:46:26.347715899Z 
 46%|████▌     | 2607/5712 [6:08:17<7:18:20,  8.47s/it]08/04/2024 15:46:26 - INFO - __main__ -   Step: 2607, LR: 3.0194982854641406e-07, Loss: 0.2298537790775299
2024-08-04T22:46:34.905528473Z 
 46%|████▌     | 2608/5712 [6:08:26<7:19:33,  8.50s/it]08/04/2024 15:46:34 - INFO - __main__ -   Step: 2608, LR: 3.0185254991609716e-07, Loss: 0.1355695128440857
2024-08-04T22:46:43.054357696Z 
 46%|████▌     | 2609/5712 [6:08:34<7:14:01,  8.39s/it]08/04/2024 15:46:43 - INFO - __main__ -   Step: 2609, LR: 3.0175527128578026e-07, Loss: 0.2594345211982727
2024-08-04T22:46:51.901471510Z 
 46%|████▌     | 2610/5712 [6:08:43<7:20:56,  8.53s/it]08/04/2024 15:46:51 - INFO - __main__ -   Step: 2610, LR: 3.0165799265546335e-07, Loss: 0.2414827048778534
2024-08-04T22:47:00.354859529Z 
 46%|████▌     | 2611/5712 [6:08:51<7:19:37,  8.51s/it]08/04/2024 15:47:00 - INFO - __main__ -   Step: 2611, LR: 3.015607140251465e-07, Loss: 0.18356597423553467
2024-08-04T22:47:08.918417747Z 
 46%|████▌     | 2612/5712 [6:09:00<7:20:22,  8.52s/it]08/04/2024 15:47:08 - INFO - __main__ -   Step: 2612, LR: 3.014634353948296e-07, Loss: 0.21031145751476288
2024-08-04T22:47:17.708093120Z 
 46%|████▌     | 2613/5712 [6:09:08<7:24:21,  8.60s/it]08/04/2024 15:47:17 - INFO - __main__ -   Step: 2613, LR: 3.0136615676451276e-07, Loss: 0.2253779172897339
2024-08-04T22:47:26.328615993Z 
 46%|████▌     | 2614/5712 [6:09:17<7:24:28,  8.61s/it]08/04/2024 15:47:26 - INFO - __main__ -   Step: 2614, LR: 3.0126887813419586e-07, Loss: 0.1228683590888977
2024-08-04T22:47:34.542064980Z 
 46%|████▌     | 2615/5712 [6:09:25<7:18:13,  8.49s/it]08/04/2024 15:47:34 - INFO - __main__ -   Step: 2615, LR: 3.01171599503879e-07, Loss: 0.1824270784854889
2024-08-04T22:47:43.376079891Z 
 46%|████▌     | 2616/5712 [6:09:34<7:23:24,  8.59s/it]08/04/2024 15:47:43 - INFO - __main__ -   Step: 2616, LR: 3.010743208735621e-07, Loss: 0.2968563735485077
2024-08-04T22:47:51.327270734Z 
 46%|████▌     | 2617/5712 [6:09:42<7:13:19,  8.40s/it]08/04/2024 15:47:51 - INFO - __main__ -   Step: 2617, LR: 3.009770422432452e-07, Loss: 0.22892874479293823
2024-08-04T22:47:59.533218820Z 
 46%|████▌     | 2618/5712 [6:09:50<7:10:10,  8.34s/it]08/04/2024 15:47:59 - INFO - __main__ -   Step: 2618, LR: 3.008797636129283e-07, Loss: 0.18016298115253448
2024-08-04T22:48:08.063574771Z 
 46%|████▌     | 2619/5712 [6:09:59<7:12:56,  8.40s/it]08/04/2024 15:48:08 - INFO - __main__ -   Step: 2619, LR: 3.0078248498261146e-07, Loss: 0.17442336678504944
2024-08-04T22:48:16.563966075Z 
 46%|████▌     | 2620/5712 [6:10:07<7:14:23,  8.43s/it]08/04/2024 15:48:16 - INFO - __main__ -   Step: 2620, LR: 3.0068520635229456e-07, Loss: 0.1196303591132164
2024-08-04T22:48:24.772260744Z 
 46%|████▌     | 2621/5712 [6:10:15<7:10:49,  8.36s/it]08/04/2024 15:48:24 - INFO - __main__ -   Step: 2621, LR: 3.0058792772197766e-07, Loss: 0.1255512833595276
2024-08-04T22:48:33.584780716Z 
 46%|████▌     | 2622/5712 [6:10:24<7:17:38,  8.50s/it]08/04/2024 15:48:33 - INFO - __main__ -   Step: 2622, LR: 3.0049064909166076e-07, Loss: 0.1800166666507721
2024-08-04T22:48:41.584376069Z 
 46%|████▌     | 2623/5712 [6:10:32<7:09:48,  8.35s/it]08/04/2024 15:48:41 - INFO - __main__ -   Step: 2623, LR: 3.003933704613439e-07, Loss: 0.1735241711139679
2024-08-04T22:48:50.639758306Z 
 46%|████▌     | 2624/5712 [6:10:41<7:20:34,  8.56s/it]08/04/2024 15:48:50 - INFO - __main__ -   Step: 2624, LR: 3.00296091831027e-07, Loss: 0.13051031529903412
2024-08-04T22:48:58.610076064Z 
 46%|████▌     | 2625/5712 [6:10:49<7:11:19,  8.38s/it]08/04/2024 15:48:58 - INFO - __main__ -   Step: 2625, LR: 3.001988132007101e-07, Loss: 0.18540702760219574
2024-08-04T22:49:07.062695673Z 
 46%|████▌     | 2626/5712 [6:10:58<7:12:15,  8.40s/it]08/04/2024 15:49:07 - INFO - __main__ -   Step: 2626, LR: 3.001015345703932e-07, Loss: 0.2142953872680664
2024-08-04T22:49:15.905271119Z 
 46%|████▌     | 2627/5712 [6:11:07<7:18:52,  8.54s/it]08/04/2024 15:49:15 - INFO - __main__ -   Step: 2627, LR: 3.0000425594007636e-07, Loss: 0.09908340126276016
2024-08-04T22:49:25.197963736Z 
 46%|████▌     | 2628/5712 [6:11:16<7:30:24,  8.76s/it]08/04/2024 15:49:25 - INFO - __main__ -   Step: 2628, LR: 2.9990697730975946e-07, Loss: 0.22645792365074158
2024-08-04T22:49:33.593880761Z 
 46%|████▌     | 2629/5712 [6:11:24<7:24:36,  8.65s/it]08/04/2024 15:49:33 - INFO - __main__ -   Step: 2629, LR: 2.9980969867944255e-07, Loss: 0.12713992595672607
2024-08-04T22:49:42.392569011Z 
 46%|████▌     | 2630/5712 [6:11:33<7:26:42,  8.70s/it]08/04/2024 15:49:42 - INFO - __main__ -   Step: 2630, LR: 2.9971242004912565e-07, Loss: 0.15245673060417175
2024-08-04T22:49:50.441819678Z 
 46%|████▌     | 2631/5712 [6:11:41<7:16:35,  8.50s/it]08/04/2024 15:49:50 - INFO - __main__ -   Step: 2631, LR: 2.9961514141880886e-07, Loss: 0.1569233536720276
2024-08-04T22:49:58.938004283Z 
 46%|████▌     | 2632/5712 [6:11:50<7:16:21,  8.50s/it]08/04/2024 15:49:58 - INFO - __main__ -   Step: 2632, LR: 2.9951786278849196e-07, Loss: 0.1978081315755844
2024-08-04T22:50:07.873815942Z 
 46%|████▌     | 2633/5712 [6:11:59<7:22:55,  8.63s/it]08/04/2024 15:50:07 - INFO - __main__ -   Step: 2633, LR: 2.9942058415817506e-07, Loss: 0.18413807451725006
2024-08-04T22:50:16.055889849Z 
 46%|████▌     | 2634/5712 [6:12:07<7:15:51,  8.50s/it]08/04/2024 15:50:16 - INFO - __main__ -   Step: 2634, LR: 2.9932330552785816e-07, Loss: 0.1863047480583191
2024-08-04T22:50:24.238664317Z 
 46%|████▌     | 2635/5712 [6:12:15<7:10:53,  8.40s/it]08/04/2024 15:50:24 - INFO - __main__ -   Step: 2635, LR: 2.992260268975413e-07, Loss: 0.2896589934825897
2024-08-04T22:50:33.217102637Z 
 46%|████▌     | 2636/5712 [6:12:24<7:19:36,  8.58s/it]08/04/2024 15:50:33 - INFO - __main__ -   Step: 2636, LR: 2.991287482672244e-07, Loss: 0.22949059307575226
2024-08-04T22:50:41.321426234Z 
 46%|████▌     | 2637/5712 [6:12:32<7:12:13,  8.43s/it]08/04/2024 15:50:41 - INFO - __main__ -   Step: 2637, LR: 2.990314696369075e-07, Loss: 0.31120848655700684
2024-08-04T22:50:49.635432474Z 
 46%|████▌     | 2638/5712 [6:12:40<7:10:15,  8.40s/it]08/04/2024 15:50:49 - INFO - __main__ -   Step: 2638, LR: 2.989341910065906e-07, Loss: 0.15099966526031494
2024-08-04T22:50:58.359999782Z 
 46%|████▌     | 2639/5712 [6:12:49<7:15:07,  8.50s/it]08/04/2024 15:50:58 - INFO - __main__ -   Step: 2639, LR: 2.9883691237627376e-07, Loss: 0.20423680543899536
2024-08-04T22:51:07.070585376Z 
 46%|████▌     | 2640/5712 [6:12:58<7:18:17,  8.56s/it]08/04/2024 15:51:07 - INFO - __main__ -   Step: 2640, LR: 2.9873963374595686e-07, Loss: 0.23808158934116364
2024-08-04T22:51:16.017314594Z 
 46%|████▌     | 2641/5712 [6:13:07<7:24:04,  8.68s/it]08/04/2024 15:51:16 - INFO - __main__ -   Step: 2641, LR: 2.9864235511563995e-07, Loss: 0.16121716797351837
2024-08-04T22:51:24.019550333Z 
 46%|████▋     | 2642/5712 [6:13:15<7:13:35,  8.47s/it]08/04/2024 15:51:24 - INFO - __main__ -   Step: 2642, LR: 2.9854507648532305e-07, Loss: 0.2730814218521118
2024-08-04T22:51:32.887074081Z 
 46%|████▋     | 2643/5712 [6:13:24<7:19:29,  8.59s/it]08/04/2024 15:51:32 - INFO - __main__ -   Step: 2643, LR: 2.9844779785500615e-07, Loss: 0.08809366822242737
2024-08-04T22:51:41.605513440Z 
 46%|████▋     | 2644/5712 [6:13:32<7:21:16,  8.63s/it]08/04/2024 15:51:41 - INFO - __main__ -   Step: 2644, LR: 2.983505192246893e-07, Loss: 0.11302974820137024
2024-08-04T22:51:50.156636808Z 
 46%|████▋     | 2645/5712 [6:13:41<7:19:55,  8.61s/it]08/04/2024 15:51:50 - INFO - __main__ -   Step: 2645, LR: 2.982532405943724e-07, Loss: 0.2789875864982605
2024-08-04T22:51:58.367411682Z 
 46%|████▋     | 2646/5712 [6:13:49<7:13:43,  8.49s/it]08/04/2024 15:51:58 - INFO - __main__ -   Step: 2646, LR: 2.981559619640555e-07, Loss: 0.18562299013137817
2024-08-04T22:52:07.321635142Z 
 46%|████▋     | 2647/5712 [6:13:58<7:20:43,  8.63s/it]08/04/2024 15:52:07 - INFO - __main__ -   Step: 2647, LR: 2.980586833337386e-07, Loss: 0.10383178293704987
2024-08-04T22:52:16.604514441Z 
 46%|████▋     | 2648/5712 [6:14:07<7:30:37,  8.82s/it]08/04/2024 15:52:16 - INFO - __main__ -   Step: 2648, LR: 2.9796140470342175e-07, Loss: 0.12601713836193085
2024-08-04T22:52:25.271920169Z 
 46%|████▋     | 2649/5712 [6:14:16<7:28:04,  8.78s/it]08/04/2024 15:52:25 - INFO - __main__ -   Step: 2649, LR: 2.978641260731049e-07, Loss: 0.19990813732147217
2024-08-04T22:52:33.508450101Z 
 46%|████▋     | 2650/5712 [6:14:24<7:19:39,  8.61s/it]08/04/2024 15:52:33 - INFO - __main__ -   Step: 2650, LR: 2.97766847442788e-07, Loss: 0.26612135767936707
2024-08-04T22:52:41.705934119Z 
 46%|████▋     | 2651/5712 [6:14:32<7:13:07,  8.49s/it]08/04/2024 15:52:41 - INFO - __main__ -   Step: 2651, LR: 2.976695688124711e-07, Loss: 0.25949543714523315
2024-08-04T22:52:49.974004394Z 
 46%|████▋     | 2652/5712 [6:14:41<7:09:34,  8.42s/it]08/04/2024 15:52:49 - INFO - __main__ -   Step: 2652, LR: 2.9757229018215426e-07, Loss: 0.16559752821922302
2024-08-04T22:52:58.609117495Z 
 46%|████▋     | 2653/5712 [6:14:49<7:12:41,  8.49s/it]08/04/2024 15:52:58 - INFO - __main__ -   Step: 2653, LR: 2.9747501155183735e-07, Loss: 0.0655180960893631
2024-08-04T22:53:06.869513911Z 
 46%|████▋     | 2654/5712 [6:14:58<7:09:05,  8.42s/it]08/04/2024 15:53:06 - INFO - __main__ -   Step: 2654, LR: 2.9737773292152045e-07, Loss: 0.10191697627305984
2024-08-04T22:53:15.050713593Z 
 46%|████▋     | 2655/5712 [6:15:06<7:05:18,  8.35s/it]08/04/2024 15:53:15 - INFO - __main__ -   Step: 2655, LR: 2.9728045429120355e-07, Loss: 0.25204384326934814
2024-08-04T22:53:23.284838184Z 
 46%|████▋     | 2656/5712 [6:15:14<7:03:26,  8.31s/it]08/04/2024 15:53:23 - INFO - __main__ -   Step: 2656, LR: 2.971831756608867e-07, Loss: 0.13552865386009216
2024-08-04T22:53:32.094518488Z 
 47%|████▋     | 2657/5712 [6:15:23<7:10:52,  8.46s/it]08/04/2024 15:53:32 - INFO - __main__ -   Step: 2657, LR: 2.970858970305698e-07, Loss: 0.23636317253112793
2024-08-04T22:53:40.525472726Z 
 47%|████▋     | 2658/5712 [6:15:31<7:10:15,  8.45s/it]08/04/2024 15:53:40 - INFO - __main__ -   Step: 2658, LR: 2.969886184002529e-07, Loss: 0.19757676124572754
2024-08-04T22:53:48.533806260Z 
 47%|████▋     | 2659/5712 [6:15:39<7:03:19,  8.32s/it]08/04/2024 15:53:48 - INFO - __main__ -   Step: 2659, LR: 2.96891339769936e-07, Loss: 0.18283192813396454
2024-08-04T22:53:57.076248290Z 
 47%|████▋     | 2660/5712 [6:15:48<7:06:35,  8.39s/it]08/04/2024 15:53:57 - INFO - __main__ -   Step: 2660, LR: 2.9679406113961915e-07, Loss: 0.26734963059425354
2024-08-04T22:54:06.277901675Z 
 47%|████▋     | 2661/5712 [6:15:57<7:18:53,  8.63s/it]08/04/2024 15:54:06 - INFO - __main__ -   Step: 2661, LR: 2.9669678250930225e-07, Loss: 0.15234160423278809
2024-08-04T22:54:14.407876151Z 
 47%|████▋     | 2662/5712 [6:16:05<7:11:06,  8.48s/it]08/04/2024 15:54:14 - INFO - __main__ -   Step: 2662, LR: 2.9659950387898535e-07, Loss: 0.142168790102005
2024-08-04T22:54:22.400687508Z 
 47%|████▋     | 2663/5712 [6:16:13<7:03:31,  8.33s/it]08/04/2024 15:54:22 - INFO - __main__ -   Step: 2663, LR: 2.9650222524866845e-07, Loss: 0.20058700442314148
2024-08-04T22:54:31.055133476Z 
 47%|████▋     | 2664/5712 [6:16:22<7:08:15,  8.43s/it]08/04/2024 15:54:31 - INFO - __main__ -   Step: 2664, LR: 2.964049466183516e-07, Loss: 0.14013275504112244
2024-08-04T22:54:39.922277381Z 
 47%|████▋     | 2665/5712 [6:16:31<7:14:46,  8.56s/it]08/04/2024 15:54:39 - INFO - __main__ -   Step: 2665, LR: 2.963076679880347e-07, Loss: 0.22969093918800354
2024-08-04T22:54:48.594733598Z 
 47%|████▋     | 2666/5712 [6:16:39<7:16:19,  8.59s/it]08/04/2024 15:54:48 - INFO - __main__ -   Step: 2666, LR: 2.962103893577178e-07, Loss: 0.17543020844459534
2024-08-04T22:54:56.988451406Z 
 47%|████▋     | 2667/5712 [6:16:48<7:13:07,  8.53s/it]08/04/2024 15:54:56 - INFO - __main__ -   Step: 2667, LR: 2.9611311072740095e-07, Loss: 0.20064762234687805
2024-08-04T22:55:05.412557447Z 
 47%|████▋     | 2668/5712 [6:16:56<7:11:18,  8.50s/it]08/04/2024 15:55:05 - INFO - __main__ -   Step: 2668, LR: 2.960158320970841e-07, Loss: 0.12764647603034973
2024-08-04T22:55:13.812632991Z 
 47%|████▋     | 2669/5712 [6:17:04<7:09:37,  8.47s/it]08/04/2024 15:55:13 - INFO - __main__ -   Step: 2669, LR: 2.959185534667672e-07, Loss: 0.17252099514007568
2024-08-04T22:55:21.977129289Z 
 47%|████▋     | 2670/5712 [6:17:13<7:04:48,  8.38s/it]08/04/2024 15:55:21 - INFO - __main__ -   Step: 2670, LR: 2.958212748364503e-07, Loss: 0.1617475003004074
2024-08-04T22:55:30.274384172Z 
 47%|████▋     | 2671/5712 [6:17:21<7:03:25,  8.35s/it]08/04/2024 15:55:30 - INFO - __main__ -   Step: 2671, LR: 2.957239962061334e-07, Loss: 0.3214833736419678
2024-08-04T22:55:38.287227417Z 
 47%|████▋     | 2672/5712 [6:17:29<6:58:06,  8.25s/it]08/04/2024 15:55:38 - INFO - __main__ -   Step: 2672, LR: 2.9562671757581655e-07, Loss: 0.3138517737388611
2024-08-04T22:55:47.080475931Z 
 47%|████▋     | 2673/5712 [6:17:38<7:06:11,  8.41s/it]08/04/2024 15:55:47 - INFO - __main__ -   Step: 2673, LR: 2.9552943894549965e-07, Loss: 0.15223625302314758
2024-08-04T22:55:55.375430988Z 
 47%|████▋     | 2674/5712 [6:17:46<7:04:13,  8.38s/it]08/04/2024 15:55:55 - INFO - __main__ -   Step: 2674, LR: 2.9543216031518275e-07, Loss: 0.1562904268503189
2024-08-04T22:56:03.817885260Z 
 47%|████▋     | 2675/5712 [6:17:54<7:05:04,  8.40s/it]08/04/2024 15:56:03 - INFO - __main__ -   Step: 2675, LR: 2.9533488168486585e-07, Loss: 0.2955206036567688
2024-08-04T22:56:12.074269903Z 
 47%|████▋     | 2676/5712 [6:18:03<7:02:46,  8.36s/it]08/04/2024 15:56:12 - INFO - __main__ -   Step: 2676, LR: 2.95237603054549e-07, Loss: 0.22641980648040771
2024-08-04T22:56:20.879110908Z 
 47%|████▋     | 2677/5712 [6:18:12<7:09:27,  8.49s/it]08/04/2024 15:56:20 - INFO - __main__ -   Step: 2677, LR: 2.951403244242321e-07, Loss: 0.3129284381866455
2024-08-04T22:56:29.866200691Z 
 47%|████▋     | 2678/5712 [6:18:21<7:16:51,  8.64s/it]08/04/2024 15:56:29 - INFO - __main__ -   Step: 2678, LR: 2.950430457939152e-07, Loss: 0.14315928518772125
2024-08-04T22:56:38.543568987Z 
 47%|████▋     | 2679/5712 [6:18:29<7:17:17,  8.65s/it]08/04/2024 15:56:38 - INFO - __main__ -   Step: 2679, LR: 2.949457671635983e-07, Loss: 0.121428482234478
2024-08-04T22:56:46.041432283Z 
 47%|████▋     | 2680/5712 [6:18:37<6:59:40,  8.30s/it]08/04/2024 15:56:46 - INFO - __main__ -   Step: 2680, LR: 2.948484885332814e-07, Loss: 0.2551431357860565
2024-08-04T22:56:54.926260643Z 
 47%|████▋     | 2681/5712 [6:18:46<7:08:19,  8.48s/it]08/04/2024 15:56:54 - INFO - __main__ -   Step: 2681, LR: 2.9475120990296455e-07, Loss: 0.16455498337745667
2024-08-04T22:57:03.148009895Z 
 47%|████▋     | 2682/5712 [6:18:54<7:04:17,  8.40s/it]08/04/2024 15:57:03 - INFO - __main__ -   Step: 2682, LR: 2.9465393127264765e-07, Loss: 0.18041656911373138
2024-08-04T22:57:11.982363311Z 
 47%|████▋     | 2683/5712 [6:19:03<7:10:41,  8.53s/it]08/04/2024 15:57:11 - INFO - __main__ -   Step: 2683, LR: 2.9455665264233075e-07, Loss: 0.17082996666431427
2024-08-04T22:57:20.615125888Z 
 47%|████▋     | 2684/5712 [6:19:11<7:12:05,  8.56s/it]08/04/2024 15:57:20 - INFO - __main__ -   Step: 2684, LR: 2.9445937401201385e-07, Loss: 0.3014461398124695
2024-08-04T22:57:28.781307277Z 
 47%|████▋     | 2685/5712 [6:19:19<7:05:57,  8.44s/it]08/04/2024 15:57:28 - INFO - __main__ -   Step: 2685, LR: 2.9436209538169705e-07, Loss: 0.12566876411437988
2024-08-04T22:57:37.203731135Z 
 47%|████▋     | 2686/5712 [6:19:28<7:05:29,  8.44s/it]08/04/2024 15:57:37 - INFO - __main__ -   Step: 2686, LR: 2.9426481675138015e-07, Loss: 0.3515550494194031
2024-08-04T22:57:45.422511127Z 
 47%|████▋     | 2687/5712 [6:19:36<7:02:03,  8.37s/it]08/04/2024 15:57:45 - INFO - __main__ -   Step: 2687, LR: 2.9416753812106325e-07, Loss: 0.2268524467945099
2024-08-04T22:57:53.506494653Z 
 47%|████▋     | 2688/5712 [6:19:44<6:57:34,  8.29s/it]08/04/2024 15:57:53 - INFO - __main__ -   Step: 2688, LR: 2.9407025949074635e-07, Loss: 0.2316824197769165
2024-08-04T22:58:01.796981212Z 
 47%|████▋     | 2689/5712 [6:19:52<6:57:31,  8.29s/it]08/04/2024 15:58:01 - INFO - __main__ -   Step: 2689, LR: 2.939729808604295e-07, Loss: 0.22525817155838013
2024-08-04T22:58:10.265872882Z 
 47%|████▋     | 2690/5712 [6:20:01<7:00:08,  8.34s/it]08/04/2024 15:58:10 - INFO - __main__ -   Step: 2690, LR: 2.938757022301126e-07, Loss: 0.18507106602191925
2024-08-04T22:58:18.503904135Z 
 47%|████▋     | 2691/5712 [6:20:09<6:58:25,  8.31s/it]08/04/2024 15:58:18 - INFO - __main__ -   Step: 2691, LR: 2.937784235997957e-07, Loss: 0.1978013962507248
2024-08-04T22:58:27.512869698Z 
 47%|████▋     | 2692/5712 [6:20:18<7:08:50,  8.52s/it]08/04/2024 15:58:27 - INFO - __main__ -   Step: 2692, LR: 2.936811449694788e-07, Loss: 0.15175823867321014
2024-08-04T22:58:35.470160775Z 
 47%|████▋     | 2693/5712 [6:20:26<7:00:12,  8.35s/it]08/04/2024 15:58:35 - INFO - __main__ -   Step: 2693, LR: 2.9358386633916195e-07, Loss: 0.21078220009803772
2024-08-04T22:58:44.381015351Z 
 47%|████▋     | 2694/5712 [6:20:35<7:08:30,  8.52s/it]08/04/2024 15:58:44 - INFO - __main__ -   Step: 2694, LR: 2.9348658770884505e-07, Loss: 0.24807600677013397
2024-08-04T22:58:52.781745445Z 
 47%|████▋     | 2695/5712 [6:20:43<7:06:35,  8.48s/it]08/04/2024 15:58:52 - INFO - __main__ -   Step: 2695, LR: 2.9338930907852815e-07, Loss: 0.23867255449295044
2024-08-04T22:59:01.112109470Z 
 47%|████▋     | 2696/5712 [6:20:52<7:04:07,  8.44s/it]08/04/2024 15:59:01 - INFO - __main__ -   Step: 2696, LR: 2.9329203044821125e-07, Loss: 0.2646373510360718
2024-08-04T22:59:09.162643066Z 
 47%|████▋     | 2697/5712 [6:21:00<6:58:08,  8.32s/it]08/04/2024 15:59:09 - INFO - __main__ -   Step: 2697, LR: 2.931947518178944e-07, Loss: 0.15507090091705322
2024-08-04T22:59:18.019111580Z 
 47%|████▋     | 2698/5712 [6:21:09<7:06:04,  8.48s/it]08/04/2024 15:59:18 - INFO - __main__ -   Step: 2698, LR: 2.930974731875775e-07, Loss: 0.18219073116779327
2024-08-04T22:59:25.519133694Z 
 47%|████▋     | 2699/5712 [6:21:16<6:51:08,  8.19s/it]08/04/2024 15:59:25 - INFO - __main__ -   Step: 2699, LR: 2.930001945572606e-07, Loss: 0.20092618465423584
2024-08-04T22:59:34.476123624Z 
 47%|████▋     | 2700/5712 [6:21:25<7:02:36,  8.42s/it]08/04/2024 15:59:34 - INFO - __main__ -   Step: 2700, LR: 2.929029159269437e-07, Loss: 0.14126582443714142
2024-08-04T22:59:42.623429515Z 
 47%|████▋     | 2701/5712 [6:21:33<6:58:22,  8.34s/it]08/04/2024 15:59:42 - INFO - __main__ -   Step: 2701, LR: 2.9280563729662685e-07, Loss: 0.40196123719215393
2024-08-04T22:59:51.114275498Z 
 47%|████▋     | 2702/5712 [6:21:42<7:00:33,  8.38s/it]08/04/2024 15:59:51 - INFO - __main__ -   Step: 2702, LR: 2.9270835866630995e-07, Loss: 0.18185947835445404
2024-08-04T22:59:59.325552121Z 
 47%|████▋     | 2703/5712 [6:21:50<6:57:49,  8.33s/it]08/04/2024 15:59:59 - INFO - __main__ -   Step: 2703, LR: 2.926110800359931e-07, Loss: 0.3805047869682312
2024-08-04T23:00:07.643908109Z 
 47%|████▋     | 2704/5712 [6:21:58<6:57:29,  8.33s/it]08/04/2024 16:00:07 - INFO - __main__ -   Step: 2704, LR: 2.925138014056762e-07, Loss: 0.23382332921028137
2024-08-04T23:00:15.788534247Z 
 47%|████▋     | 2705/5712 [6:22:06<6:54:36,  8.27s/it]08/04/2024 16:00:15 - INFO - __main__ -   Step: 2705, LR: 2.9241652277535935e-07, Loss: 0.14681823551654816
2024-08-04T23:00:24.585267184Z 
 47%|████▋     | 2706/5712 [6:22:15<7:02:20,  8.43s/it]08/04/2024 16:00:24 - INFO - __main__ -   Step: 2706, LR: 2.9231924414504245e-07, Loss: 0.22925016283988953
2024-08-04T23:00:32.959788429Z 
 47%|████▋     | 2707/5712 [6:22:24<7:01:21,  8.41s/it]08/04/2024 16:00:32 - INFO - __main__ -   Step: 2707, LR: 2.9222196551472555e-07, Loss: 0.12807101011276245
2024-08-04T23:00:41.597351895Z 
 47%|████▋     | 2708/5712 [6:22:32<7:04:35,  8.48s/it]08/04/2024 16:00:41 - INFO - __main__ -   Step: 2708, LR: 2.9212468688440865e-07, Loss: 0.18096576631069183
2024-08-04T23:00:50.457336494Z 
 47%|████▋     | 2709/5712 [6:22:41<7:10:09,  8.59s/it]08/04/2024 16:00:50 - INFO - __main__ -   Step: 2709, LR: 2.920274082540918e-07, Loss: 0.19618511199951172
2024-08-04T23:00:58.781951526Z 
 47%|████▋     | 2710/5712 [6:22:49<7:05:57,  8.51s/it]08/04/2024 16:00:58 - INFO - __main__ -   Step: 2710, LR: 2.919301296237749e-07, Loss: 0.1260850429534912
2024-08-04T23:01:07.039682089Z 
 47%|████▋     | 2711/5712 [6:22:58<7:01:58,  8.44s/it]08/04/2024 16:01:07 - INFO - __main__ -   Step: 2711, LR: 2.91832850993458e-07, Loss: 0.17614859342575073
2024-08-04T23:01:15.606107729Z 
 47%|████▋     | 2712/5712 [6:23:06<7:03:46,  8.48s/it]08/04/2024 16:01:15 - INFO - __main__ -   Step: 2712, LR: 2.917355723631411e-07, Loss: 0.13577032089233398
2024-08-04T23:01:23.731628312Z 
 47%|████▋     | 2713/5712 [6:23:14<6:58:23,  8.37s/it]08/04/2024 16:01:23 - INFO - __main__ -   Step: 2713, LR: 2.9163829373282425e-07, Loss: 0.18831366300582886
2024-08-04T23:01:32.631847567Z 
 48%|████▊     | 2714/5712 [6:23:23<7:06:11,  8.53s/it]08/04/2024 16:01:32 - INFO - __main__ -   Step: 2714, LR: 2.9154101510250735e-07, Loss: 0.14401483535766602
2024-08-04T23:01:41.193152060Z 
 48%|████▊     | 2715/5712 [6:23:32<7:06:30,  8.54s/it]08/04/2024 16:01:41 - INFO - __main__ -   Step: 2715, LR: 2.9144373647219045e-07, Loss: 0.18286491930484772
2024-08-04T23:01:49.105009697Z 
 48%|████▊     | 2716/5712 [6:23:40<6:56:59,  8.35s/it]08/04/2024 16:01:49 - INFO - __main__ -   Step: 2716, LR: 2.9134645784187355e-07, Loss: 0.13290610909461975
2024-08-04T23:01:58.147836371Z 
 48%|████▊     | 2717/5712 [6:23:49<7:07:13,  8.56s/it]08/04/2024 16:01:58 - INFO - __main__ -   Step: 2717, LR: 2.9124917921155665e-07, Loss: 0.2262214720249176
2024-08-04T23:02:06.707491871Z 
 48%|████▊     | 2718/5712 [6:23:57<7:07:05,  8.56s/it]08/04/2024 16:02:06 - INFO - __main__ -   Step: 2718, LR: 2.911519005812398e-07, Loss: 0.18464908003807068
2024-08-04T23:02:14.844863397Z 
 48%|████▊     | 2719/5712 [6:24:05<7:00:38,  8.43s/it]08/04/2024 16:02:14 - INFO - __main__ -   Step: 2719, LR: 2.910546219509229e-07, Loss: 0.23501378297805786
2024-08-04T23:02:23.265129552Z 
 48%|████▊     | 2720/5712 [6:24:14<7:00:18,  8.43s/it]08/04/2024 16:02:23 - INFO - __main__ -   Step: 2720, LR: 2.90957343320606e-07, Loss: 0.08422329276800156
2024-08-04T23:02:31.234821807Z 
 48%|████▊     | 2721/5712 [6:24:22<6:53:18,  8.29s/it]08/04/2024 16:02:31 - INFO - __main__ -   Step: 2721, LR: 2.908600646902892e-07, Loss: 0.11244266480207443
2024-08-04T23:02:40.607121875Z 
 48%|████▊     | 2722/5712 [6:24:31<7:09:20,  8.62s/it]08/04/2024 16:02:40 - INFO - __main__ -   Step: 2722, LR: 2.907627860599723e-07, Loss: 0.231222003698349
2024-08-04T23:02:48.608670787Z 
 48%|████▊     | 2723/5712 [6:24:39<7:00:01,  8.43s/it]08/04/2024 16:02:48 - INFO - __main__ -   Step: 2723, LR: 2.906655074296554e-07, Loss: 0.1865764707326889
2024-08-04T23:02:57.065227701Z 
 48%|████▊     | 2724/5712 [6:24:48<7:00:15,  8.44s/it]08/04/2024 16:02:57 - INFO - __main__ -   Step: 2724, LR: 2.905682287993385e-07, Loss: 0.19683444499969482
2024-08-04T23:03:06.365091303Z 
 48%|████▊     | 2725/5712 [6:24:57<7:12:57,  8.70s/it]08/04/2024 16:03:06 - INFO - __main__ -   Step: 2725, LR: 2.904709501690216e-07, Loss: 0.2633439302444458
2024-08-04T23:03:15.294677861Z 
 48%|████▊     | 2726/5712 [6:25:06<7:16:18,  8.77s/it]08/04/2024 16:03:15 - INFO - __main__ -   Step: 2726, LR: 2.9037367153870475e-07, Loss: 0.2962554693222046
2024-08-04T23:03:23.721917909Z 
 48%|████▊     | 2727/5712 [6:25:14<7:11:05,  8.67s/it]08/04/2024 16:03:23 - INFO - __main__ -   Step: 2727, LR: 2.9027639290838785e-07, Loss: 0.1837662011384964
2024-08-04T23:03:32.846155545Z 
 48%|████▊     | 2728/5712 [6:25:23<7:17:47,  8.80s/it]08/04/2024 16:03:32 - INFO - __main__ -   Step: 2728, LR: 2.9017911427807095e-07, Loss: 0.1690681278705597
2024-08-04T23:03:40.860569157Z 
 48%|████▊     | 2729/5712 [6:25:32<7:05:53,  8.57s/it]08/04/2024 16:03:40 - INFO - __main__ -   Step: 2729, LR: 2.9008183564775405e-07, Loss: 0.19279542565345764
2024-08-04T23:03:49.859566951Z 
 48%|████▊     | 2730/5712 [6:25:41<7:12:11,  8.70s/it]08/04/2024 16:03:49 - INFO - __main__ -   Step: 2730, LR: 2.899845570174372e-07, Loss: 0.15826964378356934
2024-08-04T23:03:57.862162656Z 
 48%|████▊     | 2731/5712 [6:25:49<7:01:42,  8.49s/it]08/04/2024 16:03:57 - INFO - __main__ -   Step: 2731, LR: 2.898872783871203e-07, Loss: 0.140131875872612
2024-08-04T23:04:06.606099423Z 
 48%|████▊     | 2732/5712 [6:25:57<7:05:23,  8.56s/it]08/04/2024 16:04:06 - INFO - __main__ -   Step: 2732, LR: 2.897899997568034e-07, Loss: 0.21585336327552795
2024-08-04T23:04:15.190509640Z 
 48%|████▊     | 2733/5712 [6:26:06<7:05:32,  8.57s/it]08/04/2024 16:04:15 - INFO - __main__ -   Step: 2733, LR: 2.896927211264865e-07, Loss: 0.2361982762813568
2024-08-04T23:04:23.829492948Z 
 48%|████▊     | 2734/5712 [6:26:14<7:06:24,  8.59s/it]08/04/2024 16:04:23 - INFO - __main__ -   Step: 2734, LR: 2.8959544249616965e-07, Loss: 0.2613614797592163
2024-08-04T23:04:32.336848493Z 
 48%|████▊     | 2735/5712 [6:26:23<7:05:01,  8.57s/it]08/04/2024 16:04:32 - INFO - __main__ -   Step: 2735, LR: 2.8949816386585275e-07, Loss: 0.1319347769021988
2024-08-04T23:04:40.460513994Z 
 48%|████▊     | 2736/5712 [6:26:31<6:58:17,  8.43s/it]08/04/2024 16:04:40 - INFO - __main__ -   Step: 2736, LR: 2.8940088523553585e-07, Loss: 0.17943865060806274
2024-08-04T23:04:48.486027968Z 
 48%|████▊     | 2737/5712 [6:26:39<6:52:05,  8.31s/it]08/04/2024 16:04:48 - INFO - __main__ -   Step: 2737, LR: 2.8930360660521895e-07, Loss: 0.09094081819057465
2024-08-04T23:04:57.109036560Z 
 48%|████▊     | 2738/5712 [6:26:48<6:56:35,  8.40s/it]08/04/2024 16:04:57 - INFO - __main__ -   Step: 2738, LR: 2.892063279749021e-07, Loss: 0.2131292074918747
2024-08-04T23:05:06.120989884Z 
 48%|████▊     | 2739/5712 [6:26:57<7:05:27,  8.59s/it]08/04/2024 16:05:06 - INFO - __main__ -   Step: 2739, LR: 2.891090493445852e-07, Loss: 0.1953580230474472
2024-08-04T23:05:14.154689367Z 
 48%|████▊     | 2740/5712 [6:27:05<6:57:07,  8.42s/it]08/04/2024 16:05:14 - INFO - __main__ -   Step: 2740, LR: 2.8901177071426835e-07, Loss: 0.1486193686723709
2024-08-04T23:05:23.207704739Z 
 48%|████▊     | 2741/5712 [6:27:14<7:06:22,  8.61s/it]08/04/2024 16:05:23 - INFO - __main__ -   Step: 2741, LR: 2.8891449208395145e-07, Loss: 0.2571563124656677
2024-08-04T23:05:31.679030106Z 
 48%|████▊     | 2742/5712 [6:27:22<7:04:09,  8.57s/it]08/04/2024 16:05:31 - INFO - __main__ -   Step: 2742, LR: 2.888172134536346e-07, Loss: 0.1869194209575653
2024-08-04T23:05:40.109122162Z 
 48%|████▊     | 2743/5712 [6:27:31<7:01:56,  8.53s/it]08/04/2024 16:05:40 - INFO - __main__ -   Step: 2743, LR: 2.887199348233177e-07, Loss: 0.167058527469635
2024-08-04T23:05:48.743349571Z 
 48%|████▊     | 2744/5712 [6:27:39<7:03:23,  8.56s/it]08/04/2024 16:05:48 - INFO - __main__ -   Step: 2744, LR: 2.886226561930008e-07, Loss: 0.1420198231935501
2024-08-04T23:05:56.869765888Z 
 48%|████▊     | 2745/5712 [6:27:48<6:56:50,  8.43s/it]08/04/2024 16:05:56 - INFO - __main__ -   Step: 2745, LR: 2.885253775626839e-07, Loss: 0.13447268307209015
2024-08-04T23:06:04.890548230Z 
 48%|████▊     | 2746/5712 [6:27:56<6:50:38,  8.31s/it]08/04/2024 16:06:04 - INFO - __main__ -   Step: 2746, LR: 2.8842809893236705e-07, Loss: 0.15345731377601624
2024-08-04T23:06:13.446187042Z 
 48%|████▊     | 2747/5712 [6:28:04<6:54:11,  8.38s/it]08/04/2024 16:06:13 - INFO - __main__ -   Step: 2747, LR: 2.8833082030205015e-07, Loss: 0.11129944026470184
2024-08-04T23:06:21.444133280Z 
 48%|████▊     | 2748/5712 [6:28:12<6:48:21,  8.27s/it]08/04/2024 16:06:21 - INFO - __main__ -   Step: 2748, LR: 2.8823354167173325e-07, Loss: 0.23342689871788025
2024-08-04T23:06:30.529210839Z 
 48%|████▊     | 2749/5712 [6:28:21<7:00:20,  8.51s/it]08/04/2024 16:06:30 - INFO - __main__ -   Step: 2749, LR: 2.8813626304141635e-07, Loss: 0.2925207316875458
2024-08-04T23:06:38.930371866Z 
 48%|████▊     | 2750/5712 [6:28:30<6:58:33,  8.48s/it]08/04/2024 16:06:38 - INFO - __main__ -   Step: 2750, LR: 2.880389844110995e-07, Loss: 0.1557481586933136
2024-08-04T23:06:47.889629309Z 
 48%|████▊     | 2751/5712 [6:28:39<7:05:32,  8.62s/it]08/04/2024 16:06:47 - INFO - __main__ -   Step: 2751, LR: 2.879417057807826e-07, Loss: 0.10593129694461823
2024-08-04T23:06:56.165720605Z 
 48%|████▊     | 2752/5712 [6:28:47<7:00:15,  8.52s/it]08/04/2024 16:06:56 - INFO - __main__ -   Step: 2752, LR: 2.878444271504657e-07, Loss: 0.18606804311275482
2024-08-04T23:07:04.306108878Z 
 48%|████▊     | 2753/5712 [6:28:55<6:54:31,  8.41s/it]08/04/2024 16:07:04 - INFO - __main__ -   Step: 2753, LR: 2.877471485201488e-07, Loss: 0.24655231833457947
2024-08-04T23:07:11.795919316Z 
 48%|████▊     | 2754/5712 [6:29:02<6:40:50,  8.13s/it]08/04/2024 16:07:11 - INFO - __main__ -   Step: 2754, LR: 2.876498698898319e-07, Loss: 0.17195357382297516
2024-08-04T23:07:20.249741066Z 
 48%|████▊     | 2755/5712 [6:29:11<6:45:29,  8.23s/it]08/04/2024 16:07:20 - INFO - __main__ -   Step: 2755, LR: 2.8755259125951505e-07, Loss: 0.11005784571170807
2024-08-04T23:07:28.691385848Z 
 48%|████▊     | 2756/5712 [6:29:19<6:48:29,  8.29s/it]08/04/2024 16:07:28 - INFO - __main__ -   Step: 2756, LR: 2.8745531262919814e-07, Loss: 0.1570792943239212
2024-08-04T23:07:37.251812777Z 
 48%|████▊     | 2757/5712 [6:29:28<6:52:20,  8.37s/it]08/04/2024 16:07:37 - INFO - __main__ -   Step: 2757, LR: 2.8735803399888124e-07, Loss: 0.18178215622901917
2024-08-04T23:07:45.973477209Z 
 48%|████▊     | 2758/5712 [6:29:37<6:57:20,  8.48s/it]08/04/2024 16:07:45 - INFO - __main__ -   Step: 2758, LR: 2.8726075536856445e-07, Loss: 0.12115772068500519
2024-08-04T23:07:54.916515690Z 
 48%|████▊     | 2759/5712 [6:29:46<7:04:06,  8.62s/it]08/04/2024 16:07:54 - INFO - __main__ -   Step: 2759, LR: 2.8716347673824755e-07, Loss: 0.16299745440483093
2024-08-04T23:08:03.113094677Z 
 48%|████▊     | 2760/5712 [6:29:54<6:57:45,  8.49s/it]08/04/2024 16:08:03 - INFO - __main__ -   Step: 2760, LR: 2.8706619810793065e-07, Loss: 0.15282610058784485
2024-08-04T23:08:11.754464671Z 
 48%|████▊     | 2761/5712 [6:30:02<6:59:49,  8.54s/it]08/04/2024 16:08:11 - INFO - __main__ -   Step: 2761, LR: 2.8696891947761375e-07, Loss: 0.24125449359416962
2024-08-04T23:08:19.310994008Z 
 48%|████▊     | 2762/5712 [6:30:10<6:45:14,  8.24s/it]08/04/2024 16:08:19 - INFO - __main__ -   Step: 2762, LR: 2.8687164084729684e-07, Loss: 0.27892765402793884
2024-08-04T23:08:28.151956545Z 
 48%|████▊     | 2763/5712 [6:30:19<6:53:56,  8.42s/it]08/04/2024 16:08:28 - INFO - __main__ -   Step: 2763, LR: 2.8677436221698e-07, Loss: 0.20436197519302368
2024-08-04T23:08:36.493984121Z 
 48%|████▊     | 2764/5712 [6:30:27<6:52:37,  8.40s/it]08/04/2024 16:08:36 - INFO - __main__ -   Step: 2764, LR: 2.866770835866631e-07, Loss: 0.14352871477603912
2024-08-04T23:08:44.698144237Z 
 48%|████▊     | 2765/5712 [6:30:35<6:49:37,  8.34s/it]08/04/2024 16:08:44 - INFO - __main__ -   Step: 2765, LR: 2.865798049563462e-07, Loss: 0.21670788526535034
2024-08-04T23:08:53.894318708Z 
 48%|████▊     | 2766/5712 [6:30:45<7:02:05,  8.60s/it]08/04/2024 16:08:53 - INFO - __main__ -   Step: 2766, LR: 2.864825263260293e-07, Loss: 0.10336185246706009
2024-08-04T23:09:03.142556059Z 
 48%|████▊     | 2767/5712 [6:30:54<7:11:32,  8.79s/it]08/04/2024 16:09:03 - INFO - __main__ -   Step: 2767, LR: 2.8638524769571245e-07, Loss: 0.2837536633014679
2024-08-04T23:09:12.638064745Z 
 48%|████▊     | 2768/5712 [6:31:03<7:21:45,  9.00s/it]08/04/2024 16:09:12 - INFO - __main__ -   Step: 2768, LR: 2.8628796906539555e-07, Loss: 0.1306494176387787
2024-08-04T23:09:20.742074449Z 
 48%|████▊     | 2769/5712 [6:31:11<7:08:22,  8.73s/it]08/04/2024 16:09:20 - INFO - __main__ -   Step: 2769, LR: 2.8619069043507864e-07, Loss: 0.24939903616905212
2024-08-04T23:09:28.723731112Z 
 48%|████▊     | 2770/5712 [6:31:19<6:57:10,  8.51s/it]08/04/2024 16:09:28 - INFO - __main__ -   Step: 2770, LR: 2.8609341180476174e-07, Loss: 0.15230104327201843
2024-08-04T23:09:37.170271701Z 
 49%|████▊     | 2771/5712 [6:31:28<6:56:07,  8.49s/it]08/04/2024 16:09:37 - INFO - __main__ -   Step: 2771, LR: 2.859961331744449e-07, Loss: 0.16194689273834229
2024-08-04T23:09:45.543907176Z 
 49%|████▊     | 2772/5712 [6:31:36<6:54:17,  8.45s/it]08/04/2024 16:09:45 - INFO - __main__ -   Step: 2772, LR: 2.85898854544128e-07, Loss: 0.08189351856708527
2024-08-04T23:09:54.067727978Z 
 49%|████▊     | 2773/5712 [6:31:45<6:55:08,  8.48s/it]08/04/2024 16:09:54 - INFO - __main__ -   Step: 2773, LR: 2.858015759138111e-07, Loss: 0.20585846900939941
2024-08-04T23:10:02.458973399Z 
 49%|████▊     | 2774/5712 [6:31:53<6:53:47,  8.45s/it]08/04/2024 16:10:02 - INFO - __main__ -   Step: 2774, LR: 2.857042972834942e-07, Loss: 0.2328386753797531
2024-08-04T23:10:11.833375025Z 
 49%|████▊     | 2775/5712 [6:32:02<7:07:11,  8.73s/it]08/04/2024 16:10:11 - INFO - __main__ -   Step: 2775, LR: 2.8560701865317734e-07, Loss: 0.19515839219093323
2024-08-04T23:10:20.465815829Z 
 49%|████▊     | 2776/5712 [6:32:11<7:05:40,  8.70s/it]08/04/2024 16:10:20 - INFO - __main__ -   Step: 2776, LR: 2.855097400228605e-07, Loss: 0.17937827110290527
2024-08-04T23:10:29.330565691Z 
 49%|████▊     | 2777/5712 [6:32:20<7:07:57,  8.75s/it]08/04/2024 16:10:29 - INFO - __main__ -   Step: 2777, LR: 2.854124613925436e-07, Loss: 0.14626231789588928
2024-08-04T23:10:37.675606954Z 
 49%|████▊     | 2778/5712 [6:32:28<7:01:53,  8.63s/it]08/04/2024 16:10:37 - INFO - __main__ -   Step: 2778, LR: 2.853151827622267e-07, Loss: 0.17508387565612793
2024-08-04T23:10:45.938874776Z 
 49%|████▊     | 2779/5712 [6:32:37<6:56:24,  8.52s/it]08/04/2024 16:10:45 - INFO - __main__ -   Step: 2779, LR: 2.8521790413190985e-07, Loss: 0.10332957655191422
2024-08-04T23:10:54.646054427Z 
 49%|████▊     | 2780/5712 [6:32:45<6:59:01,  8.58s/it]08/04/2024 16:10:54 - INFO - __main__ -   Step: 2780, LR: 2.8512062550159295e-07, Loss: 0.1992172747850418
2024-08-04T23:11:03.125759903Z 
 49%|████▊     | 2781/5712 [6:32:54<6:57:29,  8.55s/it]08/04/2024 16:11:03 - INFO - __main__ -   Step: 2781, LR: 2.8502334687127604e-07, Loss: 0.17718586325645447
2024-08-04T23:11:11.547418824Z 
 49%|████▊     | 2782/5712 [6:33:02<6:55:31,  8.51s/it]08/04/2024 16:11:11 - INFO - __main__ -   Step: 2782, LR: 2.8492606824095914e-07, Loss: 0.2546444833278656
2024-08-04T23:11:20.303718751Z 
 49%|████▊     | 2783/5712 [6:33:11<6:59:00,  8.58s/it]08/04/2024 16:11:20 - INFO - __main__ -   Step: 2783, LR: 2.848287896106423e-07, Loss: 0.24256795644760132
2024-08-04T23:11:28.694488812Z 
 49%|████▊     | 2784/5712 [6:33:19<6:56:02,  8.53s/it]08/04/2024 16:11:28 - INFO - __main__ -   Step: 2784, LR: 2.847315109803254e-07, Loss: 0.2402481585741043
2024-08-04T23:11:37.149512944Z 
 49%|████▉     | 2785/5712 [6:33:28<6:54:51,  8.50s/it]08/04/2024 16:11:37 - INFO - __main__ -   Step: 2785, LR: 2.846342323500085e-07, Loss: 0.14104098081588745
2024-08-04T23:11:45.441161862Z 
 49%|████▉     | 2786/5712 [6:33:36<6:51:37,  8.44s/it]08/04/2024 16:11:45 - INFO - __main__ -   Step: 2786, LR: 2.845369537196916e-07, Loss: 0.2053070217370987
2024-08-04T23:11:53.489803861Z 
 49%|████▉     | 2787/5712 [6:33:44<6:45:44,  8.32s/it]08/04/2024 16:11:53 - INFO - __main__ -   Step: 2787, LR: 2.8443967508937474e-07, Loss: 0.20138663053512573
2024-08-04T23:12:02.786979537Z 
 49%|████▉     | 2788/5712 [6:33:53<6:59:50,  8.62s/it]08/04/2024 16:12:02 - INFO - __main__ -   Step: 2788, LR: 2.8434239645905784e-07, Loss: 0.29818296432495117
2024-08-04T23:12:10.940144364Z 
 49%|████▉     | 2789/5712 [6:34:02<6:52:57,  8.48s/it]08/04/2024 16:12:10 - INFO - __main__ -   Step: 2789, LR: 2.8424511782874094e-07, Loss: 0.13174885511398315
2024-08-04T23:12:19.131577158Z 
 49%|████▉     | 2790/5712 [6:34:10<6:48:38,  8.39s/it]08/04/2024 16:12:19 - INFO - __main__ -   Step: 2790, LR: 2.8414783919842404e-07, Loss: 0.21695144474506378
2024-08-04T23:12:27.609582973Z 
 49%|████▉     | 2791/5712 [6:34:18<6:49:46,  8.42s/it]08/04/2024 16:12:27 - INFO - __main__ -   Step: 2791, LR: 2.8405056056810714e-07, Loss: 0.25100991129875183
2024-08-04T23:12:36.909404977Z 
 49%|████▉     | 2792/5712 [6:34:28<7:02:30,  8.68s/it]08/04/2024 16:12:36 - INFO - __main__ -   Step: 2792, LR: 2.839532819377903e-07, Loss: 0.15365876257419586
2024-08-04T23:12:45.120109330Z 
 49%|████▉     | 2793/5712 [6:34:36<6:55:30,  8.54s/it]08/04/2024 16:12:45 - INFO - __main__ -   Step: 2793, LR: 2.838560033074734e-07, Loss: 0.1325039565563202
2024-08-04T23:12:53.501459062Z 
 49%|████▉     | 2794/5712 [6:34:44<6:53:02,  8.49s/it]08/04/2024 16:12:53 - INFO - __main__ -   Step: 2794, LR: 2.8375872467715654e-07, Loss: 0.2579991817474365
2024-08-04T23:13:01.650557633Z 
 49%|████▉     | 2795/5712 [6:34:52<6:47:52,  8.39s/it]08/04/2024 16:13:01 - INFO - __main__ -   Step: 2795, LR: 2.836614460468397e-07, Loss: 0.25674766302108765
2024-08-04T23:13:10.310514060Z 
 49%|████▉     | 2796/5712 [6:35:01<6:51:40,  8.47s/it]08/04/2024 16:13:10 - INFO - __main__ -   Step: 2796, LR: 2.835641674165228e-07, Loss: 0.19217194616794586
2024-08-04T23:13:19.080495677Z 
 49%|████▉     | 2797/5712 [6:35:10<6:55:54,  8.56s/it]08/04/2024 16:13:19 - INFO - __main__ -   Step: 2797, LR: 2.834668887862059e-07, Loss: 0.17221131920814514
2024-08-04T23:13:27.239486113Z 
 49%|████▉     | 2798/5712 [6:35:18<6:49:54,  8.44s/it]08/04/2024 16:13:27 - INFO - __main__ -   Step: 2798, LR: 2.83369610155889e-07, Loss: 0.17318251729011536
2024-08-04T23:13:35.414339108Z 
 49%|████▉     | 2799/5712 [6:35:26<6:45:54,  8.36s/it]08/04/2024 16:13:35 - INFO - __main__ -   Step: 2799, LR: 2.832723315255721e-07, Loss: 0.22987708449363708
2024-08-04T23:13:44.444975601Z 
 49%|████▉     | 2800/5712 [6:35:35<6:55:31,  8.56s/it]08/04/2024 16:13:44 - INFO - __main__ -   Step: 2800, LR: 2.8317505289525524e-07, Loss: 0.16050517559051514
2024-08-04T23:13:53.011598527Z 
 49%|████▉     | 2801/5712 [6:35:44<6:55:27,  8.56s/it]08/04/2024 16:13:53 - INFO - __main__ -   Step: 2801, LR: 2.8307777426493834e-07, Loss: 0.18464365601539612
2024-08-04T23:14:01.434413650Z 
 49%|████▉     | 2802/5712 [6:35:52<6:53:16,  8.52s/it]08/04/2024 16:14:01 - INFO - __main__ -   Step: 2802, LR: 2.8298049563462144e-07, Loss: 0.2796825170516968
2024-08-04T23:14:09.754430431Z 
 49%|████▉     | 2803/5712 [6:36:00<6:50:12,  8.46s/it]08/04/2024 16:14:09 - INFO - __main__ -   Step: 2803, LR: 2.8288321700430454e-07, Loss: 0.2583847641944885
2024-08-04T23:14:18.559410008Z 
 49%|████▉     | 2804/5712 [6:36:09<6:55:03,  8.56s/it]08/04/2024 16:14:18 - INFO - __main__ -   Step: 2804, LR: 2.827859383739877e-07, Loss: 0.15443186461925507
2024-08-04T23:14:26.506545488Z 
 49%|████▉     | 2805/5712 [6:36:17<6:45:57,  8.38s/it]08/04/2024 16:14:26 - INFO - __main__ -   Step: 2805, LR: 2.826886597436708e-07, Loss: 0.1456747204065323
2024-08-04T23:14:35.193889064Z 
 49%|████▉     | 2806/5712 [6:36:26<6:50:18,  8.47s/it]08/04/2024 16:14:35 - INFO - __main__ -   Step: 2806, LR: 2.825913811133539e-07, Loss: 0.19404274225234985
2024-08-04T23:14:43.097016892Z 
 49%|████▉     | 2807/5712 [6:36:34<6:41:54,  8.30s/it]08/04/2024 16:14:43 - INFO - __main__ -   Step: 2807, LR: 2.82494102483037e-07, Loss: 0.23869428038597107
2024-08-04T23:14:51.332719099Z 
 49%|████▉     | 2808/5712 [6:36:42<6:40:49,  8.28s/it]08/04/2024 16:14:51 - INFO - __main__ -   Step: 2808, LR: 2.8239682385272014e-07, Loss: 0.15673795342445374
2024-08-04T23:15:00.825882060Z 
 49%|████▉     | 2809/5712 [6:36:51<6:58:15,  8.64s/it]08/04/2024 16:15:00 - INFO - __main__ -   Step: 2809, LR: 2.8229954522240324e-07, Loss: 0.3036191463470459
2024-08-04T23:15:09.171130094Z 
 49%|████▉     | 2810/5712 [6:37:00<6:53:46,  8.55s/it]08/04/2024 16:15:09 - INFO - __main__ -   Step: 2810, LR: 2.8220226659208634e-07, Loss: 0.18139904737472534
2024-08-04T23:15:17.262460486Z 
 49%|████▉     | 2811/5712 [6:37:08<6:46:54,  8.42s/it]08/04/2024 16:15:17 - INFO - __main__ -   Step: 2811, LR: 2.8210498796176944e-07, Loss: 0.16210739314556122
2024-08-04T23:15:26.114649210Z 
 49%|████▉     | 2812/5712 [6:37:17<6:53:05,  8.55s/it]08/04/2024 16:15:26 - INFO - __main__ -   Step: 2812, LR: 2.8200770933145264e-07, Loss: 0.1610216200351715
2024-08-04T23:15:34.456723295Z 
 49%|████▉     | 2813/5712 [6:37:25<6:49:59,  8.49s/it]08/04/2024 16:15:34 - INFO - __main__ -   Step: 2813, LR: 2.8191043070113574e-07, Loss: 0.18466982245445251
2024-08-04T23:15:42.874968716Z 
 49%|████▉     | 2814/5712 [6:37:34<6:48:52,  8.47s/it]08/04/2024 16:15:42 - INFO - __main__ -   Step: 2814, LR: 2.8181315207081884e-07, Loss: 0.2190917283296585
2024-08-04T23:15:51.409327155Z 
 49%|████▉     | 2815/5712 [6:37:42<6:49:43,  8.49s/it]08/04/2024 16:15:51 - INFO - __main__ -   Step: 2815, LR: 2.8171587344050194e-07, Loss: 0.21157188713550568
2024-08-04T23:15:59.677968621Z 
 49%|████▉     | 2816/5712 [6:37:50<6:46:26,  8.42s/it]08/04/2024 16:15:59 - INFO - __main__ -   Step: 2816, LR: 2.816185948101851e-07, Loss: 0.21037790179252625
2024-08-04T23:16:08.628311770Z 
 49%|████▉     | 2817/5712 [6:37:59<6:53:58,  8.58s/it]08/04/2024 16:16:08 - INFO - __main__ -   Step: 2817, LR: 2.815213161798682e-07, Loss: 0.19433552026748657
2024-08-04T23:16:17.373061859Z 
 49%|████▉     | 2818/5712 [6:38:08<6:56:12,  8.63s/it]08/04/2024 16:16:17 - INFO - __main__ -   Step: 2818, LR: 2.814240375495513e-07, Loss: 0.29412150382995605
2024-08-04T23:16:25.907240905Z 
 49%|████▉     | 2819/5712 [6:38:17<6:54:41,  8.60s/it]08/04/2024 16:16:25 - INFO - __main__ -   Step: 2819, LR: 2.813267589192344e-07, Loss: 0.12448371946811676
2024-08-04T23:16:33.922145361Z 
 49%|████▉     | 2820/5712 [6:38:25<6:46:05,  8.43s/it]08/04/2024 16:16:33 - INFO - __main__ -   Step: 2820, LR: 2.8122948028891754e-07, Loss: 0.16937176883220673
2024-08-04T23:16:42.278167282Z 
 49%|████▉     | 2821/5712 [6:38:33<6:44:56,  8.40s/it]08/04/2024 16:16:42 - INFO - __main__ -   Step: 2821, LR: 2.8113220165860064e-07, Loss: 0.1478079855442047
2024-08-04T23:16:50.247288769Z 
 49%|████▉     | 2822/5712 [6:38:41<6:38:30,  8.27s/it]08/04/2024 16:16:50 - INFO - __main__ -   Step: 2822, LR: 2.8103492302828374e-07, Loss: 0.16846591234207153
2024-08-04T23:16:59.186227289Z 
 49%|████▉     | 2823/5712 [6:38:50<6:47:59,  8.47s/it]08/04/2024 16:16:59 - INFO - __main__ -   Step: 2823, LR: 2.8093764439796684e-07, Loss: 0.1832386702299118
2024-08-04T23:17:07.936400277Z 
 49%|████▉     | 2824/5712 [6:38:59<6:51:51,  8.56s/it]08/04/2024 16:17:07 - INFO - __main__ -   Step: 2824, LR: 2.8084036576765e-07, Loss: 0.16859832406044006
2024-08-04T23:17:16.551767389Z 
 49%|████▉     | 2825/5712 [6:39:07<6:52:33,  8.57s/it]08/04/2024 16:17:16 - INFO - __main__ -   Step: 2825, LR: 2.807430871373331e-07, Loss: 0.1963653564453125
2024-08-04T23:17:25.409915545Z 
 49%|████▉     | 2826/5712 [6:39:16<6:56:29,  8.66s/it]08/04/2024 16:17:25 - INFO - __main__ -   Step: 2826, LR: 2.806458085070162e-07, Loss: 0.1709897220134735
2024-08-04T23:17:34.112969203Z 
 49%|████▉     | 2827/5712 [6:39:25<6:57:00,  8.67s/it]08/04/2024 16:17:34 - INFO - __main__ -   Step: 2827, LR: 2.805485298766993e-07, Loss: 0.18894661962985992
2024-08-04T23:17:42.607484017Z 
 50%|████▉     | 2828/5712 [6:39:33<6:54:17,  8.62s/it]08/04/2024 16:17:42 - INFO - __main__ -   Step: 2828, LR: 2.8045125124638244e-07, Loss: 0.14732256531715393
2024-08-04T23:17:50.817221124Z 
 50%|████▉     | 2829/5712 [6:39:41<6:48:14,  8.50s/it]08/04/2024 16:17:50 - INFO - __main__ -   Step: 2829, LR: 2.8035397261606554e-07, Loss: 0.23448501527309418
2024-08-04T23:17:59.061093524Z 
 50%|████▉     | 2830/5712 [6:39:50<6:44:28,  8.42s/it]08/04/2024 16:17:59 - INFO - __main__ -   Step: 2830, LR: 2.802566939857487e-07, Loss: 0.23581036925315857
2024-08-04T23:18:07.709431927Z 
 50%|████▉     | 2831/5712 [6:39:58<6:47:36,  8.49s/it]08/04/2024 16:18:07 - INFO - __main__ -   Step: 2831, LR: 2.801594153554318e-07, Loss: 0.15613286197185516
2024-08-04T23:18:16.431171877Z 
 50%|████▉     | 2832/5712 [6:40:07<6:50:49,  8.56s/it]08/04/2024 16:18:16 - INFO - __main__ -   Step: 2832, LR: 2.8006213672511494e-07, Loss: 0.2674846649169922
2024-08-04T23:18:24.903689828Z 
 50%|████▉     | 2833/5712 [6:40:16<6:49:26,  8.53s/it]08/04/2024 16:18:24 - INFO - __main__ -   Step: 2833, LR: 2.7996485809479804e-07, Loss: 0.19324402511119843
2024-08-04T23:18:34.356425892Z 
 50%|████▉     | 2834/5712 [6:40:25<7:02:31,  8.81s/it]08/04/2024 16:18:34 - INFO - __main__ -   Step: 2834, LR: 2.7986757946448114e-07, Loss: 0.17290441691875458
2024-08-04T23:18:42.617816867Z 
 50%|████▉     | 2835/5712 [6:40:33<6:54:30,  8.64s/it]08/04/2024 16:18:42 - INFO - __main__ -   Step: 2835, LR: 2.7977030083416424e-07, Loss: 0.1709102839231491
2024-08-04T23:18:50.954437405Z 
 50%|████▉     | 2836/5712 [6:40:42<6:49:56,  8.55s/it]08/04/2024 16:18:50 - INFO - __main__ -   Step: 2836, LR: 2.7967302220384734e-07, Loss: 0.17722868919372559
2024-08-04T23:18:59.297929939Z 
 50%|████▉     | 2837/5712 [6:40:50<6:46:47,  8.49s/it]08/04/2024 16:18:59 - INFO - __main__ -   Step: 2837, LR: 2.795757435735305e-07, Loss: 0.1740238070487976
2024-08-04T23:19:07.597356787Z 
 50%|████▉     | 2838/5712 [6:40:58<6:43:55,  8.43s/it]08/04/2024 16:19:07 - INFO - __main__ -   Step: 2838, LR: 2.794784649432136e-07, Loss: 0.19602856040000916
2024-08-04T23:19:16.099845796Z 
 50%|████▉     | 2839/5712 [6:41:07<6:44:46,  8.45s/it]08/04/2024 16:19:16 - INFO - __main__ -   Step: 2839, LR: 2.793811863128967e-07, Loss: 0.18000593781471252
2024-08-04T23:19:24.379808193Z 
 50%|████▉     | 2840/5712 [6:41:15<6:42:08,  8.40s/it]08/04/2024 16:19:24 - INFO - __main__ -   Step: 2840, LR: 2.792839076825798e-07, Loss: 0.20446136593818665
2024-08-04T23:19:32.838234740Z 
 50%|████▉     | 2841/5712 [6:41:23<6:42:49,  8.42s/it]08/04/2024 16:19:32 - INFO - __main__ -   Step: 2841, LR: 2.7918662905226294e-07, Loss: 0.14172792434692383
2024-08-04T23:19:41.235856032Z 
 50%|████▉     | 2842/5712 [6:41:32<6:42:22,  8.41s/it]08/04/2024 16:19:41 - INFO - __main__ -   Step: 2842, LR: 2.7908935042194604e-07, Loss: 0.18229445815086365
2024-08-04T23:19:50.950360325Z 
 50%|████▉     | 2843/5712 [6:41:42<7:00:54,  8.80s/it]08/04/2024 16:19:50 - INFO - __main__ -   Step: 2843, LR: 2.7899207179162914e-07, Loss: 0.23524466156959534
2024-08-04T23:19:59.380392943Z 
 50%|████▉     | 2844/5712 [6:41:50<6:55:26,  8.69s/it]08/04/2024 16:19:59 - INFO - __main__ -   Step: 2844, LR: 2.7889479316131224e-07, Loss: 0.32536813616752625
2024-08-04T23:20:07.725592213Z 
 50%|████▉     | 2845/5712 [6:41:58<6:50:20,  8.59s/it]08/04/2024 16:20:07 - INFO - __main__ -   Step: 2845, LR: 2.787975145309954e-07, Loss: 0.16173020005226135
2024-08-04T23:20:16.431360396Z 
 50%|████▉     | 2846/5712 [6:42:07<6:51:53,  8.62s/it]08/04/2024 16:20:16 - INFO - __main__ -   Step: 2846, LR: 2.787002359006785e-07, Loss: 0.2056390643119812
2024-08-04T23:20:24.522335947Z 
 50%|████▉     | 2847/5712 [6:42:15<6:44:07,  8.46s/it]08/04/2024 16:20:24 - INFO - __main__ -   Step: 2847, LR: 2.786029572703616e-07, Loss: 0.1252775639295578
2024-08-04T23:20:33.396675874Z 
 50%|████▉     | 2848/5712 [6:42:24<6:49:52,  8.59s/it]08/04/2024 16:20:33 - INFO - __main__ -   Step: 2848, LR: 2.7850567864004474e-07, Loss: 0.1903536021709442
2024-08-04T23:20:41.648898580Z 
 50%|████▉     | 2849/5712 [6:42:32<6:44:56,  8.49s/it]08/04/2024 16:20:41 - INFO - __main__ -   Step: 2849, LR: 2.784084000097279e-07, Loss: 0.19364726543426514
2024-08-04T23:20:49.773607202Z 
 50%|████▉     | 2850/5712 [6:42:40<6:39:37,  8.38s/it]08/04/2024 16:20:49 - INFO - __main__ -   Step: 2850, LR: 2.78311121379411e-07, Loss: 0.205516517162323
2024-08-04T23:20:58.779555122Z 
 50%|████▉     | 2851/5712 [6:42:49<6:48:28,  8.57s/it]08/04/2024 16:20:58 - INFO - __main__ -   Step: 2851, LR: 2.782138427490941e-07, Loss: 0.21157804131507874
2024-08-04T23:21:07.702986709Z 
 50%|████▉     | 2852/5712 [6:42:58<6:53:25,  8.67s/it]08/04/2024 16:21:07 - INFO - __main__ -   Step: 2852, LR: 2.781165641187772e-07, Loss: 0.2008635699748993
2024-08-04T23:21:15.966146259Z 
 50%|████▉     | 2853/5712 [6:43:07<6:47:25,  8.55s/it]08/04/2024 16:21:15 - INFO - __main__ -   Step: 2853, LR: 2.7801928548846034e-07, Loss: 0.21389296650886536
2024-08-04T23:21:24.146864148Z 
 50%|████▉     | 2854/5712 [6:43:15<6:41:59,  8.44s/it]08/04/2024 16:21:24 - INFO - __main__ -   Step: 2854, LR: 2.7792200685814344e-07, Loss: 0.10336785018444061
2024-08-04T23:21:32.740330680Z 
 50%|████▉     | 2855/5712 [6:43:23<6:44:03,  8.49s/it]08/04/2024 16:21:32 - INFO - __main__ -   Step: 2855, LR: 2.7782472822782654e-07, Loss: 0.1734326183795929
2024-08-04T23:21:41.166293176Z 
 50%|█████     | 2856/5712 [6:43:32<6:43:03,  8.47s/it]08/04/2024 16:21:41 - INFO - __main__ -   Step: 2856, LR: 2.7772744959750964e-07, Loss: 0.29412904381752014
2024-08-04T23:21:50.093963789Z 
 50%|█████     | 2857/5712 [6:43:41<6:49:29,  8.61s/it]08/04/2024 16:21:50 - INFO - __main__ -   Step: 2857, LR: 2.776301709671928e-07, Loss: 0.13470202684402466
2024-08-04T23:21:58.512388654Z 
 50%|█████     | 2858/5712 [6:43:49<6:46:40,  8.55s/it]08/04/2024 16:21:58 - INFO - __main__ -   Step: 2858, LR: 2.775328923368759e-07, Loss: 0.23374149203300476
2024-08-04T23:22:06.711815729Z 
 50%|█████     | 2859/5712 [6:43:57<6:41:32,  8.44s/it]08/04/2024 16:22:06 - INFO - __main__ -   Step: 2859, LR: 2.77435613706559e-07, Loss: 0.2669670879840851
2024-08-04T23:22:15.498455774Z 
 50%|█████     | 2860/5712 [6:44:06<6:46:15,  8.55s/it]08/04/2024 16:22:15 - INFO - __main__ -   Step: 2860, LR: 2.773383350762421e-07, Loss: 0.2265186607837677
2024-08-04T23:22:24.316848957Z 
 50%|█████     | 2861/5712 [6:44:15<6:50:00,  8.63s/it]08/04/2024 16:22:24 - INFO - __main__ -   Step: 2861, LR: 2.7724105644592524e-07, Loss: 0.12813223898410797
2024-08-04T23:22:32.486366951Z 
 50%|█████     | 2862/5712 [6:44:23<6:43:18,  8.49s/it]08/04/2024 16:22:32 - INFO - __main__ -   Step: 2862, LR: 2.7714377781560834e-07, Loss: 0.12779545783996582
2024-08-04T23:22:41.026513456Z 
 50%|█████     | 2863/5712 [6:44:32<6:43:52,  8.51s/it]08/04/2024 16:22:41 - INFO - __main__ -   Step: 2863, LR: 2.7704649918529144e-07, Loss: 0.15757952630519867
2024-08-04T23:22:49.240954696Z 
 50%|█████     | 2864/5712 [6:44:40<6:39:35,  8.42s/it]08/04/2024 16:22:49 - INFO - __main__ -   Step: 2864, LR: 2.7694922055497454e-07, Loss: 0.23374702036380768
2024-08-04T23:22:57.658939554Z 
 50%|█████     | 2865/5712 [6:44:48<6:39:26,  8.42s/it]08/04/2024 16:22:57 - INFO - __main__ -   Step: 2865, LR: 2.768519419246577e-07, Loss: 0.20271550118923187
2024-08-04T23:23:06.556476656Z 
 50%|█████     | 2866/5712 [6:44:57<6:46:07,  8.56s/it]08/04/2024 16:23:06 - INFO - __main__ -   Step: 2866, LR: 2.7675466329434084e-07, Loss: 0.1888289451599121
2024-08-04T23:23:14.905088525Z 
 50%|█████     | 2867/5712 [6:45:06<6:42:56,  8.50s/it]08/04/2024 16:23:14 - INFO - __main__ -   Step: 2867, LR: 2.7665738466402394e-07, Loss: 0.15977516770362854
2024-08-04T23:23:23.645642304Z 
 50%|█████     | 2868/5712 [6:45:14<6:46:15,  8.57s/it]08/04/2024 16:23:23 - INFO - __main__ -   Step: 2868, LR: 2.7656010603370704e-07, Loss: 0.20577219128608704
2024-08-04T23:23:32.346418671Z 
 50%|█████     | 2869/5712 [6:45:23<6:47:57,  8.61s/it]08/04/2024 16:23:32 - INFO - __main__ -   Step: 2869, LR: 2.764628274033902e-07, Loss: 0.15301206707954407
2024-08-04T23:23:40.516927464Z 
 50%|█████     | 2870/5712 [6:45:31<6:41:34,  8.48s/it]08/04/2024 16:23:40 - INFO - __main__ -   Step: 2870, LR: 2.763655487730733e-07, Loss: 0.21384868025779724
2024-08-04T23:23:49.305032381Z 
 50%|█████     | 2871/5712 [6:45:40<6:45:49,  8.57s/it]08/04/2024 16:23:49 - INFO - __main__ -   Step: 2871, LR: 2.762682701427564e-07, Loss: 0.13811016082763672
2024-08-04T23:23:57.219530976Z 
 50%|█████     | 2872/5712 [6:45:48<6:36:22,  8.37s/it]08/04/2024 16:23:57 - INFO - __main__ -   Step: 2872, LR: 2.761709915124395e-07, Loss: 0.1922181099653244
2024-08-04T23:24:05.672870535Z 
 50%|█████     | 2873/5712 [6:45:56<6:37:21,  8.40s/it]08/04/2024 16:24:05 - INFO - __main__ -   Step: 2873, LR: 2.760737128821226e-07, Loss: 0.2935298979282379
2024-08-04T23:24:14.221444813Z 
 50%|█████     | 2874/5712 [6:46:05<6:39:21,  8.44s/it]08/04/2024 16:24:14 - INFO - __main__ -   Step: 2874, LR: 2.7597643425180574e-07, Loss: 0.14933502674102783
2024-08-04T23:24:22.783095191Z 
 50%|█████     | 2875/5712 [6:46:13<6:40:54,  8.48s/it]08/04/2024 16:24:22 - INFO - __main__ -   Step: 2875, LR: 2.7587915562148884e-07, Loss: 0.25635290145874023
2024-08-04T23:24:31.117468303Z 
 50%|█████     | 2876/5712 [6:46:22<6:38:42,  8.44s/it]08/04/2024 16:24:31 - INFO - __main__ -   Step: 2876, LR: 2.7578187699117194e-07, Loss: 0.19796113669872284
2024-08-04T23:24:40.349066073Z 
 50%|█████     | 2877/5712 [6:46:31<6:49:50,  8.67s/it]08/04/2024 16:24:40 - INFO - __main__ -   Step: 2877, LR: 2.7568459836085504e-07, Loss: 0.15715020895004272
2024-08-04T23:24:48.299242530Z 
 50%|█████     | 2878/5712 [6:46:39<6:39:27,  8.46s/it]08/04/2024 16:24:48 - INFO - __main__ -   Step: 2878, LR: 2.755873197305382e-07, Loss: 0.23217900097370148
2024-08-04T23:24:56.761827467Z 
 50%|█████     | 2879/5712 [6:46:47<6:39:23,  8.46s/it]08/04/2024 16:24:56 - INFO - __main__ -   Step: 2879, LR: 2.754900411002213e-07, Loss: 0.17898321151733398
2024-08-04T23:25:04.952150605Z 
 50%|█████     | 2880/5712 [6:46:56<6:35:27,  8.38s/it]08/04/2024 16:25:04 - INFO - __main__ -   Step: 2880, LR: 2.753927624699044e-07, Loss: 0.2961201071739197
2024-08-04T23:25:12.913397071Z 
 50%|█████     | 2881/5712 [6:47:04<6:29:24,  8.25s/it]08/04/2024 16:25:12 - INFO - __main__ -   Step: 2881, LR: 2.752954838395875e-07, Loss: 0.1877754181623459
2024-08-04T23:25:21.842336109Z 
 50%|█████     | 2882/5712 [6:47:12<6:38:50,  8.46s/it]08/04/2024 16:25:21 - INFO - __main__ -   Step: 2882, LR: 2.7519820520927064e-07, Loss: 0.15514177083969116
2024-08-04T23:25:30.109731885Z 
 50%|█████     | 2883/5712 [6:47:21<6:36:01,  8.40s/it]08/04/2024 16:25:30 - INFO - __main__ -   Step: 2883, LR: 2.7510092657895374e-07, Loss: 0.19752830266952515
2024-08-04T23:25:38.730294696Z 
 50%|█████     | 2884/5712 [6:47:29<6:39:00,  8.47s/it]08/04/2024 16:25:38 - INFO - __main__ -   Step: 2884, LR: 2.750036479486369e-07, Loss: 0.17024752497673035
2024-08-04T23:25:47.938261224Z 
 51%|█████     | 2885/5712 [6:47:39<6:49:22,  8.69s/it]08/04/2024 16:25:47 - INFO - __main__ -   Step: 2885, LR: 2.7490636931832e-07, Loss: 0.1334153413772583
2024-08-04T23:25:56.289350183Z 
 51%|█████     | 2886/5712 [6:47:47<6:44:27,  8.59s/it]08/04/2024 16:25:56 - INFO - __main__ -   Step: 2886, LR: 2.7480909068800314e-07, Loss: 0.1211634948849678
2024-08-04T23:26:04.891547972Z 
 51%|█████     | 2887/5712 [6:47:56<6:44:31,  8.59s/it]08/04/2024 16:26:04 - INFO - __main__ -   Step: 2887, LR: 2.7471181205768624e-07, Loss: 0.1886180341243744
2024-08-04T23:26:13.256359934Z 
 51%|█████     | 2888/5712 [6:48:04<6:41:10,  8.52s/it]08/04/2024 16:26:13 - INFO - __main__ -   Step: 2888, LR: 2.7461453342736934e-07, Loss: 0.18131622672080994
2024-08-04T23:26:21.240210300Z 
 51%|█████     | 2889/5712 [6:48:12<6:33:24,  8.36s/it]08/04/2024 16:26:21 - INFO - __main__ -   Step: 2889, LR: 2.7451725479705244e-07, Loss: 0.13090813159942627
2024-08-04T23:26:29.572248580Z 
 51%|█████     | 2890/5712 [6:48:20<6:32:51,  8.35s/it]08/04/2024 16:26:29 - INFO - __main__ -   Step: 2890, LR: 2.744199761667356e-07, Loss: 0.1372239589691162
2024-08-04T23:26:38.704600991Z 
 51%|█████     | 2891/5712 [6:48:29<6:43:43,  8.59s/it]08/04/2024 16:26:38 - INFO - __main__ -   Step: 2891, LR: 2.743226975364187e-07, Loss: 0.16155952215194702
2024-08-04T23:26:47.224721992Z 
 51%|█████     | 2892/5712 [6:48:38<6:42:38,  8.57s/it]08/04/2024 16:26:47 - INFO - __main__ -   Step: 2892, LR: 2.742254189061018e-07, Loss: 0.26088571548461914
2024-08-04T23:26:55.417653281Z 
 51%|█████     | 2893/5712 [6:48:46<6:37:13,  8.45s/it]08/04/2024 16:26:55 - INFO - __main__ -   Step: 2893, LR: 2.741281402757849e-07, Loss: 0.16353745758533478
2024-08-04T23:27:04.070155360Z 
 51%|█████     | 2894/5712 [6:48:55<6:39:51,  8.51s/it]08/04/2024 16:27:04 - INFO - __main__ -   Step: 2894, LR: 2.7403086164546804e-07, Loss: 0.17431512475013733
2024-08-04T23:27:11.929726653Z 
 51%|█████     | 2895/5712 [6:49:03<6:30:31,  8.32s/it]08/04/2024 16:27:11 - INFO - __main__ -   Step: 2895, LR: 2.7393358301515114e-07, Loss: 0.2076791226863861
2024-08-04T23:27:20.955816911Z 
 51%|█████     | 2896/5712 [6:49:12<6:40:21,  8.53s/it]08/04/2024 16:27:20 - INFO - __main__ -   Step: 2896, LR: 2.7383630438483423e-07, Loss: 0.13816925883293152
2024-08-04T23:27:28.881270232Z 
 51%|█████     | 2897/5712 [6:49:20<6:31:41,  8.35s/it]08/04/2024 16:27:28 - INFO - __main__ -   Step: 2897, LR: 2.7373902575451733e-07, Loss: 0.16239097714424133
2024-08-04T23:27:37.263478180Z 
 51%|█████     | 2898/5712 [6:49:28<6:32:01,  8.36s/it]08/04/2024 16:27:37 - INFO - __main__ -   Step: 2898, LR: 2.736417471242005e-07, Loss: 0.25441768765449524
2024-08-04T23:27:45.895833661Z 
 51%|█████     | 2899/5712 [6:49:37<6:35:44,  8.44s/it]08/04/2024 16:27:45 - INFO - __main__ -   Step: 2899, LR: 2.735444684938836e-07, Loss: 0.1618422269821167
2024-08-04T23:27:54.862950415Z 
 51%|█████     | 2900/5712 [6:49:46<6:42:59,  8.60s/it]08/04/2024 16:27:54 - INFO - __main__ -   Step: 2900, LR: 2.734471898635667e-07, Loss: 0.09013892710208893
2024-08-04T23:28:02.941289177Z 
 51%|█████     | 2901/5712 [6:49:54<6:35:32,  8.44s/it]08/04/2024 16:28:02 - INFO - __main__ -   Step: 2901, LR: 2.733499112332498e-07, Loss: 0.14746946096420288
2024-08-04T23:28:11.586935874Z 
 51%|█████     | 2902/5712 [6:50:02<6:38:15,  8.50s/it]08/04/2024 16:28:11 - INFO - __main__ -   Step: 2902, LR: 2.73252632602933e-07, Loss: 0.31163302063941956
2024-08-04T23:28:19.500180029Z 
 51%|█████     | 2903/5712 [6:50:10<6:29:48,  8.33s/it]08/04/2024 16:28:19 - INFO - __main__ -   Step: 2903, LR: 2.731553539726161e-07, Loss: 0.19992634654045105
2024-08-04T23:28:28.356426946Z 
 51%|█████     | 2904/5712 [6:50:19<6:37:06,  8.49s/it]08/04/2024 16:28:28 - INFO - __main__ -   Step: 2904, LR: 2.730580753422992e-07, Loss: 0.1846207231283188
2024-08-04T23:28:36.894184727Z 
 51%|█████     | 2905/5712 [6:50:28<6:37:42,  8.50s/it]08/04/2024 16:28:36 - INFO - __main__ -   Step: 2905, LR: 2.729607967119823e-07, Loss: 0.23042233288288116
2024-08-04T23:28:45.113636625Z 
 51%|█████     | 2906/5712 [6:50:36<6:33:36,  8.42s/it]08/04/2024 16:28:45 - INFO - __main__ -   Step: 2906, LR: 2.7286351808166544e-07, Loss: 0.1689455360174179
2024-08-04T23:28:53.604999088Z 
 51%|█████     | 2907/5712 [6:50:44<6:34:31,  8.44s/it]08/04/2024 16:28:53 - INFO - __main__ -   Step: 2907, LR: 2.7276623945134854e-07, Loss: 0.18148040771484375
2024-08-04T23:29:02.193337219Z 
 51%|█████     | 2908/5712 [6:50:53<6:36:28,  8.48s/it]08/04/2024 16:29:02 - INFO - __main__ -   Step: 2908, LR: 2.7266896082103163e-07, Loss: 0.2257409691810608
2024-08-04T23:29:10.593471566Z 
 51%|█████     | 2909/5712 [6:51:01<6:35:09,  8.46s/it]08/04/2024 16:29:10 - INFO - __main__ -   Step: 2909, LR: 2.7257168219071473e-07, Loss: 0.25371015071868896
2024-08-04T23:29:19.448857018Z 
 51%|█████     | 2910/5712 [6:51:10<6:40:34,  8.58s/it]08/04/2024 16:29:19 - INFO - __main__ -   Step: 2910, LR: 2.7247440356039783e-07, Loss: 0.11757618188858032
2024-08-04T23:29:28.119884616Z 
 51%|█████     | 2911/5712 [6:51:19<6:41:43,  8.61s/it]08/04/2024 16:29:28 - INFO - __main__ -   Step: 2911, LR: 2.72377124930081e-07, Loss: 0.1250942349433899
2024-08-04T23:29:36.335179488Z 
 51%|█████     | 2912/5712 [6:51:27<6:36:08,  8.49s/it]08/04/2024 16:29:36 - INFO - __main__ -   Step: 2912, LR: 2.722798462997641e-07, Loss: 0.19872722029685974
2024-08-04T23:29:45.056808371Z 
 51%|█████     | 2913/5712 [6:51:36<6:39:15,  8.56s/it]08/04/2024 16:29:45 - INFO - __main__ -   Step: 2913, LR: 2.721825676694472e-07, Loss: 0.11939776688814163
2024-08-04T23:29:53.006509183Z 
 51%|█████     | 2914/5712 [6:51:44<6:30:35,  8.38s/it]08/04/2024 16:29:53 - INFO - __main__ -   Step: 2914, LR: 2.720852890391303e-07, Loss: 0.13749447464942932
2024-08-04T23:30:02.028079557Z 
 51%|█████     | 2915/5712 [6:51:53<6:39:29,  8.57s/it]08/04/2024 16:30:02 - INFO - __main__ -   Step: 2915, LR: 2.7198801040881343e-07, Loss: 0.18057416379451752
2024-08-04T23:30:10.752547461Z 
 51%|█████     | 2916/5712 [6:52:01<6:41:30,  8.62s/it]08/04/2024 16:30:10 - INFO - __main__ -   Step: 2916, LR: 2.7189073177849653e-07, Loss: 0.1161101758480072
2024-08-04T23:30:19.373373280Z 
 51%|█████     | 2917/5712 [6:52:10<6:41:26,  8.62s/it]08/04/2024 16:30:19 - INFO - __main__ -   Step: 2917, LR: 2.7179345314817963e-07, Loss: 0.17578600347042084
2024-08-04T23:30:28.164732945Z 
 51%|█████     | 2918/5712 [6:52:19<6:43:43,  8.67s/it]08/04/2024 16:30:28 - INFO - __main__ -   Step: 2918, LR: 2.7169617451786273e-07, Loss: 0.1450813263654709
2024-08-04T23:30:36.641637749Z 
 51%|█████     | 2919/5712 [6:52:27<6:40:52,  8.61s/it]08/04/2024 16:30:36 - INFO - __main__ -   Step: 2919, LR: 2.715988958875459e-07, Loss: 0.2666552662849426
2024-08-04T23:30:44.611821176Z 
 51%|█████     | 2920/5712 [6:52:35<6:31:46,  8.42s/it]08/04/2024 16:30:44 - INFO - __main__ -   Step: 2920, LR: 2.7150161725722904e-07, Loss: 0.1332966834306717
2024-08-04T23:30:53.272852643Z 
 51%|█████     | 2921/5712 [6:52:44<6:35:00,  8.49s/it]08/04/2024 16:30:53 - INFO - __main__ -   Step: 2921, LR: 2.7140433862691213e-07, Loss: 0.12205487489700317
2024-08-04T23:31:01.771071918Z 
 51%|█████     | 2922/5712 [6:52:52<6:34:57,  8.49s/it]08/04/2024 16:31:01 - INFO - __main__ -   Step: 2922, LR: 2.7130705999659523e-07, Loss: 0.2906305193901062
2024-08-04T23:31:10.428596228Z 
 51%|█████     | 2923/5712 [6:53:01<6:37:05,  8.54s/it]08/04/2024 16:31:10 - INFO - __main__ -   Step: 2923, LR: 2.712097813662784e-07, Loss: 0.26387542486190796
2024-08-04T23:31:19.181872533Z 
 51%|█████     | 2924/5712 [6:53:10<6:39:53,  8.61s/it]08/04/2024 16:31:19 - INFO - __main__ -   Step: 2924, LR: 2.711125027359615e-07, Loss: 0.16776685416698456
2024-08-04T23:31:27.668169925Z 
 51%|█████     | 2925/5712 [6:53:18<6:38:04,  8.57s/it]08/04/2024 16:31:27 - INFO - __main__ -   Step: 2925, LR: 2.710152241056446e-07, Loss: 0.14037683606147766
2024-08-04T23:31:36.257264908Z 
 51%|█████     | 2926/5712 [6:53:27<6:38:12,  8.58s/it]08/04/2024 16:31:36 - INFO - __main__ -   Step: 2926, LR: 2.709179454753277e-07, Loss: 0.13131749629974365
2024-08-04T23:31:44.400766064Z 
 51%|█████     | 2927/5712 [6:53:35<6:32:02,  8.45s/it]08/04/2024 16:31:44 - INFO - __main__ -   Step: 2927, LR: 2.7082066684501083e-07, Loss: 0.3376026749610901
2024-08-04T23:31:53.181856065Z 
 51%|█████▏    | 2928/5712 [6:53:44<6:36:32,  8.55s/it]08/04/2024 16:31:53 - INFO - __main__ -   Step: 2928, LR: 2.7072338821469393e-07, Loss: 0.30262523889541626
2024-08-04T23:32:02.221827813Z 
 51%|█████▏    | 2929/5712 [6:53:53<6:43:17,  8.69s/it]08/04/2024 16:32:02 - INFO - __main__ -   Step: 2929, LR: 2.7062610958437703e-07, Loss: 0.10096530616283417
2024-08-04T23:32:10.529068787Z 
 51%|█████▏    | 2930/5712 [6:54:01<6:37:45,  8.58s/it]08/04/2024 16:32:10 - INFO - __main__ -   Step: 2930, LR: 2.7052883095406013e-07, Loss: 0.18154552578926086
2024-08-04T23:32:18.751031536Z 
 51%|█████▏    | 2931/5712 [6:54:09<6:32:38,  8.47s/it]08/04/2024 16:32:18 - INFO - __main__ -   Step: 2931, LR: 2.704315523237433e-07, Loss: 0.2217159867286682
2024-08-04T23:32:27.082557697Z 
 51%|█████▏    | 2932/5712 [6:54:18<6:30:34,  8.43s/it]08/04/2024 16:32:27 - INFO - __main__ -   Step: 2932, LR: 2.703342736934264e-07, Loss: 0.19998903572559357
2024-08-04T23:32:36.112302219Z 
 51%|█████▏    | 2933/5712 [6:54:27<6:38:46,  8.61s/it]08/04/2024 16:32:36 - INFO - __main__ -   Step: 2933, LR: 2.702369950631095e-07, Loss: 0.0974944606423378
2024-08-04T23:32:44.230121702Z 
 51%|█████▏    | 2934/5712 [6:54:35<6:31:47,  8.46s/it]08/04/2024 16:32:44 - INFO - __main__ -   Step: 2934, LR: 2.701397164327926e-07, Loss: 0.2938148081302643
2024-08-04T23:32:52.448662730Z 
 51%|█████▏    | 2935/5712 [6:54:43<6:28:16,  8.39s/it]08/04/2024 16:32:52 - INFO - __main__ -   Step: 2935, LR: 2.7004243780247573e-07, Loss: 0.151652529835701
2024-08-04T23:33:01.469056831Z 
 51%|█████▏    | 2936/5712 [6:54:52<6:36:53,  8.58s/it]08/04/2024 16:33:01 - INFO - __main__ -   Step: 2936, LR: 2.6994515917215883e-07, Loss: 0.12242984026670456
2024-08-04T23:33:09.748052979Z 
 51%|█████▏    | 2937/5712 [6:55:00<6:32:35,  8.49s/it]08/04/2024 16:33:09 - INFO - __main__ -   Step: 2937, LR: 2.6984788054184193e-07, Loss: 0.18963417410850525
2024-08-04T23:33:18.401369607Z 
 51%|█████▏    | 2938/5712 [6:55:09<6:34:44,  8.54s/it]08/04/2024 16:33:18 - INFO - __main__ -   Step: 2938, LR: 2.697506019115251e-07, Loss: 0.13755559921264648
2024-08-04T23:33:26.625233942Z 
 51%|█████▏    | 2939/5712 [6:55:17<6:30:14,  8.44s/it]08/04/2024 16:33:26 - INFO - __main__ -   Step: 2939, LR: 2.6965332328120823e-07, Loss: 0.18422195315361023
2024-08-04T23:33:35.427441850Z 
 51%|█████▏    | 2940/5712 [6:55:26<6:35:04,  8.55s/it]08/04/2024 16:33:35 - INFO - __main__ -   Step: 2940, LR: 2.6955604465089133e-07, Loss: 0.1481732726097107
2024-08-04T23:33:43.700017276Z 
 51%|█████▏    | 2941/5712 [6:55:34<6:31:03,  8.47s/it]08/04/2024 16:33:43 - INFO - __main__ -   Step: 2941, LR: 2.6945876602057443e-07, Loss: 0.15157821774482727
2024-08-04T23:33:51.927067594Z 
 52%|█████▏    | 2942/5712 [6:55:43<6:27:35,  8.40s/it]08/04/2024 16:33:51 - INFO - __main__ -   Step: 2942, LR: 2.6936148739025753e-07, Loss: 0.19002582132816315
2024-08-04T23:34:00.076819036Z 
 52%|█████▏    | 2943/5712 [6:55:51<6:24:02,  8.32s/it]08/04/2024 16:34:00 - INFO - __main__ -   Step: 2943, LR: 2.692642087599407e-07, Loss: 0.1944257915019989
2024-08-04T23:34:08.328054721Z 
 52%|█████▏    | 2944/5712 [6:55:59<6:22:56,  8.30s/it]08/04/2024 16:34:08 - INFO - __main__ -   Step: 2944, LR: 2.691669301296238e-07, Loss: 0.22458940744400024
2024-08-04T23:34:17.360202824Z 
 52%|█████▏    | 2945/5712 [6:56:08<6:32:53,  8.52s/it]08/04/2024 16:34:17 - INFO - __main__ -   Step: 2945, LR: 2.690696514993069e-07, Loss: 0.2770885229110718
2024-08-04T23:34:26.087418081Z 
 52%|█████▏    | 2946/5712 [6:56:17<6:35:38,  8.58s/it]08/04/2024 16:34:26 - INFO - __main__ -   Step: 2946, LR: 2.6897237286899e-07, Loss: 0.24051503837108612
2024-08-04T23:34:34.729187718Z 
 52%|█████▏    | 2947/5712 [6:56:25<6:36:19,  8.60s/it]08/04/2024 16:34:34 - INFO - __main__ -   Step: 2947, LR: 2.688750942386731e-07, Loss: 0.23069819808006287
2024-08-04T23:34:42.905539834Z 
 52%|█████▏    | 2948/5712 [6:56:34<6:30:19,  8.47s/it]08/04/2024 16:34:42 - INFO - __main__ -   Step: 2948, LR: 2.6877781560835623e-07, Loss: 0.18481498956680298
2024-08-04T23:34:51.841146040Z 
 52%|█████▏    | 2949/5712 [6:56:42<6:36:34,  8.61s/it]08/04/2024 16:34:51 - INFO - __main__ -   Step: 2949, LR: 2.6868053697803933e-07, Loss: 0.26336002349853516
2024-08-04T23:35:00.227233950Z 
 52%|█████▏    | 2950/5712 [6:56:51<6:33:18,  8.54s/it]08/04/2024 16:35:00 - INFO - __main__ -   Step: 2950, LR: 2.6858325834772243e-07, Loss: 0.24764496088027954
2024-08-04T23:35:08.561334557Z 
 52%|█████▏    | 2951/5712 [6:56:59<6:30:16,  8.48s/it]08/04/2024 16:35:08 - INFO - __main__ -   Step: 2951, LR: 2.6848597971740553e-07, Loss: 0.2568625509738922
2024-08-04T23:35:16.780972722Z 
 52%|█████▏    | 2952/5712 [6:57:07<6:26:31,  8.40s/it]08/04/2024 16:35:16 - INFO - __main__ -   Step: 2952, LR: 2.683887010870887e-07, Loss: 0.12250968813896179
2024-08-04T23:35:25.762777892Z 
 52%|█████▏    | 2953/5712 [6:57:16<6:34:22,  8.58s/it]08/04/2024 16:35:25 - INFO - __main__ -   Step: 2953, LR: 2.682914224567718e-07, Loss: 0.1647457480430603
2024-08-04T23:35:34.548144478Z 
 52%|█████▏    | 2954/5712 [6:57:25<6:37:06,  8.64s/it]08/04/2024 16:35:34 - INFO - __main__ -   Step: 2954, LR: 2.681941438264549e-07, Loss: 0.16706790030002594
2024-08-04T23:35:42.756720539Z 
 52%|█████▏    | 2955/5712 [6:57:33<6:31:01,  8.51s/it]08/04/2024 16:35:42 - INFO - __main__ -   Step: 2955, LR: 2.68096865196138e-07, Loss: 0.13355112075805664
2024-08-04T23:35:51.016861543Z 
 52%|█████▏    | 2956/5712 [6:57:42<6:27:26,  8.43s/it]08/04/2024 16:35:51 - INFO - __main__ -   Step: 2956, LR: 2.679995865658212e-07, Loss: 0.15662714838981628
2024-08-04T23:35:59.756857060Z 
 52%|█████▏    | 2957/5712 [6:57:50<6:31:30,  8.53s/it]08/04/2024 16:35:59 - INFO - __main__ -   Step: 2957, LR: 2.679023079355043e-07, Loss: 0.12195900827646255
2024-08-04T23:36:08.012757173Z 
 52%|█████▏    | 2958/5712 [6:57:59<6:27:38,  8.45s/it]08/04/2024 16:36:08 - INFO - __main__ -   Step: 2958, LR: 2.678050293051874e-07, Loss: 0.14748528599739075
2024-08-04T23:36:16.612257366Z 
 52%|█████▏    | 2959/5712 [6:58:07<6:29:37,  8.49s/it]08/04/2024 16:36:16 - INFO - __main__ -   Step: 2959, LR: 2.677077506748705e-07, Loss: 0.10716922581195831
2024-08-04T23:36:24.958044487Z 
 52%|█████▏    | 2960/5712 [6:58:16<6:27:28,  8.45s/it]08/04/2024 16:36:24 - INFO - __main__ -   Step: 2960, LR: 2.6761047204455363e-07, Loss: 0.32838281989097595
2024-08-04T23:36:33.433492360Z 
 52%|█████▏    | 2961/5712 [6:58:24<6:27:42,  8.46s/it]08/04/2024 16:36:33 - INFO - __main__ -   Step: 2961, LR: 2.6751319341423673e-07, Loss: 0.1852351725101471
2024-08-04T23:36:42.228989499Z 
 52%|█████▏    | 2962/5712 [6:58:33<6:32:13,  8.56s/it]08/04/2024 16:36:42 - INFO - __main__ -   Step: 2962, LR: 2.6741591478391983e-07, Loss: 0.2566271424293518
2024-08-04T23:36:50.702066881Z 
 52%|█████▏    | 2963/5712 [6:58:41<6:30:56,  8.53s/it]08/04/2024 16:36:50 - INFO - __main__ -   Step: 2963, LR: 2.6731863615360293e-07, Loss: 0.15766456723213196
2024-08-04T23:36:59.310793139Z 
 52%|█████▏    | 2964/5712 [6:58:50<6:31:50,  8.56s/it]08/04/2024 16:36:59 - INFO - __main__ -   Step: 2964, LR: 2.672213575232861e-07, Loss: 0.22669823467731476
2024-08-04T23:37:07.373172564Z 
 52%|█████▏    | 2965/5712 [6:58:58<6:24:55,  8.41s/it]08/04/2024 16:37:07 - INFO - __main__ -   Step: 2965, LR: 2.671240788929692e-07, Loss: 0.21776080131530762
2024-08-04T23:37:16.092990643Z 
 52%|█████▏    | 2966/5712 [6:59:07<6:29:04,  8.50s/it]08/04/2024 16:37:16 - INFO - __main__ -   Step: 2966, LR: 2.670268002626523e-07, Loss: 0.2490820288658142
2024-08-04T23:37:24.261320275Z 
 52%|█████▏    | 2967/5712 [6:59:15<6:24:21,  8.40s/it]08/04/2024 16:37:24 - INFO - __main__ -   Step: 2967, LR: 2.669295216323354e-07, Loss: 0.16195572912693024
2024-08-04T23:37:32.449997230Z 
 52%|█████▏    | 2968/5712 [6:59:23<6:21:18,  8.34s/it]08/04/2024 16:37:32 - INFO - __main__ -   Step: 2968, LR: 2.6683224300201853e-07, Loss: 0.23128437995910645
2024-08-04T23:37:40.749294632Z 
 52%|█████▏    | 2969/5712 [6:59:31<6:20:38,  8.33s/it]08/04/2024 16:37:40 - INFO - __main__ -   Step: 2969, LR: 2.6673496437170163e-07, Loss: 0.16606414318084717
2024-08-04T23:37:49.659159238Z 
 52%|█████▏    | 2970/5712 [6:59:40<6:28:30,  8.50s/it]08/04/2024 16:37:49 - INFO - __main__ -   Step: 2970, LR: 2.6663768574138473e-07, Loss: 0.39806103706359863
2024-08-04T23:37:58.154933946Z 
 52%|█████▏    | 2971/5712 [6:59:49<6:28:17,  8.50s/it]08/04/2024 16:37:58 - INFO - __main__ -   Step: 2971, LR: 2.6654040711106783e-07, Loss: 0.2738819420337677
2024-08-04T23:38:06.466120367Z 
 52%|█████▏    | 2972/5712 [6:59:57<6:25:33,  8.44s/it]08/04/2024 16:38:06 - INFO - __main__ -   Step: 2972, LR: 2.66443128480751e-07, Loss: 0.19753530621528625
2024-08-04T23:38:14.831802055Z 
 52%|█████▏    | 2973/5712 [7:00:05<6:24:21,  8.42s/it]08/04/2024 16:38:14 - INFO - __main__ -   Step: 2973, LR: 2.663458498504341e-07, Loss: 0.2665077745914459
2024-08-04T23:38:23.022759004Z 
 52%|█████▏    | 2974/5712 [7:00:14<6:21:05,  8.35s/it]08/04/2024 16:38:23 - INFO - __main__ -   Step: 2974, LR: 2.6624857122011723e-07, Loss: 0.16924317181110382
2024-08-04T23:38:31.203692155Z 
 52%|█████▏    | 2975/5712 [7:00:22<6:18:37,  8.30s/it]08/04/2024 16:38:31 - INFO - __main__ -   Step: 2975, LR: 2.6615129258980033e-07, Loss: 0.12140053510665894
2024-08-04T23:38:39.594959627Z 
 52%|█████▏    | 2976/5712 [7:00:30<6:19:44,  8.33s/it]08/04/2024 16:38:39 - INFO - __main__ -   Step: 2976, LR: 2.660540139594835e-07, Loss: 0.1721501350402832
2024-08-04T23:38:48.327228381Z 
 52%|█████▏    | 2977/5712 [7:00:39<6:25:07,  8.45s/it]08/04/2024 16:38:48 - INFO - __main__ -   Step: 2977, LR: 2.659567353291666e-07, Loss: 0.1559174656867981
2024-08-04T23:38:57.043732728Z 
 52%|█████▏    | 2978/5712 [7:00:48<6:28:38,  8.53s/it]08/04/2024 16:38:57 - INFO - __main__ -   Step: 2978, LR: 2.658594566988497e-07, Loss: 0.14079079031944275
2024-08-04T23:39:06.272764796Z 
 52%|█████▏    | 2979/5712 [7:00:57<6:38:03,  8.74s/it]08/04/2024 16:39:06 - INFO - __main__ -   Step: 2979, LR: 2.657621780685328e-07, Loss: 0.12312158197164536
2024-08-04T23:39:14.475687555Z 
 52%|█████▏    | 2980/5712 [7:01:05<6:30:36,  8.58s/it]08/04/2024 16:39:14 - INFO - __main__ -   Step: 2980, LR: 2.6566489943821593e-07, Loss: 0.33308613300323486
2024-08-04T23:39:23.008054845Z 
 52%|█████▏    | 2981/5712 [7:01:14<6:29:49,  8.56s/it]08/04/2024 16:39:23 - INFO - __main__ -   Step: 2981, LR: 2.6556762080789903e-07, Loss: 0.16912737488746643
2024-08-04T23:39:31.741140427Z 
 52%|█████▏    | 2982/5712 [7:01:22<6:31:59,  8.62s/it]08/04/2024 16:39:31 - INFO - __main__ -   Step: 2982, LR: 2.6547034217758213e-07, Loss: 0.19929245114326477
2024-08-04T23:39:40.058873339Z 
 52%|█████▏    | 2983/5712 [7:01:31<6:27:47,  8.53s/it]08/04/2024 16:39:40 - INFO - __main__ -   Step: 2983, LR: 2.6537306354726523e-07, Loss: 0.13977564871311188
2024-08-04T23:39:48.263750100Z 
 52%|█████▏    | 2984/5712 [7:01:39<6:23:15,  8.43s/it]08/04/2024 16:39:48 - INFO - __main__ -   Step: 2984, LR: 2.6527578491694833e-07, Loss: 0.27602624893188477
2024-08-04T23:39:57.012905461Z 
 52%|█████▏    | 2985/5712 [7:01:48<6:27:29,  8.53s/it]08/04/2024 16:39:57 - INFO - __main__ -   Step: 2985, LR: 2.651785062866315e-07, Loss: 0.12159285694360733
2024-08-04T23:40:05.045668626Z 
 52%|█████▏    | 2986/5712 [7:01:56<6:20:37,  8.38s/it]08/04/2024 16:40:05 - INFO - __main__ -   Step: 2986, LR: 2.650812276563146e-07, Loss: 0.1992563009262085
2024-08-04T23:40:13.890923343Z 
 52%|█████▏    | 2987/5712 [7:02:05<6:26:50,  8.52s/it]08/04/2024 16:40:13 - INFO - __main__ -   Step: 2987, LR: 2.649839490259977e-07, Loss: 0.1517239660024643
2024-08-04T23:40:22.342231205Z 
 52%|█████▏    | 2988/5712 [7:02:13<6:25:48,  8.50s/it]08/04/2024 16:40:22 - INFO - __main__ -   Step: 2988, LR: 2.648866703956808e-07, Loss: 0.268817663192749
2024-08-04T23:40:31.375053147Z 
 52%|█████▏    | 2989/5712 [7:02:22<6:32:56,  8.66s/it]08/04/2024 16:40:31 - INFO - __main__ -   Step: 2989, LR: 2.6478939176536393e-07, Loss: 0.11690983176231384
2024-08-04T23:40:39.822930500Z 
 52%|█████▏    | 2990/5712 [7:02:30<6:29:56,  8.60s/it]08/04/2024 16:40:39 - INFO - __main__ -   Step: 2990, LR: 2.6469211313504703e-07, Loss: 0.2234364002943039
2024-08-04T23:40:48.689973842Z 
 52%|█████▏    | 2991/5712 [7:02:39<6:33:29,  8.68s/it]08/04/2024 16:40:48 - INFO - __main__ -   Step: 2991, LR: 2.645948345047301e-07, Loss: 0.20440024137496948
2024-08-04T23:40:56.643777356Z 
 52%|█████▏    | 2992/5712 [7:02:47<6:23:30,  8.46s/it]08/04/2024 16:40:56 - INFO - __main__ -   Step: 2992, LR: 2.644975558744133e-07, Loss: 0.25483304262161255
2024-08-04T23:41:05.045464895Z 
 52%|█████▏    | 2993/5712 [7:02:56<6:22:35,  8.44s/it]08/04/2024 16:41:05 - INFO - __main__ -   Step: 2993, LR: 2.6440027724409643e-07, Loss: 0.29286372661590576
2024-08-04T23:41:13.331451636Z 
 52%|█████▏    | 2994/5712 [7:03:04<6:20:18,  8.40s/it]08/04/2024 16:41:13 - INFO - __main__ -   Step: 2994, LR: 2.6430299861377953e-07, Loss: 0.19708457589149475
2024-08-04T23:41:21.780710929Z 
 52%|█████▏    | 2995/5712 [7:03:12<6:20:54,  8.41s/it]08/04/2024 16:41:21 - INFO - __main__ -   Step: 2995, LR: 2.6420571998346263e-07, Loss: 0.28085869550704956
2024-08-04T23:41:30.527622012Z 
 52%|█████▏    | 2996/5712 [7:03:21<6:25:17,  8.51s/it]08/04/2024 16:41:30 - INFO - __main__ -   Step: 2996, LR: 2.6410844135314573e-07, Loss: 0.18292589485645294
2024-08-04T23:41:38.939780530Z 
 52%|█████▏    | 2997/5712 [7:03:30<6:23:49,  8.48s/it]08/04/2024 16:41:38 - INFO - __main__ -   Step: 2997, LR: 2.640111627228289e-07, Loss: 0.23815813660621643
2024-08-04T23:41:47.601242721Z 
 52%|█████▏    | 2998/5712 [7:03:38<6:26:07,  8.54s/it]08/04/2024 16:41:47 - INFO - __main__ -   Step: 2998, LR: 2.63913884092512e-07, Loss: 0.18004682660102844
2024-08-04T23:41:55.787738428Z 
 53%|█████▎    | 2999/5712 [7:03:46<6:21:13,  8.43s/it]08/04/2024 16:41:55 - INFO - __main__ -   Step: 2999, LR: 2.638166054621951e-07, Loss: 0.1428384631872177
2024-08-04T23:42:04.297383855Z 
 53%|█████▎    | 3000/5712 [7:03:55<6:22:09,  8.45s/it]08/04/2024 16:42:04 - INFO - __main__ -   Step: 3000, LR: 2.637193268318782e-07, Loss: 0.14214098453521729
2024-08-04T23:42:12.906375593Z 
 53%|█████▎    | 3001/5712 [7:04:04<6:24:06,  8.50s/it]08/04/2024 16:42:12 - INFO - __main__ -   Step: 3001, LR: 2.6362204820156133e-07, Loss: 0.1490512490272522
2024-08-04T23:42:21.443403660Z 
 53%|█████▎    | 3002/5712 [7:04:12<6:24:27,  8.51s/it]08/04/2024 16:42:21 - INFO - __main__ -   Step: 3002, LR: 2.6352476957124443e-07, Loss: 0.08645102381706238
2024-08-04T23:42:30.096539575Z 
 53%|█████▎    | 3003/5712 [7:04:21<6:26:10,  8.55s/it]08/04/2024 16:42:30 - INFO - __main__ -   Step: 3003, LR: 2.6342749094092753e-07, Loss: 0.2123059779405594
2024-08-04T23:42:38.592497829Z 
 53%|█████▎    | 3004/5712 [7:04:29<6:25:18,  8.54s/it]08/04/2024 16:42:38 - INFO - __main__ -   Step: 3004, LR: 2.633302123106106e-07, Loss: 0.14710122346878052
2024-08-04T23:42:46.952686185Z 
 53%|█████▎    | 3005/5712 [7:04:38<6:22:45,  8.48s/it]08/04/2024 16:42:46 - INFO - __main__ -   Step: 3005, LR: 2.632329336802938e-07, Loss: 0.24742621183395386
2024-08-04T23:42:55.482109218Z 
 53%|█████▎    | 3006/5712 [7:04:46<6:23:14,  8.50s/it]08/04/2024 16:42:55 - INFO - __main__ -   Step: 3006, LR: 2.631356550499769e-07, Loss: 0.23598064482212067
2024-08-04T23:43:03.861386378Z 
 53%|█████▎    | 3007/5712 [7:04:55<6:21:30,  8.46s/it]08/04/2024 16:43:03 - INFO - __main__ -   Step: 3007, LR: 2.6303837641966e-07, Loss: 0.1264445185661316
2024-08-04T23:43:12.092786841Z 
 53%|█████▎    | 3008/5712 [7:05:03<6:18:13,  8.39s/it]08/04/2024 16:43:12 - INFO - __main__ -   Step: 3008, LR: 2.629410977893431e-07, Loss: 0.23697683215141296
2024-08-04T23:43:20.189303320Z 
 53%|█████▎    | 3009/5712 [7:05:11<6:14:05,  8.30s/it]08/04/2024 16:43:20 - INFO - __main__ -   Step: 3009, LR: 2.6284381915902623e-07, Loss: 0.2002667784690857
2024-08-04T23:43:28.422103356Z 
 53%|█████▎    | 3010/5712 [7:05:19<6:12:59,  8.28s/it]08/04/2024 16:43:28 - INFO - __main__ -   Step: 3010, LR: 2.627465405287094e-07, Loss: 0.15632131695747375
2024-08-04T23:43:36.909872474Z 
 53%|█████▎    | 3011/5712 [7:05:28<6:15:37,  8.34s/it]08/04/2024 16:43:36 - INFO - __main__ -   Step: 3011, LR: 2.626492618983925e-07, Loss: 0.1632789522409439
2024-08-04T23:43:45.728260861Z 
 53%|█████▎    | 3012/5712 [7:05:36<6:21:53,  8.49s/it]08/04/2024 16:43:45 - INFO - __main__ -   Step: 3012, LR: 2.625519832680756e-07, Loss: 0.18397822976112366
2024-08-04T23:43:54.777812343Z 
 53%|█████▎    | 3013/5712 [7:05:45<6:29:20,  8.66s/it]08/04/2024 16:43:54 - INFO - __main__ -   Step: 3013, LR: 2.6245470463775873e-07, Loss: 0.1891741007566452
2024-08-04T23:44:03.538079680Z 
 53%|█████▎    | 3014/5712 [7:05:54<6:30:37,  8.69s/it]08/04/2024 16:44:03 - INFO - __main__ -   Step: 3014, LR: 2.6235742600744183e-07, Loss: 0.128008171916008
2024-08-04T23:44:11.702854576Z 
 53%|█████▎    | 3015/5712 [7:06:02<6:23:26,  8.53s/it]08/04/2024 16:44:11 - INFO - __main__ -   Step: 3015, LR: 2.6226014737712493e-07, Loss: 0.1622035950422287
2024-08-04T23:44:20.004819469Z 
 53%|█████▎    | 3016/5712 [7:06:11<6:20:13,  8.46s/it]08/04/2024 16:44:20 - INFO - __main__ -   Step: 3016, LR: 2.62162868746808e-07, Loss: 0.19147327542304993
2024-08-04T23:44:28.216241786Z 
 53%|█████▎    | 3017/5712 [7:06:19<6:16:42,  8.39s/it]08/04/2024 16:44:28 - INFO - __main__ -   Step: 3017, LR: 2.620655901164912e-07, Loss: 0.1491483598947525
2024-08-04T23:44:36.353647382Z 
 53%|█████▎    | 3018/5712 [7:06:27<6:13:12,  8.31s/it]08/04/2024 16:44:36 - INFO - __main__ -   Step: 3018, LR: 2.619683114861743e-07, Loss: 0.2239523082971573
2024-08-04T23:44:44.617195203Z 
 53%|█████▎    | 3019/5712 [7:06:35<6:12:24,  8.30s/it]08/04/2024 16:44:44 - INFO - __main__ -   Step: 3019, LR: 2.618710328558574e-07, Loss: 0.13999445736408234
2024-08-04T23:44:53.796632943Z 
 53%|█████▎    | 3020/5712 [7:06:44<6:24:08,  8.56s/it]08/04/2024 16:44:53 - INFO - __main__ -   Step: 3020, LR: 2.617737542255405e-07, Loss: 0.142698734998703
2024-08-04T23:45:02.631134819Z 
 53%|█████▎    | 3021/5712 [7:06:53<6:27:40,  8.64s/it]08/04/2024 16:45:02 - INFO - __main__ -   Step: 3021, LR: 2.616764755952236e-07, Loss: 0.20901799201965332
2024-08-04T23:45:11.504425778Z 
 53%|█████▎    | 3022/5712 [7:07:02<6:30:37,  8.71s/it]08/04/2024 16:45:11 - INFO - __main__ -   Step: 3022, LR: 2.615791969649067e-07, Loss: 0.17226441204547882
2024-08-04T23:45:19.774671222Z 
 53%|█████▎    | 3023/5712 [7:07:10<6:24:31,  8.58s/it]08/04/2024 16:45:19 - INFO - __main__ -   Step: 3023, LR: 2.614819183345898e-07, Loss: 0.10453128814697266
2024-08-04T23:45:28.057743061Z 
 53%|█████▎    | 3024/5712 [7:07:19<6:20:23,  8.49s/it]08/04/2024 16:45:28 - INFO - __main__ -   Step: 3024, LR: 2.613846397042729e-07, Loss: 0.3206912577152252
2024-08-04T23:45:36.287462462Z 
 53%|█████▎    | 3025/5712 [7:07:27<6:16:44,  8.41s/it]08/04/2024 16:45:36 - INFO - __main__ -   Step: 3025, LR: 2.61287361073956e-07, Loss: 0.19486898183822632
2024-08-04T23:45:44.565210371Z 
 53%|█████▎    | 3026/5712 [7:07:35<6:14:47,  8.37s/it]08/04/2024 16:45:44 - INFO - __main__ -   Step: 3026, LR: 2.611900824436392e-07, Loss: 0.21522197127342224
2024-08-04T23:45:52.734791728Z 
 53%|█████▎    | 3027/5712 [7:07:43<6:11:55,  8.31s/it]08/04/2024 16:45:52 - INFO - __main__ -   Step: 3027, LR: 2.610928038133223e-07, Loss: 0.218617781996727
2024-08-04T23:46:00.930069535Z 
 53%|█████▎    | 3028/5712 [7:07:52<6:10:14,  8.28s/it]08/04/2024 16:46:00 - INFO - __main__ -   Step: 3028, LR: 2.609955251830054e-07, Loss: 0.18471543490886688
2024-08-04T23:46:09.561773275Z 
 53%|█████▎    | 3029/5712 [7:08:00<6:14:51,  8.38s/it]08/04/2024 16:46:09 - INFO - __main__ -   Step: 3029, LR: 2.608982465526885e-07, Loss: 0.1777818202972412
2024-08-04T23:46:18.370340420Z 
 53%|█████▎    | 3030/5712 [7:08:09<6:20:24,  8.51s/it]08/04/2024 16:46:18 - INFO - __main__ -   Step: 3030, LR: 2.608009679223717e-07, Loss: 0.19673120975494385
2024-08-04T23:46:26.931276727Z 
 53%|█████▎    | 3031/5712 [7:08:18<6:20:57,  8.53s/it]08/04/2024 16:46:26 - INFO - __main__ -   Step: 3031, LR: 2.607036892920548e-07, Loss: 0.1677844226360321
2024-08-04T23:46:35.616651041Z 
 53%|█████▎    | 3032/5712 [7:08:26<6:22:57,  8.57s/it]08/04/2024 16:46:35 - INFO - __main__ -   Step: 3032, LR: 2.606064106617379e-07, Loss: 0.33517783880233765
2024-08-04T23:46:43.638565964Z 
 53%|█████▎    | 3033/5712 [7:08:34<6:15:25,  8.41s/it]08/04/2024 16:46:43 - INFO - __main__ -   Step: 3033, LR: 2.60509132031421e-07, Loss: 0.11945168673992157
2024-08-04T23:46:51.833937917Z 
 53%|█████▎    | 3034/5712 [7:08:42<6:12:26,  8.34s/it]08/04/2024 16:46:51 - INFO - __main__ -   Step: 3034, LR: 2.604118534011041e-07, Loss: 0.30241501331329346
2024-08-04T23:46:59.796246629Z 
 53%|█████▎    | 3035/5712 [7:08:50<6:07:10,  8.23s/it]08/04/2024 16:46:59 - INFO - __main__ -   Step: 3035, LR: 2.603145747707872e-07, Loss: 0.18829375505447388
2024-08-04T23:47:08.096012859Z 
 53%|█████▎    | 3036/5712 [7:08:59<6:07:58,  8.25s/it]08/04/2024 16:47:08 - INFO - __main__ -   Step: 3036, LR: 2.602172961404703e-07, Loss: 0.20347177982330322
2024-08-04T23:47:17.824978205Z 
 53%|█████▎    | 3037/5712 [7:09:08<6:27:36,  8.69s/it]08/04/2024 16:47:17 - INFO - __main__ -   Step: 3037, LR: 2.601200175101534e-07, Loss: 0.26546940207481384
2024-08-04T23:47:26.483904752Z 
 53%|█████▎    | 3038/5712 [7:09:17<6:27:00,  8.68s/it]08/04/2024 16:47:26 - INFO - __main__ -   Step: 3038, LR: 2.600227388798366e-07, Loss: 0.13074395060539246
2024-08-04T23:47:35.474151653Z 
 53%|█████▎    | 3039/5712 [7:09:26<6:30:57,  8.78s/it]08/04/2024 16:47:35 - INFO - __main__ -   Step: 3039, LR: 2.599254602495197e-07, Loss: 0.16993209719657898
2024-08-04T23:47:43.495266927Z 
 53%|█████▎    | 3040/5712 [7:09:34<6:20:43,  8.55s/it]08/04/2024 16:47:43 - INFO - __main__ -   Step: 3040, LR: 2.598281816192028e-07, Loss: 0.16625481843948364
2024-08-04T23:47:51.675151110Z 
 53%|█████▎    | 3041/5712 [7:09:42<6:15:39,  8.44s/it]08/04/2024 16:47:51 - INFO - __main__ -   Step: 3041, LR: 2.5973090298888587e-07, Loss: 0.18113498389720917
2024-08-04T23:48:00.485694618Z 
 53%|█████▎    | 3042/5712 [7:09:51<6:20:28,  8.55s/it]08/04/2024 16:48:00 - INFO - __main__ -   Step: 3042, LR: 2.59633624358569e-07, Loss: 0.30973801016807556
2024-08-04T23:48:08.394417544Z 
 53%|█████▎    | 3043/5712 [7:09:59<6:11:46,  8.36s/it]08/04/2024 16:48:08 - INFO - __main__ -   Step: 3043, LR: 2.595363457282521e-07, Loss: 0.2702259421348572
2024-08-04T23:48:16.594811348Z 
 53%|█████▎    | 3044/5712 [7:10:07<6:09:32,  8.31s/it]08/04/2024 16:48:16 - INFO - __main__ -   Step: 3044, LR: 2.594390670979352e-07, Loss: 0.18329164385795593
2024-08-04T23:48:25.030780207Z 
 53%|█████▎    | 3045/5712 [7:10:16<6:11:04,  8.35s/it]08/04/2024 16:48:25 - INFO - __main__ -   Step: 3045, LR: 2.593417884676183e-07, Loss: 0.23918598890304565
2024-08-04T23:48:33.513254207Z 
 53%|█████▎    | 3046/5712 [7:10:24<6:12:43,  8.39s/it]08/04/2024 16:48:33 - INFO - __main__ -   Step: 3046, LR: 2.5924450983730153e-07, Loss: 0.17549091577529907
2024-08-04T23:48:42.878189623Z 
 53%|█████▎    | 3047/5712 [7:10:34<6:25:34,  8.68s/it]08/04/2024 16:48:42 - INFO - __main__ -   Step: 3047, LR: 2.591472312069846e-07, Loss: 0.20225046575069427
2024-08-04T23:48:50.968212958Z 
 53%|█████▎    | 3048/5712 [7:10:42<6:17:34,  8.50s/it]08/04/2024 16:48:50 - INFO - __main__ -   Step: 3048, LR: 2.590499525766677e-07, Loss: 0.18804270029067993
2024-08-04T23:48:59.113621318Z 
 53%|█████▎    | 3049/5712 [7:10:50<6:12:39,  8.40s/it]08/04/2024 16:48:59 - INFO - __main__ -   Step: 3049, LR: 2.589526739463508e-07, Loss: 0.10740406811237335
2024-08-04T23:49:08.153616815Z 
 53%|█████▎    | 3050/5712 [7:10:59<6:21:05,  8.59s/it]08/04/2024 16:49:08 - INFO - __main__ -   Step: 3050, LR: 2.58855395316034e-07, Loss: 0.18791358172893524
2024-08-04T23:49:16.271969864Z 
 53%|█████▎    | 3051/5712 [7:11:07<6:14:40,  8.45s/it]08/04/2024 16:49:16 - INFO - __main__ -   Step: 3051, LR: 2.587581166857171e-07, Loss: 0.44218558073043823
2024-08-04T23:49:24.453112165Z 
 53%|█████▎    | 3052/5712 [7:11:15<6:10:59,  8.37s/it]08/04/2024 16:49:24 - INFO - __main__ -   Step: 3052, LR: 2.586608380554002e-07, Loss: 0.15409114956855774
2024-08-04T23:49:32.460672645Z 
 53%|█████▎    | 3053/5712 [7:11:23<6:06:03,  8.26s/it]08/04/2024 16:49:32 - INFO - __main__ -   Step: 3053, LR: 2.5856355942508327e-07, Loss: 0.2682057321071625
2024-08-04T23:49:41.822312952Z 
 53%|█████▎    | 3054/5712 [7:11:32<6:20:31,  8.59s/it]08/04/2024 16:49:41 - INFO - __main__ -   Step: 3054, LR: 2.584662807947664e-07, Loss: 0.12110394239425659
2024-08-04T23:49:50.387995037Z 
 53%|█████▎    | 3055/5712 [7:11:41<6:20:05,  8.58s/it]08/04/2024 16:49:50 - INFO - __main__ -   Step: 3055, LR: 2.583690021644495e-07, Loss: 0.18325449526309967
2024-08-04T23:49:58.873450217Z 
 54%|█████▎    | 3056/5712 [7:11:50<6:18:39,  8.55s/it]08/04/2024 16:49:58 - INFO - __main__ -   Step: 3056, LR: 2.582717235341326e-07, Loss: 0.17682790756225586
2024-08-04T23:50:07.013930174Z 
 54%|█████▎    | 3057/5712 [7:11:58<6:13:01,  8.43s/it]08/04/2024 16:50:07 - INFO - __main__ -   Step: 3057, LR: 2.581744449038157e-07, Loss: 0.2143682837486267
2024-08-04T23:50:15.454442233Z 
 54%|█████▎    | 3058/5712 [7:12:06<6:13:01,  8.43s/it]08/04/2024 16:50:15 - INFO - __main__ -   Step: 3058, LR: 2.580771662734988e-07, Loss: 0.15767508745193481
2024-08-04T23:50:23.604951059Z 
 54%|█████▎    | 3059/5712 [7:12:14<6:09:07,  8.35s/it]08/04/2024 16:50:23 - INFO - __main__ -   Step: 3059, LR: 2.5797988764318197e-07, Loss: 0.21665745973587036
2024-08-04T23:50:31.613186761Z 
 54%|█████▎    | 3060/5712 [7:12:22<6:04:29,  8.25s/it]08/04/2024 16:50:31 - INFO - __main__ -   Step: 3060, LR: 2.5788260901286507e-07, Loss: 0.32130515575408936
2024-08-04T23:50:40.012938100Z 
 54%|█████▎    | 3061/5712 [7:12:31<6:06:22,  8.29s/it]08/04/2024 16:50:40 - INFO - __main__ -   Step: 3061, LR: 2.5778533038254817e-07, Loss: 0.160241961479187
2024-08-04T23:50:49.125793245Z 
 54%|█████▎    | 3062/5712 [7:12:40<6:17:06,  8.54s/it]08/04/2024 16:50:49 - INFO - __main__ -   Step: 3062, LR: 2.5768805175223127e-07, Loss: 0.31563884019851685
2024-08-04T23:50:57.305435563Z 
 54%|█████▎    | 3063/5712 [7:12:48<6:12:12,  8.43s/it]08/04/2024 16:50:57 - INFO - __main__ -   Step: 3063, LR: 2.575907731219144e-07, Loss: 0.19441597163677216
2024-08-04T23:51:05.974987117Z 
 54%|█████▎    | 3064/5712 [7:12:57<6:15:13,  8.50s/it]08/04/2024 16:51:05 - INFO - __main__ -   Step: 3064, LR: 2.574934944915976e-07, Loss: 0.18312931060791016
2024-08-04T23:51:13.961138608Z 
 54%|█████▎    | 3065/5712 [7:13:05<6:08:16,  8.35s/it]08/04/2024 16:51:13 - INFO - __main__ -   Step: 3065, LR: 2.5739621586128067e-07, Loss: 0.20092859864234924
2024-08-04T23:51:22.133166735Z 
 54%|█████▎    | 3066/5712 [7:13:13<6:05:48,  8.30s/it]08/04/2024 16:51:22 - INFO - __main__ -   Step: 3066, LR: 2.5729893723096377e-07, Loss: 0.26739799976348877
2024-08-04T23:51:30.949612656Z 
 54%|█████▎    | 3067/5712 [7:13:22<6:12:34,  8.45s/it]08/04/2024 16:51:30 - INFO - __main__ -   Step: 3067, LR: 2.572016586006469e-07, Loss: 0.1723259687423706
2024-08-04T23:51:38.878453798Z 
 54%|█████▎    | 3068/5712 [7:13:30<6:05:30,  8.29s/it]08/04/2024 16:51:38 - INFO - __main__ -   Step: 3068, LR: 2.5710437997033e-07, Loss: 0.21182988584041595
2024-08-04T23:51:47.924144799Z 
 54%|█████▎    | 3069/5712 [7:13:39<6:15:18,  8.52s/it]08/04/2024 16:51:47 - INFO - __main__ -   Step: 3069, LR: 2.570071013400131e-07, Loss: 0.14565318822860718
2024-08-04T23:51:56.083129559Z 
 54%|█████▎    | 3070/5712 [7:13:47<6:10:23,  8.41s/it]08/04/2024 16:51:56 - INFO - __main__ -   Step: 3070, LR: 2.569098227096962e-07, Loss: 0.08626337349414825
2024-08-04T23:52:04.993732955Z 
 54%|█████▍    | 3071/5712 [7:13:56<6:16:49,  8.56s/it]08/04/2024 16:52:04 - INFO - __main__ -   Step: 3071, LR: 2.5681254407937937e-07, Loss: 0.16266678273677826
2024-08-04T23:52:13.176930643Z 
 54%|█████▍    | 3072/5712 [7:14:04<6:11:42,  8.45s/it]08/04/2024 16:52:13 - INFO - __main__ -   Step: 3072, LR: 2.5671526544906247e-07, Loss: 0.12922337651252747
2024-08-04T23:52:21.597045081Z 
 54%|█████▍    | 3073/5712 [7:14:12<6:11:12,  8.44s/it]08/04/2024 16:52:21 - INFO - __main__ -   Step: 3073, LR: 2.5661798681874557e-07, Loss: 0.13236317038536072
2024-08-04T23:52:29.822121321Z 
 54%|█████▍    | 3074/5712 [7:14:20<6:08:14,  8.38s/it]08/04/2024 16:52:29 - INFO - __main__ -   Step: 3074, LR: 2.5652070818842867e-07, Loss: 0.27246028184890747
2024-08-04T23:52:38.231882393Z 
 54%|█████▍    | 3075/5712 [7:14:29<6:08:32,  8.39s/it]08/04/2024 16:52:38 - INFO - __main__ -   Step: 3075, LR: 2.564234295581118e-07, Loss: 0.15178292989730835
2024-08-04T23:52:46.425009537Z 
 54%|█████▍    | 3076/5712 [7:14:37<6:05:52,  8.33s/it]08/04/2024 16:52:46 - INFO - __main__ -   Step: 3076, LR: 2.563261509277949e-07, Loss: 0.17333635687828064
2024-08-04T23:52:54.542731020Z 
 54%|█████▍    | 3077/5712 [7:14:45<6:02:57,  8.26s/it]08/04/2024 16:52:54 - INFO - __main__ -   Step: 3077, LR: 2.56228872297478e-07, Loss: 0.15790651738643646
2024-08-04T23:53:03.030893554Z 
 54%|█████▍    | 3078/5712 [7:14:54<6:05:46,  8.33s/it]08/04/2024 16:53:03 - INFO - __main__ -   Step: 3078, LR: 2.561315936671611e-07, Loss: 0.17911005020141602
2024-08-04T23:53:12.177551536Z 
 54%|█████▍    | 3079/5712 [7:15:03<6:16:21,  8.58s/it]08/04/2024 16:53:12 - INFO - __main__ -   Step: 3079, LR: 2.5603431503684427e-07, Loss: 0.18139293789863586
2024-08-04T23:53:20.626431616Z 
 54%|█████▍    | 3080/5712 [7:15:11<6:14:32,  8.54s/it]08/04/2024 16:53:20 - INFO - __main__ -   Step: 3080, LR: 2.5593703640652737e-07, Loss: 0.22145208716392517
2024-08-04T23:53:29.530769144Z 
 54%|█████▍    | 3081/5712 [7:15:20<6:19:11,  8.65s/it]08/04/2024 16:53:29 - INFO - __main__ -   Step: 3081, LR: 2.5583975777621047e-07, Loss: 0.12453759461641312
2024-08-04T23:53:37.956425441Z 
 54%|█████▍    | 3082/5712 [7:15:29<6:16:08,  8.58s/it]08/04/2024 16:53:37 - INFO - __main__ -   Step: 3082, LR: 2.557424791458936e-07, Loss: 0.19159436225891113
2024-08-04T23:53:46.335804774Z 
 54%|█████▍    | 3083/5712 [7:15:37<6:13:21,  8.52s/it]08/04/2024 16:53:46 - INFO - __main__ -   Step: 3083, LR: 2.556452005155768e-07, Loss: 0.26127102971076965
2024-08-04T23:53:54.462911810Z 
 54%|█████▍    | 3084/5712 [7:15:45<6:08:02,  8.40s/it]08/04/2024 16:53:54 - INFO - __main__ -   Step: 3084, LR: 2.5554792188525987e-07, Loss: 0.12068496644496918
2024-08-04T23:54:02.925762503Z 
 54%|█████▍    | 3085/5712 [7:15:54<6:08:41,  8.42s/it]08/04/2024 16:54:02 - INFO - __main__ -   Step: 3085, LR: 2.5545064325494297e-07, Loss: 0.13932180404663086
2024-08-04T23:54:11.471982071Z 
 54%|█████▍    | 3086/5712 [7:16:02<6:10:11,  8.46s/it]08/04/2024 16:54:11 - INFO - __main__ -   Step: 3086, LR: 2.5535336462462607e-07, Loss: 0.15908187627792358
2024-08-04T23:54:20.586372504Z 
 54%|█████▍    | 3087/5712 [7:16:11<6:18:39,  8.66s/it]08/04/2024 16:54:20 - INFO - __main__ -   Step: 3087, LR: 2.552560859943092e-07, Loss: 0.10007697343826294
2024-08-04T23:54:29.240670908Z 
 54%|█████▍    | 3088/5712 [7:16:20<6:18:29,  8.65s/it]08/04/2024 16:54:29 - INFO - __main__ -   Step: 3088, LR: 2.551588073639923e-07, Loss: 0.08687944710254669
2024-08-04T23:54:37.453461911Z 
 54%|█████▍    | 3089/5712 [7:16:28<6:12:34,  8.52s/it]08/04/2024 16:54:37 - INFO - __main__ -   Step: 3089, LR: 2.550615287336754e-07, Loss: 0.12203363329172134
2024-08-04T23:54:46.126362946Z 
 54%|█████▍    | 3090/5712 [7:16:37<6:14:24,  8.57s/it]08/04/2024 16:54:46 - INFO - __main__ -   Step: 3090, LR: 2.549642501033585e-07, Loss: 0.20026277005672455
2024-08-04T23:54:54.688739809Z 
 54%|█████▍    | 3091/5712 [7:16:45<6:14:11,  8.57s/it]08/04/2024 16:54:54 - INFO - __main__ -   Step: 3091, LR: 2.5486697147304167e-07, Loss: 0.18208639323711395
2024-08-04T23:55:02.663726154Z 
 54%|█████▍    | 3092/5712 [7:16:53<6:06:18,  8.39s/it]08/04/2024 16:55:02 - INFO - __main__ -   Step: 3092, LR: 2.5476969284272477e-07, Loss: 0.12382717430591583
2024-08-04T23:55:11.251345988Z 
 54%|█████▍    | 3093/5712 [7:17:02<6:08:46,  8.45s/it]08/04/2024 16:55:11 - INFO - __main__ -   Step: 3093, LR: 2.5467241421240787e-07, Loss: 0.2249702662229538
2024-08-04T23:55:20.220297747Z 
 54%|█████▍    | 3094/5712 [7:17:11<6:15:26,  8.60s/it]08/04/2024 16:55:20 - INFO - __main__ -   Step: 3094, LR: 2.5457513558209097e-07, Loss: 0.1332470327615738
2024-08-04T23:55:28.382027854Z 
 54%|█████▍    | 3095/5712 [7:17:19<6:09:30,  8.47s/it]08/04/2024 16:55:28 - INFO - __main__ -   Step: 3095, LR: 2.544778569517741e-07, Loss: 0.11684110760688782
2024-08-04T23:55:37.899706883Z 
 54%|█████▍    | 3096/5712 [7:17:29<6:23:02,  8.79s/it]08/04/2024 16:55:37 - INFO - __main__ -   Step: 3096, LR: 2.543805783214572e-07, Loss: 0.16572368144989014
2024-08-04T23:55:46.225888988Z 
 54%|█████▍    | 3097/5712 [7:17:37<6:16:53,  8.65s/it]08/04/2024 16:55:46 - INFO - __main__ -   Step: 3097, LR: 2.542832996911403e-07, Loss: 0.17856678366661072
2024-08-04T23:55:54.754868781Z 
 54%|█████▍    | 3098/5712 [7:17:45<6:15:11,  8.61s/it]08/04/2024 16:55:54 - INFO - __main__ -   Step: 3098, LR: 2.541860210608234e-07, Loss: 0.22316768765449524
2024-08-04T23:56:03.940340790Z 
 54%|█████▍    | 3099/5712 [7:17:55<6:22:33,  8.78s/it]08/04/2024 16:56:03 - INFO - __main__ -   Step: 3099, LR: 2.540887424305065e-07, Loss: 0.18611092865467072
2024-08-04T23:56:11.945065155Z 
 54%|█████▍    | 3100/5712 [7:18:03<6:12:13,  8.55s/it]08/04/2024 16:56:11 - INFO - __main__ -   Step: 3100, LR: 2.539914638001897e-07, Loss: 0.28345972299575806
2024-08-04T23:56:19.978396968Z 
 54%|█████▍    | 3101/5712 [7:18:11<6:05:19,  8.40s/it]08/04/2024 16:56:19 - INFO - __main__ -   Step: 3101, LR: 2.538941851698728e-07, Loss: 0.21367663145065308
2024-08-04T23:56:28.396586382Z 
 54%|█████▍    | 3102/5712 [7:18:19<6:05:29,  8.40s/it]08/04/2024 16:56:28 - INFO - __main__ -   Step: 3102, LR: 2.537969065395559e-07, Loss: 0.20128315687179565
2024-08-04T23:56:36.277122098Z 
 54%|█████▍    | 3103/5712 [7:18:27<5:58:33,  8.25s/it]08/04/2024 16:56:36 - INFO - __main__ -   Step: 3103, LR: 2.53699627909239e-07, Loss: 0.2315264642238617
2024-08-04T23:56:44.538255607Z 
 54%|█████▍    | 3104/5712 [7:18:35<5:58:36,  8.25s/it]08/04/2024 16:56:44 - INFO - __main__ -   Step: 3104, LR: 2.5360234927892217e-07, Loss: 0.13211765885353088
2024-08-04T23:56:52.901568003Z 
 54%|█████▍    | 3105/5712 [7:18:44<5:59:56,  8.28s/it]08/04/2024 16:56:52 - INFO - __main__ -   Step: 3105, LR: 2.5350507064860527e-07, Loss: 0.08603286743164062
2024-08-04T23:57:01.221325277Z 
 54%|█████▍    | 3106/5712 [7:18:52<6:00:16,  8.29s/it]08/04/2024 16:57:01 - INFO - __main__ -   Step: 3106, LR: 2.5340779201828837e-07, Loss: 0.23953354358673096
2024-08-04T23:57:09.962246909Z 
 54%|█████▍    | 3107/5712 [7:19:01<6:05:56,  8.43s/it]08/04/2024 16:57:09 - INFO - __main__ -   Step: 3107, LR: 2.5331051338797147e-07, Loss: 0.20502294600009918
2024-08-04T23:57:18.203631634Z 
 54%|█████▍    | 3108/5712 [7:19:09<6:03:22,  8.37s/it]08/04/2024 16:57:18 - INFO - __main__ -   Step: 3108, LR: 2.532132347576546e-07, Loss: 0.19773253798484802
2024-08-04T23:57:26.242072648Z 
 54%|█████▍    | 3109/5712 [7:19:17<5:58:52,  8.27s/it]08/04/2024 16:57:26 - INFO - __main__ -   Step: 3109, LR: 2.531159561273377e-07, Loss: 0.16590256989002228
2024-08-04T23:57:34.980746952Z 
 54%|█████▍    | 3110/5712 [7:19:26<6:04:48,  8.41s/it]08/04/2024 16:57:34 - INFO - __main__ -   Step: 3110, LR: 2.530186774970208e-07, Loss: 0.15672674775123596
2024-08-04T23:57:43.183795890Z 
 54%|█████▍    | 3111/5712 [7:19:34<6:01:56,  8.35s/it]08/04/2024 16:57:43 - INFO - __main__ -   Step: 3111, LR: 2.529213988667039e-07, Loss: 0.2545022964477539
2024-08-04T23:57:51.580143385Z 
 54%|█████▍    | 3112/5712 [7:19:42<6:02:25,  8.36s/it]08/04/2024 16:57:51 - INFO - __main__ -   Step: 3112, LR: 2.5282412023638707e-07, Loss: 0.174937441945076
2024-08-04T23:58:00.477328676Z 
 54%|█████▍    | 3113/5712 [7:19:51<6:09:12,  8.52s/it]08/04/2024 16:58:00 - INFO - __main__ -   Step: 3113, LR: 2.5272684160607017e-07, Loss: 0.10953764617443085
2024-08-04T23:58:08.674913811Z 
 55%|█████▍    | 3114/5712 [7:19:59<6:04:50,  8.43s/it]08/04/2024 16:58:08 - INFO - __main__ -   Step: 3114, LR: 2.5262956297575327e-07, Loss: 0.2507637143135071
2024-08-04T23:58:17.129255259Z 
 55%|█████▍    | 3115/5712 [7:20:08<6:05:02,  8.43s/it]08/04/2024 16:58:17 - INFO - __main__ -   Step: 3115, LR: 2.5253228434543637e-07, Loss: 0.15231159329414368
2024-08-04T23:58:26.542957364Z 
 55%|█████▍    | 3116/5712 [7:20:17<6:17:38,  8.73s/it]08/04/2024 16:58:26 - INFO - __main__ -   Step: 3116, LR: 2.524350057151195e-07, Loss: 0.1835263967514038
2024-08-04T23:58:34.545551693Z 
 55%|█████▍    | 3117/5712 [7:20:25<6:08:05,  8.51s/it]08/04/2024 16:58:34 - INFO - __main__ -   Step: 3117, LR: 2.523377270848026e-07, Loss: 0.1117389053106308
2024-08-04T23:58:43.029190723Z 
 55%|█████▍    | 3118/5712 [7:20:34<6:07:35,  8.50s/it]08/04/2024 16:58:43 - INFO - __main__ -   Step: 3118, LR: 2.5224044845448577e-07, Loss: 0.25521087646484375
2024-08-04T23:58:51.220456076Z 
 55%|█████▍    | 3119/5712 [7:20:42<6:03:24,  8.41s/it]08/04/2024 16:58:51 - INFO - __main__ -   Step: 3119, LR: 2.5214316982416887e-07, Loss: 0.19113796949386597
2024-08-04T23:58:59.654200294Z 
 55%|█████▍    | 3120/5712 [7:20:50<6:03:35,  8.42s/it]08/04/2024 16:58:59 - INFO - __main__ -   Step: 3120, LR: 2.52045891193852e-07, Loss: 0.38054412603378296
2024-08-04T23:59:07.991601715Z 
 55%|█████▍    | 3121/5712 [7:20:59<6:02:25,  8.39s/it]08/04/2024 16:59:07 - INFO - __main__ -   Step: 3121, LR: 2.519486125635351e-07, Loss: 0.17873388528823853
2024-08-04T23:59:16.477923910Z 
 55%|█████▍    | 3122/5712 [7:21:07<6:03:30,  8.42s/it]08/04/2024 16:59:16 - INFO - __main__ -   Step: 3122, LR: 2.518513339332182e-07, Loss: 0.1975174844264984
2024-08-04T23:59:24.547183200Z 
 55%|█████▍    | 3123/5712 [7:21:15<5:58:48,  8.32s/it]08/04/2024 16:59:24 - INFO - __main__ -   Step: 3123, LR: 2.517540553029013e-07, Loss: 0.21993303298950195
2024-08-04T23:59:33.011163494Z 
 55%|█████▍    | 3124/5712 [7:21:24<6:00:35,  8.36s/it]08/04/2024 16:59:33 - INFO - __main__ -   Step: 3124, LR: 2.5165677667258447e-07, Loss: 0.1997583508491516
2024-08-04T23:59:41.130098603Z 
 55%|█████▍    | 3125/5712 [7:21:32<5:57:20,  8.29s/it]08/04/2024 16:59:41 - INFO - __main__ -   Step: 3125, LR: 2.5155949804226757e-07, Loss: 0.24637120962142944
2024-08-04T23:59:49.824039211Z 
 55%|█████▍    | 3126/5712 [7:21:40<6:02:26,  8.41s/it]08/04/2024 16:59:49 - INFO - __main__ -   Step: 3126, LR: 2.5146221941195067e-07, Loss: 0.13227081298828125
2024-08-04T23:59:58.247730920Z 
 55%|█████▍    | 3127/5712 [7:21:49<6:02:29,  8.41s/it]08/04/2024 16:59:58 - INFO - __main__ -   Step: 3127, LR: 2.5136494078163377e-07, Loss: 0.23080238699913025
2024-08-05T00:00:07.080670599Z 
 55%|█████▍    | 3128/5712 [7:21:58<6:07:46,  8.54s/it]08/04/2024 17:00:07 - INFO - __main__ -   Step: 3128, LR: 2.512676621513169e-07, Loss: 0.258158802986145
2024-08-05T00:00:15.387223774Z 
 55%|█████▍    | 3129/5712 [7:22:06<6:04:37,  8.47s/it]08/04/2024 17:00:15 - INFO - __main__ -   Step: 3129, LR: 2.51170383521e-07, Loss: 0.2860926389694214
2024-08-05T00:00:24.282403142Z 
 55%|█████▍    | 3130/5712 [7:22:15<6:09:58,  8.60s/it]08/04/2024 17:00:24 - INFO - __main__ -   Step: 3130, LR: 2.510731048906831e-07, Loss: 0.0912037193775177
2024-08-05T00:00:32.633783437Z 
 55%|█████▍    | 3131/5712 [7:22:23<6:06:38,  8.52s/it]08/04/2024 17:00:32 - INFO - __main__ -   Step: 3131, LR: 2.509758262603662e-07, Loss: 0.35216227173805237
2024-08-05T00:00:41.777938401Z 
 55%|█████▍    | 3132/5712 [7:22:32<6:14:30,  8.71s/it]08/04/2024 17:00:41 - INFO - __main__ -   Step: 3132, LR: 2.5087854763004937e-07, Loss: 0.24626101553440094
2024-08-05T00:00:50.237577689Z 
 55%|█████▍    | 3133/5712 [7:22:41<6:11:09,  8.63s/it]08/04/2024 17:00:50 - INFO - __main__ -   Step: 3133, LR: 2.5078126899973247e-07, Loss: 0.17637813091278076
2024-08-05T00:00:58.884365679Z 
 55%|█████▍    | 3134/5712 [7:22:50<6:11:09,  8.64s/it]08/04/2024 17:00:58 - INFO - __main__ -   Step: 3134, LR: 2.5068399036941557e-07, Loss: 0.12180519849061966
2024-08-05T00:01:06.862747783Z 
 55%|█████▍    | 3135/5712 [7:22:58<6:02:30,  8.44s/it]08/04/2024 17:01:06 - INFO - __main__ -   Step: 3135, LR: 2.5058671173909867e-07, Loss: 0.2087603211402893
2024-08-05T00:01:15.926367310Z 
 55%|█████▍    | 3136/5712 [7:23:07<6:10:24,  8.63s/it]08/04/2024 17:01:15 - INFO - __main__ -   Step: 3136, LR: 2.5048943310878187e-07, Loss: 0.14401556551456451
2024-08-05T00:01:24.633329900Z 
 55%|█████▍    | 3137/5712 [7:23:15<6:11:16,  8.65s/it]08/04/2024 17:01:24 - INFO - __main__ -   Step: 3137, LR: 2.5039215447846497e-07, Loss: 0.17642784118652344
2024-08-05T00:01:32.902315987Z 
 55%|█████▍    | 3138/5712 [7:23:24<6:06:13,  8.54s/it]08/04/2024 17:01:32 - INFO - __main__ -   Step: 3138, LR: 2.5029487584814807e-07, Loss: 0.2611098289489746
2024-08-05T00:01:41.515180784Z 
 55%|█████▍    | 3139/5712 [7:23:32<6:07:03,  8.56s/it]08/04/2024 17:01:41 - INFO - __main__ -   Step: 3139, LR: 2.5019759721783117e-07, Loss: 0.3235262632369995
2024-08-05T00:01:50.377706552Z 
 55%|█████▍    | 3140/5712 [7:23:41<6:10:48,  8.65s/it]08/04/2024 17:01:50 - INFO - __main__ -   Step: 3140, LR: 2.5010031858751427e-07, Loss: 0.17737028002738953
2024-08-05T00:01:58.812770659Z 
 55%|█████▍    | 3141/5712 [7:23:49<6:07:53,  8.59s/it]08/04/2024 17:01:58 - INFO - __main__ -   Step: 3141, LR: 2.500030399571974e-07, Loss: 0.2538074553012848
2024-08-05T00:02:07.357759552Z 
 55%|█████▌    | 3142/5712 [7:23:58<6:07:14,  8.57s/it]08/04/2024 17:02:07 - INFO - __main__ -   Step: 3142, LR: 2.499057613268805e-07, Loss: 0.14341813325881958
2024-08-05T00:02:15.592595099Z 
 55%|█████▌    | 3143/5712 [7:24:06<6:02:44,  8.47s/it]08/04/2024 17:02:15 - INFO - __main__ -   Step: 3143, LR: 2.498084826965636e-07, Loss: 0.1550709307193756
2024-08-05T00:02:23.768337642Z 
 55%|█████▌    | 3144/5712 [7:24:14<5:58:47,  8.38s/it]08/04/2024 17:02:23 - INFO - __main__ -   Step: 3144, LR: 2.497112040662467e-07, Loss: 0.17847470939159393
2024-08-05T00:02:32.216867282Z 
 55%|█████▌    | 3145/5712 [7:24:23<5:59:29,  8.40s/it]08/04/2024 17:02:32 - INFO - __main__ -   Step: 3145, LR: 2.4961392543592987e-07, Loss: 0.16455569863319397
2024-08-05T00:02:40.629849420Z 
 55%|█████▌    | 3146/5712 [7:24:31<5:59:29,  8.41s/it]08/04/2024 17:02:40 - INFO - __main__ -   Step: 3146, LR: 2.4951664680561297e-07, Loss: 0.1196369156241417
2024-08-05T00:02:49.082861227Z 
 55%|█████▌    | 3147/5712 [7:24:40<5:59:57,  8.42s/it]08/04/2024 17:02:49 - INFO - __main__ -   Step: 3147, LR: 2.4941936817529607e-07, Loss: 0.24398604035377502
2024-08-05T00:02:57.837946627Z 
 55%|█████▌    | 3148/5712 [7:24:48<6:04:06,  8.52s/it]08/04/2024 17:02:57 - INFO - __main__ -   Step: 3148, LR: 2.4932208954497916e-07, Loss: 0.1906208097934723
2024-08-05T00:03:06.965251251Z 
 55%|█████▌    | 3149/5712 [7:24:58<6:11:43,  8.70s/it]08/04/2024 17:03:06 - INFO - __main__ -   Step: 3149, LR: 2.492248109146623e-07, Loss: 0.3074641227722168
2024-08-05T00:03:15.539320239Z 
 55%|█████▌    | 3150/5712 [7:25:06<6:09:57,  8.66s/it]08/04/2024 17:03:15 - INFO - __main__ -   Step: 3150, LR: 2.491275322843454e-07, Loss: 0.10450466722249985
2024-08-05T00:03:23.978686400Z 
 55%|█████▌    | 3151/5712 [7:25:15<6:06:56,  8.60s/it]08/04/2024 17:03:23 - INFO - __main__ -   Step: 3151, LR: 2.4903025365402857e-07, Loss: 0.2033897042274475
2024-08-05T00:03:31.965401697Z 
 55%|█████▌    | 3152/5712 [7:25:23<5:58:59,  8.41s/it]08/04/2024 17:03:31 - INFO - __main__ -   Step: 3152, LR: 2.4893297502371167e-07, Loss: 0.15701675415039062
2024-08-05T00:03:40.723294527Z 
 55%|█████▌    | 3153/5712 [7:25:31<6:03:14,  8.52s/it]08/04/2024 17:03:40 - INFO - __main__ -   Step: 3153, LR: 2.4883569639339477e-07, Loss: 0.16854596138000488
2024-08-05T00:03:49.154131031Z 
 55%|█████▌    | 3154/5712 [7:25:40<6:02:00,  8.49s/it]08/04/2024 17:03:49 - INFO - __main__ -   Step: 3154, LR: 2.4873841776307786e-07, Loss: 0.24706153571605682
2024-08-05T00:03:57.569495389Z 
 55%|█████▌    | 3155/5712 [7:25:48<6:00:53,  8.47s/it]08/04/2024 17:03:57 - INFO - __main__ -   Step: 3155, LR: 2.48641139132761e-07, Loss: 0.11867723613977432
2024-08-05T00:04:06.639651378Z 
 55%|█████▌    | 3156/5712 [7:25:57<6:08:26,  8.65s/it]08/04/2024 17:04:06 - INFO - __main__ -   Step: 3156, LR: 2.485438605024441e-07, Loss: 0.21886813640594482
2024-08-05T00:04:14.937717268Z 
 55%|█████▌    | 3157/5712 [7:26:06<6:03:49,  8.54s/it]08/04/2024 17:04:14 - INFO - __main__ -   Step: 3157, LR: 2.484465818721272e-07, Loss: 0.14979788661003113
2024-08-05T00:04:23.205366750Z 
 55%|█████▌    | 3158/5712 [7:26:14<6:00:09,  8.46s/it]08/04/2024 17:04:23 - INFO - __main__ -   Step: 3158, LR: 2.483493032418103e-07, Loss: 0.1591643989086151
2024-08-05T00:04:31.954520353Z 
 55%|█████▌    | 3159/5712 [7:26:23<6:03:41,  8.55s/it]08/04/2024 17:04:31 - INFO - __main__ -   Step: 3159, LR: 2.4825202461149347e-07, Loss: 0.1793033331632614
2024-08-05T00:04:39.889609440Z 
 55%|█████▌    | 3160/5712 [7:26:31<5:55:44,  8.36s/it]08/04/2024 17:04:39 - INFO - __main__ -   Step: 3160, LR: 2.4815474598117656e-07, Loss: 0.12778069078922272
2024-08-05T00:04:48.263179092Z 
 55%|█████▌    | 3161/5712 [7:26:39<5:55:43,  8.37s/it]08/04/2024 17:04:48 - INFO - __main__ -   Step: 3161, LR: 2.480574673508597e-07, Loss: 0.1828276515007019
2024-08-05T00:04:57.048546103Z 
 55%|█████▌    | 3162/5712 [7:26:48<6:00:55,  8.49s/it]08/04/2024 17:04:57 - INFO - __main__ -   Step: 3162, LR: 2.479601887205428e-07, Loss: 0.158535897731781
2024-08-05T00:05:05.871763043Z 
 55%|█████▌    | 3163/5712 [7:26:57<6:04:59,  8.59s/it]08/04/2024 17:05:05 - INFO - __main__ -   Step: 3163, LR: 2.478629100902259e-07, Loss: 0.2592678666114807
2024-08-05T00:05:13.940470269Z 
 55%|█████▌    | 3164/5712 [7:27:05<5:58:11,  8.43s/it]08/04/2024 17:05:13 - INFO - __main__ -   Step: 3164, LR: 2.47765631459909e-07, Loss: 0.14626610279083252
2024-08-05T00:05:22.604673260Z 
 55%|█████▌    | 3165/5712 [7:27:13<6:00:58,  8.50s/it]08/04/2024 17:05:22 - INFO - __main__ -   Step: 3165, LR: 2.4766835282959217e-07, Loss: 0.17283858358860016
2024-08-05T00:05:31.408356759Z 
 55%|█████▌    | 3166/5712 [7:27:22<6:04:38,  8.59s/it]08/04/2024 17:05:31 - INFO - __main__ -   Step: 3166, LR: 2.4757107419927527e-07, Loss: 0.21129396557807922
2024-08-05T00:05:40.394395856Z 
 55%|█████▌    | 3167/5712 [7:27:31<6:09:30,  8.71s/it]08/04/2024 17:05:40 - INFO - __main__ -   Step: 3167, LR: 2.4747379556895836e-07, Loss: 0.1280624270439148
2024-08-05T00:05:48.048776024Z 
 55%|█████▌    | 3168/5712 [7:27:39<5:55:55,  8.39s/it]08/04/2024 17:05:48 - INFO - __main__ -   Step: 3168, LR: 2.473765169386415e-07, Loss: 0.1822337806224823
2024-08-05T00:05:56.722466993Z 
 55%|█████▌    | 3169/5712 [7:27:47<5:59:20,  8.48s/it]08/04/2024 17:05:56 - INFO - __main__ -   Step: 3169, LR: 2.472792383083246e-07, Loss: 0.11869116127490997
2024-08-05T00:06:05.369005389Z 
 55%|█████▌    | 3170/5712 [7:27:56<6:01:19,  8.53s/it]08/04/2024 17:06:05 - INFO - __main__ -   Step: 3170, LR: 2.471819596780077e-07, Loss: 0.18146821856498718
2024-08-05T00:06:13.592627348Z 
 56%|█████▌    | 3171/5712 [7:28:04<5:57:18,  8.44s/it]08/04/2024 17:06:13 - INFO - __main__ -   Step: 3171, LR: 2.4708468104769087e-07, Loss: 0.2583373785018921
2024-08-05T00:06:22.407661744Z 
 56%|█████▌    | 3172/5712 [7:28:13<6:01:58,  8.55s/it]08/04/2024 17:06:22 - INFO - __main__ -   Step: 3172, LR: 2.4698740241737397e-07, Loss: 0.2013898491859436
2024-08-05T00:06:31.327034915Z 
 56%|█████▌    | 3173/5712 [7:28:22<6:06:30,  8.66s/it]08/04/2024 17:06:31 - INFO - __main__ -   Step: 3173, LR: 2.4689012378705706e-07, Loss: 0.18896710872650146
2024-08-05T00:06:40.520714072Z 
 56%|█████▌    | 3174/5712 [7:28:31<6:13:07,  8.82s/it]08/04/2024 17:06:40 - INFO - __main__ -   Step: 3174, LR: 2.4679284515674016e-07, Loss: 0.16369733214378357
2024-08-05T00:06:48.972084941Z 
 56%|█████▌    | 3175/5712 [7:28:40<6:08:17,  8.71s/it]08/04/2024 17:06:48 - INFO - __main__ -   Step: 3175, LR: 2.4669556652642326e-07, Loss: 0.15563280880451202
2024-08-05T00:06:57.152661849Z 
 56%|█████▌    | 3176/5712 [7:28:48<6:01:25,  8.55s/it]08/04/2024 17:06:57 - INFO - __main__ -   Step: 3176, LR: 2.465982878961064e-07, Loss: 0.1309330314397812
2024-08-05T00:07:05.418890977Z 
 56%|█████▌    | 3177/5712 [7:28:56<5:57:40,  8.47s/it]08/04/2024 17:07:05 - INFO - __main__ -   Step: 3177, LR: 2.465010092657895e-07, Loss: 0.15671774744987488
2024-08-05T00:07:14.322335099Z 
 56%|█████▌    | 3178/5712 [7:29:05<6:03:04,  8.60s/it]08/04/2024 17:07:14 - INFO - __main__ -   Step: 3178, LR: 2.4640373063547267e-07, Loss: 0.18684184551239014
2024-08-05T00:07:22.844301324Z 
 56%|█████▌    | 3179/5712 [7:29:13<6:01:59,  8.57s/it]08/04/2024 17:07:22 - INFO - __main__ -   Step: 3179, LR: 2.4630645200515576e-07, Loss: 0.24617786705493927
2024-08-05T00:07:31.850889693Z 
 56%|█████▌    | 3180/5712 [7:29:22<6:07:18,  8.70s/it]08/04/2024 17:07:31 - INFO - __main__ -   Step: 3180, LR: 2.4620917337483886e-07, Loss: 0.2693500816822052
2024-08-05T00:07:40.478749985Z 
 56%|█████▌    | 3181/5712 [7:29:31<6:06:12,  8.68s/it]08/04/2024 17:07:40 - INFO - __main__ -   Step: 3181, LR: 2.4611189474452196e-07, Loss: 0.12658154964447021
2024-08-05T00:07:49.326296053Z 
 56%|█████▌    | 3182/5712 [7:29:40<6:08:09,  8.73s/it]08/04/2024 17:07:49 - INFO - __main__ -   Step: 3182, LR: 2.460146161142051e-07, Loss: 0.13889014720916748
2024-08-05T00:07:58.307813202Z 
 56%|█████▌    | 3183/5712 [7:29:49<6:11:10,  8.81s/it]08/04/2024 17:07:58 - INFO - __main__ -   Step: 3183, LR: 2.459173374838882e-07, Loss: 0.2447555959224701
2024-08-05T00:08:06.592560910Z 
 56%|█████▌    | 3184/5712 [7:29:57<6:04:26,  8.65s/it]08/04/2024 17:08:06 - INFO - __main__ -   Step: 3184, LR: 2.458200588535713e-07, Loss: 0.24492016434669495
2024-08-05T00:08:14.988603095Z 
 56%|█████▌    | 3185/5712 [7:30:06<6:01:05,  8.57s/it]08/04/2024 17:08:14 - INFO - __main__ -   Step: 3185, LR: 2.457227802232544e-07, Loss: 0.17205649614334106
2024-08-05T00:08:23.773510336Z 
 56%|█████▌    | 3186/5712 [7:30:14<6:03:37,  8.64s/it]08/04/2024 17:08:23 - INFO - __main__ -   Step: 3186, LR: 2.4562550159293756e-07, Loss: 0.11862469464540482
2024-08-05T00:08:31.967474907Z 
 56%|█████▌    | 3187/5712 [7:30:23<5:57:52,  8.50s/it]08/04/2024 17:08:31 - INFO - __main__ -   Step: 3187, LR: 2.4552822296262066e-07, Loss: 0.12199724465608597
2024-08-05T00:08:40.245914591Z 
 56%|█████▌    | 3188/5712 [7:30:31<5:54:53,  8.44s/it]08/04/2024 17:08:40 - INFO - __main__ -   Step: 3188, LR: 2.454309443323038e-07, Loss: 0.09936921298503876
2024-08-05T00:08:48.959679308Z 
 56%|█████▌    | 3189/5712 [7:30:40<5:58:15,  8.52s/it]08/04/2024 17:08:48 - INFO - __main__ -   Step: 3189, LR: 2.453336657019869e-07, Loss: 0.22371065616607666
2024-08-05T00:08:57.290651215Z 
 56%|█████▌    | 3190/5712 [7:30:48<5:55:43,  8.46s/it]08/04/2024 17:08:57 - INFO - __main__ -   Step: 3190, LR: 2.4523638707167e-07, Loss: 0.161958247423172
2024-08-05T00:09:06.173766999Z 
 56%|█████▌    | 3191/5712 [7:30:57<6:00:53,  8.59s/it]08/04/2024 17:09:06 - INFO - __main__ -   Step: 3191, LR: 2.451391084413531e-07, Loss: 0.14804789423942566
2024-08-05T00:09:14.554121348Z 
 56%|█████▌    | 3192/5712 [7:31:05<5:58:06,  8.53s/it]08/04/2024 17:09:14 - INFO - __main__ -   Step: 3192, LR: 2.4504182981103626e-07, Loss: 0.15589044988155365
2024-08-05T00:09:22.581257662Z 
 56%|█████▌    | 3193/5712 [7:31:13<5:51:40,  8.38s/it]08/04/2024 17:09:22 - INFO - __main__ -   Step: 3193, LR: 2.4494455118071936e-07, Loss: 0.27571988105773926
2024-08-05T00:09:31.343828713Z 
 56%|█████▌    | 3194/5712 [7:31:22<5:56:24,  8.49s/it]08/04/2024 17:09:31 - INFO - __main__ -   Step: 3194, LR: 2.4484727255040246e-07, Loss: 0.18158948421478271
2024-08-05T00:09:40.051763007Z 
 56%|█████▌    | 3195/5712 [7:31:31<5:58:57,  8.56s/it]08/04/2024 17:09:40 - INFO - __main__ -   Step: 3195, LR: 2.447499939200856e-07, Loss: 0.1864064335823059
2024-08-05T00:09:48.421099397Z 
 56%|█████▌    | 3196/5712 [7:31:39<5:56:27,  8.50s/it]08/04/2024 17:09:48 - INFO - __main__ -   Step: 3196, LR: 2.446527152897687e-07, Loss: 0.12466146796941757
2024-08-05T00:09:56.872425145Z 
 56%|█████▌    | 3197/5712 [7:31:48<5:55:42,  8.49s/it]08/04/2024 17:09:56 - INFO - __main__ -   Step: 3197, LR: 2.445554366594518e-07, Loss: 0.16620512306690216
2024-08-05T00:10:05.574015405Z 
 56%|█████▌    | 3198/5712 [7:31:56<5:58:16,  8.55s/it]08/04/2024 17:10:05 - INFO - __main__ -   Step: 3198, LR: 2.4445815802913496e-07, Loss: 0.12432743608951569
2024-08-05T00:10:14.462499788Z 
 56%|█████▌    | 3199/5712 [7:32:05<6:02:22,  8.65s/it]08/04/2024 17:10:14 - INFO - __main__ -   Step: 3199, LR: 2.4436087939881806e-07, Loss: 0.37566351890563965
2024-08-05T00:10:23.297905115Z 
 56%|█████▌    | 3200/5712 [7:32:14<6:04:31,  8.71s/it]08/04/2024 17:10:23 - INFO - __main__ -   Step: 3200, LR: 2.4426360076850116e-07, Loss: 0.2596263587474823
2024-08-05T00:10:31.466246102Z 
 56%|█████▌    | 3201/5712 [7:32:22<5:57:37,  8.55s/it]08/04/2024 17:10:31 - INFO - __main__ -   Step: 3201, LR: 2.4416632213818426e-07, Loss: 0.22220896184444427
2024-08-05T00:10:40.222652172Z 
 56%|█████▌    | 3202/5712 [7:32:31<6:00:08,  8.61s/it]08/04/2024 17:10:40 - INFO - __main__ -   Step: 3202, LR: 2.440690435078674e-07, Loss: 0.19704608619213104
2024-08-05T00:10:48.403771570Z 
 56%|█████▌    | 3203/5712 [7:32:39<5:54:37,  8.48s/it]08/04/2024 17:10:48 - INFO - __main__ -   Step: 3203, LR: 2.439717648775505e-07, Loss: 0.08906318992376328
2024-08-05T00:10:57.076219281Z 
 56%|█████▌    | 3204/5712 [7:32:48<5:56:52,  8.54s/it]08/04/2024 17:10:57 - INFO - __main__ -   Step: 3204, LR: 2.4387448624723366e-07, Loss: 0.06952834129333496
2024-08-05T00:11:05.274750312Z 
 56%|█████▌    | 3205/5712 [7:32:56<5:52:29,  8.44s/it]08/04/2024 17:11:05 - INFO - __main__ -   Step: 3205, LR: 2.4377720761691676e-07, Loss: 0.19708025455474854
2024-08-05T00:11:13.735745982Z 
 56%|█████▌    | 3206/5712 [7:33:04<5:52:39,  8.44s/it]08/04/2024 17:11:13 - INFO - __main__ -   Step: 3206, LR: 2.4367992898659986e-07, Loss: 0.147536501288414
2024-08-05T00:11:22.468945085Z 
 56%|█████▌    | 3207/5712 [7:33:13<5:56:08,  8.53s/it]08/04/2024 17:11:22 - INFO - __main__ -   Step: 3207, LR: 2.4358265035628296e-07, Loss: 0.1451333463191986
2024-08-05T00:11:31.235342619Z 
 56%|█████▌    | 3208/5712 [7:33:22<5:58:57,  8.60s/it]08/04/2024 17:11:31 - INFO - __main__ -   Step: 3208, LR: 2.434853717259661e-07, Loss: 0.13581088185310364
2024-08-05T00:11:39.600917908Z 
 56%|█████▌    | 3209/5712 [7:33:30<5:55:52,  8.53s/it]08/04/2024 17:11:39 - INFO - __main__ -   Step: 3209, LR: 2.433880930956492e-07, Loss: 0.1881580501794815
2024-08-05T00:11:47.753267010Z 
 56%|█████▌    | 3210/5712 [7:33:38<5:50:59,  8.42s/it]08/04/2024 17:11:47 - INFO - __main__ -   Step: 3210, LR: 2.432908144653323e-07, Loss: 0.19862160086631775
2024-08-05T00:11:56.512534038Z 
 56%|█████▌    | 3211/5712 [7:33:47<5:55:08,  8.52s/it]08/04/2024 17:11:56 - INFO - __main__ -   Step: 3211, LR: 2.431935358350154e-07, Loss: 0.17114165425300598
2024-08-05T00:12:05.095326687Z 
 56%|█████▌    | 3212/5712 [7:33:56<5:55:46,  8.54s/it]08/04/2024 17:12:05 - INFO - __main__ -   Step: 3212, LR: 2.430962572046985e-07, Loss: 0.12014113366603851
2024-08-05T00:12:13.564843839Z 
 56%|█████▋    | 3213/5712 [7:34:04<5:54:46,  8.52s/it]08/04/2024 17:12:13 - INFO - __main__ -   Step: 3213, LR: 2.4299897857438166e-07, Loss: 0.22588901221752167
2024-08-05T00:12:22.223546326Z 
 56%|█████▋    | 3214/5712 [7:34:13<5:56:23,  8.56s/it]08/04/2024 17:12:22 - INFO - __main__ -   Step: 3214, LR: 2.4290169994406476e-07, Loss: 0.20008349418640137
2024-08-05T00:12:30.870677555Z 
 56%|█████▋    | 3215/5712 [7:34:22<5:57:19,  8.59s/it]08/04/2024 17:12:30 - INFO - __main__ -   Step: 3215, LR: 2.428044213137479e-07, Loss: 0.15728335082530975
2024-08-05T00:12:40.135675847Z 
 56%|█████▋    | 3216/5712 [7:34:31<6:05:39,  8.79s/it]08/04/2024 17:12:40 - INFO - __main__ -   Step: 3216, LR: 2.42707142683431e-07, Loss: 0.21611222624778748
2024-08-05T00:12:48.180782007Z 
 56%|█████▋    | 3217/5712 [7:34:39<5:56:12,  8.57s/it]08/04/2024 17:12:48 - INFO - __main__ -   Step: 3217, LR: 2.426098640531141e-07, Loss: 0.13054300844669342
2024-08-05T00:12:56.599542658Z 
 56%|█████▋    | 3218/5712 [7:34:47<5:54:14,  8.52s/it]08/04/2024 17:12:56 - INFO - __main__ -   Step: 3218, LR: 2.425125854227972e-07, Loss: 0.13290055096149445
2024-08-05T00:13:05.248089713Z 
 56%|█████▋    | 3219/5712 [7:34:56<5:55:39,  8.56s/it]08/04/2024 17:13:05 - INFO - __main__ -   Step: 3219, LR: 2.4241530679248036e-07, Loss: 0.26162537932395935
2024-08-05T00:13:13.515349229Z 
 56%|█████▋    | 3220/5712 [7:35:04<5:51:52,  8.47s/it]08/04/2024 17:13:13 - INFO - __main__ -   Step: 3220, LR: 2.4231802816216346e-07, Loss: 0.15969817340373993
2024-08-05T00:13:21.776421945Z 
 56%|█████▋    | 3221/5712 [7:35:12<5:49:06,  8.41s/it]08/04/2024 17:13:21 - INFO - __main__ -   Step: 3221, LR: 2.4222074953184656e-07, Loss: 0.12852783501148224
2024-08-05T00:13:30.373431405Z 
 56%|█████▋    | 3222/5712 [7:35:21<5:51:18,  8.47s/it]08/04/2024 17:13:30 - INFO - __main__ -   Step: 3222, LR: 2.421234709015297e-07, Loss: 0.22954799234867096
2024-08-05T00:13:38.569108099Z 
 56%|█████▋    | 3223/5712 [7:35:29<5:47:48,  8.38s/it]08/04/2024 17:13:38 - INFO - __main__ -   Step: 3223, LR: 2.420261922712128e-07, Loss: 0.15302875638008118
2024-08-05T00:13:47.002311345Z 
 56%|█████▋    | 3224/5712 [7:35:38<5:48:17,  8.40s/it]08/04/2024 17:13:47 - INFO - __main__ -   Step: 3224, LR: 2.419289136408959e-07, Loss: 0.16015611588954926
2024-08-05T00:13:55.202020440Z 
 56%|█████▋    | 3225/5712 [7:35:46<5:45:39,  8.34s/it]08/04/2024 17:13:55 - INFO - __main__ -   Step: 3225, LR: 2.4183163501057906e-07, Loss: 0.21121710538864136
2024-08-05T00:14:03.785025353Z 
 56%|█████▋    | 3226/5712 [7:35:54<5:48:33,  8.41s/it]08/04/2024 17:14:03 - INFO - __main__ -   Step: 3226, LR: 2.4173435638026216e-07, Loss: 0.15363264083862305
2024-08-05T00:14:12.150129515Z 
 56%|█████▋    | 3227/5712 [7:36:03<5:47:49,  8.40s/it]08/04/2024 17:14:12 - INFO - __main__ -   Step: 3227, LR: 2.4163707774994526e-07, Loss: 0.19628998637199402
2024-08-05T00:14:20.942956984Z 
 57%|█████▋    | 3228/5712 [7:36:12<5:52:35,  8.52s/it]08/04/2024 17:14:20 - INFO - __main__ -   Step: 3228, LR: 2.4153979911962836e-07, Loss: 0.21871116757392883
2024-08-05T00:14:29.148917136Z 
 57%|█████▋    | 3229/5712 [7:36:20<5:48:35,  8.42s/it]08/04/2024 17:14:29 - INFO - __main__ -   Step: 3229, LR: 2.414425204893115e-07, Loss: 0.18640394508838654
2024-08-05T00:14:37.830038762Z 
 57%|█████▋    | 3230/5712 [7:36:28<5:51:38,  8.50s/it]08/04/2024 17:14:37 - INFO - __main__ -   Step: 3230, LR: 2.413452418589946e-07, Loss: 0.12365054339170456
2024-08-05T00:14:46.312693285Z 
 57%|█████▋    | 3231/5712 [7:36:37<5:51:16,  8.50s/it]08/04/2024 17:14:46 - INFO - __main__ -   Step: 3231, LR: 2.4124796322867776e-07, Loss: 0.21345794200897217
2024-08-05T00:14:55.487265389Z 
 57%|█████▋    | 3232/5712 [7:36:46<5:59:33,  8.70s/it]08/04/2024 17:14:55 - INFO - __main__ -   Step: 3232, LR: 2.4115068459836086e-07, Loss: 0.2152964025735855
2024-08-05T00:15:03.933912930Z 
 57%|█████▋    | 3233/5712 [7:36:55<5:56:17,  8.62s/it]08/04/2024 17:15:03 - INFO - __main__ -   Step: 3233, LR: 2.4105340596804396e-07, Loss: 0.21073924005031586
2024-08-05T00:15:12.826506621Z 
 57%|█████▋    | 3234/5712 [7:37:03<5:59:28,  8.70s/it]08/04/2024 17:15:12 - INFO - __main__ -   Step: 3234, LR: 2.4095612733772706e-07, Loss: 0.45984017848968506
2024-08-05T00:15:21.783855897Z 
 57%|█████▋    | 3235/5712 [7:37:12<6:02:28,  8.78s/it]08/04/2024 17:15:21 - INFO - __main__ -   Step: 3235, LR: 2.408588487074102e-07, Loss: 0.11888403445482254
2024-08-05T00:15:30.067827271Z 
 57%|█████▋    | 3236/5712 [7:37:21<5:56:10,  8.63s/it]08/04/2024 17:15:30 - INFO - __main__ -   Step: 3236, LR: 2.407615700770933e-07, Loss: 0.26079684495925903
2024-08-05T00:15:38.146375579Z 
 57%|█████▋    | 3237/5712 [7:37:29<5:49:11,  8.47s/it]08/04/2024 17:15:38 - INFO - __main__ -   Step: 3237, LR: 2.406642914467764e-07, Loss: 0.2045619785785675
2024-08-05T00:15:46.561360759Z 
 57%|█████▋    | 3238/5712 [7:37:37<5:48:26,  8.45s/it]08/04/2024 17:15:46 - INFO - __main__ -   Step: 3238, LR: 2.405670128164595e-07, Loss: 0.1434558629989624
2024-08-05T00:15:54.767212379Z 
 57%|█████▋    | 3239/5712 [7:37:45<5:45:16,  8.38s/it]08/04/2024 17:15:54 - INFO - __main__ -   Step: 3239, LR: 2.4046973418614266e-07, Loss: 0.17290613055229187
2024-08-05T00:16:03.672660399Z 
 57%|█████▋    | 3240/5712 [7:37:54<5:51:39,  8.54s/it]08/04/2024 17:16:03 - INFO - __main__ -   Step: 3240, LR: 2.4037245555582576e-07, Loss: 0.2149128019809723
2024-08-05T00:16:12.131500787Z 
 57%|█████▋    | 3241/5712 [7:38:03<5:50:34,  8.51s/it]08/04/2024 17:16:12 - INFO - __main__ -   Step: 3241, LR: 2.402751769255089e-07, Loss: 0.258385568857193
2024-08-05T00:16:20.370443342Z 
 57%|█████▋    | 3242/5712 [7:38:11<5:47:03,  8.43s/it]08/04/2024 17:16:20 - INFO - __main__ -   Step: 3242, LR: 2.40177898295192e-07, Loss: 0.10851743817329407
2024-08-05T00:16:29.272826622Z 
 57%|█████▋    | 3243/5712 [7:38:20<5:52:44,  8.57s/it]08/04/2024 17:16:29 - INFO - __main__ -   Step: 3243, LR: 2.400806196648751e-07, Loss: 0.19303756952285767
2024-08-05T00:16:37.459439292Z 
 57%|█████▋    | 3244/5712 [7:38:28<5:47:50,  8.46s/it]08/04/2024 17:16:37 - INFO - __main__ -   Step: 3244, LR: 2.399833410345582e-07, Loss: 0.2179696261882782
2024-08-05T00:16:45.634147302Z 
 57%|█████▋    | 3245/5712 [7:38:36<5:44:13,  8.37s/it]08/04/2024 17:16:45 - INFO - __main__ -   Step: 3245, LR: 2.3988606240424136e-07, Loss: 0.21114888787269592
2024-08-05T00:16:54.675463882Z 
 57%|█████▋    | 3246/5712 [7:38:45<5:52:20,  8.57s/it]08/04/2024 17:16:54 - INFO - __main__ -   Step: 3246, LR: 2.3978878377392446e-07, Loss: 0.18161948025226593
2024-08-05T00:17:03.260241707Z 
 57%|█████▋    | 3247/5712 [7:38:54<5:52:20,  8.58s/it]08/04/2024 17:17:03 - INFO - __main__ -   Step: 3247, LR: 2.3969150514360756e-07, Loss: 0.26046597957611084
2024-08-05T00:17:12.285830783Z 
 57%|█████▋    | 3248/5712 [7:39:03<5:57:44,  8.71s/it]08/04/2024 17:17:12 - INFO - __main__ -   Step: 3248, LR: 2.3959422651329066e-07, Loss: 0.3643895089626312
2024-08-05T00:17:20.892541154Z 
 57%|█████▋    | 3249/5712 [7:39:12<5:56:18,  8.68s/it]08/04/2024 17:17:20 - INFO - __main__ -   Step: 3249, LR: 2.394969478829738e-07, Loss: 0.1604645699262619
2024-08-05T00:17:29.098735565Z 
 57%|█████▋    | 3250/5712 [7:39:20<5:50:19,  8.54s/it]08/04/2024 17:17:29 - INFO - __main__ -   Step: 3250, LR: 2.393996692526569e-07, Loss: 0.14832156896591187
2024-08-05T00:17:38.070586730Z 
 57%|█████▋    | 3251/5712 [7:39:29<5:55:30,  8.67s/it]08/04/2024 17:17:38 - INFO - __main__ -   Step: 3251, LR: 2.3930239062234e-07, Loss: 0.1941300928592682
2024-08-05T00:17:46.864676354Z 
 57%|█████▋    | 3252/5712 [7:39:38<5:56:56,  8.71s/it]08/04/2024 17:17:46 - INFO - __main__ -   Step: 3252, LR: 2.3920511199202316e-07, Loss: 0.14057977497577667
2024-08-05T00:17:55.388766346Z 
 57%|█████▋    | 3253/5712 [7:39:46<5:54:33,  8.65s/it]08/04/2024 17:17:55 - INFO - __main__ -   Step: 3253, LR: 2.3910783336170626e-07, Loss: 0.16564038395881653
2024-08-05T00:18:03.387080044Z 
 57%|█████▋    | 3254/5712 [7:39:54<5:46:23,  8.46s/it]08/04/2024 17:18:03 - INFO - __main__ -   Step: 3254, LR: 2.3901055473138936e-07, Loss: 0.27601563930511475
2024-08-05T00:18:11.974519739Z 
 57%|█████▋    | 3255/5712 [7:40:03<5:47:52,  8.50s/it]08/04/2024 17:18:11 - INFO - __main__ -   Step: 3255, LR: 2.3891327610107246e-07, Loss: 0.19294090569019318
2024-08-05T00:18:20.526842925Z 
 57%|█████▋    | 3256/5712 [7:40:11<5:48:25,  8.51s/it]08/04/2024 17:18:20 - INFO - __main__ -   Step: 3256, LR: 2.388159974707556e-07, Loss: 0.19222919642925262
2024-08-05T00:18:28.712639312Z 
 57%|█████▋    | 3257/5712 [7:40:19<5:44:17,  8.41s/it]08/04/2024 17:18:28 - INFO - __main__ -   Step: 3257, LR: 2.387187188404387e-07, Loss: 0.2619585394859314
2024-08-05T00:18:37.573830024Z 
 57%|█████▋    | 3258/5712 [7:40:28<5:49:37,  8.55s/it]08/04/2024 17:18:37 - INFO - __main__ -   Step: 3258, LR: 2.3862144021012186e-07, Loss: 0.12240248918533325
2024-08-05T00:18:45.950933840Z 
 57%|█████▋    | 3259/5712 [7:40:37<5:47:23,  8.50s/it]08/04/2024 17:18:45 - INFO - __main__ -   Step: 3259, LR: 2.3852416157980496e-07, Loss: 0.20748600363731384
2024-08-05T00:18:54.423226472Z 
 57%|█████▋    | 3260/5712 [7:40:45<5:46:56,  8.49s/it]08/04/2024 17:18:54 - INFO - __main__ -   Step: 3260, LR: 2.3842688294948806e-07, Loss: 0.16827592253684998
2024-08-05T00:19:02.975586992Z 
 57%|█████▋    | 3261/5712 [7:40:54<5:47:34,  8.51s/it]08/04/2024 17:19:02 - INFO - __main__ -   Step: 3261, LR: 2.3832960431917118e-07, Loss: 0.12494658678770065
2024-08-05T00:19:11.216284832Z 
 57%|█████▋    | 3262/5712 [7:41:02<5:44:09,  8.43s/it]08/04/2024 17:19:11 - INFO - __main__ -   Step: 3262, LR: 2.3823232568885428e-07, Loss: 0.21891182661056519
2024-08-05T00:19:19.509441787Z 
 57%|█████▋    | 3263/5712 [7:41:10<5:42:21,  8.39s/it]08/04/2024 17:19:19 - INFO - __main__ -   Step: 3263, LR: 2.381350470585374e-07, Loss: 0.16912755370140076
2024-08-05T00:19:27.896405486Z 
 57%|█████▋    | 3264/5712 [7:41:19<5:42:12,  8.39s/it]08/04/2024 17:19:27 - INFO - __main__ -   Step: 3264, LR: 2.380377684282205e-07, Loss: 0.12735113501548767
2024-08-05T00:19:36.578603109Z 
 57%|█████▋    | 3265/5712 [7:41:27<5:45:40,  8.48s/it]08/04/2024 17:19:36 - INFO - __main__ -   Step: 3265, LR: 2.3794048979790363e-07, Loss: 0.15773309767246246
2024-08-05T00:19:44.778162613Z 
 57%|█████▋    | 3266/5712 [7:41:35<5:42:09,  8.39s/it]08/04/2024 17:19:44 - INFO - __main__ -   Step: 3266, LR: 2.3784321116758673e-07, Loss: 0.11521114408969879
2024-08-05T00:19:53.247997298Z 
 57%|█████▋    | 3267/5712 [7:41:44<5:42:57,  8.42s/it]08/04/2024 17:19:53 - INFO - __main__ -   Step: 3267, LR: 2.3774593253726988e-07, Loss: 0.11819137632846832
2024-08-05T00:20:01.986085692Z 
 57%|█████▋    | 3268/5712 [7:41:53<5:46:44,  8.51s/it]08/04/2024 17:20:01 - INFO - __main__ -   Step: 3268, LR: 2.3764865390695298e-07, Loss: 0.2202933430671692
2024-08-05T00:20:10.031740259Z 
 57%|█████▋    | 3269/5712 [7:42:01<5:40:54,  8.37s/it]08/04/2024 17:20:10 - INFO - __main__ -   Step: 3269, LR: 2.375513752766361e-07, Loss: 0.09026074409484863
2024-08-05T00:20:18.295813444Z 
 57%|█████▋    | 3270/5712 [7:42:09<5:39:26,  8.34s/it]08/04/2024 17:20:18 - INFO - __main__ -   Step: 3270, LR: 2.374540966463192e-07, Loss: 0.18090766668319702
2024-08-05T00:20:26.534776496Z 
 57%|█████▋    | 3271/5712 [7:42:17<5:38:04,  8.31s/it]08/04/2024 17:20:26 - INFO - __main__ -   Step: 3271, LR: 2.3735681801600233e-07, Loss: 0.13021738827228546
2024-08-05T00:20:35.005832884Z 
 57%|█████▋    | 3272/5712 [7:42:26<5:39:53,  8.36s/it]08/04/2024 17:20:35 - INFO - __main__ -   Step: 3272, LR: 2.3725953938568543e-07, Loss: 0.22858475148677826
2024-08-05T00:20:43.496427526Z 
 57%|█████▋    | 3273/5712 [7:42:34<5:41:22,  8.40s/it]08/04/2024 17:20:43 - INFO - __main__ -   Step: 3273, LR: 2.3716226075536856e-07, Loss: 0.15919002890586853
2024-08-05T00:20:51.878557791Z 
 57%|█████▋    | 3274/5712 [7:42:43<5:41:02,  8.39s/it]08/04/2024 17:20:51 - INFO - __main__ -   Step: 3274, LR: 2.3706498212505166e-07, Loss: 0.3076062500476837
2024-08-05T00:21:00.614609956Z 
 57%|█████▋    | 3275/5712 [7:42:51<5:45:04,  8.50s/it]08/04/2024 17:21:00 - INFO - __main__ -   Step: 3275, LR: 2.3696770349473478e-07, Loss: 0.14468668401241302
2024-08-05T00:21:09.075973828Z 
 57%|█████▋    | 3276/5712 [7:43:00<5:44:30,  8.49s/it]08/04/2024 17:21:09 - INFO - __main__ -   Step: 3276, LR: 2.368704248644179e-07, Loss: 0.15341295301914215
2024-08-05T00:21:17.463654486Z 
 57%|█████▋    | 3277/5712 [7:43:08<5:43:10,  8.46s/it]08/04/2024 17:21:17 - INFO - __main__ -   Step: 3277, LR: 2.3677314623410103e-07, Loss: 0.2159181535243988
2024-08-05T00:21:25.767859783Z 
 57%|█████▋    | 3278/5712 [7:43:16<5:41:11,  8.41s/it]08/04/2024 17:21:25 - INFO - __main__ -   Step: 3278, LR: 2.3667586760378413e-07, Loss: 0.22244134545326233
2024-08-05T00:21:33.998355863Z 
 57%|█████▋    | 3279/5712 [7:43:25<5:38:51,  8.36s/it]08/04/2024 17:21:33 - INFO - __main__ -   Step: 3279, LR: 2.3657858897346726e-07, Loss: 0.1763913631439209
2024-08-05T00:21:42.083760259Z 
 57%|█████▋    | 3280/5712 [7:43:33<5:35:25,  8.28s/it]08/04/2024 17:21:42 - INFO - __main__ -   Step: 3280, LR: 2.3648131034315036e-07, Loss: 0.19745700061321259
2024-08-05T00:21:51.282532786Z 
 57%|█████▋    | 3281/5712 [7:43:42<5:46:30,  8.55s/it]08/04/2024 17:21:51 - INFO - __main__ -   Step: 3281, LR: 2.3638403171283348e-07, Loss: 0.18543589115142822
2024-08-05T00:21:59.448550547Z 
 57%|█████▋    | 3282/5712 [7:43:50<5:41:40,  8.44s/it]08/04/2024 17:21:59 - INFO - __main__ -   Step: 3282, LR: 2.3628675308251658e-07, Loss: 0.2118397206068039
2024-08-05T00:22:08.146621148Z 
 57%|█████▋    | 3283/5712 [7:43:59<5:44:42,  8.52s/it]08/04/2024 17:22:08 - INFO - __main__ -   Step: 3283, LR: 2.361894744521997e-07, Loss: 0.12463262677192688
2024-08-05T00:22:17.059248217Z 
 57%|█████▋    | 3284/5712 [7:44:08<5:49:23,  8.63s/it]08/04/2024 17:22:17 - INFO - __main__ -   Step: 3284, LR: 2.360921958218828e-07, Loss: 0.14855076372623444
2024-08-05T00:22:25.589470068Z 
 58%|█████▊    | 3285/5712 [7:44:16<5:47:58,  8.60s/it]08/04/2024 17:22:25 - INFO - __main__ -   Step: 3285, LR: 2.3599491719156596e-07, Loss: 0.17516596615314484
2024-08-05T00:22:34.144182365Z 
 58%|█████▊    | 3286/5712 [7:44:25<5:47:15,  8.59s/it]08/04/2024 17:22:34 - INFO - __main__ -   Step: 3286, LR: 2.3589763856124906e-07, Loss: 0.21768827736377716
2024-08-05T00:22:42.343446899Z 
 58%|█████▊    | 3287/5712 [7:44:33<5:42:24,  8.47s/it]08/04/2024 17:22:42 - INFO - __main__ -   Step: 3287, LR: 2.3580035993093218e-07, Loss: 0.1738191694021225
2024-08-05T00:22:50.520305873Z 
 58%|█████▊    | 3288/5712 [7:44:41<5:38:41,  8.38s/it]08/04/2024 17:22:50 - INFO - __main__ -   Step: 3288, LR: 2.3570308130061528e-07, Loss: 0.2141100913286209
2024-08-05T00:22:59.427188843Z 
 58%|█████▊    | 3289/5712 [7:44:50<5:44:53,  8.54s/it]08/04/2024 17:22:59 - INFO - __main__ -   Step: 3289, LR: 2.3560580267029838e-07, Loss: 0.2503092885017395
2024-08-05T00:23:07.752401460Z 
 58%|█████▊    | 3290/5712 [7:44:58<5:42:08,  8.48s/it]08/04/2024 17:23:07 - INFO - __main__ -   Step: 3290, LR: 2.355085240399815e-07, Loss: 0.13648217916488647
2024-08-05T00:23:15.874524199Z 
 58%|█████▊    | 3291/5712 [7:45:07<5:37:43,  8.37s/it]08/04/2024 17:23:15 - INFO - __main__ -   Step: 3291, LR: 2.354112454096646e-07, Loss: 0.11500146985054016
2024-08-05T00:23:24.401852596Z 
 58%|█████▊    | 3292/5712 [7:45:15<5:39:28,  8.42s/it]08/04/2024 17:23:24 - INFO - __main__ -   Step: 3292, LR: 2.3531396677934773e-07, Loss: 0.17376244068145752
2024-08-05T00:23:32.593160005Z 
 58%|█████▊    | 3293/5712 [7:45:23<5:36:36,  8.35s/it]08/04/2024 17:23:32 - INFO - __main__ -   Step: 3293, LR: 2.3521668814903083e-07, Loss: 0.17819622159004211
2024-08-05T00:23:40.876117629Z 
 58%|█████▊    | 3294/5712 [7:45:32<5:35:40,  8.33s/it]08/04/2024 17:23:40 - INFO - __main__ -   Step: 3294, LR: 2.3511940951871398e-07, Loss: 0.2894638478755951
2024-08-05T00:23:49.715494633Z 
 58%|█████▊    | 3295/5712 [7:45:40<5:41:42,  8.48s/it]08/04/2024 17:23:49 - INFO - __main__ -   Step: 3295, LR: 2.3502213088839708e-07, Loss: 0.23093806207180023
2024-08-05T00:23:57.620322479Z 
 58%|█████▊    | 3296/5712 [7:45:48<5:34:34,  8.31s/it]08/04/2024 17:23:57 - INFO - __main__ -   Step: 3296, LR: 2.349248522580802e-07, Loss: 0.26029717922210693
2024-08-05T00:24:06.274396779Z 
 58%|█████▊    | 3297/5712 [7:45:57<5:38:36,  8.41s/it]08/04/2024 17:24:06 - INFO - __main__ -   Step: 3297, LR: 2.348275736277633e-07, Loss: 0.2453770637512207
2024-08-05T00:24:14.644068782Z 
 58%|█████▊    | 3298/5712 [7:46:05<5:37:56,  8.40s/it]08/04/2024 17:24:14 - INFO - __main__ -   Step: 3298, LR: 2.3473029499744643e-07, Loss: 0.15836358070373535
2024-08-05T00:24:23.256638085Z 
 58%|█████▊    | 3299/5712 [7:46:14<5:40:22,  8.46s/it]08/04/2024 17:24:23 - INFO - __main__ -   Step: 3299, LR: 2.3463301636712953e-07, Loss: 0.15461745858192444
2024-08-05T00:24:32.558160309Z 
 58%|█████▊    | 3300/5712 [7:46:23<5:50:20,  8.71s/it]08/04/2024 17:24:32 - INFO - __main__ -   Step: 3300, LR: 2.3453573773681265e-07, Loss: 0.14493444561958313
2024-08-05T00:24:41.089786683Z 
 58%|█████▊    | 3301/5712 [7:46:32<5:47:59,  8.66s/it]08/04/2024 17:24:41 - INFO - __main__ -   Step: 3301, LR: 2.3443845910649575e-07, Loss: 0.18211600184440613
2024-08-05T00:24:49.618163009Z 
 58%|█████▊    | 3302/5712 [7:46:40<5:46:14,  8.62s/it]08/04/2024 17:24:49 - INFO - __main__ -   Step: 3302, LR: 2.3434118047617888e-07, Loss: 0.2180621474981308
2024-08-05T00:24:57.775651058Z 
 58%|█████▊    | 3303/5712 [7:46:48<5:40:32,  8.48s/it]08/04/2024 17:24:57 - INFO - __main__ -   Step: 3303, LR: 2.34243901845862e-07, Loss: 0.3020939826965332
2024-08-05T00:25:06.089703693Z 
 58%|█████▊    | 3304/5712 [7:46:57<5:38:22,  8.43s/it]08/04/2024 17:25:06 - INFO - __main__ -   Step: 3304, LR: 2.3414662321554513e-07, Loss: 0.15773290395736694
2024-08-05T00:25:14.515788731Z 
 58%|█████▊    | 3305/5712 [7:47:05<5:38:10,  8.43s/it]08/04/2024 17:25:14 - INFO - __main__ -   Step: 3305, LR: 2.3404934458522823e-07, Loss: 0.14271153509616852
2024-08-05T00:25:23.073333204Z 
 58%|█████▊    | 3306/5712 [7:47:14<5:39:34,  8.47s/it]08/04/2024 17:25:23 - INFO - __main__ -   Step: 3306, LR: 2.3395206595491135e-07, Loss: 0.20151649415493011
2024-08-05T00:25:31.514101313Z 
 58%|█████▊    | 3307/5712 [7:47:22<5:39:06,  8.46s/it]08/04/2024 17:25:31 - INFO - __main__ -   Step: 3307, LR: 2.3385478732459445e-07, Loss: 0.2495720386505127
2024-08-05T00:25:39.666602572Z 
 58%|█████▊    | 3308/5712 [7:47:30<5:35:16,  8.37s/it]08/04/2024 17:25:39 - INFO - __main__ -   Step: 3308, LR: 2.3375750869427758e-07, Loss: 0.1454504132270813
2024-08-05T00:25:48.256595542Z 
 58%|█████▊    | 3309/5712 [7:47:39<5:37:47,  8.43s/it]08/04/2024 17:25:48 - INFO - __main__ -   Step: 3309, LR: 2.3366023006396068e-07, Loss: 0.20879608392715454
2024-08-05T00:25:56.528496820Z 
 58%|█████▊    | 3310/5712 [7:47:47<5:35:42,  8.39s/it]08/04/2024 17:25:56 - INFO - __main__ -   Step: 3310, LR: 2.335629514336438e-07, Loss: 0.14787110686302185
2024-08-05T00:26:04.791641946Z 
 58%|█████▊    | 3311/5712 [7:47:55<5:34:05,  8.35s/it]08/04/2024 17:26:04 - INFO - __main__ -   Step: 3311, LR: 2.334656728033269e-07, Loss: 0.21408364176750183
2024-08-05T00:26:13.133294413Z 
 58%|█████▊    | 3312/5712 [7:48:04<5:33:51,  8.35s/it]08/04/2024 17:26:13 - INFO - __main__ -   Step: 3312, LR: 2.3336839417301006e-07, Loss: 0.15529072284698486
2024-08-05T00:26:21.746488671Z 
 58%|█████▊    | 3313/5712 [7:48:12<5:36:55,  8.43s/it]08/04/2024 17:26:21 - INFO - __main__ -   Step: 3313, LR: 2.3327111554269315e-07, Loss: 0.17814446985721588
2024-08-05T00:26:30.735813454Z 
 58%|█████▊    | 3314/5712 [7:48:21<5:43:31,  8.60s/it]08/04/2024 17:26:30 - INFO - __main__ -   Step: 3314, LR: 2.3317383691237628e-07, Loss: 0.15514309704303741
2024-08-05T00:26:38.676622199Z 
 58%|█████▊    | 3315/5712 [7:48:29<5:35:32,  8.40s/it]08/04/2024 17:26:38 - INFO - __main__ -   Step: 3315, LR: 2.3307655828205938e-07, Loss: 0.23316042125225067
2024-08-05T00:26:47.772059438Z 
 58%|█████▊    | 3316/5712 [7:48:38<5:43:44,  8.61s/it]08/04/2024 17:26:47 - INFO - __main__ -   Step: 3316, LR: 2.329792796517425e-07, Loss: 0.19207443296909332
2024-08-05T00:26:56.275289705Z 
 58%|█████▊    | 3317/5712 [7:48:47<5:42:20,  8.58s/it]08/04/2024 17:26:56 - INFO - __main__ -   Step: 3317, LR: 2.328820010214256e-07, Loss: 0.22685031592845917
2024-08-05T00:27:04.309886184Z 
 58%|█████▊    | 3318/5712 [7:48:55<5:35:42,  8.41s/it]08/04/2024 17:27:04 - INFO - __main__ -   Step: 3318, LR: 2.3278472239110873e-07, Loss: 0.17808955907821655
2024-08-05T00:27:13.216366344Z 
 58%|█████▊    | 3319/5712 [7:49:04<5:41:27,  8.56s/it]08/04/2024 17:27:13 - INFO - __main__ -   Step: 3319, LR: 2.3268744376079183e-07, Loss: 0.1730087250471115
2024-08-05T00:27:21.756281811Z 
 58%|█████▊    | 3320/5712 [7:49:12<5:41:04,  8.56s/it]08/04/2024 17:27:21 - INFO - __main__ -   Step: 3320, LR: 2.3259016513047495e-07, Loss: 0.25787046551704407
2024-08-05T00:27:30.162348470Z 
 58%|█████▊    | 3321/5712 [7:49:21<5:39:08,  8.51s/it]08/04/2024 17:27:30 - INFO - __main__ -   Step: 3321, LR: 2.3249288650015808e-07, Loss: 0.1542869359254837
2024-08-05T00:27:38.359212872Z 
 58%|█████▊    | 3322/5712 [7:49:29<5:35:15,  8.42s/it]08/04/2024 17:27:38 - INFO - __main__ -   Step: 3322, LR: 2.323956078698412e-07, Loss: 0.11775998771190643
2024-08-05T00:27:46.859889777Z 
 58%|█████▊    | 3323/5712 [7:49:38<5:36:07,  8.44s/it]08/04/2024 17:27:46 - INFO - __main__ -   Step: 3323, LR: 2.322983292395243e-07, Loss: 0.13935795426368713
2024-08-05T00:27:55.251273251Z 
 58%|█████▊    | 3324/5712 [7:49:46<5:35:22,  8.43s/it]08/04/2024 17:27:55 - INFO - __main__ -   Step: 3324, LR: 2.3220105060920743e-07, Loss: 0.20073434710502625
2024-08-05T00:28:04.160297195Z 
 58%|█████▊    | 3325/5712 [7:49:55<5:40:59,  8.57s/it]08/04/2024 17:28:04 - INFO - __main__ -   Step: 3325, LR: 2.3210377197889053e-07, Loss: 0.1338639259338379
2024-08-05T00:28:12.811802695Z 
 58%|█████▊    | 3326/5712 [7:50:03<5:41:48,  8.60s/it]08/04/2024 17:28:12 - INFO - __main__ -   Step: 3326, LR: 2.3200649334857363e-07, Loss: 0.3170216679573059
2024-08-05T00:28:21.106855913Z 
 58%|█████▊    | 3327/5712 [7:50:12<5:38:04,  8.51s/it]08/04/2024 17:28:21 - INFO - __main__ -   Step: 3327, LR: 2.3190921471825675e-07, Loss: 0.1371161788702011
2024-08-05T00:28:29.628584708Z 
 58%|█████▊    | 3328/5712 [7:50:20<5:38:08,  8.51s/it]08/04/2024 17:28:29 - INFO - __main__ -   Step: 3328, LR: 2.3181193608793985e-07, Loss: 0.13793732225894928
2024-08-05T00:28:38.004266144Z 
 58%|█████▊    | 3329/5712 [7:50:29<5:36:23,  8.47s/it]08/04/2024 17:28:38 - INFO - __main__ -   Step: 3329, LR: 2.3171465745762298e-07, Loss: 0.24040007591247559
2024-08-05T00:28:46.387976289Z 
 58%|█████▊    | 3330/5712 [7:50:37<5:35:13,  8.44s/it]08/04/2024 17:28:46 - INFO - __main__ -   Step: 3330, LR: 2.316173788273061e-07, Loss: 0.16340148448944092
2024-08-05T00:28:54.818821287Z 
 58%|█████▊    | 3331/5712 [7:50:45<5:34:55,  8.44s/it]08/04/2024 17:28:54 - INFO - __main__ -   Step: 3331, LR: 2.3152010019698923e-07, Loss: 0.35522016882896423
2024-08-05T00:29:03.283531491Z 
 58%|█████▊    | 3332/5712 [7:50:54<5:35:04,  8.45s/it]08/04/2024 17:29:03 - INFO - __main__ -   Step: 3332, LR: 2.3142282156667233e-07, Loss: 0.1609334945678711
2024-08-05T00:29:12.117756095Z 
 58%|█████▊    | 3333/5712 [7:51:03<5:39:32,  8.56s/it]08/04/2024 17:29:12 - INFO - __main__ -   Step: 3333, LR: 2.3132554293635545e-07, Loss: 0.20844975113868713
2024-08-05T00:29:20.659448008Z 
 58%|█████▊    | 3334/5712 [7:51:11<5:39:08,  8.56s/it]08/04/2024 17:29:20 - INFO - __main__ -   Step: 3334, LR: 2.3122826430603855e-07, Loss: 0.16513465344905853
2024-08-05T00:29:29.132028000Z 
 58%|█████▊    | 3335/5712 [7:51:20<5:37:59,  8.53s/it]08/04/2024 17:29:29 - INFO - __main__ -   Step: 3335, LR: 2.3113098567572168e-07, Loss: 0.09447863698005676
2024-08-05T00:29:38.175831280Z 
 58%|█████▊    | 3336/5712 [7:51:29<5:43:55,  8.68s/it]08/04/2024 17:29:38 - INFO - __main__ -   Step: 3336, LR: 2.3103370704540478e-07, Loss: 0.1335144340991974
2024-08-05T00:29:46.434256103Z 
 58%|█████▊    | 3337/5712 [7:51:37<5:38:43,  8.56s/it]08/04/2024 17:29:46 - INFO - __main__ -   Step: 3337, LR: 2.309364284150879e-07, Loss: 0.17547395825386047
2024-08-05T00:29:55.225362075Z 
 58%|█████▊    | 3338/5712 [7:51:46<5:41:21,  8.63s/it]08/04/2024 17:29:55 - INFO - __main__ -   Step: 3338, LR: 2.30839149784771e-07, Loss: 0.20642676949501038
2024-08-05T00:30:03.653403164Z 
 58%|█████▊    | 3339/5712 [7:51:54<5:38:50,  8.57s/it]08/04/2024 17:30:03 - INFO - __main__ -   Step: 3339, LR: 2.3074187115445415e-07, Loss: 0.22691714763641357
2024-08-05T00:30:12.037155881Z 
 58%|█████▊    | 3340/5712 [7:52:03<5:36:31,  8.51s/it]08/04/2024 17:30:12 - INFO - __main__ -   Step: 3340, LR: 2.3064459252413725e-07, Loss: 0.20561885833740234
2024-08-05T00:30:21.063582372Z 
 58%|█████▊    | 3341/5712 [7:52:12<5:42:28,  8.67s/it]08/04/2024 17:30:21 - INFO - __main__ -   Step: 3341, LR: 2.3054731389382038e-07, Loss: 0.14059598743915558
2024-08-05T00:30:29.299548063Z 
 59%|█████▊    | 3342/5712 [7:52:20<5:37:13,  8.54s/it]08/04/2024 17:30:29 - INFO - __main__ -   Step: 3342, LR: 2.3045003526350348e-07, Loss: 0.13885316252708435
2024-08-05T00:30:38.186270176Z 
 59%|█████▊    | 3343/5712 [7:52:29<5:41:13,  8.64s/it]08/04/2024 17:30:38 - INFO - __main__ -   Step: 3343, LR: 2.303527566331866e-07, Loss: 0.1712208241224289
2024-08-05T00:30:46.784392688Z 
 59%|█████▊    | 3344/5712 [7:52:37<5:40:33,  8.63s/it]08/04/2024 17:30:46 - INFO - __main__ -   Step: 3344, LR: 2.302554780028697e-07, Loss: 0.23450636863708496
2024-08-05T00:30:55.059939876Z 
 59%|█████▊    | 3345/5712 [7:52:46<5:36:13,  8.52s/it]08/04/2024 17:30:55 - INFO - __main__ -   Step: 3345, LR: 2.3015819937255283e-07, Loss: 0.21155336499214172
2024-08-05T00:31:03.122474966Z 
 59%|█████▊    | 3346/5712 [7:52:54<5:30:38,  8.38s/it]08/04/2024 17:31:03 - INFO - __main__ -   Step: 3346, LR: 2.3006092074223593e-07, Loss: 0.1385149359703064
2024-08-05T00:31:11.902317621Z 
 59%|█████▊    | 3347/5712 [7:53:03<5:35:10,  8.50s/it]08/04/2024 17:31:11 - INFO - __main__ -   Step: 3347, LR: 2.2996364211191905e-07, Loss: 0.19478072226047516
2024-08-05T00:31:20.281320027Z 
 59%|█████▊    | 3348/5712 [7:53:11<5:33:33,  8.47s/it]08/04/2024 17:31:20 - INFO - __main__ -   Step: 3348, LR: 2.2986636348160218e-07, Loss: 0.16289031505584717
2024-08-05T00:31:29.065199575Z 
 59%|█████▊    | 3349/5712 [7:53:20<5:37:10,  8.56s/it]08/04/2024 17:31:29 - INFO - __main__ -   Step: 3349, LR: 2.297690848512853e-07, Loss: 0.31867289543151855
2024-08-05T00:31:37.600505542Z 
 59%|█████▊    | 3350/5712 [7:53:28<5:36:43,  8.55s/it]08/04/2024 17:31:37 - INFO - __main__ -   Step: 3350, LR: 2.296718062209684e-07, Loss: 0.11374182254076004
2024-08-05T00:31:46.391455802Z 
 59%|█████▊    | 3351/5712 [7:53:37<5:39:23,  8.62s/it]08/04/2024 17:31:46 - INFO - __main__ -   Step: 3351, LR: 2.2957452759065153e-07, Loss: 0.1886710524559021
2024-08-05T00:31:55.424475614Z 
 59%|█████▊    | 3352/5712 [7:53:46<5:44:03,  8.75s/it]08/04/2024 17:31:55 - INFO - __main__ -   Step: 3352, LR: 2.2947724896033463e-07, Loss: 0.21435624361038208
2024-08-05T00:32:04.120914296Z 
 59%|█████▊    | 3353/5712 [7:53:55<5:43:18,  8.73s/it]08/04/2024 17:32:04 - INFO - __main__ -   Step: 3353, LR: 2.2937997033001775e-07, Loss: 0.16507109999656677
2024-08-05T00:32:12.046703605Z 
 59%|█████▊    | 3354/5712 [7:54:03<5:33:39,  8.49s/it]08/04/2024 17:32:12 - INFO - __main__ -   Step: 3354, LR: 2.2928269169970085e-07, Loss: 0.16431978344917297
2024-08-05T00:32:21.032518605Z 
 59%|█████▊    | 3355/5712 [7:54:12<5:39:21,  8.64s/it]08/04/2024 17:32:21 - INFO - __main__ -   Step: 3355, LR: 2.2918541306938398e-07, Loss: 0.2887777090072632
2024-08-05T00:32:29.677450513Z 
 59%|█████▉    | 3356/5712 [7:54:20<5:39:17,  8.64s/it]08/04/2024 17:32:29 - INFO - __main__ -   Step: 3356, LR: 2.2908813443906707e-07, Loss: 0.11477885395288467
2024-08-05T00:32:38.474795620Z 
 59%|█████▉    | 3357/5712 [7:54:29<5:40:58,  8.69s/it]08/04/2024 17:32:38 - INFO - __main__ -   Step: 3357, LR: 2.2899085580875023e-07, Loss: 0.1858600378036499
2024-08-05T00:32:47.061951962Z 
 59%|█████▉    | 3358/5712 [7:54:38<5:39:40,  8.66s/it]08/04/2024 17:32:47 - INFO - __main__ -   Step: 3358, LR: 2.2889357717843333e-07, Loss: 0.2197272777557373
2024-08-05T00:32:55.253829453Z 
 59%|█████▉    | 3359/5712 [7:54:46<5:34:03,  8.52s/it]08/04/2024 17:32:55 - INFO - __main__ -   Step: 3359, LR: 2.2879629854811645e-07, Loss: 0.13038381934165955
2024-08-05T00:33:03.519229519Z 
 59%|█████▉    | 3360/5712 [7:54:54<5:30:56,  8.44s/it]08/04/2024 17:33:03 - INFO - __main__ -   Step: 3360, LR: 2.2869901991779955e-07, Loss: 0.22676609456539154
2024-08-05T00:33:12.348166039Z 
 59%|█████▉    | 3361/5712 [7:55:03<5:35:20,  8.56s/it]08/04/2024 17:33:12 - INFO - __main__ -   Step: 3361, LR: 2.2860174128748268e-07, Loss: 0.24763406813144684
2024-08-05T00:33:20.489078797Z 
 59%|█████▉    | 3362/5712 [7:55:11<5:30:17,  8.43s/it]08/04/2024 17:33:20 - INFO - __main__ -   Step: 3362, LR: 2.2850446265716577e-07, Loss: 0.21928507089614868
2024-08-05T00:33:29.425231994Z 
 59%|█████▉    | 3363/5712 [7:55:20<5:36:03,  8.58s/it]08/04/2024 17:33:29 - INFO - __main__ -   Step: 3363, LR: 2.2840718402684887e-07, Loss: 0.203587144613266
2024-08-05T00:33:37.996956461Z 
 59%|█████▉    | 3364/5712 [7:55:29<5:35:46,  8.58s/it]08/04/2024 17:33:37 - INFO - __main__ -   Step: 3364, LR: 2.28309905396532e-07, Loss: 0.15573902428150177
2024-08-05T00:33:46.512188703Z 
 59%|█████▉    | 3365/5712 [7:55:37<5:34:52,  8.56s/it]08/04/2024 17:33:46 - INFO - __main__ -   Step: 3365, LR: 2.282126267662151e-07, Loss: 0.18585588037967682
2024-08-05T00:33:54.878093063Z 
 59%|█████▉    | 3366/5712 [7:55:46<5:32:26,  8.50s/it]08/04/2024 17:33:54 - INFO - __main__ -   Step: 3366, LR: 2.2811534813589825e-07, Loss: 0.12291773408651352
2024-08-05T00:34:03.119061572Z 
 59%|█████▉    | 3367/5712 [7:55:54<5:29:13,  8.42s/it]08/04/2024 17:34:03 - INFO - __main__ -   Step: 3367, LR: 2.2801806950558135e-07, Loss: 0.11916355788707733
2024-08-05T00:34:12.042817058Z 
 59%|█████▉    | 3368/5712 [7:56:03<5:34:57,  8.57s/it]08/04/2024 17:34:12 - INFO - __main__ -   Step: 3368, LR: 2.2792079087526448e-07, Loss: 0.16925160586833954
2024-08-05T00:34:20.946294117Z 
 59%|█████▉    | 3369/5712 [7:56:12<5:38:40,  8.67s/it]08/04/2024 17:34:20 - INFO - __main__ -   Step: 3369, LR: 2.2782351224494757e-07, Loss: 0.3880755603313446
2024-08-05T00:34:29.493254404Z 
 59%|█████▉    | 3370/5712 [7:56:20<5:37:03,  8.63s/it]08/04/2024 17:34:29 - INFO - __main__ -   Step: 3370, LR: 2.277262336146307e-07, Loss: 0.14455434679985046
2024-08-05T00:34:37.494825802Z 
 59%|█████▉    | 3371/5712 [7:56:28<5:29:29,  8.45s/it]08/04/2024 17:34:37 - INFO - __main__ -   Step: 3371, LR: 2.276289549843138e-07, Loss: 0.10939178615808487
2024-08-05T00:34:46.270492913Z 
 59%|█████▉    | 3372/5712 [7:56:37<5:33:13,  8.54s/it]08/04/2024 17:34:46 - INFO - __main__ -   Step: 3372, LR: 2.2753167635399692e-07, Loss: 0.1473959982395172
2024-08-05T00:34:54.648874648Z 
 59%|█████▉    | 3373/5712 [7:56:45<5:31:08,  8.49s/it]08/04/2024 17:34:54 - INFO - __main__ -   Step: 3373, LR: 2.2743439772368002e-07, Loss: 0.1525108963251114
2024-08-05T00:35:04.027226936Z 
 59%|█████▉    | 3374/5712 [7:56:55<5:41:18,  8.76s/it]08/04/2024 17:35:04 - INFO - __main__ -   Step: 3374, LR: 2.2733711909336315e-07, Loss: 0.10997265577316284
2024-08-05T00:35:12.274230806Z 
 59%|█████▉    | 3375/5712 [7:57:03<5:35:12,  8.61s/it]08/04/2024 17:35:12 - INFO - __main__ -   Step: 3375, LR: 2.2723984046304625e-07, Loss: 0.17558223009109497
2024-08-05T00:35:20.418971022Z 
 59%|█████▉    | 3376/5712 [7:57:11<5:29:40,  8.47s/it]08/04/2024 17:35:20 - INFO - __main__ -   Step: 3376, LR: 2.271425618327294e-07, Loss: 0.13815127313137054
2024-08-05T00:35:29.368800341Z 
 59%|█████▉    | 3377/5712 [7:57:20<5:35:09,  8.61s/it]08/04/2024 17:35:29 - INFO - __main__ -   Step: 3377, LR: 2.270452832024125e-07, Loss: 0.19855627417564392
2024-08-05T00:35:38.003869580Z 
 59%|█████▉    | 3378/5712 [7:57:29<5:35:16,  8.62s/it]08/04/2024 17:35:38 - INFO - __main__ -   Step: 3378, LR: 2.2694800457209562e-07, Loss: 0.15739552676677704
2024-08-05T00:35:46.142737879Z 
 59%|█████▉    | 3379/5712 [7:57:37<5:29:32,  8.48s/it]08/04/2024 17:35:46 - INFO - __main__ -   Step: 3379, LR: 2.2685072594177872e-07, Loss: 0.34372982382774353
2024-08-05T00:35:54.551906579Z 
 59%|█████▉    | 3380/5712 [7:57:45<5:28:37,  8.46s/it]08/04/2024 17:35:54 - INFO - __main__ -   Step: 3380, LR: 2.2675344731146185e-07, Loss: 0.16644452512264252
2024-08-05T00:36:03.013302626Z 
 59%|█████▉    | 3381/5712 [7:57:54<5:28:33,  8.46s/it]08/04/2024 17:36:03 - INFO - __main__ -   Step: 3381, LR: 2.2665616868114495e-07, Loss: 0.12366314232349396
2024-08-05T00:36:11.646684388Z 
 59%|█████▉    | 3382/5712 [7:58:02<5:30:27,  8.51s/it]08/04/2024 17:36:11 - INFO - __main__ -   Step: 3382, LR: 2.2655889005082807e-07, Loss: 0.22897961735725403
2024-08-05T00:36:20.073463504Z 
 59%|█████▉    | 3383/5712 [7:58:11<5:29:21,  8.49s/it]08/04/2024 17:36:20 - INFO - __main__ -   Step: 3383, LR: 2.2646161142051117e-07, Loss: 0.30728471279144287
2024-08-05T00:36:28.495201441Z 
 59%|█████▉    | 3384/5712 [7:58:19<5:28:28,  8.47s/it]08/04/2024 17:36:28 - INFO - __main__ -   Step: 3384, LR: 2.263643327901943e-07, Loss: 0.1920466125011444
2024-08-05T00:36:37.435910568Z 
 59%|█████▉    | 3385/5712 [7:58:28<5:33:52,  8.61s/it]08/04/2024 17:36:37 - INFO - __main__ -   Step: 3385, LR: 2.2626705415987742e-07, Loss: 0.29234111309051514
2024-08-05T00:36:45.838607914Z 
 59%|█████▉    | 3386/5712 [7:58:36<5:31:19,  8.55s/it]08/04/2024 17:36:45 - INFO - __main__ -   Step: 3386, LR: 2.2616977552956055e-07, Loss: 0.19322466850280762
2024-08-05T00:36:54.782202370Z 
 59%|█████▉    | 3387/5712 [7:58:45<5:35:46,  8.67s/it]08/04/2024 17:36:54 - INFO - __main__ -   Step: 3387, LR: 2.2607249689924365e-07, Loss: 0.27303001284599304
2024-08-05T00:37:03.203292595Z 
 59%|█████▉    | 3388/5712 [7:58:54<5:32:49,  8.59s/it]08/04/2024 17:37:03 - INFO - __main__ -   Step: 3388, LR: 2.2597521826892677e-07, Loss: 0.2340932935476303
2024-08-05T00:37:11.835230713Z 
 59%|█████▉    | 3389/5712 [7:59:02<5:33:07,  8.60s/it]08/04/2024 17:37:11 - INFO - __main__ -   Step: 3389, LR: 2.2587793963860987e-07, Loss: 0.1364990919828415
2024-08-05T00:37:20.253124640Z 
 59%|█████▉    | 3390/5712 [7:59:11<5:30:49,  8.55s/it]08/04/2024 17:37:20 - INFO - __main__ -   Step: 3390, LR: 2.25780661008293e-07, Loss: 0.15113988518714905
2024-08-05T00:37:29.207575410Z 
 59%|█████▉    | 3391/5712 [7:59:20<5:35:22,  8.67s/it]08/04/2024 17:37:29 - INFO - __main__ -   Step: 3391, LR: 2.256833823779761e-07, Loss: 0.14796662330627441
2024-08-05T00:37:37.161040161Z 
 59%|█████▉    | 3392/5712 [7:59:28<5:26:56,  8.46s/it]08/04/2024 17:37:37 - INFO - __main__ -   Step: 3392, LR: 2.2558610374765922e-07, Loss: 0.16375288367271423
2024-08-05T00:37:46.375625963Z 
 59%|█████▉    | 3393/5712 [7:59:37<5:35:36,  8.68s/it]08/04/2024 17:37:46 - INFO - __main__ -   Step: 3393, LR: 2.2548882511734232e-07, Loss: 0.11649765074253082
2024-08-05T00:37:54.796011728Z 
 59%|█████▉    | 3394/5712 [7:59:45<5:32:24,  8.60s/it]08/04/2024 17:37:54 - INFO - __main__ -   Step: 3394, LR: 2.2539154648702547e-07, Loss: 0.3512806296348572
2024-08-05T00:38:03.289320789Z 
 59%|█████▉    | 3395/5712 [7:59:54<5:30:59,  8.57s/it]08/04/2024 17:38:03 - INFO - __main__ -   Step: 3395, LR: 2.2529426785670857e-07, Loss: 0.1425066441297531
2024-08-05T00:38:11.968379606Z 
 59%|█████▉    | 3396/5712 [8:00:03<5:32:05,  8.60s/it]08/04/2024 17:38:11 - INFO - __main__ -   Step: 3396, LR: 2.251969892263917e-07, Loss: 0.1510964035987854
2024-08-05T00:38:20.548440595Z 
 59%|█████▉    | 3397/5712 [8:00:11<5:31:40,  8.60s/it]08/04/2024 17:38:20 - INFO - __main__ -   Step: 3397, LR: 2.250997105960748e-07, Loss: 0.12986063957214355
2024-08-05T00:38:28.966461804Z 
 59%|█████▉    | 3398/5712 [8:00:20<5:29:27,  8.54s/it]08/04/2024 17:38:28 - INFO - __main__ -   Step: 3398, LR: 2.2500243196575792e-07, Loss: 0.18134301900863647
2024-08-05T00:38:37.517956922Z 
 60%|█████▉    | 3399/5712 [8:00:28<5:29:25,  8.55s/it]08/04/2024 17:38:37 - INFO - __main__ -   Step: 3399, LR: 2.2490515333544102e-07, Loss: 0.16844312846660614
2024-08-05T00:38:45.552625979Z 
 60%|█████▉    | 3400/5712 [8:00:36<5:23:22,  8.39s/it]08/04/2024 17:38:45 - INFO - __main__ -   Step: 3400, LR: 2.2480787470512412e-07, Loss: 0.2985844016075134
2024-08-05T00:38:54.082527810Z 
 60%|█████▉    | 3401/5712 [8:00:45<5:24:49,  8.43s/it]08/04/2024 17:38:54 - INFO - __main__ -   Step: 3401, LR: 2.2471059607480725e-07, Loss: 0.09962722659111023
2024-08-05T00:39:03.134073294Z 
 60%|█████▉    | 3402/5712 [8:00:54<5:31:49,  8.62s/it]08/04/2024 17:39:03 - INFO - __main__ -   Step: 3402, LR: 2.2461331744449035e-07, Loss: 0.13736087083816528
2024-08-05T00:39:11.398541520Z 
 60%|█████▉    | 3403/5712 [8:01:02<5:27:35,  8.51s/it]08/04/2024 17:39:11 - INFO - __main__ -   Step: 3403, LR: 2.245160388141735e-07, Loss: 0.2180236279964447
2024-08-05T00:39:20.513167572Z 
 60%|█████▉    | 3404/5712 [8:01:11<5:34:23,  8.69s/it]08/04/2024 17:39:20 - INFO - __main__ -   Step: 3404, LR: 2.244187601838566e-07, Loss: 0.16967123746871948
2024-08-05T00:39:28.713418340Z 
 60%|█████▉    | 3405/5712 [8:01:19<5:28:34,  8.55s/it]08/04/2024 17:39:28 - INFO - __main__ -   Step: 3405, LR: 2.2432148155353972e-07, Loss: 0.27259713411331177
2024-08-05T00:39:37.092641923Z 
 60%|█████▉    | 3406/5712 [8:01:28<5:26:30,  8.50s/it]08/04/2024 17:39:37 - INFO - __main__ -   Step: 3406, LR: 2.2422420292322282e-07, Loss: 0.18151819705963135
2024-08-05T00:39:45.906076118Z 
 60%|█████▉    | 3407/5712 [8:01:37<5:30:02,  8.59s/it]08/04/2024 17:39:45 - INFO - __main__ -   Step: 3407, LR: 2.2412692429290595e-07, Loss: 0.18051694333553314
2024-08-05T00:39:54.413888539Z 
 60%|█████▉    | 3408/5712 [8:01:45<5:28:55,  8.57s/it]08/04/2024 17:39:54 - INFO - __main__ -   Step: 3408, LR: 2.2402964566258905e-07, Loss: 0.15262660384178162
2024-08-05T00:40:02.449772258Z 
 60%|█████▉    | 3409/5712 [8:01:53<5:22:41,  8.41s/it]08/04/2024 17:40:02 - INFO - __main__ -   Step: 3409, LR: 2.2393236703227217e-07, Loss: 0.13194100558757782
2024-08-05T00:40:11.703791831Z 
 60%|█████▉    | 3410/5712 [8:02:02<5:32:17,  8.66s/it]08/04/2024 17:40:11 - INFO - __main__ -   Step: 3410, LR: 2.2383508840195527e-07, Loss: 0.20006215572357178
2024-08-05T00:40:19.865070244Z 
 60%|█████▉    | 3411/5712 [8:02:11<5:26:24,  8.51s/it]08/04/2024 17:40:19 - INFO - __main__ -   Step: 3411, LR: 2.237378097716384e-07, Loss: 0.23822596669197083
2024-08-05T00:40:28.453753978Z 
 60%|█████▉    | 3412/5712 [8:02:19<5:27:09,  8.53s/it]08/04/2024 17:40:28 - INFO - __main__ -   Step: 3412, LR: 2.2364053114132152e-07, Loss: 0.09017762541770935
2024-08-05T00:40:37.151326699Z 
 60%|█████▉    | 3413/5712 [8:02:28<5:28:53,  8.58s/it]08/04/2024 17:40:37 - INFO - __main__ -   Step: 3413, LR: 2.2354325251100465e-07, Loss: 0.1520841121673584
2024-08-05T00:40:45.317350567Z 
 60%|█████▉    | 3414/5712 [8:02:36<5:23:57,  8.46s/it]08/04/2024 17:40:45 - INFO - __main__ -   Step: 3414, LR: 2.2344597388068775e-07, Loss: 0.11296699941158295
2024-08-05T00:40:53.742511911Z 
 60%|█████▉    | 3415/5712 [8:02:44<5:23:25,  8.45s/it]08/04/2024 17:40:53 - INFO - __main__ -   Step: 3415, LR: 2.2334869525037087e-07, Loss: 0.2941531538963318
2024-08-05T00:41:02.500832188Z 
 60%|█████▉    | 3416/5712 [8:02:53<5:26:50,  8.54s/it]08/04/2024 17:41:02 - INFO - __main__ -   Step: 3416, LR: 2.2325141662005397e-07, Loss: 0.1671409010887146
2024-08-05T00:41:10.434541191Z 
 60%|█████▉    | 3417/5712 [8:03:01<5:19:44,  8.36s/it]08/04/2024 17:41:10 - INFO - __main__ -   Step: 3417, LR: 2.231541379897371e-07, Loss: 0.17511504888534546
2024-08-05T00:41:19.368936918Z 
 60%|█████▉    | 3418/5712 [8:03:10<5:26:11,  8.53s/it]08/04/2024 17:41:19 - INFO - __main__ -   Step: 3418, LR: 2.230568593594202e-07, Loss: 0.15379005670547485
2024-08-05T00:41:28.361819917Z 
 60%|█████▉    | 3419/5712 [8:03:19<5:31:20,  8.67s/it]08/04/2024 17:41:28 - INFO - __main__ -   Step: 3419, LR: 2.2295958072910332e-07, Loss: 0.12872660160064697
2024-08-05T00:41:36.323806587Z 
 60%|█████▉    | 3420/5712 [8:03:27<5:23:04,  8.46s/it]08/04/2024 17:41:36 - INFO - __main__ -   Step: 3420, LR: 2.2286230209878642e-07, Loss: 0.23588278889656067
2024-08-05T00:41:45.033657144Z 
 60%|█████▉    | 3421/5712 [8:03:36<5:25:48,  8.53s/it]08/04/2024 17:41:45 - INFO - __main__ -   Step: 3421, LR: 2.2276502346846957e-07, Loss: 0.281494677066803
2024-08-05T00:41:53.558762127Z 
 60%|█████▉    | 3422/5712 [8:03:44<5:25:35,  8.53s/it]08/04/2024 17:41:53 - INFO - __main__ -   Step: 3422, LR: 2.2266774483815267e-07, Loss: 0.1648174524307251
2024-08-05T00:42:02.002808430Z 
 60%|█████▉    | 3423/5712 [8:03:53<5:24:27,  8.50s/it]08/04/2024 17:42:02 - INFO - __main__ -   Step: 3423, LR: 2.225704662078358e-07, Loss: 0.2953687608242035
2024-08-05T00:42:10.243151784Z 
 60%|█████▉    | 3424/5712 [8:04:01<5:21:17,  8.43s/it]08/04/2024 17:42:10 - INFO - __main__ -   Step: 3424, LR: 2.224731875775189e-07, Loss: 0.29649993777275085
2024-08-05T00:42:18.974650336Z 
 60%|█████▉    | 3425/5712 [8:04:10<5:24:38,  8.52s/it]08/04/2024 17:42:18 - INFO - __main__ -   Step: 3425, LR: 2.2237590894720202e-07, Loss: 0.1849876195192337
2024-08-05T00:42:27.866201915Z 
 60%|█████▉    | 3426/5712 [8:04:19<5:28:47,  8.63s/it]08/04/2024 17:42:27 - INFO - __main__ -   Step: 3426, LR: 2.2227863031688512e-07, Loss: 0.14097891747951508
2024-08-05T00:42:36.711124289Z 
 60%|█████▉    | 3427/5712 [8:04:27<5:31:06,  8.69s/it]08/04/2024 17:42:36 - INFO - __main__ -   Step: 3427, LR: 2.2218135168656825e-07, Loss: 0.1957796812057495
2024-08-05T00:42:44.904856551Z 
 60%|██████    | 3428/5712 [8:04:36<5:25:14,  8.54s/it]08/04/2024 17:42:44 - INFO - __main__ -   Step: 3428, LR: 2.2208407305625134e-07, Loss: 0.1355867236852646
2024-08-05T00:42:53.084142409Z 
 60%|██████    | 3429/5712 [8:04:44<5:20:56,  8.43s/it]08/04/2024 17:42:53 - INFO - __main__ -   Step: 3429, LR: 2.2198679442593447e-07, Loss: 0.2174912989139557
2024-08-05T00:43:02.134901403Z 
 60%|██████    | 3430/5712 [8:04:53<5:27:49,  8.62s/it]08/04/2024 17:43:02 - INFO - __main__ -   Step: 3430, LR: 2.218895157956176e-07, Loss: 0.19614049792289734
2024-08-05T00:43:10.795549589Z 
 60%|██████    | 3431/5712 [8:05:01<5:28:09,  8.63s/it]08/04/2024 17:43:10 - INFO - __main__ -   Step: 3431, LR: 2.2179223716530072e-07, Loss: 0.17831921577453613
2024-08-05T00:43:18.941526828Z 
 60%|██████    | 3432/5712 [8:05:10<5:22:28,  8.49s/it]08/04/2024 17:43:18 - INFO - __main__ -   Step: 3432, LR: 2.2169495853498382e-07, Loss: 0.1604858785867691
2024-08-05T00:43:26.877282107Z 
 60%|██████    | 3433/5712 [8:05:18<5:16:03,  8.32s/it]08/04/2024 17:43:26 - INFO - __main__ -   Step: 3433, LR: 2.2159767990466695e-07, Loss: 0.11686664819717407
2024-08-05T00:43:35.430513715Z 
 60%|██████    | 3434/5712 [8:05:26<5:18:34,  8.39s/it]08/04/2024 17:43:35 - INFO - __main__ -   Step: 3434, LR: 2.2150040127435004e-07, Loss: 0.15462583303451538
2024-08-05T00:43:44.063945304Z 
 60%|██████    | 3435/5712 [8:05:35<5:21:11,  8.46s/it]08/04/2024 17:43:44 - INFO - __main__ -   Step: 3435, LR: 2.2140312264403317e-07, Loss: 0.14586205780506134
2024-08-05T00:43:52.736067421Z 
 60%|██████    | 3436/5712 [8:05:43<5:23:25,  8.53s/it]08/04/2024 17:43:52 - INFO - __main__ -   Step: 3436, LR: 2.2130584401371627e-07, Loss: 0.1810656487941742
2024-08-05T00:44:01.089835739Z 
 60%|██████    | 3437/5712 [8:05:52<5:21:19,  8.47s/it]08/04/2024 17:44:01 - INFO - __main__ -   Step: 3437, LR: 2.212085653833994e-07, Loss: 0.16200494766235352
2024-08-05T00:44:09.690477060Z 
 60%|██████    | 3438/5712 [8:06:00<5:22:36,  8.51s/it]08/04/2024 17:44:09 - INFO - __main__ -   Step: 3438, LR: 2.211112867530825e-07, Loss: 0.13889622688293457
2024-08-05T00:44:18.037460809Z 
 60%|██████    | 3439/5712 [8:06:09<5:20:35,  8.46s/it]08/04/2024 17:44:18 - INFO - __main__ -   Step: 3439, LR: 2.2101400812276565e-07, Loss: 0.1766415536403656
2024-08-05T00:44:26.918258264Z 
 60%|██████    | 3440/5712 [8:06:18<5:25:12,  8.59s/it]08/04/2024 17:44:26 - INFO - __main__ -   Step: 3440, LR: 2.2091672949244874e-07, Loss: 0.22038015723228455
2024-08-05T00:44:34.530582362Z 
 60%|██████    | 3441/5712 [8:06:25<5:13:58,  8.30s/it]08/04/2024 17:44:34 - INFO - __main__ -   Step: 3441, LR: 2.2081945086213184e-07, Loss: 0.10351336002349854
2024-08-05T00:44:43.207630121Z 
 60%|██████    | 3442/5712 [8:06:34<5:18:10,  8.41s/it]08/04/2024 17:44:43 - INFO - __main__ -   Step: 3442, LR: 2.2072217223181497e-07, Loss: 0.1458098143339157
2024-08-05T00:44:52.300942396Z 
 60%|██████    | 3443/5712 [8:06:43<5:25:47,  8.61s/it]08/04/2024 17:44:52 - INFO - __main__ -   Step: 3443, LR: 2.2062489360149807e-07, Loss: 0.19724607467651367
2024-08-05T00:45:00.475647780Z 
 60%|██████    | 3444/5712 [8:06:51<5:20:39,  8.48s/it]08/04/2024 17:45:00 - INFO - __main__ -   Step: 3444, LR: 2.205276149711812e-07, Loss: 0.22340542078018188
2024-08-05T00:45:08.873194332Z 
 60%|██████    | 3445/5712 [8:07:00<5:19:32,  8.46s/it]08/04/2024 17:45:08 - INFO - __main__ -   Step: 3445, LR: 2.204303363408643e-07, Loss: 0.1410573124885559
2024-08-05T00:45:17.360817015Z 
 60%|██████    | 3446/5712 [8:07:08<5:19:44,  8.47s/it]08/04/2024 17:45:17 - INFO - __main__ -   Step: 3446, LR: 2.2033305771054742e-07, Loss: 0.16975811123847961
2024-08-05T00:45:26.321429185Z 
 60%|██████    | 3447/5712 [8:07:17<5:25:12,  8.61s/it]08/04/2024 17:45:26 - INFO - __main__ -   Step: 3447, LR: 2.2023577908023052e-07, Loss: 0.12378847599029541
2024-08-05T00:45:34.438208192Z 
 60%|██████    | 3448/5712 [8:07:25<5:19:25,  8.47s/it]08/04/2024 17:45:34 - INFO - __main__ -   Step: 3448, LR: 2.2013850044991367e-07, Loss: 0.1302661895751953
2024-08-05T00:45:42.950708748Z 
 60%|██████    | 3449/5712 [8:07:34<5:19:48,  8.48s/it]08/04/2024 17:45:42 - INFO - __main__ -   Step: 3449, LR: 2.2004122181959677e-07, Loss: 0.1951366811990738
2024-08-05T00:45:51.195915245Z 
 60%|██████    | 3450/5712 [8:07:42<5:17:01,  8.41s/it]08/04/2024 17:45:51 - INFO - __main__ -   Step: 3450, LR: 2.199439431892799e-07, Loss: 0.14084580540657043
2024-08-05T00:45:59.891142256Z 
 60%|██████    | 3451/5712 [8:07:51<5:20:07,  8.49s/it]08/04/2024 17:45:59 - INFO - __main__ -   Step: 3451, LR: 2.19846664558963e-07, Loss: 0.11225305497646332
2024-08-05T00:46:08.547781627Z 
 60%|██████    | 3452/5712 [8:07:59<5:21:48,  8.54s/it]08/04/2024 17:46:08 - INFO - __main__ -   Step: 3452, LR: 2.1974938592864612e-07, Loss: 0.23068609833717346
2024-08-05T00:46:16.524870733Z 
 60%|██████    | 3453/5712 [8:08:07<5:15:15,  8.37s/it]08/04/2024 17:46:16 - INFO - __main__ -   Step: 3453, LR: 2.1965210729832922e-07, Loss: 0.1628105640411377
2024-08-05T00:46:24.840287625Z 
 60%|██████    | 3454/5712 [8:08:15<5:14:28,  8.36s/it]08/04/2024 17:46:24 - INFO - __main__ -   Step: 3454, LR: 2.1955482866801234e-07, Loss: 0.19353510439395905
2024-08-05T00:46:33.589209659Z 
 60%|██████    | 3455/5712 [8:08:24<5:18:44,  8.47s/it]08/04/2024 17:46:33 - INFO - __main__ -   Step: 3455, LR: 2.1945755003769544e-07, Loss: 0.2921674847602844
2024-08-05T00:46:42.162455530Z 
 61%|██████    | 3456/5712 [8:08:33<5:19:44,  8.50s/it]08/04/2024 17:46:42 - INFO - __main__ -   Step: 3456, LR: 2.1936027140737857e-07, Loss: 0.1461101770401001
2024-08-05T00:46:50.429329802Z 
 61%|██████    | 3457/5712 [8:08:41<5:16:55,  8.43s/it]08/04/2024 17:46:50 - INFO - __main__ -   Step: 3457, LR: 2.192629927770617e-07, Loss: 0.1586664468050003
2024-08-05T00:46:58.449798001Z 
 61%|██████    | 3458/5712 [8:08:49<5:12:08,  8.31s/it]08/04/2024 17:46:58 - INFO - __main__ -   Step: 3458, LR: 2.1916571414674482e-07, Loss: 0.173448383808136
2024-08-05T00:47:06.882401535Z 
 61%|██████    | 3459/5712 [8:08:58<5:13:23,  8.35s/it]08/04/2024 17:47:06 - INFO - __main__ -   Step: 3459, LR: 2.1906843551642792e-07, Loss: 0.27315792441368103
2024-08-05T00:47:15.464688442Z 
 61%|██████    | 3460/5712 [8:09:06<5:15:54,  8.42s/it]08/04/2024 17:47:15 - INFO - __main__ -   Step: 3460, LR: 2.1897115688611104e-07, Loss: 0.1586087942123413
2024-08-05T00:47:23.896603427Z 
 61%|██████    | 3461/5712 [8:09:15<5:15:56,  8.42s/it]08/04/2024 17:47:23 - INFO - __main__ -   Step: 3461, LR: 2.1887387825579414e-07, Loss: 0.23522281646728516
2024-08-05T00:47:32.617216837Z 
 61%|██████    | 3462/5712 [8:09:23<5:19:10,  8.51s/it]08/04/2024 17:47:32 - INFO - __main__ -   Step: 3462, LR: 2.1877659962547727e-07, Loss: 0.18569618463516235
2024-08-05T00:47:41.096174039Z 
 61%|██████    | 3463/5712 [8:09:32<5:18:40,  8.50s/it]08/04/2024 17:47:41 - INFO - __main__ -   Step: 3463, LR: 2.1867932099516037e-07, Loss: 0.272026389837265
2024-08-05T00:47:49.694745400Z 
 61%|██████    | 3464/5712 [8:09:40<5:19:36,  8.53s/it]08/04/2024 17:47:49 - INFO - __main__ -   Step: 3464, LR: 2.185820423648435e-07, Loss: 0.13864825665950775
2024-08-05T00:47:57.893807485Z 
 61%|██████    | 3465/5712 [8:09:49<5:15:44,  8.43s/it]08/04/2024 17:47:57 - INFO - __main__ -   Step: 3465, LR: 2.184847637345266e-07, Loss: 0.1276281177997589
2024-08-05T00:48:05.577508454Z 
 61%|██████    | 3466/5712 [8:09:56<5:07:12,  8.21s/it]08/04/2024 17:48:05 - INFO - __main__ -   Step: 3466, LR: 2.1838748510420974e-07, Loss: 0.11726425588130951
2024-08-05T00:48:14.799457036Z 
 61%|██████    | 3467/5712 [8:10:05<5:18:27,  8.51s/it]08/04/2024 17:48:14 - INFO - __main__ -   Step: 3467, LR: 2.1829020647389284e-07, Loss: 0.2503310739994049
2024-08-05T00:48:23.387444772Z 
 61%|██████    | 3468/5712 [8:10:14<5:19:11,  8.53s/it]08/04/2024 17:48:23 - INFO - __main__ -   Step: 3468, LR: 2.1819292784357597e-07, Loss: 0.22635889053344727
2024-08-05T00:48:31.301668569Z 
 61%|██████    | 3469/5712 [8:10:22<5:12:05,  8.35s/it]08/04/2024 17:48:31 - INFO - __main__ -   Step: 3469, LR: 2.1809564921325907e-07, Loss: 0.10843943804502487
2024-08-05T00:48:39.335030414Z 
 61%|██████    | 3470/5712 [8:10:30<5:08:25,  8.25s/it]08/04/2024 17:48:39 - INFO - __main__ -   Step: 3470, LR: 2.179983705829422e-07, Loss: 0.1498166024684906
2024-08-05T00:48:47.612130788Z 
 61%|██████    | 3471/5712 [8:10:38<5:08:32,  8.26s/it]08/04/2024 17:48:47 - INFO - __main__ -   Step: 3471, LR: 2.179010919526253e-07, Loss: 0.28811901807785034
2024-08-05T00:48:56.599509169Z 
 61%|██████    | 3472/5712 [8:10:47<5:16:31,  8.48s/it]08/04/2024 17:48:56 - INFO - __main__ -   Step: 3472, LR: 2.1780381332230842e-07, Loss: 0.1953389048576355
2024-08-05T00:49:05.099933574Z 
 61%|██████    | 3473/5712 [8:10:56<5:16:38,  8.49s/it]08/04/2024 17:49:05 - INFO - __main__ -   Step: 3473, LR: 2.1770653469199152e-07, Loss: 0.32722708582878113
2024-08-05T00:49:12.702197961Z 
 61%|██████    | 3474/5712 [8:11:03<5:06:37,  8.22s/it]08/04/2024 17:49:12 - INFO - __main__ -   Step: 3474, LR: 2.1760925606167464e-07, Loss: 0.18998092412948608
2024-08-05T00:49:21.947083037Z 
 61%|██████    | 3475/5712 [8:11:13<5:17:56,  8.53s/it]08/04/2024 17:49:21 - INFO - __main__ -   Step: 3475, LR: 2.1751197743135777e-07, Loss: 0.10307616740465164
2024-08-05T00:49:30.817869849Z 
 61%|██████    | 3476/5712 [8:11:21<5:21:38,  8.63s/it]08/04/2024 17:49:30 - INFO - __main__ -   Step: 3476, LR: 2.174146988010409e-07, Loss: 0.2115437537431717
2024-08-05T00:49:39.194850262Z 
 61%|██████    | 3477/5712 [8:11:30<5:18:39,  8.55s/it]08/04/2024 17:49:39 - INFO - __main__ -   Step: 3477, LR: 2.17317420170724e-07, Loss: 0.11362176388502121
2024-08-05T00:49:47.234403880Z 
 61%|██████    | 3478/5712 [8:11:38<5:12:45,  8.40s/it]08/04/2024 17:49:47 - INFO - __main__ -   Step: 3478, LR: 2.172201415404071e-07, Loss: 0.1834377497434616
2024-08-05T00:49:56.202455689Z 
 61%|██████    | 3479/5712 [8:11:47<5:18:57,  8.57s/it]08/04/2024 17:49:56 - INFO - __main__ -   Step: 3479, LR: 2.1712286291009022e-07, Loss: 0.20160529017448425
2024-08-05T00:50:04.970793589Z 
 61%|██████    | 3480/5712 [8:11:56<5:21:01,  8.63s/it]08/04/2024 17:50:04 - INFO - __main__ -   Step: 3480, LR: 2.1702558427977332e-07, Loss: 0.10915105044841766
2024-08-05T00:50:13.219350054Z 
 61%|██████    | 3481/5712 [8:12:04<5:16:37,  8.52s/it]08/04/2024 17:50:13 - INFO - __main__ -   Step: 3481, LR: 2.1692830564945644e-07, Loss: 0.15851908922195435
2024-08-05T00:50:21.218652092Z 
 61%|██████    | 3482/5712 [8:12:12<5:10:44,  8.36s/it]08/04/2024 17:50:21 - INFO - __main__ -   Step: 3482, LR: 2.1683102701913954e-07, Loss: 0.18370559811592102
2024-08-05T00:50:29.340256792Z 
 61%|██████    | 3483/5712 [8:12:20<5:07:55,  8.29s/it]08/04/2024 17:50:29 - INFO - __main__ -   Step: 3483, LR: 2.1673374838882267e-07, Loss: 0.12847667932510376
2024-08-05T00:50:38.104592188Z 
 61%|██████    | 3484/5712 [8:12:29<5:13:05,  8.43s/it]08/04/2024 17:50:38 - INFO - __main__ -   Step: 3484, LR: 2.166364697585058e-07, Loss: 0.2517951428890228
2024-08-05T00:50:46.620025474Z 
 61%|██████    | 3485/5712 [8:12:37<5:13:53,  8.46s/it]08/04/2024 17:50:46 - INFO - __main__ -   Step: 3485, LR: 2.1653919112818892e-07, Loss: 0.11339007318019867
2024-08-05T00:50:54.549495335Z 
 61%|██████    | 3486/5712 [8:12:45<5:07:52,  8.30s/it]08/04/2024 17:50:54 - INFO - __main__ -   Step: 3486, LR: 2.1644191249787202e-07, Loss: 0.19999945163726807
2024-08-05T00:51:03.350336961Z 
 61%|██████    | 3487/5712 [8:12:54<5:13:19,  8.45s/it]08/04/2024 17:51:03 - INFO - __main__ -   Step: 3487, LR: 2.1634463386755514e-07, Loss: 0.13038060069084167
2024-08-05T00:51:12.223969762Z 
 61%|██████    | 3488/5712 [8:13:03<5:17:54,  8.58s/it]08/04/2024 17:51:12 - INFO - __main__ -   Step: 3488, LR: 2.1624735523723824e-07, Loss: 0.17546173930168152
2024-08-05T00:51:20.677184606Z 
 61%|██████    | 3489/5712 [8:13:11<5:16:23,  8.54s/it]08/04/2024 17:51:20 - INFO - __main__ -   Step: 3489, LR: 2.1615007660692137e-07, Loss: 0.2545646131038666
2024-08-05T00:51:28.987568674Z 
 61%|██████    | 3490/5712 [8:13:20<5:13:42,  8.47s/it]08/04/2024 17:51:28 - INFO - __main__ -   Step: 3490, LR: 2.1605279797660446e-07, Loss: 0.1581086665391922
2024-08-05T00:51:36.687247219Z 
 61%|██████    | 3491/5712 [8:13:27<5:04:59,  8.24s/it]08/04/2024 17:51:36 - INFO - __main__ -   Step: 3491, LR: 2.159555193462876e-07, Loss: 0.11913812905550003
2024-08-05T00:51:45.233153418Z 
 61%|██████    | 3492/5712 [8:13:36<5:08:15,  8.33s/it]08/04/2024 17:51:45 - INFO - __main__ -   Step: 3492, LR: 2.158582407159707e-07, Loss: 0.25803059339523315
2024-08-05T00:51:53.546774233Z 
 61%|██████    | 3493/5712 [8:13:44<5:07:55,  8.33s/it]08/04/2024 17:51:53 - INFO - __main__ -   Step: 3493, LR: 2.1576096208565384e-07, Loss: 0.11363063007593155
2024-08-05T00:52:01.817319142Z 
 61%|██████    | 3494/5712 [8:13:52<5:07:10,  8.31s/it]08/04/2024 17:52:01 - INFO - __main__ -   Step: 3494, LR: 2.1566368345533694e-07, Loss: 0.23764963448047638
2024-08-05T00:52:10.242596013Z 
 61%|██████    | 3495/5712 [8:14:01<5:08:19,  8.34s/it]08/04/2024 17:52:10 - INFO - __main__ -   Step: 3495, LR: 2.1556640482502007e-07, Loss: 0.12207971513271332
2024-08-05T00:52:19.269968966Z 
 61%|██████    | 3496/5712 [8:14:10<5:15:44,  8.55s/it]08/04/2024 17:52:19 - INFO - __main__ -   Step: 3496, LR: 2.1546912619470316e-07, Loss: 0.13759785890579224
2024-08-05T00:52:27.508993684Z 
 61%|██████    | 3497/5712 [8:14:18<5:12:10,  8.46s/it]08/04/2024 17:52:27 - INFO - __main__ -   Step: 3497, LR: 2.153718475643863e-07, Loss: 0.1862225979566574
2024-08-05T00:52:35.983315969Z 
 61%|██████    | 3498/5712 [8:14:27<5:12:13,  8.46s/it]08/04/2024 17:52:35 - INFO - __main__ -   Step: 3498, LR: 2.152745689340694e-07, Loss: 0.21643471717834473
2024-08-05T00:52:43.613912589Z 
 61%|██████▏   | 3499/5712 [8:14:34<5:02:53,  8.21s/it]08/04/2024 17:52:43 - INFO - __main__ -   Step: 3499, LR: 2.1517729030375251e-07, Loss: 0.11727955937385559
2024-08-05T00:52:52.393952091Z 
 61%|██████▏   | 3500/5712 [8:14:43<5:09:02,  8.38s/it]08/04/2024 17:52:52 - INFO - __main__ -   Step: 3500, LR: 2.1508001167343561e-07, Loss: 0.12799692153930664
2024-08-05T00:53:00.978780013Z 
 61%|██████▏   | 3501/5712 [8:14:52<5:11:08,  8.44s/it]08/04/2024 17:53:00 - INFO - __main__ -   Step: 3501, LR: 2.1498273304311874e-07, Loss: 0.2324855923652649
2024-08-05T00:53:09.582648412Z 
 61%|██████▏   | 3502/5712 [8:15:00<5:12:46,  8.49s/it]08/04/2024 17:53:09 - INFO - __main__ -   Step: 3502, LR: 2.1488545441280186e-07, Loss: 0.145882248878479
2024-08-05T00:53:17.746300167Z 
 61%|██████▏   | 3503/5712 [8:15:08<5:09:00,  8.39s/it]08/04/2024 17:53:17 - INFO - __main__ -   Step: 3503, LR: 2.14788175782485e-07, Loss: 0.11965516209602356
2024-08-05T00:53:26.218847014Z 
 61%|██████▏   | 3504/5712 [8:15:17<5:09:44,  8.42s/it]08/04/2024 17:53:26 - INFO - __main__ -   Step: 3504, LR: 2.146908971521681e-07, Loss: 0.16653399169445038
2024-08-05T00:53:35.157804433Z 
 61%|██████▏   | 3505/5712 [8:15:26<5:15:21,  8.57s/it]08/04/2024 17:53:35 - INFO - __main__ -   Step: 3505, LR: 2.1459361852185121e-07, Loss: 0.17036402225494385
2024-08-05T00:53:43.629693431Z 
 61%|██████▏   | 3506/5712 [8:15:34<5:14:05,  8.54s/it]08/04/2024 17:53:43 - INFO - __main__ -   Step: 3506, LR: 2.1449633989153431e-07, Loss: 0.23630425333976746
2024-08-05T00:53:51.677911891Z 
 61%|██████▏   | 3507/5712 [8:15:42<5:08:30,  8.39s/it]08/04/2024 17:53:51 - INFO - __main__ -   Step: 3507, LR: 2.1439906126121744e-07, Loss: 0.15254974365234375
2024-08-05T00:54:00.353744114Z 
 61%|██████▏   | 3508/5712 [8:15:51<5:11:27,  8.48s/it]08/04/2024 17:54:00 - INFO - __main__ -   Step: 3508, LR: 2.1430178263090054e-07, Loss: 0.14365911483764648
2024-08-05T00:54:08.822592479Z 
 61%|██████▏   | 3509/5712 [8:15:59<5:11:12,  8.48s/it]08/04/2024 17:54:08 - INFO - __main__ -   Step: 3509, LR: 2.1420450400058366e-07, Loss: 0.13361971080303192
2024-08-05T00:54:17.017854725Z 
 61%|██████▏   | 3510/5712 [8:16:08<5:07:58,  8.39s/it]08/04/2024 17:54:17 - INFO - __main__ -   Step: 3510, LR: 2.1410722537026676e-07, Loss: 0.13300573825836182
2024-08-05T00:54:25.198315744Z 
 61%|██████▏   | 3511/5712 [8:16:16<5:05:30,  8.33s/it]08/04/2024 17:54:25 - INFO - __main__ -   Step: 3511, LR: 2.1400994673994992e-07, Loss: 0.14561590552330017
2024-08-05T00:54:34.384667151Z 
 61%|██████▏   | 3512/5712 [8:16:25<5:14:48,  8.59s/it]08/04/2024 17:54:34 - INFO - __main__ -   Step: 3512, LR: 2.1391266810963301e-07, Loss: 0.1133202612400055
2024-08-05T00:54:42.953769812Z 
 62%|██████▏   | 3513/5712 [8:16:34<5:14:28,  8.58s/it]08/04/2024 17:54:42 - INFO - __main__ -   Step: 3513, LR: 2.1381538947931614e-07, Loss: 0.14916202425956726
2024-08-05T00:54:51.124531453Z 
 62%|██████▏   | 3514/5712 [8:16:42<5:09:50,  8.46s/it]08/04/2024 17:54:51 - INFO - __main__ -   Step: 3514, LR: 2.1371811084899924e-07, Loss: 0.22367313504219055
2024-08-05T00:54:59.607124409Z 
 62%|██████▏   | 3515/5712 [8:16:50<5:09:58,  8.47s/it]08/04/2024 17:54:59 - INFO - __main__ -   Step: 3515, LR: 2.1362083221868234e-07, Loss: 0.11948993802070618
2024-08-05T00:55:08.202339568Z 
 62%|██████▏   | 3516/5712 [8:16:59<5:11:15,  8.50s/it]08/04/2024 17:55:08 - INFO - __main__ -   Step: 3516, LR: 2.1352355358836546e-07, Loss: 0.13411538302898407
2024-08-05T00:55:16.870986811Z 
 62%|██████▏   | 3517/5712 [8:17:08<5:12:54,  8.55s/it]08/04/2024 17:55:16 - INFO - __main__ -   Step: 3517, LR: 2.1342627495804856e-07, Loss: 0.2960328459739685
2024-08-05T00:55:26.004512782Z 
 62%|██████▏   | 3518/5712 [8:17:17<5:19:08,  8.73s/it]08/04/2024 17:55:26 - INFO - __main__ -   Step: 3518, LR: 2.133289963277317e-07, Loss: 0.1351429969072342
2024-08-05T00:55:34.017406275Z 
 62%|██████▏   | 3519/5712 [8:17:25<5:11:09,  8.51s/it]08/04/2024 17:55:34 - INFO - __main__ -   Step: 3519, LR: 2.132317176974148e-07, Loss: 0.09952128678560257
2024-08-05T00:55:42.732351271Z 
 62%|██████▏   | 3520/5712 [8:17:33<5:13:13,  8.57s/it]08/04/2024 17:55:42 - INFO - __main__ -   Step: 3520, LR: 2.1313443906709794e-07, Loss: 0.17426514625549316
2024-08-05T00:55:51.542670036Z 
 62%|██████▏   | 3521/5712 [8:17:42<5:15:40,  8.64s/it]08/04/2024 17:55:51 - INFO - __main__ -   Step: 3521, LR: 2.1303716043678104e-07, Loss: 0.3528349995613098
2024-08-05T00:56:00.175570789Z 
 62%|██████▏   | 3522/5712 [8:17:51<5:15:24,  8.64s/it]08/04/2024 17:56:00 - INFO - __main__ -   Step: 3522, LR: 2.1293988180646416e-07, Loss: 0.13799166679382324
2024-08-05T00:56:09.019875631Z 
 62%|██████▏   | 3523/5712 [8:18:00<5:17:28,  8.70s/it]08/04/2024 17:56:09 - INFO - __main__ -   Step: 3523, LR: 2.1284260317614726e-07, Loss: 0.19074299931526184
2024-08-05T00:56:17.439319060Z 
 62%|██████▏   | 3524/5712 [8:18:08<5:14:14,  8.62s/it]08/04/2024 17:56:17 - INFO - __main__ -   Step: 3524, LR: 2.127453245458304e-07, Loss: 0.17497467994689941
2024-08-05T00:56:26.075244625Z 
 62%|██████▏   | 3525/5712 [8:18:17<5:14:18,  8.62s/it]08/04/2024 17:56:26 - INFO - __main__ -   Step: 3525, LR: 2.126480459155135e-07, Loss: 0.16005241870880127
2024-08-05T00:56:34.530709798Z 
 62%|██████▏   | 3526/5712 [8:18:25<5:12:19,  8.57s/it]08/04/2024 17:56:34 - INFO - __main__ -   Step: 3526, LR: 2.125507672851966e-07, Loss: 0.1746082901954651
2024-08-05T00:56:42.646986056Z 
 62%|██████▏   | 3527/5712 [8:18:33<5:07:11,  8.44s/it]08/04/2024 17:56:42 - INFO - __main__ -   Step: 3527, LR: 2.124534886548797e-07, Loss: 0.13295844197273254
2024-08-05T00:56:51.202800517Z 
 62%|██████▏   | 3528/5712 [8:18:42<5:08:22,  8.47s/it]08/04/2024 17:56:51 - INFO - __main__ -   Step: 3528, LR: 2.1235621002456284e-07, Loss: 0.2202381044626236
2024-08-05T00:56:59.961406406Z 
 62%|██████▏   | 3529/5712 [8:18:51<5:11:21,  8.56s/it]08/04/2024 17:56:59 - INFO - __main__ -   Step: 3529, LR: 2.1225893139424596e-07, Loss: 0.19074979424476624
2024-08-05T00:57:09.205113834Z 
 62%|██████▏   | 3530/5712 [8:19:00<5:18:42,  8.76s/it]08/04/2024 17:57:09 - INFO - __main__ -   Step: 3530, LR: 2.121616527639291e-07, Loss: 0.14780732989311218
2024-08-05T00:57:17.456239825Z 
 62%|██████▏   | 3531/5712 [8:19:08<5:12:58,  8.61s/it]08/04/2024 17:57:17 - INFO - __main__ -   Step: 3531, LR: 2.120643741336122e-07, Loss: 0.23060257732868195
2024-08-05T00:57:25.902793861Z 
 62%|██████▏   | 3532/5712 [8:19:17<5:11:02,  8.56s/it]08/04/2024 17:57:25 - INFO - __main__ -   Step: 3532, LR: 2.119670955032953e-07, Loss: 0.29289954900741577
2024-08-05T00:57:34.064187641Z 
 62%|██████▏   | 3533/5712 [8:19:25<5:06:33,  8.44s/it]08/04/2024 17:57:34 - INFO - __main__ -   Step: 3533, LR: 2.118698168729784e-07, Loss: 0.21350818872451782
2024-08-05T00:57:42.380974546Z 
 62%|██████▏   | 3534/5712 [8:19:33<5:05:03,  8.40s/it]08/04/2024 17:57:42 - INFO - __main__ -   Step: 3534, LR: 2.1177253824266154e-07, Loss: 0.12628215551376343
2024-08-05T00:57:51.369639724Z 
 62%|██████▏   | 3535/5712 [8:19:42<5:11:16,  8.58s/it]08/04/2024 17:57:51 - INFO - __main__ -   Step: 3535, LR: 2.1167525961234464e-07, Loss: 0.2053380012512207
2024-08-05T00:57:59.781474519Z 
 62%|██████▏   | 3536/5712 [8:19:50<5:09:19,  8.53s/it]08/04/2024 17:57:59 - INFO - __main__ -   Step: 3536, LR: 2.1157798098202776e-07, Loss: 0.11872124671936035
2024-08-05T00:58:08.394708593Z 
 62%|██████▏   | 3537/5712 [8:19:59<5:10:05,  8.55s/it]08/04/2024 17:58:08 - INFO - __main__ -   Step: 3537, LR: 2.1148070235171086e-07, Loss: 0.1284710317850113
2024-08-05T00:58:16.785659445Z 
 62%|██████▏   | 3538/5712 [8:20:07<5:08:10,  8.51s/it]08/04/2024 17:58:16 - INFO - __main__ -   Step: 3538, LR: 2.11383423721394e-07, Loss: 0.2170109897851944
2024-08-05T00:58:25.619937254Z 
 62%|██████▏   | 3539/5712 [8:20:16<5:11:36,  8.60s/it]08/04/2024 17:58:25 - INFO - __main__ -   Step: 3539, LR: 2.112861450910771e-07, Loss: 0.08685978502035141
2024-08-05T00:58:34.452176956Z 
 62%|██████▏   | 3540/5712 [8:20:25<5:13:55,  8.67s/it]08/04/2024 17:58:34 - INFO - __main__ -   Step: 3540, LR: 2.1118886646076024e-07, Loss: 0.14698386192321777
2024-08-05T00:58:42.658441557Z 
 62%|██████▏   | 3541/5712 [8:20:33<5:08:44,  8.53s/it]08/04/2024 17:58:42 - INFO - __main__ -   Step: 3541, LR: 2.1109158783044334e-07, Loss: 0.16045843064785004
2024-08-05T00:58:50.907827301Z 
 62%|██████▏   | 3542/5712 [8:20:42<5:05:31,  8.45s/it]08/04/2024 17:58:50 - INFO - __main__ -   Step: 3542, LR: 2.1099430920012646e-07, Loss: 0.10618363320827484
2024-08-05T00:58:59.330621173Z 
 62%|██████▏   | 3543/5712 [8:20:50<5:05:06,  8.44s/it]08/04/2024 17:58:59 - INFO - __main__ -   Step: 3543, LR: 2.1089703056980956e-07, Loss: 0.21108072996139526
2024-08-05T00:59:07.602657009Z 
 62%|██████▏   | 3544/5712 [8:20:58<5:03:09,  8.39s/it]08/04/2024 17:59:07 - INFO - __main__ -   Step: 3544, LR: 2.1079975193949269e-07, Loss: 0.25692546367645264
2024-08-05T00:59:16.646996146Z 
 62%|██████▏   | 3545/5712 [8:21:07<5:10:06,  8.59s/it]08/04/2024 17:59:16 - INFO - __main__ -   Step: 3545, LR: 2.1070247330917579e-07, Loss: 0.19659611582756042
2024-08-05T00:59:24.764996551Z 
 62%|██████▏   | 3546/5712 [8:21:15<5:04:53,  8.45s/it]08/04/2024 17:59:24 - INFO - __main__ -   Step: 3546, LR: 2.106051946788589e-07, Loss: 0.16294631361961365
2024-08-05T00:59:33.415063644Z 
 62%|██████▏   | 3547/5712 [8:21:24<5:06:57,  8.51s/it]08/04/2024 17:59:33 - INFO - __main__ -   Step: 3547, LR: 2.1050791604854204e-07, Loss: 0.10268977284431458
2024-08-05T00:59:41.519386027Z 
 62%|██████▏   | 3548/5712 [8:21:32<5:02:27,  8.39s/it]08/04/2024 17:59:41 - INFO - __main__ -   Step: 3548, LR: 2.1041063741822516e-07, Loss: 0.2758615016937256
2024-08-05T00:59:49.759049402Z 
 62%|██████▏   | 3549/5712 [8:21:40<5:00:44,  8.34s/it]08/04/2024 17:59:49 - INFO - __main__ -   Step: 3549, LR: 2.1031335878790826e-07, Loss: 0.186460942029953
2024-08-05T00:59:58.210322109Z 
 62%|██████▏   | 3550/5712 [8:21:49<5:01:46,  8.37s/it]08/04/2024 17:59:58 - INFO - __main__ -   Step: 3550, LR: 2.1021608015759139e-07, Loss: 0.19101198017597198
2024-08-05T01:00:06.557886737Z 
 62%|██████▏   | 3551/5712 [8:21:57<5:01:20,  8.37s/it]08/04/2024 18:00:06 - INFO - __main__ -   Step: 3551, LR: 2.1011880152727449e-07, Loss: 0.11401225626468658
2024-08-05T01:00:15.457049853Z 
 62%|██████▏   | 3552/5712 [8:22:06<5:06:57,  8.53s/it]08/04/2024 18:00:15 - INFO - __main__ -   Step: 3552, LR: 2.100215228969576e-07, Loss: 0.2455684244632721
2024-08-05T01:00:23.683258793Z 
 62%|██████▏   | 3553/5712 [8:22:14<5:03:34,  8.44s/it]08/04/2024 18:00:23 - INFO - __main__ -   Step: 3553, LR: 2.099242442666407e-07, Loss: 0.2281704694032669
2024-08-05T01:00:32.099877327Z 
 62%|██████▏   | 3554/5712 [8:22:23<5:03:12,  8.43s/it]08/04/2024 18:00:32 - INFO - __main__ -   Step: 3554, LR: 2.098269656363238e-07, Loss: 0.14122536778450012
2024-08-05T01:00:40.540972500Z 
 62%|██████▏   | 3555/5712 [8:22:31<5:03:11,  8.43s/it]08/04/2024 18:00:40 - INFO - __main__ -   Step: 3555, LR: 2.0972968700600693e-07, Loss: 0.19252654910087585
2024-08-05T01:00:48.678109396Z 
 62%|██████▏   | 3556/5712 [8:22:39<4:59:51,  8.34s/it]08/04/2024 18:00:48 - INFO - __main__ -   Step: 3556, LR: 2.0963240837569006e-07, Loss: 0.19339744746685028
2024-08-05T01:00:57.312581503Z 
 62%|██████▏   | 3557/5712 [8:22:48<5:02:49,  8.43s/it]08/04/2024 18:00:57 - INFO - __main__ -   Step: 3557, LR: 2.0953512974537319e-07, Loss: 0.2266148030757904
2024-08-05T01:01:05.553394782Z 
 62%|██████▏   | 3558/5712 [8:22:56<5:00:38,  8.37s/it]08/04/2024 18:01:05 - INFO - __main__ -   Step: 3558, LR: 2.0943785111505628e-07, Loss: 0.19103971123695374
2024-08-05T01:01:13.931651464Z 
 62%|██████▏   | 3559/5712 [8:23:05<5:00:32,  8.38s/it]08/04/2024 18:01:13 - INFO - __main__ -   Step: 3559, LR: 2.093405724847394e-07, Loss: 0.1616639345884323
2024-08-05T01:01:22.186436647Z 
 62%|██████▏   | 3560/5712 [8:23:13<4:59:06,  8.34s/it]08/04/2024 18:01:22 - INFO - __main__ -   Step: 3560, LR: 2.092432938544225e-07, Loss: 0.23778539896011353
2024-08-05T01:01:30.884128292Z 
 62%|██████▏   | 3561/5712 [8:23:22<5:02:49,  8.45s/it]08/04/2024 18:01:30 - INFO - __main__ -   Step: 3561, LR: 2.0914601522410563e-07, Loss: 0.1386934220790863
2024-08-05T01:01:39.451409848Z 
 62%|██████▏   | 3562/5712 [8:23:30<5:03:58,  8.48s/it]08/04/2024 18:01:39 - INFO - __main__ -   Step: 3562, LR: 2.0904873659378873e-07, Loss: 0.1915683150291443
2024-08-05T01:01:47.878242486Z 
 62%|██████▏   | 3563/5712 [8:23:39<5:03:13,  8.47s/it]08/04/2024 18:01:47 - INFO - __main__ -   Step: 3563, LR: 2.0895145796347186e-07, Loss: 0.11721604317426682
2024-08-05T01:01:56.461219413Z 
 62%|██████▏   | 3564/5712 [8:23:47<5:04:20,  8.50s/it]08/04/2024 18:01:56 - INFO - __main__ -   Step: 3564, LR: 2.0885417933315496e-07, Loss: 0.1501842588186264
2024-08-05T01:02:05.018912187Z 
 62%|██████▏   | 3565/5712 [8:23:56<5:04:48,  8.52s/it]08/04/2024 18:02:05 - INFO - __main__ -   Step: 3565, LR: 2.087569007028381e-07, Loss: 0.26590338349342346
2024-08-05T01:02:13.124402232Z 
 62%|██████▏   | 3566/5712 [8:24:04<5:00:14,  8.39s/it]08/04/2024 18:02:13 - INFO - __main__ -   Step: 3566, LR: 2.086596220725212e-07, Loss: 0.199576273560524
2024-08-05T01:02:21.587700315Z 
 62%|██████▏   | 3567/5712 [8:24:12<5:00:50,  8.42s/it]08/04/2024 18:02:21 - INFO - __main__ -   Step: 3567, LR: 2.0856234344220434e-07, Loss: 0.09325075149536133
2024-08-05T01:02:29.584421101Z 
 62%|██████▏   | 3568/5712 [8:24:20<4:56:12,  8.29s/it]08/04/2024 18:02:29 - INFO - __main__ -   Step: 3568, LR: 2.0846506481188743e-07, Loss: 0.16845622658729553
2024-08-05T01:02:38.245129506Z 
 62%|██████▏   | 3569/5712 [8:24:29<5:00:03,  8.40s/it]08/04/2024 18:02:38 - INFO - __main__ -   Step: 3569, LR: 2.0836778618157056e-07, Loss: 0.16291557252407074
2024-08-05T01:02:46.962899755Z 
 62%|██████▎   | 3570/5712 [8:24:38<5:03:18,  8.50s/it]08/04/2024 18:02:46 - INFO - __main__ -   Step: 3570, LR: 2.0827050755125366e-07, Loss: 0.2803352475166321
2024-08-05T01:02:55.732007564Z 
 63%|██████▎   | 3571/5712 [8:24:46<5:06:05,  8.58s/it]08/04/2024 18:02:55 - INFO - __main__ -   Step: 3571, LR: 2.0817322892093678e-07, Loss: 0.1251092255115509
2024-08-05T01:03:04.094907709Z 
 63%|██████▎   | 3572/5712 [8:24:55<5:03:38,  8.51s/it]08/04/2024 18:03:04 - INFO - __main__ -   Step: 3572, LR: 2.0807595029061988e-07, Loss: 0.12738323211669922
2024-08-05T01:03:12.746240632Z 
 63%|██████▎   | 3573/5712 [8:25:03<5:04:58,  8.55s/it]08/04/2024 18:03:12 - INFO - __main__ -   Step: 3573, LR: 2.07978671660303e-07, Loss: 0.22768598794937134
2024-08-05T01:03:21.559745162Z 
 63%|██████▎   | 3574/5712 [8:25:12<5:07:35,  8.63s/it]08/04/2024 18:03:21 - INFO - __main__ -   Step: 3574, LR: 2.0788139302998613e-07, Loss: 0.3151707351207733
2024-08-05T01:03:30.048233051Z 
 63%|██████▎   | 3575/5712 [8:25:21<5:05:55,  8.59s/it]08/04/2024 18:03:30 - INFO - __main__ -   Step: 3575, LR: 2.0778411439966926e-07, Loss: 0.14889344573020935
2024-08-05T01:03:38.244760251Z 
 63%|██████▎   | 3576/5712 [8:25:29<5:01:35,  8.47s/it]08/04/2024 18:03:38 - INFO - __main__ -   Step: 3576, LR: 2.0768683576935236e-07, Loss: 0.14687232673168182
2024-08-05T01:03:46.937238203Z 
 63%|██████▎   | 3577/5712 [8:25:38<5:03:47,  8.54s/it]08/04/2024 18:03:46 - INFO - __main__ -   Step: 3577, LR: 2.0758955713903548e-07, Loss: 0.18831613659858704
2024-08-05T01:03:56.012391484Z 
 63%|██████▎   | 3578/5712 [8:25:47<5:09:23,  8.70s/it]08/04/2024 18:03:56 - INFO - __main__ -   Step: 3578, LR: 2.0749227850871858e-07, Loss: 0.20867908000946045
2024-08-05T01:04:04.509145471Z 
 63%|██████▎   | 3579/5712 [8:25:55<5:07:05,  8.64s/it]08/04/2024 18:04:04 - INFO - __main__ -   Step: 3579, LR: 2.073949998784017e-07, Loss: 0.1366424262523651
2024-08-05T01:04:12.785757685Z 
 63%|██████▎   | 3580/5712 [8:26:03<5:03:05,  8.53s/it]08/04/2024 18:04:12 - INFO - __main__ -   Step: 3580, LR: 2.072977212480848e-07, Loss: 0.1467663049697876
2024-08-05T01:04:21.250660382Z 
 63%|██████▎   | 3581/5712 [8:26:12<5:02:15,  8.51s/it]08/04/2024 18:04:21 - INFO - __main__ -   Step: 3581, LR: 2.0720044261776793e-07, Loss: 0.26754873991012573
2024-08-05T01:04:29.750950821Z 
 63%|██████▎   | 3582/5712 [8:26:20<5:02:00,  8.51s/it]08/04/2024 18:04:29 - INFO - __main__ -   Step: 3582, LR: 2.0710316398745103e-07, Loss: 0.15501739084720612
2024-08-05T01:04:37.978884803Z 
 63%|██████▎   | 3583/5712 [8:26:29<4:58:53,  8.42s/it]08/04/2024 18:04:37 - INFO - __main__ -   Step: 3583, LR: 2.0700588535713418e-07, Loss: 0.12096653878688812
2024-08-05T01:04:46.398391659Z 
 63%|██████▎   | 3584/5712 [8:26:37<4:58:42,  8.42s/it]08/04/2024 18:04:46 - INFO - __main__ -   Step: 3584, LR: 2.0690860672681728e-07, Loss: 0.215011328458786
2024-08-05T01:04:54.353419604Z 
 63%|██████▎   | 3585/5712 [8:26:45<4:53:36,  8.28s/it]08/04/2024 18:04:54 - INFO - __main__ -   Step: 3585, LR: 2.068113280965004e-07, Loss: 0.21859143674373627
2024-08-05T01:05:03.639761023Z 
 63%|██████▎   | 3586/5712 [8:26:54<5:04:08,  8.58s/it]08/04/2024 18:05:03 - INFO - __main__ -   Step: 3586, LR: 2.067140494661835e-07, Loss: 0.1594974547624588
2024-08-05T01:05:12.528615465Z 
 63%|██████▎   | 3587/5712 [8:27:03<5:07:14,  8.68s/it]08/04/2024 18:05:12 - INFO - __main__ -   Step: 3587, LR: 2.0661677083586663e-07, Loss: 0.13877084851264954
2024-08-05T01:05:20.899567807Z 
 63%|██████▎   | 3588/5712 [8:27:12<5:03:51,  8.58s/it]08/04/2024 18:05:20 - INFO - __main__ -   Step: 3588, LR: 2.0651949220554973e-07, Loss: 0.08764136582612991
2024-08-05T01:05:29.074580542Z 
 63%|██████▎   | 3589/5712 [8:27:20<4:59:23,  8.46s/it]08/04/2024 18:05:29 - INFO - __main__ -   Step: 3589, LR: 2.0642221357523286e-07, Loss: 0.1393425315618515
2024-08-05T01:05:37.490267201Z 
 63%|██████▎   | 3590/5712 [8:27:28<4:58:45,  8.45s/it]08/04/2024 18:05:37 - INFO - __main__ -   Step: 3590, LR: 2.0632493494491596e-07, Loss: 0.22226032614707947
2024-08-05T01:05:46.345585499Z 
 63%|██████▎   | 3591/5712 [8:27:37<5:02:55,  8.57s/it]08/04/2024 18:05:46 - INFO - __main__ -   Step: 3591, LR: 2.0622765631459906e-07, Loss: 0.19496490061283112
2024-08-05T01:05:54.627928067Z 
 63%|██████▎   | 3592/5712 [8:27:45<4:59:45,  8.48s/it]08/04/2024 18:05:54 - INFO - __main__ -   Step: 3592, LR: 2.061303776842822e-07, Loss: 0.12432204186916351
2024-08-05T01:06:02.143087563Z 
 63%|██████▎   | 3593/5712 [8:27:53<4:49:21,  8.19s/it]08/04/2024 18:06:02 - INFO - __main__ -   Step: 3593, LR: 2.060330990539653e-07, Loss: 0.21820923686027527
2024-08-05T01:06:10.764571015Z 
 63%|██████▎   | 3594/5712 [8:28:01<4:53:45,  8.32s/it]08/04/2024 18:06:10 - INFO - __main__ -   Step: 3594, LR: 2.0593582042364843e-07, Loss: 0.15332725644111633
2024-08-05T01:06:19.329985040Z 
 63%|██████▎   | 3595/5712 [8:28:10<4:56:11,  8.39s/it]08/04/2024 18:06:19 - INFO - __main__ -   Step: 3595, LR: 2.0583854179333153e-07, Loss: 0.2685660719871521
2024-08-05T01:06:27.515839254Z 
 63%|██████▎   | 3596/5712 [8:28:18<4:53:50,  8.33s/it]08/04/2024 18:06:27 - INFO - __main__ -   Step: 3596, LR: 2.0574126316301466e-07, Loss: 0.1923239827156067
2024-08-05T01:06:35.607396192Z 
 63%|██████▎   | 3597/5712 [8:28:26<4:51:09,  8.26s/it]08/04/2024 18:06:35 - INFO - __main__ -   Step: 3597, LR: 2.0564398453269776e-07, Loss: 0.26789677143096924
2024-08-05T01:06:44.255803875Z 
 63%|██████▎   | 3598/5712 [8:28:35<4:55:08,  8.38s/it]08/04/2024 18:06:44 - INFO - __main__ -   Step: 3598, LR: 2.0554670590238088e-07, Loss: 0.16212859749794006
2024-08-05T01:06:52.724661509Z 
 63%|██████▎   | 3599/5712 [8:28:43<4:55:58,  8.40s/it]08/04/2024 18:06:52 - INFO - __main__ -   Step: 3599, LR: 2.0544942727206398e-07, Loss: 0.24790991842746735
2024-08-05T01:07:01.570423379Z 
 63%|██████▎   | 3600/5712 [8:28:52<5:00:29,  8.54s/it]08/04/2024 18:07:01 - INFO - __main__ -   Step: 3600, LR: 2.053521486417471e-07, Loss: 0.24530377984046936
2024-08-05T01:07:09.144773045Z 
 63%|██████▎   | 3601/5712 [8:29:00<4:50:11,  8.25s/it]08/04/2024 18:07:09 - INFO - __main__ -   Step: 3601, LR: 2.0525487001143023e-07, Loss: 0.1966407746076584
2024-08-05T01:07:17.507090924Z 
 63%|██████▎   | 3602/5712 [8:29:08<4:51:15,  8.28s/it]08/04/2024 18:07:17 - INFO - __main__ -   Step: 3602, LR: 2.0515759138111336e-07, Loss: 0.2897098660469055
2024-08-05T01:07:26.133477496Z 
 63%|██████▎   | 3603/5712 [8:29:17<4:54:45,  8.39s/it]08/04/2024 18:07:26 - INFO - __main__ -   Step: 3603, LR: 2.0506031275079646e-07, Loss: 0.1651240587234497
2024-08-05T01:07:34.829816033Z 
 63%|██████▎   | 3604/5712 [8:29:25<4:57:53,  8.48s/it]08/04/2024 18:07:34 - INFO - __main__ -   Step: 3604, LR: 2.0496303412047958e-07, Loss: 0.20188337564468384
2024-08-05T01:07:43.401536937Z 
 63%|██████▎   | 3605/5712 [8:29:34<4:58:43,  8.51s/it]08/04/2024 18:07:43 - INFO - __main__ -   Step: 3605, LR: 2.0486575549016268e-07, Loss: 0.133138507604599
2024-08-05T01:07:51.859854047Z 
 63%|██████▎   | 3606/5712 [8:29:43<4:58:04,  8.49s/it]08/04/2024 18:07:51 - INFO - __main__ -   Step: 3606, LR: 2.047684768598458e-07, Loss: 0.09636932611465454
2024-08-05T01:08:00.287959837Z 
 63%|██████▎   | 3607/5712 [8:29:51<4:57:15,  8.47s/it]08/04/2024 18:08:00 - INFO - __main__ -   Step: 3607, LR: 2.046711982295289e-07, Loss: 0.20305055379867554
2024-08-05T01:08:09.308789266Z 
 63%|██████▎   | 3608/5712 [8:30:00<5:02:52,  8.64s/it]08/04/2024 18:08:09 - INFO - __main__ -   Step: 3608, LR: 2.0457391959921203e-07, Loss: 0.10837182402610779
2024-08-05T01:08:17.256848222Z 
 63%|██████▎   | 3609/5712 [8:30:08<4:55:29,  8.43s/it]08/04/2024 18:08:17 - INFO - __main__ -   Step: 3609, LR: 2.0447664096889513e-07, Loss: 0.13162514567375183
2024-08-05T01:08:25.510040657Z 
 63%|██████▎   | 3610/5712 [8:30:16<4:53:29,  8.38s/it]08/04/2024 18:08:25 - INFO - __main__ -   Step: 3610, LR: 2.0437936233857828e-07, Loss: 0.12418487668037415
2024-08-05T01:08:34.263071290Z 
 63%|██████▎   | 3611/5712 [8:30:25<4:57:17,  8.49s/it]08/04/2024 18:08:34 - INFO - __main__ -   Step: 3611, LR: 2.0428208370826138e-07, Loss: 0.18793722987174988
2024-08-05T01:08:42.696669053Z 
 63%|██████▎   | 3612/5712 [8:30:33<4:56:33,  8.47s/it]08/04/2024 18:08:42 - INFO - __main__ -   Step: 3612, LR: 2.041848050779445e-07, Loss: 0.287388414144516
2024-08-05T01:08:51.135954040Z 
 63%|██████▎   | 3613/5712 [8:30:42<4:56:03,  8.46s/it]08/04/2024 18:08:51 - INFO - __main__ -   Step: 3613, LR: 2.040875264476276e-07, Loss: 0.18476602435112
2024-08-05T01:08:59.299835488Z 
 63%|██████▎   | 3614/5712 [8:30:50<4:52:47,  8.37s/it]08/04/2024 18:08:59 - INFO - __main__ -   Step: 3614, LR: 2.0399024781731073e-07, Loss: 0.19374129176139832
2024-08-05T01:09:07.942573805Z 
 63%|██████▎   | 3615/5712 [8:30:59<4:55:28,  8.45s/it]08/04/2024 18:09:07 - INFO - __main__ -   Step: 3615, LR: 2.0389296918699383e-07, Loss: 0.25097423791885376
2024-08-05T01:09:16.154665172Z 
 63%|██████▎   | 3616/5712 [8:31:07<4:52:47,  8.38s/it]08/04/2024 18:09:16 - INFO - __main__ -   Step: 3616, LR: 2.0379569055667696e-07, Loss: 0.1766248345375061
2024-08-05T01:09:24.417424849Z 
 63%|██████▎   | 3617/5712 [8:31:15<4:51:24,  8.35s/it]08/04/2024 18:09:24 - INFO - __main__ -   Step: 3617, LR: 2.0369841192636006e-07, Loss: 0.21517489850521088
2024-08-05T01:09:33.282938078Z 
 63%|██████▎   | 3618/5712 [8:31:24<4:56:41,  8.50s/it]08/04/2024 18:09:33 - INFO - __main__ -   Step: 3618, LR: 2.0360113329604318e-07, Loss: 0.21618647873401642
2024-08-05T01:09:41.556233726Z 
 63%|██████▎   | 3619/5712 [8:31:32<4:54:10,  8.43s/it]08/04/2024 18:09:41 - INFO - __main__ -   Step: 3619, LR: 2.035038546657263e-07, Loss: 0.10968753695487976
2024-08-05T01:09:50.090403536Z 
 63%|██████▎   | 3620/5712 [8:31:41<4:55:05,  8.46s/it]08/04/2024 18:09:50 - INFO - __main__ -   Step: 3620, LR: 2.0340657603540943e-07, Loss: 0.1316119134426117
2024-08-05T01:09:58.501075554Z 
 63%|██████▎   | 3621/5712 [8:31:49<4:54:24,  8.45s/it]08/04/2024 18:09:58 - INFO - __main__ -   Step: 3621, LR: 2.0330929740509253e-07, Loss: 0.2689460515975952
2024-08-05T01:10:07.342797719Z 
 63%|██████▎   | 3622/5712 [8:31:58<4:58:22,  8.57s/it]08/04/2024 18:10:07 - INFO - __main__ -   Step: 3622, LR: 2.0321201877477566e-07, Loss: 0.19647029042243958
2024-08-05T01:10:15.589946782Z 
 63%|██████▎   | 3623/5712 [8:32:06<4:54:54,  8.47s/it]08/04/2024 18:10:15 - INFO - __main__ -   Step: 3623, LR: 2.0311474014445876e-07, Loss: 0.3339857757091522
2024-08-05T01:10:24.532870172Z 
 63%|██████▎   | 3624/5712 [8:32:15<4:59:42,  8.61s/it]08/04/2024 18:10:24 - INFO - __main__ -   Step: 3624, LR: 2.0301746151414188e-07, Loss: 0.19364267587661743
2024-08-05T01:10:33.221934620Z 
 63%|██████▎   | 3625/5712 [8:32:24<5:00:20,  8.63s/it]08/04/2024 18:10:33 - INFO - __main__ -   Step: 3625, LR: 2.0292018288382498e-07, Loss: 0.1639031022787094
2024-08-05T01:10:41.448139459Z 
 63%|██████▎   | 3626/5712 [8:32:32<4:55:57,  8.51s/it]08/04/2024 18:10:41 - INFO - __main__ -   Step: 3626, LR: 2.028229042535081e-07, Loss: 0.1867421269416809
2024-08-05T01:10:49.694640012Z 
 63%|██████▎   | 3627/5712 [8:32:40<4:53:02,  8.43s/it]08/04/2024 18:10:49 - INFO - __main__ -   Step: 3627, LR: 2.027256256231912e-07, Loss: 0.22028189897537231
2024-08-05T01:10:58.182883166Z 
 64%|██████▎   | 3628/5712 [8:32:49<4:53:28,  8.45s/it]08/04/2024 18:10:58 - INFO - __main__ -   Step: 3628, LR: 2.0262834699287436e-07, Loss: 0.1732533723115921
2024-08-05T01:11:07.025283579Z 
 64%|██████▎   | 3629/5712 [8:32:58<4:57:25,  8.57s/it]08/04/2024 18:11:07 - INFO - __main__ -   Step: 3629, LR: 2.0253106836255746e-07, Loss: 0.21902553737163544
2024-08-05T01:11:15.467632558Z 
 64%|██████▎   | 3630/5712 [8:33:06<4:55:59,  8.53s/it]08/04/2024 18:11:15 - INFO - __main__ -   Step: 3630, LR: 2.0243378973224055e-07, Loss: 0.23468458652496338
2024-08-05T01:11:23.759848651Z 
 64%|██████▎   | 3631/5712 [8:33:14<4:53:22,  8.46s/it]08/04/2024 18:11:23 - INFO - __main__ -   Step: 3631, LR: 2.0233651110192368e-07, Loss: 0.24056723713874817
2024-08-05T01:11:32.574350427Z 
 64%|██████▎   | 3632/5712 [8:33:23<4:56:56,  8.57s/it]08/04/2024 18:11:32 - INFO - __main__ -   Step: 3632, LR: 2.0223923247160678e-07, Loss: 0.1386253386735916
2024-08-05T01:11:41.034290902Z 
 64%|██████▎   | 3633/5712 [8:33:32<4:55:41,  8.53s/it]08/04/2024 18:11:41 - INFO - __main__ -   Step: 3633, LR: 2.021419538412899e-07, Loss: 0.15780046582221985
2024-08-05T01:11:48.952291276Z 
 64%|██████▎   | 3634/5712 [8:33:40<4:49:09,  8.35s/it]08/04/2024 18:11:48 - INFO - __main__ -   Step: 3634, LR: 2.02044675210973e-07, Loss: 0.24991098046302795
2024-08-05T01:11:57.809012643Z 
 64%|██████▎   | 3635/5712 [8:33:48<4:54:17,  8.50s/it]08/04/2024 18:11:57 - INFO - __main__ -   Step: 3635, LR: 2.0194739658065613e-07, Loss: 0.18887832760810852
2024-08-05T01:12:05.722457136Z 
 64%|██████▎   | 3636/5712 [8:33:56<4:48:02,  8.32s/it]08/04/2024 18:12:05 - INFO - __main__ -   Step: 3636, LR: 2.0185011795033923e-07, Loss: 0.2485814392566681
2024-08-05T01:12:13.892741623Z 
 64%|██████▎   | 3637/5712 [8:34:05<4:46:18,  8.28s/it]08/04/2024 18:12:13 - INFO - __main__ -   Step: 3637, LR: 2.0175283932002238e-07, Loss: 0.16310261189937592
2024-08-05T01:12:22.612164867Z 
 64%|██████▎   | 3638/5712 [8:34:13<4:50:43,  8.41s/it]08/04/2024 18:12:22 - INFO - __main__ -   Step: 3638, LR: 2.0165556068970548e-07, Loss: 0.09551792591810226
2024-08-05T01:12:30.832100680Z 
 64%|██████▎   | 3639/5712 [8:34:21<4:48:36,  8.35s/it]08/04/2024 18:12:30 - INFO - __main__ -   Step: 3639, LR: 2.015582820593886e-07, Loss: 0.2516975700855255
2024-08-05T01:12:39.482604071Z 
 64%|██████▎   | 3640/5712 [8:34:30<4:51:32,  8.44s/it]08/04/2024 18:12:39 - INFO - __main__ -   Step: 3640, LR: 2.014610034290717e-07, Loss: 0.12256715446710587
2024-08-05T01:12:47.875288376Z 
 64%|██████▎   | 3641/5712 [8:34:39<4:50:53,  8.43s/it]08/04/2024 18:12:47 - INFO - __main__ -   Step: 3641, LR: 2.0136372479875483e-07, Loss: 0.13034602999687195
2024-08-05T01:12:55.939450319Z 
 64%|██████▍   | 3642/5712 [8:34:47<4:46:59,  8.32s/it]08/04/2024 18:12:55 - INFO - __main__ -   Step: 3642, LR: 2.0126644616843793e-07, Loss: 0.24529963731765747
2024-08-05T01:13:04.244083913Z 
 64%|██████▍   | 3643/5712 [8:34:55<4:46:42,  8.31s/it]08/04/2024 18:13:04 - INFO - __main__ -   Step: 3643, LR: 2.0116916753812105e-07, Loss: 0.1437126100063324
2024-08-05T01:13:12.513683311Z 
 64%|██████▍   | 3644/5712 [8:35:03<4:46:06,  8.30s/it]08/04/2024 18:13:12 - INFO - __main__ -   Step: 3644, LR: 2.0107188890780415e-07, Loss: 0.11577236652374268
2024-08-05T01:13:21.241623936Z 
 64%|██████▍   | 3645/5712 [8:35:12<4:50:22,  8.43s/it]08/04/2024 18:13:21 - INFO - __main__ -   Step: 3645, LR: 2.0097461027748728e-07, Loss: 0.21182669699192047
2024-08-05T01:13:29.726133531Z 
 64%|██████▍   | 3646/5712 [8:35:20<4:50:49,  8.45s/it]08/04/2024 18:13:29 - INFO - __main__ -   Step: 3646, LR: 2.008773316471704e-07, Loss: 0.14432647824287415
2024-08-05T01:13:38.276297005Z 
 64%|██████▍   | 3647/5712 [8:35:29<4:51:45,  8.48s/it]08/04/2024 18:13:38 - INFO - __main__ -   Step: 3647, LR: 2.0078005301685353e-07, Loss: 0.25636833906173706
2024-08-05T01:13:47.438500326Z 
 64%|██████▍   | 3648/5712 [8:35:38<4:58:39,  8.68s/it]08/04/2024 18:13:47 - INFO - __main__ -   Step: 3648, LR: 2.0068277438653663e-07, Loss: 0.28634050488471985
2024-08-05T01:13:56.215633547Z 
 64%|██████▍   | 3649/5712 [8:35:47<4:59:30,  8.71s/it]08/04/2024 18:13:56 - INFO - __main__ -   Step: 3649, LR: 2.0058549575621975e-07, Loss: 0.1956111192703247
2024-08-05T01:14:04.287115350Z 
 64%|██████▍   | 3650/5712 [8:35:55<4:52:46,  8.52s/it]08/04/2024 18:14:04 - INFO - __main__ -   Step: 3650, LR: 2.0048821712590285e-07, Loss: 0.18609628081321716
2024-08-05T01:14:12.462289559Z 
 64%|██████▍   | 3651/5712 [8:36:03<4:49:05,  8.42s/it]08/04/2024 18:14:12 - INFO - __main__ -   Step: 3651, LR: 2.0039093849558598e-07, Loss: 0.2321121245622635
2024-08-05T01:14:20.554093636Z 
 64%|██████▍   | 3652/5712 [8:36:11<4:45:36,  8.32s/it]08/04/2024 18:14:20 - INFO - __main__ -   Step: 3652, LR: 2.0029365986526908e-07, Loss: 0.17285315692424774
2024-08-05T01:14:28.502534114Z 
 64%|██████▍   | 3653/5712 [8:36:19<4:41:39,  8.21s/it]08/04/2024 18:14:28 - INFO - __main__ -   Step: 3653, LR: 2.001963812349522e-07, Loss: 0.19650204479694366
2024-08-05T01:14:36.745794398Z 
 64%|██████▍   | 3654/5712 [8:36:27<4:41:53,  8.22s/it]08/04/2024 18:14:36 - INFO - __main__ -   Step: 3654, LR: 2.000991026046353e-07, Loss: 0.21858340501785278
2024-08-05T01:14:45.008756509Z 
 64%|██████▍   | 3655/5712 [8:36:36<4:42:12,  8.23s/it]08/04/2024 18:14:45 - INFO - __main__ -   Step: 3655, LR: 2.0000182397431845e-07, Loss: 0.18516471982002258
2024-08-05T01:14:53.332256438Z 
 64%|██████▍   | 3656/5712 [8:36:44<4:43:00,  8.26s/it]08/04/2024 18:14:53 - INFO - __main__ -   Step: 3656, LR: 1.9990454534400155e-07, Loss: 0.17227095365524292
2024-08-05T01:15:02.186459957Z 
 64%|██████▍   | 3657/5712 [8:36:53<4:48:59,  8.44s/it]08/04/2024 18:15:02 - INFO - __main__ -   Step: 3657, LR: 1.9980726671368468e-07, Loss: 0.13315844535827637
2024-08-05T01:15:10.401524945Z 
 64%|██████▍   | 3658/5712 [8:37:01<4:46:33,  8.37s/it]08/04/2024 18:15:10 - INFO - __main__ -   Step: 3658, LR: 1.9970998808336778e-07, Loss: 0.2076747566461563
2024-08-05T01:15:18.872837626Z 
 64%|██████▍   | 3659/5712 [8:37:10<4:47:26,  8.40s/it]08/04/2024 18:15:18 - INFO - __main__ -   Step: 3659, LR: 1.996127094530509e-07, Loss: 0.0962754338979721
2024-08-05T01:15:27.072222030Z 
 64%|██████▍   | 3660/5712 [8:37:18<4:45:15,  8.34s/it]08/04/2024 18:15:27 - INFO - __main__ -   Step: 3660, LR: 1.99515430822734e-07, Loss: 0.17457734048366547
2024-08-05T01:15:35.368598883Z 
 64%|██████▍   | 3661/5712 [8:37:26<4:44:39,  8.33s/it]08/04/2024 18:15:35 - INFO - __main__ -   Step: 3661, LR: 1.9941815219241713e-07, Loss: 0.10701499134302139
2024-08-05T01:15:43.645479172Z 
 64%|██████▍   | 3662/5712 [8:37:34<4:44:00,  8.31s/it]08/04/2024 18:15:43 - INFO - __main__ -   Step: 3662, LR: 1.9932087356210023e-07, Loss: 0.1700764000415802
2024-08-05T01:15:52.230153413Z 
 64%|██████▍   | 3663/5712 [8:37:43<4:46:39,  8.39s/it]08/04/2024 18:15:52 - INFO - __main__ -   Step: 3663, LR: 1.9922359493178335e-07, Loss: 0.17070332169532776
2024-08-05T01:16:00.590185398Z 
 64%|██████▍   | 3664/5712 [8:37:51<4:46:10,  8.38s/it]08/04/2024 18:16:00 - INFO - __main__ -   Step: 3664, LR: 1.9912631630146648e-07, Loss: 0.2139071524143219
2024-08-05T01:16:09.529015045Z 
 64%|██████▍   | 3665/5712 [8:38:00<4:51:42,  8.55s/it]08/04/2024 18:16:09 - INFO - __main__ -   Step: 3665, LR: 1.990290376711496e-07, Loss: 0.12663885951042175
2024-08-05T01:16:18.379437507Z 
 64%|██████▍   | 3666/5712 [8:38:09<4:54:38,  8.64s/it]08/04/2024 18:16:18 - INFO - __main__ -   Step: 3666, LR: 1.989317590408327e-07, Loss: 0.17587482929229736
2024-08-05T01:16:25.900694051Z 
 64%|██████▍   | 3667/5712 [8:38:17<4:43:02,  8.30s/it]08/04/2024 18:16:25 - INFO - __main__ -   Step: 3667, LR: 1.9883448041051583e-07, Loss: 0.10923434793949127
2024-08-05T01:16:34.077115831Z 
 64%|██████▍   | 3668/5712 [8:38:25<4:41:35,  8.27s/it]08/04/2024 18:16:34 - INFO - __main__ -   Step: 3668, LR: 1.9873720178019893e-07, Loss: 0.11991944909095764
2024-08-05T01:16:42.464890204Z 
 64%|██████▍   | 3669/5712 [8:38:33<4:42:42,  8.30s/it]08/04/2024 18:16:42 - INFO - __main__ -   Step: 3669, LR: 1.9863992314988203e-07, Loss: 0.2119550108909607
2024-08-05T01:16:50.642093745Z 
 64%|██████▍   | 3670/5712 [8:38:41<4:41:17,  8.27s/it]08/04/2024 18:16:50 - INFO - __main__ -   Step: 3670, LR: 1.9854264451956515e-07, Loss: 0.12225552648305893
2024-08-05T01:16:59.283626913Z 
 64%|██████▍   | 3671/5712 [8:38:50<4:44:59,  8.38s/it]08/04/2024 18:16:59 - INFO - __main__ -   Step: 3671, LR: 1.9844536588924825e-07, Loss: 0.19593077898025513
2024-08-05T01:17:07.638226944Z 
 64%|██████▍   | 3672/5712 [8:38:58<4:44:36,  8.37s/it]08/04/2024 18:17:07 - INFO - __main__ -   Step: 3672, LR: 1.9834808725893138e-07, Loss: 0.3178081512451172
2024-08-05T01:17:15.988679984Z 
 64%|██████▍   | 3673/5712 [8:39:07<4:44:15,  8.36s/it]08/04/2024 18:17:15 - INFO - __main__ -   Step: 3673, LR: 1.982508086286145e-07, Loss: 0.24562934041023254
2024-08-05T01:17:24.818635656Z 
 64%|██████▍   | 3674/5712 [8:39:15<4:48:51,  8.50s/it]08/04/2024 18:17:24 - INFO - __main__ -   Step: 3674, LR: 1.9815352999829763e-07, Loss: 0.19320417940616608
2024-08-05T01:17:32.921726782Z 
 64%|██████▍   | 3675/5712 [8:39:24<4:44:38,  8.38s/it]08/04/2024 18:17:32 - INFO - __main__ -   Step: 3675, LR: 1.9805625136798073e-07, Loss: 0.10480770468711853
2024-08-05T01:17:41.743346362Z 
 64%|██████▍   | 3676/5712 [8:39:32<4:48:56,  8.51s/it]08/04/2024 18:17:41 - INFO - __main__ -   Step: 3676, LR: 1.9795897273766385e-07, Loss: 0.16721689701080322
2024-08-05T01:17:50.073336095Z 
 64%|██████▍   | 3677/5712 [8:39:41<4:46:55,  8.46s/it]08/04/2024 18:17:50 - INFO - __main__ -   Step: 3677, LR: 1.9786169410734695e-07, Loss: 0.16966457664966583
2024-08-05T01:17:58.853753339Z 
 64%|██████▍   | 3678/5712 [8:39:50<4:50:02,  8.56s/it]08/04/2024 18:17:58 - INFO - __main__ -   Step: 3678, LR: 1.9776441547703008e-07, Loss: 0.19608184695243835
2024-08-05T01:18:07.411938107Z 
 64%|██████▍   | 3679/5712 [8:39:58<4:49:55,  8.56s/it]08/04/2024 18:18:07 - INFO - __main__ -   Step: 3679, LR: 1.9766713684671318e-07, Loss: 0.1571141481399536
2024-08-05T01:18:16.270188105Z 
 64%|██████▍   | 3680/5712 [8:40:07<4:52:51,  8.65s/it]08/04/2024 18:18:16 - INFO - __main__ -   Step: 3680, LR: 1.975698582163963e-07, Loss: 0.18530315160751343
2024-08-05T01:18:24.469701498Z 
 64%|██████▍   | 3681/5712 [8:40:15<4:48:09,  8.51s/it]08/04/2024 18:18:24 - INFO - __main__ -   Step: 3681, LR: 1.974725795860794e-07, Loss: 0.15027853846549988
2024-08-05T01:18:33.742036879Z 
 64%|██████▍   | 3682/5712 [8:40:24<4:55:42,  8.74s/it]08/04/2024 18:18:33 - INFO - __main__ -   Step: 3682, LR: 1.9737530095576255e-07, Loss: 0.1462579369544983
2024-08-05T01:18:42.085244184Z 
 64%|██████▍   | 3683/5712 [8:40:33<4:51:33,  8.62s/it]08/04/2024 18:18:42 - INFO - __main__ -   Step: 3683, LR: 1.9727802232544565e-07, Loss: 0.14013999700546265
2024-08-05T01:18:50.098693221Z 
 64%|██████▍   | 3684/5712 [8:40:41<4:45:14,  8.44s/it]08/04/2024 18:18:50 - INFO - __main__ -   Step: 3684, LR: 1.9718074369512878e-07, Loss: 0.22062303125858307
2024-08-05T01:18:58.746319865Z 
 65%|██████▍   | 3685/5712 [8:40:49<4:47:12,  8.50s/it]08/04/2024 18:18:58 - INFO - __main__ -   Step: 3685, LR: 1.9708346506481188e-07, Loss: 0.09549340605735779
2024-08-05T01:19:07.377902801Z 
 65%|██████▍   | 3686/5712 [8:40:58<4:48:23,  8.54s/it]08/04/2024 18:19:07 - INFO - __main__ -   Step: 3686, LR: 1.96986186434495e-07, Loss: 0.10809996724128723
2024-08-05T01:19:15.430514650Z 
 65%|██████▍   | 3687/5712 [8:41:06<4:43:18,  8.39s/it]08/04/2024 18:19:15 - INFO - __main__ -   Step: 3687, LR: 1.968889078041781e-07, Loss: 0.2068329155445099
2024-08-05T01:19:23.969329487Z 
 65%|██████▍   | 3688/5712 [8:41:15<4:44:37,  8.44s/it]08/04/2024 18:19:23 - INFO - __main__ -   Step: 3688, LR: 1.9679162917386123e-07, Loss: 0.16644327342510223
2024-08-05T01:19:32.415176651Z 
 65%|██████▍   | 3689/5712 [8:41:23<4:44:34,  8.44s/it]08/04/2024 18:19:32 - INFO - __main__ -   Step: 3689, LR: 1.9669435054354432e-07, Loss: 0.20969991385936737
2024-08-05T01:19:41.146514753Z 
 65%|██████▍   | 3690/5712 [8:41:32<4:47:22,  8.53s/it]08/04/2024 18:19:41 - INFO - __main__ -   Step: 3690, LR: 1.9659707191322745e-07, Loss: 0.15825054049491882
2024-08-05T01:19:49.524108157Z 
 65%|██████▍   | 3691/5712 [8:41:40<4:45:43,  8.48s/it]08/04/2024 18:19:49 - INFO - __main__ -   Step: 3691, LR: 1.9649979328291058e-07, Loss: 0.1880328357219696
2024-08-05T01:19:57.667938437Z 
 65%|██████▍   | 3692/5712 [8:41:48<4:42:09,  8.38s/it]08/04/2024 18:19:57 - INFO - __main__ -   Step: 3692, LR: 1.964025146525937e-07, Loss: 0.18513667583465576
2024-08-05T01:20:06.600045405Z 
 65%|██████▍   | 3693/5712 [8:41:57<4:47:34,  8.55s/it]08/04/2024 18:20:06 - INFO - __main__ -   Step: 3693, LR: 1.963052360222768e-07, Loss: 0.1156773641705513
2024-08-05T01:20:15.266891196Z 
 65%|██████▍   | 3694/5712 [8:42:06<4:48:39,  8.58s/it]08/04/2024 18:20:15 - INFO - __main__ -   Step: 3694, LR: 1.9620795739195993e-07, Loss: 0.21818827092647552
2024-08-05T01:20:23.200947714Z 
 65%|██████▍   | 3695/5712 [8:42:14<4:41:58,  8.39s/it]08/04/2024 18:20:23 - INFO - __main__ -   Step: 3695, LR: 1.9611067876164302e-07, Loss: 0.14933758974075317
2024-08-05T01:20:31.720191583Z 
 65%|██████▍   | 3696/5712 [8:42:22<4:43:09,  8.43s/it]08/04/2024 18:20:31 - INFO - __main__ -   Step: 3696, LR: 1.9601340013132615e-07, Loss: 0.17994631826877594
2024-08-05T01:20:41.291925957Z 
 65%|██████▍   | 3697/5712 [8:42:32<4:54:32,  8.77s/it]08/04/2024 18:20:41 - INFO - __main__ -   Step: 3697, LR: 1.9591612150100925e-07, Loss: 0.19954906404018402
2024-08-05T01:20:50.006471571Z 
 65%|██████▍   | 3698/5712 [8:42:41<4:53:50,  8.75s/it]08/04/2024 18:20:50 - INFO - __main__ -   Step: 3698, LR: 1.9581884287069237e-07, Loss: 0.19956035912036896
2024-08-05T01:20:58.981102523Z 
 65%|██████▍   | 3699/5712 [8:42:50<4:55:54,  8.82s/it]08/04/2024 18:20:58 - INFO - __main__ -   Step: 3699, LR: 1.9572156424037547e-07, Loss: 0.3278849422931671
2024-08-05T01:21:07.229745886Z 
 65%|██████▍   | 3700/5712 [8:42:58<4:50:01,  8.65s/it]08/04/2024 18:21:07 - INFO - __main__ -   Step: 3700, LR: 1.9562428561005863e-07, Loss: 0.2940197288990021
2024-08-05T01:21:15.945393615Z 
 65%|██████▍   | 3701/5712 [8:43:07<4:50:32,  8.67s/it]08/04/2024 18:21:15 - INFO - __main__ -   Step: 3701, LR: 1.9552700697974172e-07, Loss: 0.2011786848306656
2024-08-05T01:21:24.031746961Z 
 65%|██████▍   | 3702/5712 [8:43:15<4:44:32,  8.49s/it]08/04/2024 18:21:24 - INFO - __main__ -   Step: 3702, LR: 1.9542972834942485e-07, Loss: 0.28018975257873535
2024-08-05T01:21:32.097874640Z 
 65%|██████▍   | 3703/5712 [8:43:23<4:40:06,  8.37s/it]08/04/2024 18:21:32 - INFO - __main__ -   Step: 3703, LR: 1.9533244971910795e-07, Loss: 0.2111119031906128
2024-08-05T01:21:40.296842330Z 
 65%|██████▍   | 3704/5712 [8:43:31<4:38:18,  8.32s/it]08/04/2024 18:21:40 - INFO - __main__ -   Step: 3704, LR: 1.9523517108879107e-07, Loss: 0.20098194479942322
2024-08-05T01:21:48.694548498Z 
 65%|██████▍   | 3705/5712 [8:43:39<4:38:58,  8.34s/it]08/04/2024 18:21:48 - INFO - __main__ -   Step: 3705, LR: 1.9513789245847417e-07, Loss: 0.19269150495529175
2024-08-05T01:21:56.983214600Z 
 65%|██████▍   | 3706/5712 [8:43:48<4:38:19,  8.32s/it]08/04/2024 18:21:56 - INFO - __main__ -   Step: 3706, LR: 1.9504061382815727e-07, Loss: 0.2362697720527649
2024-08-05T01:22:05.492846460Z 
 65%|██████▍   | 3707/5712 [8:43:56<4:40:02,  8.38s/it]08/04/2024 18:22:05 - INFO - __main__ -   Step: 3707, LR: 1.949433351978404e-07, Loss: 0.10700462013483047
2024-08-05T01:22:13.740357224Z 
 65%|██████▍   | 3708/5712 [8:44:04<4:38:34,  8.34s/it]08/04/2024 18:22:13 - INFO - __main__ -   Step: 3708, LR: 1.948460565675235e-07, Loss: 0.11575668305158615
2024-08-05T01:22:21.861104256Z 
 65%|██████▍   | 3709/5712 [8:44:13<4:36:13,  8.27s/it]08/04/2024 18:22:21 - INFO - __main__ -   Step: 3709, LR: 1.9474877793720665e-07, Loss: 0.22243909537792206
2024-08-05T01:22:30.739257481Z 
 65%|██████▍   | 3710/5712 [8:44:21<4:42:07,  8.46s/it]08/04/2024 18:22:30 - INFO - __main__ -   Step: 3710, LR: 1.9465149930688975e-07, Loss: 0.15928047895431519
2024-08-05T01:22:39.471726468Z 
 65%|██████▍   | 3711/5712 [8:44:30<4:44:45,  8.54s/it]08/04/2024 18:22:39 - INFO - __main__ -   Step: 3711, LR: 1.9455422067657287e-07, Loss: 0.17409072816371918
2024-08-05T01:22:47.523562867Z 
 65%|██████▍   | 3712/5712 [8:44:38<4:39:45,  8.39s/it]08/04/2024 18:22:47 - INFO - __main__ -   Step: 3712, LR: 1.9445694204625597e-07, Loss: 0.18533797562122345
2024-08-05T01:22:55.986316395Z 
 65%|██████▌   | 3713/5712 [8:44:47<4:40:18,  8.41s/it]08/04/2024 18:22:55 - INFO - __main__ -   Step: 3713, LR: 1.943596634159391e-07, Loss: 0.13521519303321838
2024-08-05T01:23:04.769152892Z 
 65%|██████▌   | 3714/5712 [8:44:55<4:43:52,  8.52s/it]08/04/2024 18:23:04 - INFO - __main__ -   Step: 3714, LR: 1.942623847856222e-07, Loss: 0.2905814051628113
2024-08-05T01:23:13.597614594Z 
 65%|██████▌   | 3715/5712 [8:45:04<4:46:45,  8.62s/it]08/04/2024 18:23:13 - INFO - __main__ -   Step: 3715, LR: 1.9416510615530532e-07, Loss: 0.1601599007844925
2024-08-05T01:23:22.106574339Z 
 65%|██████▌   | 3716/5712 [8:45:13<4:45:31,  8.58s/it]08/04/2024 18:23:22 - INFO - __main__ -   Step: 3716, LR: 1.9406782752498842e-07, Loss: 0.31179508566856384
2024-08-05T01:23:30.339318737Z 
 65%|██████▌   | 3717/5712 [8:45:21<4:41:54,  8.48s/it]08/04/2024 18:23:30 - INFO - __main__ -   Step: 3717, LR: 1.9397054889467155e-07, Loss: 0.15060335397720337
2024-08-05T01:23:38.580663067Z 
 65%|██████▌   | 3718/5712 [8:45:29<4:39:24,  8.41s/it]08/04/2024 18:23:38 - INFO - __main__ -   Step: 3718, LR: 1.9387327026435467e-07, Loss: 0.20172737538814545
2024-08-05T01:23:46.687457393Z 
 65%|██████▌   | 3719/5712 [8:45:37<4:36:16,  8.32s/it]08/04/2024 18:23:46 - INFO - __main__ -   Step: 3719, LR: 1.937759916340378e-07, Loss: 0.1739373356103897
2024-08-05T01:23:54.979952672Z 
 65%|██████▌   | 3720/5712 [8:45:46<4:35:52,  8.31s/it]08/04/2024 18:23:54 - INFO - __main__ -   Step: 3720, LR: 1.936787130037209e-07, Loss: 0.20213088393211365
2024-08-05T01:24:02.940981303Z 
 65%|██████▌   | 3721/5712 [8:45:54<4:32:16,  8.21s/it]08/04/2024 18:24:02 - INFO - __main__ -   Step: 3721, LR: 1.9358143437340402e-07, Loss: 0.28370946645736694
2024-08-05T01:24:11.600826154Z 
 65%|██████▌   | 3722/5712 [8:46:02<4:36:39,  8.34s/it]08/04/2024 18:24:11 - INFO - __main__ -   Step: 3722, LR: 1.9348415574308712e-07, Loss: 0.1877443790435791
2024-08-05T01:24:20.365734205Z 
 65%|██████▌   | 3723/5712 [8:46:11<4:40:44,  8.47s/it]08/04/2024 18:24:20 - INFO - __main__ -   Step: 3723, LR: 1.9338687711277025e-07, Loss: 0.22825001180171967
2024-08-05T01:24:28.753765774Z 
 65%|██████▌   | 3724/5712 [8:46:19<4:39:47,  8.44s/it]08/04/2024 18:24:28 - INFO - __main__ -   Step: 3724, LR: 1.9328959848245335e-07, Loss: 0.1865273416042328
2024-08-05T01:24:37.294039769Z 
 65%|██████▌   | 3725/5712 [8:46:28<4:40:36,  8.47s/it]08/04/2024 18:24:37 - INFO - __main__ -   Step: 3725, LR: 1.9319231985213647e-07, Loss: 0.16594776511192322
2024-08-05T01:24:45.470498632Z 
 65%|██████▌   | 3726/5712 [8:46:36<4:37:31,  8.38s/it]08/04/2024 18:24:45 - INFO - __main__ -   Step: 3726, LR: 1.9309504122181957e-07, Loss: 0.20502427220344543
2024-08-05T01:24:54.087595244Z 
 65%|██████▌   | 3727/5712 [8:46:45<4:39:41,  8.45s/it]08/04/2024 18:24:54 - INFO - __main__ -   Step: 3727, LR: 1.9299776259150272e-07, Loss: 0.16014182567596436
2024-08-05T01:25:02.334537130Z 
 65%|██████▌   | 3728/5712 [8:46:53<4:37:29,  8.39s/it]08/04/2024 18:25:02 - INFO - __main__ -   Step: 3728, LR: 1.9290048396118582e-07, Loss: 0.17176252603530884
2024-08-05T01:25:10.494062544Z 
 65%|██████▌   | 3729/5712 [8:47:01<4:35:02,  8.32s/it]08/04/2024 18:25:10 - INFO - __main__ -   Step: 3729, LR: 1.9280320533086895e-07, Loss: 0.073527991771698
2024-08-05T01:25:19.150674679Z 
 65%|██████▌   | 3730/5712 [8:47:10<4:38:13,  8.42s/it]08/04/2024 18:25:19 - INFO - __main__ -   Step: 3730, LR: 1.9270592670055205e-07, Loss: 0.19224773347377777
2024-08-05T01:25:28.364978937Z 
 65%|██████▌   | 3731/5712 [8:47:19<4:45:55,  8.66s/it]08/04/2024 18:25:28 - INFO - __main__ -   Step: 3731, LR: 1.9260864807023517e-07, Loss: 0.19624114036560059
2024-08-05T01:25:37.127901842Z 
 65%|██████▌   | 3732/5712 [8:47:28<4:46:47,  8.69s/it]08/04/2024 18:25:37 - INFO - __main__ -   Step: 3732, LR: 1.9251136943991827e-07, Loss: 0.14698055386543274
2024-08-05T01:25:46.294638987Z 
 65%|██████▌   | 3733/5712 [8:47:37<4:51:20,  8.83s/it]08/04/2024 18:25:46 - INFO - __main__ -   Step: 3733, LR: 1.924140908096014e-07, Loss: 0.1952955722808838
2024-08-05T01:25:54.905288045Z 
 65%|██████▌   | 3734/5712 [8:47:46<4:49:00,  8.77s/it]08/04/2024 18:25:54 - INFO - __main__ -   Step: 3734, LR: 1.923168121792845e-07, Loss: 0.1724034696817398
2024-08-05T01:26:03.384431784Z 
 65%|██████▌   | 3735/5712 [8:47:54<4:46:01,  8.68s/it]08/04/2024 18:26:03 - INFO - __main__ -   Step: 3735, LR: 1.9221953354896762e-07, Loss: 0.11023959517478943
2024-08-05T01:26:11.758039888Z 
 65%|██████▌   | 3736/5712 [8:48:02<4:42:51,  8.59s/it]08/04/2024 18:26:11 - INFO - __main__ -   Step: 3736, LR: 1.9212225491865075e-07, Loss: 0.0959472507238388
2024-08-05T01:26:19.896869315Z 
 65%|██████▌   | 3737/5712 [8:48:11<4:38:15,  8.45s/it]08/04/2024 18:26:19 - INFO - __main__ -   Step: 3737, LR: 1.9202497628833387e-07, Loss: 0.17817774415016174
2024-08-05T01:26:28.202229140Z 
 65%|██████▌   | 3738/5712 [8:48:19<4:36:38,  8.41s/it]08/04/2024 18:26:28 - INFO - __main__ -   Step: 3738, LR: 1.9192769765801697e-07, Loss: 0.3041658103466034
2024-08-05T01:26:36.632202382Z 
 65%|██████▌   | 3739/5712 [8:48:27<4:36:44,  8.42s/it]08/04/2024 18:26:36 - INFO - __main__ -   Step: 3739, LR: 1.918304190277001e-07, Loss: 0.1443738341331482
2024-08-05T01:26:45.061711099Z 
 65%|██████▌   | 3740/5712 [8:48:36<4:36:43,  8.42s/it]08/04/2024 18:26:45 - INFO - __main__ -   Step: 3740, LR: 1.917331403973832e-07, Loss: 0.14551249146461487
2024-08-05T01:26:53.276352877Z 
 65%|██████▌   | 3741/5712 [8:48:44<4:34:33,  8.36s/it]08/04/2024 18:26:53 - INFO - __main__ -   Step: 3741, LR: 1.9163586176706632e-07, Loss: 0.2945825457572937
2024-08-05T01:27:01.832022823Z 
 66%|██████▌   | 3742/5712 [8:48:52<4:36:22,  8.42s/it]08/04/2024 18:27:01 - INFO - __main__ -   Step: 3742, LR: 1.9153858313674942e-07, Loss: 0.23563474416732788
2024-08-05T01:27:10.037369792Z 
 66%|██████▌   | 3743/5712 [8:49:01<4:34:08,  8.35s/it]08/04/2024 18:27:10 - INFO - __main__ -   Step: 3743, LR: 1.9144130450643252e-07, Loss: 0.16762422025203705
2024-08-05T01:27:18.381903965Z 
 66%|██████▌   | 3744/5712 [8:49:09<4:33:54,  8.35s/it]08/04/2024 18:27:18 - INFO - __main__ -   Step: 3744, LR: 1.9134402587611565e-07, Loss: 0.15181675553321838
2024-08-05T01:27:26.751510486Z 
 66%|██████▌   | 3745/5712 [8:49:17<4:33:57,  8.36s/it]08/04/2024 18:27:26 - INFO - __main__ -   Step: 3745, LR: 1.9124674724579877e-07, Loss: 0.14260002970695496
2024-08-05T01:27:35.716253953Z 
 66%|██████▌   | 3746/5712 [8:49:26<4:39:47,  8.54s/it]08/04/2024 18:27:35 - INFO - __main__ -   Step: 3746, LR: 1.911494686154819e-07, Loss: 0.20889821648597717
2024-08-05T01:27:45.052330650Z 
 66%|██████▌   | 3747/5712 [8:49:36<4:47:29,  8.78s/it]08/04/2024 18:27:45 - INFO - __main__ -   Step: 3747, LR: 1.91052189985165e-07, Loss: 0.12832953035831451
2024-08-05T01:27:53.791525140Z 
 66%|██████▌   | 3748/5712 [8:49:44<4:46:57,  8.77s/it]08/04/2024 18:27:53 - INFO - __main__ -   Step: 3748, LR: 1.9095491135484812e-07, Loss: 0.13380564749240875
2024-08-05T01:28:02.292419663Z 
 66%|██████▌   | 3749/5712 [8:49:53<4:44:12,  8.69s/it]08/04/2024 18:28:02 - INFO - __main__ -   Step: 3749, LR: 1.9085763272453122e-07, Loss: 0.18879109621047974
2024-08-05T01:28:11.261585237Z 
 66%|██████▌   | 3750/5712 [8:50:02<4:46:49,  8.77s/it]08/04/2024 18:28:11 - INFO - __main__ -   Step: 3750, LR: 1.9076035409421435e-07, Loss: 0.18726752698421478
2024-08-05T01:28:19.513577172Z 
 66%|██████▌   | 3751/5712 [8:50:10<4:41:35,  8.62s/it]08/04/2024 18:28:19 - INFO - __main__ -   Step: 3751, LR: 1.9066307546389744e-07, Loss: 0.3186318874359131
2024-08-05T01:28:27.786611093Z 
 66%|██████▌   | 3752/5712 [8:50:18<4:38:05,  8.51s/it]08/04/2024 18:28:27 - INFO - __main__ -   Step: 3752, LR: 1.9056579683358057e-07, Loss: 0.22375039756298065
2024-08-05T01:28:35.973981001Z 
 66%|██████▌   | 3753/5712 [8:50:27<4:34:45,  8.42s/it]08/04/2024 18:28:35 - INFO - __main__ -   Step: 3753, LR: 1.9046851820326367e-07, Loss: 0.18216633796691895
2024-08-05T01:28:44.076756855Z 
 66%|██████▌   | 3754/5712 [8:50:35<4:31:33,  8.32s/it]08/04/2024 18:28:44 - INFO - __main__ -   Step: 3754, LR: 1.9037123957294682e-07, Loss: 0.26404106616973877
2024-08-05T01:28:52.428067147Z 
 66%|██████▌   | 3755/5712 [8:50:43<4:31:42,  8.33s/it]08/04/2024 18:28:52 - INFO - __main__ -   Step: 3755, LR: 1.9027396094262992e-07, Loss: 0.11817478388547897
2024-08-05T01:29:01.050931324Z 
 66%|██████▌   | 3756/5712 [8:50:52<4:34:25,  8.42s/it]08/04/2024 18:29:01 - INFO - __main__ -   Step: 3756, LR: 1.9017668231231305e-07, Loss: 0.2206217646598816
2024-08-05T01:29:09.169261535Z 
 66%|██████▌   | 3757/5712 [8:51:00<4:31:21,  8.33s/it]08/04/2024 18:29:09 - INFO - __main__ -   Step: 3757, LR: 1.9007940368199614e-07, Loss: 0.18126241862773895
2024-08-05T01:29:17.540461371Z 
 66%|██████▌   | 3758/5712 [8:51:08<4:31:38,  8.34s/it]08/04/2024 18:29:17 - INFO - __main__ -   Step: 3758, LR: 1.8998212505167927e-07, Loss: 0.1490376889705658
2024-08-05T01:29:26.487686871Z 
 66%|██████▌   | 3759/5712 [8:51:17<4:37:25,  8.52s/it]08/04/2024 18:29:26 - INFO - __main__ -   Step: 3759, LR: 1.8988484642136237e-07, Loss: 0.2937980890274048
2024-08-05T01:29:34.832235835Z 
 66%|██████▌   | 3760/5712 [8:51:25<4:35:32,  8.47s/it]08/04/2024 18:29:34 - INFO - __main__ -   Step: 3760, LR: 1.897875677910455e-07, Loss: 0.24621261656284332
2024-08-05T01:29:43.042359099Z 
 66%|██████▌   | 3761/5712 [8:51:34<4:32:51,  8.39s/it]08/04/2024 18:29:43 - INFO - __main__ -   Step: 3761, LR: 1.896902891607286e-07, Loss: 0.12959010899066925
2024-08-05T01:29:51.264127354Z 
 66%|██████▌   | 3762/5712 [8:51:42<4:31:04,  8.34s/it]08/04/2024 18:29:51 - INFO - __main__ -   Step: 3762, LR: 1.8959301053041172e-07, Loss: 0.16894562542438507
2024-08-05T01:29:59.935132000Z 
 66%|██████▌   | 3763/5712 [8:51:51<4:34:09,  8.44s/it]08/04/2024 18:29:59 - INFO - __main__ -   Step: 3763, LR: 1.8949573190009485e-07, Loss: 0.16543829441070557
2024-08-05T01:30:08.886712976Z 
 66%|██████▌   | 3764/5712 [8:52:00<4:38:59,  8.59s/it]08/04/2024 18:30:08 - INFO - __main__ -   Step: 3764, LR: 1.8939845326977797e-07, Loss: 0.12792693078517914
2024-08-05T01:30:17.292748546Z 
 66%|██████▌   | 3765/5712 [8:52:08<4:37:01,  8.54s/it]08/04/2024 18:30:17 - INFO - __main__ -   Step: 3765, LR: 1.8930117463946107e-07, Loss: 0.17171701788902283
2024-08-05T01:30:25.517370125Z 
 66%|██████▌   | 3766/5712 [8:52:16<4:33:50,  8.44s/it]08/04/2024 18:30:25 - INFO - __main__ -   Step: 3766, LR: 1.892038960091442e-07, Loss: 0.1623763144016266
2024-08-05T01:30:34.168803890Z 
 66%|██████▌   | 3767/5712 [8:52:25<4:35:43,  8.51s/it]08/04/2024 18:30:34 - INFO - __main__ -   Step: 3767, LR: 1.891066173788273e-07, Loss: 0.23009994626045227
2024-08-05T01:30:42.562795732Z 
 66%|██████▌   | 3768/5712 [8:52:33<4:34:30,  8.47s/it]08/04/2024 18:30:42 - INFO - __main__ -   Step: 3768, LR: 1.8900933874851042e-07, Loss: 0.21188846230506897
2024-08-05T01:30:51.479419364Z 
 66%|██████▌   | 3769/5712 [8:52:42<4:38:40,  8.61s/it]08/04/2024 18:30:51 - INFO - __main__ -   Step: 3769, LR: 1.8891206011819352e-07, Loss: 0.25281038880348206
2024-08-05T01:30:59.569815539Z 
 66%|██████▌   | 3770/5712 [8:52:50<4:33:31,  8.45s/it]08/04/2024 18:30:59 - INFO - __main__ -   Step: 3770, LR: 1.8881478148787664e-07, Loss: 0.14374716579914093
2024-08-05T01:31:07.935650327Z 
 66%|██████▌   | 3771/5712 [8:52:59<4:32:33,  8.43s/it]08/04/2024 18:31:07 - INFO - __main__ -   Step: 3771, LR: 1.8871750285755974e-07, Loss: 0.16791316866874695
2024-08-05T01:31:16.141854790Z 
 66%|██████▌   | 3772/5712 [8:53:07<4:30:17,  8.36s/it]08/04/2024 18:31:16 - INFO - __main__ -   Step: 3772, LR: 1.886202242272429e-07, Loss: 0.2551642656326294
2024-08-05T01:31:24.551793668Z 
 66%|██████▌   | 3773/5712 [8:53:15<4:30:38,  8.37s/it]08/04/2024 18:31:24 - INFO - __main__ -   Step: 3773, LR: 1.88522945596926e-07, Loss: 0.16311819851398468
2024-08-05T01:31:33.007309003Z 
 66%|██████▌   | 3774/5712 [8:53:24<4:31:17,  8.40s/it]08/04/2024 18:31:33 - INFO - __main__ -   Step: 3774, LR: 1.8842566696660912e-07, Loss: 0.19942086935043335
2024-08-05T01:31:41.159786152Z 
 66%|██████▌   | 3775/5712 [8:53:32<4:28:45,  8.33s/it]08/04/2024 18:31:41 - INFO - __main__ -   Step: 3775, LR: 1.8832838833629222e-07, Loss: 0.14986346662044525
2024-08-05T01:31:49.601110823Z 
 66%|██████▌   | 3776/5712 [8:53:40<4:29:44,  8.36s/it]08/04/2024 18:31:49 - INFO - __main__ -   Step: 3776, LR: 1.8823110970597534e-07, Loss: 0.22266961634159088
2024-08-05T01:31:58.003321155Z 
 66%|██████▌   | 3777/5712 [8:53:49<4:30:00,  8.37s/it]08/04/2024 18:31:58 - INFO - __main__ -   Step: 3777, LR: 1.8813383107565844e-07, Loss: 0.21078631281852722
2024-08-05T01:32:06.735460077Z 
 66%|██████▌   | 3778/5712 [8:53:57<4:33:21,  8.48s/it]08/04/2024 18:32:06 - INFO - __main__ -   Step: 3778, LR: 1.8803655244534157e-07, Loss: 0.2346513271331787
2024-08-05T01:32:15.842479536Z 
 66%|██████▌   | 3779/5712 [8:54:06<4:39:15,  8.67s/it]08/04/2024 18:32:15 - INFO - __main__ -   Step: 3779, LR: 1.8793927381502467e-07, Loss: 0.2015237808227539
2024-08-05T01:32:24.055650370Z 
 66%|██████▌   | 3780/5712 [8:54:15<4:34:43,  8.53s/it]08/04/2024 18:32:24 - INFO - __main__ -   Step: 3780, LR: 1.8784199518470777e-07, Loss: 0.3059546947479248
2024-08-05T01:32:32.661075489Z 
 66%|██████▌   | 3781/5712 [8:54:23<4:35:17,  8.55s/it]08/04/2024 18:32:32 - INFO - __main__ -   Step: 3781, LR: 1.8774471655439092e-07, Loss: 0.11954890191555023
2024-08-05T01:32:41.464323208Z 
 66%|██████▌   | 3782/5712 [8:54:32<4:37:33,  8.63s/it]08/04/2024 18:32:41 - INFO - __main__ -   Step: 3782, LR: 1.8764743792407402e-07, Loss: 0.22065770626068115
2024-08-05T01:32:50.122696306Z 
 66%|██████▌   | 3783/5712 [8:54:41<4:37:41,  8.64s/it]08/04/2024 18:32:50 - INFO - __main__ -   Step: 3783, LR: 1.8755015929375714e-07, Loss: 0.09618736058473587
2024-08-05T01:32:59.359385333Z 
 66%|██████▌   | 3784/5712 [8:54:50<4:43:20,  8.82s/it]08/04/2024 18:32:59 - INFO - __main__ -   Step: 3784, LR: 1.8745288066344024e-07, Loss: 0.1672457903623581
2024-08-05T01:33:07.540368051Z 
 66%|██████▋   | 3785/5712 [8:54:58<4:37:03,  8.63s/it]08/04/2024 18:33:07 - INFO - __main__ -   Step: 3785, LR: 1.8735560203312337e-07, Loss: 0.15426483750343323
2024-08-05T01:33:15.546821112Z 
 66%|██████▋   | 3786/5712 [8:55:06<4:30:56,  8.44s/it]08/04/2024 18:33:15 - INFO - __main__ -   Step: 3786, LR: 1.8725832340280647e-07, Loss: 0.22009892761707306
2024-08-05T01:33:23.692551847Z 
 66%|██████▋   | 3787/5712 [8:55:14<4:27:57,  8.35s/it]08/04/2024 18:33:23 - INFO - __main__ -   Step: 3787, LR: 1.871610447724896e-07, Loss: 0.1177368313074112
2024-08-05T01:33:32.136400142Z 
 66%|██████▋   | 3788/5712 [8:55:23<4:28:42,  8.38s/it]08/04/2024 18:33:32 - INFO - __main__ -   Step: 3788, LR: 1.870637661421727e-07, Loss: 0.28182530403137207
2024-08-05T01:33:40.509696742Z 
 66%|██████▋   | 3789/5712 [8:55:31<4:28:30,  8.38s/it]08/04/2024 18:33:40 - INFO - __main__ -   Step: 3789, LR: 1.8696648751185582e-07, Loss: 0.15073047578334808
2024-08-05T01:33:48.937927852Z 
 66%|██████▋   | 3790/5712 [8:55:40<4:28:51,  8.39s/it]08/04/2024 18:33:48 - INFO - __main__ -   Step: 3790, LR: 1.8686920888153894e-07, Loss: 0.17539972066879272
2024-08-05T01:33:57.531606311Z 
 66%|██████▋   | 3791/5712 [8:55:48<4:30:38,  8.45s/it]08/04/2024 18:33:57 - INFO - __main__ -   Step: 3791, LR: 1.8677193025122207e-07, Loss: 0.2047245353460312
2024-08-05T01:34:05.974339242Z 
 66%|██████▋   | 3792/5712 [8:55:57<4:30:23,  8.45s/it]08/04/2024 18:34:05 - INFO - __main__ -   Step: 3792, LR: 1.8667465162090517e-07, Loss: 0.16467440128326416
2024-08-05T01:34:14.903619701Z 
 66%|██████▋   | 3793/5712 [8:56:06<4:34:51,  8.59s/it]08/04/2024 18:34:14 - INFO - __main__ -   Step: 3793, LR: 1.865773729905883e-07, Loss: 0.13349005579948425
2024-08-05T01:34:22.428765103Z 
 66%|██████▋   | 3794/5712 [8:56:13<4:24:27,  8.27s/it]08/04/2024 18:34:22 - INFO - __main__ -   Step: 3794, LR: 1.864800943602714e-07, Loss: 0.23128628730773926
2024-08-05T01:34:31.580016617Z 
 66%|██████▋   | 3795/5712 [8:56:22<4:32:44,  8.54s/it]08/04/2024 18:34:31 - INFO - __main__ -   Step: 3795, LR: 1.8638281572995452e-07, Loss: 0.2564728856086731
2024-08-05T01:34:41.285883417Z 
 66%|██████▋   | 3796/5712 [8:56:32<4:43:48,  8.89s/it]08/04/2024 18:34:41 - INFO - __main__ -   Step: 3796, LR: 1.8628553709963762e-07, Loss: 0.15287697315216064
2024-08-05T01:34:49.616680809Z 
 66%|██████▋   | 3797/5712 [8:56:40<4:38:19,  8.72s/it]08/04/2024 18:34:49 - INFO - __main__ -   Step: 3797, LR: 1.8618825846932074e-07, Loss: 0.18749180436134338
2024-08-05T01:34:58.003195403Z 
 66%|██████▋   | 3798/5712 [8:56:49<4:34:59,  8.62s/it]08/04/2024 18:34:58 - INFO - __main__ -   Step: 3798, LR: 1.8609097983900384e-07, Loss: 0.16261373460292816
2024-08-05T01:35:06.599819288Z 
 67%|██████▋   | 3799/5712 [8:56:57<4:34:36,  8.61s/it]08/04/2024 18:35:06 - INFO - __main__ -   Step: 3799, LR: 1.8599370120868697e-07, Loss: 0.14881807565689087
2024-08-05T01:35:14.773883659Z 
 67%|██████▋   | 3800/5712 [8:57:05<4:30:16,  8.48s/it]08/04/2024 18:35:14 - INFO - __main__ -   Step: 3800, LR: 1.858964225783701e-07, Loss: 0.10315178334712982
2024-08-05T01:35:23.334249862Z 
 67%|██████▋   | 3801/5712 [8:57:14<4:30:53,  8.51s/it]08/04/2024 18:35:23 - INFO - __main__ -   Step: 3801, LR: 1.8579914394805322e-07, Loss: 0.1846277415752411
2024-08-05T01:35:31.362293727Z 
 67%|██████▋   | 3802/5712 [8:57:22<4:26:11,  8.36s/it]08/04/2024 18:35:31 - INFO - __main__ -   Step: 3802, LR: 1.8570186531773632e-07, Loss: 0.09839058667421341
2024-08-05T01:35:39.609346949Z 
 67%|██████▋   | 3803/5712 [8:57:30<4:24:57,  8.33s/it]08/04/2024 18:35:39 - INFO - __main__ -   Step: 3803, LR: 1.8560458668741944e-07, Loss: 0.1910998523235321
2024-08-05T01:35:48.070673116Z 
 67%|██████▋   | 3804/5712 [8:57:39<4:26:05,  8.37s/it]08/04/2024 18:35:48 - INFO - __main__ -   Step: 3804, LR: 1.8550730805710254e-07, Loss: 0.3010140359401703
2024-08-05T01:35:56.549386825Z 
 67%|██████▋   | 3805/5712 [8:57:47<4:27:00,  8.40s/it]08/04/2024 18:35:56 - INFO - __main__ -   Step: 3805, LR: 1.8541002942678567e-07, Loss: 0.1730842888355255
2024-08-05T01:36:04.800408825Z 
 67%|██████▋   | 3806/5712 [8:57:55<4:25:26,  8.36s/it]08/04/2024 18:36:04 - INFO - __main__ -   Step: 3806, LR: 1.8531275079646877e-07, Loss: 0.2781553566455841
2024-08-05T01:36:13.626039930Z 
 67%|██████▋   | 3807/5712 [8:58:04<4:29:46,  8.50s/it]08/04/2024 18:36:13 - INFO - __main__ -   Step: 3807, LR: 1.852154721661519e-07, Loss: 0.11658654361963272
2024-08-05T01:36:21.847884578Z 
 67%|██████▋   | 3808/5712 [8:58:12<4:27:00,  8.41s/it]08/04/2024 18:36:21 - INFO - __main__ -   Step: 3808, LR: 1.85118193535835e-07, Loss: 0.18037483096122742
2024-08-05T01:36:30.923453076Z Configuration saved in /output/epoch_1/config.json
2024-08-05T01:36:30.923795388Z Configuration saved in /output/epoch_1/generation_config.json
2024-08-05T01:36:41.256052546Z The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at /output/epoch_1/pytorch_model.bin.index.json.
2024-08-05T01:36:49.679856138Z 
 67%|██████▋   | 3809/5712 [8:58:40<7:31:38, 14.24s/it]08/04/2024 18:36:49 - INFO - __main__ -   Step: 3809, LR: 1.8502091490551814e-07, Loss: 0.07152853161096573
2024-08-05T01:36:58.062065086Z 
 67%|██████▋   | 3810/5712 [8:58:49<6:35:41, 12.48s/it]08/04/2024 18:36:58 - INFO - __main__ -   Step: 3810, LR: 1.8492363627520124e-07, Loss: 0.09787660837173462
2024-08-05T01:37:06.318683755Z 
 67%|██████▋   | 3811/5712 [8:58:57<5:55:18, 11.21s/it]08/04/2024 18:37:06 - INFO - __main__ -   Step: 3811, LR: 1.8482635764488437e-07, Loss: 0.10210122913122177
2024-08-05T01:37:14.979141886Z 
 67%|██████▋   | 3812/5712 [8:59:06<5:30:52, 10.45s/it]08/04/2024 18:37:14 - INFO - __main__ -   Step: 3812, LR: 1.8472907901456747e-07, Loss: 0.08290114998817444
2024-08-05T01:37:23.737965152Z 
 67%|██████▋   | 3813/5712 [8:59:14<5:14:39,  9.94s/it]08/04/2024 18:37:23 - INFO - __main__ -   Step: 3813, LR: 1.846318003842506e-07, Loss: 0.0619690865278244
2024-08-05T01:37:31.999173241Z 
 67%|██████▋   | 3814/5712 [8:59:23<4:58:31,  9.44s/it]08/04/2024 18:37:31 - INFO - __main__ -   Step: 3814, LR: 1.845345217539337e-07, Loss: 0.07823439687490463
2024-08-05T01:37:40.859419360Z 
 67%|██████▋   | 3815/5712 [8:59:32<4:52:54,  9.26s/it]08/04/2024 18:37:40 - INFO - __main__ -   Step: 3815, LR: 1.8443724312361682e-07, Loss: 0.04066888615489006
2024-08-05T01:37:49.261231028Z 
 67%|██████▋   | 3816/5712 [8:59:40<4:44:34,  9.01s/it]08/04/2024 18:37:49 - INFO - __main__ -   Step: 3816, LR: 1.8433996449329992e-07, Loss: 0.07956826686859131
2024-08-05T01:37:57.475353447Z 
 67%|██████▋   | 3817/5712 [8:59:48<4:36:55,  8.77s/it]08/04/2024 18:37:57 - INFO - __main__ -   Step: 3817, LR: 1.8424268586298301e-07, Loss: 0.06235364079475403
2024-08-05T01:38:05.934985268Z 
 67%|██████▋   | 3818/5712 [8:59:57<4:33:51,  8.68s/it]08/04/2024 18:38:05 - INFO - __main__ -   Step: 3818, LR: 1.8414540723266617e-07, Loss: 0.10411421954631805
2024-08-05T01:38:14.362495614Z 
 67%|██████▋   | 3819/5712 [9:00:05<4:31:21,  8.60s/it]08/04/2024 18:38:14 - INFO - __main__ -   Step: 3819, LR: 1.840481286023493e-07, Loss: 0.0771106481552124
2024-08-05T01:38:23.106243521Z 
 67%|██████▋   | 3820/5712 [9:00:14<4:32:34,  8.64s/it]08/04/2024 18:38:23 - INFO - __main__ -   Step: 3820, LR: 1.839508499720324e-07, Loss: 0.0395335927605629
2024-08-05T01:38:32.712709302Z 
 67%|██████▋   | 3821/5712 [9:00:23<4:41:30,  8.93s/it]08/04/2024 18:38:32 - INFO - __main__ -   Step: 3821, LR: 1.838535713417155e-07, Loss: 0.06665242463350296
2024-08-05T01:38:41.502746458Z 
 67%|██████▋   | 3822/5712 [9:00:32<4:40:02,  8.89s/it]08/04/2024 18:38:41 - INFO - __main__ -   Step: 3822, LR: 1.8375629271139862e-07, Loss: 0.11001580953598022
2024-08-05T01:38:49.060411743Z 
 67%|██████▋   | 3823/5712 [9:00:40<4:27:18,  8.49s/it]08/04/2024 18:38:49 - INFO - __main__ -   Step: 3823, LR: 1.8365901408108171e-07, Loss: 0.07771439850330353
2024-08-05T01:38:57.878789960Z 
 67%|██████▋   | 3824/5712 [9:00:49<4:30:15,  8.59s/it]08/04/2024 18:38:57 - INFO - __main__ -   Step: 3824, LR: 1.8356173545076484e-07, Loss: 0.06754506379365921
2024-08-05T01:39:06.514075092Z 
 67%|██████▋   | 3825/5712 [9:00:57<4:30:33,  8.60s/it]08/04/2024 18:39:06 - INFO - __main__ -   Step: 3825, LR: 1.8346445682044794e-07, Loss: 0.08532115817070007
2024-08-05T01:39:15.002907335Z 
 67%|██████▋   | 3826/5712 [9:01:06<4:29:20,  8.57s/it]08/04/2024 18:39:15 - INFO - __main__ -   Step: 3826, LR: 1.8336717819013106e-07, Loss: 0.13266196846961975
2024-08-05T01:39:23.280463225Z 
 67%|██████▋   | 3827/5712 [9:01:14<4:26:27,  8.48s/it]08/04/2024 18:39:23 - INFO - __main__ -   Step: 3827, LR: 1.832698995598142e-07, Loss: 0.07197248935699463
2024-08-05T01:39:31.407688298Z 
 67%|██████▋   | 3828/5712 [9:01:22<4:22:58,  8.38s/it]08/04/2024 18:39:31 - INFO - __main__ -   Step: 3828, LR: 1.8317262092949732e-07, Loss: 0.07102014124393463
2024-08-05T01:39:40.119091781Z 
 67%|██████▋   | 3829/5712 [9:01:31<4:26:00,  8.48s/it]08/04/2024 18:39:40 - INFO - __main__ -   Step: 3829, LR: 1.8307534229918041e-07, Loss: 0.0714481920003891
2024-08-05T01:39:49.017020717Z 
 67%|██████▋   | 3830/5712 [9:01:40<4:29:49,  8.60s/it]08/04/2024 18:39:49 - INFO - __main__ -   Step: 3830, LR: 1.8297806366886354e-07, Loss: 0.0911826491355896
2024-08-05T01:39:56.980179977Z 
 67%|██████▋   | 3831/5712 [9:01:48<4:23:40,  8.41s/it]08/04/2024 18:39:56 - INFO - __main__ -   Step: 3831, LR: 1.8288078503854664e-07, Loss: 0.1103939563035965
2024-08-05T01:40:06.173759291Z 
 67%|██████▋   | 3832/5712 [9:01:57<4:30:53,  8.65s/it]08/04/2024 18:40:06 - INFO - __main__ -   Step: 3832, LR: 1.8278350640822976e-07, Loss: 0.10937322676181793
2024-08-05T01:40:14.858760030Z 
 67%|██████▋   | 3833/5712 [9:02:06<4:31:07,  8.66s/it]08/04/2024 18:40:14 - INFO - __main__ -   Step: 3833, LR: 1.8268622777791286e-07, Loss: 0.07391676306724548
2024-08-05T01:40:22.992187276Z 
 67%|██████▋   | 3834/5712 [9:02:14<4:26:03,  8.50s/it]08/04/2024 18:40:22 - INFO - __main__ -   Step: 3834, LR: 1.82588949147596e-07, Loss: 0.05209445208311081
2024-08-05T01:40:31.077113987Z 
 67%|██████▋   | 3835/5712 [9:02:22<4:22:01,  8.38s/it]08/04/2024 18:40:31 - INFO - __main__ -   Step: 3835, LR: 1.824916705172791e-07, Loss: 0.07401411235332489
2024-08-05T01:40:39.343013263Z 
 67%|██████▋   | 3836/5712 [9:02:30<4:20:50,  8.34s/it]08/04/2024 18:40:39 - INFO - __main__ -   Step: 3836, LR: 1.8239439188696224e-07, Loss: 0.06507093459367752
2024-08-05T01:40:47.666081921Z 
 67%|██████▋   | 3837/5712 [9:02:38<4:20:31,  8.34s/it]08/04/2024 18:40:47 - INFO - __main__ -   Step: 3837, LR: 1.8229711325664534e-07, Loss: 0.05704260617494583
2024-08-05T01:40:57.184525415Z 
 67%|██████▋   | 3838/5712 [9:02:48<4:31:27,  8.69s/it]08/04/2024 18:40:57 - INFO - __main__ -   Step: 3838, LR: 1.8219983462632846e-07, Loss: 0.06433276832103729
2024-08-05T01:41:06.095162149Z 
 67%|██████▋   | 3839/5712 [9:02:57<4:33:22,  8.76s/it]08/04/2024 18:41:06 - INFO - __main__ -   Step: 3839, LR: 1.8210255599601156e-07, Loss: 0.06442330777645111
2024-08-05T01:41:14.771808589Z 
 67%|██████▋   | 3840/5712 [9:03:05<4:32:28,  8.73s/it]08/04/2024 18:41:14 - INFO - __main__ -   Step: 3840, LR: 1.820052773656947e-07, Loss: 0.061833567917346954
2024-08-05T01:41:23.727001239Z 
 67%|██████▋   | 3841/5712 [9:03:14<4:34:24,  8.80s/it]08/04/2024 18:41:23 - INFO - __main__ -   Step: 3841, LR: 1.819079987353778e-07, Loss: 0.09063906967639923
2024-08-05T01:41:32.348979381Z 
 67%|██████▋   | 3842/5712 [9:03:23<4:32:35,  8.75s/it]08/04/2024 18:41:32 - INFO - __main__ -   Step: 3842, LR: 1.8181072010506091e-07, Loss: 0.09747256338596344
2024-08-05T01:41:40.759452037Z 
 67%|██████▋   | 3843/5712 [9:03:31<4:29:18,  8.65s/it]08/04/2024 18:41:40 - INFO - __main__ -   Step: 3843, LR: 1.81713441474744e-07, Loss: 0.04892846196889877
2024-08-05T01:41:49.533712021Z 
 67%|██████▋   | 3844/5712 [9:03:40<4:30:22,  8.68s/it]08/04/2024 18:41:49 - INFO - __main__ -   Step: 3844, LR: 1.8161616284442714e-07, Loss: 0.11419804394245148
2024-08-05T01:41:58.036747073Z 
 67%|██████▋   | 3845/5712 [9:03:49<4:28:31,  8.63s/it]08/04/2024 18:41:58 - INFO - __main__ -   Step: 3845, LR: 1.8151888421411026e-07, Loss: 0.10562142729759216
2024-08-05T01:42:07.301084755Z 
 67%|██████▋   | 3846/5712 [9:03:58<4:34:18,  8.82s/it]08/04/2024 18:42:07 - INFO - __main__ -   Step: 3846, LR: 1.814216055837934e-07, Loss: 0.08909519761800766
2024-08-05T01:42:15.508284111Z 
 67%|██████▋   | 3847/5712 [9:04:06<4:28:26,  8.64s/it]08/04/2024 18:42:15 - INFO - __main__ -   Step: 3847, LR: 1.813243269534765e-07, Loss: 0.08776716887950897
2024-08-05T01:42:24.625064090Z 
 67%|██████▋   | 3848/5712 [9:04:15<4:32:46,  8.78s/it]08/04/2024 18:42:24 - INFO - __main__ -   Step: 3848, LR: 1.8122704832315961e-07, Loss: 0.08481504768133163
2024-08-05T01:42:33.661938076Z 
 67%|██████▋   | 3849/5712 [9:04:24<4:35:00,  8.86s/it]08/04/2024 18:42:33 - INFO - __main__ -   Step: 3849, LR: 1.811297696928427e-07, Loss: 0.0973505824804306
2024-08-05T01:42:42.332569535Z 
 67%|██████▋   | 3850/5712 [9:04:33<4:33:08,  8.80s/it]08/04/2024 18:42:42 - INFO - __main__ -   Step: 3850, LR: 1.8103249106252584e-07, Loss: 0.09939233213663101
2024-08-05T01:42:50.733573016Z 
 67%|██████▋   | 3851/5712 [9:04:41<4:29:15,  8.68s/it]08/04/2024 18:42:50 - INFO - __main__ -   Step: 3851, LR: 1.8093521243220894e-07, Loss: 0.09805931150913239
2024-08-05T01:42:58.815438436Z 
 67%|██████▋   | 3852/5712 [9:04:49<4:23:32,  8.50s/it]08/04/2024 18:42:58 - INFO - __main__ -   Step: 3852, LR: 1.8083793380189206e-07, Loss: 0.08021409809589386
2024-08-05T01:43:07.043546430Z 
 67%|██████▋   | 3853/5712 [9:04:58<4:20:51,  8.42s/it]08/04/2024 18:43:07 - INFO - __main__ -   Step: 3853, LR: 1.8074065517157516e-07, Loss: 0.11882321536540985
2024-08-05T01:43:15.948468532Z 
 67%|██████▋   | 3854/5712 [9:05:07<4:25:14,  8.57s/it]08/04/2024 18:43:15 - INFO - __main__ -   Step: 3854, LR: 1.8064337654125831e-07, Loss: 0.12078982591629028
2024-08-05T01:43:24.949053823Z 
 67%|██████▋   | 3855/5712 [9:05:16<4:29:07,  8.70s/it]08/04/2024 18:43:24 - INFO - __main__ -   Step: 3855, LR: 1.805460979109414e-07, Loss: 0.047236666083335876
2024-08-05T01:43:33.443439544Z 
 68%|██████▊   | 3856/5712 [9:05:24<4:27:07,  8.64s/it]08/04/2024 18:43:33 - INFO - __main__ -   Step: 3856, LR: 1.8044881928062454e-07, Loss: 0.05233636125922203
2024-08-05T01:43:41.975932556Z 
 68%|██████▊   | 3857/5712 [9:05:33<4:26:01,  8.60s/it]08/04/2024 18:43:41 - INFO - __main__ -   Step: 3857, LR: 1.8035154065030764e-07, Loss: 0.049140602350234985
2024-08-05T01:43:50.372615565Z 
 68%|██████▊   | 3858/5712 [9:05:41<4:23:57,  8.54s/it]08/04/2024 18:43:50 - INFO - __main__ -   Step: 3858, LR: 1.8025426201999074e-07, Loss: 0.07386474311351776
2024-08-05T01:43:59.115176234Z 
 68%|██████▊   | 3859/5712 [9:05:50<4:25:39,  8.60s/it]08/04/2024 18:43:59 - INFO - __main__ -   Step: 3859, LR: 1.8015698338967386e-07, Loss: 0.07268283516168594
2024-08-05T01:44:07.039517184Z 
 68%|██████▊   | 3860/5712 [9:05:58<4:19:14,  8.40s/it]08/04/2024 18:44:07 - INFO - __main__ -   Step: 3860, LR: 1.8005970475935696e-07, Loss: 0.10906495898962021
2024-08-05T01:44:15.229922524Z 
 68%|██████▊   | 3861/5712 [9:06:06<4:17:10,  8.34s/it]08/04/2024 18:44:15 - INFO - __main__ -   Step: 3861, LR: 1.7996242612904009e-07, Loss: 0.06974931806325912
2024-08-05T01:44:23.464705985Z 
 68%|██████▊   | 3862/5712 [9:06:14<4:16:05,  8.31s/it]08/04/2024 18:44:23 - INFO - __main__ -   Step: 3862, LR: 1.7986514749872319e-07, Loss: 0.0671880692243576
2024-08-05T01:44:31.758413996Z 
 68%|██████▊   | 3863/5712 [9:06:22<4:15:50,  8.30s/it]08/04/2024 18:44:31 - INFO - __main__ -   Step: 3863, LR: 1.7976786886840634e-07, Loss: 0.06920680403709412
2024-08-05T01:44:39.787274966Z 
 68%|██████▊   | 3864/5712 [9:06:30<4:13:11,  8.22s/it]08/04/2024 18:44:39 - INFO - __main__ -   Step: 3864, LR: 1.7967059023808944e-07, Loss: 0.08532552421092987
2024-08-05T01:44:48.593546847Z 
 68%|██████▊   | 3865/5712 [9:06:39<4:18:27,  8.40s/it]08/04/2024 18:44:48 - INFO - __main__ -   Step: 3865, LR: 1.7957331160777256e-07, Loss: 0.05505640059709549
2024-08-05T01:44:57.362691000Z 
 68%|██████▊   | 3866/5712 [9:06:48<4:21:45,  8.51s/it]08/04/2024 18:44:57 - INFO - __main__ -   Step: 3866, LR: 1.7947603297745566e-07, Loss: 0.07404720783233643
2024-08-05T01:45:05.400476709Z 
 68%|██████▊   | 3867/5712 [9:06:56<4:17:17,  8.37s/it]08/04/2024 18:45:05 - INFO - __main__ -   Step: 3867, LR: 1.793787543471388e-07, Loss: 0.09089536964893341
2024-08-05T01:45:13.759949635Z 
 68%|██████▊   | 3868/5712 [9:07:04<4:17:04,  8.36s/it]08/04/2024 18:45:13 - INFO - __main__ -   Step: 3868, LR: 1.7928147571682189e-07, Loss: 0.05233819782733917
2024-08-05T01:45:22.130985774Z 
 68%|██████▊   | 3869/5712 [9:07:13<4:16:59,  8.37s/it]08/04/2024 18:45:22 - INFO - __main__ -   Step: 3869, LR: 1.79184197086505e-07, Loss: 0.09037408232688904
2024-08-05T01:45:30.422368964Z 
 68%|██████▊   | 3870/5712 [9:07:21<4:16:09,  8.34s/it]08/04/2024 18:45:30 - INFO - __main__ -   Step: 3870, LR: 1.790869184561881e-07, Loss: 0.0741979256272316
2024-08-05T01:45:38.849219758Z 
 68%|██████▊   | 3871/5712 [9:07:29<4:16:47,  8.37s/it]08/04/2024 18:45:38 - INFO - __main__ -   Step: 3871, LR: 1.7898963982587124e-07, Loss: 0.18661627173423767
2024-08-05T01:45:47.528873222Z 
 68%|██████▊   | 3872/5712 [9:07:38<4:19:29,  8.46s/it]08/04/2024 18:45:47 - INFO - __main__ -   Step: 3872, LR: 1.7889236119555436e-07, Loss: 0.043523289263248444
2024-08-05T01:45:56.445798748Z 
 68%|██████▊   | 3873/5712 [9:07:47<4:23:32,  8.60s/it]08/04/2024 18:45:56 - INFO - __main__ -   Step: 3873, LR: 1.787950825652375e-07, Loss: 0.08113185316324234
2024-08-05T01:46:05.188468151Z 
 68%|██████▊   | 3874/5712 [9:07:56<4:24:43,  8.64s/it]08/04/2024 18:46:05 - INFO - __main__ -   Step: 3874, LR: 1.7869780393492059e-07, Loss: 0.13421159982681274
2024-08-05T01:46:13.682180846Z 
 68%|██████▊   | 3875/5712 [9:08:04<4:23:13,  8.60s/it]08/04/2024 18:46:13 - INFO - __main__ -   Step: 3875, LR: 1.786005253046037e-07, Loss: 0.07760602235794067
2024-08-05T01:46:21.665168377Z 
 68%|██████▊   | 3876/5712 [9:08:12<4:17:26,  8.41s/it]08/04/2024 18:46:21 - INFO - __main__ -   Step: 3876, LR: 1.785032466742868e-07, Loss: 0.13625401258468628
2024-08-05T01:46:29.804947918Z 
 68%|██████▊   | 3877/5712 [9:08:20<4:14:47,  8.33s/it]08/04/2024 18:46:29 - INFO - __main__ -   Step: 3877, LR: 1.7840596804396994e-07, Loss: 0.07555335760116577
2024-08-05T01:46:38.480376135Z 
 68%|██████▊   | 3878/5712 [9:08:29<4:17:48,  8.43s/it]08/04/2024 18:46:38 - INFO - __main__ -   Step: 3878, LR: 1.7830868941365304e-07, Loss: 0.09188789874315262
2024-08-05T01:46:46.783779653Z 
 68%|██████▊   | 3879/5712 [9:08:37<4:16:28,  8.40s/it]08/04/2024 18:46:46 - INFO - __main__ -   Step: 3879, LR: 1.7821141078333616e-07, Loss: 0.053442906588315964
2024-08-05T01:46:55.201260602Z 
 68%|██████▊   | 3880/5712 [9:08:46<4:16:32,  8.40s/it]08/04/2024 18:46:55 - INFO - __main__ -   Step: 3880, LR: 1.7811413215301926e-07, Loss: 0.10024692118167877
2024-08-05T01:47:04.287462730Z 
 68%|██████▊   | 3881/5712 [9:08:55<4:22:39,  8.61s/it]08/04/2024 18:47:04 - INFO - __main__ -   Step: 3881, LR: 1.780168535227024e-07, Loss: 0.07319406419992447
2024-08-05T01:47:13.825296843Z 
 68%|██████▊   | 3882/5712 [9:09:04<4:31:01,  8.89s/it]08/04/2024 18:47:13 - INFO - __main__ -   Step: 3882, LR: 1.779195748923855e-07, Loss: 0.05813884735107422
2024-08-05T01:47:23.074483398Z 
 68%|██████▊   | 3883/5712 [9:09:14<4:34:11,  8.99s/it]08/04/2024 18:47:23 - INFO - __main__ -   Step: 3883, LR: 1.7782229626206864e-07, Loss: 0.06956851482391357
2024-08-05T01:47:31.383590330Z 
 68%|██████▊   | 3884/5712 [9:09:22<4:27:47,  8.79s/it]08/04/2024 18:47:31 - INFO - __main__ -   Step: 3884, LR: 1.7772501763175174e-07, Loss: 0.07605960965156555
2024-08-05T01:47:39.846480009Z 
 68%|██████▊   | 3885/5712 [9:09:30<4:24:39,  8.69s/it]08/04/2024 18:47:39 - INFO - __main__ -   Step: 3885, LR: 1.7762773900143486e-07, Loss: 0.0673016607761383
2024-08-05T01:47:47.841113384Z 
 68%|██████▊   | 3886/5712 [9:09:38<4:18:08,  8.48s/it]08/04/2024 18:47:47 - INFO - __main__ -   Step: 3886, LR: 1.7753046037111796e-07, Loss: 0.08317375183105469
2024-08-05T01:47:56.286464151Z 
 68%|██████▊   | 3887/5712 [9:09:47<4:17:40,  8.47s/it]08/04/2024 18:47:56 - INFO - __main__ -   Step: 3887, LR: 1.7743318174080109e-07, Loss: 0.10008707642555237
2024-08-05T01:48:04.674114925Z 
 68%|██████▊   | 3888/5712 [9:09:55<4:16:45,  8.45s/it]08/04/2024 18:48:04 - INFO - __main__ -   Step: 3888, LR: 1.7733590311048418e-07, Loss: 0.06561291962862015
2024-08-05T01:48:13.737579513Z 
 68%|██████▊   | 3889/5712 [9:10:04<4:22:13,  8.63s/it]08/04/2024 18:48:13 - INFO - __main__ -   Step: 3889, LR: 1.772386244801673e-07, Loss: 0.05598188191652298
2024-08-05T01:48:22.404668069Z 
 68%|██████▊   | 3890/5712 [9:10:13<4:22:26,  8.64s/it]08/04/2024 18:48:22 - INFO - __main__ -   Step: 3890, LR: 1.7714134584985044e-07, Loss: 0.0887964516878128
2024-08-05T01:48:31.374159340Z 
 68%|██████▊   | 3891/5712 [9:10:22<4:25:16,  8.74s/it]08/04/2024 18:48:31 - INFO - __main__ -   Step: 3891, LR: 1.7704406721953356e-07, Loss: 0.09758372604846954
2024-08-05T01:48:39.523214095Z 
 68%|██████▊   | 3892/5712 [9:10:30<4:19:44,  8.56s/it]08/04/2024 18:48:39 - INFO - __main__ -   Step: 3892, LR: 1.7694678858921666e-07, Loss: 0.11613842844963074
2024-08-05T01:48:47.918672388Z 
 68%|██████▊   | 3893/5712 [9:10:39<4:18:04,  8.51s/it]08/04/2024 18:48:47 - INFO - __main__ -   Step: 3893, LR: 1.7684950995889979e-07, Loss: 0.0720483586192131
2024-08-05T01:48:55.884089286Z 
 68%|██████▊   | 3894/5712 [9:10:47<4:12:57,  8.35s/it]08/04/2024 18:48:55 - INFO - __main__ -   Step: 3894, LR: 1.7675223132858288e-07, Loss: 0.15068021416664124
2024-08-05T01:49:04.631452131Z 
 68%|██████▊   | 3895/5712 [9:10:55<4:16:26,  8.47s/it]08/04/2024 18:49:04 - INFO - __main__ -   Step: 3895, LR: 1.7665495269826598e-07, Loss: 0.0855763852596283
2024-08-05T01:49:12.876977604Z 
 68%|██████▊   | 3896/5712 [9:11:04<4:14:16,  8.40s/it]08/04/2024 18:49:12 - INFO - __main__ -   Step: 3896, LR: 1.765576740679491e-07, Loss: 0.05514111369848251
2024-08-05T01:49:21.800389664Z 
 68%|██████▊   | 3897/5712 [9:11:12<4:18:52,  8.56s/it]08/04/2024 18:49:21 - INFO - __main__ -   Step: 3897, LR: 1.764603954376322e-07, Loss: 0.08143459260463715
2024-08-05T01:49:30.061874760Z 
 68%|██████▊   | 3898/5712 [9:11:21<4:16:02,  8.47s/it]08/04/2024 18:49:30 - INFO - __main__ -   Step: 3898, LR: 1.7636311680731533e-07, Loss: 0.06575001776218414
2024-08-05T01:49:39.152383972Z 
 68%|██████▊   | 3899/5712 [9:11:30<4:21:32,  8.66s/it]08/04/2024 18:49:39 - INFO - __main__ -   Step: 3899, LR: 1.7626583817699846e-07, Loss: 0.12211932241916656
2024-08-05T01:49:47.949376224Z 
 68%|██████▊   | 3900/5712 [9:11:39<4:22:40,  8.70s/it]08/04/2024 18:49:47 - INFO - __main__ -   Step: 3900, LR: 1.7616855954668158e-07, Loss: 0.04069826006889343
2024-08-05T01:49:56.161710094Z 
 68%|██████▊   | 3901/5712 [9:11:47<4:18:08,  8.55s/it]08/04/2024 18:49:56 - INFO - __main__ -   Step: 3901, LR: 1.7607128091636468e-07, Loss: 0.09039261192083359
2024-08-05T01:50:04.542082730Z 
 68%|██████▊   | 3902/5712 [9:11:55<4:16:26,  8.50s/it]08/04/2024 18:50:04 - INFO - __main__ -   Step: 3902, LR: 1.759740022860478e-07, Loss: 0.12773026525974274
2024-08-05T01:50:13.142820492Z 
 68%|██████▊   | 3903/5712 [9:12:04<4:17:12,  8.53s/it]08/04/2024 18:50:13 - INFO - __main__ -   Step: 3903, LR: 1.758767236557309e-07, Loss: 0.12207245826721191
2024-08-05T01:50:21.082082865Z 
 68%|██████▊   | 3904/5712 [9:12:12<4:11:42,  8.35s/it]08/04/2024 18:50:21 - INFO - __main__ -   Step: 3904, LR: 1.7577944502541403e-07, Loss: 0.0341479554772377
2024-08-05T01:50:30.153208847Z 
 68%|██████▊   | 3905/5712 [9:12:21<4:18:03,  8.57s/it]08/04/2024 18:50:30 - INFO - __main__ -   Step: 3905, LR: 1.7568216639509713e-07, Loss: 0.10671313107013702
2024-08-05T01:50:39.214686389Z 
 68%|██████▊   | 3906/5712 [9:12:30<4:22:21,  8.72s/it]08/04/2024 18:50:39 - INFO - __main__ -   Step: 3906, LR: 1.7558488776478026e-07, Loss: 0.0731343924999237
2024-08-05T01:50:48.126934919Z 
 68%|██████▊   | 3907/5712 [9:12:39<4:23:59,  8.78s/it]08/04/2024 18:50:48 - INFO - __main__ -   Step: 3907, LR: 1.7548760913446336e-07, Loss: 0.09202492237091064
2024-08-05T01:50:56.585121642Z 
 68%|██████▊   | 3908/5712 [9:12:47<4:20:59,  8.68s/it]08/04/2024 18:50:56 - INFO - __main__ -   Step: 3908, LR: 1.753903305041465e-07, Loss: 0.07342883944511414
2024-08-05T01:51:05.059359521Z 
 68%|██████▊   | 3909/5712 [9:12:56<4:18:59,  8.62s/it]08/04/2024 18:51:05 - INFO - __main__ -   Step: 3909, LR: 1.752930518738296e-07, Loss: 0.06099103391170502
2024-08-05T01:51:13.132354853Z 
 68%|██████▊   | 3910/5712 [9:13:04<4:13:55,  8.45s/it]08/04/2024 18:51:13 - INFO - __main__ -   Step: 3910, LR: 1.7519577324351273e-07, Loss: 0.06956283748149872
2024-08-05T01:51:21.634098725Z 
 68%|██████▊   | 3911/5712 [9:13:12<4:14:12,  8.47s/it]08/04/2024 18:51:21 - INFO - __main__ -   Step: 3911, LR: 1.7509849461319583e-07, Loss: 0.0624970942735672
2024-08-05T01:51:30.078479658Z 
 68%|██████▊   | 3912/5712 [9:13:21<4:13:50,  8.46s/it]08/04/2024 18:51:30 - INFO - __main__ -   Step: 3912, LR: 1.7500121598287896e-07, Loss: 0.03744690492749214
2024-08-05T01:51:38.107227835Z 
 69%|██████▊   | 3913/5712 [9:13:29<4:09:48,  8.33s/it]08/04/2024 18:51:38 - INFO - __main__ -   Step: 3913, LR: 1.7490393735256206e-07, Loss: 0.1058441549539566
2024-08-05T01:51:46.826550277Z 
 69%|██████▊   | 3914/5712 [9:13:37<4:13:09,  8.45s/it]08/04/2024 18:51:46 - INFO - __main__ -   Step: 3914, LR: 1.7480665872224518e-07, Loss: 0.14411664009094238
2024-08-05T01:51:55.136170981Z 
 69%|██████▊   | 3915/5712 [9:13:46<4:11:46,  8.41s/it]08/04/2024 18:51:55 - INFO - __main__ -   Step: 3915, LR: 1.7470938009192828e-07, Loss: 0.1501992642879486
2024-08-05T01:52:03.881745874Z 
 69%|██████▊   | 3916/5712 [9:13:55<4:14:40,  8.51s/it]08/04/2024 18:52:03 - INFO - __main__ -   Step: 3916, LR: 1.746121014616114e-07, Loss: 0.051041487604379654
2024-08-05T01:52:12.541798508Z 
 69%|██████▊   | 3917/5712 [9:14:03<4:15:53,  8.55s/it]08/04/2024 18:52:12 - INFO - __main__ -   Step: 3917, LR: 1.7451482283129453e-07, Loss: 0.1380147486925125
2024-08-05T01:52:20.129751759Z 
 69%|██████▊   | 3918/5712 [9:14:11<4:07:05,  8.26s/it]08/04/2024 18:52:20 - INFO - __main__ -   Step: 3918, LR: 1.7441754420097766e-07, Loss: 0.03729140758514404
2024-08-05T01:52:29.128431947Z 
 69%|██████▊   | 3919/5712 [9:14:20<4:13:32,  8.48s/it]08/04/2024 18:52:29 - INFO - __main__ -   Step: 3919, LR: 1.7432026557066076e-07, Loss: 0.05434495955705643
2024-08-05T01:52:37.921715915Z 
 69%|██████▊   | 3920/5712 [9:14:29<4:16:10,  8.58s/it]08/04/2024 18:52:37 - INFO - __main__ -   Step: 3920, LR: 1.7422298694034388e-07, Loss: 0.07174630463123322
2024-08-05T01:52:45.570303448Z 
 69%|██████▊   | 3921/5712 [9:14:36<4:07:42,  8.30s/it]08/04/2024 18:52:45 - INFO - __main__ -   Step: 3921, LR: 1.7412570831002698e-07, Loss: 0.09433091431856155
2024-08-05T01:52:54.335363660Z 
 69%|██████▊   | 3922/5712 [9:14:45<4:11:44,  8.44s/it]08/04/2024 18:52:54 - INFO - __main__ -   Step: 3922, LR: 1.740284296797101e-07, Loss: 0.07859793305397034
2024-08-05T01:53:03.774575423Z 
 69%|██████▊   | 3923/5712 [9:14:54<4:20:32,  8.74s/it]08/04/2024 18:53:03 - INFO - __main__ -   Step: 3923, LR: 1.739311510493932e-07, Loss: 0.09466813504695892
2024-08-05T01:53:12.256331524Z 
 69%|██████▊   | 3924/5712 [9:15:03<4:18:07,  8.66s/it]08/04/2024 18:53:12 - INFO - __main__ -   Step: 3924, LR: 1.7383387241907633e-07, Loss: 0.09510833770036697
2024-08-05T01:53:20.761297098Z 
 69%|██████▊   | 3925/5712 [9:15:11<4:16:34,  8.61s/it]08/04/2024 18:53:20 - INFO - __main__ -   Step: 3925, LR: 1.7373659378875943e-07, Loss: 0.14243483543395996
2024-08-05T01:53:28.804652288Z 
 69%|██████▊   | 3926/5712 [9:15:19<4:11:19,  8.44s/it]08/04/2024 18:53:28 - INFO - __main__ -   Step: 3926, LR: 1.7363931515844258e-07, Loss: 0.07811857759952545
2024-08-05T01:53:37.076851839Z 
 69%|██████▉   | 3927/5712 [9:15:28<4:09:39,  8.39s/it]08/04/2024 18:53:37 - INFO - __main__ -   Step: 3927, LR: 1.7354203652812568e-07, Loss: 0.0720917358994484
2024-08-05T01:53:45.104861795Z 
 69%|██████▉   | 3928/5712 [9:15:36<4:06:16,  8.28s/it]08/04/2024 18:53:45 - INFO - __main__ -   Step: 3928, LR: 1.734447578978088e-07, Loss: 0.07841809093952179
2024-08-05T01:53:53.164094407Z 
 69%|██████▉   | 3929/5712 [9:15:44<4:04:08,  8.22s/it]08/04/2024 18:53:53 - INFO - __main__ -   Step: 3929, LR: 1.733474792674919e-07, Loss: 0.04752148687839508
2024-08-05T01:54:02.031838128Z 
 69%|██████▉   | 3930/5712 [9:15:53<4:09:48,  8.41s/it]08/04/2024 18:54:02 - INFO - __main__ -   Step: 3930, LR: 1.7325020063717503e-07, Loss: 0.058017611503601074
2024-08-05T01:54:10.747042050Z 
 69%|██████▉   | 3931/5712 [9:16:01<4:12:22,  8.50s/it]08/04/2024 18:54:10 - INFO - __main__ -   Step: 3931, LR: 1.7315292200685813e-07, Loss: 0.0948675125837326
2024-08-05T01:54:19.459952627Z 
 69%|██████▉   | 3932/5712 [9:16:10<4:14:06,  8.57s/it]08/04/2024 18:54:19 - INFO - __main__ -   Step: 3932, LR: 1.7305564337654123e-07, Loss: 0.04962373524904251
2024-08-05T01:54:28.345795825Z 
 69%|██████▉   | 3933/5712 [9:16:19<4:16:49,  8.66s/it]08/04/2024 18:54:28 - INFO - __main__ -   Step: 3933, LR: 1.7295836474622436e-07, Loss: 0.043287284672260284
2024-08-05T01:54:36.843125831Z 
 69%|██████▉   | 3934/5712 [9:16:27<4:15:12,  8.61s/it]08/04/2024 18:54:36 - INFO - __main__ -   Step: 3934, LR: 1.7286108611590746e-07, Loss: 0.08066815882921219
2024-08-05T01:54:44.953634007Z 
 69%|██████▉   | 3935/5712 [9:16:36<4:10:36,  8.46s/it]08/04/2024 18:54:44 - INFO - __main__ -   Step: 3935, LR: 1.727638074855906e-07, Loss: 0.13022564351558685
2024-08-05T01:54:53.249498859Z 
 69%|██████▉   | 3936/5712 [9:16:44<4:08:59,  8.41s/it]08/04/2024 18:54:53 - INFO - __main__ -   Step: 3936, LR: 1.726665288552737e-07, Loss: 0.08612425625324249
2024-08-05T01:55:01.153196614Z 
 69%|██████▉   | 3937/5712 [9:16:52<4:04:20,  8.26s/it]08/04/2024 18:55:01 - INFO - __main__ -   Step: 3937, LR: 1.7256925022495683e-07, Loss: 0.1349572092294693
2024-08-05T01:55:09.627517338Z 
 69%|██████▉   | 3938/5712 [9:17:00<4:06:06,  8.32s/it]08/04/2024 18:55:09 - INFO - __main__ -   Step: 3938, LR: 1.7247197159463993e-07, Loss: 0.07607074081897736
2024-08-05T01:55:18.073130560Z 
 69%|██████▉   | 3939/5712 [9:17:09<4:07:03,  8.36s/it]08/04/2024 18:55:18 - INFO - __main__ -   Step: 3939, LR: 1.7237469296432306e-07, Loss: 0.08266405761241913
2024-08-05T01:55:27.607197184Z 
 69%|██████▉   | 3940/5712 [9:17:18<4:17:17,  8.71s/it]08/04/2024 18:55:27 - INFO - __main__ -   Step: 3940, LR: 1.7227741433400616e-07, Loss: 0.06479880958795547
2024-08-05T01:55:36.361137365Z 
 69%|██████▉   | 3941/5712 [9:17:27<4:17:32,  8.73s/it]08/04/2024 18:55:36 - INFO - __main__ -   Step: 3941, LR: 1.7218013570368928e-07, Loss: 0.09702776372432709
2024-08-05T01:55:44.527281214Z 
 69%|██████▉   | 3942/5712 [9:17:35<4:12:26,  8.56s/it]08/04/2024 18:55:44 - INFO - __main__ -   Step: 3942, LR: 1.7208285707337238e-07, Loss: 0.06521029025316238
2024-08-05T01:55:52.528327544Z 
 69%|██████▉   | 3943/5712 [9:17:43<4:07:22,  8.39s/it]08/04/2024 18:55:52 - INFO - __main__ -   Step: 3943, LR: 1.719855784430555e-07, Loss: 0.09325466305017471
2024-08-05T01:56:01.116623199Z 
 69%|██████▉   | 3944/5712 [9:17:52<4:08:59,  8.45s/it]08/04/2024 18:56:01 - INFO - __main__ -   Step: 3944, LR: 1.7188829981273863e-07, Loss: 0.06867508590221405
2024-08-05T01:56:09.303855169Z 
 69%|██████▉   | 3945/5712 [9:18:00<4:06:31,  8.37s/it]08/04/2024 18:56:09 - INFO - __main__ -   Step: 3945, LR: 1.7179102118242176e-07, Loss: 0.09894062578678131
2024-08-05T01:56:17.696095128Z 
 69%|██████▉   | 3946/5712 [9:18:08<4:06:34,  8.38s/it]08/04/2024 18:56:17 - INFO - __main__ -   Step: 3946, LR: 1.7169374255210486e-07, Loss: 0.0758851170539856
2024-08-05T01:56:26.448351418Z 
 69%|██████▉   | 3947/5712 [9:18:17<4:09:44,  8.49s/it]08/04/2024 18:56:26 - INFO - __main__ -   Step: 3947, LR: 1.7159646392178798e-07, Loss: 0.0569503977894783
2024-08-05T01:56:34.826951426Z 
 69%|██████▉   | 3948/5712 [9:18:25<4:08:37,  8.46s/it]08/04/2024 18:56:34 - INFO - __main__ -   Step: 3948, LR: 1.7149918529147108e-07, Loss: 0.08006414771080017
2024-08-05T01:56:43.782021248Z 
 69%|██████▉   | 3949/5712 [9:18:34<4:12:52,  8.61s/it]08/04/2024 18:56:43 - INFO - __main__ -   Step: 3949, LR: 1.714019066611542e-07, Loss: 0.06872709095478058
2024-08-05T01:56:52.144984192Z 
 69%|██████▉   | 3950/5712 [9:18:43<4:10:35,  8.53s/it]08/04/2024 18:56:52 - INFO - __main__ -   Step: 3950, LR: 1.713046280308373e-07, Loss: 0.0734110027551651
2024-08-05T01:57:00.281374322Z 
 69%|██████▉   | 3951/5712 [9:18:51<4:06:56,  8.41s/it]08/04/2024 18:57:00 - INFO - __main__ -   Step: 3951, LR: 1.7120734940052043e-07, Loss: 0.03626541793346405
2024-08-05T01:57:08.327906584Z 
 69%|██████▉   | 3952/5712 [9:18:59<4:03:35,  8.30s/it]08/04/2024 18:57:08 - INFO - __main__ -   Step: 3952, LR: 1.7111007077020353e-07, Loss: 0.060497552156448364
2024-08-05T01:57:16.813674575Z 
 69%|██████▉   | 3953/5712 [9:19:07<4:05:02,  8.36s/it]08/04/2024 18:57:16 - INFO - __main__ -   Step: 3953, LR: 1.7101279213988668e-07, Loss: 0.10082238912582397
2024-08-05T01:57:25.260033065Z 
 69%|██████▉   | 3954/5712 [9:19:16<4:05:40,  8.38s/it]08/04/2024 18:57:25 - INFO - __main__ -   Step: 3954, LR: 1.7091551350956978e-07, Loss: 0.07527026534080505
2024-08-05T01:57:34.066191516Z 
 69%|██████▉   | 3955/5712 [9:19:25<4:09:14,  8.51s/it]08/04/2024 18:57:34 - INFO - __main__ -   Step: 3955, LR: 1.708182348792529e-07, Loss: 0.05248178169131279
2024-08-05T01:57:42.704180251Z 
 69%|██████▉   | 3956/5712 [9:19:33<4:10:12,  8.55s/it]08/04/2024 18:57:42 - INFO - __main__ -   Step: 3956, LR: 1.70720956248936e-07, Loss: 0.07322567701339722
2024-08-05T01:57:52.048113876Z 
 69%|██████▉   | 3957/5712 [9:19:43<4:17:01,  8.79s/it]08/04/2024 18:57:52 - INFO - __main__ -   Step: 3957, LR: 1.7062367761861913e-07, Loss: 0.13756051659584045
2024-08-05T01:58:00.496863720Z 
 69%|██████▉   | 3958/5712 [9:19:51<4:13:55,  8.69s/it]08/04/2024 18:58:00 - INFO - __main__ -   Step: 3958, LR: 1.7052639898830223e-07, Loss: 0.10028903186321259
2024-08-05T01:58:08.515361539Z 
 69%|██████▉   | 3959/5712 [9:19:59<4:07:55,  8.49s/it]08/04/2024 18:58:08 - INFO - __main__ -   Step: 3959, LR: 1.7042912035798535e-07, Loss: 0.06501347571611404
2024-08-05T01:58:17.184754919Z 
 69%|██████▉   | 3960/5712 [9:20:08<4:09:23,  8.54s/it]08/04/2024 18:58:17 - INFO - __main__ -   Step: 3960, LR: 1.7033184172766845e-07, Loss: 0.12634357810020447
2024-08-05T01:58:25.882200261Z 
 69%|██████▉   | 3961/5712 [9:20:17<4:10:37,  8.59s/it]08/04/2024 18:58:25 - INFO - __main__ -   Step: 3961, LR: 1.7023456309735158e-07, Loss: 0.06559713929891586
2024-08-05T01:58:33.906020125Z 
 69%|██████▉   | 3962/5712 [9:20:25<4:05:32,  8.42s/it]08/04/2024 18:58:33 - INFO - __main__ -   Step: 3962, LR: 1.701372844670347e-07, Loss: 0.03763282299041748
2024-08-05T01:58:42.799337183Z 
 69%|██████▉   | 3963/5712 [9:20:33<4:09:33,  8.56s/it]08/04/2024 18:58:42 - INFO - __main__ -   Step: 3963, LR: 1.7004000583671783e-07, Loss: 0.10765595734119415
2024-08-05T01:58:51.041090099Z 
 69%|██████▉   | 3964/5712 [9:20:42<4:06:37,  8.47s/it]08/04/2024 18:58:51 - INFO - __main__ -   Step: 3964, LR: 1.6994272720640093e-07, Loss: 0.1058889627456665
2024-08-05T01:58:59.400408577Z 
 69%|██████▉   | 3965/5712 [9:20:50<4:05:33,  8.43s/it]08/04/2024 18:58:59 - INFO - __main__ -   Step: 3965, LR: 1.6984544857608406e-07, Loss: 0.06292274594306946
2024-08-05T01:59:07.687180617Z 
 69%|██████▉   | 3966/5712 [9:20:58<4:04:08,  8.39s/it]08/04/2024 18:59:07 - INFO - __main__ -   Step: 3966, LR: 1.6974816994576715e-07, Loss: 0.09666933119297028
2024-08-05T01:59:15.850366307Z 
 69%|██████▉   | 3967/5712 [9:21:06<4:02:01,  8.32s/it]08/04/2024 18:59:15 - INFO - __main__ -   Step: 3967, LR: 1.6965089131545028e-07, Loss: 0.08605518192052841
2024-08-05T01:59:23.910576427Z 
 69%|██████▉   | 3968/5712 [9:21:15<3:59:36,  8.24s/it]08/04/2024 18:59:23 - INFO - __main__ -   Step: 3968, LR: 1.6955361268513338e-07, Loss: 0.060542717576026917
2024-08-05T01:59:32.074664511Z 
 69%|██████▉   | 3969/5712 [9:21:23<3:58:46,  8.22s/it]08/04/2024 18:59:32 - INFO - __main__ -   Step: 3969, LR: 1.694563340548165e-07, Loss: 0.06514321267604828
2024-08-05T01:59:40.364577668Z 
 70%|██████▉   | 3970/5712 [9:21:31<3:59:15,  8.24s/it]08/04/2024 18:59:40 - INFO - __main__ -   Step: 3970, LR: 1.693590554244996e-07, Loss: 0.05039452388882637
2024-08-05T01:59:48.868692491Z 
 70%|██████▉   | 3971/5712 [9:21:40<4:01:24,  8.32s/it]08/04/2024 18:59:48 - INFO - __main__ -   Step: 3971, LR: 1.6926177679418276e-07, Loss: 0.11772744357585907
2024-08-05T01:59:57.541859681Z 
 70%|██████▉   | 3972/5712 [9:21:48<4:04:20,  8.43s/it]08/04/2024 18:59:57 - INFO - __main__ -   Step: 3972, LR: 1.6916449816386585e-07, Loss: 0.07422366738319397
2024-08-05T02:00:06.419416674Z 
 70%|██████▉   | 3973/5712 [9:21:57<4:08:08,  8.56s/it]08/04/2024 19:00:06 - INFO - __main__ -   Step: 3973, LR: 1.6906721953354895e-07, Loss: 0.07461463660001755
2024-08-05T02:00:15.431510412Z 
 70%|██████▉   | 3974/5712 [9:22:06<4:11:53,  8.70s/it]08/04/2024 19:00:15 - INFO - __main__ -   Step: 3974, LR: 1.6896994090323208e-07, Loss: 0.05313718318939209
2024-08-05T02:00:24.290769818Z 
 70%|██████▉   | 3975/5712 [9:22:15<4:13:10,  8.75s/it]08/04/2024 19:00:24 - INFO - __main__ -   Step: 3975, LR: 1.6887266227291518e-07, Loss: 0.02300719916820526
2024-08-05T02:00:32.359878574Z 
 70%|██████▉   | 3976/5712 [9:22:23<4:07:09,  8.54s/it]08/04/2024 19:00:32 - INFO - __main__ -   Step: 3976, LR: 1.687753836425983e-07, Loss: 0.031742215156555176
2024-08-05T02:00:40.581824740Z 
 70%|██████▉   | 3977/5712 [9:22:31<4:04:14,  8.45s/it]08/04/2024 19:00:40 - INFO - __main__ -   Step: 3977, LR: 1.686781050122814e-07, Loss: 0.05814969912171364
2024-08-05T02:00:48.833981992Z 
 70%|██████▉   | 3978/5712 [9:22:39<4:02:25,  8.39s/it]08/04/2024 19:00:48 - INFO - __main__ -   Step: 3978, LR: 1.6858082638196453e-07, Loss: 0.09254541248083115
2024-08-05T02:00:57.540699543Z 
 70%|██████▉   | 3979/5712 [9:22:48<4:05:02,  8.48s/it]08/04/2024 19:00:57 - INFO - __main__ -   Step: 3979, LR: 1.6848354775164763e-07, Loss: 0.08249558508396149
2024-08-05T02:01:05.798977699Z 
 70%|██████▉   | 3980/5712 [9:22:56<4:02:56,  8.42s/it]08/04/2024 19:01:05 - INFO - __main__ -   Step: 3980, LR: 1.6838626912133078e-07, Loss: 0.09118226170539856
2024-08-05T02:01:14.107524581Z 
 70%|██████▉   | 3981/5712 [9:23:05<4:01:52,  8.38s/it]08/04/2024 19:01:14 - INFO - __main__ -   Step: 3981, LR: 1.6828899049101388e-07, Loss: 0.0505925752222538
2024-08-05T02:01:22.754672540Z 
 70%|██████▉   | 3982/5712 [9:23:13<4:04:00,  8.46s/it]08/04/2024 19:01:22 - INFO - __main__ -   Step: 3982, LR: 1.68191711860697e-07, Loss: 0.1509019136428833
2024-08-05T02:01:30.859450828Z 
 70%|██████▉   | 3983/5712 [9:23:22<4:00:46,  8.36s/it]08/04/2024 19:01:30 - INFO - __main__ -   Step: 3983, LR: 1.680944332303801e-07, Loss: 0.040926482528448105
2024-08-05T02:01:39.169306586Z 
 70%|██████▉   | 3984/5712 [9:23:30<4:00:14,  8.34s/it]08/04/2024 19:01:39 - INFO - __main__ -   Step: 3984, LR: 1.6799715460006323e-07, Loss: 0.11055338382720947
2024-08-05T02:01:47.324683504Z 
 70%|██████▉   | 3985/5712 [9:23:38<3:58:29,  8.29s/it]08/04/2024 19:01:47 - INFO - __main__ -   Step: 3985, LR: 1.6789987596974633e-07, Loss: 0.138142392039299
2024-08-05T02:01:55.423193692Z 
 70%|██████▉   | 3986/5712 [9:23:46<3:56:44,  8.23s/it]08/04/2024 19:01:55 - INFO - __main__ -   Step: 3986, LR: 1.6780259733942945e-07, Loss: 0.10511688888072968
2024-08-05T02:02:03.554501420Z 
 70%|██████▉   | 3987/5712 [9:23:54<3:55:45,  8.20s/it]08/04/2024 19:02:03 - INFO - __main__ -   Step: 3987, LR: 1.6770531870911255e-07, Loss: 0.047942373901605606
2024-08-05T02:02:12.221043947Z 
 70%|██████▉   | 3988/5712 [9:24:03<3:59:38,  8.34s/it]08/04/2024 19:02:12 - INFO - __main__ -   Step: 3988, LR: 1.6760804007879568e-07, Loss: 0.07112963497638702
2024-08-05T02:02:21.518299162Z 
 70%|██████▉   | 3989/5712 [9:24:12<4:07:44,  8.63s/it]08/04/2024 19:02:21 - INFO - __main__ -   Step: 3989, LR: 1.675107614484788e-07, Loss: 0.15465913712978363
2024-08-05T02:02:30.758532381Z 
 70%|██████▉   | 3990/5712 [9:24:21<4:12:52,  8.81s/it]08/04/2024 19:02:30 - INFO - __main__ -   Step: 3990, LR: 1.6741348281816193e-07, Loss: 0.08648623526096344
2024-08-05T02:02:39.059519575Z 
 70%|██████▉   | 3991/5712 [9:24:30<4:08:20,  8.66s/it]08/04/2024 19:02:39 - INFO - __main__ -   Step: 3991, LR: 1.6731620418784503e-07, Loss: 0.0888424962759018
2024-08-05T02:02:47.492451767Z 
 70%|██████▉   | 3992/5712 [9:24:38<4:06:15,  8.59s/it]08/04/2024 19:02:47 - INFO - __main__ -   Step: 3992, LR: 1.6721892555752815e-07, Loss: 0.0492229126393795
2024-08-05T02:02:56.013096835Z 
 70%|██████▉   | 3993/5712 [9:24:47<4:05:30,  8.57s/it]08/04/2024 19:02:56 - INFO - __main__ -   Step: 3993, LR: 1.6712164692721125e-07, Loss: 0.0663967877626419
2024-08-05T02:03:04.187666015Z 
 70%|██████▉   | 3994/5712 [9:24:55<4:01:58,  8.45s/it]08/04/2024 19:03:04 - INFO - __main__ -   Step: 3994, LR: 1.6702436829689438e-07, Loss: 0.043543942272663116
2024-08-05T02:03:12.247426570Z 
 70%|██████▉   | 3995/5712 [9:25:03<3:58:28,  8.33s/it]08/04/2024 19:03:12 - INFO - __main__ -   Step: 3995, LR: 1.6692708966657748e-07, Loss: 0.1265678107738495
2024-08-05T02:03:20.622469869Z 
 70%|██████▉   | 3996/5712 [9:25:11<3:58:41,  8.35s/it]08/04/2024 19:03:20 - INFO - __main__ -   Step: 3996, LR: 1.668298110362606e-07, Loss: 0.0448690764605999
2024-08-05T02:03:29.433597353Z 
 70%|██████▉   | 3997/5712 [9:25:20<4:02:32,  8.49s/it]08/04/2024 19:03:29 - INFO - __main__ -   Step: 3997, LR: 1.667325324059437e-07, Loss: 0.0913611501455307
2024-08-05T02:03:38.016272818Z 
 70%|██████▉   | 3998/5712 [9:25:29<4:03:14,  8.51s/it]08/04/2024 19:03:38 - INFO - __main__ -   Step: 3998, LR: 1.6663525377562685e-07, Loss: 0.16165751218795776
2024-08-05T02:03:46.565719310Z 
 70%|███████   | 3999/5712 [9:25:37<4:03:23,  8.53s/it]08/04/2024 19:03:46 - INFO - __main__ -   Step: 3999, LR: 1.6653797514530995e-07, Loss: 0.07072746753692627
2024-08-05T02:03:54.740480283Z 
 70%|███████   | 4000/5712 [9:25:45<4:00:15,  8.42s/it]08/04/2024 19:03:54 - INFO - __main__ -   Step: 4000, LR: 1.6644069651499308e-07, Loss: 0.07567781955003738
2024-08-05T02:04:03.428994279Z 
 70%|███████   | 4001/5712 [9:25:54<4:02:24,  8.50s/it]08/04/2024 19:04:03 - INFO - __main__ -   Step: 4001, LR: 1.6634341788467618e-07, Loss: 0.060020796954631805
2024-08-05T02:04:11.706387346Z 
 70%|███████   | 4002/5712 [9:26:02<4:00:21,  8.43s/it]08/04/2024 19:04:11 - INFO - __main__ -   Step: 4002, LR: 1.662461392543593e-07, Loss: 0.10609874129295349
2024-08-05T02:04:19.660807949Z 
 70%|███████   | 4003/5712 [9:26:10<3:56:07,  8.29s/it]08/04/2024 19:04:19 - INFO - __main__ -   Step: 4003, LR: 1.661488606240424e-07, Loss: 0.07892768085002899
2024-08-05T02:04:27.961676315Z 
 70%|███████   | 4004/5712 [9:26:19<3:56:04,  8.29s/it]08/04/2024 19:04:27 - INFO - __main__ -   Step: 4004, LR: 1.6605158199372553e-07, Loss: 0.05643842741847038
2024-08-05T02:04:36.510782475Z 
 70%|███████   | 4005/5712 [9:26:27<3:58:07,  8.37s/it]08/04/2024 19:04:36 - INFO - __main__ -   Step: 4005, LR: 1.6595430336340863e-07, Loss: 0.09244237840175629
2024-08-05T02:04:44.917441191Z 
 70%|███████   | 4006/5712 [9:26:36<3:58:17,  8.38s/it]08/04/2024 19:04:44 - INFO - __main__ -   Step: 4006, LR: 1.6585702473309175e-07, Loss: 0.061020832508802414
2024-08-05T02:04:54.520487457Z 
 70%|███████   | 4007/5712 [9:26:45<4:08:34,  8.75s/it]08/04/2024 19:04:54 - INFO - __main__ -   Step: 4007, LR: 1.6575974610277488e-07, Loss: 0.06188631057739258
2024-08-05T02:05:03.003720993Z 
 70%|███████   | 4008/5712 [9:26:54<4:06:10,  8.67s/it]08/04/2024 19:05:03 - INFO - __main__ -   Step: 4008, LR: 1.65662467472458e-07, Loss: 0.09146635234355927
2024-08-05T02:05:10.547712216Z 
 70%|███████   | 4009/5712 [9:27:01<3:56:27,  8.33s/it]08/04/2024 19:05:10 - INFO - __main__ -   Step: 4009, LR: 1.655651888421411e-07, Loss: 0.07096854597330093
2024-08-05T02:05:19.311511098Z 
 70%|███████   | 4010/5712 [9:27:10<4:00:00,  8.46s/it]08/04/2024 19:05:19 - INFO - __main__ -   Step: 4010, LR: 1.654679102118242e-07, Loss: 0.09930990636348724
2024-08-05T02:05:27.556724980Z 
 70%|███████   | 4011/5712 [9:27:18<3:58:01,  8.40s/it]08/04/2024 19:05:27 - INFO - __main__ -   Step: 4011, LR: 1.6537063158150733e-07, Loss: 0.049836575984954834
2024-08-05T02:05:35.541524168Z 
 70%|███████   | 4012/5712 [9:27:26<3:54:23,  8.27s/it]08/04/2024 19:05:35 - INFO - __main__ -   Step: 4012, LR: 1.6527335295119042e-07, Loss: 0.0559576079249382
2024-08-05T02:05:44.215192534Z 
 70%|███████   | 4013/5712 [9:27:35<3:57:39,  8.39s/it]08/04/2024 19:05:44 - INFO - __main__ -   Step: 4013, LR: 1.6517607432087355e-07, Loss: 0.11858353018760681
2024-08-05T02:05:52.527443044Z 
 70%|███████   | 4014/5712 [9:27:43<3:56:50,  8.37s/it]08/04/2024 19:05:52 - INFO - __main__ -   Step: 4014, LR: 1.6507879569055665e-07, Loss: 0.05923710763454437
2024-08-05T02:06:01.696520978Z 
 70%|███████   | 4015/5712 [9:27:52<4:03:29,  8.61s/it]08/04/2024 19:06:01 - INFO - __main__ -   Step: 4015, LR: 1.6498151706023977e-07, Loss: 0.055246513336896896
2024-08-05T02:06:10.088696230Z 
 70%|███████   | 4016/5712 [9:28:01<4:01:30,  8.54s/it]08/04/2024 19:06:10 - INFO - __main__ -   Step: 4016, LR: 1.648842384299229e-07, Loss: 0.04437507688999176
2024-08-05T02:06:17.612180336Z 
 70%|███████   | 4017/5712 [9:28:08<3:52:42,  8.24s/it]08/04/2024 19:06:17 - INFO - __main__ -   Step: 4017, LR: 1.6478695979960603e-07, Loss: 0.062087129801511765
2024-08-05T02:06:26.023529497Z 
 70%|███████   | 4018/5712 [9:28:17<3:54:02,  8.29s/it]08/04/2024 19:06:26 - INFO - __main__ -   Step: 4018, LR: 1.6468968116928913e-07, Loss: 0.04869431257247925
2024-08-05T02:06:34.106099428Z 
 70%|███████   | 4019/5712 [9:28:25<3:52:09,  8.23s/it]08/04/2024 19:06:34 - INFO - __main__ -   Step: 4019, LR: 1.6459240253897225e-07, Loss: 0.10922617465257645
2024-08-05T02:06:42.087641924Z 
 70%|███████   | 4020/5712 [9:28:33<3:49:56,  8.15s/it]08/04/2024 19:06:42 - INFO - __main__ -   Step: 4020, LR: 1.6449512390865535e-07, Loss: 0.05569120869040489
2024-08-05T02:06:50.888106068Z 
 70%|███████   | 4021/5712 [9:28:42<3:55:16,  8.35s/it]08/04/2024 19:06:50 - INFO - __main__ -   Step: 4021, LR: 1.6439784527833848e-07, Loss: 0.07838939130306244
2024-08-05T02:06:59.392675812Z 
 70%|███████   | 4022/5712 [9:28:50<3:56:27,  8.39s/it]08/04/2024 19:06:59 - INFO - __main__ -   Step: 4022, LR: 1.6430056664802157e-07, Loss: 0.2354210466146469
2024-08-05T02:07:08.099722076Z 
 70%|███████   | 4023/5712 [9:28:59<3:58:56,  8.49s/it]08/04/2024 19:07:08 - INFO - __main__ -   Step: 4023, LR: 1.642032880177047e-07, Loss: 0.07845740765333176
2024-08-05T02:07:17.269246232Z 
 70%|███████   | 4024/5712 [9:29:08<4:04:33,  8.69s/it]08/04/2024 19:07:17 - INFO - __main__ -   Step: 4024, LR: 1.641060093873878e-07, Loss: 0.05470188707113266
2024-08-05T02:07:25.575870374Z 
 70%|███████   | 4025/5712 [9:29:16<4:01:09,  8.58s/it]08/04/2024 19:07:25 - INFO - __main__ -   Step: 4025, LR: 1.6400873075707095e-07, Loss: 0.10124938189983368
2024-08-05T02:07:33.756293312Z 
 70%|███████   | 4026/5712 [9:29:24<3:57:40,  8.46s/it]08/04/2024 19:07:33 - INFO - __main__ -   Step: 4026, LR: 1.6391145212675405e-07, Loss: 0.0607798770070076
2024-08-05T02:07:42.562128045Z 
 71%|███████   | 4027/5712 [9:29:33<4:00:27,  8.56s/it]08/04/2024 19:07:42 - INFO - __main__ -   Step: 4027, LR: 1.6381417349643718e-07, Loss: 0.049072012305259705
2024-08-05T02:07:50.513645501Z 
 71%|███████   | 4028/5712 [9:29:41<3:55:10,  8.38s/it]08/04/2024 19:07:50 - INFO - __main__ -   Step: 4028, LR: 1.6371689486612027e-07, Loss: 0.061985936015844345
2024-08-05T02:07:59.280706452Z 
 71%|███████   | 4029/5712 [9:29:50<3:58:17,  8.50s/it]08/04/2024 19:07:59 - INFO - __main__ -   Step: 4029, LR: 1.636196162358034e-07, Loss: 0.051418520510196686
2024-08-05T02:08:08.627914777Z 
 71%|███████   | 4030/5712 [9:29:59<4:05:19,  8.75s/it]08/04/2024 19:08:08 - INFO - __main__ -   Step: 4030, LR: 1.635223376054865e-07, Loss: 0.0649593323469162
2024-08-05T02:08:16.811597001Z 
 71%|███████   | 4031/5712 [9:30:07<4:00:24,  8.58s/it]08/04/2024 19:08:16 - INFO - __main__ -   Step: 4031, LR: 1.6342505897516962e-07, Loss: 0.07171399891376495
2024-08-05T02:08:25.740563513Z 
 71%|███████   | 4032/5712 [9:30:16<4:03:11,  8.69s/it]08/04/2024 19:08:25 - INFO - __main__ -   Step: 4032, LR: 1.6332778034485272e-07, Loss: 0.05996859073638916
2024-08-05T02:08:34.115251184Z 
 71%|███████   | 4033/5712 [9:30:25<4:00:26,  8.59s/it]08/04/2024 19:08:34 - INFO - __main__ -   Step: 4033, LR: 1.6323050171453585e-07, Loss: 0.08928123861551285
2024-08-05T02:08:42.202231472Z 
 71%|███████   | 4034/5712 [9:30:33<3:56:03,  8.44s/it]08/04/2024 19:08:42 - INFO - __main__ -   Step: 4034, LR: 1.6313322308421897e-07, Loss: 0.029837653040885925
2024-08-05T02:08:50.358223182Z 
 71%|███████   | 4035/5712 [9:30:41<3:53:31,  8.36s/it]08/04/2024 19:08:50 - INFO - __main__ -   Step: 4035, LR: 1.630359444539021e-07, Loss: 0.09312281757593155
2024-08-05T02:08:58.339697189Z 
 71%|███████   | 4036/5712 [9:30:49<3:50:15,  8.24s/it]08/04/2024 19:08:58 - INFO - __main__ -   Step: 4036, LR: 1.629386658235852e-07, Loss: 0.03323759138584137
2024-08-05T02:09:06.478677584Z 
 71%|███████   | 4037/5712 [9:30:57<3:49:14,  8.21s/it]08/04/2024 19:09:06 - INFO - __main__ -   Step: 4037, LR: 1.6284138719326832e-07, Loss: 0.12013053148984909
2024-08-05T02:09:15.509234451Z 
 71%|███████   | 4038/5712 [9:31:06<3:55:57,  8.46s/it]08/04/2024 19:09:15 - INFO - __main__ -   Step: 4038, LR: 1.6274410856295142e-07, Loss: 0.05880007892847061
2024-08-05T02:09:24.368552786Z 
 71%|███████   | 4039/5712 [9:31:15<3:59:11,  8.58s/it]08/04/2024 19:09:24 - INFO - __main__ -   Step: 4039, LR: 1.6264682993263455e-07, Loss: 0.07085221260786057
2024-08-05T02:09:33.092901037Z 
 71%|███████   | 4040/5712 [9:31:24<4:00:15,  8.62s/it]08/04/2024 19:09:33 - INFO - __main__ -   Step: 4040, LR: 1.6254955130231765e-07, Loss: 0.03350163251161575
2024-08-05T02:09:41.897082315Z 
 71%|███████   | 4041/5712 [9:31:33<4:01:38,  8.68s/it]08/04/2024 19:09:41 - INFO - __main__ -   Step: 4041, LR: 1.6245227267200077e-07, Loss: 0.06255006790161133
2024-08-05T02:09:50.347000422Z 
 71%|███████   | 4042/5712 [9:31:41<3:59:36,  8.61s/it]08/04/2024 19:09:50 - INFO - __main__ -   Step: 4042, LR: 1.6235499404168387e-07, Loss: 0.04525137320160866
2024-08-05T02:09:58.671240080Z 
 71%|███████   | 4043/5712 [9:31:49<3:57:05,  8.52s/it]08/04/2024 19:09:58 - INFO - __main__ -   Step: 4043, LR: 1.6225771541136702e-07, Loss: 0.04239220917224884
2024-08-05T02:10:07.138239227Z 
 71%|███████   | 4044/5712 [9:31:58<3:56:28,  8.51s/it]08/04/2024 19:10:07 - INFO - __main__ -   Step: 4044, LR: 1.6216043678105012e-07, Loss: 0.08743396401405334
2024-08-05T02:10:15.179503621Z 
 71%|███████   | 4045/5712 [9:32:06<3:52:27,  8.37s/it]08/04/2024 19:10:15 - INFO - __main__ -   Step: 4045, LR: 1.6206315815073325e-07, Loss: 0.08517512679100037
2024-08-05T02:10:23.778801591Z 
 71%|███████   | 4046/5712 [9:32:14<3:54:15,  8.44s/it]08/04/2024 19:10:23 - INFO - __main__ -   Step: 4046, LR: 1.6196587952041635e-07, Loss: 0.14672785997390747
2024-08-05T02:10:32.518930643Z 
 71%|███████   | 4047/5712 [9:32:23<3:56:38,  8.53s/it]08/04/2024 19:10:32 - INFO - __main__ -   Step: 4047, LR: 1.6186860089009945e-07, Loss: 0.04036349058151245
2024-08-05T02:10:41.251288316Z 
 71%|███████   | 4048/5712 [9:32:32<3:58:12,  8.59s/it]08/04/2024 19:10:41 - INFO - __main__ -   Step: 4048, LR: 1.6177132225978257e-07, Loss: 0.09914432466030121
2024-08-05T02:10:49.557126605Z 
 71%|███████   | 4049/5712 [9:32:40<3:55:42,  8.50s/it]08/04/2024 19:10:49 - INFO - __main__ -   Step: 4049, LR: 1.6167404362946567e-07, Loss: 0.038038287311792374
2024-08-05T02:10:57.942059075Z 
 71%|███████   | 4050/5712 [9:32:49<3:54:34,  8.47s/it]08/04/2024 19:10:57 - INFO - __main__ -   Step: 4050, LR: 1.615767649991488e-07, Loss: 0.07067279517650604
2024-08-05T02:11:06.220866818Z 
 71%|███████   | 4051/5712 [9:32:57<3:52:51,  8.41s/it]08/04/2024 19:11:06 - INFO - __main__ -   Step: 4051, LR: 1.614794863688319e-07, Loss: 0.08447422087192535
2024-08-05T02:11:14.583219714Z 
 71%|███████   | 4052/5712 [9:33:05<3:52:18,  8.40s/it]08/04/2024 19:11:14 - INFO - __main__ -   Step: 4052, LR: 1.6138220773851505e-07, Loss: 0.05927835404872894
2024-08-05T02:11:22.506813699Z 
 71%|███████   | 4053/5712 [9:33:13<3:48:14,  8.25s/it]08/04/2024 19:11:22 - INFO - __main__ -   Step: 4053, LR: 1.6128492910819815e-07, Loss: 0.06241605430841446
2024-08-05T02:11:30.877610016Z 
 71%|███████   | 4054/5712 [9:33:22<3:49:03,  8.29s/it]08/04/2024 19:11:30 - INFO - __main__ -   Step: 4054, LR: 1.6118765047788127e-07, Loss: 0.059019219130277634
2024-08-05T02:11:39.745134828Z 
 71%|███████   | 4055/5712 [9:33:30<3:53:43,  8.46s/it]08/04/2024 19:11:39 - INFO - __main__ -   Step: 4055, LR: 1.6109037184756437e-07, Loss: 0.07745420187711716
2024-08-05T02:11:48.422594919Z 
 71%|███████   | 4056/5712 [9:33:39<3:55:21,  8.53s/it]08/04/2024 19:11:48 - INFO - __main__ -   Step: 4056, LR: 1.609930932172475e-07, Loss: 0.10506024956703186
2024-08-05T02:11:57.342687287Z 
 71%|███████   | 4057/5712 [9:33:48<3:58:27,  8.65s/it]08/04/2024 19:11:57 - INFO - __main__ -   Step: 4057, LR: 1.608958145869306e-07, Loss: 0.059933409094810486
2024-08-05T02:12:05.491739417Z 
 71%|███████   | 4058/5712 [9:33:56<3:54:13,  8.50s/it]08/04/2024 19:12:05 - INFO - __main__ -   Step: 4058, LR: 1.6079853595661372e-07, Loss: 0.0985107272863388
2024-08-05T02:12:13.701088515Z 
 71%|███████   | 4059/5712 [9:34:04<3:51:42,  8.41s/it]08/04/2024 19:12:13 - INFO - __main__ -   Step: 4059, LR: 1.6070125732629682e-07, Loss: 0.09709302335977554
2024-08-05T02:12:21.940660951Z 
 71%|███████   | 4060/5712 [9:34:13<3:50:09,  8.36s/it]08/04/2024 19:12:21 - INFO - __main__ -   Step: 4060, LR: 1.6060397869597995e-07, Loss: 0.06769292056560516
2024-08-05T02:12:30.181587309Z 
 71%|███████   | 4061/5712 [9:34:21<3:49:02,  8.32s/it]08/04/2024 19:12:30 - INFO - __main__ -   Step: 4061, LR: 1.6050670006566307e-07, Loss: 0.050658583641052246
2024-08-05T02:12:38.628618531Z 
 71%|███████   | 4062/5712 [9:34:29<3:49:55,  8.36s/it]08/04/2024 19:12:38 - INFO - __main__ -   Step: 4062, LR: 1.604094214353462e-07, Loss: 0.07513877749443054
2024-08-05T02:12:46.805334400Z 
 71%|███████   | 4063/5712 [9:34:37<3:48:15,  8.31s/it]08/04/2024 19:12:46 - INFO - __main__ -   Step: 4063, LR: 1.603121428050293e-07, Loss: 0.09314963221549988
2024-08-05T02:12:55.265299231Z 
 71%|███████   | 4064/5712 [9:34:46<3:49:23,  8.35s/it]08/04/2024 19:12:55 - INFO - __main__ -   Step: 4064, LR: 1.6021486417471242e-07, Loss: 0.05815427377820015
2024-08-05T02:13:04.138355905Z 
 71%|███████   | 4065/5712 [9:34:55<3:53:33,  8.51s/it]08/04/2024 19:13:04 - INFO - __main__ -   Step: 4065, LR: 1.6011758554439552e-07, Loss: 0.03194911405444145
2024-08-05T02:13:12.903145511Z 
 71%|███████   | 4066/5712 [9:35:04<3:55:31,  8.59s/it]08/04/2024 19:13:12 - INFO - __main__ -   Step: 4066, LR: 1.6002030691407865e-07, Loss: 0.13322824239730835
2024-08-05T02:13:21.131522108Z 
 71%|███████   | 4067/5712 [9:35:12<3:52:26,  8.48s/it]08/04/2024 19:13:21 - INFO - __main__ -   Step: 4067, LR: 1.5992302828376175e-07, Loss: 0.07006953656673431
2024-08-05T02:13:29.658499127Z 
 71%|███████   | 4068/5712 [9:35:20<3:52:42,  8.49s/it]08/04/2024 19:13:29 - INFO - __main__ -   Step: 4068, LR: 1.5982574965344487e-07, Loss: 0.06565045565366745
2024-08-05T02:13:37.644910558Z 
 71%|███████   | 4069/5712 [9:35:28<3:48:24,  8.34s/it]08/04/2024 19:13:37 - INFO - __main__ -   Step: 4069, LR: 1.5972847102312797e-07, Loss: 0.09966164827346802
2024-08-05T02:13:46.339820784Z 
 71%|███████▏  | 4070/5712 [9:35:37<3:51:10,  8.45s/it]08/04/2024 19:13:46 - INFO - __main__ -   Step: 4070, LR: 1.5963119239281112e-07, Loss: 0.0954221859574318
2024-08-05T02:13:54.583672768Z 
 71%|███████▏  | 4071/5712 [9:35:45<3:49:21,  8.39s/it]08/04/2024 19:13:54 - INFO - __main__ -   Step: 4071, LR: 1.5953391376249422e-07, Loss: 0.09777025133371353
2024-08-05T02:14:03.165718078Z 
 71%|███████▏  | 4072/5712 [9:35:54<3:50:49,  8.44s/it]08/04/2024 19:14:03 - INFO - __main__ -   Step: 4072, LR: 1.5943663513217735e-07, Loss: 0.06970708072185516
2024-08-05T02:14:11.480902036Z 
 71%|███████▏  | 4073/5712 [9:36:02<3:49:37,  8.41s/it]08/04/2024 19:14:11 - INFO - __main__ -   Step: 4073, LR: 1.5933935650186045e-07, Loss: 0.08192828297615051
2024-08-05T02:14:20.088112302Z 
 71%|███████▏  | 4074/5712 [9:36:11<3:51:07,  8.47s/it]08/04/2024 19:14:20 - INFO - __main__ -   Step: 4074, LR: 1.5924207787154357e-07, Loss: 0.08569109439849854
2024-08-05T02:14:28.491982040Z 
 71%|███████▏  | 4075/5712 [9:36:19<3:50:28,  8.45s/it]08/04/2024 19:14:28 - INFO - __main__ -   Step: 4075, LR: 1.5914479924122667e-07, Loss: 0.05257808789610863
2024-08-05T02:14:36.508265072Z 
 71%|███████▏  | 4076/5712 [9:36:27<3:46:48,  8.32s/it]08/04/2024 19:14:36 - INFO - __main__ -   Step: 4076, LR: 1.590475206109098e-07, Loss: 0.09110280871391296
2024-08-05T02:14:44.528564877Z 
 71%|███████▏  | 4077/5712 [9:36:35<3:44:14,  8.23s/it]08/04/2024 19:14:44 - INFO - __main__ -   Step: 4077, LR: 1.589502419805929e-07, Loss: 0.18776211142539978
2024-08-05T02:14:53.318904249Z 
 71%|███████▏  | 4078/5712 [9:36:44<3:48:41,  8.40s/it]08/04/2024 19:14:53 - INFO - __main__ -   Step: 4078, LR: 1.5885296335027602e-07, Loss: 0.07271862030029297
2024-08-05T02:15:02.101086184Z 
 71%|███████▏  | 4079/5712 [9:36:53<3:51:41,  8.51s/it]08/04/2024 19:15:02 - INFO - __main__ -   Step: 4079, LR: 1.5875568471995915e-07, Loss: 0.12277847528457642
2024-08-05T02:15:11.371548983Z 
 71%|███████▏  | 4080/5712 [9:37:02<3:57:43,  8.74s/it]08/04/2024 19:15:11 - INFO - __main__ -   Step: 4080, LR: 1.5865840608964227e-07, Loss: 0.08638913929462433
2024-08-05T02:15:19.577102985Z 
 71%|███████▏  | 4081/5712 [9:37:10<3:53:13,  8.58s/it]08/04/2024 19:15:19 - INFO - __main__ -   Step: 4081, LR: 1.5856112745932537e-07, Loss: 0.07861128449440002
2024-08-05T02:15:27.850151225Z 
 71%|███████▏  | 4082/5712 [9:37:18<3:50:34,  8.49s/it]08/04/2024 19:15:27 - INFO - __main__ -   Step: 4082, LR: 1.584638488290085e-07, Loss: 0.03892338275909424
2024-08-05T02:15:36.652706027Z 
 71%|███████▏  | 4083/5712 [9:37:27<3:53:00,  8.58s/it]08/04/2024 19:15:36 - INFO - __main__ -   Step: 4083, LR: 1.583665701986916e-07, Loss: 0.04695336893200874
2024-08-05T02:15:44.832667341Z 
 71%|███████▏  | 4084/5712 [9:37:35<3:49:35,  8.46s/it]08/04/2024 19:15:44 - INFO - __main__ -   Step: 4084, LR: 1.582692915683747e-07, Loss: 0.03991515189409256
2024-08-05T02:15:53.203077722Z 
 72%|███████▏  | 4085/5712 [9:37:44<3:48:42,  8.43s/it]08/04/2024 19:15:53 - INFO - __main__ -   Step: 4085, LR: 1.5817201293805782e-07, Loss: 0.07816115766763687
2024-08-05T02:16:02.052222480Z 
 72%|███████▏  | 4086/5712 [9:37:53<3:51:56,  8.56s/it]08/04/2024 19:16:02 - INFO - __main__ -   Step: 4086, LR: 1.5807473430774092e-07, Loss: 0.0605858713388443
2024-08-05T02:16:11.076126493Z 
 72%|███████▏  | 4087/5712 [9:38:02<3:55:34,  8.70s/it]08/04/2024 19:16:11 - INFO - __main__ -   Step: 4087, LR: 1.5797745567742404e-07, Loss: 0.10450135171413422
2024-08-05T02:16:20.088089146Z 
 72%|███████▏  | 4088/5712 [9:38:11<3:57:58,  8.79s/it]08/04/2024 19:16:20 - INFO - __main__ -   Step: 4088, LR: 1.5788017704710717e-07, Loss: 0.08595743775367737
2024-08-05T02:16:28.613514015Z 
 72%|███████▏  | 4089/5712 [9:38:19<3:55:40,  8.71s/it]08/04/2024 19:16:28 - INFO - __main__ -   Step: 4089, LR: 1.577828984167903e-07, Loss: 0.07381211966276169
2024-08-05T02:16:37.498619876Z 
 72%|███████▏  | 4090/5712 [9:38:28<3:56:55,  8.76s/it]08/04/2024 19:16:37 - INFO - __main__ -   Step: 4090, LR: 1.576856197864734e-07, Loss: 0.04969990998506546
2024-08-05T02:16:46.231611101Z 
 72%|███████▏  | 4091/5712 [9:38:37<3:56:31,  8.75s/it]08/04/2024 19:16:46 - INFO - __main__ -   Step: 4091, LR: 1.5758834115615652e-07, Loss: 0.05058407038450241
2024-08-05T02:16:54.626797413Z 
 72%|███████▏  | 4092/5712 [9:38:45<3:53:28,  8.65s/it]08/04/2024 19:16:54 - INFO - __main__ -   Step: 4092, LR: 1.5749106252583962e-07, Loss: 0.10483568906784058
2024-08-05T02:17:02.890613822Z 
 72%|███████▏  | 4093/5712 [9:38:54<3:50:13,  8.53s/it]08/04/2024 19:17:02 - INFO - __main__ -   Step: 4093, LR: 1.5739378389552274e-07, Loss: 0.041622694581747055
2024-08-05T02:17:11.329642099Z 
 72%|███████▏  | 4094/5712 [9:39:02<3:49:19,  8.50s/it]08/04/2024 19:17:11 - INFO - __main__ -   Step: 4094, LR: 1.5729650526520584e-07, Loss: 0.11665980517864227
2024-08-05T02:17:20.208095087Z 
 72%|███████▏  | 4095/5712 [9:39:11<3:52:12,  8.62s/it]08/04/2024 19:17:20 - INFO - __main__ -   Step: 4095, LR: 1.5719922663488897e-07, Loss: 0.12800036370754242
2024-08-05T02:17:28.588554604Z 
 72%|███████▏  | 4096/5712 [9:39:19<3:50:09,  8.55s/it]08/04/2024 19:17:28 - INFO - __main__ -   Step: 4096, LR: 1.5710194800457207e-07, Loss: 0.0798722505569458
2024-08-05T02:17:36.997569082Z 
 72%|███████▏  | 4097/5712 [9:39:28<3:48:55,  8.50s/it]08/04/2024 19:17:36 - INFO - __main__ -   Step: 4097, LR: 1.5700466937425522e-07, Loss: 0.04889996722340584
2024-08-05T02:17:45.126166401Z 
 72%|███████▏  | 4098/5712 [9:39:36<3:45:44,  8.39s/it]08/04/2024 19:17:45 - INFO - __main__ -   Step: 4098, LR: 1.5690739074393832e-07, Loss: 0.1328592300415039
2024-08-05T02:17:53.527495345Z 
 72%|███████▏  | 4099/5712 [9:39:44<3:45:40,  8.39s/it]08/04/2024 19:17:53 - INFO - __main__ -   Step: 4099, LR: 1.5681011211362144e-07, Loss: 0.053072668612003326
2024-08-05T02:18:01.825802246Z 
 72%|███████▏  | 4100/5712 [9:39:52<3:44:45,  8.37s/it]08/04/2024 19:18:01 - INFO - __main__ -   Step: 4100, LR: 1.5671283348330454e-07, Loss: 0.10261484235525131
2024-08-05T02:18:10.216754056Z 
 72%|███████▏  | 4101/5712 [9:40:01<3:44:49,  8.37s/it]08/04/2024 19:18:10 - INFO - __main__ -   Step: 4101, LR: 1.5661555485298767e-07, Loss: 0.08641928434371948
2024-08-05T02:18:18.230188850Z 
 72%|███████▏  | 4102/5712 [9:40:09<3:41:47,  8.27s/it]08/04/2024 19:18:18 - INFO - __main__ -   Step: 4102, LR: 1.5651827622267077e-07, Loss: 0.09770337492227554
2024-08-05T02:18:27.078300194Z 
 72%|███████▏  | 4103/5712 [9:40:18<3:46:20,  8.44s/it]08/04/2024 19:18:27 - INFO - __main__ -   Step: 4103, LR: 1.564209975923539e-07, Loss: 0.0892416387796402
2024-08-05T02:18:35.681804272Z 
 72%|███████▏  | 4104/5712 [9:40:26<3:47:30,  8.49s/it]08/04/2024 19:18:35 - INFO - __main__ -   Step: 4104, LR: 1.56323718962037e-07, Loss: 0.09331922233104706
2024-08-05T02:18:43.780086757Z 
 72%|███████▏  | 4105/5712 [9:40:34<3:44:13,  8.37s/it]08/04/2024 19:18:43 - INFO - __main__ -   Step: 4105, LR: 1.5622644033172012e-07, Loss: 0.08967863023281097
2024-08-05T02:18:52.059700235Z 
 72%|███████▏  | 4106/5712 [9:40:43<3:43:20,  8.34s/it]08/04/2024 19:18:52 - INFO - __main__ -   Step: 4106, LR: 1.5612916170140324e-07, Loss: 0.1045711487531662
2024-08-05T02:19:00.620669508Z 
 72%|███████▏  | 4107/5712 [9:40:51<3:44:56,  8.41s/it]08/04/2024 19:19:00 - INFO - __main__ -   Step: 4107, LR: 1.5603188307108637e-07, Loss: 0.10193346440792084
2024-08-05T02:19:09.139784506Z 
 72%|███████▏  | 4108/5712 [9:41:00<3:45:41,  8.44s/it]08/04/2024 19:19:09 - INFO - __main__ -   Step: 4108, LR: 1.5593460444076947e-07, Loss: 0.10178447514772415
2024-08-05T02:19:17.496731653Z 
 72%|███████▏  | 4109/5712 [9:41:08<3:44:51,  8.42s/it]08/04/2024 19:19:17 - INFO - __main__ -   Step: 4109, LR: 1.558373258104526e-07, Loss: 0.07156975567340851
2024-08-05T02:19:25.599801480Z 
 72%|███████▏  | 4110/5712 [9:41:16<3:42:12,  8.32s/it]08/04/2024 19:19:25 - INFO - __main__ -   Step: 4110, LR: 1.557400471801357e-07, Loss: 0.07551605999469757
2024-08-05T02:19:33.743043326Z 
 72%|███████▏  | 4111/5712 [9:41:24<3:40:38,  8.27s/it]08/04/2024 19:19:33 - INFO - __main__ -   Step: 4111, LR: 1.5564276854981882e-07, Loss: 0.1429026871919632
2024-08-05T02:19:42.343230930Z 
 72%|███████▏  | 4112/5712 [9:41:33<3:43:09,  8.37s/it]08/04/2024 19:19:42 - INFO - __main__ -   Step: 4112, LR: 1.5554548991950192e-07, Loss: 0.06446561217308044
2024-08-05T02:19:50.584739739Z 
 72%|███████▏  | 4113/5712 [9:41:41<3:42:00,  8.33s/it]08/04/2024 19:19:50 - INFO - __main__ -   Step: 4113, LR: 1.5544821128918504e-07, Loss: 0.05878811329603195
2024-08-05T02:19:58.674143165Z 
 72%|███████▏  | 4114/5712 [9:41:49<3:39:56,  8.26s/it]08/04/2024 19:19:58 - INFO - __main__ -   Step: 4114, LR: 1.5535093265886814e-07, Loss: 0.08273841440677643
2024-08-05T02:20:07.419292308Z 
 72%|███████▏  | 4115/5712 [9:41:58<3:43:41,  8.40s/it]08/04/2024 19:20:07 - INFO - __main__ -   Step: 4115, LR: 1.552536540285513e-07, Loss: 0.06510324031114578
2024-08-05T02:20:15.779073391Z 
 72%|███████▏  | 4116/5712 [9:42:06<3:43:11,  8.39s/it]08/04/2024 19:20:15 - INFO - __main__ -   Step: 4116, LR: 1.551563753982344e-07, Loss: 0.07807154953479767
2024-08-05T02:20:24.125562343Z 
 72%|███████▏  | 4117/5712 [9:42:15<3:42:42,  8.38s/it]08/04/2024 19:20:24 - INFO - __main__ -   Step: 4117, LR: 1.5505909676791752e-07, Loss: 0.0753999724984169
2024-08-05T02:20:32.822575152Z 
 72%|███████▏  | 4118/5712 [9:42:23<3:45:06,  8.47s/it]08/04/2024 19:20:32 - INFO - __main__ -   Step: 4118, LR: 1.5496181813760062e-07, Loss: 0.06967185437679291
2024-08-05T02:20:40.810662734Z 
 72%|███████▏  | 4119/5712 [9:42:31<3:41:05,  8.33s/it]08/04/2024 19:20:40 - INFO - __main__ -   Step: 4119, LR: 1.5486453950728374e-07, Loss: 0.062498271465301514
2024-08-05T02:20:50.252058930Z 
 72%|███████▏  | 4120/5712 [9:42:41<3:49:49,  8.66s/it]08/04/2024 19:20:50 - INFO - __main__ -   Step: 4120, LR: 1.5476726087696684e-07, Loss: 0.09231629222631454
2024-08-05T02:20:58.832461674Z 
 72%|███████▏  | 4121/5712 [9:42:49<3:49:01,  8.64s/it]08/04/2024 19:20:58 - INFO - __main__ -   Step: 4121, LR: 1.5466998224664997e-07, Loss: 0.0869835838675499
2024-08-05T02:21:07.018485883Z 
 72%|███████▏  | 4122/5712 [9:42:58<3:45:18,  8.50s/it]08/04/2024 19:21:07 - INFO - __main__ -   Step: 4122, LR: 1.5457270361633307e-07, Loss: 0.07861977070569992
2024-08-05T02:21:15.685122607Z 
 72%|███████▏  | 4123/5712 [9:43:06<3:46:28,  8.55s/it]08/04/2024 19:21:15 - INFO - __main__ -   Step: 4123, LR: 1.5447542498601617e-07, Loss: 0.12473617494106293
2024-08-05T02:21:24.445844828Z 
 72%|███████▏  | 4124/5712 [9:43:15<3:47:59,  8.61s/it]08/04/2024 19:21:24 - INFO - __main__ -   Step: 4124, LR: 1.5437814635569932e-07, Loss: 0.05139491707086563
2024-08-05T02:21:32.636767056Z 
 72%|███████▏  | 4125/5712 [9:43:23<3:44:29,  8.49s/it]08/04/2024 19:21:32 - INFO - __main__ -   Step: 4125, LR: 1.5428086772538242e-07, Loss: 0.11715297400951385
2024-08-05T02:21:40.933193501Z 
 72%|███████▏  | 4126/5712 [9:43:32<3:42:50,  8.43s/it]08/04/2024 19:21:40 - INFO - __main__ -   Step: 4126, LR: 1.5418358909506554e-07, Loss: 0.0724877417087555
2024-08-05T02:21:49.303855574Z 
 72%|███████▏  | 4127/5712 [9:43:40<3:42:13,  8.41s/it]08/04/2024 19:21:49 - INFO - __main__ -   Step: 4127, LR: 1.5408631046474864e-07, Loss: 0.07779589295387268
2024-08-05T02:21:57.727463613Z 
 72%|███████▏  | 4128/5712 [9:43:48<3:42:09,  8.42s/it]08/04/2024 19:21:57 - INFO - __main__ -   Step: 4128, LR: 1.5398903183443177e-07, Loss: 0.06441439688205719
2024-08-05T02:22:06.992451111Z 
 72%|███████▏  | 4129/5712 [9:43:58<3:48:45,  8.67s/it]08/04/2024 19:22:06 - INFO - __main__ -   Step: 4129, LR: 1.5389175320411487e-07, Loss: 0.10457216203212738
2024-08-05T02:22:15.013370052Z 
 72%|███████▏  | 4130/5712 [9:44:06<3:43:28,  8.48s/it]08/04/2024 19:22:15 - INFO - __main__ -   Step: 4130, LR: 1.53794474573798e-07, Loss: 0.15894410014152527
2024-08-05T02:22:23.355540761Z 
 72%|███████▏  | 4131/5712 [9:44:14<3:42:16,  8.44s/it]08/04/2024 19:22:23 - INFO - __main__ -   Step: 4131, LR: 1.536971959434811e-07, Loss: 0.07769618928432465
2024-08-05T02:22:31.699853906Z 
 72%|███████▏  | 4132/5712 [9:44:22<3:41:24,  8.41s/it]08/04/2024 19:22:31 - INFO - __main__ -   Step: 4132, LR: 1.5359991731316422e-07, Loss: 0.13064798712730408
2024-08-05T02:22:40.090847218Z 
 72%|███████▏  | 4133/5712 [9:44:31<3:41:08,  8.40s/it]08/04/2024 19:22:40 - INFO - __main__ -   Step: 4133, LR: 1.5350263868284734e-07, Loss: 0.05735236406326294
2024-08-05T02:22:48.299753967Z 
 72%|███████▏  | 4134/5712 [9:44:39<3:39:28,  8.34s/it]08/04/2024 19:22:48 - INFO - __main__ -   Step: 4134, LR: 1.5340536005253047e-07, Loss: 0.041491761803627014
2024-08-05T02:22:56.872126680Z 
 72%|███████▏  | 4135/5712 [9:44:48<3:41:07,  8.41s/it]08/04/2024 19:22:56 - INFO - __main__ -   Step: 4135, LR: 1.5330808142221357e-07, Loss: 0.08789324760437012
2024-08-05T02:23:04.946551120Z 
 72%|███████▏  | 4136/5712 [9:44:56<3:38:18,  8.31s/it]08/04/2024 19:23:04 - INFO - __main__ -   Step: 4136, LR: 1.532108027918967e-07, Loss: 0.07797528803348541
2024-08-05T02:23:13.948296458Z 
 72%|███████▏  | 4137/5712 [9:45:05<3:43:36,  8.52s/it]08/04/2024 19:23:13 - INFO - __main__ -   Step: 4137, LR: 1.531135241615798e-07, Loss: 0.08830410987138748
2024-08-05T02:23:22.006347351Z 
 72%|███████▏  | 4138/5712 [9:45:13<3:39:50,  8.38s/it]08/04/2024 19:23:22 - INFO - __main__ -   Step: 4138, LR: 1.5301624553126292e-07, Loss: 0.06672792136669159
2024-08-05T02:23:30.320172081Z 
 72%|███████▏  | 4139/5712 [9:45:21<3:39:11,  8.36s/it]08/04/2024 19:23:30 - INFO - __main__ -   Step: 4139, LR: 1.5291896690094602e-07, Loss: 0.12373840063810349
2024-08-05T02:23:39.293667698Z 
 72%|███████▏  | 4140/5712 [9:45:30<3:43:51,  8.54s/it]08/04/2024 19:23:39 - INFO - __main__ -   Step: 4140, LR: 1.5282168827062914e-07, Loss: 0.05453868210315704
2024-08-05T02:23:47.680284929Z 
 72%|███████▏  | 4141/5712 [9:45:38<3:42:28,  8.50s/it]08/04/2024 19:23:47 - INFO - __main__ -   Step: 4141, LR: 1.5272440964031224e-07, Loss: 0.055759817361831665
2024-08-05T02:23:55.789412343Z 
 73%|███████▎  | 4142/5712 [9:45:46<3:39:17,  8.38s/it]08/04/2024 19:23:55 - INFO - __main__ -   Step: 4142, LR: 1.526271310099954e-07, Loss: 0.049513667821884155
2024-08-05T02:24:03.772430698Z 
 73%|███████▎  | 4143/5712 [9:45:54<3:36:02,  8.26s/it]08/04/2024 19:24:03 - INFO - __main__ -   Step: 4143, LR: 1.525298523796785e-07, Loss: 0.07778584212064743
2024-08-05T02:24:12.644998763Z 
 73%|███████▎  | 4144/5712 [9:46:03<3:40:41,  8.44s/it]08/04/2024 19:24:12 - INFO - __main__ -   Step: 4144, LR: 1.5243257374936162e-07, Loss: 0.09716875851154327
2024-08-05T02:24:20.907488974Z 
 73%|███████▎  | 4145/5712 [9:46:12<3:39:07,  8.39s/it]08/04/2024 19:24:20 - INFO - __main__ -   Step: 4145, LR: 1.5233529511904472e-07, Loss: 0.07392047345638275
2024-08-05T02:24:29.173379572Z 
 73%|███████▎  | 4146/5712 [9:46:20<3:38:00,  8.35s/it]08/04/2024 19:24:29 - INFO - __main__ -   Step: 4146, LR: 1.5223801648872784e-07, Loss: 0.07135586440563202
2024-08-05T02:24:37.315623284Z 
 73%|███████▎  | 4147/5712 [9:46:28<3:36:13,  8.29s/it]08/04/2024 19:24:37 - INFO - __main__ -   Step: 4147, LR: 1.5214073785841094e-07, Loss: 0.09410485625267029
2024-08-05T02:24:45.656027012Z 
 73%|███████▎  | 4148/5712 [9:46:36<3:36:28,  8.30s/it]08/04/2024 19:24:45 - INFO - __main__ -   Step: 4148, LR: 1.5204345922809407e-07, Loss: 0.07588418573141098
2024-08-05T02:24:54.441778599Z 
 73%|███████▎  | 4149/5712 [9:46:45<3:40:06,  8.45s/it]08/04/2024 19:24:54 - INFO - __main__ -   Step: 4149, LR: 1.5194618059777716e-07, Loss: 0.09215788543224335
2024-08-05T02:25:02.423335233Z 
 73%|███████▎  | 4150/5712 [9:46:53<3:36:18,  8.31s/it]08/04/2024 19:25:02 - INFO - __main__ -   Step: 4150, LR: 1.518489019674603e-07, Loss: 0.06585786491632462
2024-08-05T02:25:10.564443505Z 
 73%|███████▎  | 4151/5712 [9:47:01<3:34:51,  8.26s/it]08/04/2024 19:25:10 - INFO - __main__ -   Step: 4151, LR: 1.5175162333714342e-07, Loss: 0.08366134762763977
2024-08-05T02:25:19.210496742Z 
 73%|███████▎  | 4152/5712 [9:47:10<3:37:44,  8.37s/it]08/04/2024 19:25:19 - INFO - __main__ -   Step: 4152, LR: 1.5165434470682654e-07, Loss: 0.10107897222042084
2024-08-05T02:25:27.886101117Z 
 73%|███████▎  | 4153/5712 [9:47:19<3:39:56,  8.46s/it]08/04/2024 19:25:27 - INFO - __main__ -   Step: 4153, LR: 1.5155706607650964e-07, Loss: 0.03809059411287308
2024-08-05T02:25:36.468454599Z 
 73%|███████▎  | 4154/5712 [9:47:27<3:40:42,  8.50s/it]08/04/2024 19:25:36 - INFO - __main__ -   Step: 4154, LR: 1.5145978744619277e-07, Loss: 0.10840397328138351
2024-08-05T02:25:44.572795401Z 
 73%|███████▎  | 4155/5712 [9:47:35<3:37:30,  8.38s/it]08/04/2024 19:25:44 - INFO - __main__ -   Step: 4155, LR: 1.5136250881587586e-07, Loss: 0.06569970399141312
2024-08-05T02:25:53.098931287Z 
 73%|███████▎  | 4156/5712 [9:47:44<3:38:29,  8.42s/it]08/04/2024 19:25:53 - INFO - __main__ -   Step: 4156, LR: 1.51265230185559e-07, Loss: 0.07244879007339478
2024-08-05T02:26:02.446699683Z 
 73%|███████▎  | 4157/5712 [9:47:53<3:45:31,  8.70s/it]08/04/2024 19:26:02 - INFO - __main__ -   Step: 4157, LR: 1.511679515552421e-07, Loss: 0.043153539299964905
2024-08-05T02:26:10.907316622Z 
 73%|███████▎  | 4158/5712 [9:48:02<3:43:30,  8.63s/it]08/04/2024 19:26:10 - INFO - __main__ -   Step: 4158, LR: 1.5107067292492521e-07, Loss: 0.04295285791158676
2024-08-05T02:26:19.060067491Z 
 73%|███████▎  | 4159/5712 [9:48:10<3:39:39,  8.49s/it]08/04/2024 19:26:19 - INFO - __main__ -   Step: 4159, LR: 1.5097339429460831e-07, Loss: 0.08064945787191391
2024-08-05T02:26:27.522309684Z 
 73%|███████▎  | 4160/5712 [9:48:18<3:39:19,  8.48s/it]08/04/2024 19:26:27 - INFO - __main__ -   Step: 4160, LR: 1.5087611566429147e-07, Loss: 0.06279142200946808
2024-08-05T02:26:36.160272889Z 
 73%|███████▎  | 4161/5712 [9:48:27<3:40:25,  8.53s/it]08/04/2024 19:26:36 - INFO - __main__ -   Step: 4161, LR: 1.5077883703397457e-07, Loss: 0.07895147800445557
2024-08-05T02:26:44.117546164Z 
 73%|███████▎  | 4162/5712 [9:48:35<3:35:51,  8.36s/it]08/04/2024 19:26:44 - INFO - __main__ -   Step: 4162, LR: 1.5068155840365766e-07, Loss: 0.06516171991825104
2024-08-05T02:26:52.665209273Z 
 73%|███████▎  | 4163/5712 [9:48:43<3:37:12,  8.41s/it]08/04/2024 19:26:52 - INFO - __main__ -   Step: 4163, LR: 1.505842797733408e-07, Loss: 0.06698238104581833
2024-08-05T02:27:01.445735972Z 
 73%|███████▎  | 4164/5712 [9:48:52<3:39:54,  8.52s/it]08/04/2024 19:27:01 - INFO - __main__ -   Step: 4164, LR: 1.504870011430239e-07, Loss: 0.1412447690963745
2024-08-05T02:27:10.406002611Z 
 73%|███████▎  | 4165/5712 [9:49:01<3:43:08,  8.65s/it]08/04/2024 19:27:10 - INFO - __main__ -   Step: 4165, LR: 1.5038972251270701e-07, Loss: 0.050026483833789825
2024-08-05T02:27:18.896800175Z 
 73%|███████▎  | 4166/5712 [9:49:10<3:41:44,  8.61s/it]08/04/2024 19:27:18 - INFO - __main__ -   Step: 4166, LR: 1.502924438823901e-07, Loss: 0.02666543237864971
2024-08-05T02:27:27.080978898Z 
 73%|███████▎  | 4167/5712 [9:49:18<3:38:20,  8.48s/it]08/04/2024 19:27:27 - INFO - __main__ -   Step: 4167, LR: 1.5019516525207324e-07, Loss: 0.0915086567401886
2024-08-05T02:27:35.109838339Z 
 73%|███████▎  | 4168/5712 [9:49:26<3:34:43,  8.34s/it]08/04/2024 19:27:35 - INFO - __main__ -   Step: 4168, LR: 1.5009788662175634e-07, Loss: 0.041005879640579224
2024-08-05T02:27:44.002962530Z 
 73%|███████▎  | 4169/5712 [9:49:35<3:38:48,  8.51s/it]08/04/2024 19:27:44 - INFO - __main__ -   Step: 4169, LR: 1.500006079914395e-07, Loss: 0.07474090158939362
2024-08-05T02:27:51.932264067Z 
 73%|███████▎  | 4170/5712 [9:49:43<3:34:12,  8.33s/it]08/04/2024 19:27:51 - INFO - __main__ -   Step: 4170, LR: 1.499033293611226e-07, Loss: 0.09037391096353531
2024-08-05T02:28:00.821400561Z 
 73%|███████▎  | 4171/5712 [9:49:51<3:38:20,  8.50s/it]08/04/2024 19:28:00 - INFO - __main__ -   Step: 4171, LR: 1.4980605073080571e-07, Loss: 0.15857085585594177
2024-08-05T02:28:09.058413099Z 
 73%|███████▎  | 4172/5712 [9:50:00<3:36:09,  8.42s/it]08/04/2024 19:28:09 - INFO - __main__ -   Step: 4172, LR: 1.4970877210048881e-07, Loss: 0.06871820986270905
2024-08-05T02:28:17.472340228Z 
 73%|███████▎  | 4173/5712 [9:50:08<3:35:57,  8.42s/it]08/04/2024 19:28:17 - INFO - __main__ -   Step: 4173, LR: 1.4961149347017194e-07, Loss: 0.10041111707687378
2024-08-05T02:28:25.722548907Z 
 73%|███████▎  | 4174/5712 [9:50:16<3:34:31,  8.37s/it]08/04/2024 19:28:25 - INFO - __main__ -   Step: 4174, LR: 1.4951421483985504e-07, Loss: 0.07929082214832306
2024-08-05T02:28:34.006330309Z 
 73%|███████▎  | 4175/5712 [9:50:25<3:33:43,  8.34s/it]08/04/2024 19:28:34 - INFO - __main__ -   Step: 4175, LR: 1.4941693620953816e-07, Loss: 0.10901176184415817
2024-08-05T02:28:42.303374518Z 
 73%|███████▎  | 4176/5712 [9:50:33<3:33:14,  8.33s/it]08/04/2024 19:28:42 - INFO - __main__ -   Step: 4176, LR: 1.4931965757922126e-07, Loss: 0.07954730093479156
2024-08-05T02:28:51.182526691Z 
 73%|███████▎  | 4177/5712 [9:50:42<3:37:18,  8.49s/it]08/04/2024 19:28:51 - INFO - __main__ -   Step: 4177, LR: 1.492223789489044e-07, Loss: 0.11219178140163422
2024-08-05T02:28:59.572653994Z 
 73%|███████▎  | 4178/5712 [9:50:50<3:36:22,  8.46s/it]08/04/2024 19:28:59 - INFO - __main__ -   Step: 4178, LR: 1.4912510031858751e-07, Loss: 0.04171553999185562
2024-08-05T02:29:07.166077938Z 
 73%|███████▎  | 4179/5712 [9:50:58<3:29:33,  8.20s/it]08/04/2024 19:29:07 - INFO - __main__ -   Step: 4179, LR: 1.4902782168827064e-07, Loss: 0.07281893491744995
2024-08-05T02:29:15.794846427Z 
 73%|███████▎  | 4180/5712 [9:51:06<3:32:41,  8.33s/it]08/04/2024 19:29:15 - INFO - __main__ -   Step: 4180, LR: 1.4893054305795374e-07, Loss: 0.06319920718669891
2024-08-05T02:29:24.581545344Z 
 73%|███████▎  | 4181/5712 [9:51:15<3:36:03,  8.47s/it]08/04/2024 19:29:24 - INFO - __main__ -   Step: 4181, LR: 1.4883326442763686e-07, Loss: 0.07689997553825378
2024-08-05T02:29:33.149056337Z 
 73%|███████▎  | 4182/5712 [9:51:24<3:36:40,  8.50s/it]08/04/2024 19:29:33 - INFO - __main__ -   Step: 4182, LR: 1.4873598579731996e-07, Loss: 0.08858049660921097
2024-08-05T02:29:41.284646026Z 
 73%|███████▎  | 4183/5712 [9:51:32<3:33:46,  8.39s/it]08/04/2024 19:29:41 - INFO - __main__ -   Step: 4183, LR: 1.486387071670031e-07, Loss: 0.07638044655323029
2024-08-05T02:29:49.514667802Z 
 73%|███████▎  | 4184/5712 [9:51:40<3:32:25,  8.34s/it]08/04/2024 19:29:49 - INFO - __main__ -   Step: 4184, LR: 1.485414285366862e-07, Loss: 0.11622624099254608
2024-08-05T02:29:57.818114104Z 
 73%|███████▎  | 4185/5712 [9:51:48<3:31:59,  8.33s/it]08/04/2024 19:29:57 - INFO - __main__ -   Step: 4185, LR: 1.484441499063693e-07, Loss: 0.1270541250705719
2024-08-05T02:30:06.282148188Z 
 73%|███████▎  | 4186/5712 [9:51:57<3:32:52,  8.37s/it]08/04/2024 19:30:06 - INFO - __main__ -   Step: 4186, LR: 1.483468712760524e-07, Loss: 0.07964739203453064
2024-08-05T02:30:13.886035804Z 
 73%|███████▎  | 4187/5712 [9:52:05<3:26:53,  8.14s/it]08/04/2024 19:30:13 - INFO - __main__ -   Step: 4187, LR: 1.4824959264573556e-07, Loss: 0.10064676403999329
2024-08-05T02:30:23.004182526Z 
 73%|███████▎  | 4188/5712 [9:52:14<3:34:12,  8.43s/it]08/04/2024 19:30:23 - INFO - __main__ -   Step: 4188, LR: 1.4815231401541866e-07, Loss: 0.03163193166255951
2024-08-05T02:30:31.506189352Z 
 73%|███████▎  | 4189/5712 [9:52:22<3:34:35,  8.45s/it]08/04/2024 19:30:31 - INFO - __main__ -   Step: 4189, LR: 1.480550353851018e-07, Loss: 0.07222071290016174
2024-08-05T02:30:40.395212963Z 
 73%|███████▎  | 4190/5712 [9:52:31<3:37:45,  8.58s/it]08/04/2024 19:30:40 - INFO - __main__ -   Step: 4190, LR: 1.479577567547849e-07, Loss: 0.07167030870914459
2024-08-05T02:30:48.751731557Z 
 73%|███████▎  | 4191/5712 [9:52:39<3:35:53,  8.52s/it]08/04/2024 19:30:48 - INFO - __main__ -   Step: 4191, LR: 1.47860478124468e-07, Loss: 0.05727700889110565
2024-08-05T02:30:56.973179350Z 
 73%|███████▎  | 4192/5712 [9:52:48<3:33:30,  8.43s/it]08/04/2024 19:30:56 - INFO - __main__ -   Step: 4192, LR: 1.477631994941511e-07, Loss: 0.18075282871723175
2024-08-05T02:31:05.473796381Z 
 73%|███████▎  | 4193/5712 [9:52:56<3:33:54,  8.45s/it]08/04/2024 19:31:05 - INFO - __main__ -   Step: 4193, LR: 1.4766592086383424e-07, Loss: 0.07945264875888824
2024-08-05T02:31:13.967559283Z 
 73%|███████▎  | 4194/5712 [9:53:05<3:34:06,  8.46s/it]08/04/2024 19:31:13 - INFO - __main__ -   Step: 4194, LR: 1.4756864223351734e-07, Loss: 0.06336092948913574
2024-08-05T02:31:22.196249026Z 
 73%|███████▎  | 4195/5712 [9:53:13<3:32:11,  8.39s/it]08/04/2024 19:31:22 - INFO - __main__ -   Step: 4195, LR: 1.4747136360320046e-07, Loss: 0.0651211068034172
2024-08-05T02:31:29.739748754Z 
 73%|███████▎  | 4196/5712 [9:53:20<3:25:36,  8.14s/it]08/04/2024 19:31:29 - INFO - __main__ -   Step: 4196, LR: 1.473740849728836e-07, Loss: 0.15815779566764832
2024-08-05T02:31:38.690742780Z 
 73%|███████▎  | 4197/5712 [9:53:29<3:31:38,  8.38s/it]08/04/2024 19:31:38 - INFO - __main__ -   Step: 4197, LR: 1.472768063425667e-07, Loss: 0.09137706458568573
2024-08-05T02:31:47.455237013Z 
 73%|███████▎  | 4198/5712 [9:53:38<3:34:23,  8.50s/it]08/04/2024 19:31:47 - INFO - __main__ -   Step: 4198, LR: 1.471795277122498e-07, Loss: 0.08203929662704468
2024-08-05T02:31:55.807542238Z 
 74%|███████▎  | 4199/5712 [9:53:46<3:33:09,  8.45s/it]08/04/2024 19:31:55 - INFO - __main__ -   Step: 4199, LR: 1.470822490819329e-07, Loss: 0.06441596895456314
2024-08-05T02:32:03.921391732Z 
 74%|███████▎  | 4200/5712 [9:53:55<3:30:27,  8.35s/it]08/04/2024 19:32:03 - INFO - __main__ -   Step: 4200, LR: 1.4698497045161604e-07, Loss: 0.08607888221740723
2024-08-05T02:32:11.876498896Z 
 74%|███████▎  | 4201/5712 [9:54:03<3:27:19,  8.23s/it]08/04/2024 19:32:11 - INFO - __main__ -   Step: 4201, LR: 1.4688769182129914e-07, Loss: 0.12906774878501892
2024-08-05T02:32:20.735497194Z 
 74%|███████▎  | 4202/5712 [9:54:11<3:31:54,  8.42s/it]08/04/2024 19:32:20 - INFO - __main__ -   Step: 4202, LR: 1.4679041319098226e-07, Loss: 0.06859640777111053
2024-08-05T02:32:29.186274149Z 
 74%|███████▎  | 4203/5712 [9:54:20<3:32:00,  8.43s/it]08/04/2024 19:32:29 - INFO - __main__ -   Step: 4203, LR: 1.4669313456066536e-07, Loss: 0.10721544176340103
2024-08-05T02:32:36.803899412Z 
 74%|███████▎  | 4204/5712 [9:54:27<3:25:44,  8.19s/it]08/04/2024 19:32:36 - INFO - __main__ -   Step: 4204, LR: 1.4659585593034849e-07, Loss: 0.052989933639764786
2024-08-05T02:32:45.838426700Z 
 74%|███████▎  | 4205/5712 [9:54:36<3:31:59,  8.44s/it]08/04/2024 19:32:45 - INFO - __main__ -   Step: 4205, LR: 1.464985773000316e-07, Loss: 0.08276953548192978
2024-08-05T02:32:54.586918559Z 
 74%|███████▎  | 4206/5712 [9:54:45<3:34:10,  8.53s/it]08/04/2024 19:32:54 - INFO - __main__ -   Step: 4206, LR: 1.4640129866971474e-07, Loss: 0.0880376473069191
2024-08-05T02:33:03.259167156Z 
 74%|███████▎  | 4207/5712 [9:54:54<3:35:05,  8.57s/it]08/04/2024 19:33:03 - INFO - __main__ -   Step: 4207, LR: 1.4630402003939784e-07, Loss: 0.07366012036800385
2024-08-05T02:33:11.296073780Z 
 74%|███████▎  | 4208/5712 [9:55:02<3:30:53,  8.41s/it]08/04/2024 19:33:11 - INFO - __main__ -   Step: 4208, LR: 1.4620674140908096e-07, Loss: 0.05477098375558853
2024-08-05T02:33:19.632731110Z 
 74%|███████▎  | 4209/5712 [9:55:10<3:30:10,  8.39s/it]08/04/2024 19:33:19 - INFO - __main__ -   Step: 4209, LR: 1.4610946277876406e-07, Loss: 0.0692010447382927
2024-08-05T02:33:28.196260026Z 
 74%|███████▎  | 4210/5712 [9:55:19<3:31:20,  8.44s/it]08/04/2024 19:33:28 - INFO - __main__ -   Step: 4210, LR: 1.4601218414844719e-07, Loss: 0.03605591505765915
2024-08-05T02:33:36.514854187Z 
 74%|███████▎  | 4211/5712 [9:55:27<3:30:16,  8.41s/it]08/04/2024 19:33:36 - INFO - __main__ -   Step: 4211, LR: 1.4591490551813028e-07, Loss: 0.07322447746992111
2024-08-05T02:33:44.822765077Z 
 74%|███████▎  | 4212/5712 [9:55:35<3:29:24,  8.38s/it]08/04/2024 19:33:44 - INFO - __main__ -   Step: 4212, LR: 1.458176268878134e-07, Loss: 0.1258077621459961
2024-08-05T02:33:53.033896228Z 
 74%|███████▍  | 4213/5712 [9:55:44<3:28:01,  8.33s/it]08/04/2024 19:33:53 - INFO - __main__ -   Step: 4213, LR: 1.457203482574965e-07, Loss: 0.057983845472335815
2024-08-05T02:34:01.982557260Z 
 74%|███████▍  | 4214/5712 [9:55:53<3:32:32,  8.51s/it]08/04/2024 19:34:01 - INFO - __main__ -   Step: 4214, LR: 1.4562306962717966e-07, Loss: 0.1147487610578537
2024-08-05T02:34:10.782050920Z 
 74%|███████▍  | 4215/5712 [9:56:01<3:34:32,  8.60s/it]08/04/2024 19:34:10 - INFO - __main__ -   Step: 4215, LR: 1.4552579099686276e-07, Loss: 0.03733764588832855
2024-08-05T02:34:18.925955318Z 
 74%|███████▍  | 4216/5712 [9:56:10<3:30:59,  8.46s/it]08/04/2024 19:34:18 - INFO - __main__ -   Step: 4216, LR: 1.4542851236654589e-07, Loss: 0.06955352425575256
2024-08-05T02:34:27.165071121Z 
 74%|███████▍  | 4217/5712 [9:56:18<3:29:11,  8.40s/it]08/04/2024 19:34:27 - INFO - __main__ -   Step: 4217, LR: 1.4533123373622899e-07, Loss: 0.07031726837158203
2024-08-05T02:34:35.385475921Z 
 74%|███████▍  | 4218/5712 [9:56:26<3:27:44,  8.34s/it]08/04/2024 19:34:35 - INFO - __main__ -   Step: 4218, LR: 1.452339551059121e-07, Loss: 0.10939760506153107
2024-08-05T02:34:43.951460956Z 
 74%|███████▍  | 4219/5712 [9:56:35<3:29:15,  8.41s/it]08/04/2024 19:34:43 - INFO - __main__ -   Step: 4219, LR: 1.451366764755952e-07, Loss: 0.07596105337142944
2024-08-05T02:34:52.350084510Z 
 74%|███████▍  | 4220/5712 [9:56:43<3:29:02,  8.41s/it]08/04/2024 19:34:52 - INFO - __main__ -   Step: 4220, LR: 1.4503939784527834e-07, Loss: 0.09126133471727371
2024-08-05T02:35:00.712415665Z 
 74%|███████▍  | 4221/5712 [9:56:51<3:28:34,  8.39s/it]08/04/2024 19:35:00 - INFO - __main__ -   Step: 4221, LR: 1.4494211921496143e-07, Loss: 0.04215191677212715
2024-08-05T02:35:09.851183114Z 
 74%|███████▍  | 4222/5712 [9:57:00<3:33:58,  8.62s/it]08/04/2024 19:35:09 - INFO - __main__ -   Step: 4222, LR: 1.4484484058464456e-07, Loss: 0.09941326826810837
2024-08-05T02:35:18.269488115Z 
 74%|███████▍  | 4223/5712 [9:57:09<3:32:22,  8.56s/it]08/04/2024 19:35:18 - INFO - __main__ -   Step: 4223, LR: 1.4474756195432766e-07, Loss: 0.15318280458450317
2024-08-05T02:35:26.886623343Z 
 74%|███████▍  | 4224/5712 [9:57:18<3:32:40,  8.58s/it]08/04/2024 19:35:26 - INFO - __main__ -   Step: 4224, LR: 1.446502833240108e-07, Loss: 0.09347270429134369
2024-08-05T02:35:35.148810049Z 
 74%|███████▍  | 4225/5712 [9:57:26<3:30:11,  8.48s/it]08/04/2024 19:35:35 - INFO - __main__ -   Step: 4225, LR: 1.445530046936939e-07, Loss: 0.056978654116392136
2024-08-05T02:35:43.399677331Z 
 74%|███████▍  | 4226/5712 [9:57:34<3:28:20,  8.41s/it]08/04/2024 19:35:43 - INFO - __main__ -   Step: 4226, LR: 1.4445572606337704e-07, Loss: 0.0617937408387661
2024-08-05T02:35:52.069125988Z 
 74%|███████▍  | 4227/5712 [9:57:43<3:30:06,  8.49s/it]08/04/2024 19:35:52 - INFO - __main__ -   Step: 4227, LR: 1.4435844743306013e-07, Loss: 0.037708625197410583
2024-08-05T02:36:00.126770564Z 
 74%|███████▍  | 4228/5712 [9:57:51<3:26:46,  8.36s/it]08/04/2024 19:36:00 - INFO - __main__ -   Step: 4228, LR: 1.4426116880274326e-07, Loss: 0.07667383551597595
2024-08-05T02:36:08.663321199Z 
 74%|███████▍  | 4229/5712 [9:57:59<3:27:56,  8.41s/it]08/04/2024 19:36:08 - INFO - __main__ -   Step: 4229, LR: 1.4416389017242636e-07, Loss: 0.08062897622585297
2024-08-05T02:36:17.950047602Z 
 74%|███████▍  | 4230/5712 [9:58:09<3:34:16,  8.68s/it]08/04/2024 19:36:17 - INFO - __main__ -   Step: 4230, LR: 1.4406661154210948e-07, Loss: 0.0410994291305542
2024-08-05T02:36:26.896719919Z 
 74%|███████▍  | 4231/5712 [9:58:18<3:36:08,  8.76s/it]08/04/2024 19:36:26 - INFO - __main__ -   Step: 4231, LR: 1.4396933291179258e-07, Loss: 0.06656070798635483
2024-08-05T02:36:35.469295836Z 
 74%|███████▍  | 4232/5712 [9:58:26<3:34:38,  8.70s/it]08/04/2024 19:36:35 - INFO - __main__ -   Step: 4232, LR: 1.438720542814757e-07, Loss: 0.07294424623250961
2024-08-05T02:36:43.872327214Z 
 74%|███████▍  | 4233/5712 [9:58:35<3:32:16,  8.61s/it]08/04/2024 19:36:43 - INFO - __main__ -   Step: 4233, LR: 1.4377477565115883e-07, Loss: 0.08028267323970795
2024-08-05T02:36:52.223644834Z 
 74%|███████▍  | 4234/5712 [9:58:43<3:30:12,  8.53s/it]08/04/2024 19:36:52 - INFO - __main__ -   Step: 4234, LR: 1.4367749702084196e-07, Loss: 0.08557617664337158
2024-08-05T02:37:00.610869959Z 
 74%|███████▍  | 4235/5712 [9:58:51<3:28:59,  8.49s/it]08/04/2024 19:37:00 - INFO - __main__ -   Step: 4235, LR: 1.4358021839052506e-07, Loss: 0.032547712326049805
2024-08-05T02:37:09.077515830Z 
 74%|███████▍  | 4236/5712 [9:59:00<3:28:40,  8.48s/it]08/04/2024 19:37:09 - INFO - __main__ -   Step: 4236, LR: 1.4348293976020818e-07, Loss: 0.11776702105998993
2024-08-05T02:37:17.623034701Z 
 74%|███████▍  | 4237/5712 [9:59:08<3:28:59,  8.50s/it]08/04/2024 19:37:17 - INFO - __main__ -   Step: 4237, LR: 1.4338566112989128e-07, Loss: 0.07127527892589569
2024-08-05T02:37:25.950742995Z 
 74%|███████▍  | 4238/5712 [9:59:17<3:27:34,  8.45s/it]08/04/2024 19:37:25 - INFO - __main__ -   Step: 4238, LR: 1.4328838249957438e-07, Loss: 0.032209984958171844
2024-08-05T02:37:34.904258751Z 
 74%|███████▍  | 4239/5712 [9:59:26<3:31:08,  8.60s/it]08/04/2024 19:37:34 - INFO - __main__ -   Step: 4239, LR: 1.431911038692575e-07, Loss: 0.1284995973110199
2024-08-05T02:37:43.070134785Z 
 74%|███████▍  | 4240/5712 [9:59:34<3:27:48,  8.47s/it]08/04/2024 19:37:43 - INFO - __main__ -   Step: 4240, LR: 1.430938252389406e-07, Loss: 0.10754861682653427
2024-08-05T02:37:51.493903096Z 
 74%|███████▍  | 4241/5712 [9:59:42<3:27:19,  8.46s/it]08/04/2024 19:37:51 - INFO - __main__ -   Step: 4241, LR: 1.4299654660862373e-07, Loss: 0.05194442719221115
2024-08-05T02:38:00.194834134Z 
 74%|███████▍  | 4242/5712 [9:59:51<3:28:58,  8.53s/it]08/04/2024 19:38:00 - INFO - __main__ -   Step: 4242, LR: 1.4289926797830686e-07, Loss: 0.05234453082084656
2024-08-05T02:38:08.934810207Z 
 74%|███████▍  | 4243/5712 [10:00:00<3:30:22,  8.59s/it]08/04/2024 19:38:08 - INFO - __main__ -   Step: 4243, LR: 1.4280198934798998e-07, Loss: 0.07823656499385834
2024-08-05T02:38:17.404138535Z 
 74%|███████▍  | 4244/5712 [10:00:08<3:29:19,  8.56s/it]08/04/2024 19:38:17 - INFO - __main__ -   Step: 4244, LR: 1.4270471071767308e-07, Loss: 0.09479133039712906
2024-08-05T02:38:25.383725502Z 
 74%|███████▍  | 4245/5712 [10:00:16<3:24:57,  8.38s/it]08/04/2024 19:38:25 - INFO - __main__ -   Step: 4245, LR: 1.426074320873562e-07, Loss: 0.07326094061136246
2024-08-05T02:38:34.038071108Z 
 74%|███████▍  | 4246/5712 [10:00:25<3:26:48,  8.46s/it]08/04/2024 19:38:34 - INFO - __main__ -   Step: 4246, LR: 1.425101534570393e-07, Loss: 0.04672396928071976
2024-08-05T02:38:42.574176305Z 
 74%|███████▍  | 4247/5712 [10:00:33<3:27:11,  8.49s/it]08/04/2024 19:38:42 - INFO - __main__ -   Step: 4247, LR: 1.4241287482672243e-07, Loss: 0.09321531653404236
2024-08-05T02:38:50.979598836Z 
 74%|███████▍  | 4248/5712 [10:00:42<3:26:27,  8.46s/it]08/04/2024 19:38:50 - INFO - __main__ -   Step: 4248, LR: 1.4231559619640553e-07, Loss: 0.05698401853442192
2024-08-05T02:38:58.969212378Z 
 74%|███████▍  | 4249/5712 [10:00:50<3:22:52,  8.32s/it]08/04/2024 19:38:58 - INFO - __main__ -   Step: 4249, LR: 1.4221831756608866e-07, Loss: 0.039404742419719696
2024-08-05T02:39:07.022216745Z 
 74%|███████▍  | 4250/5712 [10:00:58<3:20:46,  8.24s/it]08/04/2024 19:39:07 - INFO - __main__ -   Step: 4250, LR: 1.4212103893577176e-07, Loss: 0.07422482967376709
2024-08-05T02:39:15.612716597Z 
 74%|███████▍  | 4251/5712 [10:01:06<3:23:12,  8.35s/it]08/04/2024 19:39:15 - INFO - __main__ -   Step: 4251, LR: 1.420237603054549e-07, Loss: 0.13075117766857147
2024-08-05T02:39:23.992237207Z 
 74%|███████▍  | 4252/5712 [10:01:15<3:23:19,  8.36s/it]08/04/2024 19:39:23 - INFO - __main__ -   Step: 4252, LR: 1.41926481675138e-07, Loss: 0.061613306403160095
2024-08-05T02:39:32.118842587Z 
 74%|███████▍  | 4253/5712 [10:01:23<3:21:30,  8.29s/it]08/04/2024 19:39:32 - INFO - __main__ -   Step: 4253, LR: 1.4182920304482113e-07, Loss: 0.06640958040952682
2024-08-05T02:39:40.366939341Z 
 74%|███████▍  | 4254/5712 [10:01:31<3:21:05,  8.28s/it]08/04/2024 19:39:40 - INFO - __main__ -   Step: 4254, LR: 1.4173192441450423e-07, Loss: 0.0545944944024086
2024-08-05T02:39:49.220074874Z 
 74%|███████▍  | 4255/5712 [10:01:40<3:25:09,  8.45s/it]08/04/2024 19:39:49 - INFO - __main__ -   Step: 4255, LR: 1.4163464578418736e-07, Loss: 0.03107638657093048
2024-08-05T02:39:58.506084429Z 
 75%|███████▍  | 4256/5712 [10:01:49<3:31:06,  8.70s/it]08/04/2024 19:39:58 - INFO - __main__ -   Step: 4256, LR: 1.4153736715387046e-07, Loss: 0.03270315006375313
2024-08-05T02:40:06.075343156Z 
 75%|███████▍  | 4257/5712 [10:01:57<3:22:44,  8.36s/it]08/04/2024 19:40:06 - INFO - __main__ -   Step: 4257, LR: 1.4144008852355358e-07, Loss: 0.08793798089027405
2024-08-05T02:40:14.738081779Z 
 75%|███████▍  | 4258/5712 [10:02:05<3:24:48,  8.45s/it]08/04/2024 19:40:14 - INFO - __main__ -   Step: 4258, LR: 1.4134280989323668e-07, Loss: 0.06880179047584534
2024-08-05T02:40:22.912969545Z 
 75%|███████▍  | 4259/5712 [10:02:14<3:22:39,  8.37s/it]08/04/2024 19:40:22 - INFO - __main__ -   Step: 4259, LR: 1.412455312629198e-07, Loss: 0.1466355323791504
2024-08-05T02:40:31.783369887Z 
 75%|███████▍  | 4260/5712 [10:02:22<3:26:09,  8.52s/it]08/04/2024 19:40:31 - INFO - __main__ -   Step: 4260, LR: 1.4114825263260293e-07, Loss: 0.06667129695415497
2024-08-05T02:40:39.855993464Z 
 75%|███████▍  | 4261/5712 [10:02:31<3:22:46,  8.38s/it]08/04/2024 19:40:39 - INFO - __main__ -   Step: 4261, LR: 1.4105097400228606e-07, Loss: 0.0661543756723404
2024-08-05T02:40:47.827743890Z 
 75%|███████▍  | 4262/5712 [10:02:38<3:19:38,  8.26s/it]08/04/2024 19:40:47 - INFO - __main__ -   Step: 4262, LR: 1.4095369537196916e-07, Loss: 0.08603809028863907
2024-08-05T02:40:56.199538651Z 
 75%|███████▍  | 4263/5712 [10:02:47<3:20:18,  8.29s/it]08/04/2024 19:40:56 - INFO - __main__ -   Step: 4263, LR: 1.4085641674165228e-07, Loss: 0.09118783473968506
2024-08-05T02:41:05.007768448Z 
 75%|███████▍  | 4264/5712 [10:02:56<3:23:53,  8.45s/it]08/04/2024 19:41:05 - INFO - __main__ -   Step: 4264, LR: 1.4075913811133538e-07, Loss: 0.15844565629959106
2024-08-05T02:41:13.328726787Z 
 75%|███████▍  | 4265/5712 [10:03:04<3:22:49,  8.41s/it]08/04/2024 19:41:13 - INFO - __main__ -   Step: 4265, LR: 1.406618594810185e-07, Loss: 0.044867053627967834
2024-08-05T02:41:21.793644601Z 
 75%|███████▍  | 4266/5712 [10:03:12<3:23:04,  8.43s/it]08/04/2024 19:41:21 - INFO - __main__ -   Step: 4266, LR: 1.405645808507016e-07, Loss: 0.0988273173570633
2024-08-05T02:41:30.026010372Z 
 75%|███████▍  | 4267/5712 [10:03:21<3:21:32,  8.37s/it]08/04/2024 19:41:30 - INFO - __main__ -   Step: 4267, LR: 1.4046730222038473e-07, Loss: 0.07715660333633423
2024-08-05T02:41:38.212035223Z 
 75%|███████▍  | 4268/5712 [10:03:29<3:20:04,  8.31s/it]08/04/2024 19:41:38 - INFO - __main__ -   Step: 4268, LR: 1.4037002359006783e-07, Loss: 0.06757186353206635
2024-08-05T02:41:46.371222244Z 
 75%|███████▍  | 4269/5712 [10:03:37<3:18:49,  8.27s/it]08/04/2024 19:41:46 - INFO - __main__ -   Step: 4269, LR: 1.4027274495975098e-07, Loss: 0.06150789558887482
2024-08-05T02:41:54.411683061Z 
 75%|███████▍  | 4270/5712 [10:03:45<3:17:03,  8.20s/it]08/04/2024 19:41:54 - INFO - __main__ -   Step: 4270, LR: 1.4017546632943408e-07, Loss: 0.07002714276313782
2024-08-05T02:42:02.926643739Z 
 75%|███████▍  | 4271/5712 [10:03:54<3:19:11,  8.29s/it]08/04/2024 19:42:02 - INFO - __main__ -   Step: 4271, LR: 1.400781876991172e-07, Loss: 0.09290096163749695
2024-08-05T02:42:11.313394855Z 
 75%|███████▍  | 4272/5712 [10:04:02<3:19:43,  8.32s/it]08/04/2024 19:42:11 - INFO - __main__ -   Step: 4272, LR: 1.399809090688003e-07, Loss: 0.06696252524852753
2024-08-05T02:42:20.222819143Z 
 75%|███████▍  | 4273/5712 [10:04:11<3:23:48,  8.50s/it]08/04/2024 19:42:20 - INFO - __main__ -   Step: 4273, LR: 1.3988363043848343e-07, Loss: 0.07868551462888718
2024-08-05T02:42:28.514886749Z 
 75%|███████▍  | 4274/5712 [10:04:19<3:22:11,  8.44s/it]08/04/2024 19:42:28 - INFO - __main__ -   Step: 4274, LR: 1.3978635180816653e-07, Loss: 0.05582936108112335
2024-08-05T02:42:36.798272416Z 
 75%|███████▍  | 4275/5712 [10:04:27<3:20:57,  8.39s/it]08/04/2024 19:42:36 - INFO - __main__ -   Step: 4275, LR: 1.3968907317784963e-07, Loss: 0.10585092008113861
2024-08-05T02:42:45.437627608Z 
 75%|███████▍  | 4276/5712 [10:04:36<3:22:35,  8.47s/it]08/04/2024 19:42:45 - INFO - __main__ -   Step: 4276, LR: 1.3959179454753276e-07, Loss: 0.043928809463977814
2024-08-05T02:42:54.112715631Z 
 75%|███████▍  | 4277/5712 [10:04:45<3:23:57,  8.53s/it]08/04/2024 19:42:54 - INFO - __main__ -   Step: 4277, LR: 1.3949451591721585e-07, Loss: 0.10674084722995758
2024-08-05T02:43:02.167331829Z 
 75%|███████▍  | 4278/5712 [10:04:53<3:20:25,  8.39s/it]08/04/2024 19:43:02 - INFO - __main__ -   Step: 4278, LR: 1.39397237286899e-07, Loss: 0.07396379858255386
2024-08-05T02:43:10.873139048Z 
 75%|███████▍  | 4279/5712 [10:05:02<3:22:34,  8.48s/it]08/04/2024 19:43:10 - INFO - __main__ -   Step: 4279, LR: 1.392999586565821e-07, Loss: 0.10798481106758118
2024-08-05T02:43:19.939208331Z 
 75%|███████▍  | 4280/5712 [10:05:11<3:26:36,  8.66s/it]08/04/2024 19:43:19 - INFO - __main__ -   Step: 4280, LR: 1.3920268002626523e-07, Loss: 0.07291959971189499
2024-08-05T02:43:28.228586273Z 
 75%|███████▍  | 4281/5712 [10:05:19<3:23:50,  8.55s/it]08/04/2024 19:43:28 - INFO - __main__ -   Step: 4281, LR: 1.3910540139594833e-07, Loss: 0.0728028267621994
2024-08-05T02:43:36.756897838Z 
 75%|███████▍  | 4282/5712 [10:05:27<3:23:34,  8.54s/it]08/04/2024 19:43:36 - INFO - __main__ -   Step: 4282, LR: 1.3900812276563146e-07, Loss: 0.05006762966513634
2024-08-05T02:43:45.026680048Z 
 75%|███████▍  | 4283/5712 [10:05:36<3:21:29,  8.46s/it]08/04/2024 19:43:45 - INFO - __main__ -   Step: 4283, LR: 1.3891084413531455e-07, Loss: 0.06672710180282593
2024-08-05T02:43:53.039886428Z 
 75%|███████▌  | 4284/5712 [10:05:44<3:18:09,  8.33s/it]08/04/2024 19:43:53 - INFO - __main__ -   Step: 4284, LR: 1.3881356550499768e-07, Loss: 0.09199653565883636
2024-08-05T02:44:01.422780707Z 
 75%|███████▌  | 4285/5712 [10:05:52<3:18:25,  8.34s/it]08/04/2024 19:44:01 - INFO - __main__ -   Step: 4285, LR: 1.3871628687468078e-07, Loss: 0.059463221579790115
2024-08-05T02:44:09.602050143Z 
 75%|███████▌  | 4286/5712 [10:06:00<3:17:07,  8.29s/it]08/04/2024 19:44:09 - INFO - __main__ -   Step: 4286, LR: 1.386190082443639e-07, Loss: 0.11954803764820099
2024-08-05T02:44:17.662027384Z 
 75%|███████▌  | 4287/5712 [10:06:08<3:15:18,  8.22s/it]08/04/2024 19:44:17 - INFO - __main__ -   Step: 4287, LR: 1.3852172961404703e-07, Loss: 0.10567480325698853
2024-08-05T02:44:26.241393099Z 
 75%|███████▌  | 4288/5712 [10:06:17<3:17:42,  8.33s/it]08/04/2024 19:44:26 - INFO - __main__ -   Step: 4288, LR: 1.3842445098373016e-07, Loss: 0.07554788887500763
2024-08-05T02:44:34.658256174Z 
 75%|███████▌  | 4289/5712 [10:06:25<3:18:10,  8.36s/it]08/04/2024 19:44:34 - INFO - __main__ -   Step: 4289, LR: 1.3832717235341325e-07, Loss: 0.06988780945539474
2024-08-05T02:44:43.078198848Z 
 75%|███████▌  | 4290/5712 [10:06:34<3:18:29,  8.38s/it]08/04/2024 19:44:43 - INFO - __main__ -   Step: 4290, LR: 1.3822989372309638e-07, Loss: 0.06095121428370476
2024-08-05T02:44:51.643620422Z 
 75%|███████▌  | 4291/5712 [10:06:42<3:19:42,  8.43s/it]08/04/2024 19:44:51 - INFO - __main__ -   Step: 4291, LR: 1.3813261509277948e-07, Loss: 0.10196898877620697
2024-08-05T02:44:59.832106761Z 
 75%|███████▌  | 4292/5712 [10:06:50<3:17:50,  8.36s/it]08/04/2024 19:44:59 - INFO - __main__ -   Step: 4292, LR: 1.380353364624626e-07, Loss: 0.08512122184038162
2024-08-05T02:45:08.644535654Z 
 75%|███████▌  | 4293/5712 [10:06:59<3:20:54,  8.50s/it]08/04/2024 19:45:08 - INFO - __main__ -   Step: 4293, LR: 1.379380578321457e-07, Loss: 0.05580785870552063
2024-08-05T02:45:17.007643477Z 
 75%|███████▌  | 4294/5712 [10:07:08<3:19:49,  8.46s/it]08/04/2024 19:45:17 - INFO - __main__ -   Step: 4294, LR: 1.3784077920182883e-07, Loss: 0.07541973888874054
2024-08-05T02:45:25.385003898Z 
 75%|███████▌  | 4295/5712 [10:07:16<3:19:08,  8.43s/it]08/04/2024 19:45:25 - INFO - __main__ -   Step: 4295, LR: 1.3774350057151193e-07, Loss: 0.04509664326906204
2024-08-05T02:45:33.879408969Z 
 75%|███████▌  | 4296/5712 [10:07:25<3:19:26,  8.45s/it]08/04/2024 19:45:33 - INFO - __main__ -   Step: 4296, LR: 1.3764622194119508e-07, Loss: 0.06199236959218979
2024-08-05T02:45:43.060714659Z 
 75%|███████▌  | 4297/5712 [10:07:34<3:24:28,  8.67s/it]08/04/2024 19:45:43 - INFO - __main__ -   Step: 4297, LR: 1.3754894331087818e-07, Loss: 0.07644354552030563
2024-08-05T02:45:51.233755046Z 
 75%|███████▌  | 4298/5712 [10:07:42<3:20:48,  8.52s/it]08/04/2024 19:45:51 - INFO - __main__ -   Step: 4298, LR: 1.374516646805613e-07, Loss: 0.07589446753263474
2024-08-05T02:45:59.429731643Z 
 75%|███████▌  | 4299/5712 [10:07:50<3:18:22,  8.42s/it]08/04/2024 19:45:59 - INFO - __main__ -   Step: 4299, LR: 1.373543860502444e-07, Loss: 0.05716720223426819
2024-08-05T02:46:07.789495721Z 
 75%|███████▌  | 4300/5712 [10:07:58<3:17:46,  8.40s/it]08/04/2024 19:46:07 - INFO - __main__ -   Step: 4300, LR: 1.3725710741992753e-07, Loss: 0.07795263826847076
2024-08-05T02:46:16.263373052Z 
 75%|███████▌  | 4301/5712 [10:08:07<3:18:07,  8.43s/it]08/04/2024 19:46:16 - INFO - __main__ -   Step: 4301, LR: 1.3715982878961063e-07, Loss: 0.04827257990837097
2024-08-05T02:46:24.143193963Z 
 75%|███████▌  | 4302/5712 [10:08:15<3:14:08,  8.26s/it]08/04/2024 19:46:24 - INFO - __main__ -   Step: 4302, LR: 1.3706255015929375e-07, Loss: 0.056383997201919556
2024-08-05T02:46:33.020169356Z 
 75%|███████▌  | 4303/5712 [10:08:24<3:18:20,  8.45s/it]08/04/2024 19:46:33 - INFO - __main__ -   Step: 4303, LR: 1.3696527152897685e-07, Loss: 0.06854332238435745
2024-08-05T02:46:42.159138812Z 
 75%|███████▌  | 4304/5712 [10:08:33<3:23:04,  8.65s/it]08/04/2024 19:46:42 - INFO - __main__ -   Step: 4304, LR: 1.3686799289865998e-07, Loss: 0.062221676111221313
2024-08-05T02:46:51.186272452Z 
 75%|███████▌  | 4305/5712 [10:08:42<3:25:33,  8.77s/it]08/04/2024 19:46:51 - INFO - __main__ -   Step: 4305, LR: 1.367707142683431e-07, Loss: 0.07412342727184296
2024-08-05T02:46:59.775720347Z 
 75%|███████▌  | 4306/5712 [10:08:50<3:24:10,  8.71s/it]08/04/2024 19:46:59 - INFO - __main__ -   Step: 4306, LR: 1.3667343563802623e-07, Loss: 0.055174700915813446
2024-08-05T02:47:08.557726087Z 
 75%|███████▌  | 4307/5712 [10:08:59<3:24:30,  8.73s/it]08/04/2024 19:47:08 - INFO - __main__ -   Step: 4307, LR: 1.3657615700770933e-07, Loss: 0.054763779044151306
2024-08-05T02:47:17.248117171Z 
 75%|███████▌  | 4308/5712 [10:09:08<3:24:04,  8.72s/it]08/04/2024 19:47:17 - INFO - __main__ -   Step: 4308, LR: 1.3647887837739245e-07, Loss: 0.06888693571090698
2024-08-05T02:47:25.797016836Z 
 75%|███████▌  | 4309/5712 [10:09:16<3:22:42,  8.67s/it]08/04/2024 19:47:25 - INFO - __main__ -   Step: 4309, LR: 1.3638159974707555e-07, Loss: 0.06082497909665108
2024-08-05T02:47:33.960529965Z 
 75%|███████▌  | 4310/5712 [10:09:25<3:19:01,  8.52s/it]08/04/2024 19:47:33 - INFO - __main__ -   Step: 4310, LR: 1.3628432111675868e-07, Loss: 0.08703502267599106
2024-08-05T02:47:42.944113618Z 
 75%|███████▌  | 4311/5712 [10:09:34<3:22:09,  8.66s/it]08/04/2024 19:47:42 - INFO - __main__ -   Step: 4311, LR: 1.3618704248644178e-07, Loss: 0.05850914865732193
2024-08-05T02:47:51.557909528Z 
 75%|███████▌  | 4312/5712 [10:09:42<3:21:41,  8.64s/it]08/04/2024 19:47:51 - INFO - __main__ -   Step: 4312, LR: 1.3608976385612488e-07, Loss: 0.04226919636130333
2024-08-05T02:48:00.992010936Z 
 76%|███████▌  | 4313/5712 [10:09:52<3:27:04,  8.88s/it]08/04/2024 19:48:00 - INFO - __main__ -   Step: 4313, LR: 1.35992485225808e-07, Loss: 0.07441911101341248
2024-08-05T02:48:09.619872692Z 
 76%|███████▌  | 4314/5712 [10:10:00<3:25:09,  8.81s/it]08/04/2024 19:48:09 - INFO - __main__ -   Step: 4314, LR: 1.3589520659549113e-07, Loss: 0.07514262944459915
2024-08-05T02:48:18.119637725Z 
 76%|███████▌  | 4315/5712 [10:10:09<3:22:52,  8.71s/it]08/04/2024 19:48:18 - INFO - __main__ -   Step: 4315, LR: 1.3579792796517425e-07, Loss: 0.0750042274594307
2024-08-05T02:48:26.504428393Z 
 76%|███████▌  | 4316/5712 [10:10:17<3:20:26,  8.61s/it]08/04/2024 19:48:26 - INFO - __main__ -   Step: 4316, LR: 1.3570064933485735e-07, Loss: 0.06317049264907837
2024-08-05T02:48:34.622482316Z 
 76%|███████▌  | 4317/5712 [10:10:25<3:16:50,  8.47s/it]08/04/2024 19:48:34 - INFO - __main__ -   Step: 4317, LR: 1.3560337070454048e-07, Loss: 0.09062118828296661
2024-08-05T02:48:43.139077967Z 
 76%|███████▌  | 4318/5712 [10:10:34<3:17:02,  8.48s/it]08/04/2024 19:48:43 - INFO - __main__ -   Step: 4318, LR: 1.3550609207422358e-07, Loss: 0.08244580030441284
2024-08-05T02:48:51.143406312Z 
 76%|███████▌  | 4319/5712 [10:10:42<3:13:34,  8.34s/it]08/04/2024 19:48:51 - INFO - __main__ -   Step: 4319, LR: 1.354088134439067e-07, Loss: 0.020196329802274704
2024-08-05T02:48:59.419935555Z 
 76%|███████▌  | 4320/5712 [10:10:50<3:13:00,  8.32s/it]08/04/2024 19:48:59 - INFO - __main__ -   Step: 4320, LR: 1.353115348135898e-07, Loss: 0.06265292316675186
2024-08-05T02:49:07.753752204Z 
 76%|███████▌  | 4321/5712 [10:10:58<3:12:58,  8.32s/it]08/04/2024 19:49:07 - INFO - __main__ -   Step: 4321, LR: 1.3521425618327293e-07, Loss: 0.09194433689117432
2024-08-05T02:49:16.467184684Z 
 76%|███████▌  | 4322/5712 [10:11:07<3:15:32,  8.44s/it]08/04/2024 19:49:16 - INFO - __main__ -   Step: 4322, LR: 1.3511697755295603e-07, Loss: 0.0914146900177002
2024-08-05T02:49:24.606838390Z 
 76%|███████▌  | 4323/5712 [10:11:15<3:13:18,  8.35s/it]08/04/2024 19:49:24 - INFO - __main__ -   Step: 4323, LR: 1.3501969892263918e-07, Loss: 0.04661642014980316
2024-08-05T02:49:33.524757277Z 
 76%|███████▌  | 4324/5712 [10:11:24<3:17:06,  8.52s/it]08/04/2024 19:49:33 - INFO - __main__ -   Step: 4324, LR: 1.3492242029232228e-07, Loss: 0.054909057915210724
2024-08-05T02:49:41.946014852Z 
 76%|███████▌  | 4325/5712 [10:11:33<3:16:16,  8.49s/it]08/04/2024 19:49:41 - INFO - __main__ -   Step: 4325, LR: 1.348251416620054e-07, Loss: 0.04211491346359253
2024-08-05T02:49:50.210715797Z 
 76%|███████▌  | 4326/5712 [10:11:41<3:14:34,  8.42s/it]08/04/2024 19:49:50 - INFO - __main__ -   Step: 4326, LR: 1.347278630316885e-07, Loss: 0.06807604432106018
2024-08-05T02:49:58.078737364Z 
 76%|███████▌  | 4327/5712 [10:11:49<3:10:35,  8.26s/it]08/04/2024 19:49:58 - INFO - __main__ -   Step: 4327, LR: 1.3463058440137163e-07, Loss: 0.10932989418506622
2024-08-05T02:50:06.892465339Z 
 76%|███████▌  | 4328/5712 [10:11:58<3:14:18,  8.42s/it]08/04/2024 19:50:06 - INFO - __main__ -   Step: 4328, LR: 1.3453330577105473e-07, Loss: 0.054523102939128876
2024-08-05T02:50:15.360449088Z 
 76%|███████▌  | 4329/5712 [10:12:06<3:14:28,  8.44s/it]08/04/2024 19:50:15 - INFO - __main__ -   Step: 4329, LR: 1.3443602714073785e-07, Loss: 0.0912315621972084
2024-08-05T02:50:23.807996780Z 
 76%|███████▌  | 4330/5712 [10:12:14<3:14:24,  8.44s/it]08/04/2024 19:50:23 - INFO - __main__ -   Step: 4330, LR: 1.3433874851042095e-07, Loss: 0.09914363920688629
2024-08-05T02:50:32.155331030Z 
 76%|███████▌  | 4331/5712 [10:12:23<3:13:37,  8.41s/it]08/04/2024 19:50:32 - INFO - __main__ -   Step: 4331, LR: 1.3424146988010408e-07, Loss: 0.05840621143579483
2024-08-05T02:50:40.537783485Z 
 76%|███████▌  | 4332/5712 [10:12:31<3:13:16,  8.40s/it]08/04/2024 19:50:40 - INFO - __main__ -   Step: 4332, LR: 1.341441912497872e-07, Loss: 0.06551125645637512
2024-08-05T02:50:48.692048017Z 
 76%|███████▌  | 4333/5712 [10:12:39<3:11:25,  8.33s/it]08/04/2024 19:50:48 - INFO - __main__ -   Step: 4333, LR: 1.3404691261947033e-07, Loss: 0.05117170140147209
2024-08-05T02:50:57.162214771Z 
 76%|███████▌  | 4334/5712 [10:12:48<3:12:15,  8.37s/it]08/04/2024 19:50:57 - INFO - __main__ -   Step: 4334, LR: 1.3394963398915343e-07, Loss: 0.07715222239494324
2024-08-05T02:51:05.120825867Z 
 76%|███████▌  | 4335/5712 [10:12:56<3:09:16,  8.25s/it]08/04/2024 19:51:05 - INFO - __main__ -   Step: 4335, LR: 1.3385235535883655e-07, Loss: 0.06393895298242569
2024-08-05T02:51:13.422191834Z 
 76%|███████▌  | 4336/5712 [10:13:04<3:09:30,  8.26s/it]08/04/2024 19:51:13 - INFO - __main__ -   Step: 4336, LR: 1.3375507672851965e-07, Loss: 0.08827973902225494
2024-08-05T02:51:21.876397036Z 
 76%|███████▌  | 4337/5712 [10:13:13<3:10:41,  8.32s/it]08/04/2024 19:51:21 - INFO - __main__ -   Step: 4337, LR: 1.3365779809820278e-07, Loss: 0.08946067094802856
2024-08-05T02:51:30.360074136Z 
 76%|███████▌  | 4338/5712 [10:13:21<3:11:39,  8.37s/it]08/04/2024 19:51:30 - INFO - __main__ -   Step: 4338, LR: 1.3356051946788588e-07, Loss: 0.1440192461013794
2024-08-05T02:51:38.627864511Z 
 76%|███████▌  | 4339/5712 [10:13:29<3:10:49,  8.34s/it]08/04/2024 19:51:38 - INFO - __main__ -   Step: 4339, LR: 1.33463240837569e-07, Loss: 0.119038425385952
2024-08-05T02:51:47.168787828Z 
 76%|███████▌  | 4340/5712 [10:13:38<3:12:04,  8.40s/it]08/04/2024 19:51:47 - INFO - __main__ -   Step: 4340, LR: 1.333659622072521e-07, Loss: 0.0671364814043045
2024-08-05T02:51:55.851044972Z 
 76%|███████▌  | 4341/5712 [10:13:46<3:13:51,  8.48s/it]08/04/2024 19:51:55 - INFO - __main__ -   Step: 4341, LR: 1.3326868357693525e-07, Loss: 0.04225064441561699
2024-08-05T02:52:04.243605561Z 
 76%|███████▌  | 4342/5712 [10:13:55<3:13:06,  8.46s/it]08/04/2024 19:52:04 - INFO - __main__ -   Step: 4342, LR: 1.3317140494661835e-07, Loss: 0.12588976323604584
2024-08-05T02:52:12.250323397Z 
 76%|███████▌  | 4343/5712 [10:14:03<3:09:52,  8.32s/it]08/04/2024 19:52:12 - INFO - __main__ -   Step: 4343, LR: 1.3307412631630148e-07, Loss: 0.1151566207408905
2024-08-05T02:52:20.460474185Z 
 76%|███████▌  | 4344/5712 [10:14:11<3:08:58,  8.29s/it]08/04/2024 19:52:20 - INFO - __main__ -   Step: 4344, LR: 1.3297684768598458e-07, Loss: 0.07247865200042725
2024-08-05T02:52:29.389751244Z 
 76%|███████▌  | 4345/5712 [10:14:20<3:13:13,  8.48s/it]08/04/2024 19:52:29 - INFO - __main__ -   Step: 4345, LR: 1.328795690556677e-07, Loss: 0.08122970163822174
2024-08-05T02:52:38.170459699Z 
 76%|███████▌  | 4346/5712 [10:14:29<3:15:07,  8.57s/it]08/04/2024 19:52:38 - INFO - __main__ -   Step: 4346, LR: 1.327822904253508e-07, Loss: 0.057036492973566055
2024-08-05T02:52:46.333856743Z 
 76%|███████▌  | 4347/5712 [10:14:37<3:12:12,  8.45s/it]08/04/2024 19:52:46 - INFO - __main__ -   Step: 4347, LR: 1.3268501179503393e-07, Loss: 0.07933247089385986
2024-08-05T02:52:55.193330430Z 
 76%|███████▌  | 4348/5712 [10:14:46<3:14:51,  8.57s/it]08/04/2024 19:52:55 - INFO - __main__ -   Step: 4348, LR: 1.3258773316471702e-07, Loss: 0.05037201941013336
2024-08-05T02:53:03.710538159Z 
 76%|███████▌  | 4349/5712 [10:14:54<3:14:20,  8.56s/it]08/04/2024 19:53:03 - INFO - __main__ -   Step: 4349, LR: 1.3249045453440012e-07, Loss: 0.05702804774045944
2024-08-05T02:53:12.160488928Z 
 76%|███████▌  | 4350/5712 [10:15:03<3:13:28,  8.52s/it]08/04/2024 19:53:12 - INFO - __main__ -   Step: 4350, LR: 1.3239317590408328e-07, Loss: 0.10657448321580887
2024-08-05T02:53:20.508792633Z 
 76%|███████▌  | 4351/5712 [10:15:11<3:12:09,  8.47s/it]08/04/2024 19:53:20 - INFO - __main__ -   Step: 4351, LR: 1.322958972737664e-07, Loss: 0.07427924126386642
2024-08-05T02:53:27.971202027Z 
 76%|███████▌  | 4352/5712 [10:15:19<3:05:09,  8.17s/it]08/04/2024 19:53:27 - INFO - __main__ -   Step: 4352, LR: 1.321986186434495e-07, Loss: 0.10869920253753662
2024-08-05T02:53:36.578331928Z 
 76%|███████▌  | 4353/5712 [10:15:27<3:07:59,  8.30s/it]08/04/2024 19:53:36 - INFO - __main__ -   Step: 4353, LR: 1.321013400131326e-07, Loss: 0.05934879183769226
2024-08-05T02:53:45.479620072Z 
 76%|███████▌  | 4354/5712 [10:15:36<3:11:56,  8.48s/it]08/04/2024 19:53:45 - INFO - __main__ -   Step: 4354, LR: 1.3200406138281572e-07, Loss: 0.04978162795305252
2024-08-05T02:53:53.716608428Z 
 76%|███████▌  | 4355/5712 [10:15:44<3:10:08,  8.41s/it]08/04/2024 19:53:53 - INFO - __main__ -   Step: 4355, LR: 1.3190678275249882e-07, Loss: 0.06512726843357086
2024-08-05T02:54:02.001428968Z 
 76%|███████▋  | 4356/5712 [10:15:53<3:09:10,  8.37s/it]08/04/2024 19:54:02 - INFO - __main__ -   Step: 4356, LR: 1.3180950412218195e-07, Loss: 0.08739002048969269
2024-08-05T02:54:10.192847137Z 
 76%|███████▋  | 4357/5712 [10:16:01<3:07:49,  8.32s/it]08/04/2024 19:54:10 - INFO - __main__ -   Step: 4357, LR: 1.3171222549186505e-07, Loss: 0.11093899607658386
2024-08-05T02:54:18.700863503Z 
 76%|███████▋  | 4358/5712 [10:16:09<3:08:58,  8.37s/it]08/04/2024 19:54:18 - INFO - __main__ -   Step: 4358, LR: 1.3161494686154817e-07, Loss: 0.058166928589344025
2024-08-05T02:54:26.787709055Z 
 76%|███████▋  | 4359/5712 [10:16:17<3:06:53,  8.29s/it]08/04/2024 19:54:26 - INFO - __main__ -   Step: 4359, LR: 1.315176682312313e-07, Loss: 0.06601220369338989
2024-08-05T02:54:34.808918072Z 
 76%|███████▋  | 4360/5712 [10:16:25<3:04:57,  8.21s/it]08/04/2024 19:54:34 - INFO - __main__ -   Step: 4360, LR: 1.3142038960091443e-07, Loss: 0.034228529781103134
2024-08-05T02:54:42.951658637Z 
 76%|███████▋  | 4361/5712 [10:16:34<3:04:22,  8.19s/it]08/04/2024 19:54:42 - INFO - __main__ -   Step: 4361, LR: 1.3132311097059752e-07, Loss: 0.0906192809343338
2024-08-05T02:54:52.130469929Z 
 76%|███████▋  | 4362/5712 [10:16:43<3:10:55,  8.49s/it]08/04/2024 19:54:52 - INFO - __main__ -   Step: 4362, LR: 1.3122583234028065e-07, Loss: 0.12758216261863708
2024-08-05T02:55:00.720342632Z 
 76%|███████▋  | 4363/5712 [10:16:51<3:11:29,  8.52s/it]08/04/2024 19:55:00 - INFO - __main__ -   Step: 4363, LR: 1.3112855370996375e-07, Loss: 0.08297412097454071
2024-08-05T02:55:08.752808646Z 
 76%|███████▋  | 4364/5712 [10:16:59<3:08:04,  8.37s/it]08/04/2024 19:55:08 - INFO - __main__ -   Step: 4364, LR: 1.3103127507964687e-07, Loss: 0.06598779559135437
2024-08-05T02:55:17.212464709Z 
 76%|███████▋  | 4365/5712 [10:17:08<3:08:32,  8.40s/it]08/04/2024 19:55:17 - INFO - __main__ -   Step: 4365, LR: 1.3093399644932997e-07, Loss: 0.04596903920173645
2024-08-05T02:55:25.688065590Z 
 76%|███████▋  | 4366/5712 [10:17:16<3:08:54,  8.42s/it]08/04/2024 19:55:25 - INFO - __main__ -   Step: 4366, LR: 1.308367178190131e-07, Loss: 0.04158715903759003
2024-08-05T02:55:33.706074588Z 
 76%|███████▋  | 4367/5712 [10:17:24<3:06:03,  8.30s/it]08/04/2024 19:55:33 - INFO - __main__ -   Step: 4367, LR: 1.307394391886962e-07, Loss: 0.06881935149431229
2024-08-05T02:55:42.067279738Z 
 76%|███████▋  | 4368/5712 [10:17:33<3:06:20,  8.32s/it]08/04/2024 19:55:42 - INFO - __main__ -   Step: 4368, LR: 1.3064216055837935e-07, Loss: 0.09461504220962524
2024-08-05T02:55:50.001145177Z 
 76%|███████▋  | 4369/5712 [10:17:41<3:03:36,  8.20s/it]08/04/2024 19:55:50 - INFO - __main__ -   Step: 4369, LR: 1.3054488192806245e-07, Loss: 0.07891116291284561
2024-08-05T02:55:58.722891576Z 
 77%|███████▋  | 4370/5712 [10:17:49<3:06:57,  8.36s/it]08/04/2024 19:55:58 - INFO - __main__ -   Step: 4370, LR: 1.3044760329774557e-07, Loss: 0.05808644741773605
2024-08-05T02:56:07.133167450Z 
 77%|███████▋  | 4371/5712 [10:17:58<3:07:09,  8.37s/it]08/04/2024 19:56:07 - INFO - __main__ -   Step: 4371, LR: 1.3035032466742867e-07, Loss: 0.047269780188798904
2024-08-05T02:56:15.176005766Z 
 77%|███████▋  | 4372/5712 [10:18:06<3:04:48,  8.27s/it]08/04/2024 19:56:15 - INFO - __main__ -   Step: 4372, LR: 1.302530460371118e-07, Loss: 0.10515701770782471
2024-08-05T02:56:23.628663865Z 
 77%|███████▋  | 4373/5712 [10:18:14<3:05:51,  8.33s/it]08/04/2024 19:56:23 - INFO - __main__ -   Step: 4373, LR: 1.301557674067949e-07, Loss: 0.11302536725997925
2024-08-05T02:56:31.991232557Z 
 77%|███████▋  | 4374/5712 [10:18:23<3:05:56,  8.34s/it]08/04/2024 19:56:31 - INFO - __main__ -   Step: 4374, LR: 1.3005848877647802e-07, Loss: 0.07935823500156403
2024-08-05T02:56:40.162813387Z 
 77%|███████▋  | 4375/5712 [10:18:31<3:04:41,  8.29s/it]08/04/2024 19:56:40 - INFO - __main__ -   Step: 4375, LR: 1.2996121014616112e-07, Loss: 0.08534408360719681
2024-08-05T02:56:48.229277572Z 
 77%|███████▋  | 4376/5712 [10:18:39<3:03:04,  8.22s/it]08/04/2024 19:56:48 - INFO - __main__ -   Step: 4376, LR: 1.2986393151584425e-07, Loss: 0.07593412697315216
2024-08-05T02:56:56.593306076Z 
 77%|███████▋  | 4377/5712 [10:18:47<3:03:53,  8.26s/it]08/04/2024 19:56:56 - INFO - __main__ -   Step: 4377, LR: 1.2976665288552737e-07, Loss: 0.1451304405927658
2024-08-05T02:57:04.785549432Z 
 77%|███████▋  | 4378/5712 [10:18:55<3:03:15,  8.24s/it]08/04/2024 19:57:04 - INFO - __main__ -   Step: 4378, LR: 1.296693742552105e-07, Loss: 0.11827416718006134
2024-08-05T02:57:13.980759639Z 
 77%|███████▋  | 4379/5712 [10:19:05<3:09:28,  8.53s/it]08/04/2024 19:57:13 - INFO - __main__ -   Step: 4379, LR: 1.295720956248936e-07, Loss: 0.0640278309583664
2024-08-05T02:57:22.289155567Z 
 77%|███████▋  | 4380/5712 [10:19:13<3:07:52,  8.46s/it]08/04/2024 19:57:22 - INFO - __main__ -   Step: 4380, LR: 1.2947481699457672e-07, Loss: 0.04064692556858063
2024-08-05T02:57:30.413312617Z 
 77%|███████▋  | 4381/5712 [10:19:21<3:05:28,  8.36s/it]08/04/2024 19:57:30 - INFO - __main__ -   Step: 4381, LR: 1.2937753836425982e-07, Loss: 0.10529075562953949
2024-08-05T02:57:38.831907495Z 
 77%|███████▋  | 4382/5712 [10:19:29<3:05:43,  8.38s/it]08/04/2024 19:57:38 - INFO - __main__ -   Step: 4382, LR: 1.2928025973394295e-07, Loss: 0.05292542278766632
2024-08-05T02:57:47.184870487Z 
 77%|███████▋  | 4383/5712 [10:19:38<3:05:24,  8.37s/it]08/04/2024 19:57:47 - INFO - __main__ -   Step: 4383, LR: 1.2918298110362605e-07, Loss: 0.06204189360141754
2024-08-05T02:57:55.527748300Z 
 77%|███████▋  | 4384/5712 [10:19:46<3:05:05,  8.36s/it]08/04/2024 19:57:55 - INFO - __main__ -   Step: 4384, LR: 1.2908570247330917e-07, Loss: 0.07931284606456757
2024-08-05T02:58:03.553223638Z 
 77%|███████▋  | 4385/5712 [10:19:54<3:02:42,  8.26s/it]08/04/2024 19:58:03 - INFO - __main__ -   Step: 4385, LR: 1.2898842384299227e-07, Loss: 0.09884922206401825
2024-08-05T02:58:11.882814451Z 
 77%|███████▋  | 4386/5712 [10:20:03<3:03:01,  8.28s/it]08/04/2024 19:58:11 - INFO - __main__ -   Step: 4386, LR: 1.2889114521267542e-07, Loss: 0.07880307734012604
2024-08-05T02:58:20.621505800Z 
 77%|███████▋  | 4387/5712 [10:20:11<3:05:55,  8.42s/it]08/04/2024 19:58:20 - INFO - __main__ -   Step: 4387, LR: 1.2879386658235852e-07, Loss: 0.09603311121463776
2024-08-05T02:58:29.029527213Z 
 77%|███████▋  | 4388/5712 [10:20:20<3:05:42,  8.42s/it]08/04/2024 19:58:29 - INFO - __main__ -   Step: 4388, LR: 1.2869658795204165e-07, Loss: 0.05206085368990898
2024-08-05T02:58:37.018549364Z 
 77%|███████▋  | 4389/5712 [10:20:28<3:02:44,  8.29s/it]08/04/2024 19:58:37 - INFO - __main__ -   Step: 4389, LR: 1.2859930932172475e-07, Loss: 0.2404678910970688
2024-08-05T02:58:46.037309771Z 
 77%|███████▋  | 4390/5712 [10:20:37<3:07:26,  8.51s/it]08/04/2024 19:58:46 - INFO - __main__ -   Step: 4390, LR: 1.2850203069140785e-07, Loss: 0.07763983309268951
2024-08-05T02:58:54.359909395Z 
 77%|███████▋  | 4391/5712 [10:20:45<3:06:04,  8.45s/it]08/04/2024 19:58:54 - INFO - __main__ -   Step: 4391, LR: 1.2840475206109097e-07, Loss: 0.047482118010520935
2024-08-05T02:59:02.523183027Z 
 77%|███████▋  | 4392/5712 [10:20:53<3:04:01,  8.37s/it]08/04/2024 19:59:02 - INFO - __main__ -   Step: 4392, LR: 1.2830747343077407e-07, Loss: 0.08351604640483856
2024-08-05T02:59:10.098700960Z 
 77%|███████▋  | 4393/5712 [10:21:01<2:58:41,  8.13s/it]08/04/2024 19:59:10 - INFO - __main__ -   Step: 4393, LR: 1.282101948004572e-07, Loss: 0.08037722110748291
2024-08-05T02:59:18.759483272Z 
 77%|███████▋  | 4394/5712 [10:21:09<3:02:03,  8.29s/it]08/04/2024 19:59:18 - INFO - __main__ -   Step: 4394, LR: 1.281129161701403e-07, Loss: 0.052195336669683456
2024-08-05T02:59:27.446014523Z 
 77%|███████▋  | 4395/5712 [10:21:18<3:04:32,  8.41s/it]08/04/2024 19:59:27 - INFO - __main__ -   Step: 4395, LR: 1.2801563753982345e-07, Loss: 0.04445367306470871
2024-08-05T02:59:36.569232835Z 
 77%|███████▋  | 4396/5712 [10:21:27<3:09:06,  8.62s/it]08/04/2024 19:59:36 - INFO - __main__ -   Step: 4396, LR: 1.2791835890950655e-07, Loss: 0.07638058066368103
2024-08-05T02:59:44.506129785Z 
 77%|███████▋  | 4397/5712 [10:21:35<3:04:27,  8.42s/it]08/04/2024 19:59:44 - INFO - __main__ -   Step: 4397, LR: 1.2782108027918967e-07, Loss: 0.0792425274848938
2024-08-05T02:59:52.936022275Z 
 77%|███████▋  | 4398/5712 [10:21:44<3:04:24,  8.42s/it]08/04/2024 19:59:52 - INFO - __main__ -   Step: 4398, LR: 1.2772380164887277e-07, Loss: 0.03963978588581085
2024-08-05T03:00:01.146120378Z 
 77%|███████▋  | 4399/5712 [10:21:52<3:02:53,  8.36s/it]08/04/2024 20:00:01 - INFO - __main__ -   Step: 4399, LR: 1.276265230185559e-07, Loss: 0.043409571051597595
2024-08-05T03:00:09.391374487Z 
 77%|███████▋  | 4400/5712 [10:22:00<3:02:00,  8.32s/it]08/04/2024 20:00:09 - INFO - __main__ -   Step: 4400, LR: 1.27529244388239e-07, Loss: 0.1248449981212616
2024-08-05T03:00:17.598033809Z 
 77%|███████▋  | 4401/5712 [10:22:08<3:01:06,  8.29s/it]08/04/2024 20:00:17 - INFO - __main__ -   Step: 4401, LR: 1.2743196575792212e-07, Loss: 0.08338803052902222
2024-08-05T03:00:25.659546743Z 
 77%|███████▋  | 4402/5712 [10:22:16<2:59:28,  8.22s/it]08/04/2024 20:00:25 - INFO - __main__ -   Step: 4402, LR: 1.2733468712760522e-07, Loss: 0.0819447711110115
2024-08-05T03:00:33.891671559Z 
 77%|███████▋  | 4403/5712 [10:22:25<2:59:25,  8.22s/it]08/04/2024 20:00:33 - INFO - __main__ -   Step: 4403, LR: 1.2723740849728835e-07, Loss: 0.09471674263477325
2024-08-05T03:00:42.687188478Z 
 77%|███████▋  | 4404/5712 [10:22:33<3:03:01,  8.40s/it]08/04/2024 20:00:42 - INFO - __main__ -   Step: 4404, LR: 1.2714012986697147e-07, Loss: 0.09657880663871765
2024-08-05T03:00:51.117174917Z 
 77%|███████▋  | 4405/5712 [10:22:42<3:03:06,  8.41s/it]08/04/2024 20:00:51 - INFO - __main__ -   Step: 4405, LR: 1.270428512366546e-07, Loss: 0.06572078168392181
2024-08-05T03:00:59.348542537Z 
 77%|███████▋  | 4406/5712 [10:22:50<3:01:49,  8.35s/it]08/04/2024 20:00:59 - INFO - __main__ -   Step: 4406, LR: 1.269455726063377e-07, Loss: 0.07049456238746643
2024-08-05T03:01:07.980262248Z 
 77%|███████▋  | 4407/5712 [10:22:59<3:03:30,  8.44s/it]08/04/2024 20:01:07 - INFO - __main__ -   Step: 4407, LR: 1.2684829397602082e-07, Loss: 0.07853526622056961
2024-08-05T03:01:16.254918501Z 
 77%|███████▋  | 4408/5712 [10:23:07<3:02:18,  8.39s/it]08/04/2024 20:01:16 - INFO - __main__ -   Step: 4408, LR: 1.2675101534570392e-07, Loss: 0.06386454403400421
2024-08-05T03:01:24.266429184Z 
 77%|███████▋  | 4409/5712 [10:23:15<2:59:42,  8.28s/it]08/04/2024 20:01:24 - INFO - __main__ -   Step: 4409, LR: 1.2665373671538705e-07, Loss: 0.06525543332099915
2024-08-05T03:01:32.235219494Z 
 77%|███████▋  | 4410/5712 [10:23:23<2:57:34,  8.18s/it]08/04/2024 20:01:32 - INFO - __main__ -   Step: 4410, LR: 1.2655645808507014e-07, Loss: 0.14540380239486694
2024-08-05T03:01:40.966824107Z 
 77%|███████▋  | 4411/5712 [10:23:32<3:01:00,  8.35s/it]08/04/2024 20:01:40 - INFO - __main__ -   Step: 4411, LR: 1.2645917945475327e-07, Loss: 0.08052905648946762
2024-08-05T03:01:50.292185846Z 
 77%|███████▋  | 4412/5712 [10:23:41<3:07:12,  8.64s/it]08/04/2024 20:01:50 - INFO - __main__ -   Step: 4412, LR: 1.2636190082443637e-07, Loss: 0.06062159687280655
2024-08-05T03:01:59.287083132Z 
 77%|███████▋  | 4413/5712 [10:23:50<3:09:22,  8.75s/it]08/04/2024 20:01:59 - INFO - __main__ -   Step: 4413, LR: 1.2626462219411952e-07, Loss: 0.057166650891304016
2024-08-05T03:02:07.528783460Z 
 77%|███████▋  | 4414/5712 [10:23:58<3:05:57,  8.60s/it]08/04/2024 20:02:07 - INFO - __main__ -   Step: 4414, LR: 1.2616734356380262e-07, Loss: 0.054172348231077194
2024-08-05T03:02:16.065366703Z 
 77%|███████▋  | 4415/5712 [10:24:07<3:05:25,  8.58s/it]08/04/2024 20:02:16 - INFO - __main__ -   Step: 4415, LR: 1.2607006493348575e-07, Loss: 0.0777827799320221
2024-08-05T03:02:24.728948668Z 
 77%|███████▋  | 4416/5712 [10:24:15<3:05:50,  8.60s/it]08/04/2024 20:02:24 - INFO - __main__ -   Step: 4416, LR: 1.2597278630316885e-07, Loss: 0.06413056701421738
2024-08-05T03:02:33.113461768Z 
 77%|███████▋  | 4417/5712 [10:24:24<3:04:16,  8.54s/it]08/04/2024 20:02:33 - INFO - __main__ -   Step: 4417, LR: 1.2587550767285197e-07, Loss: 0.1139272004365921
2024-08-05T03:02:41.419564575Z 
 77%|███████▋  | 4418/5712 [10:24:32<3:02:37,  8.47s/it]08/04/2024 20:02:41 - INFO - __main__ -   Step: 4418, LR: 1.2577822904253507e-07, Loss: 0.03235651180148125
2024-08-05T03:02:49.413861184Z 
 77%|███████▋  | 4419/5712 [10:24:40<2:59:25,  8.33s/it]08/04/2024 20:02:49 - INFO - __main__ -   Step: 4419, LR: 1.256809504122182e-07, Loss: 0.07463403046131134
2024-08-05T03:02:58.352974167Z 
 77%|███████▋  | 4420/5712 [10:24:49<3:03:15,  8.51s/it]08/04/2024 20:02:58 - INFO - __main__ -   Step: 4420, LR: 1.255836717819013e-07, Loss: 0.09684150665998459
2024-08-05T03:03:06.749993614Z 
 77%|███████▋  | 4421/5712 [10:24:57<3:02:22,  8.48s/it]08/04/2024 20:03:06 - INFO - __main__ -   Step: 4421, LR: 1.2548639315158442e-07, Loss: 0.13048739731311798
2024-08-05T03:03:14.937616677Z 
 77%|███████▋  | 4422/5712 [10:25:06<3:00:22,  8.39s/it]08/04/2024 20:03:14 - INFO - __main__ -   Step: 4422, LR: 1.2538911452126755e-07, Loss: 0.11909308284521103
2024-08-05T03:03:23.228991756Z 
 77%|███████▋  | 4423/5712 [10:25:14<2:59:36,  8.36s/it]08/04/2024 20:03:23 - INFO - __main__ -   Step: 4423, LR: 1.2529183589095067e-07, Loss: 0.0328485369682312
2024-08-05T03:03:32.078997902Z 
 77%|███████▋  | 4424/5712 [10:25:23<3:02:37,  8.51s/it]08/04/2024 20:03:32 - INFO - __main__ -   Step: 4424, LR: 1.2519455726063377e-07, Loss: 0.11808286607265472
2024-08-05T03:03:40.266591381Z 
 77%|███████▋  | 4425/5712 [10:25:31<3:00:25,  8.41s/it]08/04/2024 20:03:40 - INFO - __main__ -   Step: 4425, LR: 1.250972786303169e-07, Loss: 0.09270458668470383
2024-08-05T03:03:48.303022239Z 
 77%|███████▋  | 4426/5712 [10:25:39<2:57:52,  8.30s/it]08/04/2024 20:03:48 - INFO - __main__ -   Step: 4426, LR: 1.25e-07, Loss: 0.09915714710950851
2024-08-05T03:03:56.617203117Z 
 78%|███████▊  | 4427/5712 [10:25:47<2:57:49,  8.30s/it]08/04/2024 20:03:56 - INFO - __main__ -   Step: 4427, LR: 1.249027213696831e-07, Loss: 0.0544896200299263
2024-08-05T03:04:05.446502039Z 
 78%|███████▊  | 4428/5712 [10:25:56<3:01:04,  8.46s/it]08/04/2024 20:04:05 - INFO - __main__ -   Step: 4428, LR: 1.2480544273936622e-07, Loss: 0.06748669594526291
2024-08-05T03:04:14.275883595Z 
 78%|███████▊  | 4429/5712 [10:26:05<3:03:16,  8.57s/it]08/04/2024 20:04:14 - INFO - __main__ -   Step: 4429, LR: 1.2470816410904934e-07, Loss: 0.11032790690660477
2024-08-05T03:04:22.833611691Z 
 78%|███████▊  | 4430/5712 [10:26:13<3:03:03,  8.57s/it]08/04/2024 20:04:22 - INFO - __main__ -   Step: 4430, LR: 1.2461088547873244e-07, Loss: 0.05092557147145271
2024-08-05T03:04:31.397873653Z 
 78%|███████▊  | 4431/5712 [10:26:22<3:02:53,  8.57s/it]08/04/2024 20:04:31 - INFO - __main__ -   Step: 4431, LR: 1.2451360684841557e-07, Loss: 0.06255567073822021
2024-08-05T03:04:40.179036037Z 
 78%|███████▊  | 4432/5712 [10:26:31<3:04:07,  8.63s/it]08/04/2024 20:04:40 - INFO - __main__ -   Step: 4432, LR: 1.2441632821809867e-07, Loss: 0.06514671444892883
2024-08-05T03:04:48.349130793Z 
 78%|███████▊  | 4433/5712 [10:26:39<3:01:02,  8.49s/it]08/04/2024 20:04:48 - INFO - __main__ -   Step: 4433, LR: 1.243190495877818e-07, Loss: 0.05210179090499878
2024-08-05T03:04:56.658816033Z 
 78%|███████▊  | 4434/5712 [10:26:47<2:59:43,  8.44s/it]08/04/2024 20:04:56 - INFO - __main__ -   Step: 4434, LR: 1.2422177095746492e-07, Loss: 0.10120067000389099
2024-08-05T03:05:04.888881181Z 
 78%|███████▊  | 4435/5712 [10:26:56<2:58:15,  8.38s/it]08/04/2024 20:05:04 - INFO - __main__ -   Step: 4435, LR: 1.2412449232714802e-07, Loss: 0.09089821577072144
2024-08-05T03:05:13.038241118Z 
 78%|███████▊  | 4436/5712 [10:27:04<2:56:40,  8.31s/it]08/04/2024 20:05:13 - INFO - __main__ -   Step: 4436, LR: 1.2402721369683114e-07, Loss: 0.04708172008395195
2024-08-05T03:05:21.329726234Z 
 78%|███████▊  | 4437/5712 [10:27:12<2:56:26,  8.30s/it]08/04/2024 20:05:21 - INFO - __main__ -   Step: 4437, LR: 1.2392993506651424e-07, Loss: 0.06568633019924164
2024-08-05T03:05:29.989554427Z 
 78%|███████▊  | 4438/5712 [10:27:21<2:58:34,  8.41s/it]08/04/2024 20:05:29 - INFO - __main__ -   Step: 4438, LR: 1.2383265643619737e-07, Loss: 0.03785884007811546
2024-08-05T03:05:38.655930951Z 
 78%|███████▊  | 4439/5712 [10:27:29<3:00:03,  8.49s/it]08/04/2024 20:05:38 - INFO - __main__ -   Step: 4439, LR: 1.237353778058805e-07, Loss: 0.07871536910533905
2024-08-05T03:05:47.129994403Z 
 78%|███████▊  | 4440/5712 [10:27:38<2:59:50,  8.48s/it]08/04/2024 20:05:47 - INFO - __main__ -   Step: 4440, LR: 1.236380991755636e-07, Loss: 0.10475650429725647
2024-08-05T03:05:55.969981265Z 
 78%|███████▊  | 4441/5712 [10:27:47<3:01:57,  8.59s/it]08/04/2024 20:05:55 - INFO - __main__ -   Step: 4441, LR: 1.2354082054524672e-07, Loss: 0.06893956661224365
2024-08-05T03:06:04.197518462Z 
 78%|███████▊  | 4442/5712 [10:27:55<2:59:31,  8.48s/it]08/04/2024 20:06:04 - INFO - __main__ -   Step: 4442, LR: 1.2344354191492984e-07, Loss: 0.1901552379131317
2024-08-05T03:06:12.114031645Z 
 78%|███████▊  | 4443/5712 [10:28:03<2:55:47,  8.31s/it]08/04/2024 20:06:12 - INFO - __main__ -   Step: 4443, LR: 1.2334626328461294e-07, Loss: 0.06453128904104233
2024-08-05T03:06:20.347722721Z 
 78%|███████▊  | 4444/5712 [10:28:11<2:55:09,  8.29s/it]08/04/2024 20:06:20 - INFO - __main__ -   Step: 4444, LR: 1.2324898465429607e-07, Loss: 0.06207381933927536
2024-08-05T03:06:28.808114298Z 
 78%|███████▊  | 4445/5712 [10:28:19<2:56:06,  8.34s/it]08/04/2024 20:06:28 - INFO - __main__ -   Step: 4445, LR: 1.2315170602397917e-07, Loss: 0.06706026196479797
2024-08-05T03:06:38.162070084Z 
 78%|███████▊  | 4446/5712 [10:28:29<3:02:22,  8.64s/it]08/04/2024 20:06:38 - INFO - __main__ -   Step: 4446, LR: 1.230544273936623e-07, Loss: 0.09486682713031769
2024-08-05T03:06:46.489465773Z 
 78%|███████▊  | 4447/5712 [10:28:37<3:00:14,  8.55s/it]08/04/2024 20:06:46 - INFO - __main__ -   Step: 4447, LR: 1.2295714876334542e-07, Loss: 0.06657053530216217
2024-08-05T03:06:55.099834028Z 
 78%|███████▊  | 4448/5712 [10:28:46<3:00:29,  8.57s/it]08/04/2024 20:06:55 - INFO - __main__ -   Step: 4448, LR: 1.2285987013302852e-07, Loss: 0.13154307007789612
2024-08-05T03:07:03.710578187Z 
 78%|███████▊  | 4449/5712 [10:28:54<3:00:37,  8.58s/it]08/04/2024 20:07:03 - INFO - __main__ -   Step: 4449, LR: 1.2276259150271164e-07, Loss: 0.08003561198711395
2024-08-05T03:07:12.125968875Z 
 78%|███████▊  | 4450/5712 [10:29:03<2:59:26,  8.53s/it]08/04/2024 20:07:12 - INFO - __main__ -   Step: 4450, LR: 1.2266531287239474e-07, Loss: 0.05801020935177803
2024-08-05T03:07:20.234884683Z 
 78%|███████▊  | 4451/5712 [10:29:11<2:56:37,  8.40s/it]08/04/2024 20:07:20 - INFO - __main__ -   Step: 4451, LR: 1.2256803424207787e-07, Loss: 0.08436225354671478
2024-08-05T03:07:28.679246729Z 
 78%|███████▊  | 4452/5712 [10:29:19<2:56:44,  8.42s/it]08/04/2024 20:07:28 - INFO - __main__ -   Step: 4452, LR: 1.22470755611761e-07, Loss: 0.09539258480072021
2024-08-05T03:07:36.674086981Z 
 78%|███████▊  | 4453/5712 [10:29:27<2:53:56,  8.29s/it]08/04/2024 20:07:36 - INFO - __main__ -   Step: 4453, LR: 1.223734769814441e-07, Loss: 0.07483591139316559
2024-08-05T03:07:45.583071426Z 
 78%|███████▊  | 4454/5712 [10:29:36<2:57:42,  8.48s/it]08/04/2024 20:07:45 - INFO - __main__ -   Step: 4454, LR: 1.2227619835112722e-07, Loss: 0.062430061399936676
2024-08-05T03:07:53.842366989Z 
 78%|███████▊  | 4455/5712 [10:29:44<2:56:12,  8.41s/it]08/04/2024 20:07:53 - INFO - __main__ -   Step: 4455, LR: 1.2217891972081032e-07, Loss: 0.04397359862923622
2024-08-05T03:08:02.078406563Z 
 78%|███████▊  | 4456/5712 [10:29:53<2:54:58,  8.36s/it]08/04/2024 20:08:02 - INFO - __main__ -   Step: 4456, LR: 1.2208164109049344e-07, Loss: 0.13525013625621796
2024-08-05T03:08:10.609708235Z 
 78%|███████▊  | 4457/5712 [10:30:01<2:55:54,  8.41s/it]08/04/2024 20:08:10 - INFO - __main__ -   Step: 4457, LR: 1.2198436246017657e-07, Loss: 0.05757822096347809
2024-08-05T03:08:19.324563705Z 
 78%|███████▊  | 4458/5712 [10:30:10<2:57:41,  8.50s/it]08/04/2024 20:08:19 - INFO - __main__ -   Step: 4458, LR: 1.2188708382985967e-07, Loss: 0.08584517240524292
2024-08-05T03:08:27.464855661Z 
 78%|███████▊  | 4459/5712 [10:30:18<2:55:16,  8.39s/it]08/04/2024 20:08:27 - INFO - __main__ -   Step: 4459, LR: 1.217898051995428e-07, Loss: 0.08088172227144241
2024-08-05T03:08:35.485690380Z 
 78%|███████▊  | 4460/5712 [10:30:26<2:52:48,  8.28s/it]08/04/2024 20:08:35 - INFO - __main__ -   Step: 4460, LR: 1.2169252656922592e-07, Loss: 0.0509064607322216
2024-08-05T03:08:44.356405660Z 
 78%|███████▊  | 4461/5712 [10:30:35<2:56:21,  8.46s/it]08/04/2024 20:08:44 - INFO - __main__ -   Step: 4461, LR: 1.2159524793890902e-07, Loss: 0.05084904283285141
2024-08-05T03:08:52.689225844Z 
 78%|███████▊  | 4462/5712 [10:30:43<2:55:25,  8.42s/it]08/04/2024 20:08:52 - INFO - __main__ -   Step: 4462, LR: 1.2149796930859214e-07, Loss: 0.08210118860006332
2024-08-05T03:09:01.675843676Z 
 78%|███████▊  | 4463/5712 [10:30:52<2:58:48,  8.59s/it]08/04/2024 20:09:01 - INFO - __main__ -   Step: 4463, LR: 1.2140069067827524e-07, Loss: 0.1099080890417099
2024-08-05T03:09:10.361022175Z 
 78%|███████▊  | 4464/5712 [10:31:01<2:59:16,  8.62s/it]08/04/2024 20:09:10 - INFO - __main__ -   Step: 4464, LR: 1.2130341204795834e-07, Loss: 0.09143346548080444
2024-08-05T03:09:18.669702595Z 
 78%|███████▊  | 4465/5712 [10:31:09<2:57:11,  8.53s/it]08/04/2024 20:09:18 - INFO - __main__ -   Step: 4465, LR: 1.2120613341764147e-07, Loss: 0.1254037320613861
2024-08-05T03:09:27.173839581Z 
 78%|███████▊  | 4466/5712 [10:31:18<2:56:55,  8.52s/it]08/04/2024 20:09:27 - INFO - __main__ -   Step: 4466, LR: 1.211088547873246e-07, Loss: 0.03931654989719391
2024-08-05T03:09:35.850843175Z 
 78%|███████▊  | 4467/5712 [10:31:26<2:57:45,  8.57s/it]08/04/2024 20:09:35 - INFO - __main__ -   Step: 4467, LR: 1.210115761570077e-07, Loss: 0.057209208607673645
2024-08-05T03:09:43.788311821Z 
 78%|███████▊  | 4468/5712 [10:31:34<2:53:41,  8.38s/it]08/04/2024 20:09:43 - INFO - __main__ -   Step: 4468, LR: 1.2091429752669082e-07, Loss: 0.09344227612018585
2024-08-05T03:09:52.232341382Z 
 78%|███████▊  | 4469/5712 [10:31:43<2:53:58,  8.40s/it]08/04/2024 20:09:52 - INFO - __main__ -   Step: 4469, LR: 1.2081701889637394e-07, Loss: 0.08382505178451538
2024-08-05T03:10:00.577635364Z 
 78%|███████▊  | 4470/5712 [10:31:51<2:53:30,  8.38s/it]08/04/2024 20:10:00 - INFO - __main__ -   Step: 4470, LR: 1.2071974026605704e-07, Loss: 0.06635195761919022
2024-08-05T03:10:08.650393780Z 
 78%|███████▊  | 4471/5712 [10:31:59<2:51:27,  8.29s/it]08/04/2024 20:10:08 - INFO - __main__ -   Step: 4471, LR: 1.2062246163574017e-07, Loss: 0.1171436756849289
2024-08-05T03:10:17.042287390Z 
 78%|███████▊  | 4472/5712 [10:32:08<2:51:56,  8.32s/it]08/04/2024 20:10:17 - INFO - __main__ -   Step: 4472, LR: 1.2052518300542327e-07, Loss: 0.04222657158970833
2024-08-05T03:10:25.329599241Z 
 78%|███████▊  | 4473/5712 [10:32:16<2:51:36,  8.31s/it]08/04/2024 20:10:25 - INFO - __main__ -   Step: 4473, LR: 1.204279043751064e-07, Loss: 0.0856984332203865
2024-08-05T03:10:33.537781506Z 
 78%|███████▊  | 4474/5712 [10:32:24<2:50:50,  8.28s/it]08/04/2024 20:10:33 - INFO - __main__ -   Step: 4474, LR: 1.2033062574478952e-07, Loss: 0.11624445021152496
2024-08-05T03:10:42.310649303Z 
 78%|███████▊  | 4475/5712 [10:32:33<2:53:44,  8.43s/it]08/04/2024 20:10:42 - INFO - __main__ -   Step: 4475, LR: 1.2023334711447262e-07, Loss: 0.06094340980052948
2024-08-05T03:10:50.559127603Z 
 78%|███████▊  | 4476/5712 [10:32:41<2:52:30,  8.37s/it]08/04/2024 20:10:50 - INFO - __main__ -   Step: 4476, LR: 1.2013606848415574e-07, Loss: 0.07207591086626053
2024-08-05T03:10:59.020694664Z 
 78%|███████▊  | 4477/5712 [10:32:50<2:52:53,  8.40s/it]08/04/2024 20:10:59 - INFO - __main__ -   Step: 4477, LR: 1.2003878985383884e-07, Loss: 0.04547782987356186
2024-08-05T03:11:07.714048621Z 
 78%|███████▊  | 4478/5712 [10:32:58<2:54:34,  8.49s/it]08/04/2024 20:11:07 - INFO - __main__ -   Step: 4478, LR: 1.1994151122352197e-07, Loss: 0.062428250908851624
2024-08-05T03:11:16.024723225Z 
 78%|███████▊  | 4479/5712 [10:33:07<2:53:20,  8.43s/it]08/04/2024 20:11:16 - INFO - __main__ -   Step: 4479, LR: 1.198442325932051e-07, Loss: 0.07357323169708252
2024-08-05T03:11:24.768924011Z 
 78%|███████▊  | 4480/5712 [10:33:15<2:55:05,  8.53s/it]08/04/2024 20:11:24 - INFO - __main__ -   Step: 4480, LR: 1.197469539628882e-07, Loss: 0.04806149750947952
2024-08-05T03:11:33.368392978Z 
 78%|███████▊  | 4481/5712 [10:33:24<2:55:24,  8.55s/it]08/04/2024 20:11:33 - INFO - __main__ -   Step: 4481, LR: 1.1964967533257132e-07, Loss: 0.06675896793603897
2024-08-05T03:11:42.073956309Z 
 78%|███████▊  | 4482/5712 [10:33:33<2:56:13,  8.60s/it]08/04/2024 20:11:42 - INFO - __main__ -   Step: 4482, LR: 1.1955239670225441e-07, Loss: 0.07216706871986389
2024-08-05T03:11:50.355937562Z 
 78%|███████▊  | 4483/5712 [10:33:41<2:54:08,  8.50s/it]08/04/2024 20:11:50 - INFO - __main__ -   Step: 4483, LR: 1.1945511807193754e-07, Loss: 0.09486297518014908
2024-08-05T03:11:58.775361506Z 
 79%|███████▊  | 4484/5712 [10:33:49<2:53:29,  8.48s/it]08/04/2024 20:11:58 - INFO - __main__ -   Step: 4484, LR: 1.1935783944162067e-07, Loss: 0.0294901505112648
2024-08-05T03:12:06.992932838Z 
 79%|███████▊  | 4485/5712 [10:33:58<2:51:46,  8.40s/it]08/04/2024 20:12:06 - INFO - __main__ -   Step: 4485, LR: 1.1926056081130376e-07, Loss: 0.06257776916027069
2024-08-05T03:12:16.181201438Z 
 79%|███████▊  | 4486/5712 [10:34:07<2:56:27,  8.64s/it]08/04/2024 20:12:16 - INFO - __main__ -   Step: 4486, LR: 1.1916328218098688e-07, Loss: 0.07955078780651093
2024-08-05T03:12:25.181433218Z 
 79%|███████▊  | 4487/5712 [10:34:16<2:58:32,  8.75s/it]08/04/2024 20:12:25 - INFO - __main__ -   Step: 4487, LR: 1.1906600355067e-07, Loss: 0.06352973729372025
2024-08-05T03:12:33.575474847Z 
 79%|███████▊  | 4488/5712 [10:34:24<2:56:15,  8.64s/it]08/04/2024 20:12:33 - INFO - __main__ -   Step: 4488, LR: 1.1896872492035311e-07, Loss: 0.10304417461156845
2024-08-05T03:12:42.810021908Z 
 79%|███████▊  | 4489/5712 [10:34:33<2:59:44,  8.82s/it]08/04/2024 20:12:42 - INFO - __main__ -   Step: 4489, LR: 1.1887144629003623e-07, Loss: 0.10167466849088669
2024-08-05T03:12:51.185143227Z 
 79%|███████▊  | 4490/5712 [10:34:42<2:56:53,  8.69s/it]08/04/2024 20:12:51 - INFO - __main__ -   Step: 4490, LR: 1.1877416765971934e-07, Loss: 0.09798897802829742
2024-08-05T03:12:59.496412670Z 
 79%|███████▊  | 4491/5712 [10:34:50<2:54:27,  8.57s/it]08/04/2024 20:12:59 - INFO - __main__ -   Step: 4491, LR: 1.1867688902940245e-07, Loss: 0.06916261464357376
2024-08-05T03:13:07.741612164Z 
 79%|███████▊  | 4492/5712 [10:34:58<2:52:19,  8.47s/it]08/04/2024 20:13:07 - INFO - __main__ -   Step: 4492, LR: 1.1857961039908558e-07, Loss: 0.11300978064537048
2024-08-05T03:13:15.848329606Z 
 79%|███████▊  | 4493/5712 [10:35:06<2:49:55,  8.36s/it]08/04/2024 20:13:15 - INFO - __main__ -   Step: 4493, LR: 1.1848233176876869e-07, Loss: 0.08159953355789185
2024-08-05T03:13:24.044090652Z 
 79%|███████▊  | 4494/5712 [10:35:15<2:48:46,  8.31s/it]08/04/2024 20:13:24 - INFO - __main__ -   Step: 4494, LR: 1.183850531384518e-07, Loss: 0.08688391745090485
2024-08-05T03:13:32.473491096Z 
 79%|███████▊  | 4495/5712 [10:35:23<2:49:20,  8.35s/it]08/04/2024 20:13:32 - INFO - __main__ -   Step: 4495, LR: 1.1828777450813491e-07, Loss: 0.11610138416290283
2024-08-05T03:13:40.915375935Z 
 79%|███████▊  | 4496/5712 [10:35:32<2:49:45,  8.38s/it]08/04/2024 20:13:40 - INFO - __main__ -   Step: 4496, LR: 1.1819049587781804e-07, Loss: 0.10052796453237534
2024-08-05T03:13:49.826126650Z 
 79%|███████▊  | 4497/5712 [10:35:40<2:52:51,  8.54s/it]08/04/2024 20:13:49 - INFO - __main__ -   Step: 4497, LR: 1.1809321724750115e-07, Loss: 0.036236099898815155
2024-08-05T03:13:58.131416125Z 
 79%|███████▊  | 4498/5712 [10:35:49<2:51:18,  8.47s/it]08/04/2024 20:13:58 - INFO - __main__ -   Step: 4498, LR: 1.1799593861718426e-07, Loss: 0.05755765363574028
2024-08-05T03:14:06.636805477Z 
 79%|███████▉  | 4499/5712 [10:35:57<2:51:25,  8.48s/it]08/04/2024 20:14:06 - INFO - __main__ -   Step: 4499, LR: 1.1789865998686738e-07, Loss: 0.09367595613002777
2024-08-05T03:14:15.054796475Z 
 79%|███████▉  | 4500/5712 [10:36:06<2:50:54,  8.46s/it]08/04/2024 20:14:15 - INFO - __main__ -   Step: 4500, LR: 1.1780138135655049e-07, Loss: 0.073072649538517
2024-08-05T03:14:23.128836247Z 
 79%|███████▉  | 4501/5712 [10:36:14<2:48:25,  8.34s/it]08/04/2024 20:14:23 - INFO - __main__ -   Step: 4501, LR: 1.1770410272623361e-07, Loss: 0.07161827385425568
2024-08-05T03:14:31.377060345Z 
 79%|███████▉  | 4502/5712 [10:36:22<2:47:42,  8.32s/it]08/04/2024 20:14:31 - INFO - __main__ -   Step: 4502, LR: 1.1760682409591673e-07, Loss: 0.06670606136322021
2024-08-05T03:14:40.313351830Z 
 79%|███████▉  | 4503/5712 [10:36:31<2:51:18,  8.50s/it]08/04/2024 20:14:40 - INFO - __main__ -   Step: 4503, LR: 1.1750954546559984e-07, Loss: 0.049799297004938126
2024-08-05T03:14:48.911990166Z 
 79%|███████▉  | 4504/5712 [10:36:40<2:51:45,  8.53s/it]08/04/2024 20:14:48 - INFO - __main__ -   Step: 4504, LR: 1.1741226683528295e-07, Loss: 0.08434142172336578
2024-08-05T03:14:57.795234535Z 
 79%|███████▉  | 4505/5712 [10:36:48<2:53:44,  8.64s/it]08/04/2024 20:14:57 - INFO - __main__ -   Step: 4505, LR: 1.1731498820496608e-07, Loss: 0.11096783727407455
2024-08-05T03:15:06.369277997Z 
 79%|███████▉  | 4506/5712 [10:36:57<2:53:13,  8.62s/it]08/04/2024 20:15:06 - INFO - __main__ -   Step: 4506, LR: 1.1721770957464919e-07, Loss: 0.06774690002202988
2024-08-05T03:15:14.688121850Z 
 79%|███████▉  | 4507/5712 [10:37:05<2:51:16,  8.53s/it]08/04/2024 20:15:14 - INFO - __main__ -   Step: 4507, LR: 1.171204309443323e-07, Loss: 0.02874259278178215
2024-08-05T03:15:22.884706312Z 
 79%|███████▉  | 4508/5712 [10:37:14<2:49:08,  8.43s/it]08/04/2024 20:15:22 - INFO - __main__ -   Step: 4508, LR: 1.1702315231401541e-07, Loss: 0.040355291217565536
2024-08-05T03:15:31.051133151Z 
 79%|███████▉  | 4509/5712 [10:37:22<2:47:25,  8.35s/it]08/04/2024 20:15:31 - INFO - __main__ -   Step: 4509, LR: 1.1692587368369853e-07, Loss: 0.06312732398509979
2024-08-05T03:15:39.283191957Z 
 79%|███████▉  | 4510/5712 [10:37:30<2:46:34,  8.31s/it]08/04/2024 20:15:39 - INFO - __main__ -   Step: 4510, LR: 1.1682859505338165e-07, Loss: 0.0334080271422863
2024-08-05T03:15:47.686191952Z 
 79%|███████▉  | 4511/5712 [10:37:38<2:46:57,  8.34s/it]08/04/2024 20:15:47 - INFO - __main__ -   Step: 4511, LR: 1.1673131642306476e-07, Loss: 0.07388081401586533
2024-08-05T03:15:56.719087243Z 
 79%|███████▉  | 4512/5712 [10:37:47<2:50:58,  8.55s/it]08/04/2024 20:15:56 - INFO - __main__ -   Step: 4512, LR: 1.1663403779274788e-07, Loss: 0.08450866490602493
2024-08-05T03:16:05.077233225Z 
 79%|███████▉  | 4513/5712 [10:37:56<2:49:41,  8.49s/it]08/04/2024 20:16:05 - INFO - __main__ -   Step: 4513, LR: 1.1653675916243099e-07, Loss: 0.06768985837697983
2024-08-05T03:16:14.498116141Z 
 79%|███████▉  | 4514/5712 [10:38:05<2:55:06,  8.77s/it]08/04/2024 20:16:14 - INFO - __main__ -   Step: 4514, LR: 1.1643948053211411e-07, Loss: 0.042054541409015656
2024-08-05T03:16:23.155936395Z 
 79%|███████▉  | 4515/5712 [10:38:14<2:54:17,  8.74s/it]08/04/2024 20:16:23 - INFO - __main__ -   Step: 4515, LR: 1.1634220190179723e-07, Loss: 0.06210637837648392
2024-08-05T03:16:31.977653053Z 
 79%|███████▉  | 4516/5712 [10:38:23<2:54:39,  8.76s/it]08/04/2024 20:16:31 - INFO - __main__ -   Step: 4516, LR: 1.1624492327148034e-07, Loss: 0.06726795434951782
2024-08-05T03:16:40.297533680Z 
 79%|███████▉  | 4517/5712 [10:38:31<2:51:52,  8.63s/it]08/04/2024 20:16:40 - INFO - __main__ -   Step: 4517, LR: 1.1614764464116345e-07, Loss: 0.05347346514463425
2024-08-05T03:16:49.037576351Z 
 79%|███████▉  | 4518/5712 [10:38:40<2:52:23,  8.66s/it]08/04/2024 20:16:49 - INFO - __main__ -   Step: 4518, LR: 1.1605036601084656e-07, Loss: 0.11973230540752411
2024-08-05T03:16:57.545730988Z 
 79%|███████▉  | 4519/5712 [10:38:48<2:51:19,  8.62s/it]08/04/2024 20:16:57 - INFO - __main__ -   Step: 4519, LR: 1.1595308738052969e-07, Loss: 0.08974838256835938
2024-08-05T03:17:06.534879754Z 
 79%|███████▉  | 4520/5712 [10:38:57<2:53:23,  8.73s/it]08/04/2024 20:17:06 - INFO - __main__ -   Step: 4520, LR: 1.158558087502128e-07, Loss: 0.0427498035132885
2024-08-05T03:17:15.038792898Z 
 79%|███████▉  | 4521/5712 [10:39:06<2:51:55,  8.66s/it]08/04/2024 20:17:15 - INFO - __main__ -   Step: 4521, LR: 1.157585301198959e-07, Loss: 0.028247101232409477
2024-08-05T03:17:24.331876802Z 
 79%|███████▉  | 4522/5712 [10:39:15<2:55:32,  8.85s/it]08/04/2024 20:17:24 - INFO - __main__ -   Step: 4522, LR: 1.1566125148957901e-07, Loss: 0.10138678550720215
2024-08-05T03:17:32.730744594Z 
 79%|███████▉  | 4523/5712 [10:39:23<2:52:42,  8.72s/it]08/04/2024 20:17:32 - INFO - __main__ -   Step: 4523, LR: 1.1556397285926214e-07, Loss: 0.08751916885375977
2024-08-05T03:17:41.854352077Z 
 79%|███████▉  | 4524/5712 [10:39:33<2:54:59,  8.84s/it]08/04/2024 20:17:41 - INFO - __main__ -   Step: 4524, LR: 1.1546669422894525e-07, Loss: 0.05211697891354561
2024-08-05T03:17:50.041512747Z 
 79%|███████▉  | 4525/5712 [10:39:41<2:50:58,  8.64s/it]08/04/2024 20:17:50 - INFO - __main__ -   Step: 4525, LR: 1.1536941559862836e-07, Loss: 0.035922758281230927
2024-08-05T03:17:58.567326883Z 
 79%|███████▉  | 4526/5712 [10:39:49<2:50:08,  8.61s/it]08/04/2024 20:17:58 - INFO - __main__ -   Step: 4526, LR: 1.1527213696831147e-07, Loss: 0.05193135887384415
2024-08-05T03:18:07.256954935Z 
 79%|███████▉  | 4527/5712 [10:39:58<2:50:29,  8.63s/it]08/04/2024 20:18:07 - INFO - __main__ -   Step: 4527, LR: 1.1517485833799459e-07, Loss: 0.09289775043725967
2024-08-05T03:18:15.489820147Z 
 79%|███████▉  | 4528/5712 [10:40:06<2:47:58,  8.51s/it]08/04/2024 20:18:15 - INFO - __main__ -   Step: 4528, LR: 1.1507757970767771e-07, Loss: 0.06977801769971848
2024-08-05T03:18:24.291174236Z 
 79%|███████▉  | 4529/5712 [10:40:15<2:49:32,  8.60s/it]08/04/2024 20:18:24 - INFO - __main__ -   Step: 4529, LR: 1.1498030107736082e-07, Loss: 0.09395039081573486
2024-08-05T03:18:32.317840084Z 
 79%|███████▉  | 4530/5712 [10:40:23<2:46:01,  8.43s/it]08/04/2024 20:18:32 - INFO - __main__ -   Step: 4530, LR: 1.1488302244704394e-07, Loss: 0.05576401203870773
2024-08-05T03:18:40.958661763Z 
 79%|███████▉  | 4531/5712 [10:40:32<2:47:08,  8.49s/it]08/04/2024 20:18:40 - INFO - __main__ -   Step: 4531, LR: 1.1478574381672705e-07, Loss: 0.0520404651761055
2024-08-05T03:18:49.548986176Z 
 79%|███████▉  | 4532/5712 [10:40:40<2:47:34,  8.52s/it]08/04/2024 20:18:49 - INFO - __main__ -   Step: 4532, LR: 1.1468846518641016e-07, Loss: 0.09117820858955383
2024-08-05T03:18:57.995554019Z 
 79%|███████▉  | 4533/5712 [10:40:49<2:47:00,  8.50s/it]08/04/2024 20:18:57 - INFO - __main__ -   Step: 4533, LR: 1.1459118655609329e-07, Loss: 0.07064653187990189
2024-08-05T03:19:06.197830833Z 
 79%|███████▉  | 4534/5712 [10:40:57<2:45:06,  8.41s/it]08/04/2024 20:19:06 - INFO - __main__ -   Step: 4534, LR: 1.144939079257764e-07, Loss: 0.11876928806304932
2024-08-05T03:19:15.020045901Z 
 79%|███████▉  | 4535/5712 [10:41:06<2:47:23,  8.53s/it]08/04/2024 20:19:15 - INFO - __main__ -   Step: 4535, LR: 1.1439662929545951e-07, Loss: 0.05980765447020531
2024-08-05T03:19:23.806217426Z 
 79%|███████▉  | 4536/5712 [10:41:14<2:48:44,  8.61s/it]08/04/2024 20:19:23 - INFO - __main__ -   Step: 4536, LR: 1.1429935066514262e-07, Loss: 0.06544537097215652
2024-08-05T03:19:32.643658253Z 
 79%|███████▉  | 4537/5712 [10:41:23<2:49:56,  8.68s/it]08/04/2024 20:19:32 - INFO - __main__ -   Step: 4537, LR: 1.1420207203482575e-07, Loss: 0.05142033100128174
2024-08-05T03:19:41.402704568Z 
 79%|███████▉  | 4538/5712 [10:41:32<2:50:16,  8.70s/it]08/04/2024 20:19:41 - INFO - __main__ -   Step: 4538, LR: 1.1410479340450886e-07, Loss: 0.06738249212503433
2024-08-05T03:19:50.054762015Z 
 79%|███████▉  | 4539/5712 [10:41:41<2:49:49,  8.69s/it]08/04/2024 20:19:50 - INFO - __main__ -   Step: 4539, LR: 1.1400751477419197e-07, Loss: 0.11007094383239746
2024-08-05T03:19:58.716932065Z 
 79%|███████▉  | 4540/5712 [10:41:49<2:49:32,  8.68s/it]08/04/2024 20:19:58 - INFO - __main__ -   Step: 4540, LR: 1.1391023614387509e-07, Loss: 0.07659108191728592
2024-08-05T03:20:07.041614828Z 
 79%|███████▉  | 4541/5712 [10:41:58<2:47:19,  8.57s/it]08/04/2024 20:20:07 - INFO - __main__ -   Step: 4541, LR: 1.138129575135582e-07, Loss: 0.06702523678541183
2024-08-05T03:20:15.081630631Z 
 80%|███████▉  | 4542/5712 [10:42:06<2:44:03,  8.41s/it]08/04/2024 20:20:15 - INFO - __main__ -   Step: 4542, LR: 1.1371567888324132e-07, Loss: 0.06943266093730927
2024-08-05T03:20:23.814417663Z 
 80%|███████▉  | 4543/5712 [10:42:14<2:45:47,  8.51s/it]08/04/2024 20:20:23 - INFO - __main__ -   Step: 4543, LR: 1.1361840025292444e-07, Loss: 0.0882929190993309
2024-08-05T03:20:32.196599450Z 
 80%|███████▉  | 4544/5712 [10:42:23<2:44:54,  8.47s/it]08/04/2024 20:20:32 - INFO - __main__ -   Step: 4544, LR: 1.1352112162260755e-07, Loss: 0.05203831195831299
2024-08-05T03:20:40.368044147Z 
 80%|███████▉  | 4545/5712 [10:42:31<2:43:00,  8.38s/it]08/04/2024 20:20:40 - INFO - __main__ -   Step: 4545, LR: 1.1342384299229066e-07, Loss: 0.140709787607193
2024-08-05T03:20:48.897684712Z 
 80%|███████▉  | 4546/5712 [10:42:40<2:43:44,  8.43s/it]08/04/2024 20:20:48 - INFO - __main__ -   Step: 4546, LR: 1.1332656436197379e-07, Loss: 0.03237646073102951
2024-08-05T03:20:57.313854467Z 
 80%|███████▉  | 4547/5712 [10:42:48<2:43:31,  8.42s/it]08/04/2024 20:20:57 - INFO - __main__ -   Step: 4547, LR: 1.132292857316569e-07, Loss: 0.047173842787742615
2024-08-05T03:21:05.842367830Z 
 80%|███████▉  | 4548/5712 [10:42:56<2:44:01,  8.45s/it]08/04/2024 20:21:05 - INFO - __main__ -   Step: 4548, LR: 1.1313200710134001e-07, Loss: 0.054668694734573364
2024-08-05T03:21:14.576503852Z 
 80%|███████▉  | 4549/5712 [10:43:05<2:45:30,  8.54s/it]08/04/2024 20:21:14 - INFO - __main__ -   Step: 4549, LR: 1.1303472847102312e-07, Loss: 0.11089682579040527
2024-08-05T03:21:22.992282102Z 
 80%|███████▉  | 4550/5712 [10:43:14<2:44:39,  8.50s/it]08/04/2024 20:21:22 - INFO - __main__ -   Step: 4550, LR: 1.1293744984070623e-07, Loss: 0.08471368998289108
2024-08-05T03:21:31.665430406Z 
 80%|███████▉  | 4551/5712 [10:43:22<2:45:30,  8.55s/it]08/04/2024 20:21:31 - INFO - __main__ -   Step: 4551, LR: 1.1284017121038936e-07, Loss: 0.09666670858860016
2024-08-05T03:21:40.037545337Z 
 80%|███████▉  | 4552/5712 [10:43:31<2:44:18,  8.50s/it]08/04/2024 20:21:40 - INFO - __main__ -   Step: 4552, LR: 1.1274289258007247e-07, Loss: 0.04751371592283249
2024-08-05T03:21:48.471371746Z 
 80%|███████▉  | 4553/5712 [10:43:39<2:43:47,  8.48s/it]08/04/2024 20:21:48 - INFO - __main__ -   Step: 4553, LR: 1.1264561394975558e-07, Loss: 0.02931765280663967
2024-08-05T03:21:56.965906883Z 
 80%|███████▉  | 4554/5712 [10:43:48<2:43:44,  8.48s/it]08/04/2024 20:21:56 - INFO - __main__ -   Step: 4554, LR: 1.125483353194387e-07, Loss: 0.12626305222511292
2024-08-05T03:22:05.196497547Z 
 80%|███████▉  | 4555/5712 [10:43:56<2:42:07,  8.41s/it]08/04/2024 20:22:05 - INFO - __main__ -   Step: 4555, LR: 1.1245105668912182e-07, Loss: 0.06430856883525848
2024-08-05T03:22:13.858792459Z 
 80%|███████▉  | 4556/5712 [10:44:05<2:43:27,  8.48s/it]08/04/2024 20:22:13 - INFO - __main__ -   Step: 4556, LR: 1.1235377805880493e-07, Loss: 0.06685091555118561
2024-08-05T03:22:22.133266800Z 
 80%|███████▉  | 4557/5712 [10:44:13<2:42:06,  8.42s/it]08/04/2024 20:22:22 - INFO - __main__ -   Step: 4557, LR: 1.1225649942848805e-07, Loss: 0.06346599757671356
2024-08-05T03:22:30.231320987Z 
 80%|███████▉  | 4558/5712 [10:44:21<2:40:06,  8.32s/it]08/04/2024 20:22:30 - INFO - __main__ -   Step: 4558, LR: 1.1215922079817116e-07, Loss: 0.09052766859531403
2024-08-05T03:22:38.287990160Z 
 80%|███████▉  | 4559/5712 [10:44:29<2:38:25,  8.24s/it]08/04/2024 20:22:38 - INFO - __main__ -   Step: 4559, LR: 1.1206194216785426e-07, Loss: 0.09171692281961441
2024-08-05T03:22:46.890077581Z 
 80%|███████▉  | 4560/5712 [10:44:38<2:40:20,  8.35s/it]08/04/2024 20:22:46 - INFO - __main__ -   Step: 4560, LR: 1.1196466353753738e-07, Loss: 0.0872189998626709
2024-08-05T03:22:55.378182069Z 
 80%|███████▉  | 4561/5712 [10:44:46<2:40:59,  8.39s/it]08/04/2024 20:22:55 - INFO - __main__ -   Step: 4561, LR: 1.118673849072205e-07, Loss: 0.056192897260189056
2024-08-05T03:23:03.504974451Z 
 80%|███████▉  | 4562/5712 [10:44:54<2:39:19,  8.31s/it]08/04/2024 20:23:03 - INFO - __main__ -   Step: 4562, LR: 1.1177010627690361e-07, Loss: 0.09634004533290863
2024-08-05T03:23:12.121653775Z 
 80%|███████▉  | 4563/5712 [10:45:03<2:40:56,  8.40s/it]08/04/2024 20:23:12 - INFO - __main__ -   Step: 4563, LR: 1.1167282764658672e-07, Loss: 0.11555976420640945
2024-08-05T03:23:20.680939608Z 
 80%|███████▉  | 4564/5712 [10:45:11<2:41:41,  8.45s/it]08/04/2024 20:23:20 - INFO - __main__ -   Step: 4564, LR: 1.1157554901626985e-07, Loss: 0.04923883453011513
2024-08-05T03:23:28.852763860Z 
 80%|███████▉  | 4565/5712 [10:45:20<2:39:56,  8.37s/it]08/04/2024 20:23:28 - INFO - __main__ -   Step: 4565, LR: 1.1147827038595296e-07, Loss: 0.057036254554986954
2024-08-05T03:23:36.977506780Z 
 80%|███████▉  | 4566/5712 [10:45:28<2:38:25,  8.29s/it]08/04/2024 20:23:36 - INFO - __main__ -   Step: 4566, LR: 1.1138099175563607e-07, Loss: 0.053629204630851746
2024-08-05T03:23:45.021198021Z 
 80%|███████▉  | 4567/5712 [10:45:36<2:36:50,  8.22s/it]08/04/2024 20:23:45 - INFO - __main__ -   Step: 4567, LR: 1.1128371312531918e-07, Loss: 0.04213033989071846
2024-08-05T03:23:53.450945481Z 
 80%|███████▉  | 4568/5712 [10:45:44<2:37:54,  8.28s/it]08/04/2024 20:23:53 - INFO - __main__ -   Step: 4568, LR: 1.111864344950023e-07, Loss: 0.05349241569638252
2024-08-05T03:24:02.962605800Z 
 80%|███████▉  | 4569/5712 [10:45:54<2:44:48,  8.65s/it]08/04/2024 20:24:02 - INFO - __main__ -   Step: 4569, LR: 1.1108915586468542e-07, Loss: 0.08075413107872009
2024-08-05T03:24:11.198136851Z 
 80%|████████  | 4570/5712 [10:46:02<2:42:17,  8.53s/it]08/04/2024 20:24:11 - INFO - __main__ -   Step: 4570, LR: 1.1099187723436853e-07, Loss: 0.07693333923816681
2024-08-05T03:24:19.416160768Z 
 80%|████████  | 4571/5712 [10:46:10<2:40:23,  8.43s/it]08/04/2024 20:24:19 - INFO - __main__ -   Step: 4571, LR: 1.1089459860405165e-07, Loss: 0.07764962315559387
2024-08-05T03:24:28.050087970Z 
 80%|████████  | 4572/5712 [10:46:19<2:41:22,  8.49s/it]08/04/2024 20:24:28 - INFO - __main__ -   Step: 4572, LR: 1.1079731997373476e-07, Loss: 0.052327439188957214
2024-08-05T03:24:36.891908467Z 
 80%|████████  | 4573/5712 [10:46:28<2:43:13,  8.60s/it]08/04/2024 20:24:36 - INFO - __main__ -   Step: 4573, LR: 1.1070004134341788e-07, Loss: 0.13067492842674255
2024-08-05T03:24:45.139979905Z 
 80%|████████  | 4574/5712 [10:46:36<2:41:05,  8.49s/it]08/04/2024 20:24:45 - INFO - __main__ -   Step: 4574, LR: 1.10602762713101e-07, Loss: 0.028803478926420212
2024-08-05T03:24:52.664588787Z 
 80%|████████  | 4575/5712 [10:46:43<2:35:26,  8.20s/it]08/04/2024 20:24:52 - INFO - __main__ -   Step: 4575, LR: 1.1050548408278411e-07, Loss: 0.0953359305858612
2024-08-05T03:25:00.990069762Z 
 80%|████████  | 4576/5712 [10:46:52<2:36:00,  8.24s/it]08/04/2024 20:25:00 - INFO - __main__ -   Step: 4576, LR: 1.1040820545246722e-07, Loss: 0.05525391548871994
2024-08-05T03:25:09.866564434Z 
 80%|████████  | 4577/5712 [10:47:01<2:39:28,  8.43s/it]08/04/2024 20:25:09 - INFO - __main__ -   Step: 4577, LR: 1.1031092682215033e-07, Loss: 0.07856173068284988
2024-08-05T03:25:18.566441141Z 
 80%|████████  | 4578/5712 [10:47:09<2:40:51,  8.51s/it]08/04/2024 20:25:18 - INFO - __main__ -   Step: 4578, LR: 1.1021364819183346e-07, Loss: 0.08349163830280304
2024-08-05T03:25:27.213846577Z 
 80%|████████  | 4579/5712 [10:47:18<2:41:29,  8.55s/it]08/04/2024 20:25:27 - INFO - __main__ -   Step: 4579, LR: 1.1011636956151657e-07, Loss: 0.024873610585927963
2024-08-05T03:25:35.882170428Z 
 80%|████████  | 4580/5712 [10:47:27<2:42:00,  8.59s/it]08/04/2024 20:25:35 - INFO - __main__ -   Step: 4580, LR: 1.1001909093119968e-07, Loss: 0.101346455514431
2024-08-05T03:25:44.481568159Z 
 80%|████████  | 4581/5712 [10:47:35<2:41:56,  8.59s/it]08/04/2024 20:25:44 - INFO - __main__ -   Step: 4581, LR: 1.099218123008828e-07, Loss: 0.06192922592163086
2024-08-05T03:25:52.690864644Z 
 80%|████████  | 4582/5712 [10:47:43<2:39:38,  8.48s/it]08/04/2024 20:25:52 - INFO - __main__ -   Step: 4582, LR: 1.0982453367056592e-07, Loss: 0.07424339652061462
2024-08-05T03:26:00.760142001Z 
 80%|████████  | 4583/5712 [10:47:51<2:37:11,  8.35s/it]08/04/2024 20:26:00 - INFO - __main__ -   Step: 4583, LR: 1.0972725504024903e-07, Loss: 0.07697667181491852
2024-08-05T03:26:09.540543631Z 
 80%|████████  | 4584/5712 [10:48:00<2:39:27,  8.48s/it]08/04/2024 20:26:09 - INFO - __main__ -   Step: 4584, LR: 1.0962997640993214e-07, Loss: 0.07430830597877502
2024-08-05T03:26:18.613821544Z 
 80%|████████  | 4585/5712 [10:48:09<2:42:39,  8.66s/it]08/04/2024 20:26:18 - INFO - __main__ -   Step: 4585, LR: 1.0953269777961526e-07, Loss: 0.10992474853992462
2024-08-05T03:26:27.865696851Z 
 80%|████████  | 4586/5712 [10:48:19<2:45:50,  8.84s/it]08/04/2024 20:26:27 - INFO - __main__ -   Step: 4586, LR: 1.0943541914929837e-07, Loss: 0.11072501540184021
2024-08-05T03:26:36.285724209Z 
 80%|████████  | 4587/5712 [10:48:27<2:43:20,  8.71s/it]08/04/2024 20:26:36 - INFO - __main__ -   Step: 4587, LR: 1.093381405189815e-07, Loss: 0.08985266834497452
2024-08-05T03:26:44.873512267Z 
 80%|████████  | 4588/5712 [10:48:36<2:42:30,  8.67s/it]08/04/2024 20:26:44 - INFO - __main__ -   Step: 4588, LR: 1.0924086188866461e-07, Loss: 0.124691903591156
2024-08-05T03:26:53.187086014Z 
 80%|████████  | 4589/5712 [10:48:44<2:40:20,  8.57s/it]08/04/2024 20:26:53 - INFO - __main__ -   Step: 4589, LR: 1.0914358325834772e-07, Loss: 0.09604373574256897
2024-08-05T03:27:01.655377609Z 
 80%|████████  | 4590/5712 [10:48:52<2:39:38,  8.54s/it]08/04/2024 20:27:01 - INFO - __main__ -   Step: 4590, LR: 1.0904630462803083e-07, Loss: 0.10413317382335663
2024-08-05T03:27:09.722324355Z 
 80%|████████  | 4591/5712 [10:49:00<2:36:51,  8.40s/it]08/04/2024 20:27:09 - INFO - __main__ -   Step: 4591, LR: 1.0894902599771396e-07, Loss: 0.08338892459869385
2024-08-05T03:27:17.701493083Z 
 80%|████████  | 4592/5712 [10:49:08<2:34:23,  8.27s/it]08/04/2024 20:27:17 - INFO - __main__ -   Step: 4592, LR: 1.0885174736739707e-07, Loss: 0.07582563161849976
2024-08-05T03:27:26.286768007Z 
 80%|████████  | 4593/5712 [10:49:17<2:36:00,  8.37s/it]08/04/2024 20:27:26 - INFO - __main__ -   Step: 4593, LR: 1.0875446873708018e-07, Loss: 0.06475230306386948
2024-08-05T03:27:34.820548920Z 
 80%|████████  | 4594/5712 [10:49:25<2:36:48,  8.42s/it]08/04/2024 20:27:34 - INFO - __main__ -   Step: 4594, LR: 1.086571901067633e-07, Loss: 0.03760711848735809
2024-08-05T03:27:43.437230142Z 
 80%|████████  | 4595/5712 [10:49:34<2:37:47,  8.48s/it]08/04/2024 20:27:43 - INFO - __main__ -   Step: 4595, LR: 1.085599114764464e-07, Loss: 0.11443408578634262
2024-08-05T03:27:51.749590755Z 
 80%|████████  | 4596/5712 [10:49:42<2:36:44,  8.43s/it]08/04/2024 20:27:51 - INFO - __main__ -   Step: 4596, LR: 1.0846263284612953e-07, Loss: 0.0425766259431839
2024-08-05T03:28:00.354390797Z 
 80%|████████  | 4597/5712 [10:49:51<2:37:35,  8.48s/it]08/04/2024 20:28:00 - INFO - __main__ -   Step: 4597, LR: 1.0836535421581264e-07, Loss: 0.05298268795013428
2024-08-05T03:28:09.355716969Z 
 80%|████████  | 4598/5712 [10:50:00<2:40:21,  8.64s/it]08/04/2024 20:28:09 - INFO - __main__ -   Step: 4598, LR: 1.0826807558549574e-07, Loss: 0.08584664016962051
2024-08-05T03:28:17.607027277Z 
 81%|████████  | 4599/5712 [10:50:08<2:38:03,  8.52s/it]08/04/2024 20:28:17 - INFO - __main__ -   Step: 4599, LR: 1.0817079695517886e-07, Loss: 0.05742817744612694
2024-08-05T03:28:25.192976727Z 
 81%|████████  | 4600/5712 [10:50:16<2:32:43,  8.24s/it]08/04/2024 20:28:25 - INFO - __main__ -   Step: 4600, LR: 1.0807351832486198e-07, Loss: 0.07870103418827057
2024-08-05T03:28:33.491354070Z 
 81%|████████  | 4601/5712 [10:50:24<2:32:54,  8.26s/it]08/04/2024 20:28:33 - INFO - __main__ -   Step: 4601, LR: 1.079762396945451e-07, Loss: 0.03389532119035721
2024-08-05T03:28:42.054373743Z 
 81%|████████  | 4602/5712 [10:50:33<2:34:27,  8.35s/it]08/04/2024 20:28:42 - INFO - __main__ -   Step: 4602, LR: 1.078789610642282e-07, Loss: 0.09912557154893875
2024-08-05T03:28:50.298083950Z 
 81%|████████  | 4603/5712 [10:50:41<2:33:44,  8.32s/it]08/04/2024 20:28:50 - INFO - __main__ -   Step: 4603, LR: 1.0778168243391132e-07, Loss: 0.06239932030439377
2024-08-05T03:28:58.695100852Z 
 81%|████████  | 4604/5712 [10:50:49<2:34:02,  8.34s/it]08/04/2024 20:28:58 - INFO - __main__ -   Step: 4604, LR: 1.0768440380359443e-07, Loss: 0.1217971071600914
2024-08-05T03:29:07.012194652Z 
 81%|████████  | 4605/5712 [10:50:58<2:33:46,  8.33s/it]08/04/2024 20:29:07 - INFO - __main__ -   Step: 4605, LR: 1.0758712517327756e-07, Loss: 0.07346969842910767
2024-08-05T03:29:16.371316935Z 
 81%|████████  | 4606/5712 [10:51:07<2:39:17,  8.64s/it]08/04/2024 20:29:16 - INFO - __main__ -   Step: 4606, LR: 1.0748984654296067e-07, Loss: 0.06859366595745087
2024-08-05T03:29:24.759391342Z 
 81%|████████  | 4607/5712 [10:51:15<2:37:44,  8.57s/it]08/04/2024 20:29:24 - INFO - __main__ -   Step: 4607, LR: 1.0739256791264378e-07, Loss: 0.08156049251556396
2024-08-05T03:29:32.593802841Z 
 81%|████████  | 4608/5712 [10:51:23<2:33:34,  8.35s/it]08/04/2024 20:29:32 - INFO - __main__ -   Step: 4608, LR: 1.0729528928232689e-07, Loss: 0.048282843083143234
2024-08-05T03:29:40.545375622Z 
 81%|████████  | 4609/5712 [10:51:31<2:31:15,  8.23s/it]08/04/2024 20:29:40 - INFO - __main__ -   Step: 4609, LR: 1.0719801065201002e-07, Loss: 0.04710761830210686
2024-08-05T03:29:48.712035488Z 
 81%|████████  | 4610/5712 [10:51:39<2:30:46,  8.21s/it]08/04/2024 20:29:48 - INFO - __main__ -   Step: 4610, LR: 1.0710073202169313e-07, Loss: 0.05193399637937546
2024-08-05T03:29:57.770943245Z 
 81%|████████  | 4611/5712 [10:51:48<2:35:19,  8.46s/it]08/04/2024 20:29:57 - INFO - __main__ -   Step: 4611, LR: 1.0700345339137624e-07, Loss: 0.19195187091827393
2024-08-05T03:30:07.209853197Z 
 81%|████████  | 4612/5712 [10:51:58<2:40:32,  8.76s/it]08/04/2024 20:30:07 - INFO - __main__ -   Step: 4612, LR: 1.0690617476105935e-07, Loss: 0.10982706397771835
2024-08-05T03:30:15.186148910Z 
 81%|████████  | 4613/5712 [10:52:06<2:36:06,  8.52s/it]08/04/2024 20:30:15 - INFO - __main__ -   Step: 4613, LR: 1.0680889613074247e-07, Loss: 0.07062327116727829
2024-08-05T03:30:23.769740205Z 
 81%|████████  | 4614/5712 [10:52:14<2:36:17,  8.54s/it]08/04/2024 20:30:23 - INFO - __main__ -   Step: 4614, LR: 1.0671161750042559e-07, Loss: 0.04400821775197983
2024-08-05T03:30:31.954969916Z 
 81%|████████  | 4615/5712 [10:52:23<2:34:12,  8.43s/it]08/04/2024 20:30:31 - INFO - __main__ -   Step: 4615, LR: 1.066143388701087e-07, Loss: 0.11149434745311737
2024-08-05T03:30:39.709477551Z 
 81%|████████  | 4616/5712 [10:52:30<2:30:20,  8.23s/it]08/04/2024 20:30:39 - INFO - __main__ -   Step: 4616, LR: 1.0651706023979182e-07, Loss: 0.059542279690504074
2024-08-05T03:30:47.835596246Z 
 81%|████████  | 4617/5712 [10:52:38<2:29:37,  8.20s/it]08/04/2024 20:30:47 - INFO - __main__ -   Step: 4617, LR: 1.0641978160947493e-07, Loss: 0.09119849652051926
2024-08-05T03:30:56.381549850Z 
 81%|████████  | 4618/5712 [10:52:47<2:31:23,  8.30s/it]08/04/2024 20:30:56 - INFO - __main__ -   Step: 4618, LR: 1.0632250297915806e-07, Loss: 0.06730303168296814
2024-08-05T03:31:04.962506651Z 
 81%|████████  | 4619/5712 [10:52:56<2:32:46,  8.39s/it]08/04/2024 20:31:04 - INFO - __main__ -   Step: 4619, LR: 1.0622522434884117e-07, Loss: 0.07299862802028656
2024-08-05T03:31:13.886299251Z 
 81%|████████  | 4620/5712 [10:53:05<2:35:34,  8.55s/it]08/04/2024 20:31:13 - INFO - __main__ -   Step: 4620, LR: 1.0612794571852428e-07, Loss: 0.09358285367488861
2024-08-05T03:31:22.079440100Z 
 81%|████████  | 4621/5712 [10:53:13<2:33:29,  8.44s/it]08/04/2024 20:31:22 - INFO - __main__ -   Step: 4621, LR: 1.0603066708820739e-07, Loss: 0.06022908166050911
2024-08-05T03:31:30.552103061Z 
 81%|████████  | 4622/5712 [10:53:21<2:33:31,  8.45s/it]08/04/2024 20:31:30 - INFO - __main__ -   Step: 4622, LR: 1.059333884578905e-07, Loss: 0.03928261995315552
2024-08-05T03:31:38.899759479Z 
 81%|████████  | 4623/5712 [10:53:30<2:32:49,  8.42s/it]08/04/2024 20:31:38 - INFO - __main__ -   Step: 4623, LR: 1.0583610982757363e-07, Loss: 0.0717313140630722
2024-08-05T03:31:47.358097878Z 
 81%|████████  | 4624/5712 [10:53:38<2:32:53,  8.43s/it]08/04/2024 20:31:47 - INFO - __main__ -   Step: 4624, LR: 1.0573883119725674e-07, Loss: 0.05978856235742569
2024-08-05T03:31:55.330364540Z 
 81%|████████  | 4625/5712 [10:53:46<2:30:15,  8.29s/it]08/04/2024 20:31:55 - INFO - __main__ -   Step: 4625, LR: 1.0564155256693985e-07, Loss: 0.08710653334856033
2024-08-05T03:32:03.698437346Z 
 81%|████████  | 4626/5712 [10:53:54<2:30:31,  8.32s/it]08/04/2024 20:32:03 - INFO - __main__ -   Step: 4626, LR: 1.0554427393662297e-07, Loss: 0.056854166090488434
2024-08-05T03:32:12.226454227Z 
 81%|████████  | 4627/5712 [10:54:03<2:31:31,  8.38s/it]08/04/2024 20:32:12 - INFO - __main__ -   Step: 4627, LR: 1.0544699530630609e-07, Loss: 0.04297608882188797
2024-08-05T03:32:20.977834774Z 
 81%|████████  | 4628/5712 [10:54:12<2:33:24,  8.49s/it]08/04/2024 20:32:20 - INFO - __main__ -   Step: 4628, LR: 1.053497166759892e-07, Loss: 0.10278932750225067
2024-08-05T03:32:29.837375451Z 
 81%|████████  | 4629/5712 [10:54:20<2:35:15,  8.60s/it]08/04/2024 20:32:29 - INFO - __main__ -   Step: 4629, LR: 1.0525243804567232e-07, Loss: 0.05489334464073181
2024-08-05T03:32:37.965280661Z 
 81%|████████  | 4630/5712 [10:54:29<2:32:33,  8.46s/it]08/04/2024 20:32:37 - INFO - __main__ -   Step: 4630, LR: 1.0515515941535543e-07, Loss: 0.07074607163667679
2024-08-05T03:32:46.680490404Z 
 81%|████████  | 4631/5712 [10:54:37<2:33:47,  8.54s/it]08/04/2024 20:32:46 - INFO - __main__ -   Step: 4631, LR: 1.0505788078503854e-07, Loss: 0.12526609003543854
2024-08-05T03:32:54.764793403Z 
 81%|████████  | 4632/5712 [10:54:45<2:31:12,  8.40s/it]08/04/2024 20:32:54 - INFO - __main__ -   Step: 4632, LR: 1.0496060215472167e-07, Loss: 0.08354935050010681
2024-08-05T03:33:02.707290543Z 
 81%|████████  | 4633/5712 [10:54:53<2:28:36,  8.26s/it]08/04/2024 20:33:02 - INFO - __main__ -   Step: 4633, LR: 1.0486332352440478e-07, Loss: 0.07879070937633514
2024-08-05T03:33:10.833625644Z 
 81%|████████  | 4634/5712 [10:55:01<2:27:43,  8.22s/it]08/04/2024 20:33:10 - INFO - __main__ -   Step: 4634, LR: 1.0476604489408789e-07, Loss: 0.09815038740634918
2024-08-05T03:33:19.720378493Z 
 81%|████████  | 4635/5712 [10:55:10<2:31:09,  8.42s/it]08/04/2024 20:33:19 - INFO - __main__ -   Step: 4635, LR: 1.0466876626377099e-07, Loss: 0.043038636445999146
2024-08-05T03:33:29.255749896Z 
 81%|████████  | 4636/5712 [10:55:20<2:37:00,  8.76s/it]08/04/2024 20:33:29 - INFO - __main__ -   Step: 4636, LR: 1.0457148763345412e-07, Loss: 0.06636957824230194
2024-08-05T03:33:37.613186936Z 
 81%|████████  | 4637/5712 [10:55:28<2:34:44,  8.64s/it]08/04/2024 20:33:37 - INFO - __main__ -   Step: 4637, LR: 1.0447420900313723e-07, Loss: 0.0816875770688057
2024-08-05T03:33:45.799698396Z 
 81%|████████  | 4638/5712 [10:55:36<2:32:10,  8.50s/it]08/04/2024 20:33:45 - INFO - __main__ -   Step: 4638, LR: 1.0437693037282034e-07, Loss: 0.050899408757686615
2024-08-05T03:33:55.153971479Z 
 81%|████████  | 4639/5712 [10:55:46<2:36:36,  8.76s/it]08/04/2024 20:33:55 - INFO - __main__ -   Step: 4639, LR: 1.0427965174250345e-07, Loss: 0.03614955022931099
2024-08-05T03:34:03.276474428Z 
 81%|████████  | 4640/5712 [10:55:54<2:33:03,  8.57s/it]08/04/2024 20:34:03 - INFO - __main__ -   Step: 4640, LR: 1.0418237311218657e-07, Loss: 0.06860104203224182
2024-08-05T03:34:11.732988243Z 
 81%|████████▏ | 4641/5712 [10:56:02<2:32:19,  8.53s/it]08/04/2024 20:34:11 - INFO - __main__ -   Step: 4641, LR: 1.0408509448186969e-07, Loss: 0.07065501064062119
2024-08-05T03:34:19.751360227Z 
 81%|████████▏ | 4642/5712 [10:56:10<2:29:25,  8.38s/it]08/04/2024 20:34:19 - INFO - __main__ -   Step: 4642, LR: 1.039878158515528e-07, Loss: 0.07524341344833374
2024-08-05T03:34:28.572371940Z 
 81%|████████▏ | 4643/5712 [10:56:19<2:31:38,  8.51s/it]08/04/2024 20:34:28 - INFO - __main__ -   Step: 4643, LR: 1.0389053722123592e-07, Loss: 0.0338708870112896
2024-08-05T03:34:37.704572886Z 
 81%|████████▏ | 4644/5712 [10:56:28<2:34:49,  8.70s/it]08/04/2024 20:34:37 - INFO - __main__ -   Step: 4644, LR: 1.0379325859091903e-07, Loss: 0.09392198920249939
2024-08-05T03:34:46.755196211Z 
 81%|████████▏ | 4645/5712 [10:56:37<2:36:33,  8.80s/it]08/04/2024 20:34:46 - INFO - __main__ -   Step: 4645, LR: 1.0369597996060215e-07, Loss: 0.042509227991104126
2024-08-05T03:34:55.175104838Z 
 81%|████████▏ | 4646/5712 [10:56:46<2:34:22,  8.69s/it]08/04/2024 20:34:55 - INFO - __main__ -   Step: 4646, LR: 1.0359870133028527e-07, Loss: 0.055477723479270935
2024-08-05T03:35:04.064600391Z 
 81%|████████▏ | 4647/5712 [10:56:55<2:35:17,  8.75s/it]08/04/2024 20:35:04 - INFO - __main__ -   Step: 4647, LR: 1.0350142269996838e-07, Loss: 0.05983235314488411
2024-08-05T03:35:12.246975615Z 
 81%|████████▏ | 4648/5712 [10:57:03<2:32:07,  8.58s/it]08/04/2024 20:35:12 - INFO - __main__ -   Step: 4648, LR: 1.0340414406965149e-07, Loss: 0.06580992788076401
2024-08-05T03:35:20.312696721Z 
 81%|████████▏ | 4649/5712 [10:57:11<2:29:15,  8.42s/it]08/04/2024 20:35:20 - INFO - __main__ -   Step: 4649, LR: 1.033068654393346e-07, Loss: 0.057108163833618164
2024-08-05T03:35:28.536149434Z 
 81%|████████▏ | 4650/5712 [10:57:19<2:28:03,  8.36s/it]08/04/2024 20:35:28 - INFO - __main__ -   Step: 4650, LR: 1.0320958680901773e-07, Loss: 0.07614527642726898
2024-08-05T03:35:37.092123913Z 
 81%|████████▏ | 4651/5712 [10:57:28<2:28:55,  8.42s/it]08/04/2024 20:35:37 - INFO - __main__ -   Step: 4651, LR: 1.0311230817870084e-07, Loss: 0.049660392105579376
2024-08-05T03:35:45.443756348Z 
 81%|████████▏ | 4652/5712 [10:57:36<2:28:24,  8.40s/it]08/04/2024 20:35:45 - INFO - __main__ -   Step: 4652, LR: 1.0301502954838395e-07, Loss: 0.11790961027145386
2024-08-05T03:35:53.904368029Z 
 81%|████████▏ | 4653/5712 [10:57:45<2:28:35,  8.42s/it]08/04/2024 20:35:53 - INFO - __main__ -   Step: 4653, LR: 1.0291775091806706e-07, Loss: 0.0855681449174881
2024-08-05T03:36:02.602142788Z 
 81%|████████▏ | 4654/5712 [10:57:53<2:29:55,  8.50s/it]08/04/2024 20:36:02 - INFO - __main__ -   Step: 4654, LR: 1.0282047228775019e-07, Loss: 0.0646602213382721
2024-08-05T03:36:10.761803646Z 
 81%|████████▏ | 4655/5712 [10:58:01<2:27:57,  8.40s/it]08/04/2024 20:36:10 - INFO - __main__ -   Step: 4655, LR: 1.027231936574333e-07, Loss: 0.03588477522134781
2024-08-05T03:36:19.983339412Z 
 82%|████████▏ | 4656/5712 [10:58:11<2:32:10,  8.65s/it]08/04/2024 20:36:19 - INFO - __main__ -   Step: 4656, LR: 1.0262591502711641e-07, Loss: 0.07438874244689941
2024-08-05T03:36:28.107660960Z 
 82%|████████▏ | 4657/5712 [10:58:19<2:29:16,  8.49s/it]08/04/2024 20:36:28 - INFO - __main__ -   Step: 4657, LR: 1.0252863639679953e-07, Loss: 0.09257014095783234
2024-08-05T03:36:36.749399760Z 
 82%|████████▏ | 4658/5712 [10:58:27<2:29:56,  8.54s/it]08/04/2024 20:36:36 - INFO - __main__ -   Step: 4658, LR: 1.0243135776648264e-07, Loss: 0.23731881380081177
2024-08-05T03:36:44.695292345Z 
 82%|████████▏ | 4659/5712 [10:58:35<2:26:41,  8.36s/it]08/04/2024 20:36:44 - INFO - __main__ -   Step: 4659, LR: 1.0233407913616576e-07, Loss: 0.1396036297082901
2024-08-05T03:36:53.454682990Z 
 82%|████████▏ | 4660/5712 [10:58:44<2:28:39,  8.48s/it]08/04/2024 20:36:53 - INFO - __main__ -   Step: 4660, LR: 1.0223680050584888e-07, Loss: 0.09941999614238739
2024-08-05T03:37:02.245570236Z 
 82%|████████▏ | 4661/5712 [10:58:53<2:30:09,  8.57s/it]08/04/2024 20:37:02 - INFO - __main__ -   Step: 4661, LR: 1.0213952187553199e-07, Loss: 0.06222625449299812
2024-08-05T03:37:10.779657213Z 
 82%|████████▏ | 4662/5712 [10:59:01<2:29:48,  8.56s/it]08/04/2024 20:37:10 - INFO - __main__ -   Step: 4662, LR: 1.020422432452151e-07, Loss: 0.018763234838843346
2024-08-05T03:37:19.326731673Z 
 82%|████████▏ | 4663/5712 [10:59:10<2:29:35,  8.56s/it]08/04/2024 20:37:19 - INFO - __main__ -   Step: 4663, LR: 1.0194496461489823e-07, Loss: 0.07537596672773361
2024-08-05T03:37:27.911783708Z 
 82%|████████▏ | 4664/5712 [10:59:19<2:29:36,  8.57s/it]08/04/2024 20:37:27 - INFO - __main__ -   Step: 4664, LR: 1.0184768598458134e-07, Loss: 0.05156467482447624
2024-08-05T03:37:36.105071981Z 
 82%|████████▏ | 4665/5712 [10:59:27<2:27:30,  8.45s/it]08/04/2024 20:37:36 - INFO - __main__ -   Step: 4665, LR: 1.0175040735426445e-07, Loss: 0.09300432354211807
2024-08-05T03:37:44.332448399Z 
 82%|████████▏ | 4666/5712 [10:59:35<2:26:11,  8.39s/it]08/04/2024 20:37:44 - INFO - __main__ -   Step: 4666, LR: 1.0165312872394756e-07, Loss: 0.07060426473617554
2024-08-05T03:37:53.046776638Z 
 82%|████████▏ | 4667/5712 [10:59:44<2:27:46,  8.48s/it]08/04/2024 20:37:53 - INFO - __main__ -   Step: 4667, LR: 1.0155585009363068e-07, Loss: 0.19295406341552734
2024-08-05T03:38:02.117914939Z 
 82%|████████▏ | 4668/5712 [10:59:53<2:30:41,  8.66s/it]08/04/2024 20:38:02 - INFO - __main__ -   Step: 4668, LR: 1.014585714633138e-07, Loss: 0.05550434812903404
2024-08-05T03:38:11.160197138Z 
 82%|████████▏ | 4669/5712 [11:00:02<2:32:32,  8.78s/it]08/04/2024 20:38:11 - INFO - __main__ -   Step: 4669, LR: 1.0136129283299691e-07, Loss: 0.052904754877090454
2024-08-05T03:38:19.785823766Z 
 82%|████████▏ | 4670/5712 [11:00:10<2:31:36,  8.73s/it]08/04/2024 20:38:19 - INFO - __main__ -   Step: 4670, LR: 1.0126401420268003e-07, Loss: 0.037561818957328796
2024-08-05T03:38:28.415014662Z 
 82%|████████▏ | 4671/5712 [11:00:19<2:30:56,  8.70s/it]08/04/2024 20:38:28 - INFO - __main__ -   Step: 4671, LR: 1.0116673557236314e-07, Loss: 0.11076490581035614
2024-08-05T03:38:36.998639656Z 
 82%|████████▏ | 4672/5712 [11:00:28<2:30:11,  8.67s/it]08/04/2024 20:38:36 - INFO - __main__ -   Step: 4672, LR: 1.0106945694204626e-07, Loss: 0.051900703459978104
2024-08-05T03:38:45.389309023Z 
 82%|████████▏ | 4673/5712 [11:00:36<2:28:37,  8.58s/it]08/04/2024 20:38:45 - INFO - __main__ -   Step: 4673, LR: 1.0097217831172938e-07, Loss: 0.054355863481760025
2024-08-05T03:38:53.460719343Z 
 82%|████████▏ | 4674/5712 [11:00:44<2:25:49,  8.43s/it]08/04/2024 20:38:53 - INFO - __main__ -   Step: 4674, LR: 1.0087489968141248e-07, Loss: 0.0781722292304039
2024-08-05T03:39:01.666932537Z 
 82%|████████▏ | 4675/5712 [11:00:52<2:24:31,  8.36s/it]08/04/2024 20:39:01 - INFO - __main__ -   Step: 4675, LR: 1.0077762105109559e-07, Loss: 0.11331643164157867
2024-08-05T03:39:10.220948624Z 
 82%|████████▏ | 4676/5712 [11:01:01<2:25:23,  8.42s/it]08/04/2024 20:39:10 - INFO - __main__ -   Step: 4676, LR: 1.006803424207787e-07, Loss: 0.07421799749135971
2024-08-05T03:39:18.668361254Z 
 82%|████████▏ | 4677/5712 [11:01:09<2:25:23,  8.43s/it]08/04/2024 20:39:18 - INFO - __main__ -   Step: 4677, LR: 1.0058306379046183e-07, Loss: 0.09132833033800125
2024-08-05T03:39:28.054116483Z 
 82%|████████▏ | 4678/5712 [11:01:19<2:30:11,  8.72s/it]08/04/2024 20:39:28 - INFO - __main__ -   Step: 4678, LR: 1.0048578516014494e-07, Loss: 0.07766032963991165
2024-08-05T03:39:36.520027910Z 
 82%|████████▏ | 4679/5712 [11:01:27<2:28:45,  8.64s/it]08/04/2024 20:39:36 - INFO - __main__ -   Step: 4679, LR: 1.0038850652982805e-07, Loss: 0.08220875263214111
2024-08-05T03:39:45.213381220Z 
 82%|████████▏ | 4680/5712 [11:01:36<2:28:53,  8.66s/it]08/04/2024 20:39:45 - INFO - __main__ -   Step: 4680, LR: 1.0029122789951116e-07, Loss: 0.038463789969682693
2024-08-05T03:39:52.783707652Z 
 82%|████████▏ | 4681/5712 [11:01:43<2:23:08,  8.33s/it]08/04/2024 20:39:52 - INFO - __main__ -   Step: 4681, LR: 1.0019394926919429e-07, Loss: 0.05000252276659012
2024-08-05T03:40:01.271810135Z 
 82%|████████▏ | 4682/5712 [11:01:52<2:23:49,  8.38s/it]08/04/2024 20:40:01 - INFO - __main__ -   Step: 4682, LR: 1.000966706388774e-07, Loss: 0.09574765712022781
2024-08-05T03:40:09.282541095Z 
 82%|████████▏ | 4683/5712 [11:02:00<2:21:47,  8.27s/it]08/04/2024 20:40:09 - INFO - __main__ -   Step: 4683, LR: 9.999939200856051e-08, Loss: 0.07301364839076996
2024-08-05T03:40:17.678894752Z 
 82%|████████▏ | 4684/5712 [11:02:08<2:22:18,  8.31s/it]08/04/2024 20:40:17 - INFO - __main__ -   Step: 4684, LR: 9.990211337824362e-08, Loss: 0.034868594259023666
2024-08-05T03:40:26.931319387Z 
 82%|████████▏ | 4685/5712 [11:02:18<2:27:02,  8.59s/it]08/04/2024 20:40:26 - INFO - __main__ -   Step: 4685, LR: 9.980483474792674e-08, Loss: 0.047300778329372406
2024-08-05T03:40:35.439047064Z 
 82%|████████▏ | 4686/5712 [11:02:26<2:26:28,  8.57s/it]08/04/2024 20:40:35 - INFO - __main__ -   Step: 4686, LR: 9.970755611760986e-08, Loss: 0.03788869082927704
2024-08-05T03:40:44.004530141Z 
 82%|████████▏ | 4687/5712 [11:02:35<2:26:19,  8.57s/it]08/04/2024 20:40:44 - INFO - __main__ -   Step: 4687, LR: 9.961027748729297e-08, Loss: 0.06074809283018112
2024-08-05T03:40:52.651825759Z 
 82%|████████▏ | 4688/5712 [11:02:43<2:26:36,  8.59s/it]08/04/2024 20:40:52 - INFO - __main__ -   Step: 4688, LR: 9.951299885697609e-08, Loss: 0.11106719076633453
2024-08-05T03:41:00.793311916Z 
 82%|████████▏ | 4689/5712 [11:02:51<2:24:09,  8.46s/it]08/04/2024 20:41:00 - INFO - __main__ -   Step: 4689, LR: 9.94157202266592e-08, Loss: 0.043568797409534454
2024-08-05T03:41:08.794985207Z 
 82%|████████▏ | 4690/5712 [11:02:59<2:21:42,  8.32s/it]08/04/2024 20:41:08 - INFO - __main__ -   Step: 4690, LR: 9.931844159634232e-08, Loss: 0.04338639974594116
2024-08-05T03:41:16.857496749Z 
 82%|████████▏ | 4691/5712 [11:03:08<2:20:15,  8.24s/it]08/04/2024 20:41:16 - INFO - __main__ -   Step: 4691, LR: 9.922116296602544e-08, Loss: 0.09484447538852692
2024-08-05T03:41:24.906177422Z 
 82%|████████▏ | 4692/5712 [11:03:16<2:19:07,  8.18s/it]08/04/2024 20:41:24 - INFO - __main__ -   Step: 4692, LR: 9.912388433570855e-08, Loss: 0.0552750788629055
2024-08-05T03:41:33.315554669Z 
 82%|████████▏ | 4693/5712 [11:03:24<2:20:08,  8.25s/it]08/04/2024 20:41:33 - INFO - __main__ -   Step: 4693, LR: 9.902660570539166e-08, Loss: 0.07398030906915665
2024-08-05T03:41:42.194694875Z 
 82%|████████▏ | 4694/5712 [11:03:33<2:23:11,  8.44s/it]08/04/2024 20:41:42 - INFO - __main__ -   Step: 4694, LR: 9.892932707507477e-08, Loss: 0.08906424045562744
2024-08-05T03:41:50.965379833Z 
 82%|████████▏ | 4695/5712 [11:03:42<2:24:44,  8.54s/it]08/04/2024 20:41:50 - INFO - __main__ -   Step: 4695, LR: 9.88320484447579e-08, Loss: 0.09928855299949646
2024-08-05T03:41:59.582408085Z 
 82%|████████▏ | 4696/5712 [11:03:50<2:24:59,  8.56s/it]08/04/2024 20:41:59 - INFO - __main__ -   Step: 4696, LR: 9.873476981444101e-08, Loss: 0.05961957201361656
2024-08-05T03:42:08.276627463Z 
 82%|████████▏ | 4697/5712 [11:03:59<2:25:31,  8.60s/it]08/04/2024 20:42:08 - INFO - __main__ -   Step: 4697, LR: 9.863749118412412e-08, Loss: 0.05151095241308212
2024-08-05T03:42:15.848918712Z 
 82%|████████▏ | 4698/5712 [11:04:06<2:20:09,  8.29s/it]08/04/2024 20:42:15 - INFO - __main__ -   Step: 4698, LR: 9.854021255380724e-08, Loss: 0.05929841473698616
2024-08-05T03:42:24.366364463Z 
 82%|████████▏ | 4699/5712 [11:04:15<2:21:09,  8.36s/it]08/04/2024 20:42:24 - INFO - __main__ -   Step: 4699, LR: 9.844293392349036e-08, Loss: 0.13810831308364868
2024-08-05T03:42:32.791373480Z 
 82%|████████▏ | 4700/5712 [11:04:23<2:21:20,  8.38s/it]08/04/2024 20:42:32 - INFO - __main__ -   Step: 4700, LR: 9.834565529317347e-08, Loss: 0.04841454699635506
2024-08-05T03:42:41.063043393Z 
 82%|████████▏ | 4701/5712 [11:04:32<2:20:39,  8.35s/it]08/04/2024 20:42:41 - INFO - __main__ -   Step: 4701, LR: 9.824837666285659e-08, Loss: 0.10255801677703857
2024-08-05T03:42:49.302742530Z 
 82%|████████▏ | 4702/5712 [11:04:40<2:19:57,  8.31s/it]08/04/2024 20:42:49 - INFO - __main__ -   Step: 4702, LR: 9.81510980325397e-08, Loss: 0.08536042273044586
2024-08-05T03:42:58.142136915Z 
 82%|████████▏ | 4703/5712 [11:04:49<2:22:28,  8.47s/it]08/04/2024 20:42:58 - INFO - __main__ -   Step: 4703, LR: 9.805381940222281e-08, Loss: 0.10946743935346603
2024-08-05T03:43:06.464622063Z 
 82%|████████▏ | 4704/5712 [11:04:57<2:21:34,  8.43s/it]08/04/2024 20:43:06 - INFO - __main__ -   Step: 4704, LR: 9.795654077190594e-08, Loss: 0.07017917931079865
2024-08-05T03:43:15.216926029Z 
 82%|████████▏ | 4705/5712 [11:05:06<2:23:04,  8.52s/it]08/04/2024 20:43:15 - INFO - __main__ -   Step: 4705, LR: 9.785926214158905e-08, Loss: 0.1229037195444107
2024-08-05T03:43:23.322626809Z 
 82%|████████▏ | 4706/5712 [11:05:14<2:20:49,  8.40s/it]08/04/2024 20:43:23 - INFO - __main__ -   Step: 4706, LR: 9.776198351127216e-08, Loss: 0.06698885560035706
2024-08-05T03:43:31.803670762Z 
 82%|████████▏ | 4707/5712 [11:05:22<2:21:05,  8.42s/it]08/04/2024 20:43:31 - INFO - __main__ -   Step: 4707, LR: 9.766470488095527e-08, Loss: 0.04232360050082207
2024-08-05T03:43:40.267204495Z 
 82%|████████▏ | 4708/5712 [11:05:31<2:21:09,  8.44s/it]08/04/2024 20:43:40 - INFO - __main__ -   Step: 4708, LR: 9.75674262506384e-08, Loss: 0.11837714910507202
2024-08-05T03:43:48.781080790Z 
 82%|████████▏ | 4709/5712 [11:05:39<2:21:24,  8.46s/it]08/04/2024 20:43:48 - INFO - __main__ -   Step: 4709, LR: 9.747014762032151e-08, Loss: 0.14858198165893555
2024-08-05T03:43:56.993990121Z 
 82%|████████▏ | 4710/5712 [11:05:48<2:20:02,  8.39s/it]08/04/2024 20:43:56 - INFO - __main__ -   Step: 4710, LR: 9.737286899000462e-08, Loss: 0.07137790322303772
2024-08-05T03:44:05.873357333Z 
 82%|████████▏ | 4711/5712 [11:05:57<2:22:22,  8.53s/it]08/04/2024 20:44:05 - INFO - __main__ -   Step: 4711, LR: 9.727559035968772e-08, Loss: 0.09549436718225479
2024-08-05T03:44:14.457256558Z 
 82%|████████▏ | 4712/5712 [11:06:05<2:22:28,  8.55s/it]08/04/2024 20:44:14 - INFO - __main__ -   Step: 4712, LR: 9.717831172937083e-08, Loss: 0.05958383530378342
2024-08-05T03:44:23.426956353Z 
 83%|████████▎ | 4713/5712 [11:06:14<2:24:26,  8.67s/it]08/04/2024 20:44:23 - INFO - __main__ -   Step: 4713, LR: 9.708103309905396e-08, Loss: 0.04549672454595566
2024-08-05T03:44:31.700254706Z 
 83%|████████▎ | 4714/5712 [11:06:22<2:22:17,  8.55s/it]08/04/2024 20:44:31 - INFO - __main__ -   Step: 4714, LR: 9.698375446873707e-08, Loss: 0.06875833868980408
2024-08-05T03:44:39.775771713Z 
 83%|████████▎ | 4715/5712 [11:06:30<2:19:45,  8.41s/it]08/04/2024 20:44:39 - INFO - __main__ -   Step: 4715, LR: 9.688647583842018e-08, Loss: 0.06642013788223267
2024-08-05T03:44:48.105189304Z 
 83%|████████▎ | 4716/5712 [11:06:39<2:19:12,  8.39s/it]08/04/2024 20:44:48 - INFO - __main__ -   Step: 4716, LR: 9.67891972081033e-08, Loss: 0.03689980506896973
2024-08-05T03:44:56.708487011Z 
 83%|████████▎ | 4717/5712 [11:06:47<2:20:09,  8.45s/it]08/04/2024 20:44:56 - INFO - __main__ -   Step: 4717, LR: 9.669191857778642e-08, Loss: 0.055608078837394714
2024-08-05T03:45:04.889803811Z 
 83%|████████▎ | 4718/5712 [11:06:56<2:18:40,  8.37s/it]08/04/2024 20:45:04 - INFO - __main__ -   Step: 4718, LR: 9.659463994746953e-08, Loss: 0.051759831607341766
2024-08-05T03:45:13.225282411Z 
 83%|████████▎ | 4719/5712 [11:07:04<2:18:21,  8.36s/it]08/04/2024 20:45:13 - INFO - __main__ -   Step: 4719, LR: 9.649736131715265e-08, Loss: 0.053926993161439896
2024-08-05T03:45:22.330239052Z 
 83%|████████▎ | 4720/5712 [11:07:13<2:21:54,  8.58s/it]08/04/2024 20:45:22 - INFO - __main__ -   Step: 4720, LR: 9.640008268683576e-08, Loss: 0.10943622142076492
2024-08-05T03:45:30.854862036Z 
 83%|████████▎ | 4721/5712 [11:07:22<2:21:28,  8.57s/it]08/04/2024 20:45:30 - INFO - __main__ -   Step: 4721, LR: 9.630280405651887e-08, Loss: 0.09450141340494156
2024-08-05T03:45:39.043463520Z 
 83%|████████▎ | 4722/5712 [11:07:30<2:19:28,  8.45s/it]08/04/2024 20:45:39 - INFO - __main__ -   Step: 4722, LR: 9.6205525426202e-08, Loss: 0.09338478744029999
2024-08-05T03:45:47.373620887Z 
 83%|████████▎ | 4723/5712 [11:07:38<2:18:43,  8.42s/it]08/04/2024 20:45:47 - INFO - __main__ -   Step: 4723, LR: 9.610824679588511e-08, Loss: 0.04546370357275009
2024-08-05T03:45:55.940131823Z 
 83%|████████▎ | 4724/5712 [11:07:47<2:19:19,  8.46s/it]08/04/2024 20:45:55 - INFO - __main__ -   Step: 4724, LR: 9.601096816556822e-08, Loss: 0.08486144244670868
2024-08-05T03:46:04.915719991Z 
 83%|████████▎ | 4725/5712 [11:07:56<2:21:43,  8.62s/it]08/04/2024 20:46:04 - INFO - __main__ -   Step: 4725, LR: 9.591368953525133e-08, Loss: 0.10659781098365784
2024-08-05T03:46:13.171397623Z 
 83%|████████▎ | 4726/5712 [11:08:04<2:19:48,  8.51s/it]08/04/2024 20:46:13 - INFO - __main__ -   Step: 4726, LR: 9.581641090493446e-08, Loss: 0.05855204164981842
2024-08-05T03:46:21.708571151Z 
 83%|████████▎ | 4727/5712 [11:08:12<2:19:48,  8.52s/it]08/04/2024 20:46:21 - INFO - __main__ -   Step: 4727, LR: 9.571913227461757e-08, Loss: 0.12105710804462433
2024-08-05T03:46:30.300147198Z 
 83%|████████▎ | 4728/5712 [11:08:21<2:20:02,  8.54s/it]08/04/2024 20:46:30 - INFO - __main__ -   Step: 4728, LR: 9.562185364430068e-08, Loss: 0.06017770618200302
2024-08-05T03:46:38.711551810Z 
 83%|████████▎ | 4729/5712 [11:08:29<2:19:16,  8.50s/it]08/04/2024 20:46:38 - INFO - __main__ -   Step: 4729, LR: 9.55245750139838e-08, Loss: 0.06469328701496124
2024-08-05T03:46:47.084000539Z 
 83%|████████▎ | 4730/5712 [11:08:38<2:18:29,  8.46s/it]08/04/2024 20:46:47 - INFO - __main__ -   Step: 4730, LR: 9.542729638366691e-08, Loss: 0.04502309858798981
2024-08-05T03:46:55.365419070Z 
 83%|████████▎ | 4731/5712 [11:08:46<2:17:28,  8.41s/it]08/04/2024 20:46:55 - INFO - __main__ -   Step: 4731, LR: 9.533001775335003e-08, Loss: 0.11245141923427582
2024-08-05T03:47:03.430278550Z 
 83%|████████▎ | 4732/5712 [11:08:54<2:15:38,  8.31s/it]08/04/2024 20:47:03 - INFO - __main__ -   Step: 4732, LR: 9.523273912303315e-08, Loss: 0.06501510739326477
2024-08-05T03:47:12.233289075Z 
 83%|████████▎ | 4733/5712 [11:09:03<2:17:56,  8.45s/it]08/04/2024 20:47:12 - INFO - __main__ -   Step: 4733, LR: 9.513546049271626e-08, Loss: 0.08136981725692749
2024-08-05T03:47:21.156226125Z 
 83%|████████▎ | 4734/5712 [11:09:12<2:20:05,  8.59s/it]08/04/2024 20:47:21 - INFO - __main__ -   Step: 4734, LR: 9.503818186239937e-08, Loss: 0.11361071467399597
2024-08-05T03:47:29.329013280Z 
 83%|████████▎ | 4735/5712 [11:09:20<2:17:53,  8.47s/it]08/04/2024 20:47:29 - INFO - __main__ -   Step: 4735, LR: 9.49409032320825e-08, Loss: 0.11511241644620895
2024-08-05T03:47:37.714042432Z 
 83%|████████▎ | 4736/5712 [11:09:28<2:17:20,  8.44s/it]08/04/2024 20:47:37 - INFO - __main__ -   Step: 4736, LR: 9.484362460176561e-08, Loss: 0.09030895680189133
2024-08-05T03:47:46.289921946Z 
 83%|████████▎ | 4737/5712 [11:09:37<2:17:50,  8.48s/it]08/04/2024 20:47:46 - INFO - __main__ -   Step: 4737, LR: 9.474634597144872e-08, Loss: 0.05652012303471565
2024-08-05T03:47:54.776033901Z 
 83%|████████▎ | 4738/5712 [11:09:45<2:17:43,  8.48s/it]08/04/2024 20:47:54 - INFO - __main__ -   Step: 4738, LR: 9.464906734113183e-08, Loss: 0.028547396883368492
2024-08-05T03:48:03.615810630Z 
 83%|████████▎ | 4739/5712 [11:09:54<2:19:18,  8.59s/it]08/04/2024 20:48:03 - INFO - __main__ -   Step: 4739, LR: 9.455178871081495e-08, Loss: 0.06906941533088684
2024-08-05T03:48:12.032156338Z 
 83%|████████▎ | 4740/5712 [11:10:03<2:18:19,  8.54s/it]08/04/2024 20:48:12 - INFO - __main__ -   Step: 4740, LR: 9.445451008049807e-08, Loss: 0.10682012140750885
2024-08-05T03:48:20.465228719Z 
 83%|████████▎ | 4741/5712 [11:10:11<2:17:40,  8.51s/it]08/04/2024 20:48:20 - INFO - __main__ -   Step: 4741, LR: 9.435723145018118e-08, Loss: 0.07002750039100647
2024-08-05T03:48:29.294199464Z 
 83%|████████▎ | 4742/5712 [11:10:20<2:19:05,  8.60s/it]08/04/2024 20:48:29 - INFO - __main__ -   Step: 4742, LR: 9.42599528198643e-08, Loss: 0.10662499070167542
2024-08-05T03:48:37.710567581Z 
 83%|████████▎ | 4743/5712 [11:10:28<2:18:02,  8.55s/it]08/04/2024 20:48:37 - INFO - __main__ -   Step: 4743, LR: 9.416267418954741e-08, Loss: 0.10437525808811188
2024-08-05T03:48:46.744976657Z 
 83%|████████▎ | 4744/5712 [11:10:37<2:20:15,  8.69s/it]08/04/2024 20:48:46 - INFO - __main__ -   Step: 4744, LR: 9.406539555923052e-08, Loss: 0.05991276726126671
2024-08-05T03:48:56.019910920Z 
 83%|████████▎ | 4745/5712 [11:10:47<2:22:55,  8.87s/it]08/04/2024 20:48:56 - INFO - __main__ -   Step: 4745, LR: 9.396811692891365e-08, Loss: 0.06971640884876251
2024-08-05T03:49:04.735197358Z 
 83%|████████▎ | 4746/5712 [11:10:55<2:22:02,  8.82s/it]08/04/2024 20:49:04 - INFO - __main__ -   Step: 4746, LR: 9.387083829859676e-08, Loss: 0.05353359878063202
2024-08-05T03:49:13.179338749Z 
 83%|████████▎ | 4747/5712 [11:11:04<2:20:03,  8.71s/it]08/04/2024 20:49:13 - INFO - __main__ -   Step: 4747, LR: 9.377355966827987e-08, Loss: 0.049043722450733185
2024-08-05T03:49:21.473933679Z 
 83%|████████▎ | 4748/5712 [11:11:12<2:17:55,  8.58s/it]08/04/2024 20:49:21 - INFO - __main__ -   Step: 4748, LR: 9.367628103796298e-08, Loss: 0.06778126955032349
2024-08-05T03:49:29.881255983Z 
 83%|████████▎ | 4749/5712 [11:11:21<2:16:55,  8.53s/it]08/04/2024 20:49:29 - INFO - __main__ -   Step: 4749, LR: 9.357900240764611e-08, Loss: 0.07884113490581512
2024-08-05T03:49:38.426041713Z 
 83%|████████▎ | 4750/5712 [11:11:29<2:16:50,  8.54s/it]08/04/2024 20:49:38 - INFO - __main__ -   Step: 4750, LR: 9.348172377732921e-08, Loss: 0.04862261563539505
2024-08-05T03:49:47.178409835Z 
 83%|████████▎ | 4751/5712 [11:11:38<2:17:45,  8.60s/it]08/04/2024 20:49:47 - INFO - __main__ -   Step: 4751, LR: 9.338444514701232e-08, Loss: 0.10223528742790222
2024-08-05T03:49:55.969845396Z 
 83%|████████▎ | 4752/5712 [11:11:47<2:18:31,  8.66s/it]08/04/2024 20:49:55 - INFO - __main__ -   Step: 4752, LR: 9.328716651669543e-08, Loss: 0.06806229799985886
2024-08-05T03:50:04.832930954Z 
 83%|████████▎ | 4753/5712 [11:11:55<2:19:21,  8.72s/it]08/04/2024 20:50:04 - INFO - __main__ -   Step: 4753, LR: 9.318988788637854e-08, Loss: 0.05268220603466034
2024-08-05T03:50:13.346343694Z 
 83%|████████▎ | 4754/5712 [11:12:04<2:18:13,  8.66s/it]08/04/2024 20:50:13 - INFO - __main__ -   Step: 4754, LR: 9.309260925606167e-08, Loss: 0.06260192394256592
2024-08-05T03:50:21.828647005Z 
 83%|████████▎ | 4755/5712 [11:12:12<2:17:14,  8.60s/it]08/04/2024 20:50:21 - INFO - __main__ -   Step: 4755, LR: 9.299533062574478e-08, Loss: 0.21502703428268433
2024-08-05T03:50:30.010317970Z 
 83%|████████▎ | 4756/5712 [11:12:21<2:15:04,  8.48s/it]08/04/2024 20:50:30 - INFO - __main__ -   Step: 4756, LR: 9.28980519954279e-08, Loss: 0.07959769666194916
2024-08-05T03:50:38.340417437Z 
 83%|████████▎ | 4757/5712 [11:12:29<2:14:14,  8.43s/it]08/04/2024 20:50:38 - INFO - __main__ -   Step: 4757, LR: 9.2800773365111e-08, Loss: 0.05115051567554474
2024-08-05T03:50:47.083341957Z 
 83%|████████▎ | 4758/5712 [11:12:38<2:15:34,  8.53s/it]08/04/2024 20:50:47 - INFO - __main__ -   Step: 4758, LR: 9.270349473479413e-08, Loss: 0.07377928495407104
2024-08-05T03:50:55.698831211Z 
 83%|████████▎ | 4759/5712 [11:12:46<2:15:51,  8.55s/it]08/04/2024 20:50:55 - INFO - __main__ -   Step: 4759, LR: 9.260621610447724e-08, Loss: 0.06285928934812546
2024-08-05T03:51:04.084566532Z 
 83%|████████▎ | 4760/5712 [11:12:55<2:14:54,  8.50s/it]08/04/2024 20:51:04 - INFO - __main__ -   Step: 4760, LR: 9.250893747416036e-08, Loss: 0.0925598070025444
2024-08-05T03:51:12.338250668Z 
 83%|████████▎ | 4761/5712 [11:13:03<2:13:35,  8.43s/it]08/04/2024 20:51:12 - INFO - __main__ -   Step: 4761, LR: 9.241165884384347e-08, Loss: 0.04152902215719223
2024-08-05T03:51:20.935581855Z 
 83%|████████▎ | 4762/5712 [11:13:12<2:14:14,  8.48s/it]08/04/2024 20:51:20 - INFO - __main__ -   Step: 4762, LR: 9.231438021352658e-08, Loss: 0.1307440847158432
2024-08-05T03:51:29.737310933Z 
 83%|████████▎ | 4763/5712 [11:13:20<2:15:38,  8.58s/it]08/04/2024 20:51:29 - INFO - __main__ -   Step: 4763, LR: 9.22171015832097e-08, Loss: 0.13868264853954315
2024-08-05T03:51:37.958420980Z 
 83%|████████▎ | 4764/5712 [11:13:29<2:13:48,  8.47s/it]08/04/2024 20:51:37 - INFO - __main__ -   Step: 4764, LR: 9.211982295289282e-08, Loss: 0.10764463245868683
2024-08-05T03:51:46.217919186Z 
 83%|████████▎ | 4765/5712 [11:13:37<2:12:40,  8.41s/it]08/04/2024 20:51:46 - INFO - __main__ -   Step: 4765, LR: 9.202254432257593e-08, Loss: 0.03874314948916435
2024-08-05T03:51:54.413116560Z 
 83%|████████▎ | 4766/5712 [11:13:45<2:11:32,  8.34s/it]08/04/2024 20:51:54 - INFO - __main__ -   Step: 4766, LR: 9.192526569225904e-08, Loss: 0.06085576117038727
2024-08-05T03:52:02.885579658Z 
 83%|████████▎ | 4767/5712 [11:13:54<2:12:00,  8.38s/it]08/04/2024 20:52:02 - INFO - __main__ -   Step: 4767, LR: 9.182798706194217e-08, Loss: 0.09029246866703033
2024-08-05T03:52:11.277885391Z 
 83%|████████▎ | 4768/5712 [11:14:02<2:11:55,  8.38s/it]08/04/2024 20:52:11 - INFO - __main__ -   Step: 4768, LR: 9.173070843162528e-08, Loss: 0.056025587022304535
2024-08-05T03:52:19.429645236Z 
 83%|████████▎ | 4769/5712 [11:14:10<2:10:41,  8.32s/it]08/04/2024 20:52:19 - INFO - __main__ -   Step: 4769, LR: 9.163342980130839e-08, Loss: 0.05146151781082153
2024-08-05T03:52:27.859705143Z 
 84%|████████▎ | 4770/5712 [11:14:19<2:11:05,  8.35s/it]08/04/2024 20:52:27 - INFO - __main__ -   Step: 4770, LR: 9.15361511709915e-08, Loss: 0.044734690338373184
2024-08-05T03:52:36.752512554Z 
 84%|████████▎ | 4771/5712 [11:14:27<2:13:30,  8.51s/it]08/04/2024 20:52:36 - INFO - __main__ -   Step: 4771, LR: 9.143887254067462e-08, Loss: 0.05848586559295654
2024-08-05T03:52:44.928336569Z 
 84%|████████▎ | 4772/5712 [11:14:36<2:11:46,  8.41s/it]08/04/2024 20:52:44 - INFO - __main__ -   Step: 4772, LR: 9.134159391035774e-08, Loss: 0.0504688024520874
2024-08-05T03:52:53.105300991Z 
 84%|████████▎ | 4773/5712 [11:14:44<2:10:32,  8.34s/it]08/04/2024 20:52:53 - INFO - __main__ -   Step: 4773, LR: 9.124431528004086e-08, Loss: 0.10715998709201813
2024-08-05T03:53:01.644741390Z 
 84%|████████▎ | 4774/5712 [11:14:52<2:11:19,  8.40s/it]08/04/2024 20:53:01 - INFO - __main__ -   Step: 4774, LR: 9.114703664972397e-08, Loss: 0.11194664984941483
2024-08-05T03:53:10.110552698Z 
 84%|████████▎ | 4775/5712 [11:15:01<2:11:29,  8.42s/it]08/04/2024 20:53:10 - INFO - __main__ -   Step: 4775, LR: 9.104975801940708e-08, Loss: 0.07441890239715576
2024-08-05T03:53:18.905237959Z 
 84%|████████▎ | 4776/5712 [11:15:10<2:13:06,  8.53s/it]08/04/2024 20:53:18 - INFO - __main__ -   Step: 4776, LR: 9.09524793890902e-08, Loss: 0.07405029237270355
2024-08-05T03:53:27.461417675Z 
 84%|████████▎ | 4777/5712 [11:15:18<2:13:04,  8.54s/it]08/04/2024 20:53:27 - INFO - __main__ -   Step: 4777, LR: 9.085520075877332e-08, Loss: 0.06450824439525604
2024-08-05T03:53:35.510587447Z 
 84%|████████▎ | 4778/5712 [11:15:26<2:10:38,  8.39s/it]08/04/2024 20:53:35 - INFO - __main__ -   Step: 4778, LR: 9.075792212845643e-08, Loss: 0.04161830618977547
2024-08-05T03:53:44.194028024Z 
 84%|████████▎ | 4779/5712 [11:15:35<2:11:51,  8.48s/it]08/04/2024 20:53:44 - INFO - __main__ -   Step: 4779, LR: 9.066064349813954e-08, Loss: 0.12764811515808105
2024-08-05T03:53:52.347286794Z 
 84%|████████▎ | 4780/5712 [11:15:43<2:10:11,  8.38s/it]08/04/2024 20:53:52 - INFO - __main__ -   Step: 4780, LR: 9.056336486782265e-08, Loss: 0.031844571232795715
2024-08-05T03:54:00.868509466Z 
 84%|████████▎ | 4781/5712 [11:15:52<2:10:42,  8.42s/it]08/04/2024 20:54:00 - INFO - __main__ -   Step: 4781, LR: 9.046608623750578e-08, Loss: 0.067983478307724
2024-08-05T03:54:09.801655135Z 
 84%|████████▎ | 4782/5712 [11:16:00<2:12:56,  8.58s/it]08/04/2024 20:54:09 - INFO - __main__ -   Step: 4782, LR: 9.036880760718889e-08, Loss: 0.07020049542188644
2024-08-05T03:54:18.865170567Z 
 84%|████████▎ | 4783/5712 [11:16:10<2:15:03,  8.72s/it]08/04/2024 20:54:18 - INFO - __main__ -   Step: 4783, LR: 9.0271528976872e-08, Loss: 0.057346295565366745
2024-08-05T03:54:27.743396739Z 
 84%|████████▍ | 4784/5712 [11:16:18<2:15:37,  8.77s/it]08/04/2024 20:54:27 - INFO - __main__ -   Step: 4784, LR: 9.017425034655512e-08, Loss: 0.08014194667339325
2024-08-05T03:54:36.307398741Z 
 84%|████████▍ | 4785/5712 [11:16:27<2:14:32,  8.71s/it]08/04/2024 20:54:36 - INFO - __main__ -   Step: 4785, LR: 9.007697171623824e-08, Loss: 0.05578329786658287
2024-08-05T03:54:45.183358607Z 
 84%|████████▍ | 4786/5712 [11:16:36<2:15:10,  8.76s/it]08/04/2024 20:54:45 - INFO - __main__ -   Step: 4786, LR: 8.997969308592136e-08, Loss: 0.08877062797546387
2024-08-05T03:54:53.568920022Z 
 84%|████████▍ | 4787/5712 [11:16:44<2:13:17,  8.65s/it]08/04/2024 20:54:53 - INFO - __main__ -   Step: 4787, LR: 8.988241445560445e-08, Loss: 0.06734529137611389
2024-08-05T03:55:02.795051207Z 
 84%|████████▍ | 4788/5712 [11:16:53<2:15:50,  8.82s/it]08/04/2024 20:55:02 - INFO - __main__ -   Step: 4788, LR: 8.978513582528757e-08, Loss: 0.06882984191179276
2024-08-05T03:55:11.219526024Z 
 84%|████████▍ | 4789/5712 [11:17:02<2:13:51,  8.70s/it]08/04/2024 20:55:11 - INFO - __main__ -   Step: 4789, LR: 8.968785719497068e-08, Loss: 0.15316137671470642
2024-08-05T03:55:19.436839309Z 
 84%|████████▍ | 4790/5712 [11:17:10<2:11:28,  8.56s/it]08/04/2024 20:55:19 - INFO - __main__ -   Step: 4790, LR: 8.95905785646538e-08, Loss: 0.11742258071899414
2024-08-05T03:55:28.426951465Z 
 84%|████████▍ | 4791/5712 [11:17:19<2:13:20,  8.69s/it]08/04/2024 20:55:28 - INFO - __main__ -   Step: 4791, LR: 8.949329993433692e-08, Loss: 0.04383547604084015
2024-08-05T03:55:37.143206625Z 
 84%|████████▍ | 4792/5712 [11:17:28<2:13:19,  8.70s/it]08/04/2024 20:55:37 - INFO - __main__ -   Step: 4792, LR: 8.939602130402003e-08, Loss: 0.09377609193325043
2024-08-05T03:55:45.688554831Z 
 84%|████████▍ | 4793/5712 [11:17:36<2:12:29,  8.65s/it]08/04/2024 20:55:45 - INFO - __main__ -   Step: 4793, LR: 8.929874267370314e-08, Loss: 0.09703025966882706
2024-08-05T03:55:54.304064127Z 
 84%|████████▍ | 4794/5712 [11:17:45<2:12:11,  8.64s/it]08/04/2024 20:55:54 - INFO - __main__ -   Step: 4794, LR: 8.920146404338627e-08, Loss: 0.12235898524522781
2024-08-05T03:56:02.525663319Z 
 84%|████████▍ | 4795/5712 [11:17:53<2:10:07,  8.51s/it]08/04/2024 20:56:02 - INFO - __main__ -   Step: 4795, LR: 8.910418541306938e-08, Loss: 0.028429966419935226
2024-08-05T03:56:11.062662295Z 
 84%|████████▍ | 4796/5712 [11:18:02<2:10:05,  8.52s/it]08/04/2024 20:56:11 - INFO - __main__ -   Step: 4796, LR: 8.900690678275249e-08, Loss: 0.06015566363930702
2024-08-05T03:56:19.313263321Z 
 84%|████████▍ | 4797/5712 [11:18:10<2:08:42,  8.44s/it]08/04/2024 20:56:19 - INFO - __main__ -   Step: 4797, LR: 8.89096281524356e-08, Loss: 0.06191384047269821
2024-08-05T03:56:27.543715209Z 
 84%|████████▍ | 4798/5712 [11:18:18<2:07:36,  8.38s/it]08/04/2024 20:56:27 - INFO - __main__ -   Step: 4798, LR: 8.881234952211872e-08, Loss: 0.06548694521188736
2024-08-05T03:56:35.992074024Z 
 84%|████████▍ | 4799/5712 [11:18:27<2:07:47,  8.40s/it]08/04/2024 20:56:35 - INFO - __main__ -   Step: 4799, LR: 8.871507089180184e-08, Loss: 0.07469067722558975
2024-08-05T03:56:44.756273435Z 
 84%|████████▍ | 4800/5712 [11:18:35<2:09:19,  8.51s/it]08/04/2024 20:56:44 - INFO - __main__ -   Step: 4800, LR: 8.861779226148495e-08, Loss: 0.10290029644966125
2024-08-05T03:56:53.584018452Z 
 84%|████████▍ | 4801/5712 [11:18:44<2:10:38,  8.60s/it]08/04/2024 20:56:53 - INFO - __main__ -   Step: 4801, LR: 8.852051363116807e-08, Loss: 0.04331094026565552
2024-08-05T03:57:01.947690806Z 
 84%|████████▍ | 4802/5712 [11:18:53<2:09:24,  8.53s/it]08/04/2024 20:57:01 - INFO - __main__ -   Step: 4802, LR: 8.842323500085118e-08, Loss: 0.08414734154939651
2024-08-05T03:57:10.198043009Z 
 84%|████████▍ | 4803/5712 [11:19:01<2:07:58,  8.45s/it]08/04/2024 20:57:10 - INFO - __main__ -   Step: 4803, LR: 8.83259563705343e-08, Loss: 0.06461258977651596
2024-08-05T03:57:18.476963677Z 
 84%|████████▍ | 4804/5712 [11:19:09<2:07:04,  8.40s/it]08/04/2024 20:57:18 - INFO - __main__ -   Step: 4804, LR: 8.822867774021742e-08, Loss: 0.08936545997858047
2024-08-05T03:57:26.939395840Z 
 84%|████████▍ | 4805/5712 [11:19:18<2:07:13,  8.42s/it]08/04/2024 20:57:26 - INFO - __main__ -   Step: 4805, LR: 8.813139910990053e-08, Loss: 0.08494766056537628
2024-08-05T03:57:35.590477204Z 
 84%|████████▍ | 4806/5712 [11:19:26<2:08:09,  8.49s/it]08/04/2024 20:57:35 - INFO - __main__ -   Step: 4806, LR: 8.803412047958364e-08, Loss: 0.09559419751167297
2024-08-05T03:57:44.089445880Z 
 84%|████████▍ | 4807/5712 [11:19:35<2:08:03,  8.49s/it]08/04/2024 20:57:44 - INFO - __main__ -   Step: 4807, LR: 8.793684184926675e-08, Loss: 0.05451277270913124
2024-08-05T03:57:53.211086846Z 
 84%|████████▍ | 4808/5712 [11:19:44<2:10:46,  8.68s/it]08/04/2024 20:57:53 - INFO - __main__ -   Step: 4808, LR: 8.783956321894988e-08, Loss: 0.0689883679151535
2024-08-05T03:58:01.882984385Z 
 84%|████████▍ | 4809/5712 [11:19:53<2:10:35,  8.68s/it]08/04/2024 20:58:01 - INFO - __main__ -   Step: 4809, LR: 8.774228458863299e-08, Loss: 0.051765039563179016
2024-08-05T03:58:10.747259661Z 
 84%|████████▍ | 4810/5712 [11:20:01<2:11:17,  8.73s/it]08/04/2024 20:58:10 - INFO - __main__ -   Step: 4810, LR: 8.76450059583161e-08, Loss: 0.03840266913175583
2024-08-05T03:58:18.944427184Z 
 84%|████████▍ | 4811/5712 [11:20:10<2:08:43,  8.57s/it]08/04/2024 20:58:18 - INFO - __main__ -   Step: 4811, LR: 8.754772732799921e-08, Loss: 0.1185300201177597
2024-08-05T03:58:27.616666708Z 
 84%|████████▍ | 4812/5712 [11:20:18<2:09:02,  8.60s/it]08/04/2024 20:58:27 - INFO - __main__ -   Step: 4812, LR: 8.745044869768234e-08, Loss: 0.0863974392414093
2024-08-05T03:58:35.767458867Z 
 84%|████████▍ | 4813/5712 [11:20:26<2:06:51,  8.47s/it]08/04/2024 20:58:35 - INFO - __main__ -   Step: 4813, LR: 8.735317006736545e-08, Loss: 0.07141938805580139
2024-08-05T03:58:44.421351011Z 
 84%|████████▍ | 4814/5712 [11:20:35<2:07:33,  8.52s/it]08/04/2024 20:58:44 - INFO - __main__ -   Step: 4814, LR: 8.725589143704857e-08, Loss: 0.09615428745746613
2024-08-05T03:58:52.862664418Z 
 84%|████████▍ | 4815/5712 [11:20:44<2:07:03,  8.50s/it]08/04/2024 20:58:52 - INFO - __main__ -   Step: 4815, LR: 8.715861280673168e-08, Loss: 0.05453433841466904
2024-08-05T03:59:01.314986162Z 
 84%|████████▍ | 4816/5712 [11:20:52<2:06:42,  8.48s/it]08/04/2024 20:59:01 - INFO - __main__ -   Step: 4816, LR: 8.706133417641479e-08, Loss: 0.05256405845284462
2024-08-05T03:59:10.437516992Z 
 84%|████████▍ | 4817/5712 [11:21:01<2:09:24,  8.68s/it]08/04/2024 20:59:10 - INFO - __main__ -   Step: 4817, LR: 8.696405554609792e-08, Loss: 0.040078386664390564
2024-08-05T03:59:18.529606301Z 
 84%|████████▍ | 4818/5712 [11:21:09<2:06:39,  8.50s/it]08/04/2024 20:59:18 - INFO - __main__ -   Step: 4818, LR: 8.686677691578103e-08, Loss: 0.06498543918132782
2024-08-05T03:59:27.616281331Z 
 84%|████████▍ | 4819/5712 [11:21:18<2:09:08,  8.68s/it]08/04/2024 20:59:27 - INFO - __main__ -   Step: 4819, LR: 8.676949828546414e-08, Loss: 0.04371585696935654
2024-08-05T03:59:35.554659005Z 
 84%|████████▍ | 4820/5712 [11:21:26<2:05:42,  8.46s/it]08/04/2024 20:59:35 - INFO - __main__ -   Step: 4820, LR: 8.667221965514725e-08, Loss: 0.05182608589529991
2024-08-05T03:59:44.042891840Z 
 84%|████████▍ | 4821/5712 [11:21:35<2:05:42,  8.46s/it]08/04/2024 20:59:44 - INFO - __main__ -   Step: 4821, LR: 8.657494102483038e-08, Loss: 0.08313558995723724
2024-08-05T03:59:52.555123838Z 
 84%|████████▍ | 4822/5712 [11:21:43<2:05:46,  8.48s/it]08/04/2024 20:59:52 - INFO - __main__ -   Step: 4822, LR: 8.647766239451349e-08, Loss: 0.08606317639350891
2024-08-05T04:00:01.213153154Z 
 84%|████████▍ | 4823/5712 [11:21:52<2:06:25,  8.53s/it]08/04/2024 21:00:01 - INFO - __main__ -   Step: 4823, LR: 8.63803837641966e-08, Loss: 0.07066181302070618
2024-08-05T04:00:09.502478221Z 
 84%|████████▍ | 4824/5712 [11:22:00<2:05:12,  8.46s/it]08/04/2024 21:00:09 - INFO - __main__ -   Step: 4824, LR: 8.628310513387971e-08, Loss: 0.12628766894340515
2024-08-05T04:00:17.969842505Z 
 84%|████████▍ | 4825/5712 [11:22:09<2:05:05,  8.46s/it]08/04/2024 21:00:17 - INFO - __main__ -   Step: 4825, LR: 8.618582650356281e-08, Loss: 0.13108772039413452
2024-08-05T04:00:26.434276711Z 
 84%|████████▍ | 4826/5712 [11:22:17<2:04:58,  8.46s/it]08/04/2024 21:00:26 - INFO - __main__ -   Step: 4826, LR: 8.608854787324594e-08, Loss: 0.05991686135530472
2024-08-05T04:00:35.216836668Z 
 85%|████████▍ | 4827/5712 [11:22:26<2:06:14,  8.56s/it]08/04/2024 21:00:35 - INFO - __main__ -   Step: 4827, LR: 8.599126924292905e-08, Loss: 0.08674005419015884
2024-08-05T04:00:43.139223999Z 
 85%|████████▍ | 4828/5712 [11:22:34<2:03:17,  8.37s/it]08/04/2024 21:00:43 - INFO - __main__ -   Step: 4828, LR: 8.589399061261216e-08, Loss: 0.0303591750562191
2024-08-05T04:00:51.487833752Z 
 85%|████████▍ | 4829/5712 [11:22:42<2:03:03,  8.36s/it]08/04/2024 21:00:51 - INFO - __main__ -   Step: 4829, LR: 8.579671198229528e-08, Loss: 0.04991428181529045
2024-08-05T04:00:59.612267053Z 
 85%|████████▍ | 4830/5712 [11:22:50<2:01:52,  8.29s/it]08/04/2024 21:00:59 - INFO - __main__ -   Step: 4830, LR: 8.56994333519784e-08, Loss: 0.14270468056201935
2024-08-05T04:01:08.330517567Z 
 85%|████████▍ | 4831/5712 [11:22:59<2:03:37,  8.42s/it]08/04/2024 21:01:08 - INFO - __main__ -   Step: 4831, LR: 8.560215472166151e-08, Loss: 0.061750657856464386
2024-08-05T04:01:16.822494726Z 
 85%|████████▍ | 4832/5712 [11:23:07<2:03:47,  8.44s/it]08/04/2024 21:01:16 - INFO - __main__ -   Step: 4832, LR: 8.550487609134463e-08, Loss: 0.05833272635936737
2024-08-05T04:01:25.499363940Z 
 85%|████████▍ | 4833/5712 [11:23:16<2:04:41,  8.51s/it]08/04/2024 21:01:25 - INFO - __main__ -   Step: 4833, LR: 8.540759746102774e-08, Loss: 0.06175018474459648
2024-08-05T04:01:34.272139599Z 
 85%|████████▍ | 4834/5712 [11:23:25<2:05:41,  8.59s/it]08/04/2024 21:01:34 - INFO - __main__ -   Step: 4834, LR: 8.531031883071085e-08, Loss: 0.051195934414863586
2024-08-05T04:01:42.360501651Z 
 85%|████████▍ | 4835/5712 [11:23:33<2:03:21,  8.44s/it]08/04/2024 21:01:42 - INFO - __main__ -   Step: 4835, LR: 8.521304020039398e-08, Loss: 0.08806674927473068
2024-08-05T04:01:50.699453352Z 
 85%|████████▍ | 4836/5712 [11:23:41<2:02:46,  8.41s/it]08/04/2024 21:01:50 - INFO - __main__ -   Step: 4836, LR: 8.511576157007709e-08, Loss: 0.12148580700159073
2024-08-05T04:01:59.268424852Z 
 85%|████████▍ | 4837/5712 [11:23:50<2:03:20,  8.46s/it]08/04/2024 21:01:59 - INFO - __main__ -   Step: 4837, LR: 8.50184829397602e-08, Loss: 0.09876701235771179
2024-08-05T04:02:07.638337880Z 
 85%|████████▍ | 4838/5712 [11:23:58<2:02:48,  8.43s/it]08/04/2024 21:02:07 - INFO - __main__ -   Step: 4838, LR: 8.492120430944331e-08, Loss: 0.08065930008888245
2024-08-05T04:02:15.999170066Z 
 85%|████████▍ | 4839/5712 [11:24:07<2:02:21,  8.41s/it]08/04/2024 21:02:15 - INFO - __main__ -   Step: 4839, LR: 8.482392567912644e-08, Loss: 0.11690917611122131
2024-08-05T04:02:24.310771402Z 
 85%|████████▍ | 4840/5712 [11:24:15<2:01:47,  8.38s/it]08/04/2024 21:02:24 - INFO - __main__ -   Step: 4840, LR: 8.472664704880955e-08, Loss: 0.0646308958530426
2024-08-05T04:02:32.538737189Z 
 85%|████████▍ | 4841/5712 [11:24:23<2:00:59,  8.33s/it]08/04/2024 21:02:32 - INFO - __main__ -   Step: 4841, LR: 8.462936841849266e-08, Loss: 0.13372062146663666
2024-08-05T04:02:41.030386511Z 
 85%|████████▍ | 4842/5712 [11:24:32<2:01:32,  8.38s/it]08/04/2024 21:02:41 - INFO - __main__ -   Step: 4842, LR: 8.453208978817578e-08, Loss: 0.07099109143018723
2024-08-05T04:02:50.017553783Z 
 85%|████████▍ | 4843/5712 [11:24:41<2:04:01,  8.56s/it]08/04/2024 21:02:50 - INFO - __main__ -   Step: 4843, LR: 8.443481115785889e-08, Loss: 0.0603049099445343
2024-08-05T04:02:58.207676989Z 
 85%|████████▍ | 4844/5712 [11:24:49<2:02:15,  8.45s/it]08/04/2024 21:02:58 - INFO - __main__ -   Step: 4844, LR: 8.433753252754201e-08, Loss: 0.11963866651058197
2024-08-05T04:03:06.535954988Z 
 85%|████████▍ | 4845/5712 [11:24:57<2:01:35,  8.41s/it]08/04/2024 21:03:06 - INFO - __main__ -   Step: 4845, LR: 8.424025389722513e-08, Loss: 0.03643854707479477
2024-08-05T04:03:14.830557355Z 
 85%|████████▍ | 4846/5712 [11:25:05<2:00:55,  8.38s/it]08/04/2024 21:03:14 - INFO - __main__ -   Step: 4846, LR: 8.414297526690824e-08, Loss: 0.0658605545759201
2024-08-05T04:03:23.330879136Z 
 85%|████████▍ | 4847/5712 [11:25:14<2:01:19,  8.42s/it]08/04/2024 21:03:23 - INFO - __main__ -   Step: 4847, LR: 8.404569663659135e-08, Loss: 0.07476099580526352
2024-08-05T04:03:31.700663335Z 
 85%|████████▍ | 4848/5712 [11:25:22<2:00:58,  8.40s/it]08/04/2024 21:03:31 - INFO - __main__ -   Step: 4848, LR: 8.394841800627448e-08, Loss: 0.054256901144981384
2024-08-05T04:03:39.909204055Z 
 85%|████████▍ | 4849/5712 [11:25:31<2:00:00,  8.34s/it]08/04/2024 21:03:39 - INFO - __main__ -   Step: 4849, LR: 8.385113937595759e-08, Loss: 0.05405797064304352
2024-08-05T04:03:48.779711773Z 
 85%|████████▍ | 4850/5712 [11:25:39<2:02:08,  8.50s/it]08/04/2024 21:03:48 - INFO - __main__ -   Step: 4850, LR: 8.37538607456407e-08, Loss: 0.05650885030627251
2024-08-05T04:03:57.341828546Z 
 85%|████████▍ | 4851/5712 [11:25:48<2:02:15,  8.52s/it]08/04/2024 21:03:57 - INFO - __main__ -   Step: 4851, LR: 8.365658211532381e-08, Loss: 0.08899092674255371
2024-08-05T04:04:05.753892808Z 
 85%|████████▍ | 4852/5712 [11:25:56<2:01:39,  8.49s/it]08/04/2024 21:04:05 - INFO - __main__ -   Step: 4852, LR: 8.355930348500692e-08, Loss: 0.06292065978050232
2024-08-05T04:04:14.198148605Z 
 85%|████████▍ | 4853/5712 [11:26:05<2:01:19,  8.47s/it]08/04/2024 21:04:14 - INFO - __main__ -   Step: 4853, LR: 8.346202485469005e-08, Loss: 0.10459055006504059
2024-08-05T04:04:22.121272018Z 
 85%|████████▍ | 4854/5712 [11:26:13<1:58:49,  8.31s/it]08/04/2024 21:04:22 - INFO - __main__ -   Step: 4854, LR: 8.336474622437316e-08, Loss: 0.10114403069019318
2024-08-05T04:04:30.398960913Z 
 85%|████████▍ | 4855/5712 [11:26:21<1:58:32,  8.30s/it]08/04/2024 21:04:30 - INFO - __main__ -   Step: 4855, LR: 8.326746759405627e-08, Loss: 0.11853574216365814
2024-08-05T04:04:38.896206258Z 
 85%|████████▌ | 4856/5712 [11:26:30<1:59:15,  8.36s/it]08/04/2024 21:04:38 - INFO - __main__ -   Step: 4856, LR: 8.317018896373939e-08, Loss: 0.070854552090168
2024-08-05T04:04:47.268120085Z 
 85%|████████▌ | 4857/5712 [11:26:38<1:59:10,  8.36s/it]08/04/2024 21:04:47 - INFO - __main__ -   Step: 4857, LR: 8.307291033342251e-08, Loss: 0.07813592255115509
2024-08-05T04:04:55.628362764Z 
 85%|████████▌ | 4858/5712 [11:26:46<1:59:01,  8.36s/it]08/04/2024 21:04:55 - INFO - __main__ -   Step: 4858, LR: 8.297563170310562e-08, Loss: 0.09330429881811142
2024-08-05T04:05:04.401309936Z 
 85%|████████▌ | 4859/5712 [11:26:55<2:00:38,  8.49s/it]08/04/2024 21:05:04 - INFO - __main__ -   Step: 4859, LR: 8.287835307278874e-08, Loss: 0.1403706967830658
2024-08-05T04:05:13.019333423Z 
 85%|████████▌ | 4860/5712 [11:27:04<2:01:03,  8.53s/it]08/04/2024 21:05:13 - INFO - __main__ -   Step: 4860, LR: 8.278107444247185e-08, Loss: 0.08300858736038208
2024-08-05T04:05:21.628163334Z 
 85%|████████▌ | 4861/5712 [11:27:12<2:01:16,  8.55s/it]08/04/2024 21:05:21 - INFO - __main__ -   Step: 4861, LR: 8.268379581215496e-08, Loss: 0.0973692536354065
2024-08-05T04:05:29.605573328Z 
 85%|████████▌ | 4862/5712 [11:27:20<1:58:41,  8.38s/it]08/04/2024 21:05:29 - INFO - __main__ -   Step: 4862, LR: 8.258651718183809e-08, Loss: 0.048964984714984894
2024-08-05T04:05:38.173168612Z 
 85%|████████▌ | 4863/5712 [11:27:29<1:59:21,  8.44s/it]08/04/2024 21:05:38 - INFO - __main__ -   Step: 4863, LR: 8.248923855152119e-08, Loss: 0.039260078221559525
2024-08-05T04:05:46.791935034Z 
 85%|████████▌ | 4864/5712 [11:27:37<1:59:59,  8.49s/it]08/04/2024 21:05:46 - INFO - __main__ -   Step: 4864, LR: 8.23919599212043e-08, Loss: 0.05062849074602127
2024-08-05T04:05:55.741242142Z 
 85%|████████▌ | 4865/5712 [11:27:46<2:01:47,  8.63s/it]08/04/2024 21:05:55 - INFO - __main__ -   Step: 4865, LR: 8.229468129088741e-08, Loss: 0.05940815433859825
2024-08-05T04:06:04.457040830Z 
 85%|████████▌ | 4866/5712 [11:27:55<2:02:01,  8.65s/it]08/04/2024 21:06:04 - INFO - __main__ -   Step: 4866, LR: 8.219740266057054e-08, Loss: 0.10697580873966217
2024-08-05T04:06:12.986822501Z 
 85%|████████▌ | 4867/5712 [11:28:04<2:01:21,  8.62s/it]08/04/2024 21:06:12 - INFO - __main__ -   Step: 4867, LR: 8.210012403025365e-08, Loss: 0.047590553760528564
2024-08-05T04:06:21.460532935Z 
 85%|████████▌ | 4868/5712 [11:28:12<2:00:36,  8.57s/it]08/04/2024 21:06:21 - INFO - __main__ -   Step: 4868, LR: 8.200284539993676e-08, Loss: 0.07480353116989136
2024-08-05T04:06:30.213801015Z 
 85%|████████▌ | 4869/5712 [11:28:21<2:01:13,  8.63s/it]08/04/2024 21:06:30 - INFO - __main__ -   Step: 4869, LR: 8.190556676961987e-08, Loss: 0.03938969597220421
2024-08-05T04:06:38.564268058Z 
 85%|████████▌ | 4870/5712 [11:28:29<1:59:54,  8.54s/it]08/04/2024 21:06:38 - INFO - __main__ -   Step: 4870, LR: 8.180828813930299e-08, Loss: 0.07818372547626495
2024-08-05T04:06:46.586862667Z 
 85%|████████▌ | 4871/5712 [11:28:37<1:57:34,  8.39s/it]08/04/2024 21:06:46 - INFO - __main__ -   Step: 4871, LR: 8.171100950898611e-08, Loss: 0.09746700525283813
2024-08-05T04:06:55.511938196Z 
 85%|████████▌ | 4872/5712 [11:28:46<1:59:41,  8.55s/it]08/04/2024 21:06:55 - INFO - __main__ -   Step: 4872, LR: 8.161373087866922e-08, Loss: 0.04900118708610535
2024-08-05T04:07:04.191452578Z 
 85%|████████▌ | 4873/5712 [11:28:55<2:00:05,  8.59s/it]08/04/2024 21:07:04 - INFO - __main__ -   Step: 4873, LR: 8.151645224835234e-08, Loss: 0.09988798946142197
2024-08-05T04:07:12.934571903Z 
 85%|████████▌ | 4874/5712 [11:29:04<2:00:35,  8.63s/it]08/04/2024 21:07:12 - INFO - __main__ -   Step: 4874, LR: 8.141917361803545e-08, Loss: 0.09567133337259293
2024-08-05T04:07:21.478348892Z 
 85%|████████▌ | 4875/5712 [11:29:12<2:00:04,  8.61s/it]08/04/2024 21:07:21 - INFO - __main__ -   Step: 4875, LR: 8.132189498771857e-08, Loss: 0.04672042280435562
2024-08-05T04:07:30.408355094Z 
 85%|████████▌ | 4876/5712 [11:29:21<2:01:16,  8.70s/it]08/04/2024 21:07:30 - INFO - __main__ -   Step: 4876, LR: 8.122461635740169e-08, Loss: 0.08951041102409363
2024-08-05T04:07:39.010067038Z 
 85%|████████▌ | 4877/5712 [11:29:30<2:00:42,  8.67s/it]08/04/2024 21:07:39 - INFO - __main__ -   Step: 4877, LR: 8.11273377270848e-08, Loss: 0.05827724561095238
2024-08-05T04:07:47.563793996Z 
 85%|████████▌ | 4878/5712 [11:29:38<2:00:03,  8.64s/it]08/04/2024 21:07:47 - INFO - __main__ -   Step: 4878, LR: 8.103005909676791e-08, Loss: 0.09396514296531677
2024-08-05T04:07:55.466618055Z 
 85%|████████▌ | 4879/5712 [11:29:46<1:56:51,  8.42s/it]08/04/2024 21:07:55 - INFO - __main__ -   Step: 4879, LR: 8.093278046645102e-08, Loss: 0.05294696241617203
2024-08-05T04:08:04.204131066Z 
 85%|████████▌ | 4880/5712 [11:29:55<1:58:02,  8.51s/it]08/04/2024 21:08:04 - INFO - __main__ -   Step: 4880, LR: 8.083550183613415e-08, Loss: 0.09383662045001984
2024-08-05T04:08:13.145791482Z 
 85%|████████▌ | 4881/5712 [11:30:04<1:59:41,  8.64s/it]08/04/2024 21:08:13 - INFO - __main__ -   Step: 4881, LR: 8.073822320581726e-08, Loss: 0.090133897960186
2024-08-05T04:08:21.795507340Z 
 85%|████████▌ | 4882/5712 [11:30:12<1:59:34,  8.64s/it]08/04/2024 21:08:21 - INFO - __main__ -   Step: 4882, LR: 8.064094457550037e-08, Loss: 0.05607675015926361
2024-08-05T04:08:30.516202638Z 
 85%|████████▌ | 4883/5712 [11:30:21<1:59:45,  8.67s/it]08/04/2024 21:08:30 - INFO - __main__ -   Step: 4883, LR: 8.054366594518348e-08, Loss: 0.09475866705179214
2024-08-05T04:08:38.757767715Z 
 86%|████████▌ | 4884/5712 [11:30:29<1:57:50,  8.54s/it]08/04/2024 21:08:38 - INFO - __main__ -   Step: 4884, LR: 8.044638731486661e-08, Loss: 0.04055233672261238
2024-08-05T04:08:47.419473058Z 
 86%|████████▌ | 4885/5712 [11:30:38<1:58:12,  8.58s/it]08/04/2024 21:08:47 - INFO - __main__ -   Step: 4885, LR: 8.034910868454972e-08, Loss: 0.06698538362979889
2024-08-05T04:08:56.085030392Z 
 86%|████████▌ | 4886/5712 [11:30:47<1:58:26,  8.60s/it]08/04/2024 21:08:56 - INFO - __main__ -   Step: 4886, LR: 8.025183005423283e-08, Loss: 0.07625693082809448
2024-08-05T04:09:04.688290892Z 
 86%|████████▌ | 4887/5712 [11:30:55<1:58:17,  8.60s/it]08/04/2024 21:09:04 - INFO - __main__ -   Step: 4887, LR: 8.015455142391595e-08, Loss: 0.11466781795024872
2024-08-05T04:09:12.719167106Z 
 86%|████████▌ | 4888/5712 [11:31:03<1:55:47,  8.43s/it]08/04/2024 21:09:12 - INFO - __main__ -   Step: 4888, LR: 8.005727279359906e-08, Loss: 0.11020586639642715
2024-08-05T04:09:21.200753956Z 
 86%|████████▌ | 4889/5712 [11:31:12<1:55:51,  8.45s/it]08/04/2024 21:09:21 - INFO - __main__ -   Step: 4889, LR: 7.995999416328218e-08, Loss: 0.0641210675239563
2024-08-05T04:09:29.652286497Z 
 86%|████████▌ | 4890/5712 [11:31:20<1:55:44,  8.45s/it]08/04/2024 21:09:29 - INFO - __main__ -   Step: 4890, LR: 7.98627155329653e-08, Loss: 0.11658455431461334
2024-08-05T04:09:38.203614490Z 
 86%|████████▌ | 4891/5712 [11:31:29<1:56:01,  8.48s/it]08/04/2024 21:09:38 - INFO - __main__ -   Step: 4891, LR: 7.976543690264841e-08, Loss: 0.05547560751438141
2024-08-05T04:09:46.885412366Z 
 86%|████████▌ | 4892/5712 [11:31:38<1:56:42,  8.54s/it]08/04/2024 21:09:46 - INFO - __main__ -   Step: 4892, LR: 7.966815827233152e-08, Loss: 0.13596460223197937
2024-08-05T04:09:55.074764876Z 
 86%|████████▌ | 4893/5712 [11:31:46<1:55:08,  8.43s/it]08/04/2024 21:09:55 - INFO - __main__ -   Step: 4893, LR: 7.957087964201465e-08, Loss: 0.09924579411745071
2024-08-05T04:10:03.895572380Z 
 86%|████████▌ | 4894/5712 [11:31:55<1:56:34,  8.55s/it]08/04/2024 21:10:03 - INFO - __main__ -   Step: 4894, LR: 7.947360101169776e-08, Loss: 0.13526219129562378
2024-08-05T04:10:12.346932516Z 
 86%|████████▌ | 4895/5712 [11:32:03<1:56:01,  8.52s/it]08/04/2024 21:10:12 - INFO - __main__ -   Step: 4895, LR: 7.937632238138087e-08, Loss: 0.025884727016091347
2024-08-05T04:10:20.625592580Z 
 86%|████████▌ | 4896/5712 [11:32:11<1:54:53,  8.45s/it]08/04/2024 21:10:20 - INFO - __main__ -   Step: 4896, LR: 7.927904375106398e-08, Loss: 0.05950935557484627
2024-08-05T04:10:28.780541044Z 
 86%|████████▌ | 4897/5712 [11:32:19<1:53:33,  8.36s/it]08/04/2024 21:10:28 - INFO - __main__ -   Step: 4897, LR: 7.91817651207471e-08, Loss: 0.04037724435329437
2024-08-05T04:10:37.415614929Z 
 86%|████████▌ | 4898/5712 [11:32:28<1:54:32,  8.44s/it]08/04/2024 21:10:37 - INFO - __main__ -   Step: 4898, LR: 7.908448649043022e-08, Loss: 0.06547676026821136
2024-08-05T04:10:46.052588848Z 
 86%|████████▌ | 4899/5712 [11:32:37<1:55:11,  8.50s/it]08/04/2024 21:10:46 - INFO - __main__ -   Step: 4899, LR: 7.898720786011333e-08, Loss: 0.06095854938030243
2024-08-05T04:10:54.733135353Z 
 86%|████████▌ | 4900/5712 [11:32:45<1:55:46,  8.55s/it]08/04/2024 21:10:54 - INFO - __main__ -   Step: 4900, LR: 7.888992922979645e-08, Loss: 0.051511913537979126
2024-08-05T04:11:03.114525644Z 
 86%|████████▌ | 4901/5712 [11:32:54<1:54:55,  8.50s/it]08/04/2024 21:11:03 - INFO - __main__ -   Step: 4901, LR: 7.879265059947955e-08, Loss: 0.09543803334236145
2024-08-05T04:11:11.399606843Z 
 86%|████████▌ | 4902/5712 [11:33:02<1:53:54,  8.44s/it]08/04/2024 21:11:11 - INFO - __main__ -   Step: 4902, LR: 7.869537196916267e-08, Loss: 0.06315048038959503
2024-08-05T04:11:20.144067826Z 
 86%|████████▌ | 4903/5712 [11:33:11<1:55:00,  8.53s/it]08/04/2024 21:11:20 - INFO - __main__ -   Step: 4903, LR: 7.859809333884578e-08, Loss: 0.047165289521217346
2024-08-05T04:11:28.550172108Z 
 86%|████████▌ | 4904/5712 [11:33:19<1:54:21,  8.49s/it]08/04/2024 21:11:28 - INFO - __main__ -   Step: 4904, LR: 7.85008147085289e-08, Loss: 0.05496135354042053
2024-08-05T04:11:36.809854015Z 
 86%|████████▌ | 4905/5712 [11:33:27<1:53:17,  8.42s/it]08/04/2024 21:11:36 - INFO - __main__ -   Step: 4905, LR: 7.840353607821201e-08, Loss: 0.031793102622032166
2024-08-05T04:11:45.642452287Z 
 86%|████████▌ | 4906/5712 [11:33:36<1:54:47,  8.55s/it]08/04/2024 21:11:45 - INFO - __main__ -   Step: 4906, LR: 7.830625744789512e-08, Loss: 0.06748218834400177
2024-08-05T04:11:54.048353185Z 
 86%|████████▌ | 4907/5712 [11:33:45<1:54:05,  8.50s/it]08/04/2024 21:11:54 - INFO - __main__ -   Step: 4907, LR: 7.820897881757825e-08, Loss: 0.060945168137550354
2024-08-05T04:12:02.901665787Z 
 86%|████████▌ | 4908/5712 [11:33:54<1:55:21,  8.61s/it]08/04/2024 21:12:02 - INFO - __main__ -   Step: 4908, LR: 7.811170018726136e-08, Loss: 0.07250512391328812
2024-08-05T04:12:11.263072029Z 
 86%|████████▌ | 4909/5712 [11:34:02<1:54:13,  8.53s/it]08/04/2024 21:12:11 - INFO - __main__ -   Step: 4909, LR: 7.801442155694447e-08, Loss: 0.0806359052658081
2024-08-05T04:12:19.773184292Z 
 86%|████████▌ | 4910/5712 [11:34:10<1:53:58,  8.53s/it]08/04/2024 21:12:19 - INFO - __main__ -   Step: 4910, LR: 7.791714292662758e-08, Loss: 0.041461389511823654
2024-08-05T04:12:28.090664011Z 
 86%|████████▌ | 4911/5712 [11:34:19<1:52:59,  8.46s/it]08/04/2024 21:12:28 - INFO - __main__ -   Step: 4911, LR: 7.781986429631071e-08, Loss: 0.06318874657154083
2024-08-05T04:12:37.162253658Z 
 86%|████████▌ | 4912/5712 [11:34:28<1:55:17,  8.65s/it]08/04/2024 21:12:37 - INFO - __main__ -   Step: 4912, LR: 7.772258566599382e-08, Loss: 0.06599102169275284
2024-08-05T04:12:45.643387221Z 
 86%|████████▌ | 4913/5712 [11:34:36<1:54:28,  8.60s/it]08/04/2024 21:12:45 - INFO - __main__ -   Step: 4913, LR: 7.762530703567693e-08, Loss: 0.030078493058681488
2024-08-05T04:12:54.110950170Z 
 86%|████████▌ | 4914/5712 [11:34:45<1:53:49,  8.56s/it]08/04/2024 21:12:54 - INFO - __main__ -   Step: 4914, LR: 7.752802840536004e-08, Loss: 0.10139399021863937
2024-08-05T04:13:02.549332249Z 
 86%|████████▌ | 4915/5712 [11:34:53<1:53:12,  8.52s/it]08/04/2024 21:13:02 - INFO - __main__ -   Step: 4915, LR: 7.743074977504316e-08, Loss: 0.04512578621506691
2024-08-05T04:13:11.414272844Z 
 86%|████████▌ | 4916/5712 [11:35:02<1:54:25,  8.62s/it]08/04/2024 21:13:11 - INFO - __main__ -   Step: 4916, LR: 7.733347114472628e-08, Loss: 0.06837819516658783
2024-08-05T04:13:19.916081818Z 
 86%|████████▌ | 4917/5712 [11:35:11<1:53:47,  8.59s/it]08/04/2024 21:13:19 - INFO - __main__ -   Step: 4917, LR: 7.72361925144094e-08, Loss: 0.07056846469640732
2024-08-05T04:13:27.468094088Z 
 86%|████████▌ | 4918/5712 [11:35:18<1:49:32,  8.28s/it]08/04/2024 21:13:27 - INFO - __main__ -   Step: 4918, LR: 7.713891388409251e-08, Loss: 0.07754123210906982
2024-08-05T04:13:36.261031585Z 
 86%|████████▌ | 4919/5712 [11:35:27<1:51:26,  8.43s/it]08/04/2024 21:13:36 - INFO - __main__ -   Step: 4919, LR: 7.704163525377562e-08, Loss: 0.09182717651128769
2024-08-05T04:13:44.634287192Z 
 86%|████████▌ | 4920/5712 [11:35:35<1:51:04,  8.41s/it]08/04/2024 21:13:44 - INFO - __main__ -   Step: 4920, LR: 7.694435662345874e-08, Loss: 0.13605894148349762
2024-08-05T04:13:53.210096522Z 
 86%|████████▌ | 4921/5712 [11:35:44<1:51:34,  8.46s/it]08/04/2024 21:13:53 - INFO - __main__ -   Step: 4921, LR: 7.684707799314186e-08, Loss: 0.1552775800228119
2024-08-05T04:14:01.511729827Z 
 86%|████████▌ | 4922/5712 [11:35:52<1:50:47,  8.41s/it]08/04/2024 21:14:01 - INFO - __main__ -   Step: 4922, LR: 7.674979936282497e-08, Loss: 0.08496613055467606
2024-08-05T04:14:09.870119516Z 
 86%|████████▌ | 4923/5712 [11:36:01<1:50:25,  8.40s/it]08/04/2024 21:14:09 - INFO - __main__ -   Step: 4923, LR: 7.665252073250808e-08, Loss: 0.062169115990400314
2024-08-05T04:14:18.402432712Z 
 86%|████████▌ | 4924/5712 [11:36:09<1:50:49,  8.44s/it]08/04/2024 21:14:18 - INFO - __main__ -   Step: 4924, LR: 7.65552421021912e-08, Loss: 0.014343385584652424
2024-08-05T04:14:26.683817408Z 
 86%|████████▌ | 4925/5712 [11:36:17<1:50:03,  8.39s/it]08/04/2024 21:14:26 - INFO - __main__ -   Step: 4925, LR: 7.645796347187432e-08, Loss: 0.0616089329123497
2024-08-05T04:14:34.776174048Z 
 86%|████████▌ | 4926/5712 [11:36:25<1:48:44,  8.30s/it]08/04/2024 21:14:34 - INFO - __main__ -   Step: 4926, LR: 7.636068484155743e-08, Loss: 0.03580459952354431
2024-08-05T04:14:43.458037499Z 
 86%|████████▋ | 4927/5712 [11:36:34<1:50:06,  8.42s/it]08/04/2024 21:14:43 - INFO - __main__ -   Step: 4927, LR: 7.626340621124054e-08, Loss: 0.109512098133564
2024-08-05T04:14:52.302448904Z 
 86%|████████▋ | 4928/5712 [11:36:43<1:51:38,  8.54s/it]08/04/2024 21:14:52 - INFO - __main__ -   Step: 4928, LR: 7.616612758092366e-08, Loss: 0.06026916205883026
2024-08-05T04:15:00.852730379Z 
 86%|████████▋ | 4929/5712 [11:36:51<1:51:31,  8.55s/it]08/04/2024 21:15:00 - INFO - __main__ -   Step: 4929, LR: 7.606884895060678e-08, Loss: 0.0487084686756134
2024-08-05T04:15:09.008178592Z 
 86%|████████▋ | 4930/5712 [11:37:00<1:49:51,  8.43s/it]08/04/2024 21:15:09 - INFO - __main__ -   Step: 4930, LR: 7.59715703202899e-08, Loss: 0.056013453751802444
2024-08-05T04:15:17.847377617Z 
 86%|████████▋ | 4931/5712 [11:37:08<1:51:19,  8.55s/it]08/04/2024 21:15:17 - INFO - __main__ -   Step: 4931, LR: 7.5874291689973e-08, Loss: 0.0779167115688324
2024-08-05T04:15:26.860198183Z 
 86%|████████▋ | 4932/5712 [11:37:18<1:52:58,  8.69s/it]08/04/2024 21:15:26 - INFO - __main__ -   Step: 4932, LR: 7.577701305965612e-08, Loss: 0.02692841738462448
2024-08-05T04:15:35.295474366Z 
 86%|████████▋ | 4933/5712 [11:37:26<1:51:50,  8.61s/it]08/04/2024 21:15:35 - INFO - __main__ -   Step: 4933, LR: 7.567973442933923e-08, Loss: 0.04680851101875305
2024-08-05T04:15:43.479777749Z 
 86%|████████▋ | 4934/5712 [11:37:34<1:50:01,  8.48s/it]08/04/2024 21:15:43 - INFO - __main__ -   Step: 4934, LR: 7.558245579902236e-08, Loss: 0.13508164882659912
2024-08-05T04:15:51.944104022Z 
 86%|████████▋ | 4935/5712 [11:37:43<1:49:47,  8.48s/it]08/04/2024 21:15:51 - INFO - __main__ -   Step: 4935, LR: 7.548517716870547e-08, Loss: 0.07114531099796295
2024-08-05T04:16:00.615877094Z 
 86%|████████▋ | 4936/5712 [11:37:51<1:50:24,  8.54s/it]08/04/2024 21:16:00 - INFO - __main__ -   Step: 4936, LR: 7.538789853838858e-08, Loss: 0.06274491548538208
2024-08-05T04:16:08.609536460Z 
 86%|████████▋ | 4937/5712 [11:37:59<1:48:09,  8.37s/it]08/04/2024 21:16:08 - INFO - __main__ -   Step: 4937, LR: 7.529061990807169e-08, Loss: 0.12546996772289276
2024-08-05T04:16:16.774183468Z 
 86%|████████▋ | 4938/5712 [11:38:07<1:47:12,  8.31s/it]08/04/2024 21:16:16 - INFO - __main__ -   Step: 4938, LR: 7.519334127775482e-08, Loss: 0.11841930449008942
2024-08-05T04:16:25.280968742Z 
 86%|████████▋ | 4939/5712 [11:38:16<1:47:49,  8.37s/it]08/04/2024 21:16:25 - INFO - __main__ -   Step: 4939, LR: 7.509606264743793e-08, Loss: 0.044377777725458145
2024-08-05T04:16:34.091010424Z 
 86%|████████▋ | 4940/5712 [11:38:25<1:49:23,  8.50s/it]08/04/2024 21:16:34 - INFO - __main__ -   Step: 4940, LR: 7.499878401712103e-08, Loss: 0.06687997281551361
2024-08-05T04:16:42.714870767Z 
 87%|████████▋ | 4941/5712 [11:38:33<1:49:43,  8.54s/it]08/04/2024 21:16:42 - INFO - __main__ -   Step: 4941, LR: 7.490150538680414e-08, Loss: 0.08754174411296844
2024-08-05T04:16:50.968732250Z 
 87%|████████▋ | 4942/5712 [11:38:42<1:48:28,  8.45s/it]08/04/2024 21:16:50 - INFO - __main__ -   Step: 4942, LR: 7.480422675648725e-08, Loss: 0.037887945771217346
2024-08-05T04:16:59.557023327Z 
 87%|████████▋ | 4943/5712 [11:38:50<1:48:51,  8.49s/it]08/04/2024 21:16:59 - INFO - __main__ -   Step: 4943, LR: 7.470694812617038e-08, Loss: 0.04509831964969635
2024-08-05T04:17:07.760848755Z 
 87%|████████▋ | 4944/5712 [11:38:58<1:47:36,  8.41s/it]08/04/2024 21:17:07 - INFO - __main__ -   Step: 4944, LR: 7.460966949585349e-08, Loss: 0.026384497061371803
2024-08-05T04:17:15.916653641Z 
 87%|████████▋ | 4945/5712 [11:39:07<1:46:30,  8.33s/it]08/04/2024 21:17:15 - INFO - __main__ -   Step: 4945, LR: 7.45123908655366e-08, Loss: 0.0800873264670372
2024-08-05T04:17:24.137090815Z 
 87%|████████▋ | 4946/5712 [11:39:15<1:45:56,  8.30s/it]08/04/2024 21:17:24 - INFO - __main__ -   Step: 4946, LR: 7.441511223521972e-08, Loss: 0.06023339927196503
2024-08-05T04:17:32.489697186Z 
 87%|████████▋ | 4947/5712 [11:39:23<1:46:00,  8.31s/it]08/04/2024 21:17:32 - INFO - __main__ -   Step: 4947, LR: 7.431783360490284e-08, Loss: 0.20157387852668762
2024-08-05T04:17:40.890675645Z 
 87%|████████▋ | 4948/5712 [11:39:32<1:46:11,  8.34s/it]08/04/2024 21:17:40 - INFO - __main__ -   Step: 4948, LR: 7.422055497458595e-08, Loss: 0.058556247502565384
2024-08-05T04:17:49.195969410Z 
 87%|████████▋ | 4949/5712 [11:39:40<1:45:55,  8.33s/it]08/04/2024 21:17:49 - INFO - __main__ -   Step: 4949, LR: 7.412327634426907e-08, Loss: 0.08159004151821136
2024-08-05T04:17:57.668447780Z 
 87%|████████▋ | 4950/5712 [11:39:48<1:46:19,  8.37s/it]08/04/2024 21:17:57 - INFO - __main__ -   Step: 4950, LR: 7.402599771395218e-08, Loss: 0.07314878702163696
2024-08-05T04:18:06.052725701Z 
 87%|████████▋ | 4951/5712 [11:39:57<1:46:14,  8.38s/it]08/04/2024 21:18:06 - INFO - __main__ -   Step: 4951, LR: 7.392871908363529e-08, Loss: 0.1580708771944046
2024-08-05T04:18:15.443810678Z 
 87%|████████▋ | 4952/5712 [11:40:06<1:49:57,  8.68s/it]08/04/2024 21:18:15 - INFO - __main__ -   Step: 4952, LR: 7.383144045331842e-08, Loss: 0.06471264362335205
2024-08-05T04:18:23.900654454Z 
 87%|████████▋ | 4953/5712 [11:40:15<1:48:57,  8.61s/it]08/04/2024 21:18:23 - INFO - __main__ -   Step: 4953, LR: 7.373416182300153e-08, Loss: 0.05197082459926605
2024-08-05T04:18:32.262705471Z 
 87%|████████▋ | 4954/5712 [11:40:23<1:47:51,  8.54s/it]08/04/2024 21:18:32 - INFO - __main__ -   Step: 4954, LR: 7.363688319268464e-08, Loss: 0.09407587349414825
2024-08-05T04:18:40.941749765Z 
 87%|████████▋ | 4955/5712 [11:40:32<1:48:15,  8.58s/it]08/04/2024 21:18:40 - INFO - __main__ -   Step: 4955, LR: 7.353960456236775e-08, Loss: 0.058207280933856964
2024-08-05T04:18:48.911249436Z 
 87%|████████▋ | 4956/5712 [11:40:40<1:45:48,  8.40s/it]08/04/2024 21:18:48 - INFO - __main__ -   Step: 4956, LR: 7.344232593205087e-08, Loss: 0.0858093872666359
2024-08-05T04:18:57.342904106Z 
 87%|████████▋ | 4957/5712 [11:40:48<1:45:47,  8.41s/it]08/04/2024 21:18:57 - INFO - __main__ -   Step: 4957, LR: 7.334504730173399e-08, Loss: 0.0485413558781147
2024-08-05T04:19:06.052175076Z 
 87%|████████▋ | 4958/5712 [11:40:57<1:46:47,  8.50s/it]08/04/2024 21:19:06 - INFO - __main__ -   Step: 4958, LR: 7.32477686714171e-08, Loss: 0.09260892868041992
2024-08-05T04:19:13.903309045Z 
 87%|████████▋ | 4959/5712 [11:41:05<1:44:12,  8.30s/it]08/04/2024 21:19:13 - INFO - __main__ -   Step: 4959, LR: 7.315049004110022e-08, Loss: 0.054891135543584824
2024-08-05T04:19:23.418586490Z 
 87%|████████▋ | 4960/5712 [11:41:14<1:48:37,  8.67s/it]08/04/2024 21:19:23 - INFO - __main__ -   Step: 4960, LR: 7.305321141078333e-08, Loss: 0.10874082148075104
2024-08-05T04:19:32.001938171Z 
 87%|████████▋ | 4961/5712 [11:41:23<1:48:10,  8.64s/it]08/04/2024 21:19:32 - INFO - __main__ -   Step: 4961, LR: 7.295593278046645e-08, Loss: 0.0687611848115921
2024-08-05T04:19:40.740610231Z 
 87%|████████▋ | 4962/5712 [11:41:31<1:48:23,  8.67s/it]08/04/2024 21:19:40 - INFO - __main__ -   Step: 4962, LR: 7.285865415014957e-08, Loss: 0.05615294724702835
2024-08-05T04:19:48.999937686Z 
 87%|████████▋ | 4963/5712 [11:41:40<1:46:41,  8.55s/it]08/04/2024 21:19:48 - INFO - __main__ -   Step: 4963, LR: 7.276137551983268e-08, Loss: 0.07017634809017181
2024-08-05T04:19:57.250141323Z 
 87%|████████▋ | 4964/5712 [11:41:48<1:45:27,  8.46s/it]08/04/2024 21:19:57 - INFO - __main__ -   Step: 4964, LR: 7.266409688951579e-08, Loss: 0.11486057192087173
2024-08-05T04:20:05.649812158Z 
 87%|████████▋ | 4965/5712 [11:41:56<1:45:05,  8.44s/it]08/04/2024 21:20:05 - INFO - __main__ -   Step: 4965, LR: 7.25668182591989e-08, Loss: 0.055736951529979706
2024-08-05T04:20:14.030188039Z 
 87%|████████▋ | 4966/5712 [11:42:05<1:44:43,  8.42s/it]08/04/2024 21:20:14 - INFO - __main__ -   Step: 4966, LR: 7.246953962888203e-08, Loss: 0.055854614824056625
2024-08-05T04:20:22.085703550Z 
 87%|████████▋ | 4967/5712 [11:42:13<1:43:12,  8.31s/it]08/04/2024 21:20:22 - INFO - __main__ -   Step: 4967, LR: 7.237226099856514e-08, Loss: 0.050934672355651855
2024-08-05T04:20:30.604226031Z 
 87%|████████▋ | 4968/5712 [11:42:21<1:43:50,  8.37s/it]08/04/2024 21:20:30 - INFO - __main__ -   Step: 4968, LR: 7.227498236824825e-08, Loss: 0.04798836633563042
2024-08-05T04:20:39.220138819Z 
 87%|████████▋ | 4969/5712 [11:42:30<1:44:36,  8.45s/it]08/04/2024 21:20:39 - INFO - __main__ -   Step: 4969, LR: 7.217770373793137e-08, Loss: 0.03458140790462494
2024-08-05T04:20:47.782448986Z 
 87%|████████▋ | 4970/5712 [11:42:38<1:44:53,  8.48s/it]08/04/2024 21:20:47 - INFO - __main__ -   Step: 4970, LR: 7.208042510761449e-08, Loss: 0.06736829876899719
2024-08-05T04:20:56.447836265Z 
 87%|████████▋ | 4971/5712 [11:42:47<1:45:25,  8.54s/it]08/04/2024 21:20:56 - INFO - __main__ -   Step: 4971, LR: 7.19831464772976e-08, Loss: 0.05129723995923996
2024-08-05T04:21:04.758169699Z 
 87%|████████▋ | 4972/5712 [11:42:55<1:44:26,  8.47s/it]08/04/2024 21:21:04 - INFO - __main__ -   Step: 4972, LR: 7.188586784698072e-08, Loss: 0.04511226341128349
2024-08-05T04:21:12.902232923Z 
 87%|████████▋ | 4973/5712 [11:43:04<1:43:06,  8.37s/it]08/04/2024 21:21:12 - INFO - __main__ -   Step: 4973, LR: 7.178858921666383e-08, Loss: 0.02972075715661049
2024-08-05T04:21:21.270317166Z 
 87%|████████▋ | 4974/5712 [11:43:12<1:42:57,  8.37s/it]08/04/2024 21:21:21 - INFO - __main__ -   Step: 4974, LR: 7.169131058634694e-08, Loss: 0.10740749537944794
2024-08-05T04:21:29.672474424Z 
 87%|████████▋ | 4975/5712 [11:43:20<1:42:55,  8.38s/it]08/04/2024 21:21:29 - INFO - __main__ -   Step: 4975, LR: 7.159403195603007e-08, Loss: 0.046691980212926865
2024-08-05T04:21:38.274551847Z 
 87%|████████▋ | 4976/5712 [11:43:29<1:43:36,  8.45s/it]08/04/2024 21:21:38 - INFO - __main__ -   Step: 4976, LR: 7.149675332571318e-08, Loss: 0.03828665614128113
2024-08-05T04:21:47.257235070Z 
 87%|████████▋ | 4977/5712 [11:43:38<1:45:26,  8.61s/it]08/04/2024 21:21:47 - INFO - __main__ -   Step: 4977, LR: 7.139947469539628e-08, Loss: 0.040258001536130905
2024-08-05T04:21:55.628653752Z 
 87%|████████▋ | 4978/5712 [11:43:46<1:44:25,  8.54s/it]08/04/2024 21:21:55 - INFO - __main__ -   Step: 4978, LR: 7.130219606507939e-08, Loss: 0.07978643476963043
2024-08-05T04:22:04.005149815Z 
 87%|████████▋ | 4979/5712 [11:43:55<1:43:42,  8.49s/it]08/04/2024 21:22:04 - INFO - __main__ -   Step: 4979, LR: 7.120491743476251e-08, Loss: 0.09456801414489746
2024-08-05T04:22:12.777099632Z 
 87%|████████▋ | 4980/5712 [11:44:03<1:44:35,  8.57s/it]08/04/2024 21:22:12 - INFO - __main__ -   Step: 4980, LR: 7.110763880444563e-08, Loss: 0.02219042181968689
2024-08-05T04:22:20.938929975Z 
 87%|████████▋ | 4981/5712 [11:44:12<1:42:56,  8.45s/it]08/04/2024 21:22:20 - INFO - __main__ -   Step: 4981, LR: 7.101036017412874e-08, Loss: 0.06295162439346313
2024-08-05T04:22:29.361774584Z 
 87%|████████▋ | 4982/5712 [11:44:20<1:42:42,  8.44s/it]08/04/2024 21:22:29 - INFO - __main__ -   Step: 4982, LR: 7.091308154381185e-08, Loss: 0.05109773948788643
2024-08-05T04:22:37.683744998Z 
 87%|████████▋ | 4983/5712 [11:44:28<1:42:07,  8.41s/it]08/04/2024 21:22:37 - INFO - __main__ -   Step: 4983, LR: 7.081580291349496e-08, Loss: 0.09372881799936295
2024-08-05T04:22:46.263778823Z 
 87%|████████▋ | 4984/5712 [11:44:37<1:42:37,  8.46s/it]08/04/2024 21:22:46 - INFO - __main__ -   Step: 4984, LR: 7.071852428317809e-08, Loss: 0.08764252066612244
2024-08-05T04:22:54.434966163Z 
 87%|████████▋ | 4985/5712 [11:44:45<1:41:26,  8.37s/it]08/04/2024 21:22:54 - INFO - __main__ -   Step: 4985, LR: 7.06212456528612e-08, Loss: 0.048399314284324646
2024-08-05T04:23:03.136846728Z 
 87%|████████▋ | 4986/5712 [11:44:54<1:42:29,  8.47s/it]08/04/2024 21:23:03 - INFO - __main__ -   Step: 4986, LR: 7.052396702254431e-08, Loss: 0.061343684792518616
2024-08-05T04:23:11.732019612Z 
 87%|████████▋ | 4987/5712 [11:45:02<1:42:48,  8.51s/it]08/04/2024 21:23:11 - INFO - __main__ -   Step: 4987, LR: 7.042668839222743e-08, Loss: 0.13575948774814606
2024-08-05T04:23:20.012599617Z 
 87%|████████▋ | 4988/5712 [11:45:11<1:41:50,  8.44s/it]08/04/2024 21:23:20 - INFO - __main__ -   Step: 4988, LR: 7.032940976191055e-08, Loss: 0.06232359632849693
2024-08-05T04:23:28.536199495Z 
 87%|████████▋ | 4989/5712 [11:45:19<1:42:00,  8.47s/it]08/04/2024 21:23:28 - INFO - __main__ -   Step: 4989, LR: 7.023213113159366e-08, Loss: 0.10756190121173859
2024-08-05T04:23:37.070422705Z 
 87%|████████▋ | 4990/5712 [11:45:28<1:42:06,  8.49s/it]08/04/2024 21:23:37 - INFO - __main__ -   Step: 4990, LR: 7.013485250127678e-08, Loss: 0.09654282033443451
2024-08-05T04:23:45.729686294Z 
 87%|████████▋ | 4991/5712 [11:45:36<1:42:35,  8.54s/it]08/04/2024 21:23:45 - INFO - __main__ -   Step: 4991, LR: 7.003757387095989e-08, Loss: 0.05882009118795395
2024-08-05T04:23:54.755421569Z 
 87%|████████▋ | 4992/5712 [11:45:45<1:44:12,  8.68s/it]08/04/2024 21:23:54 - INFO - __main__ -   Step: 4992, LR: 6.9940295240643e-08, Loss: 0.04086875915527344
2024-08-05T04:24:03.133693137Z 
 87%|████████▋ | 4993/5712 [11:45:54<1:42:57,  8.59s/it]08/04/2024 21:24:03 - INFO - __main__ -   Step: 4993, LR: 6.984301661032613e-08, Loss: 0.09939248114824295
2024-08-05T04:24:11.382330514Z 
 87%|████████▋ | 4994/5712 [11:46:02<1:41:35,  8.49s/it]08/04/2024 21:24:11 - INFO - __main__ -   Step: 4994, LR: 6.974573798000924e-08, Loss: 0.10665512084960938
2024-08-05T04:24:19.547660557Z 
 87%|████████▋ | 4995/5712 [11:46:10<1:40:17,  8.39s/it]08/04/2024 21:24:19 - INFO - __main__ -   Step: 4995, LR: 6.964845934969235e-08, Loss: 0.12307696789503098
2024-08-05T04:24:27.992682913Z 
 87%|████████▋ | 4996/5712 [11:46:19<1:40:20,  8.41s/it]08/04/2024 21:24:27 - INFO - __main__ -   Step: 4996, LR: 6.955118071937546e-08, Loss: 0.15016326308250427
2024-08-05T04:24:36.207893684Z 
 87%|████████▋ | 4997/5712 [11:46:27<1:39:30,  8.35s/it]08/04/2024 21:24:36 - INFO - __main__ -   Step: 4997, LR: 6.945390208905859e-08, Loss: 0.032243214547634125
2024-08-05T04:24:44.530444379Z 
 88%|████████▊ | 4998/5712 [11:46:35<1:39:16,  8.34s/it]08/04/2024 21:24:44 - INFO - __main__ -   Step: 4998, LR: 6.93566234587417e-08, Loss: 0.09793305397033691
2024-08-05T04:24:53.376058816Z 
 88%|████████▊ | 4999/5712 [11:46:44<1:40:55,  8.49s/it]08/04/2024 21:24:53 - INFO - __main__ -   Step: 4999, LR: 6.925934482842481e-08, Loss: 0.041826315224170685
2024-08-05T04:25:01.801413761Z 
 88%|████████▊ | 5000/5712 [11:46:52<1:40:32,  8.47s/it]08/04/2024 21:25:01 - INFO - __main__ -   Step: 5000, LR: 6.916206619810793e-08, Loss: 0.05748867988586426
2024-08-05T04:25:10.210378027Z 
 88%|████████▊ | 5001/5712 [11:47:01<1:40:10,  8.45s/it]08/04/2024 21:25:10 - INFO - __main__ -   Step: 5001, LR: 6.906478756779104e-08, Loss: 0.08805567771196365
2024-08-05T04:25:18.431171990Z 
 88%|████████▊ | 5002/5712 [11:47:09<1:39:12,  8.38s/it]08/04/2024 21:25:18 - INFO - __main__ -   Step: 5002, LR: 6.896750893747416e-08, Loss: 0.06457097083330154
2024-08-05T04:25:27.021892807Z 
 88%|████████▊ | 5003/5712 [11:47:18<1:39:47,  8.45s/it]08/04/2024 21:25:27 - INFO - __main__ -   Step: 5003, LR: 6.887023030715728e-08, Loss: 0.09011034667491913
2024-08-05T04:25:35.741869948Z 
 88%|████████▊ | 5004/5712 [11:47:26<1:40:37,  8.53s/it]08/04/2024 21:25:35 - INFO - __main__ -   Step: 5004, LR: 6.877295167684039e-08, Loss: 0.03684783726930618
2024-08-05T04:25:43.915072106Z 
 88%|████████▊ | 5005/5712 [11:47:35<1:39:14,  8.42s/it]08/04/2024 21:25:43 - INFO - __main__ -   Step: 5005, LR: 6.86756730465235e-08, Loss: 0.08456814289093018
2024-08-05T04:25:52.001803534Z 
 88%|████████▊ | 5006/5712 [11:47:43<1:37:54,  8.32s/it]08/04/2024 21:25:52 - INFO - __main__ -   Step: 5006, LR: 6.857839441620663e-08, Loss: 0.12799349427223206
2024-08-05T04:26:00.278294700Z 
 88%|████████▊ | 5007/5712 [11:47:51<1:37:37,  8.31s/it]08/04/2024 21:26:00 - INFO - __main__ -   Step: 5007, LR: 6.848111578588974e-08, Loss: 0.07897365093231201
2024-08-05T04:26:08.709164333Z 
 88%|████████▊ | 5008/5712 [11:47:59<1:37:54,  8.34s/it]08/04/2024 21:26:08 - INFO - __main__ -   Step: 5008, LR: 6.838383715557285e-08, Loss: 0.06503511965274811
2024-08-05T04:26:17.749303629Z 
 88%|████████▊ | 5009/5712 [11:48:08<1:40:12,  8.55s/it]08/04/2024 21:26:17 - INFO - __main__ -   Step: 5009, LR: 6.828655852525596e-08, Loss: 0.02382432110607624
2024-08-05T04:26:26.335401696Z 
 88%|████████▊ | 5010/5712 [11:48:17<1:40:11,  8.56s/it]08/04/2024 21:26:26 - INFO - __main__ -   Step: 5010, LR: 6.818927989493907e-08, Loss: 0.04200700670480728
2024-08-05T04:26:34.882708935Z 
 88%|████████▊ | 5011/5712 [11:48:26<1:39:59,  8.56s/it]08/04/2024 21:26:34 - INFO - __main__ -   Step: 5011, LR: 6.80920012646222e-08, Loss: 0.08518143743276596
2024-08-05T04:26:43.321986718Z 
 88%|████████▊ | 5012/5712 [11:48:34<1:39:25,  8.52s/it]08/04/2024 21:26:43 - INFO - __main__ -   Step: 5012, LR: 6.799472263430531e-08, Loss: 0.07225649058818817
2024-08-05T04:26:51.759321390Z 
 88%|████████▊ | 5013/5712 [11:48:42<1:38:59,  8.50s/it]08/04/2024 21:26:51 - INFO - __main__ -   Step: 5013, LR: 6.789744400398843e-08, Loss: 0.11720467358827591
2024-08-05T04:26:59.888307447Z 
 88%|████████▊ | 5014/5712 [11:48:51<1:37:33,  8.39s/it]08/04/2024 21:26:59 - INFO - __main__ -   Step: 5014, LR: 6.780016537367152e-08, Loss: 0.12694358825683594
2024-08-05T04:27:08.041183179Z 
 88%|████████▊ | 5015/5712 [11:48:59<1:36:36,  8.32s/it]08/04/2024 21:27:08 - INFO - __main__ -   Step: 5015, LR: 6.770288674335466e-08, Loss: 0.024866219609975815
2024-08-05T04:27:16.813754641Z 
 88%|████████▊ | 5016/5712 [11:49:07<1:38:03,  8.45s/it]08/04/2024 21:27:16 - INFO - __main__ -   Step: 5016, LR: 6.760560811303776e-08, Loss: 0.051819153130054474
2024-08-05T04:27:25.018746850Z 
 88%|████████▊ | 5017/5712 [11:49:16<1:37:03,  8.38s/it]08/04/2024 21:27:25 - INFO - __main__ -   Step: 5017, LR: 6.750832948272087e-08, Loss: 0.0893816202878952
2024-08-05T04:27:33.484806027Z 
 88%|████████▊ | 5018/5712 [11:49:24<1:37:13,  8.41s/it]08/04/2024 21:27:33 - INFO - __main__ -   Step: 5018, LR: 6.741105085240399e-08, Loss: 0.09878571331501007
2024-08-05T04:27:41.672320809Z 
 88%|████████▊ | 5019/5712 [11:49:32<1:36:19,  8.34s/it]08/04/2024 21:27:41 - INFO - __main__ -   Step: 5019, LR: 6.73137722220871e-08, Loss: 0.04999886453151703
2024-08-05T04:27:50.600102847Z 
 88%|████████▊ | 5020/5712 [11:49:41<1:38:12,  8.52s/it]08/04/2024 21:27:50 - INFO - __main__ -   Step: 5020, LR: 6.721649359177022e-08, Loss: 0.054014239460229874
2024-08-05T04:27:59.067166685Z 
 88%|████████▊ | 5021/5712 [11:49:50<1:37:54,  8.50s/it]08/04/2024 21:27:59 - INFO - __main__ -   Step: 5021, LR: 6.711921496145334e-08, Loss: 0.07277346402406693
2024-08-05T04:28:07.050371918Z 
 88%|████████▊ | 5022/5712 [11:49:58<1:35:58,  8.35s/it]08/04/2024 21:28:07 - INFO - __main__ -   Step: 5022, LR: 6.702193633113645e-08, Loss: 0.051498472690582275
2024-08-05T04:28:15.284358742Z 
 88%|████████▊ | 5023/5712 [11:50:06<1:35:27,  8.31s/it]08/04/2024 21:28:15 - INFO - __main__ -   Step: 5023, LR: 6.692465770081956e-08, Loss: 0.03167547285556793
2024-08-05T04:28:24.205591473Z 
 88%|████████▊ | 5024/5712 [11:50:15<1:37:24,  8.50s/it]08/04/2024 21:28:24 - INFO - __main__ -   Step: 5024, LR: 6.682737907050269e-08, Loss: 0.09922043234109879
2024-08-05T04:28:33.260513717Z 
 88%|████████▊ | 5025/5712 [11:50:24<1:39:11,  8.66s/it]08/04/2024 21:28:33 - INFO - __main__ -   Step: 5025, LR: 6.67301004401858e-08, Loss: 0.04571284353733063
2024-08-05T04:28:41.706536255Z 
 88%|████████▊ | 5026/5712 [11:50:32<1:38:18,  8.60s/it]08/04/2024 21:28:41 - INFO - __main__ -   Step: 5026, LR: 6.663282180986891e-08, Loss: 0.07986993342638016
2024-08-05T04:28:49.932773132Z 
 88%|████████▊ | 5027/5712 [11:50:41<1:36:53,  8.49s/it]08/04/2024 21:28:49 - INFO - __main__ -   Step: 5027, LR: 6.653554317955202e-08, Loss: 0.043473925441503525
2024-08-05T04:28:58.279493104Z 
 88%|████████▊ | 5028/5712 [11:50:49<1:36:16,  8.44s/it]08/04/2024 21:28:58 - INFO - __main__ -   Step: 5028, LR: 6.643826454923514e-08, Loss: 0.0857471451163292
2024-08-05T04:29:06.913402197Z 
 88%|████████▊ | 5029/5712 [11:50:58<1:36:46,  8.50s/it]08/04/2024 21:29:06 - INFO - __main__ -   Step: 5029, LR: 6.634098591891826e-08, Loss: 0.0431080237030983
2024-08-05T04:29:15.238799828Z 
 88%|████████▊ | 5030/5712 [11:51:06<1:36:01,  8.45s/it]08/04/2024 21:29:15 - INFO - __main__ -   Step: 5030, LR: 6.624370728860137e-08, Loss: 0.04826740920543671
2024-08-05T04:29:23.258056663Z 
 88%|████████▊ | 5031/5712 [11:51:14<1:34:25,  8.32s/it]08/04/2024 21:29:23 - INFO - __main__ -   Step: 5031, LR: 6.614642865828449e-08, Loss: 0.1037055253982544
2024-08-05T04:29:31.412787495Z 
 88%|████████▊ | 5032/5712 [11:51:22<1:33:43,  8.27s/it]08/04/2024 21:29:31 - INFO - __main__ -   Step: 5032, LR: 6.60491500279676e-08, Loss: 0.044639721512794495
2024-08-05T04:29:40.466711783Z 
 88%|████████▊ | 5033/5712 [11:51:31<1:36:15,  8.51s/it]08/04/2024 21:29:40 - INFO - __main__ -   Step: 5033, LR: 6.595187139765072e-08, Loss: 0.09741762280464172
2024-08-05T04:29:48.932984130Z 
 88%|████████▊ | 5034/5712 [11:51:40<1:35:58,  8.49s/it]08/04/2024 21:29:48 - INFO - __main__ -   Step: 5034, LR: 6.585459276733384e-08, Loss: 0.043000414967536926
2024-08-05T04:29:57.551947648Z 
 88%|████████▊ | 5035/5712 [11:51:48<1:36:15,  8.53s/it]08/04/2024 21:29:57 - INFO - __main__ -   Step: 5035, LR: 6.575731413701695e-08, Loss: 0.1340479850769043
2024-08-05T04:30:05.888966570Z 
 88%|████████▊ | 5036/5712 [11:51:57<1:35:27,  8.47s/it]08/04/2024 21:30:05 - INFO - __main__ -   Step: 5036, LR: 6.566003550670006e-08, Loss: 0.07796639204025269
2024-08-05T04:30:14.656683543Z 
 88%|████████▊ | 5037/5712 [11:52:05<1:36:18,  8.56s/it]08/04/2024 21:30:14 - INFO - __main__ -   Step: 5037, LR: 6.556275687638317e-08, Loss: 0.06507602334022522
2024-08-05T04:30:23.479280892Z 
 88%|████████▊ | 5038/5712 [11:52:14<1:37:03,  8.64s/it]08/04/2024 21:30:23 - INFO - __main__ -   Step: 5038, LR: 6.54654782460663e-08, Loss: 0.07310087978839874
2024-08-05T04:30:31.971232468Z 
 88%|████████▊ | 5039/5712 [11:52:23<1:36:24,  8.60s/it]08/04/2024 21:30:31 - INFO - __main__ -   Step: 5039, LR: 6.536819961574941e-08, Loss: 0.055004581809043884
2024-08-05T04:30:40.072692186Z 
 88%|████████▊ | 5040/5712 [11:52:31<1:34:36,  8.45s/it]08/04/2024 21:30:40 - INFO - __main__ -   Step: 5040, LR: 6.527092098543252e-08, Loss: 0.04765508696436882
2024-08-05T04:30:49.086173273Z 
 88%|████████▊ | 5041/5712 [11:52:40<1:36:22,  8.62s/it]08/04/2024 21:30:49 - INFO - __main__ -   Step: 5041, LR: 6.517364235511564e-08, Loss: 0.06785373389720917
2024-08-05T04:30:58.346850265Z 
 88%|████████▊ | 5042/5712 [11:52:49<1:38:22,  8.81s/it]08/04/2024 21:30:58 - INFO - __main__ -   Step: 5042, LR: 6.507636372479876e-08, Loss: 0.11129605025053024
2024-08-05T04:31:06.739914684Z 
 88%|████████▊ | 5043/5712 [11:52:57<1:36:50,  8.69s/it]08/04/2024 21:31:06 - INFO - __main__ -   Step: 5043, LR: 6.497908509448187e-08, Loss: 0.10315614938735962
2024-08-05T04:31:14.894327958Z 
 88%|████████▊ | 5044/5712 [11:53:06<1:34:55,  8.53s/it]08/04/2024 21:31:14 - INFO - __main__ -   Step: 5044, LR: 6.488180646416499e-08, Loss: 0.13113048672676086
2024-08-05T04:31:23.348737848Z 
 88%|████████▊ | 5045/5712 [11:53:14<1:34:32,  8.50s/it]08/04/2024 21:31:23 - INFO - __main__ -   Step: 5045, LR: 6.47845278338481e-08, Loss: 0.04667770862579346
2024-08-05T04:31:31.522727488Z 
 88%|████████▊ | 5046/5712 [11:53:22<1:33:17,  8.41s/it]08/04/2024 21:31:31 - INFO - __main__ -   Step: 5046, LR: 6.468724920353121e-08, Loss: 0.05949034541845322
2024-08-05T04:31:39.881775822Z 
 88%|████████▊ | 5047/5712 [11:53:31<1:33:00,  8.39s/it]08/04/2024 21:31:39 - INFO - __main__ -   Step: 5047, LR: 6.458997057321434e-08, Loss: 0.06355706602334976
2024-08-05T04:31:47.996764864Z 
 88%|████████▊ | 5048/5712 [11:53:39<1:31:56,  8.31s/it]08/04/2024 21:31:47 - INFO - __main__ -   Step: 5048, LR: 6.449269194289745e-08, Loss: 0.07178759574890137
2024-08-05T04:31:56.303723920Z 
 88%|████████▊ | 5049/5712 [11:53:47<1:31:48,  8.31s/it]08/04/2024 21:31:56 - INFO - __main__ -   Step: 5049, LR: 6.439541331258056e-08, Loss: 0.0875445306301117
2024-08-05T04:32:05.302856745Z 
 88%|████████▊ | 5050/5712 [11:53:56<1:33:57,  8.52s/it]08/04/2024 21:32:05 - INFO - __main__ -   Step: 5050, LR: 6.429813468226367e-08, Loss: 0.06823927164077759
2024-08-05T04:32:14.302581493Z 
 88%|████████▊ | 5051/5712 [11:54:05<1:35:24,  8.66s/it]08/04/2024 21:32:14 - INFO - __main__ -   Step: 5051, LR: 6.42008560519468e-08, Loss: 0.07029509544372559
2024-08-05T04:32:22.634035347Z 
 88%|████████▊ | 5052/5712 [11:54:13<1:34:10,  8.56s/it]08/04/2024 21:32:22 - INFO - __main__ -   Step: 5052, LR: 6.410357742162991e-08, Loss: 0.0517883375287056
2024-08-05T04:32:31.238723676Z 
 88%|████████▊ | 5053/5712 [11:54:22<1:34:10,  8.57s/it]08/04/2024 21:32:31 - INFO - __main__ -   Step: 5053, LR: 6.400629879131301e-08, Loss: 0.08347741514444351
2024-08-05T04:32:39.835591319Z 
 88%|████████▊ | 5054/5712 [11:54:30<1:34:06,  8.58s/it]08/04/2024 21:32:39 - INFO - __main__ -   Step: 5054, LR: 6.390902016099612e-08, Loss: 0.09016187489032745
2024-08-05T04:32:48.023149707Z 
 88%|████████▊ | 5055/5712 [11:54:39<1:32:40,  8.46s/it]08/04/2024 21:32:48 - INFO - __main__ -   Step: 5055, LR: 6.381174153067923e-08, Loss: 0.0682082548737526
2024-08-05T04:32:56.375660829Z 
 89%|████████▊ | 5056/5712 [11:54:47<1:32:10,  8.43s/it]08/04/2024 21:32:56 - INFO - __main__ -   Step: 5056, LR: 6.371446290036236e-08, Loss: 0.05780943110585213
2024-08-05T04:33:04.877362228Z 
 89%|████████▊ | 5057/5712 [11:54:56<1:32:15,  8.45s/it]08/04/2024 21:33:04 - INFO - __main__ -   Step: 5057, LR: 6.361718427004547e-08, Loss: 0.07060736417770386
2024-08-05T04:33:13.524509937Z 
 89%|████████▊ | 5058/5712 [11:55:04<1:32:45,  8.51s/it]08/04/2024 21:33:13 - INFO - __main__ -   Step: 5058, LR: 6.351990563972858e-08, Loss: 0.06464909762144089
2024-08-05T04:33:22.549158912Z 
 89%|████████▊ | 5059/5712 [11:55:13<1:34:17,  8.66s/it]08/04/2024 21:33:22 - INFO - __main__ -   Step: 5059, LR: 6.34226270094117e-08, Loss: 0.06005220487713814
2024-08-05T04:33:31.462948108Z 
 89%|████████▊ | 5060/5712 [11:55:22<1:34:58,  8.74s/it]08/04/2024 21:33:31 - INFO - __main__ -   Step: 5060, LR: 6.332534837909482e-08, Loss: 0.06717771291732788
2024-08-05T04:33:40.138882311Z 
 89%|████████▊ | 5061/5712 [11:55:31<1:34:37,  8.72s/it]08/04/2024 21:33:40 - INFO - __main__ -   Step: 5061, LR: 6.322806974877793e-08, Loss: 0.06957702338695526
2024-08-05T04:33:48.301369002Z 
 89%|████████▊ | 5062/5712 [11:55:39<1:32:39,  8.55s/it]08/04/2024 21:33:48 - INFO - __main__ -   Step: 5062, LR: 6.313079111846105e-08, Loss: 0.07403847575187683
2024-08-05T04:33:56.812849221Z 
 89%|████████▊ | 5063/5712 [11:55:47<1:32:22,  8.54s/it]08/04/2024 21:33:56 - INFO - __main__ -   Step: 5063, LR: 6.303351248814416e-08, Loss: 0.09530239552259445
2024-08-05T04:34:05.121489740Z 
 89%|████████▊ | 5064/5712 [11:55:56<1:31:29,  8.47s/it]08/04/2024 21:34:05 - INFO - __main__ -   Step: 5064, LR: 6.293623385782727e-08, Loss: 0.12629090249538422
2024-08-05T04:34:13.191206377Z 
 89%|████████▊ | 5065/5712 [11:56:04<1:30:02,  8.35s/it]08/04/2024 21:34:13 - INFO - __main__ -   Step: 5065, LR: 6.28389552275104e-08, Loss: 0.1017787903547287
2024-08-05T04:34:21.558387159Z 
 89%|████████▊ | 5066/5712 [11:56:12<1:29:57,  8.36s/it]08/04/2024 21:34:21 - INFO - __main__ -   Step: 5066, LR: 6.274167659719351e-08, Loss: 0.06464669853448868
2024-08-05T04:34:30.907631975Z 
 89%|████████▊ | 5067/5712 [11:56:22<1:33:01,  8.65s/it]08/04/2024 21:34:30 - INFO - __main__ -   Step: 5067, LR: 6.264439796687662e-08, Loss: 0.08211184293031693
2024-08-05T04:34:39.545443081Z 
 89%|████████▊ | 5068/5712 [11:56:30<1:32:49,  8.65s/it]08/04/2024 21:34:39 - INFO - __main__ -   Step: 5068, LR: 6.254711933655973e-08, Loss: 0.08713796734809875
2024-08-05T04:34:48.048360313Z 
 89%|████████▊ | 5069/5712 [11:56:39<1:32:12,  8.60s/it]08/04/2024 21:34:48 - INFO - __main__ -   Step: 5069, LR: 6.244984070624286e-08, Loss: 0.16982492804527283
2024-08-05T04:34:56.392017161Z 
 89%|████████▉ | 5070/5712 [11:56:47<1:31:14,  8.53s/it]08/04/2024 21:34:56 - INFO - __main__ -   Step: 5070, LR: 6.235256207592597e-08, Loss: 0.046036675572395325
2024-08-05T04:35:05.155642161Z 
 89%|████████▉ | 5071/5712 [11:56:56<1:31:51,  8.60s/it]08/04/2024 21:35:05 - INFO - __main__ -   Step: 5071, LR: 6.225528344560908e-08, Loss: 0.0670737624168396
2024-08-05T04:35:13.363578476Z 
 89%|████████▉ | 5072/5712 [11:57:04<1:30:27,  8.48s/it]08/04/2024 21:35:13 - INFO - __main__ -   Step: 5072, LR: 6.21580048152922e-08, Loss: 0.06267188489437103
2024-08-05T04:35:20.872738308Z 
 89%|████████▉ | 5073/5712 [11:57:12<1:27:13,  8.19s/it]08/04/2024 21:35:20 - INFO - __main__ -   Step: 5073, LR: 6.206072618497531e-08, Loss: 0.0539727583527565
2024-08-05T04:35:29.299158371Z 
 89%|████████▉ | 5074/5712 [11:57:20<1:27:50,  8.26s/it]08/04/2024 21:35:29 - INFO - __main__ -   Step: 5074, LR: 6.196344755465842e-08, Loss: 0.09152989089488983
2024-08-05T04:35:37.378242709Z 
 89%|████████▉ | 5075/5712 [11:57:28<1:27:07,  8.21s/it]08/04/2024 21:35:37 - INFO - __main__ -   Step: 5075, LR: 6.186616892434155e-08, Loss: 0.1393161416053772
2024-08-05T04:35:46.164472801Z 
 89%|████████▉ | 5076/5712 [11:57:37<1:28:49,  8.38s/it]08/04/2024 21:35:46 - INFO - __main__ -   Step: 5076, LR: 6.176889029402466e-08, Loss: 0.09179073572158813
2024-08-05T04:35:54.844483635Z 
 89%|████████▉ | 5077/5712 [11:57:45<1:29:38,  8.47s/it]08/04/2024 21:35:54 - INFO - __main__ -   Step: 5077, LR: 6.167161166370777e-08, Loss: 0.0712861567735672
2024-08-05T04:36:03.460251709Z 
 89%|████████▉ | 5078/5712 [11:57:54<1:29:57,  8.51s/it]08/04/2024 21:36:03 - INFO - __main__ -   Step: 5078, LR: 6.157433303339088e-08, Loss: 0.04189341142773628
2024-08-05T04:36:11.409508423Z 
 89%|████████▉ | 5079/5712 [11:58:02<1:28:02,  8.34s/it]08/04/2024 21:36:11 - INFO - __main__ -   Step: 5079, LR: 6.147705440307401e-08, Loss: 0.058613479137420654
2024-08-05T04:36:20.083833300Z 
 89%|████████▉ | 5080/5712 [11:58:11<1:28:56,  8.44s/it]08/04/2024 21:36:20 - INFO - __main__ -   Step: 5080, LR: 6.137977577275712e-08, Loss: 0.08812601864337921
2024-08-05T04:36:28.052443340Z 
 89%|████████▉ | 5081/5712 [11:58:19<1:27:18,  8.30s/it]08/04/2024 21:36:28 - INFO - __main__ -   Step: 5081, LR: 6.128249714244023e-08, Loss: 0.05629134923219681
2024-08-05T04:36:36.799425050Z 
 89%|████████▉ | 5082/5712 [11:58:27<1:28:33,  8.43s/it]08/04/2024 21:36:36 - INFO - __main__ -   Step: 5082, LR: 6.118521851212334e-08, Loss: 0.1122254878282547
2024-08-05T04:36:44.725242281Z 
 89%|████████▉ | 5083/5712 [11:58:35<1:26:49,  8.28s/it]08/04/2024 21:36:44 - INFO - __main__ -   Step: 5083, LR: 6.108793988180646e-08, Loss: 0.055422328412532806
2024-08-05T04:36:53.834290616Z 
 89%|████████▉ | 5084/5712 [11:58:44<1:29:16,  8.53s/it]08/04/2024 21:36:53 - INFO - __main__ -   Step: 5084, LR: 6.099066125148958e-08, Loss: 0.11211864650249481
2024-08-05T04:37:02.318832709Z 
 89%|████████▉ | 5085/5712 [11:58:53<1:28:59,  8.52s/it]08/04/2024 21:37:02 - INFO - __main__ -   Step: 5085, LR: 6.08933826211727e-08, Loss: 0.07838708907365799
2024-08-05T04:37:10.731373197Z 
 89%|████████▉ | 5086/5712 [11:59:01<1:28:31,  8.49s/it]08/04/2024 21:37:10 - INFO - __main__ -   Step: 5086, LR: 6.079610399085581e-08, Loss: 0.10737103223800659
2024-08-05T04:37:19.461235870Z 
 89%|████████▉ | 5087/5712 [11:59:10<1:29:09,  8.56s/it]08/04/2024 21:37:19 - INFO - __main__ -   Step: 5087, LR: 6.069882536053892e-08, Loss: 0.06703420728445053
2024-08-05T04:37:28.345016002Z 
 89%|████████▉ | 5088/5712 [11:59:19<1:30:01,  8.66s/it]08/04/2024 21:37:28 - INFO - __main__ -   Step: 5088, LR: 6.060154673022204e-08, Loss: 0.08548205345869064
2024-08-05T04:37:36.621796713Z 
 89%|████████▉ | 5089/5712 [11:59:27<1:28:42,  8.54s/it]08/04/2024 21:37:36 - INFO - __main__ -   Step: 5089, LR: 6.050426809990516e-08, Loss: 0.12097346037626266
2024-08-05T04:37:45.268411046Z 
 89%|████████▉ | 5090/5712 [11:59:36<1:28:52,  8.57s/it]08/04/2024 21:37:45 - INFO - __main__ -   Step: 5090, LR: 6.040698946958827e-08, Loss: 0.06102979555726051
2024-08-05T04:37:54.071196301Z 
 89%|████████▉ | 5091/5712 [11:59:45<1:29:26,  8.64s/it]08/04/2024 21:37:54 - INFO - __main__ -   Step: 5091, LR: 6.030971083927138e-08, Loss: 0.09439422190189362
2024-08-05T04:38:02.094383205Z 
 89%|████████▉ | 5092/5712 [11:59:53<1:27:23,  8.46s/it]08/04/2024 21:38:02 - INFO - __main__ -   Step: 5092, LR: 6.02124322089545e-08, Loss: 0.04652436077594757
2024-08-05T04:38:11.306769779Z 
 89%|████████▉ | 5093/5712 [12:00:02<1:29:34,  8.68s/it]08/04/2024 21:38:11 - INFO - __main__ -   Step: 5093, LR: 6.01151535786376e-08, Loss: 0.037490103393793106
2024-08-05T04:38:19.724316799Z 
 89%|████████▉ | 5094/5712 [12:00:10<1:28:37,  8.60s/it]08/04/2024 21:38:19 - INFO - __main__ -   Step: 5094, LR: 6.001787494832072e-08, Loss: 0.04961498826742172
2024-08-05T04:38:28.169948711Z 
 89%|████████▉ | 5095/5712 [12:00:19<1:27:59,  8.56s/it]08/04/2024 21:38:28 - INFO - __main__ -   Step: 5095, LR: 5.992059631800384e-08, Loss: 0.09348727017641068
2024-08-05T04:38:37.128132617Z 
 89%|████████▉ | 5096/5712 [12:00:28<1:29:04,  8.68s/it]08/04/2024 21:38:37 - INFO - __main__ -   Step: 5096, LR: 5.982331768768696e-08, Loss: 0.06380296498537064
2024-08-05T04:38:45.271137175Z 
 89%|████████▉ | 5097/5712 [12:00:36<1:27:17,  8.52s/it]08/04/2024 21:38:45 - INFO - __main__ -   Step: 5097, LR: 5.972603905737007e-08, Loss: 0.09870292246341705
2024-08-05T04:38:53.287908628Z 
 89%|████████▉ | 5098/5712 [12:00:44<1:25:37,  8.37s/it]08/04/2024 21:38:53 - INFO - __main__ -   Step: 5098, LR: 5.962876042705318e-08, Loss: 0.057374730706214905
2024-08-05T04:39:01.875248662Z 
 89%|████████▉ | 5099/5712 [12:00:53<1:26:09,  8.43s/it]08/04/2024 21:39:01 - INFO - __main__ -   Step: 5099, LR: 5.95314817967363e-08, Loss: 0.09413646161556244
2024-08-05T04:39:10.145077890Z 
 89%|████████▉ | 5100/5712 [12:01:01<1:25:31,  8.38s/it]08/04/2024 21:39:10 - INFO - __main__ -   Step: 5100, LR: 5.943420316641942e-08, Loss: 0.06533296406269073
2024-08-05T04:39:18.660031935Z 
 89%|████████▉ | 5101/5712 [12:01:09<1:25:46,  8.42s/it]08/04/2024 21:39:18 - INFO - __main__ -   Step: 5101, LR: 5.9336924536102524e-08, Loss: 0.07278867065906525
2024-08-05T04:39:27.156633018Z 
 89%|████████▉ | 5102/5712 [12:01:18<1:25:51,  8.45s/it]08/04/2024 21:39:27 - INFO - __main__ -   Step: 5102, LR: 5.923964590578564e-08, Loss: 0.06919597834348679
2024-08-05T04:39:35.995998987Z 
 89%|████████▉ | 5103/5712 [12:01:27<1:26:55,  8.56s/it]08/04/2024 21:39:35 - INFO - __main__ -   Step: 5103, LR: 5.9142367275468755e-08, Loss: 0.08133214712142944
2024-08-05T04:39:44.601293013Z 
 89%|████████▉ | 5104/5712 [12:01:35<1:26:54,  8.58s/it]08/04/2024 21:39:44 - INFO - __main__ -   Step: 5104, LR: 5.9045088645151874e-08, Loss: 0.07124213129281998
2024-08-05T04:39:53.686068689Z 
 89%|████████▉ | 5105/5712 [12:01:44<1:28:18,  8.73s/it]08/04/2024 21:39:53 - INFO - __main__ -   Step: 5105, LR: 5.8947810014834986e-08, Loss: 0.10220736265182495
2024-08-05T04:40:02.101642024Z 
 89%|████████▉ | 5106/5712 [12:01:53<1:27:12,  8.63s/it]08/04/2024 21:40:02 - INFO - __main__ -   Step: 5106, LR: 5.8850531384518105e-08, Loss: 0.049746811389923096
2024-08-05T04:40:10.244851131Z 
 89%|████████▉ | 5107/5712 [12:02:01<1:25:34,  8.49s/it]08/04/2024 21:40:10 - INFO - __main__ -   Step: 5107, LR: 5.875325275420122e-08, Loss: 0.07800832390785217
2024-08-05T04:40:18.448494617Z 
 89%|████████▉ | 5108/5712 [12:02:09<1:24:34,  8.40s/it]08/04/2024 21:40:18 - INFO - __main__ -   Step: 5108, LR: 5.865597412388433e-08, Loss: 0.06480738520622253
2024-08-05T04:40:26.158697525Z 
 89%|████████▉ | 5109/5712 [12:02:17<1:22:21,  8.19s/it]08/04/2024 21:40:26 - INFO - __main__ -   Step: 5109, LR: 5.855869549356745e-08, Loss: 0.07289286702871323
2024-08-05T04:40:35.656034083Z 
 89%|████████▉ | 5110/5712 [12:02:26<1:26:07,  8.58s/it]08/04/2024 21:40:35 - INFO - __main__ -   Step: 5110, LR: 5.846141686325056e-08, Loss: 0.020669851452112198
2024-08-05T04:40:44.148605539Z 
 89%|████████▉ | 5111/5712 [12:02:35<1:25:43,  8.56s/it]08/04/2024 21:40:44 - INFO - __main__ -   Step: 5111, LR: 5.836413823293368e-08, Loss: 0.05131352320313454
2024-08-05T04:40:52.345900262Z 
 89%|████████▉ | 5112/5712 [12:02:43<1:24:29,  8.45s/it]08/04/2024 21:40:52 - INFO - __main__ -   Step: 5112, LR: 5.826685960261679e-08, Loss: 0.06929922103881836
2024-08-05T04:41:01.015221086Z 
 90%|████████▉ | 5113/5712 [12:02:52<1:25:00,  8.52s/it]08/04/2024 21:41:01 - INFO - __main__ -   Step: 5113, LR: 5.816958097229991e-08, Loss: 0.0456773117184639
2024-08-05T04:41:09.252193262Z 
 90%|████████▉ | 5114/5712 [12:03:00<1:24:02,  8.43s/it]08/04/2024 21:41:09 - INFO - __main__ -   Step: 5114, LR: 5.8072302341983023e-08, Loss: 0.04297330230474472
2024-08-05T04:41:17.576970918Z 
 90%|████████▉ | 5115/5712 [12:03:08<1:23:34,  8.40s/it]08/04/2024 21:41:17 - INFO - __main__ -   Step: 5115, LR: 5.7975023711666136e-08, Loss: 0.0764804556965828
2024-08-05T04:41:25.769879418Z 
 90%|████████▉ | 5116/5712 [12:03:16<1:22:49,  8.34s/it]08/04/2024 21:41:25 - INFO - __main__ -   Step: 5116, LR: 5.7877745081349255e-08, Loss: 0.06711950898170471
2024-08-05T04:41:33.816309275Z 
 90%|████████▉ | 5117/5712 [12:03:24<1:21:49,  8.25s/it]08/04/2024 21:41:33 - INFO - __main__ -   Step: 5117, LR: 5.778046645103237e-08, Loss: 0.10921268165111542
2024-08-05T04:41:42.868569509Z 
 90%|████████▉ | 5118/5712 [12:03:34<1:24:03,  8.49s/it]08/04/2024 21:41:42 - INFO - __main__ -   Step: 5118, LR: 5.7683187820715486e-08, Loss: 0.08058908581733704
2024-08-05T04:41:51.614253480Z 
 90%|████████▉ | 5119/5712 [12:03:42<1:24:40,  8.57s/it]08/04/2024 21:41:51 - INFO - __main__ -   Step: 5119, LR: 5.758590919039859e-08, Loss: 0.06214441359043121
2024-08-05T04:42:00.128365682Z 
 90%|████████▉ | 5120/5712 [12:03:51<1:24:22,  8.55s/it]08/04/2024 21:42:00 - INFO - __main__ -   Step: 5120, LR: 5.748863056008171e-08, Loss: 0.12057548761367798
2024-08-05T04:42:08.306034460Z 
 90%|████████▉ | 5121/5712 [12:03:59<1:23:07,  8.44s/it]08/04/2024 21:42:08 - INFO - __main__ -   Step: 5121, LR: 5.739135192976482e-08, Loss: 0.08414927124977112
2024-08-05T04:42:17.098160266Z 
 90%|████████▉ | 5122/5712 [12:04:08<1:24:01,  8.54s/it]08/04/2024 21:42:17 - INFO - __main__ -   Step: 5122, LR: 5.729407329944794e-08, Loss: 0.1337926834821701
2024-08-05T04:42:25.518163435Z 
 90%|████████▉ | 5123/5712 [12:04:16<1:23:31,  8.51s/it]08/04/2024 21:42:25 - INFO - __main__ -   Step: 5123, LR: 5.7196794669131054e-08, Loss: 0.05975130945444107
2024-08-05T04:42:33.559501679Z 
 90%|████████▉ | 5124/5712 [12:04:24<1:22:00,  8.37s/it]08/04/2024 21:42:33 - INFO - __main__ -   Step: 5124, LR: 5.7099516038814166e-08, Loss: 0.06869915872812271
2024-08-05T04:42:41.599319005Z 
 90%|████████▉ | 5125/5712 [12:04:32<1:20:54,  8.27s/it]08/04/2024 21:42:41 - INFO - __main__ -   Step: 5125, LR: 5.7002237408497285e-08, Loss: 0.0434078685939312
2024-08-05T04:42:49.815062499Z 
 90%|████████▉ | 5126/5712 [12:04:40<1:20:36,  8.25s/it]08/04/2024 21:42:49 - INFO - __main__ -   Step: 5126, LR: 5.69049587781804e-08, Loss: 0.04894924908876419
2024-08-05T04:42:59.173791247Z 
 90%|████████▉ | 5127/5712 [12:04:50<1:23:41,  8.58s/it]08/04/2024 21:42:59 - INFO - __main__ -   Step: 5127, LR: 5.6807680147863516e-08, Loss: 0.06858494877815247
2024-08-05T04:43:07.744248900Z 
 90%|████████▉ | 5128/5712 [12:04:58<1:23:31,  8.58s/it]08/04/2024 21:43:07 - INFO - __main__ -   Step: 5128, LR: 5.671040151754663e-08, Loss: 0.04568810015916824
2024-08-05T04:43:16.416953699Z 
 90%|████████▉ | 5129/5712 [12:05:07<1:23:38,  8.61s/it]08/04/2024 21:43:16 - INFO - __main__ -   Step: 5129, LR: 5.661312288722975e-08, Loss: 0.08106014132499695
2024-08-05T04:43:24.560345921Z 
 90%|████████▉ | 5130/5712 [12:05:15<1:22:08,  8.47s/it]08/04/2024 21:43:24 - INFO - __main__ -   Step: 5130, LR: 5.651584425691286e-08, Loss: 0.06212036684155464
2024-08-05T04:43:32.776449882Z 
 90%|████████▉ | 5131/5712 [12:05:23<1:21:16,  8.39s/it]08/04/2024 21:43:32 - INFO - __main__ -   Step: 5131, LR: 5.641856562659598e-08, Loss: 0.08595231175422668
2024-08-05T04:43:40.871487346Z 
 90%|████████▉ | 5132/5712 [12:05:32<1:20:16,  8.30s/it]08/04/2024 21:43:40 - INFO - __main__ -   Step: 5132, LR: 5.632128699627909e-08, Loss: 0.06326571106910706
2024-08-05T04:43:49.482291335Z 
 90%|████████▉ | 5133/5712 [12:05:40<1:21:01,  8.40s/it]08/04/2024 21:43:49 - INFO - __main__ -   Step: 5133, LR: 5.62240083659622e-08, Loss: 0.06032866984605789
2024-08-05T04:43:57.440966339Z 
 90%|████████▉ | 5134/5712 [12:05:48<1:19:36,  8.26s/it]08/04/2024 21:43:57 - INFO - __main__ -   Step: 5134, LR: 5.612672973564532e-08, Loss: 0.0563247948884964
2024-08-05T04:44:06.975186839Z 
 90%|████████▉ | 5135/5712 [12:05:58<1:23:08,  8.65s/it]08/04/2024 21:44:06 - INFO - __main__ -   Step: 5135, LR: 5.6029451105328434e-08, Loss: 0.06577684730291367
2024-08-05T04:44:16.033950634Z 
 90%|████████▉ | 5136/5712 [12:06:07<1:24:11,  8.77s/it]08/04/2024 21:44:16 - INFO - __main__ -   Step: 5136, LR: 5.593217247501155e-08, Loss: 0.04563485085964203
2024-08-05T04:44:24.059752155Z 
 90%|████████▉ | 5137/5712 [12:06:15<1:21:54,  8.55s/it]08/04/2024 21:44:24 - INFO - __main__ -   Step: 5137, LR: 5.5834893844694665e-08, Loss: 0.0349707156419754
2024-08-05T04:44:32.918018750Z 
 90%|████████▉ | 5138/5712 [12:06:24<1:22:39,  8.64s/it]08/04/2024 21:44:32 - INFO - __main__ -   Step: 5138, LR: 5.5737615214377784e-08, Loss: 0.07373273372650146
2024-08-05T04:44:42.241251926Z 
 90%|████████▉ | 5139/5712 [12:06:33<1:24:27,  8.84s/it]08/04/2024 21:44:42 - INFO - __main__ -   Step: 5139, LR: 5.564033658406089e-08, Loss: 0.0636383444070816
2024-08-05T04:44:50.209025532Z 
 90%|████████▉ | 5140/5712 [12:06:41<1:21:48,  8.58s/it]08/04/2024 21:44:50 - INFO - __main__ -   Step: 5140, LR: 5.554305795374401e-08, Loss: 0.06073082610964775
2024-08-05T04:44:58.417010751Z 
 90%|█████████ | 5141/5712 [12:06:49<1:20:36,  8.47s/it]08/04/2024 21:44:58 - INFO - __main__ -   Step: 5141, LR: 5.544577932342712e-08, Loss: 0.09744603931903839
2024-08-05T04:45:06.431648145Z 
 90%|█████████ | 5142/5712 [12:06:57<1:19:09,  8.33s/it]08/04/2024 21:45:06 - INFO - __main__ -   Step: 5142, LR: 5.5348500693110234e-08, Loss: 0.05472399294376373
2024-08-05T04:45:15.199400220Z 
 90%|█████████ | 5143/5712 [12:07:06<1:20:15,  8.46s/it]08/04/2024 21:45:15 - INFO - __main__ -   Step: 5143, LR: 5.525122206279335e-08, Loss: 0.09980704635381699
2024-08-05T04:45:23.793783215Z 
 90%|█████████ | 5144/5712 [12:07:14<1:20:29,  8.50s/it]08/04/2024 21:45:23 - INFO - __main__ -   Step: 5144, LR: 5.5153943432476465e-08, Loss: 0.029144512489438057
2024-08-05T04:45:32.779297646Z 
 90%|█████████ | 5145/5712 [12:07:23<1:21:43,  8.65s/it]08/04/2024 21:45:32 - INFO - __main__ -   Step: 5145, LR: 5.5056664802159584e-08, Loss: 0.029664622619748116
2024-08-05T04:45:41.674764229Z 
 90%|█████████ | 5146/5712 [12:07:32<1:22:16,  8.72s/it]08/04/2024 21:45:41 - INFO - __main__ -   Step: 5146, LR: 5.4959386171842696e-08, Loss: 0.05698680505156517
2024-08-05T04:45:49.822444436Z 
 90%|█████████ | 5147/5712 [12:07:40<1:20:30,  8.55s/it]08/04/2024 21:45:49 - INFO - __main__ -   Step: 5147, LR: 5.4862107541525815e-08, Loss: 0.044814541935920715
2024-08-05T04:45:58.022974050Z 
 90%|█████████ | 5148/5712 [12:07:49<1:19:22,  8.44s/it]08/04/2024 21:45:58 - INFO - __main__ -   Step: 5148, LR: 5.476482891120893e-08, Loss: 0.04927276819944382
2024-08-05T04:46:06.040782921Z 
 90%|█████████ | 5149/5712 [12:07:57<1:18:02,  8.32s/it]08/04/2024 21:46:06 - INFO - __main__ -   Step: 5149, LR: 5.4667550280892046e-08, Loss: 0.025747744366526604
2024-08-05T04:46:14.321159299Z 
 90%|█████████ | 5150/5712 [12:08:05<1:17:47,  8.31s/it]08/04/2024 21:46:14 - INFO - __main__ -   Step: 5150, LR: 5.457027165057516e-08, Loss: 0.05322328582406044
2024-08-05T04:46:22.834889676Z 
 90%|█████████ | 5151/5712 [12:08:13<1:18:14,  8.37s/it]08/04/2024 21:46:22 - INFO - __main__ -   Step: 5151, LR: 5.447299302025827e-08, Loss: 0.08034007251262665
2024-08-05T04:46:31.691277314Z 
 90%|█████████ | 5152/5712 [12:08:22<1:19:28,  8.51s/it]08/04/2024 21:46:31 - INFO - __main__ -   Step: 5152, LR: 5.437571438994139e-08, Loss: 0.09905692934989929
2024-08-05T04:46:40.586610828Z 
 90%|█████████ | 5153/5712 [12:08:31<1:20:23,  8.63s/it]08/04/2024 21:46:40 - INFO - __main__ -   Step: 5153, LR: 5.42784357596245e-08, Loss: 0.0912921130657196
2024-08-05T04:46:48.779046756Z 
 90%|█████████ | 5154/5712 [12:08:39<1:19:01,  8.50s/it]08/04/2024 21:46:48 - INFO - __main__ -   Step: 5154, LR: 5.418115712930762e-08, Loss: 0.06932766735553741
2024-08-05T04:46:57.325042090Z 
 90%|█████████ | 5155/5712 [12:08:48<1:19:01,  8.51s/it]08/04/2024 21:46:57 - INFO - __main__ -   Step: 5155, LR: 5.408387849899073e-08, Loss: 0.05007370561361313
2024-08-05T04:47:06.117185836Z 
 90%|█████████ | 5156/5712 [12:08:57<1:19:39,  8.60s/it]08/04/2024 21:47:06 - INFO - __main__ -   Step: 5156, LR: 5.398659986867385e-08, Loss: 0.06591011583805084
2024-08-05T04:47:14.056506402Z 
 90%|█████████ | 5157/5712 [12:09:05<1:17:41,  8.40s/it]08/04/2024 21:47:14 - INFO - __main__ -   Step: 5157, LR: 5.388932123835696e-08, Loss: 0.04027394950389862
2024-08-05T04:47:22.016967386Z 
 90%|█████████ | 5158/5712 [12:09:13<1:16:20,  8.27s/it]08/04/2024 21:47:22 - INFO - __main__ -   Step: 5158, LR: 5.3792042608040076e-08, Loss: 0.15793585777282715
2024-08-05T04:47:30.680411584Z 
 90%|█████████ | 5159/5712 [12:09:21<1:17:17,  8.39s/it]08/04/2024 21:47:30 - INFO - __main__ -   Step: 5159, LR: 5.369476397772319e-08, Loss: 0.08789479732513428
2024-08-05T04:47:38.980907715Z 
 90%|█████████ | 5160/5712 [12:09:30<1:16:55,  8.36s/it]08/04/2024 21:47:38 - INFO - __main__ -   Step: 5160, LR: 5.35974853474063e-08, Loss: 0.08451499789953232
2024-08-05T04:47:47.496544073Z 
 90%|█████████ | 5161/5712 [12:09:38<1:17:12,  8.41s/it]08/04/2024 21:47:47 - INFO - __main__ -   Step: 5161, LR: 5.350020671708942e-08, Loss: 0.03902188688516617
2024-08-05T04:47:56.375695620Z 
 90%|█████████ | 5162/5712 [12:09:47<1:18:21,  8.55s/it]08/04/2024 21:47:56 - INFO - __main__ -   Step: 5162, LR: 5.340292808677253e-08, Loss: 0.09102937579154968
2024-08-05T04:48:04.809631374Z 
 90%|█████████ | 5163/5712 [12:09:55<1:17:54,  8.51s/it]08/04/2024 21:48:04 - INFO - __main__ -   Step: 5163, LR: 5.330564945645565e-08, Loss: 0.07494618743658066
2024-08-05T04:48:13.184159257Z 
 90%|█████████ | 5164/5712 [12:10:04<1:17:22,  8.47s/it]08/04/2024 21:48:13 - INFO - __main__ -   Step: 5164, LR: 5.320837082613876e-08, Loss: 0.05510677397251129
2024-08-05T04:48:21.350169276Z 
 90%|█████████ | 5165/5712 [12:10:12<1:16:24,  8.38s/it]08/04/2024 21:48:21 - INFO - __main__ -   Step: 5165, LR: 5.311109219582188e-08, Loss: 0.07974551618099213
2024-08-05T04:48:29.277270617Z 
 90%|█████████ | 5166/5712 [12:10:20<1:15:01,  8.24s/it]08/04/2024 21:48:29 - INFO - __main__ -   Step: 5166, LR: 5.3013813565504994e-08, Loss: 0.07083764672279358
2024-08-05T04:48:37.515799357Z 
 90%|█████████ | 5167/5712 [12:10:28<1:14:52,  8.24s/it]08/04/2024 21:48:37 - INFO - __main__ -   Step: 5167, LR: 5.2916534935188113e-08, Loss: 0.091251902282238
2024-08-05T04:48:45.910342611Z 
 90%|█████████ | 5168/5712 [12:10:37<1:15:08,  8.29s/it]08/04/2024 21:48:45 - INFO - __main__ -   Step: 5168, LR: 5.2819256304871226e-08, Loss: 0.0579942986369133
2024-08-05T04:48:54.824163358Z 
 90%|█████████ | 5169/5712 [12:10:45<1:16:42,  8.48s/it]08/04/2024 21:48:54 - INFO - __main__ -   Step: 5169, LR: 5.272197767455434e-08, Loss: 0.08959698677062988
2024-08-05T04:49:03.234838557Z 
 91%|█████████ | 5170/5712 [12:10:54<1:16:23,  8.46s/it]08/04/2024 21:49:03 - INFO - __main__ -   Step: 5170, LR: 5.262469904423746e-08, Loss: 0.07320652902126312
2024-08-05T04:49:11.732315100Z 
 91%|█████████ | 5171/5712 [12:11:02<1:16:21,  8.47s/it]08/04/2024 21:49:11 - INFO - __main__ -   Step: 5171, LR: 5.252742041392057e-08, Loss: 0.06436607241630554
2024-08-05T04:49:19.905012315Z 
 91%|█████████ | 5172/5712 [12:11:11<1:15:25,  8.38s/it]08/04/2024 21:49:19 - INFO - __main__ -   Step: 5172, LR: 5.243014178360369e-08, Loss: 0.04208870604634285
2024-08-05T04:49:28.814147693Z 
 91%|█████████ | 5173/5712 [12:11:19<1:16:42,  8.54s/it]08/04/2024 21:49:28 - INFO - __main__ -   Step: 5173, LR: 5.23328631532868e-08, Loss: 0.09212030470371246
2024-08-05T04:49:36.729739299Z 
 91%|█████████ | 5174/5712 [12:11:27<1:14:53,  8.35s/it]08/04/2024 21:49:36 - INFO - __main__ -   Step: 5174, LR: 5.223558452296992e-08, Loss: 0.13525621592998505
2024-08-05T04:49:44.978403196Z 
 91%|█████████ | 5175/5712 [12:11:36<1:14:28,  8.32s/it]08/04/2024 21:49:44 - INFO - __main__ -   Step: 5175, LR: 5.213830589265303e-08, Loss: 0.057339318096637726
2024-08-05T04:49:53.705465876Z 
 91%|█████████ | 5176/5712 [12:11:44<1:15:25,  8.44s/it]08/04/2024 21:49:53 - INFO - __main__ -   Step: 5176, LR: 5.204102726233615e-08, Loss: 0.08739406615495682
2024-08-05T04:50:02.066718201Z 
 91%|█████████ | 5177/5712 [12:11:53<1:15:03,  8.42s/it]08/04/2024 21:50:02 - INFO - __main__ -   Step: 5177, LR: 5.1943748632019256e-08, Loss: 0.06570088863372803
2024-08-05T04:50:10.771640281Z 
 91%|█████████ | 5178/5712 [12:12:01<1:15:41,  8.50s/it]08/04/2024 21:50:10 - INFO - __main__ -   Step: 5178, LR: 5.184647000170237e-08, Loss: 0.0461483895778656
2024-08-05T04:50:19.453551940Z 
 91%|█████████ | 5179/5712 [12:12:10<1:16:01,  8.56s/it]08/04/2024 21:50:19 - INFO - __main__ -   Step: 5179, LR: 5.174919137138549e-08, Loss: 0.05786708742380142
2024-08-05T04:50:27.911370035Z 
 91%|█████████ | 5180/5712 [12:12:19<1:15:36,  8.53s/it]08/04/2024 21:50:27 - INFO - __main__ -   Step: 5180, LR: 5.16519127410686e-08, Loss: 0.05242779850959778
2024-08-05T04:50:36.533688754Z 
 91%|█████████ | 5181/5712 [12:12:27<1:15:43,  8.56s/it]08/04/2024 21:50:36 - INFO - __main__ -   Step: 5181, LR: 5.155463411075172e-08, Loss: 0.08684448897838593
2024-08-05T04:50:44.734285831Z 
 91%|█████████ | 5182/5712 [12:12:35<1:14:37,  8.45s/it]08/04/2024 21:50:44 - INFO - __main__ -   Step: 5182, LR: 5.145735548043483e-08, Loss: 0.07477013766765594
2024-08-05T04:50:53.481784711Z 
 91%|█████████ | 5183/5712 [12:12:44<1:15:17,  8.54s/it]08/04/2024 21:50:53 - INFO - __main__ -   Step: 5183, LR: 5.136007685011795e-08, Loss: 0.08767752349376678
2024-08-05T04:51:01.855246628Z 
 91%|█████████ | 5184/5712 [12:12:53<1:14:42,  8.49s/it]08/04/2024 21:51:01 - INFO - __main__ -   Step: 5184, LR: 5.126279821980106e-08, Loss: 0.0977756679058075
2024-08-05T04:51:10.745763244Z 
 91%|█████████ | 5185/5712 [12:13:01<1:15:37,  8.61s/it]08/04/2024 21:51:10 - INFO - __main__ -   Step: 5185, LR: 5.116551958948418e-08, Loss: 0.1410103440284729
2024-08-05T04:51:19.281678739Z 
 91%|█████████ | 5186/5712 [12:13:10<1:15:17,  8.59s/it]08/04/2024 21:51:19 - INFO - __main__ -   Step: 5186, LR: 5.106824095916729e-08, Loss: 0.041677847504615784
2024-08-05T04:51:27.542587288Z 
 91%|█████████ | 5187/5712 [12:13:18<1:14:16,  8.49s/it]08/04/2024 21:51:27 - INFO - __main__ -   Step: 5187, LR: 5.0970962328850405e-08, Loss: 0.1284744292497635
2024-08-05T04:51:35.537803599Z 
 91%|█████████ | 5188/5712 [12:13:26<1:12:50,  8.34s/it]08/04/2024 21:51:35 - INFO - __main__ -   Step: 5188, LR: 5.0873683698533524e-08, Loss: 0.051781438291072845
2024-08-05T04:51:44.093595931Z 
 91%|█████████ | 5189/5712 [12:13:35<1:13:15,  8.41s/it]08/04/2024 21:51:44 - INFO - __main__ -   Step: 5189, LR: 5.0776405068216636e-08, Loss: 0.10636238753795624
2024-08-05T04:51:52.890207001Z 
 91%|█████████ | 5190/5712 [12:13:44<1:14:08,  8.52s/it]08/04/2024 21:51:52 - INFO - __main__ -   Step: 5190, LR: 5.0679126437899755e-08, Loss: 0.07387566566467285
2024-08-05T04:52:01.081371391Z 
 91%|█████████ | 5191/5712 [12:13:52<1:13:08,  8.42s/it]08/04/2024 21:52:01 - INFO - __main__ -   Step: 5191, LR: 5.058184780758287e-08, Loss: 0.0634821280837059
2024-08-05T04:52:10.329789795Z 
 91%|█████████ | 5192/5712 [12:14:01<1:15:08,  8.67s/it]08/04/2024 21:52:10 - INFO - __main__ -   Step: 5192, LR: 5.0484569177265987e-08, Loss: 0.06705328822135925
2024-08-05T04:52:18.606547371Z 
 91%|█████████ | 5193/5712 [12:14:09<1:13:58,  8.55s/it]08/04/2024 21:52:18 - INFO - __main__ -   Step: 5193, LR: 5.03872905469491e-08, Loss: 0.05678177997469902
2024-08-05T04:52:26.823839498Z 
 91%|█████████ | 5194/5712 [12:14:17<1:12:58,  8.45s/it]08/04/2024 21:52:26 - INFO - __main__ -   Step: 5194, LR: 5.029001191663222e-08, Loss: 0.03343846648931503
2024-08-05T04:52:35.723347662Z 
 91%|█████████ | 5195/5712 [12:14:26<1:13:59,  8.59s/it]08/04/2024 21:52:35 - INFO - __main__ -   Step: 5195, LR: 5.0192733286315323e-08, Loss: 0.06472287327051163
2024-08-05T04:52:44.132000893Z 
 91%|█████████ | 5196/5712 [12:14:35<1:13:22,  8.53s/it]08/04/2024 21:52:44 - INFO - __main__ -   Step: 5196, LR: 5.0095454655998436e-08, Loss: 0.061918217688798904
2024-08-05T04:52:52.535291040Z 
 91%|█████████ | 5197/5712 [12:14:43<1:12:54,  8.49s/it]08/04/2024 21:52:52 - INFO - __main__ -   Step: 5197, LR: 4.9998176025681555e-08, Loss: 0.0774005800485611
2024-08-05T04:53:00.736868934Z 
 91%|█████████ | 5198/5712 [12:14:51<1:12:00,  8.41s/it]08/04/2024 21:53:00 - INFO - __main__ -   Step: 5198, LR: 4.990089739536467e-08, Loss: 0.05644960701465607
2024-08-05T04:53:09.041688693Z 
 91%|█████████ | 5199/5712 [12:15:00<1:11:36,  8.38s/it]08/04/2024 21:53:09 - INFO - __main__ -   Step: 5199, LR: 4.9803618765047786e-08, Loss: 0.07830803096294403
2024-08-05T04:53:17.547245279Z 
 91%|█████████ | 5200/5712 [12:15:08<1:11:48,  8.41s/it]08/04/2024 21:53:17 - INFO - __main__ -   Step: 5200, LR: 4.97063401347309e-08, Loss: 0.09265559911727905
2024-08-05T04:53:26.826977521Z 
 91%|█████████ | 5201/5712 [12:15:17<1:13:52,  8.67s/it]08/04/2024 21:53:26 - INFO - __main__ -   Step: 5201, LR: 4.960906150441402e-08, Loss: 0.0724090039730072
2024-08-05T04:53:35.222149453Z 
 91%|█████████ | 5202/5712 [12:15:26<1:13:01,  8.59s/it]08/04/2024 21:53:35 - INFO - __main__ -   Step: 5202, LR: 4.951178287409713e-08, Loss: 0.055411167442798615
2024-08-05T04:53:44.004328693Z 
 91%|█████████ | 5203/5712 [12:15:35<1:13:21,  8.65s/it]08/04/2024 21:53:44 - INFO - __main__ -   Step: 5203, LR: 4.941450424378025e-08, Loss: 0.05017304793000221
2024-08-05T04:53:52.728454317Z 
 91%|█████████ | 5204/5712 [12:15:43<1:13:24,  8.67s/it]08/04/2024 21:53:52 - INFO - __main__ -   Step: 5204, LR: 4.931722561346336e-08, Loss: 0.07373137772083282
2024-08-05T04:54:01.016893976Z 
 91%|█████████ | 5205/5712 [12:15:52<1:12:17,  8.56s/it]08/04/2024 21:54:01 - INFO - __main__ -   Step: 5205, LR: 4.921994698314647e-08, Loss: 0.07319636642932892
2024-08-05T04:54:09.818158708Z 
 91%|█████████ | 5206/5712 [12:16:00<1:12:46,  8.63s/it]08/04/2024 21:54:09 - INFO - __main__ -   Step: 5206, LR: 4.912266835282959e-08, Loss: 0.055597275495529175
2024-08-05T04:54:18.685322894Z 
 91%|█████████ | 5207/5712 [12:16:09<1:13:13,  8.70s/it]08/04/2024 21:54:18 - INFO - __main__ -   Step: 5207, LR: 4.9025389722512704e-08, Loss: 0.0739993080496788
2024-08-05T04:54:26.758771999Z 
 91%|█████████ | 5208/5712 [12:16:17<1:11:30,  8.51s/it]08/04/2024 21:54:26 - INFO - __main__ -   Step: 5208, LR: 4.892811109219582e-08, Loss: 0.054486580193042755
2024-08-05T04:54:35.221502515Z 
 91%|█████████ | 5209/5712 [12:16:26<1:11:14,  8.50s/it]08/04/2024 21:54:35 - INFO - __main__ -   Step: 5209, LR: 4.8830832461878935e-08, Loss: 0.043015483766794205
2024-08-05T04:54:43.947465587Z 
 91%|█████████ | 5210/5712 [12:16:35<1:11:40,  8.57s/it]08/04/2024 21:54:43 - INFO - __main__ -   Step: 5210, LR: 4.8733553831562054e-08, Loss: 0.05957132950425148
2024-08-05T04:54:52.240646214Z 
 91%|█████████ | 5211/5712 [12:16:43<1:10:50,  8.48s/it]08/04/2024 21:54:52 - INFO - __main__ -   Step: 5211, LR: 4.8636275201245166e-08, Loss: 0.07758674770593643
2024-08-05T04:55:00.892582242Z 
 91%|█████████ | 5212/5712 [12:16:52<1:11:07,  8.53s/it]08/04/2024 21:55:00 - INFO - __main__ -   Step: 5212, LR: 4.8538996570928285e-08, Loss: 0.10163120180368423
2024-08-05T04:55:09.149955206Z 
 91%|█████████▏| 5213/5712 [12:17:00<1:10:17,  8.45s/it]08/04/2024 21:55:09 - INFO - __main__ -   Step: 5213, LR: 4.84417179406114e-08, Loss: 0.09824854135513306
2024-08-05T04:55:17.945977490Z 
 91%|█████████▏| 5214/5712 [12:17:09<1:11:00,  8.55s/it]08/04/2024 21:55:17 - INFO - __main__ -   Step: 5214, LR: 4.83444393102945e-08, Loss: 0.0883321762084961
2024-08-05T04:55:25.969959180Z 
 91%|█████████▏| 5215/5712 [12:17:17<1:09:32,  8.40s/it]08/04/2024 21:55:25 - INFO - __main__ -   Step: 5215, LR: 4.824716067997762e-08, Loss: 0.037788260728120804
2024-08-05T04:55:34.546113376Z 
 91%|█████████▏| 5216/5712 [12:17:25<1:09:51,  8.45s/it]08/04/2024 21:55:34 - INFO - __main__ -   Step: 5216, LR: 4.8149882049660734e-08, Loss: 0.052278004586696625
2024-08-05T04:55:42.998316863Z 
 91%|█████████▏| 5217/5712 [12:17:34<1:09:42,  8.45s/it]08/04/2024 21:55:42 - INFO - __main__ -   Step: 5217, LR: 4.805260341934385e-08, Loss: 0.17349278926849365
2024-08-05T04:55:51.870793535Z 
 91%|█████████▏| 5218/5712 [12:17:43<1:10:36,  8.58s/it]08/04/2024 21:55:51 - INFO - __main__ -   Step: 5218, LR: 4.7955324789026965e-08, Loss: 0.08237698674201965
2024-08-05T04:56:00.275714038Z 
 91%|█████████▏| 5219/5712 [12:17:51<1:10:03,  8.53s/it]08/04/2024 21:56:00 - INFO - __main__ -   Step: 5219, LR: 4.7858046158710084e-08, Loss: 0.10144706815481186
2024-08-05T04:56:09.033303092Z 
 91%|█████████▏| 5220/5712 [12:18:00<1:10:28,  8.60s/it]08/04/2024 21:56:09 - INFO - __main__ -   Step: 5220, LR: 4.7760767528393197e-08, Loss: 0.1866687536239624
2024-08-05T04:56:17.545171456Z 
 91%|█████████▏| 5221/5712 [12:18:08<1:10:07,  8.57s/it]08/04/2024 21:56:17 - INFO - __main__ -   Step: 5221, LR: 4.766348889807631e-08, Loss: 0.06286885589361191
2024-08-05T04:56:25.743995703Z 
 91%|█████████▏| 5222/5712 [12:18:16<1:09:04,  8.46s/it]08/04/2024 21:56:25 - INFO - __main__ -   Step: 5222, LR: 4.756621026775943e-08, Loss: 0.02792475000023842
2024-08-05T04:56:34.035787847Z 
 91%|█████████▏| 5223/5712 [12:18:25<1:08:31,  8.41s/it]08/04/2024 21:56:34 - INFO - __main__ -   Step: 5223, LR: 4.746893163744254e-08, Loss: 0.06769872456789017
2024-08-05T04:56:43.315607549Z 
 91%|█████████▏| 5224/5712 [12:18:34<1:10:30,  8.67s/it]08/04/2024 21:56:43 - INFO - __main__ -   Step: 5224, LR: 4.737165300712566e-08, Loss: 0.03878471255302429
2024-08-05T04:56:51.437497024Z 
 91%|█████████▏| 5225/5712 [12:18:42<1:09:02,  8.51s/it]08/04/2024 21:56:51 - INFO - __main__ -   Step: 5225, LR: 4.727437437680877e-08, Loss: 0.08104052394628525
2024-08-05T04:56:59.860245935Z 
 91%|█████████▏| 5226/5712 [12:18:51<1:08:41,  8.48s/it]08/04/2024 21:56:59 - INFO - __main__ -   Step: 5226, LR: 4.717709574649189e-08, Loss: 0.10850648581981659
2024-08-05T04:57:07.979222425Z 
 92%|█████████▏| 5227/5712 [12:18:59<1:07:40,  8.37s/it]08/04/2024 21:57:07 - INFO - __main__ -   Step: 5227, LR: 4.7079817116175e-08, Loss: 0.08827235549688339
2024-08-05T04:57:16.321733407Z 
 92%|█████████▏| 5228/5712 [12:19:07<1:07:27,  8.36s/it]08/04/2024 21:57:16 - INFO - __main__ -   Step: 5228, LR: 4.698253848585812e-08, Loss: 0.069768026471138
2024-08-05T04:57:24.647241227Z 
 92%|█████████▏| 5229/5712 [12:19:15<1:07:14,  8.35s/it]08/04/2024 21:57:24 - INFO - __main__ -   Step: 5229, LR: 4.6885259855541234e-08, Loss: 0.14463822543621063
2024-08-05T04:57:33.147086239Z 
 92%|█████████▏| 5230/5712 [12:19:24<1:07:26,  8.40s/it]08/04/2024 21:57:33 - INFO - __main__ -   Step: 5230, LR: 4.6787981225224346e-08, Loss: 0.07779932022094727
2024-08-05T04:57:41.634590148Z 
 92%|█████████▏| 5231/5712 [12:19:32<1:07:31,  8.42s/it]08/04/2024 21:57:41 - INFO - __main__ -   Step: 5231, LR: 4.6690702594907465e-08, Loss: 0.03938113898038864
2024-08-05T04:57:50.160467014Z 
 92%|█████████▏| 5232/5712 [12:19:41<1:07:38,  8.45s/it]08/04/2024 21:57:50 - INFO - __main__ -   Step: 5232, LR: 4.659342396459058e-08, Loss: 0.08811536431312561
2024-08-05T04:57:58.523226699Z 
 92%|█████████▏| 5233/5712 [12:19:49<1:07:16,  8.43s/it]08/04/2024 21:57:58 - INFO - __main__ -   Step: 5233, LR: 4.649614533427369e-08, Loss: 0.0618986114859581
2024-08-05T04:58:07.122271525Z 
 92%|█████████▏| 5234/5712 [12:19:58<1:07:32,  8.48s/it]08/04/2024 21:58:07 - INFO - __main__ -   Step: 5234, LR: 4.63988667039568e-08, Loss: 0.06832846254110336
2024-08-05T04:58:15.783528837Z 
 92%|█████████▏| 5235/5712 [12:20:06<1:07:50,  8.53s/it]08/04/2024 21:58:15 - INFO - __main__ -   Step: 5235, LR: 4.630158807363992e-08, Loss: 0.08234436810016632
2024-08-05T04:58:24.662127624Z 
 92%|█████████▏| 5236/5712 [12:20:15<1:08:31,  8.64s/it]08/04/2024 21:58:24 - INFO - __main__ -   Step: 5236, LR: 4.620430944332303e-08, Loss: 0.06104373559355736
2024-08-05T04:58:33.017794168Z 
 92%|█████████▏| 5237/5712 [12:20:24<1:07:42,  8.55s/it]08/04/2024 21:58:33 - INFO - __main__ -   Step: 5237, LR: 4.610703081300615e-08, Loss: 0.10737992823123932
2024-08-05T04:58:41.369329715Z 
 92%|█████████▏| 5238/5712 [12:20:32<1:07:05,  8.49s/it]08/04/2024 21:58:41 - INFO - __main__ -   Step: 5238, LR: 4.6009752182689264e-08, Loss: 0.08750784397125244
2024-08-05T04:58:49.829606588Z 
 92%|█████████▏| 5239/5712 [12:20:40<1:06:52,  8.48s/it]08/04/2024 21:58:49 - INFO - __main__ -   Step: 5239, LR: 4.5912473552372376e-08, Loss: 0.07554805278778076
2024-08-05T04:58:58.237175371Z 
 92%|█████████▏| 5240/5712 [12:20:49<1:06:33,  8.46s/it]08/04/2024 21:58:58 - INFO - __main__ -   Step: 5240, LR: 4.5815194922055495e-08, Loss: 0.04138056933879852
2024-08-05T04:59:07.945544806Z 
 92%|█████████▏| 5241/5712 [12:20:59<1:09:20,  8.83s/it]08/04/2024 21:59:07 - INFO - __main__ -   Step: 5241, LR: 4.571791629173861e-08, Loss: 0.05601387098431587
2024-08-05T04:59:16.627655211Z 
 92%|█████████▏| 5242/5712 [12:21:07<1:08:50,  8.79s/it]08/04/2024 21:59:16 - INFO - __main__ -   Step: 5242, LR: 4.5620637661421726e-08, Loss: 0.03402059152722359
2024-08-05T04:59:24.994774888Z 
 92%|█████████▏| 5243/5712 [12:21:16<1:07:42,  8.66s/it]08/04/2024 21:59:24 - INFO - __main__ -   Step: 5243, LR: 4.552335903110484e-08, Loss: 0.10998201370239258
2024-08-05T04:59:33.719488010Z 
 92%|█████████▏| 5244/5712 [12:21:24<1:07:42,  8.68s/it]08/04/2024 21:59:33 - INFO - __main__ -   Step: 5244, LR: 4.542608040078796e-08, Loss: 0.150431826710701
2024-08-05T04:59:41.861332837Z 
 92%|█████████▏| 5245/5712 [12:21:33<1:06:18,  8.52s/it]08/04/2024 21:59:41 - INFO - __main__ -   Step: 5245, LR: 4.532880177047107e-08, Loss: 0.06066380441188812
2024-08-05T04:59:50.334011492Z 
 92%|█████████▏| 5246/5712 [12:21:41<1:06:03,  8.51s/it]08/04/2024 21:59:50 - INFO - __main__ -   Step: 5246, LR: 4.523152314015419e-08, Loss: 0.10972929000854492
2024-08-05T04:59:58.643627811Z 
 92%|█████████▏| 5247/5712 [12:21:49<1:05:27,  8.45s/it]08/04/2024 21:59:58 - INFO - __main__ -   Step: 5247, LR: 4.51342445098373e-08, Loss: 0.10071452707052231
2024-08-05T05:00:06.851565090Z 
 92%|█████████▏| 5248/5712 [12:21:57<1:04:46,  8.38s/it]08/04/2024 22:00:06 - INFO - __main__ -   Step: 5248, LR: 4.503696587952041e-08, Loss: 0.04795340076088905
2024-08-05T05:00:15.255299411Z 
 92%|█████████▏| 5249/5712 [12:22:06<1:04:41,  8.38s/it]08/04/2024 22:00:15 - INFO - __main__ -   Step: 5249, LR: 4.493968724920353e-08, Loss: 0.1255466341972351
2024-08-05T05:00:23.552369049Z 
 92%|█████████▏| 5250/5712 [12:22:14<1:04:21,  8.36s/it]08/04/2024 22:00:23 - INFO - __main__ -   Step: 5250, LR: 4.4842408618886644e-08, Loss: 0.032363809645175934
2024-08-05T05:00:31.867440053Z 
 92%|█████████▏| 5251/5712 [12:22:23<1:04:07,  8.34s/it]08/04/2024 22:00:31 - INFO - __main__ -   Step: 5251, LR: 4.474512998856976e-08, Loss: 0.016605466604232788
2024-08-05T05:00:40.386560497Z 
 92%|█████████▏| 5252/5712 [12:22:31<1:04:22,  8.40s/it]08/04/2024 22:00:40 - INFO - __main__ -   Step: 5252, LR: 4.464785135825287e-08, Loss: 0.11358237266540527
2024-08-05T05:00:49.098961662Z 
 92%|█████████▏| 5253/5712 [12:22:40<1:04:57,  8.49s/it]08/04/2024 22:00:49 - INFO - __main__ -   Step: 5253, LR: 4.455057272793599e-08, Loss: 0.05378712713718414
2024-08-05T05:00:57.763825239Z 
 92%|█████████▏| 5254/5712 [12:22:48<1:05:13,  8.54s/it]08/04/2024 22:00:57 - INFO - __main__ -   Step: 5254, LR: 4.44532940976191e-08, Loss: 0.13670003414154053
2024-08-05T05:01:06.608291150Z 
 92%|█████████▏| 5255/5712 [12:22:57<1:05:45,  8.63s/it]08/04/2024 22:01:06 - INFO - __main__ -   Step: 5255, LR: 4.435601546730222e-08, Loss: 0.09453223645687103
2024-08-05T05:01:14.920116497Z 
 92%|█████████▏| 5256/5712 [12:23:06<1:04:53,  8.54s/it]08/04/2024 22:01:14 - INFO - __main__ -   Step: 5256, LR: 4.425873683698533e-08, Loss: 0.06683284044265747
2024-08-05T05:01:23.356430492Z 
 92%|█████████▏| 5257/5712 [12:23:14<1:04:30,  8.51s/it]08/04/2024 22:01:23 - INFO - __main__ -   Step: 5257, LR: 4.4161458206668444e-08, Loss: 0.08468817919492722
2024-08-05T05:01:32.235178204Z 
 92%|█████████▏| 5258/5712 [12:23:23<1:05:12,  8.62s/it]08/04/2024 22:01:32 - INFO - __main__ -   Step: 5258, LR: 4.406417957635156e-08, Loss: 0.10785141587257385
2024-08-05T05:01:40.490505488Z 
 92%|█████████▏| 5259/5712 [12:23:31<1:04:14,  8.51s/it]08/04/2024 22:01:40 - INFO - __main__ -   Step: 5259, LR: 4.3966900946034675e-08, Loss: 0.07379741966724396
2024-08-05T05:01:48.741130974Z 
 92%|█████████▏| 5260/5712 [12:23:39<1:03:31,  8.43s/it]08/04/2024 22:01:48 - INFO - __main__ -   Step: 5260, LR: 4.3869622315717794e-08, Loss: 0.061683639883995056
2024-08-05T05:01:57.316769211Z 
 92%|█████████▏| 5261/5712 [12:23:48<1:03:42,  8.48s/it]08/04/2024 22:01:57 - INFO - __main__ -   Step: 5261, LR: 4.3772343685400906e-08, Loss: 0.04190444201231003
2024-08-05T05:02:05.444876481Z 
 92%|█████████▏| 5262/5712 [12:23:56<1:02:46,  8.37s/it]08/04/2024 22:02:05 - INFO - __main__ -   Step: 5262, LR: 4.3675065055084025e-08, Loss: 0.06082737818360329
2024-08-05T05:02:13.790588015Z 
 92%|█████████▏| 5263/5712 [12:24:04<1:02:35,  8.36s/it]08/04/2024 22:02:13 - INFO - __main__ -   Step: 5263, LR: 4.357778642476714e-08, Loss: 0.0898878201842308
2024-08-05T05:02:22.734424436Z 
 92%|█████████▏| 5264/5712 [12:24:13<1:03:44,  8.54s/it]08/04/2024 22:02:22 - INFO - __main__ -   Step: 5264, LR: 4.3480507794450256e-08, Loss: 0.07582421600818634
2024-08-05T05:02:31.180891087Z 
 92%|█████████▏| 5265/5712 [12:24:22<1:03:24,  8.51s/it]08/04/2024 22:02:31 - INFO - __main__ -   Step: 5265, LR: 4.338322916413337e-08, Loss: 0.0664871484041214
2024-08-05T05:02:39.369876241Z 
 92%|█████████▏| 5266/5712 [12:24:30<1:02:32,  8.41s/it]08/04/2024 22:02:39 - INFO - __main__ -   Step: 5266, LR: 4.328595053381648e-08, Loss: 0.05811253562569618
2024-08-05T05:02:47.670949922Z 
 92%|█████████▏| 5267/5712 [12:24:38<1:02:09,  8.38s/it]08/04/2024 22:02:47 - INFO - __main__ -   Step: 5267, LR: 4.31886719034996e-08, Loss: 0.07540541887283325
2024-08-05T05:02:55.883201022Z 
 92%|█████████▏| 5268/5712 [12:24:47<1:01:38,  8.33s/it]08/04/2024 22:02:55 - INFO - __main__ -   Step: 5268, LR: 4.309139327318271e-08, Loss: 0.06813414394855499
2024-08-05T05:03:05.173882927Z 
 92%|█████████▏| 5269/5712 [12:24:56<1:03:37,  8.62s/it]08/04/2024 22:03:05 - INFO - __main__ -   Step: 5269, LR: 4.299411464286583e-08, Loss: 0.06987522542476654
2024-08-05T05:03:13.001687436Z 
 92%|█████████▏| 5270/5712 [12:25:04<1:01:44,  8.38s/it]08/04/2024 22:03:13 - INFO - __main__ -   Step: 5270, LR: 4.289683601254894e-08, Loss: 0.0536920428276062
2024-08-05T05:03:21.746472303Z 
 92%|█████████▏| 5271/5712 [12:25:12<1:02:24,  8.49s/it]08/04/2024 22:03:21 - INFO - __main__ -   Step: 5271, LR: 4.279955738223206e-08, Loss: 0.09698878228664398
2024-08-05T05:03:30.587399910Z 
 92%|█████████▏| 5272/5712 [12:25:21<1:03:01,  8.60s/it]08/04/2024 22:03:30 - INFO - __main__ -   Step: 5272, LR: 4.270227875191517e-08, Loss: 0.08592117577791214
2024-08-05T05:03:38.895275791Z 
 92%|█████████▏| 5273/5712 [12:25:30<1:02:15,  8.51s/it]08/04/2024 22:03:38 - INFO - __main__ -   Step: 5273, LR: 4.2605000121598286e-08, Loss: 0.10644391179084778
2024-08-05T05:03:47.672104817Z 
 92%|█████████▏| 5274/5712 [12:25:38<1:02:42,  8.59s/it]08/04/2024 22:03:47 - INFO - __main__ -   Step: 5274, LR: 4.25077214912814e-08, Loss: 0.11815306544303894
2024-08-05T05:03:56.273374880Z 
 92%|█████████▏| 5275/5712 [12:25:47<1:02:35,  8.59s/it]08/04/2024 22:03:56 - INFO - __main__ -   Step: 5275, LR: 4.241044286096451e-08, Loss: 0.044276587665081024
2024-08-05T05:04:04.633983340Z 
 92%|█████████▏| 5276/5712 [12:25:55<1:01:56,  8.52s/it]08/04/2024 22:04:04 - INFO - __main__ -   Step: 5276, LR: 4.231316423064763e-08, Loss: 0.06273107975721359
2024-08-05T05:04:12.877690218Z 
 92%|█████████▏| 5277/5712 [12:26:04<1:01:11,  8.44s/it]08/04/2024 22:04:12 - INFO - __main__ -   Step: 5277, LR: 4.221588560033074e-08, Loss: 0.04737738519906998
2024-08-05T05:04:21.201510212Z 
 92%|█████████▏| 5278/5712 [12:26:12<1:00:47,  8.40s/it]08/04/2024 22:04:21 - INFO - __main__ -   Step: 5278, LR: 4.211860697001386e-08, Loss: 0.11899959295988083
2024-08-05T05:04:29.471894523Z 
 92%|█████████▏| 5279/5712 [12:26:20<1:00:21,  8.36s/it]08/04/2024 22:04:29 - INFO - __main__ -   Step: 5279, LR: 4.202132833969697e-08, Loss: 0.026436682790517807
2024-08-05T05:04:37.873585117Z 
 92%|█████████▏| 5280/5712 [12:26:29<1:00:18,  8.38s/it]08/04/2024 22:04:37 - INFO - __main__ -   Step: 5280, LR: 4.192404970938009e-08, Loss: 0.052261121571063995
2024-08-05T05:04:46.140388623Z 
 92%|█████████▏| 5281/5712 [12:26:37<59:55,  8.34s/it]  08/04/2024 22:04:46 - INFO - __main__ -   Step: 5281, LR: 4.1826771079063204e-08, Loss: 0.07699651271104813
2024-08-05T05:04:54.734736996Z 
 92%|█████████▏| 5282/5712 [12:26:45<1:00:19,  8.42s/it]08/04/2024 22:04:54 - INFO - __main__ -   Step: 5282, LR: 4.1729492448746323e-08, Loss: 0.056779757142066956
2024-08-05T05:05:03.429728403Z 
 92%|█████████▏| 5283/5712 [12:26:54<1:00:47,  8.50s/it]08/04/2024 22:05:03 - INFO - __main__ -   Step: 5283, LR: 4.1632213818429436e-08, Loss: 0.06578940898180008
2024-08-05T05:05:11.801428150Z 
 93%|█████████▎| 5284/5712 [12:27:02<1:00:21,  8.46s/it]08/04/2024 22:05:11 - INFO - __main__ -   Step: 5284, LR: 4.153493518811255e-08, Loss: 0.034280236810445786
2024-08-05T05:05:20.512952678Z 
 93%|█████████▎| 5285/5712 [12:27:11<1:00:45,  8.54s/it]08/04/2024 22:05:20 - INFO - __main__ -   Step: 5285, LR: 4.143765655779567e-08, Loss: 0.03614761680364609
2024-08-05T05:05:29.177656745Z 
 93%|█████████▎| 5286/5712 [12:27:20<1:00:53,  8.58s/it]08/04/2024 22:05:29 - INFO - __main__ -   Step: 5286, LR: 4.134037792747878e-08, Loss: 0.10330668836832047
2024-08-05T05:05:37.261611685Z 
 93%|█████████▎| 5287/5712 [12:27:28<59:41,  8.43s/it]  08/04/2024 22:05:37 - INFO - __main__ -   Step: 5287, LR: 4.12430992971619e-08, Loss: 0.09069608896970749
2024-08-05T05:05:46.089453388Z 
 93%|█████████▎| 5288/5712 [12:27:37<1:00:24,  8.55s/it]08/04/2024 22:05:46 - INFO - __main__ -   Step: 5288, LR: 4.114582066684501e-08, Loss: 0.0786701962351799
2024-08-05T05:05:54.891773073Z 
 93%|█████████▎| 5289/5712 [12:27:46<1:00:48,  8.62s/it]08/04/2024 22:05:54 - INFO - __main__ -   Step: 5289, LR: 4.104854203652813e-08, Loss: 0.07514436542987823
2024-08-05T05:06:04.208425184Z 
 93%|█████████▎| 5290/5712 [12:27:55<1:02:07,  8.83s/it]08/04/2024 22:06:04 - INFO - __main__ -   Step: 5290, LR: 4.0951263406211235e-08, Loss: 0.07626738399267197
2024-08-05T05:06:12.958208827Z 
 93%|█████████▎| 5291/5712 [12:28:04<1:01:47,  8.81s/it]08/04/2024 22:06:12 - INFO - __main__ -   Step: 5291, LR: 4.0853984775894354e-08, Loss: 0.0399712473154068
2024-08-05T05:06:22.016741414Z 
 93%|█████████▎| 5292/5712 [12:28:13<1:02:10,  8.88s/it]08/04/2024 22:06:22 - INFO - __main__ -   Step: 5292, LR: 4.0756706145577466e-08, Loss: 0.09730483591556549
2024-08-05T05:06:31.039478574Z 
 93%|█████████▎| 5293/5712 [12:28:22<1:02:19,  8.92s/it]08/04/2024 22:06:31 - INFO - __main__ -   Step: 5293, LR: 4.065942751526058e-08, Loss: 0.05707770213484764
2024-08-05T05:06:39.467421703Z 
 93%|█████████▎| 5294/5712 [12:28:30<1:01:08,  8.78s/it]08/04/2024 22:06:39 - INFO - __main__ -   Step: 5294, LR: 4.05621488849437e-08, Loss: 0.10123991221189499
2024-08-05T05:06:47.647678994Z 
 93%|█████████▎| 5295/5712 [12:28:38<59:44,  8.60s/it]  08/04/2024 22:06:47 - INFO - __main__ -   Step: 5295, LR: 4.046487025462681e-08, Loss: 0.061272356659173965
2024-08-05T05:06:55.797533343Z 
 93%|█████████▎| 5296/5712 [12:28:46<58:40,  8.46s/it]08/04/2024 22:06:55 - INFO - __main__ -   Step: 5296, LR: 4.036759162430993e-08, Loss: 0.14987102150917053
2024-08-05T05:07:04.319191097Z 
 93%|█████████▎| 5297/5712 [12:28:55<58:39,  8.48s/it]08/04/2024 22:07:04 - INFO - __main__ -   Step: 5297, LR: 4.027031299399304e-08, Loss: 0.05511483550071716
2024-08-05T05:07:12.773013015Z 
 93%|█████████▎| 5298/5712 [12:29:03<58:27,  8.47s/it]08/04/2024 22:07:12 - INFO - __main__ -   Step: 5298, LR: 4.017303436367616e-08, Loss: 0.03306470066308975
2024-08-05T05:07:21.158776982Z 
 93%|█████████▎| 5299/5712 [12:29:12<58:08,  8.45s/it]08/04/2024 22:07:21 - INFO - __main__ -   Step: 5299, LR: 4.007575573335927e-08, Loss: 0.12539802491664886
2024-08-05T05:07:29.286337805Z 
 93%|█████████▎| 5300/5712 [12:29:20<57:20,  8.35s/it]08/04/2024 22:07:29 - INFO - __main__ -   Step: 5300, LR: 3.997847710304239e-08, Loss: 0.06967899203300476
2024-08-05T05:07:37.934624689Z 
 93%|█████████▎| 5301/5712 [12:29:29<57:48,  8.44s/it]08/04/2024 22:07:37 - INFO - __main__ -   Step: 5301, LR: 3.98811984727255e-08, Loss: 0.17188678681850433
2024-08-05T05:07:46.440367352Z 
 93%|█████████▎| 5302/5712 [12:29:37<57:48,  8.46s/it]08/04/2024 22:07:46 - INFO - __main__ -   Step: 5302, LR: 3.9783919842408615e-08, Loss: 0.12655219435691833
2024-08-05T05:07:55.465858047Z 
 93%|█████████▎| 5303/5712 [12:29:46<58:49,  8.63s/it]08/04/2024 22:07:55 - INFO - __main__ -   Step: 5303, LR: 3.9686641212091734e-08, Loss: 0.04098412021994591
2024-08-05T05:08:03.609412704Z 
 93%|█████████▎| 5304/5712 [12:29:54<57:41,  8.48s/it]08/04/2024 22:08:03 - INFO - __main__ -   Step: 5304, LR: 3.9589362581774846e-08, Loss: 0.05964178964495659
2024-08-05T05:08:12.117158094Z 
 93%|█████████▎| 5305/5712 [12:30:03<57:35,  8.49s/it]08/04/2024 22:08:12 - INFO - __main__ -   Step: 5305, LR: 3.9492083951457965e-08, Loss: 0.04712978005409241
2024-08-05T05:08:20.578547826Z 
 93%|█████████▎| 5306/5712 [12:30:11<57:23,  8.48s/it]08/04/2024 22:08:20 - INFO - __main__ -   Step: 5306, LR: 3.939480532114108e-08, Loss: 0.13271871209144592
2024-08-05T05:08:28.888145611Z 
 93%|█████████▎| 5307/5712 [12:30:20<56:54,  8.43s/it]08/04/2024 22:08:28 - INFO - __main__ -   Step: 5307, LR: 3.9297526690824197e-08, Loss: 0.044214267283678055
2024-08-05T05:08:37.439756154Z 
 93%|█████████▎| 5308/5712 [12:30:28<57:00,  8.47s/it]08/04/2024 22:08:37 - INFO - __main__ -   Step: 5308, LR: 3.920024806050731e-08, Loss: 0.042390573769807816
2024-08-05T05:08:46.143353364Z 
 93%|█████████▎| 5309/5712 [12:30:37<57:20,  8.54s/it]08/04/2024 22:08:46 - INFO - __main__ -   Step: 5309, LR: 3.910296943019043e-08, Loss: 0.05993553623557091
2024-08-05T05:08:54.561214171Z 
 93%|█████████▎| 5310/5712 [12:30:45<56:57,  8.50s/it]08/04/2024 22:08:54 - INFO - __main__ -   Step: 5310, LR: 3.9005690799873533e-08, Loss: 0.05102718621492386
2024-08-05T05:09:02.767242727Z 
 93%|█████████▎| 5311/5712 [12:30:53<56:13,  8.41s/it]08/04/2024 22:09:02 - INFO - __main__ -   Step: 5311, LR: 3.8908412169556646e-08, Loss: 0.07440635561943054
2024-08-05T05:09:11.364644804Z 
 93%|█████████▎| 5312/5712 [12:31:02<56:27,  8.47s/it]08/04/2024 22:09:11 - INFO - __main__ -   Step: 5312, LR: 3.8811133539239765e-08, Loss: 0.03889595344662666
2024-08-05T05:09:20.230880595Z 
 93%|█████████▎| 5313/5712 [12:31:11<57:06,  8.59s/it]08/04/2024 22:09:20 - INFO - __main__ -   Step: 5313, LR: 3.871385490892288e-08, Loss: 0.06793016195297241
2024-08-05T05:09:28.475903634Z 
 93%|█████████▎| 5314/5712 [12:31:19<56:17,  8.49s/it]08/04/2024 22:09:28 - INFO - __main__ -   Step: 5314, LR: 3.8616576278605996e-08, Loss: 0.08590550720691681
2024-08-05T05:09:36.634197302Z 
 93%|█████████▎| 5315/5712 [12:31:27<55:29,  8.39s/it]08/04/2024 22:09:36 - INFO - __main__ -   Step: 5315, LR: 3.851929764828911e-08, Loss: 0.06421700119972229
2024-08-05T05:09:44.944682243Z 
 93%|█████████▎| 5316/5712 [12:31:36<55:12,  8.36s/it]08/04/2024 22:09:44 - INFO - __main__ -   Step: 5316, LR: 3.842201901797223e-08, Loss: 0.04800108075141907
2024-08-05T05:09:53.212704531Z 
 93%|█████████▎| 5317/5712 [12:31:44<54:52,  8.34s/it]08/04/2024 22:09:53 - INFO - __main__ -   Step: 5317, LR: 3.832474038765534e-08, Loss: 0.10666000843048096
2024-08-05T05:10:01.497886979Z 
 93%|█████████▎| 5318/5712 [12:31:52<54:38,  8.32s/it]08/04/2024 22:10:01 - INFO - __main__ -   Step: 5318, LR: 3.822746175733846e-08, Loss: 0.03946875408291817
2024-08-05T05:10:09.752738912Z 
 93%|█████████▎| 5319/5712 [12:32:00<54:22,  8.30s/it]08/04/2024 22:10:09 - INFO - __main__ -   Step: 5319, LR: 3.813018312702157e-08, Loss: 0.06335227936506271
2024-08-05T05:10:18.679378972Z 
 93%|█████████▎| 5320/5712 [12:32:09<55:27,  8.49s/it]08/04/2024 22:10:18 - INFO - __main__ -   Step: 5320, LR: 3.803290449670468e-08, Loss: 0.046316806226968765
2024-08-05T05:10:27.175829604Z 
 93%|█████████▎| 5321/5712 [12:32:18<55:19,  8.49s/it]08/04/2024 22:10:27 - INFO - __main__ -   Step: 5321, LR: 3.79356258663878e-08, Loss: 0.05712277442216873
2024-08-05T05:10:35.404195744Z 
 93%|█████████▎| 5322/5712 [12:32:26<54:40,  8.41s/it]08/04/2024 22:10:35 - INFO - __main__ -   Step: 5322, LR: 3.7838347236070914e-08, Loss: 0.0560980886220932
2024-08-05T05:10:43.864737605Z 
 93%|█████████▎| 5323/5712 [12:32:35<54:38,  8.43s/it]08/04/2024 22:10:43 - INFO - __main__ -   Step: 5323, LR: 3.774106860575403e-08, Loss: 0.09320810437202454
2024-08-05T05:10:52.051252592Z 
 93%|█████████▎| 5324/5712 [12:32:43<54:01,  8.35s/it]08/04/2024 22:10:52 - INFO - __main__ -   Step: 5324, LR: 3.7643789975437145e-08, Loss: 0.1034291535615921
2024-08-05T05:11:00.332710378Z 
 93%|█████████▎| 5325/5712 [12:32:51<53:44,  8.33s/it]08/04/2024 22:11:00 - INFO - __main__ -   Step: 5325, LR: 3.7546511345120264e-08, Loss: 0.05940266698598862
2024-08-05T05:11:09.307622362Z 
 93%|█████████▎| 5326/5712 [12:33:00<54:50,  8.52s/it]08/04/2024 22:11:09 - INFO - __main__ -   Step: 5326, LR: 3.7449232714803376e-08, Loss: 0.09979216754436493
2024-08-05T05:11:17.853104951Z 
 93%|█████████▎| 5327/5712 [12:33:09<54:44,  8.53s/it]08/04/2024 22:11:17 - INFO - __main__ -   Step: 5327, LR: 3.735195408448649e-08, Loss: 0.05653028190135956
2024-08-05T05:11:25.811703285Z 
 93%|█████████▎| 5328/5712 [12:33:16<53:30,  8.36s/it]08/04/2024 22:11:25 - INFO - __main__ -   Step: 5328, LR: 3.72546754541696e-08, Loss: 0.07324329018592834
2024-08-05T05:11:34.090093824Z 
 93%|█████████▎| 5329/5712 [12:33:25<53:12,  8.34s/it]08/04/2024 22:11:34 - INFO - __main__ -   Step: 5329, LR: 3.715739682385271e-08, Loss: 0.061933260411024094
2024-08-05T05:11:43.107028491Z 
 93%|█████████▎| 5330/5712 [12:33:34<54:22,  8.54s/it]08/04/2024 22:11:43 - INFO - __main__ -   Step: 5330, LR: 3.706011819353583e-08, Loss: 0.0904308557510376
2024-08-05T05:11:51.300999918Z 
 93%|█████████▎| 5331/5712 [12:33:42<53:34,  8.44s/it]08/04/2024 22:11:51 - INFO - __main__ -   Step: 5331, LR: 3.6962839563218944e-08, Loss: 0.1662777066230774
2024-08-05T05:11:59.391093341Z 
 93%|█████████▎| 5332/5712 [12:33:50<52:46,  8.33s/it]08/04/2024 22:11:59 - INFO - __main__ -   Step: 5332, LR: 3.686556093290206e-08, Loss: 0.08405712991952896
2024-08-05T05:12:07.873129023Z 
 93%|█████████▎| 5333/5712 [12:33:59<52:54,  8.38s/it]08/04/2024 22:12:07 - INFO - __main__ -   Step: 5333, LR: 3.6768282302585175e-08, Loss: 0.07479166984558105
2024-08-05T05:12:16.568168256Z 
 93%|█████████▎| 5334/5712 [12:34:07<53:22,  8.47s/it]08/04/2024 22:12:16 - INFO - __main__ -   Step: 5334, LR: 3.6671003672268294e-08, Loss: 0.07247195392847061
2024-08-05T05:12:24.989062107Z 
 93%|█████████▎| 5335/5712 [12:34:16<53:08,  8.46s/it]08/04/2024 22:12:24 - INFO - __main__ -   Step: 5335, LR: 3.6573725041951407e-08, Loss: 0.059744156897068024
2024-08-05T05:12:32.989621141Z 
 93%|█████████▎| 5336/5712 [12:34:24<52:08,  8.32s/it]08/04/2024 22:12:32 - INFO - __main__ -   Step: 5336, LR: 3.647644641163452e-08, Loss: 0.06332431733608246
2024-08-05T05:12:42.148882491Z 
 93%|█████████▎| 5337/5712 [12:34:33<53:34,  8.57s/it]08/04/2024 22:12:42 - INFO - __main__ -   Step: 5337, LR: 3.637916778131764e-08, Loss: 0.13186344504356384
2024-08-05T05:12:50.862693661Z 
 93%|█████████▎| 5338/5712 [12:34:42<53:41,  8.61s/it]08/04/2024 22:12:50 - INFO - __main__ -   Step: 5338, LR: 3.628188915100075e-08, Loss: 0.05829141288995743
2024-08-05T05:13:00.070310076Z 
 93%|█████████▎| 5339/5712 [12:34:51<54:39,  8.79s/it]08/04/2024 22:13:00 - INFO - __main__ -   Step: 5339, LR: 3.618461052068387e-08, Loss: 0.08944344520568848
2024-08-05T05:13:08.737479308Z 
 93%|█████████▎| 5340/5712 [12:34:59<54:16,  8.75s/it]08/04/2024 22:13:08 - INFO - __main__ -   Step: 5340, LR: 3.608733189036698e-08, Loss: 0.06276880204677582
2024-08-05T05:13:16.912228399Z 
 94%|█████████▎| 5341/5712 [12:35:08<53:03,  8.58s/it]08/04/2024 22:13:16 - INFO - __main__ -   Step: 5341, LR: 3.59900532600501e-08, Loss: 0.05353429913520813
2024-08-05T05:13:25.443999567Z 
 94%|█████████▎| 5342/5712 [12:35:16<52:49,  8.57s/it]08/04/2024 22:13:25 - INFO - __main__ -   Step: 5342, LR: 3.589277462973321e-08, Loss: 0.03568950295448303
2024-08-05T05:13:34.315631171Z 
 94%|█████████▎| 5343/5712 [12:35:25<53:14,  8.66s/it]08/04/2024 22:13:34 - INFO - __main__ -   Step: 5343, LR: 3.579549599941633e-08, Loss: 0.06811439245939255
2024-08-05T05:13:42.710298921Z 
 94%|█████████▎| 5344/5712 [12:35:33<52:37,  8.58s/it]08/04/2024 22:13:42 - INFO - __main__ -   Step: 5344, LR: 3.5698217369099444e-08, Loss: 0.1321314573287964
2024-08-05T05:13:50.777465085Z 
 94%|█████████▎| 5345/5712 [12:35:41<51:32,  8.43s/it]08/04/2024 22:13:50 - INFO - __main__ -   Step: 5345, LR: 3.5600938738782556e-08, Loss: 0.06822425127029419
2024-08-05T05:13:59.431149501Z 
 94%|█████████▎| 5346/5712 [12:35:50<51:48,  8.49s/it]08/04/2024 22:13:59 - INFO - __main__ -   Step: 5346, LR: 3.5503660108465675e-08, Loss: 0.0512397326529026
2024-08-05T05:14:07.709516387Z 
 94%|█████████▎| 5347/5712 [12:35:58<51:16,  8.43s/it]08/04/2024 22:14:07 - INFO - __main__ -   Step: 5347, LR: 3.540638147814878e-08, Loss: 0.05932401493191719
2024-08-05T05:14:16.546252470Z 
 94%|█████████▎| 5348/5712 [12:36:07<51:52,  8.55s/it]08/04/2024 22:14:16 - INFO - __main__ -   Step: 5348, LR: 3.53091028478319e-08, Loss: 0.05467242747545242
2024-08-05T05:14:24.465464392Z 
 94%|█████████▎| 5349/5712 [12:36:15<50:35,  8.36s/it]08/04/2024 22:14:24 - INFO - __main__ -   Step: 5349, LR: 3.521182421751501e-08, Loss: 0.14129769802093506
2024-08-05T05:14:32.871880765Z 
 94%|█████████▎| 5350/5712 [12:36:24<50:31,  8.38s/it]08/04/2024 22:14:32 - INFO - __main__ -   Step: 5350, LR: 3.511454558719813e-08, Loss: 0.06335002928972244
2024-08-05T05:14:41.216084469Z 
 94%|█████████▎| 5351/5712 [12:36:32<50:20,  8.37s/it]08/04/2024 22:14:41 - INFO - __main__ -   Step: 5351, LR: 3.501726695688124e-08, Loss: 0.022743254899978638
2024-08-05T05:14:49.675510942Z 
 94%|█████████▎| 5352/5712 [12:36:40<50:21,  8.39s/it]08/04/2024 22:14:49 - INFO - __main__ -   Step: 5352, LR: 3.491998832656436e-08, Loss: 0.03954382985830307
2024-08-05T05:14:57.648702346Z 
 94%|█████████▎| 5353/5712 [12:36:48<49:28,  8.27s/it]08/04/2024 22:14:57 - INFO - __main__ -   Step: 5353, LR: 3.4822709696247474e-08, Loss: 0.056001052260398865
2024-08-05T05:15:06.746800636Z 
 94%|█████████▎| 5354/5712 [12:36:57<50:49,  8.52s/it]08/04/2024 22:15:06 - INFO - __main__ -   Step: 5354, LR: 3.4725431065930586e-08, Loss: 0.06754331290721893
2024-08-05T05:15:15.140779488Z 
 94%|█████████▍| 5355/5712 [12:37:06<50:27,  8.48s/it]08/04/2024 22:15:15 - INFO - __main__ -   Step: 5355, LR: 3.4628152435613705e-08, Loss: 0.03730315715074539
2024-08-05T05:15:23.801716518Z 
 94%|█████████▍| 5356/5712 [12:37:14<50:38,  8.53s/it]08/04/2024 22:15:23 - INFO - __main__ -   Step: 5356, LR: 3.453087380529682e-08, Loss: 0.037660785019397736
2024-08-05T05:15:31.857377556Z 
 94%|█████████▍| 5357/5712 [12:37:23<49:38,  8.39s/it]08/04/2024 22:15:31 - INFO - __main__ -   Step: 5357, LR: 3.4433595174979936e-08, Loss: 0.06541973352432251
2024-08-05T05:15:40.213109266Z 
 94%|█████████▍| 5358/5712 [12:37:31<49:26,  8.38s/it]08/04/2024 22:15:40 - INFO - __main__ -   Step: 5358, LR: 3.433631654466305e-08, Loss: 0.044218502938747406
2024-08-05T05:15:48.765375611Z 
 94%|█████████▍| 5359/5712 [12:37:39<49:36,  8.43s/it]08/04/2024 22:15:48 - INFO - __main__ -   Step: 5359, LR: 3.423903791434617e-08, Loss: 0.06770381331443787
2024-08-05T05:15:57.478801420Z 
 94%|█████████▍| 5360/5712 [12:37:48<49:57,  8.52s/it]08/04/2024 22:15:57 - INFO - __main__ -   Step: 5360, LR: 3.414175928402928e-08, Loss: 0.06965945661067963
2024-08-05T05:16:05.408139513Z 
 94%|█████████▍| 5361/5712 [12:37:56<48:47,  8.34s/it]08/04/2024 22:16:05 - INFO - __main__ -   Step: 5361, LR: 3.40444806537124e-08, Loss: 0.05426673963665962
2024-08-05T05:16:13.618062038Z 
 94%|█████████▍| 5362/5712 [12:38:04<48:25,  8.30s/it]08/04/2024 22:16:13 - INFO - __main__ -   Step: 5362, LR: 3.394720202339551e-08, Loss: 0.041690848767757416
2024-08-05T05:16:21.926648186Z 
 94%|█████████▍| 5363/5712 [12:38:13<48:17,  8.30s/it]08/04/2024 22:16:21 - INFO - __main__ -   Step: 5363, LR: 3.384992339307862e-08, Loss: 0.06888838112354279
2024-08-05T05:16:30.197261924Z 
 94%|█████████▍| 5364/5712 [12:38:21<48:06,  8.29s/it]08/04/2024 22:16:30 - INFO - __main__ -   Step: 5364, LR: 3.375264476276174e-08, Loss: 0.08572980761528015
2024-08-05T05:16:38.833159653Z 
 94%|█████████▍| 5365/5712 [12:38:29<48:33,  8.40s/it]08/04/2024 22:16:38 - INFO - __main__ -   Step: 5365, LR: 3.3655366132444854e-08, Loss: 0.0926995798945427
2024-08-05T05:16:46.379165556Z 
 94%|█████████▍| 5366/5712 [12:38:37<46:56,  8.14s/it]08/04/2024 22:16:46 - INFO - __main__ -   Step: 5366, LR: 3.3558087502127967e-08, Loss: 0.05643462762236595
2024-08-05T05:16:54.902466436Z 
 94%|█████████▍| 5367/5712 [12:38:46<47:28,  8.26s/it]08/04/2024 22:16:54 - INFO - __main__ -   Step: 5367, LR: 3.346080887181108e-08, Loss: 0.03537537902593613
2024-08-05T05:17:03.197202262Z 
 94%|█████████▍| 5368/5712 [12:38:54<47:24,  8.27s/it]08/04/2024 22:17:03 - INFO - __main__ -   Step: 5368, LR: 3.33635302414942e-08, Loss: 0.06966642290353775
2024-08-05T05:17:11.396236605Z 
 94%|█████████▍| 5369/5712 [12:39:02<47:08,  8.25s/it]08/04/2024 22:17:11 - INFO - __main__ -   Step: 5369, LR: 3.326625161117731e-08, Loss: 0.051371339708566666
2024-08-05T05:17:19.459644179Z 
 94%|█████████▍| 5370/5712 [12:39:10<46:41,  8.19s/it]08/04/2024 22:17:19 - INFO - __main__ -   Step: 5370, LR: 3.316897298086043e-08, Loss: 0.06559831649065018
2024-08-05T05:17:28.669117517Z 
 94%|█████████▍| 5371/5712 [12:39:19<48:17,  8.50s/it]08/04/2024 22:17:28 - INFO - __main__ -   Step: 5371, LR: 3.307169435054354e-08, Loss: 0.10710830986499786
2024-08-05T05:17:37.325796035Z 
 94%|█████████▍| 5372/5712 [12:39:28<48:25,  8.55s/it]08/04/2024 22:17:37 - INFO - __main__ -   Step: 5372, LR: 3.2974415720226654e-08, Loss: 0.050267256796360016
2024-08-05T05:17:45.627926699Z 
 94%|█████████▍| 5373/5712 [12:39:36<47:52,  8.47s/it]08/04/2024 22:17:45 - INFO - __main__ -   Step: 5373, LR: 3.287713708990977e-08, Loss: 0.101371631026268
2024-08-05T05:17:53.763127707Z 
 94%|█████████▍| 5374/5712 [12:39:44<47:09,  8.37s/it]08/04/2024 22:17:53 - INFO - __main__ -   Step: 5374, LR: 3.2779858459592885e-08, Loss: 0.05956590175628662
2024-08-05T05:18:01.810579234Z 
 94%|█████████▍| 5375/5712 [12:39:52<46:28,  8.27s/it]08/04/2024 22:18:01 - INFO - __main__ -   Step: 5375, LR: 3.2682579829276004e-08, Loss: 0.0455780103802681
2024-08-05T05:18:11.136459597Z 
 94%|█████████▍| 5376/5712 [12:40:02<48:06,  8.59s/it]08/04/2024 22:18:11 - INFO - __main__ -   Step: 5376, LR: 3.2585301198959116e-08, Loss: 0.1076572835445404
2024-08-05T05:18:19.970868761Z 
 94%|█████████▍| 5377/5712 [12:40:11<48:22,  8.66s/it]08/04/2024 22:18:19 - INFO - __main__ -   Step: 5377, LR: 3.2488022568642235e-08, Loss: 0.07111269235610962
2024-08-05T05:18:28.606929855Z 
 94%|█████████▍| 5378/5712 [12:40:19<48:10,  8.65s/it]08/04/2024 22:18:28 - INFO - __main__ -   Step: 5378, LR: 3.239074393832535e-08, Loss: 0.05726775527000427
2024-08-05T05:18:37.681876014Z 
 94%|█████████▍| 5379/5712 [12:40:28<48:44,  8.78s/it]08/04/2024 22:18:37 - INFO - __main__ -   Step: 5379, LR: 3.2293465308008466e-08, Loss: 0.05795605480670929
2024-08-05T05:18:46.061763617Z 
 94%|█████████▍| 5380/5712 [12:40:37<47:55,  8.66s/it]08/04/2024 22:18:46 - INFO - __main__ -   Step: 5380, LR: 3.219618667769158e-08, Loss: 0.07888361811637878
2024-08-05T05:18:55.070831656Z 
 94%|█████████▍| 5381/5712 [12:40:46<48:21,  8.77s/it]08/04/2024 22:18:55 - INFO - __main__ -   Step: 5381, LR: 3.209890804737469e-08, Loss: 0.06332366913557053
2024-08-05T05:19:03.057339736Z 
 94%|█████████▍| 5382/5712 [12:40:54<46:55,  8.53s/it]08/04/2024 22:19:03 - INFO - __main__ -   Step: 5382, LR: 3.200162941705781e-08, Loss: 0.09011802077293396
2024-08-05T05:19:11.679268173Z 
 94%|█████████▍| 5383/5712 [12:41:02<46:55,  8.56s/it]08/04/2024 22:19:11 - INFO - __main__ -   Step: 5383, LR: 3.190435078674092e-08, Loss: 0.04500112682580948
2024-08-05T05:19:20.076324763Z 
 94%|█████████▍| 5384/5712 [12:41:11<46:31,  8.51s/it]08/04/2024 22:19:20 - INFO - __main__ -   Step: 5384, LR: 3.180707215642404e-08, Loss: 0.10232119262218475
2024-08-05T05:19:28.688082794Z 
 94%|█████████▍| 5385/5712 [12:41:19<46:32,  8.54s/it]08/04/2024 22:19:28 - INFO - __main__ -   Step: 5385, LR: 3.1709793526107146e-08, Loss: 0.09085189551115036
2024-08-05T05:19:37.337158024Z 
 94%|█████████▍| 5386/5712 [12:41:28<46:34,  8.57s/it]08/04/2024 22:19:37 - INFO - __main__ -   Step: 5386, LR: 3.1612514895790265e-08, Loss: 0.11464877426624298
2024-08-05T05:19:46.062978602Z 
 94%|█████████▍| 5387/5712 [12:41:37<46:41,  8.62s/it]08/04/2024 22:19:46 - INFO - __main__ -   Step: 5387, LR: 3.151523626547338e-08, Loss: 0.04942409321665764
2024-08-05T05:19:55.903637490Z 
 94%|█████████▍| 5388/5712 [12:41:47<48:31,  8.99s/it]08/04/2024 22:19:55 - INFO - __main__ -   Step: 5388, LR: 3.1417957635156496e-08, Loss: 0.08287091553211212
2024-08-05T05:20:04.233149859Z 
 94%|█████████▍| 5389/5712 [12:41:55<47:18,  8.79s/it]08/04/2024 22:20:04 - INFO - __main__ -   Step: 5389, LR: 3.132067900483961e-08, Loss: 0.059553712606430054
2024-08-05T05:20:12.717931619Z 
 94%|█████████▍| 5390/5712 [12:42:03<46:40,  8.70s/it]08/04/2024 22:20:12 - INFO - __main__ -   Step: 5390, LR: 3.122340037452273e-08, Loss: 0.0949835255742073
2024-08-05T05:20:20.241684659Z 
 94%|█████████▍| 5391/5712 [12:42:11<44:38,  8.35s/it]08/04/2024 22:20:20 - INFO - __main__ -   Step: 5391, LR: 3.112612174420584e-08, Loss: 0.10212964564561844
2024-08-05T05:20:28.480899370Z 
 94%|█████████▍| 5392/5712 [12:42:19<44:20,  8.31s/it]08/04/2024 22:20:28 - INFO - __main__ -   Step: 5392, LR: 3.102884311388896e-08, Loss: 0.09843138605356216
2024-08-05T05:20:37.484027498Z 
 94%|█████████▍| 5393/5712 [12:42:28<45:17,  8.52s/it]08/04/2024 22:20:37 - INFO - __main__ -   Step: 5393, LR: 3.093156448357207e-08, Loss: 0.06961513310670853
2024-08-05T05:20:46.001121455Z 
 94%|█████████▍| 5394/5712 [12:42:37<45:08,  8.52s/it]08/04/2024 22:20:46 - INFO - __main__ -   Step: 5394, LR: 3.0834285853255183e-08, Loss: 0.04530157893896103
2024-08-05T05:20:54.854320827Z 
 94%|█████████▍| 5395/5712 [12:42:46<45:32,  8.62s/it]08/04/2024 22:20:54 - INFO - __main__ -   Step: 5395, LR: 3.0737007222938296e-08, Loss: 0.13590651750564575
2024-08-05T05:21:03.306438646Z 
 94%|█████████▍| 5396/5712 [12:42:54<45:07,  8.57s/it]08/04/2024 22:21:03 - INFO - __main__ -   Step: 5396, LR: 3.0639728592621415e-08, Loss: 0.07697013765573502
2024-08-05T05:21:11.651767468Z 
 94%|█████████▍| 5397/5712 [12:43:02<44:38,  8.50s/it]08/04/2024 22:21:11 - INFO - __main__ -   Step: 5397, LR: 3.054244996230453e-08, Loss: 0.09146696329116821
2024-08-05T05:21:19.899044124Z 
 95%|█████████▍| 5398/5712 [12:43:11<44:05,  8.43s/it]08/04/2024 22:21:19 - INFO - __main__ -   Step: 5398, LR: 3.0445171331987646e-08, Loss: 0.04345501959323883
2024-08-05T05:21:27.705782079Z 
 95%|█████████▍| 5399/5712 [12:43:18<42:59,  8.24s/it]08/04/2024 22:21:27 - INFO - __main__ -   Step: 5399, LR: 3.034789270167076e-08, Loss: 0.0676717534661293
2024-08-05T05:21:36.195039715Z 
 95%|█████████▍| 5400/5712 [12:43:27<43:14,  8.31s/it]08/04/2024 22:21:36 - INFO - __main__ -   Step: 5400, LR: 3.025061407135388e-08, Loss: 0.040998876094818115
2024-08-05T05:21:44.691645698Z 
 95%|█████████▍| 5401/5712 [12:43:35<43:22,  8.37s/it]08/04/2024 22:21:44 - INFO - __main__ -   Step: 5401, LR: 3.015333544103699e-08, Loss: 0.061822518706321716
2024-08-05T05:21:52.895887141Z 
 95%|█████████▍| 5402/5712 [12:43:44<42:59,  8.32s/it]08/04/2024 22:21:52 - INFO - __main__ -   Step: 5402, LR: 3.005605681072011e-08, Loss: 0.05024067312479019
2024-08-05T05:22:01.261658444Z 
 95%|█████████▍| 5403/5712 [12:43:52<42:55,  8.33s/it]08/04/2024 22:22:01 - INFO - __main__ -   Step: 5403, LR: 2.995877818040322e-08, Loss: 0.04431072250008583
2024-08-05T05:22:09.824115404Z 
 95%|█████████▍| 5404/5712 [12:44:00<43:07,  8.40s/it]08/04/2024 22:22:09 - INFO - __main__ -   Step: 5404, LR: 2.986149955008633e-08, Loss: 0.07019266486167908
2024-08-05T05:22:18.784147794Z 
 95%|█████████▍| 5405/5712 [12:44:09<43:50,  8.57s/it]08/04/2024 22:22:18 - INFO - __main__ -   Step: 5405, LR: 2.9764220919769448e-08, Loss: 0.10466273128986359
2024-08-05T05:22:26.991909516Z 
 95%|█████████▍| 5406/5712 [12:44:18<43:09,  8.46s/it]08/04/2024 22:22:26 - INFO - __main__ -   Step: 5406, LR: 2.9666942289452564e-08, Loss: 0.07303895056247711
2024-08-05T05:22:35.158258730Z 
 95%|█████████▍| 5407/5712 [12:44:26<42:33,  8.37s/it]08/04/2024 22:22:35 - INFO - __main__ -   Step: 5407, LR: 2.956966365913568e-08, Loss: 0.06394143402576447
2024-08-05T05:22:43.097775072Z 
 95%|█████████▍| 5408/5712 [12:44:34<41:45,  8.24s/it]08/04/2024 22:22:43 - INFO - __main__ -   Step: 5408, LR: 2.9472385028818795e-08, Loss: 0.06847778707742691
2024-08-05T05:22:51.239844083Z 
 95%|█████████▍| 5409/5712 [12:44:42<41:28,  8.21s/it]08/04/2024 22:22:51 - INFO - __main__ -   Step: 5409, LR: 2.9375106398501907e-08, Loss: 0.06802865862846375
2024-08-05T05:22:59.478978560Z 
 95%|█████████▍| 5410/5712 [12:44:50<41:22,  8.22s/it]08/04/2024 22:22:59 - INFO - __main__ -   Step: 5410, LR: 2.9277827768185023e-08, Loss: 0.08674024045467377
2024-08-05T05:23:08.343355368Z 
 95%|█████████▍| 5411/5712 [12:44:59<42:12,  8.41s/it]08/04/2024 22:23:08 - INFO - __main__ -   Step: 5411, LR: 2.9180549137868135e-08, Loss: 0.05654476583003998
2024-08-05T05:23:17.086154554Z 
 95%|█████████▍| 5412/5712 [12:45:08<42:33,  8.51s/it]08/04/2024 22:23:17 - INFO - __main__ -   Step: 5412, LR: 2.908327050755125e-08, Loss: 0.08759549260139465
2024-08-05T05:23:25.352015908Z 
 95%|█████████▍| 5413/5712 [12:45:16<42:03,  8.44s/it]08/04/2024 22:23:25 - INFO - __main__ -   Step: 5413, LR: 2.8985991877234366e-08, Loss: 0.1339016556739807
2024-08-05T05:23:33.737602520Z 
 95%|█████████▍| 5414/5712 [12:45:24<41:49,  8.42s/it]08/04/2024 22:23:33 - INFO - __main__ -   Step: 5414, LR: 2.8888713246917482e-08, Loss: 0.04680219665169716
2024-08-05T05:23:42.003282845Z 
 95%|█████████▍| 5415/5712 [12:45:33<41:27,  8.38s/it]08/04/2024 22:23:42 - INFO - __main__ -   Step: 5415, LR: 2.8791434616600597e-08, Loss: 0.06976494938135147
2024-08-05T05:23:50.068347541Z 
 95%|█████████▍| 5416/5712 [12:45:41<40:51,  8.28s/it]08/04/2024 22:23:50 - INFO - __main__ -   Step: 5416, LR: 2.8694155986283713e-08, Loss: 0.08115231990814209
2024-08-05T05:23:58.273184650Z 
 95%|█████████▍| 5417/5712 [12:45:49<40:36,  8.26s/it]08/04/2024 22:23:58 - INFO - __main__ -   Step: 5417, LR: 2.859687735596683e-08, Loss: 0.07019608467817307
2024-08-05T05:24:06.720801445Z 
 95%|█████████▍| 5418/5712 [12:45:57<40:44,  8.32s/it]08/04/2024 22:24:06 - INFO - __main__ -   Step: 5418, LR: 2.8499598725649944e-08, Loss: 0.06804513186216354
2024-08-05T05:24:14.916403233Z 
 95%|█████████▍| 5419/5712 [12:46:06<40:25,  8.28s/it]08/04/2024 22:24:14 - INFO - __main__ -   Step: 5419, LR: 2.8402320095333057e-08, Loss: 0.08188233524560928
2024-08-05T05:24:23.641891952Z 
 95%|█████████▍| 5420/5712 [12:46:14<40:56,  8.41s/it]08/04/2024 22:24:23 - INFO - __main__ -   Step: 5420, LR: 2.830504146501617e-08, Loss: 0.08217989653348923
2024-08-05T05:24:32.424569221Z 
 95%|█████████▍| 5421/5712 [12:46:23<41:20,  8.52s/it]08/04/2024 22:24:32 - INFO - __main__ -   Step: 5421, LR: 2.8207762834699284e-08, Loss: 0.06460502743721008
2024-08-05T05:24:41.158720110Z 
 95%|█████████▍| 5422/5712 [12:46:32<41:30,  8.59s/it]08/04/2024 22:24:41 - INFO - __main__ -   Step: 5422, LR: 2.81104842043824e-08, Loss: 0.12309066951274872
2024-08-05T05:24:49.430387780Z 
 95%|█████████▍| 5423/5712 [12:46:40<40:54,  8.49s/it]08/04/2024 22:24:49 - INFO - __main__ -   Step: 5423, LR: 2.8013205574065516e-08, Loss: 0.10715018957853317
2024-08-05T05:24:57.480097620Z 
 95%|█████████▍| 5424/5712 [12:46:48<40:07,  8.36s/it]08/04/2024 22:24:57 - INFO - __main__ -   Step: 5424, LR: 2.791592694374863e-08, Loss: 0.051074638962745667
2024-08-05T05:25:05.823927777Z 
 95%|█████████▍| 5425/5712 [12:46:56<39:57,  8.35s/it]08/04/2024 22:25:05 - INFO - __main__ -   Step: 5425, LR: 2.7818648313431747e-08, Loss: 0.08207692950963974
2024-08-05T05:25:13.898602180Z 
 95%|█████████▍| 5426/5712 [12:47:05<39:25,  8.27s/it]08/04/2024 22:25:13 - INFO - __main__ -   Step: 5426, LR: 2.7721369683114862e-08, Loss: 0.05197756737470627
2024-08-05T05:25:22.127811025Z 
 95%|█████████▌| 5427/5712 [12:47:13<39:13,  8.26s/it]08/04/2024 22:25:22 - INFO - __main__ -   Step: 5427, LR: 2.7624091052797978e-08, Loss: 0.07356573641300201
2024-08-05T05:25:31.471159525Z 
 95%|█████████▌| 5428/5712 [12:47:22<40:37,  8.58s/it]08/04/2024 22:25:31 - INFO - __main__ -   Step: 5428, LR: 2.752681242248109e-08, Loss: 0.04996149241924286
2024-08-05T05:25:39.876738903Z 
 95%|█████████▌| 5429/5712 [12:47:31<40:14,  8.53s/it]08/04/2024 22:25:39 - INFO - __main__ -   Step: 5429, LR: 2.7429533792164202e-08, Loss: 0.039671652019023895
2024-08-05T05:25:48.499399284Z 
 95%|█████████▌| 5430/5712 [12:47:39<40:13,  8.56s/it]08/04/2024 22:25:48 - INFO - __main__ -   Step: 5430, LR: 2.7332255161847318e-08, Loss: 0.06738698482513428
2024-08-05T05:25:56.768357910Z 
 95%|█████████▌| 5431/5712 [12:47:47<39:40,  8.47s/it]08/04/2024 22:25:56 - INFO - __main__ -   Step: 5431, LR: 2.7234976531530434e-08, Loss: 0.04107160121202469
2024-08-05T05:26:04.883621125Z 
 95%|█████████▌| 5432/5712 [12:47:56<39:02,  8.36s/it]08/04/2024 22:26:04 - INFO - __main__ -   Step: 5432, LR: 2.713769790121355e-08, Loss: 0.03675030916929245
2024-08-05T05:26:13.201940444Z 
 95%|█████████▌| 5433/5712 [12:48:04<38:49,  8.35s/it]08/04/2024 22:26:13 - INFO - __main__ -   Step: 5433, LR: 2.7040419270896665e-08, Loss: 0.04746558517217636
2024-08-05T05:26:22.017585979Z 
 95%|█████████▌| 5434/5712 [12:48:13<39:20,  8.49s/it]08/04/2024 22:26:22 - INFO - __main__ -   Step: 5434, LR: 2.694314064057978e-08, Loss: 0.04387032240629196
2024-08-05T05:26:30.586789257Z 
 95%|█████████▌| 5435/5712 [12:48:21<39:18,  8.51s/it]08/04/2024 22:26:30 - INFO - __main__ -   Step: 5435, LR: 2.6845862010262896e-08, Loss: 0.08602388203144073
2024-08-05T05:26:39.163075083Z 
 95%|█████████▌| 5436/5712 [12:48:30<39:14,  8.53s/it]08/04/2024 22:26:39 - INFO - __main__ -   Step: 5436, LR: 2.674858337994601e-08, Loss: 0.09237538278102875
2024-08-05T05:26:48.875761186Z 
 95%|█████████▌| 5437/5712 [12:48:40<40:43,  8.89s/it]08/04/2024 22:26:48 - INFO - __main__ -   Step: 5437, LR: 2.6651304749629127e-08, Loss: 0.07316040992736816
2024-08-05T05:26:57.123298914Z 
 95%|█████████▌| 5438/5712 [12:48:48<39:42,  8.69s/it]08/04/2024 22:26:57 - INFO - __main__ -   Step: 5438, LR: 2.6554026119312236e-08, Loss: 0.05804349482059479
2024-08-05T05:27:05.787516313Z 
 95%|█████████▌| 5439/5712 [12:48:56<39:31,  8.69s/it]08/04/2024 22:27:05 - INFO - __main__ -   Step: 5439, LR: 2.6456747488995352e-08, Loss: 0.14601826667785645
2024-08-05T05:27:13.848503626Z 
 95%|█████████▌| 5440/5712 [12:49:04<38:31,  8.50s/it]08/04/2024 22:27:13 - INFO - __main__ -   Step: 5440, LR: 2.6359468858678467e-08, Loss: 0.06853322684764862
2024-08-05T05:27:22.207042499Z 
 95%|█████████▌| 5441/5712 [12:49:13<38:11,  8.46s/it]08/04/2024 22:27:22 - INFO - __main__ -   Step: 5441, LR: 2.6262190228361583e-08, Loss: 0.038705840706825256
2024-08-05T05:27:30.954312465Z 
 95%|█████████▌| 5442/5712 [12:49:22<38:26,  8.54s/it]08/04/2024 22:27:30 - INFO - __main__ -   Step: 5442, LR: 2.61649115980447e-08, Loss: 0.04966533184051514
2024-08-05T05:27:39.422519368Z 
 95%|█████████▌| 5443/5712 [12:49:30<38:12,  8.52s/it]08/04/2024 22:27:39 - INFO - __main__ -   Step: 5443, LR: 2.6067632967727814e-08, Loss: 0.05748956277966499
2024-08-05T05:27:47.785909523Z 
 95%|█████████▌| 5444/5712 [12:49:38<37:50,  8.47s/it]08/04/2024 22:27:47 - INFO - __main__ -   Step: 5444, LR: 2.597035433741093e-08, Loss: 0.03088681399822235
2024-08-05T05:27:57.112213257Z 
 95%|█████████▌| 5445/5712 [12:49:48<38:50,  8.73s/it]08/04/2024 22:27:57 - INFO - __main__ -   Step: 5445, LR: 2.5873075707094045e-08, Loss: 0.09940062463283539
2024-08-05T05:28:05.303661594Z 
 95%|█████████▌| 5446/5712 [12:49:56<37:59,  8.57s/it]08/04/2024 22:28:05 - INFO - __main__ -   Step: 5446, LR: 2.577579707677716e-08, Loss: 0.12453776597976685
2024-08-05T05:28:13.708489387Z 
 95%|█████████▌| 5447/5712 [12:50:04<37:37,  8.52s/it]08/04/2024 22:28:13 - INFO - __main__ -   Step: 5447, LR: 2.567851844646027e-08, Loss: 0.09427425265312195
2024-08-05T05:28:21.870425035Z 
 95%|█████████▌| 5448/5712 [12:50:13<37:00,  8.41s/it]08/04/2024 22:28:21 - INFO - __main__ -   Step: 5448, LR: 2.5581239816143385e-08, Loss: 0.07283991575241089
2024-08-05T05:28:30.008837403Z 
 95%|█████████▌| 5449/5712 [12:50:21<36:30,  8.33s/it]08/04/2024 22:28:30 - INFO - __main__ -   Step: 5449, LR: 2.54839611858265e-08, Loss: 0.07605811953544617
2024-08-05T05:28:38.639264699Z 
 95%|█████████▌| 5450/5712 [12:50:29<36:46,  8.42s/it]08/04/2024 22:28:38 - INFO - __main__ -   Step: 5450, LR: 2.5386682555509617e-08, Loss: 0.031890153884887695
2024-08-05T05:28:46.807506623Z 
 95%|█████████▌| 5451/5712 [12:50:37<36:17,  8.34s/it]08/04/2024 22:28:46 - INFO - __main__ -   Step: 5451, LR: 2.5289403925192732e-08, Loss: 0.09009140729904175
2024-08-05T05:28:55.638058436Z 
 95%|█████████▌| 5452/5712 [12:50:46<36:47,  8.49s/it]08/04/2024 22:28:55 - INFO - __main__ -   Step: 5452, LR: 2.5192125294875848e-08, Loss: 0.07530639320611954
2024-08-05T05:29:04.686509899Z 
 95%|█████████▌| 5453/5712 [12:50:55<37:22,  8.66s/it]08/04/2024 22:29:04 - INFO - __main__ -   Step: 5453, LR: 2.5094846664558963e-08, Loss: 0.03547009080648422
2024-08-05T05:29:13.291028021Z 
 95%|█████████▌| 5454/5712 [12:51:04<37:09,  8.64s/it]08/04/2024 22:29:13 - INFO - __main__ -   Step: 5454, LR: 2.499756803424208e-08, Loss: 0.03677865117788315
2024-08-05T05:29:21.329244829Z 
 96%|█████████▌| 5455/5712 [12:51:12<36:14,  8.46s/it]08/04/2024 22:29:21 - INFO - __main__ -   Step: 5455, LR: 2.4900289403925195e-08, Loss: 0.06894226372241974
2024-08-05T05:29:30.181416855Z 
 96%|█████████▌| 5456/5712 [12:51:21<36:35,  8.58s/it]08/04/2024 22:29:30 - INFO - __main__ -   Step: 5456, LR: 2.4803010773608304e-08, Loss: 0.05486252158880234
2024-08-05T05:29:38.123865580Z 
 96%|█████████▌| 5457/5712 [12:51:29<35:38,  8.39s/it]08/04/2024 22:29:38 - INFO - __main__ -   Step: 5457, LR: 2.470573214329142e-08, Loss: 0.053254157304763794
2024-08-05T05:29:46.503184152Z 
 96%|█████████▌| 5458/5712 [12:51:37<35:29,  8.39s/it]08/04/2024 22:29:46 - INFO - __main__ -   Step: 5458, LR: 2.4608453512974535e-08, Loss: 0.06086019426584244
2024-08-05T05:29:55.118210371Z 
 96%|█████████▌| 5459/5712 [12:51:46<35:38,  8.45s/it]08/04/2024 22:29:55 - INFO - __main__ -   Step: 5459, LR: 2.451117488265765e-08, Loss: 0.14401260018348694
2024-08-05T05:30:03.537998330Z 
 96%|█████████▌| 5460/5712 [12:51:54<35:27,  8.44s/it]08/04/2024 22:30:03 - INFO - __main__ -   Step: 5460, LR: 2.4413896252340766e-08, Loss: 0.11900061368942261
2024-08-05T05:30:12.269408444Z 
 96%|█████████▌| 5461/5712 [12:52:03<35:41,  8.53s/it]08/04/2024 22:30:12 - INFO - __main__ -   Step: 5461, LR: 2.431661762202388e-08, Loss: 0.08426927775144577
2024-08-05T05:30:21.351086206Z 
 96%|█████████▌| 5462/5712 [12:52:12<36:13,  8.70s/it]08/04/2024 22:30:21 - INFO - __main__ -   Step: 5462, LR: 2.4219338991706997e-08, Loss: 0.04050059616565704
2024-08-05T05:30:29.581169409Z 
 96%|█████████▌| 5463/5712 [12:52:20<35:30,  8.56s/it]08/04/2024 22:30:29 - INFO - __main__ -   Step: 5463, LR: 2.4122060361390113e-08, Loss: 0.06996995955705643
2024-08-05T05:30:37.789208221Z 
 96%|█████████▌| 5464/5712 [12:52:28<34:56,  8.45s/it]08/04/2024 22:30:37 - INFO - __main__ -   Step: 5464, LR: 2.4024781731073225e-08, Loss: 0.11342500150203705
2024-08-05T05:30:45.760122615Z 
 96%|█████████▌| 5465/5712 [12:52:36<34:11,  8.31s/it]08/04/2024 22:30:45 - INFO - __main__ -   Step: 5465, LR: 2.392750310075634e-08, Loss: 0.05755458027124405
2024-08-05T05:30:53.831753690Z 
 96%|█████████▌| 5466/5712 [12:52:44<33:46,  8.24s/it]08/04/2024 22:30:53 - INFO - __main__ -   Step: 5466, LR: 2.3830224470439453e-08, Loss: 0.06407039612531662
2024-08-05T05:31:02.153207180Z 
 96%|█████████▌| 5467/5712 [12:52:53<33:44,  8.26s/it]08/04/2024 22:31:02 - INFO - __main__ -   Step: 5467, LR: 2.373294584012257e-08, Loss: 0.05852742865681648
2024-08-05T05:31:10.227608961Z 
 96%|█████████▌| 5468/5712 [12:53:01<33:22,  8.21s/it]08/04/2024 22:31:10 - INFO - __main__ -   Step: 5468, LR: 2.3635667209805684e-08, Loss: 0.07359087467193604
2024-08-05T05:31:18.930694279Z 
 96%|█████████▌| 5469/5712 [12:53:10<33:50,  8.36s/it]08/04/2024 22:31:18 - INFO - __main__ -   Step: 5469, LR: 2.35383885794888e-08, Loss: 0.04754310101270676
2024-08-05T05:31:27.849826670Z 
 96%|█████████▌| 5470/5712 [12:53:18<34:22,  8.52s/it]08/04/2024 22:31:27 - INFO - __main__ -   Step: 5470, LR: 2.3441109949171915e-08, Loss: 0.10961809009313583
2024-08-05T05:31:36.295859723Z 
 96%|█████████▌| 5471/5712 [12:53:27<34:08,  8.50s/it]08/04/2024 22:31:36 - INFO - __main__ -   Step: 5471, LR: 2.334383131885503e-08, Loss: 0.10218620300292969
2024-08-05T05:31:44.375313407Z 
 96%|█████████▌| 5472/5712 [12:53:35<33:29,  8.37s/it]08/04/2024 22:31:44 - INFO - __main__ -   Step: 5472, LR: 2.3246552688538146e-08, Loss: 0.09355193376541138
2024-08-05T05:31:53.184849273Z 
 96%|█████████▌| 5473/5712 [12:53:44<33:52,  8.50s/it]08/04/2024 22:31:53 - INFO - __main__ -   Step: 5473, LR: 2.314927405822126e-08, Loss: 0.024304646998643875
2024-08-05T05:32:01.152863856Z 
 96%|█████████▌| 5474/5712 [12:53:52<33:05,  8.34s/it]08/04/2024 22:32:01 - INFO - __main__ -   Step: 5474, LR: 2.3051995427904374e-08, Loss: 0.09480848163366318
2024-08-05T05:32:09.581843656Z 
 96%|█████████▌| 5475/5712 [12:54:00<33:03,  8.37s/it]08/04/2024 22:32:09 - INFO - __main__ -   Step: 5475, LR: 2.2954716797587487e-08, Loss: 0.04879625886678696
2024-08-05T05:32:17.836138973Z 
 96%|█████████▌| 5476/5712 [12:54:08<32:47,  8.33s/it]08/04/2024 22:32:17 - INFO - __main__ -   Step: 5476, LR: 2.2857438167270602e-08, Loss: 0.13343441486358643
2024-08-05T05:32:26.072237408Z 
 96%|█████████▌| 5477/5712 [12:54:17<32:31,  8.31s/it]08/04/2024 22:32:26 - INFO - __main__ -   Step: 5477, LR: 2.2760159536953718e-08, Loss: 0.030945774167776108
2024-08-05T05:32:34.684995979Z 
 96%|█████████▌| 5478/5712 [12:54:25<32:45,  8.40s/it]08/04/2024 22:32:34 - INFO - __main__ -   Step: 5478, LR: 2.2662880906636833e-08, Loss: 0.09059333801269531
2024-08-05T05:32:43.903800269Z 
 96%|█████████▌| 5479/5712 [12:54:35<33:34,  8.64s/it]08/04/2024 22:32:43 - INFO - __main__ -   Step: 5479, LR: 2.256560227631995e-08, Loss: 0.08584356307983398
2024-08-05T05:32:52.074050778Z 
 96%|█████████▌| 5480/5712 [12:54:43<32:52,  8.50s/it]08/04/2024 22:32:52 - INFO - __main__ -   Step: 5480, LR: 2.2468323646003064e-08, Loss: 0.05765431001782417
2024-08-05T05:33:00.570695422Z 
 96%|█████████▌| 5481/5712 [12:54:51<32:43,  8.50s/it]08/04/2024 22:33:00 - INFO - __main__ -   Step: 5481, LR: 2.237104501568618e-08, Loss: 0.07776731997728348
2024-08-05T05:33:08.777320321Z 
 96%|█████████▌| 5482/5712 [12:54:59<32:14,  8.41s/it]08/04/2024 22:33:08 - INFO - __main__ -   Step: 5482, LR: 2.2273766385369292e-08, Loss: 0.08359532803297043
2024-08-05T05:33:17.311791982Z 
 96%|█████████▌| 5483/5712 [12:55:08<32:14,  8.45s/it]08/04/2024 22:33:17 - INFO - __main__ -   Step: 5483, LR: 2.2176487755052408e-08, Loss: 0.06333766877651215
2024-08-05T05:33:25.684170054Z 
 96%|█████████▌| 5484/5712 [12:55:16<32:01,  8.43s/it]08/04/2024 22:33:25 - INFO - __main__ -   Step: 5484, LR: 2.2079209124735524e-08, Loss: 0.0727347880601883
2024-08-05T05:33:34.097691643Z 
 96%|█████████▌| 5485/5712 [12:55:25<31:51,  8.42s/it]08/04/2024 22:33:34 - INFO - __main__ -   Step: 5485, LR: 2.1981930494418636e-08, Loss: 0.05488298833370209
2024-08-05T05:33:43.266796277Z 
 96%|█████████▌| 5486/5712 [12:55:34<32:34,  8.65s/it]08/04/2024 22:33:43 - INFO - __main__ -   Step: 5486, LR: 2.188465186410175e-08, Loss: 0.05689515173435211
2024-08-05T05:33:51.812231061Z 
 96%|█████████▌| 5487/5712 [12:55:42<32:18,  8.62s/it]08/04/2024 22:33:51 - INFO - __main__ -   Step: 5487, LR: 2.1787373233784867e-08, Loss: 0.05987773835659027
2024-08-05T05:34:00.638748871Z 
 96%|█████████▌| 5488/5712 [12:55:51<32:24,  8.68s/it]08/04/2024 22:34:00 - INFO - __main__ -   Step: 5488, LR: 2.1690094603467983e-08, Loss: 0.041213031858205795
2024-08-05T05:34:08.842803288Z 
 96%|█████████▌| 5489/5712 [12:55:59<31:43,  8.54s/it]08/04/2024 22:34:08 - INFO - __main__ -   Step: 5489, LR: 2.1592815973151098e-08, Loss: 0.09553393721580505
2024-08-05T05:34:17.461216162Z 
 96%|█████████▌| 5490/5712 [12:56:08<31:40,  8.56s/it]08/04/2024 22:34:17 - INFO - __main__ -   Step: 5490, LR: 2.1495537342834214e-08, Loss: 0.09643730521202087
2024-08-05T05:34:26.098667696Z 
 96%|█████████▌| 5491/5712 [12:56:17<31:37,  8.58s/it]08/04/2024 22:34:26 - INFO - __main__ -   Step: 5491, LR: 2.1398258712517326e-08, Loss: 0.06683275103569031
2024-08-05T05:34:34.387084187Z 
 96%|█████████▌| 5492/5712 [12:56:25<31:08,  8.50s/it]08/04/2024 22:34:34 - INFO - __main__ -   Step: 5492, LR: 2.130098008220044e-08, Loss: 0.03528094291687012
2024-08-05T05:34:42.303692393Z 
 96%|█████████▌| 5493/5712 [12:56:33<30:22,  8.32s/it]08/04/2024 22:34:42 - INFO - __main__ -   Step: 5493, LR: 2.1203701451883557e-08, Loss: 0.06970863044261932
2024-08-05T05:34:50.955832917Z 
 96%|█████████▌| 5494/5712 [12:56:42<30:35,  8.42s/it]08/04/2024 22:34:50 - INFO - __main__ -   Step: 5494, LR: 2.110642282156667e-08, Loss: 0.05069035291671753
2024-08-05T05:34:59.397442356Z 
 96%|█████████▌| 5495/5712 [12:56:50<30:28,  8.43s/it]08/04/2024 22:34:59 - INFO - __main__ -   Step: 5495, LR: 2.1009144191249785e-08, Loss: 0.04117642343044281
2024-08-05T05:35:09.098718190Z 
 96%|█████████▌| 5496/5712 [12:57:00<31:42,  8.81s/it]08/04/2024 22:35:09 - INFO - __main__ -   Step: 5496, LR: 2.09118655609329e-08, Loss: 0.11279121786355972
2024-08-05T05:35:17.366450100Z 
 96%|█████████▌| 5497/5712 [12:57:08<30:59,  8.65s/it]08/04/2024 22:35:17 - INFO - __main__ -   Step: 5497, LR: 2.0814586930616016e-08, Loss: 0.0665319412946701
2024-08-05T05:35:25.500913249Z 
 96%|█████████▋| 5498/5712 [12:57:16<30:17,  8.49s/it]08/04/2024 22:35:25 - INFO - __main__ -   Step: 5498, LR: 2.0717308300299132e-08, Loss: 0.058602556586265564
2024-08-05T05:35:33.938439983Z 
 96%|█████████▋| 5499/5712 [12:57:25<30:05,  8.48s/it]08/04/2024 22:35:33 - INFO - __main__ -   Step: 5499, LR: 2.0620029669982247e-08, Loss: 0.05033267289400101
2024-08-05T05:35:42.301161236Z 
 96%|█████████▋| 5500/5712 [12:57:33<29:49,  8.44s/it]08/04/2024 22:35:42 - INFO - __main__ -   Step: 5500, LR: 2.052275103966536e-08, Loss: 0.06459847092628479
2024-08-05T05:35:50.286813693Z 
 96%|█████████▋| 5501/5712 [12:57:41<29:12,  8.31s/it]08/04/2024 22:35:50 - INFO - __main__ -   Step: 5501, LR: 2.0425472409348475e-08, Loss: 0.13410203158855438
2024-08-05T05:35:58.754624474Z 
 96%|█████████▋| 5502/5712 [12:57:49<29:14,  8.35s/it]08/04/2024 22:35:58 - INFO - __main__ -   Step: 5502, LR: 2.032819377903159e-08, Loss: 0.06171588599681854
2024-08-05T05:36:07.812871163Z 
 96%|█████████▋| 5503/5712 [12:57:58<29:50,  8.57s/it]08/04/2024 22:36:07 - INFO - __main__ -   Step: 5503, LR: 2.0230915148714706e-08, Loss: 0.060549572110176086
2024-08-05T05:36:16.936258199Z 
 96%|█████████▋| 5504/5712 [12:58:08<30:16,  8.73s/it]08/04/2024 22:36:16 - INFO - __main__ -   Step: 5504, LR: 2.013363651839782e-08, Loss: 0.052655771374702454
2024-08-05T05:36:25.437011065Z 
 96%|█████████▋| 5505/5712 [12:58:16<29:53,  8.66s/it]08/04/2024 22:36:25 - INFO - __main__ -   Step: 5505, LR: 2.0036357888080934e-08, Loss: 0.046932026743888855
2024-08-05T05:36:34.129877985Z 
 96%|█████████▋| 5506/5712 [12:58:25<29:46,  8.67s/it]08/04/2024 22:36:34 - INFO - __main__ -   Step: 5506, LR: 1.993907925776405e-08, Loss: 0.07523753494024277
2024-08-05T05:36:42.638379684Z 
 96%|█████████▋| 5507/5712 [12:58:33<29:27,  8.62s/it]08/04/2024 22:36:42 - INFO - __main__ -   Step: 5507, LR: 1.9841800627447166e-08, Loss: 0.07490026205778122
2024-08-05T05:36:50.920041272Z 
 96%|█████████▋| 5508/5712 [12:58:42<28:58,  8.52s/it]08/04/2024 22:36:50 - INFO - __main__ -   Step: 5508, LR: 1.974452199713028e-08, Loss: 0.07713162899017334
2024-08-05T05:36:59.038629732Z 
 96%|█████████▋| 5509/5712 [12:58:50<28:25,  8.40s/it]08/04/2024 22:36:59 - INFO - __main__ -   Step: 5509, LR: 1.9647243366813393e-08, Loss: 0.05497591942548752
2024-08-05T05:37:07.283234348Z 
 96%|█████████▋| 5510/5712 [12:58:58<28:07,  8.35s/it]08/04/2024 22:37:07 - INFO - __main__ -   Step: 5510, LR: 1.954996473649651e-08, Loss: 0.03681012988090515
2024-08-05T05:37:15.943018116Z 
 96%|█████████▋| 5511/5712 [12:59:07<28:17,  8.45s/it]08/04/2024 22:37:15 - INFO - __main__ -   Step: 5511, LR: 1.9452686106179625e-08, Loss: 0.12217213213443756
2024-08-05T05:37:24.440549210Z 
 96%|█████████▋| 5512/5712 [12:59:15<28:12,  8.46s/it]08/04/2024 22:37:24 - INFO - __main__ -   Step: 5512, LR: 1.935540747586274e-08, Loss: 0.041544876992702484
2024-08-05T05:37:33.846919121Z 
 97%|█████████▋| 5513/5712 [12:59:24<29:00,  8.74s/it]08/04/2024 22:37:33 - INFO - __main__ -   Step: 5513, LR: 1.9258128845545852e-08, Loss: 0.08946270495653152
2024-08-05T05:37:42.055705033Z 
 97%|█████████▋| 5514/5712 [12:59:33<28:19,  8.58s/it]08/04/2024 22:37:42 - INFO - __main__ -   Step: 5514, LR: 1.9160850215228968e-08, Loss: 0.05441853776574135
2024-08-05T05:37:50.256684834Z 
 97%|█████████▋| 5515/5712 [12:59:41<27:48,  8.47s/it]08/04/2024 22:37:50 - INFO - __main__ -   Step: 5515, LR: 1.9063571584912084e-08, Loss: 0.15646210312843323
2024-08-05T05:37:58.513615628Z 
 97%|█████████▋| 5516/5712 [12:59:49<27:27,  8.41s/it]08/04/2024 22:37:58 - INFO - __main__ -   Step: 5516, LR: 1.89662929545952e-08, Loss: 0.09765390306711197
2024-08-05T05:38:06.925101495Z 
 97%|█████████▋| 5517/5712 [12:59:58<27:19,  8.41s/it]08/04/2024 22:38:06 - INFO - __main__ -   Step: 5517, LR: 1.886901432427831e-08, Loss: 0.06249963492155075
2024-08-05T05:38:15.412590445Z 
 97%|█████████▋| 5518/5712 [13:00:06<27:15,  8.43s/it]08/04/2024 22:38:15 - INFO - __main__ -   Step: 5518, LR: 1.8771735693961427e-08, Loss: 0.06097320839762688
2024-08-05T05:38:23.620129352Z 
 97%|█████████▋| 5519/5712 [13:00:14<26:54,  8.36s/it]08/04/2024 22:38:23 - INFO - __main__ -   Step: 5519, LR: 1.8674457063644543e-08, Loss: 0.049392152577638626
2024-08-05T05:38:32.452748780Z 
 97%|█████████▋| 5520/5712 [13:00:23<27:12,  8.50s/it]08/04/2024 22:38:32 - INFO - __main__ -   Step: 5520, LR: 1.8577178433327658e-08, Loss: 0.09953515976667404
2024-08-05T05:38:40.941820162Z 
 97%|█████████▋| 5521/5712 [13:00:32<27:03,  8.50s/it]08/04/2024 22:38:40 - INFO - __main__ -   Step: 5521, LR: 1.8479899803010774e-08, Loss: 0.048231519758701324
2024-08-05T05:38:49.556469086Z 
 97%|█████████▋| 5522/5712 [13:00:40<27:01,  8.53s/it]08/04/2024 22:38:49 - INFO - __main__ -   Step: 5522, LR: 1.838262117269389e-08, Loss: 0.08678112924098969
2024-08-05T05:38:57.968911721Z 
 97%|█████████▋| 5523/5712 [13:00:49<26:46,  8.50s/it]08/04/2024 22:38:57 - INFO - __main__ -   Step: 5523, LR: 1.8285342542377002e-08, Loss: 0.07395263016223907
2024-08-05T05:39:06.647107349Z 
 97%|█████████▋| 5524/5712 [13:00:57<26:47,  8.55s/it]08/04/2024 22:39:06 - INFO - __main__ -   Step: 5524, LR: 1.8188063912060117e-08, Loss: 0.03268317133188248
2024-08-05T05:39:14.743058779Z 
 97%|█████████▋| 5525/5712 [13:01:05<26:13,  8.42s/it]08/04/2024 22:39:14 - INFO - __main__ -   Step: 5525, LR: 1.8090785281743233e-08, Loss: 0.04092688113451004
2024-08-05T05:39:22.921557340Z 
 97%|█████████▋| 5526/5712 [13:01:14<25:52,  8.34s/it]08/04/2024 22:39:22 - INFO - __main__ -   Step: 5526, LR: 1.7993506651426345e-08, Loss: 0.08536945283412933
2024-08-05T05:39:32.209973141Z 
 97%|█████████▋| 5527/5712 [13:01:23<26:36,  8.63s/it]08/04/2024 22:39:32 - INFO - __main__ -   Step: 5527, LR: 1.789622802110946e-08, Loss: 0.03851402550935745
2024-08-05T05:39:40.911696811Z 
 97%|█████████▋| 5528/5712 [13:01:32<26:31,  8.65s/it]08/04/2024 22:39:40 - INFO - __main__ -   Step: 5528, LR: 1.7798949390792576e-08, Loss: 0.13319388031959534
2024-08-05T05:39:49.376889462Z 
 97%|█████████▋| 5529/5712 [13:01:40<26:12,  8.59s/it]08/04/2024 22:39:49 - INFO - __main__ -   Step: 5529, LR: 1.7701670760475692e-08, Loss: 0.10014854371547699
2024-08-05T05:39:58.707169263Z 
 97%|█████████▋| 5530/5712 [13:01:49<26:44,  8.81s/it]08/04/2024 22:39:58 - INFO - __main__ -   Step: 5530, LR: 1.7604392130158808e-08, Loss: 0.055827487260103226
2024-08-05T05:40:06.848836554Z 
 97%|█████████▋| 5531/5712 [13:01:57<25:58,  8.61s/it]08/04/2024 22:40:06 - INFO - __main__ -   Step: 5531, LR: 1.7507113499841923e-08, Loss: 0.07716326415538788
2024-08-05T05:40:15.713148808Z 
 97%|█████████▋| 5532/5712 [13:02:06<26:03,  8.69s/it]08/04/2024 22:40:15 - INFO - __main__ -   Step: 5532, LR: 1.7409834869525035e-08, Loss: 0.16121041774749756
2024-08-05T05:40:24.029053829Z 
 97%|█████████▋| 5533/5712 [13:02:15<25:35,  8.58s/it]08/04/2024 22:40:24 - INFO - __main__ -   Step: 5533, LR: 1.731255623920815e-08, Loss: 0.08606375008821487
2024-08-05T05:40:32.476152144Z 
 97%|█████████▋| 5534/5712 [13:02:23<25:19,  8.54s/it]08/04/2024 22:40:32 - INFO - __main__ -   Step: 5534, LR: 1.7215277608891267e-08, Loss: 0.07586044073104858
2024-08-05T05:40:41.479229922Z 
 97%|█████████▋| 5535/5712 [13:02:32<25:35,  8.68s/it]08/04/2024 22:40:41 - INFO - __main__ -   Step: 5535, LR: 1.711799897857438e-08, Loss: 0.07983502000570297
2024-08-05T05:40:50.010001668Z 
 97%|█████████▋| 5536/5712 [13:02:41<25:19,  8.63s/it]08/04/2024 22:40:50 - INFO - __main__ -   Step: 5536, LR: 1.7020720348257494e-08, Loss: 0.07669071853160858
2024-08-05T05:40:58.321628554Z 
 97%|█████████▋| 5537/5712 [13:02:49<24:53,  8.54s/it]08/04/2024 22:40:58 - INFO - __main__ -   Step: 5537, LR: 1.692344171794061e-08, Loss: 0.07609446346759796
2024-08-05T05:41:07.168413067Z 
 97%|█████████▋| 5538/5712 [13:02:58<25:01,  8.63s/it]08/04/2024 22:41:07 - INFO - __main__ -   Step: 5538, LR: 1.6826163087623726e-08, Loss: 0.034318480640649796
2024-08-05T05:41:15.988631619Z 
 97%|█████████▋| 5539/5712 [13:03:07<25:02,  8.69s/it]08/04/2024 22:41:15 - INFO - __main__ -   Step: 5539, LR: 1.672888445730684e-08, Loss: 0.0619066059589386
2024-08-05T05:41:24.769296667Z 
 97%|█████████▋| 5540/5712 [13:03:15<24:58,  8.72s/it]08/04/2024 22:41:24 - INFO - __main__ -   Step: 5540, LR: 1.6631605826989957e-08, Loss: 0.08321144431829453
2024-08-05T05:41:32.817233797Z 
 97%|█████████▋| 5541/5712 [13:03:23<24:16,  8.51s/it]08/04/2024 22:41:32 - INFO - __main__ -   Step: 5541, LR: 1.6534327196673072e-08, Loss: 0.06917780637741089
2024-08-05T05:41:40.911828426Z 
 97%|█████████▋| 5542/5712 [13:03:32<23:46,  8.39s/it]08/04/2024 22:41:40 - INFO - __main__ -   Step: 5542, LR: 1.6437048566356185e-08, Loss: 0.04274029657244682
2024-08-05T05:41:49.363890734Z 
 97%|█████████▋| 5543/5712 [13:03:40<23:40,  8.41s/it]08/04/2024 22:41:49 - INFO - __main__ -   Step: 5543, LR: 1.63397699360393e-08, Loss: 0.05570049583911896
2024-08-05T05:41:57.679916248Z 
 97%|█████████▋| 5544/5712 [13:03:48<23:27,  8.38s/it]08/04/2024 22:41:57 - INFO - __main__ -   Step: 5544, LR: 1.6242491305722413e-08, Loss: 0.03429797291755676
2024-08-05T05:42:06.230450227Z 
 97%|█████████▋| 5545/5712 [13:03:57<23:28,  8.43s/it]08/04/2024 22:42:06 - INFO - __main__ -   Step: 5545, LR: 1.6145212675405528e-08, Loss: 0.09791349619626999
2024-08-05T05:42:14.656001273Z 
 97%|█████████▋| 5546/5712 [13:04:05<23:19,  8.43s/it]08/04/2024 22:42:14 - INFO - __main__ -   Step: 5546, LR: 1.6047934045088644e-08, Loss: 0.025801725685596466
2024-08-05T05:42:23.975128002Z 
 97%|█████████▋| 5547/5712 [13:04:15<23:54,  8.70s/it]08/04/2024 22:42:23 - INFO - __main__ -   Step: 5547, LR: 1.595065541477176e-08, Loss: 0.07642053067684174
2024-08-05T05:42:32.749837494Z 
 97%|█████████▋| 5548/5712 [13:04:23<23:50,  8.72s/it]08/04/2024 22:42:32 - INFO - __main__ -   Step: 5548, LR: 1.5853376784454875e-08, Loss: 0.046873271465301514
2024-08-05T05:42:41.274240155Z 
 97%|█████████▋| 5549/5712 [13:04:32<23:31,  8.66s/it]08/04/2024 22:42:41 - INFO - __main__ -   Step: 5549, LR: 1.575609815413799e-08, Loss: 0.07114431262016296
2024-08-05T05:42:49.340097040Z 
 97%|█████████▋| 5550/5712 [13:04:40<22:54,  8.48s/it]08/04/2024 22:42:49 - INFO - __main__ -   Step: 5550, LR: 1.5658819523821106e-08, Loss: 0.05591827630996704
2024-08-05T05:42:57.776199905Z 
 97%|█████████▋| 5551/5712 [13:04:48<22:43,  8.47s/it]08/04/2024 22:42:57 - INFO - __main__ -   Step: 5551, LR: 1.556154089350422e-08, Loss: 0.05247378721833229
2024-08-05T05:43:05.833069932Z 
 97%|█████████▋| 5552/5712 [13:04:56<22:15,  8.35s/it]08/04/2024 22:43:05 - INFO - __main__ -   Step: 5552, LR: 1.5464262263187334e-08, Loss: 0.06843475997447968
2024-08-05T05:43:14.239282573Z 
 97%|█████████▋| 5553/5712 [13:05:05<22:09,  8.36s/it]08/04/2024 22:43:14 - INFO - __main__ -   Step: 5553, LR: 1.536698363287045e-08, Loss: 0.05841001495718956
2024-08-05T05:43:22.770505789Z 
 97%|█████████▋| 5554/5712 [13:05:13<22:09,  8.41s/it]08/04/2024 22:43:22 - INFO - __main__ -   Step: 5554, LR: 1.5269705002553565e-08, Loss: 0.11659691482782364
2024-08-05T05:43:31.146445658Z 
 97%|█████████▋| 5555/5712 [13:05:22<21:59,  8.40s/it]08/04/2024 22:43:31 - INFO - __main__ -   Step: 5555, LR: 1.5172426372236677e-08, Loss: 0.10854904353618622
2024-08-05T05:43:39.836525398Z 
 97%|█████████▋| 5556/5712 [13:05:30<22:04,  8.49s/it]08/04/2024 22:43:39 - INFO - __main__ -   Step: 5556, LR: 1.5075147741919793e-08, Loss: 0.12719891965389252
2024-08-05T05:43:48.382843829Z 
 97%|█████████▋| 5557/5712 [13:05:39<21:58,  8.51s/it]08/04/2024 22:43:48 - INFO - __main__ -   Step: 5557, LR: 1.497786911160291e-08, Loss: 0.0421520434319973
2024-08-05T05:43:56.399089949Z 
 97%|█████████▋| 5558/5712 [13:05:47<21:27,  8.36s/it]08/04/2024 22:43:56 - INFO - __main__ -   Step: 5558, LR: 1.4880590481286023e-08, Loss: 0.03986872732639313
2024-08-05T05:44:04.708922554Z 
 97%|█████████▋| 5559/5712 [13:05:55<21:16,  8.34s/it]08/04/2024 22:44:04 - INFO - __main__ -   Step: 5559, LR: 1.4783311850969136e-08, Loss: 0.09116105735301971
2024-08-05T05:44:13.119811034Z 
 97%|█████████▋| 5560/5712 [13:06:04<21:11,  8.36s/it]08/04/2024 22:44:13 - INFO - __main__ -   Step: 5560, LR: 1.4686033220652252e-08, Loss: 0.10299452394247055
2024-08-05T05:44:21.057397820Z 
 97%|█████████▋| 5561/5712 [13:06:12<20:43,  8.24s/it]08/04/2024 22:44:21 - INFO - __main__ -   Step: 5561, LR: 1.4588754590335368e-08, Loss: 0.04736551269888878
2024-08-05T05:44:29.704053712Z 
 97%|█████████▋| 5562/5712 [13:06:20<20:53,  8.36s/it]08/04/2024 22:44:29 - INFO - __main__ -   Step: 5562, LR: 1.4491475960018483e-08, Loss: 0.06172000616788864
2024-08-05T05:44:38.324219774Z 
 97%|█████████▋| 5563/5712 [13:06:29<20:57,  8.44s/it]08/04/2024 22:44:38 - INFO - __main__ -   Step: 5563, LR: 1.4394197329701597e-08, Loss: 0.038365207612514496
2024-08-05T05:44:47.968922791Z 
 97%|█████████▋| 5564/5712 [13:06:39<21:42,  8.80s/it]08/04/2024 22:44:47 - INFO - __main__ -   Step: 5564, LR: 1.4296918699384711e-08, Loss: 0.11938756704330444
2024-08-05T05:44:56.847119339Z 
 97%|█████████▋| 5565/5712 [13:06:47<21:37,  8.82s/it]08/04/2024 22:44:56 - INFO - __main__ -   Step: 5565, LR: 1.4199640069067827e-08, Loss: 0.0476161390542984
2024-08-05T05:45:05.142535106Z 
 97%|█████████▋| 5566/5712 [13:06:56<21:05,  8.67s/it]08/04/2024 22:45:05 - INFO - __main__ -   Step: 5566, LR: 1.4102361438750942e-08, Loss: 0.07789839804172516
2024-08-05T05:45:13.362846374Z 
 97%|█████████▋| 5567/5712 [13:07:04<20:37,  8.53s/it]08/04/2024 22:45:13 - INFO - __main__ -   Step: 5567, LR: 1.4005082808434058e-08, Loss: 0.09680572152137756
2024-08-05T05:45:21.432357544Z 
 97%|█████████▋| 5568/5712 [13:07:12<20:08,  8.39s/it]08/04/2024 22:45:21 - INFO - __main__ -   Step: 5568, LR: 1.390780417811717e-08, Loss: 0.03700752183794975
2024-08-05T05:45:29.946782223Z 
 97%|█████████▋| 5569/5712 [13:07:21<20:05,  8.43s/it]08/04/2024 22:45:29 - INFO - __main__ -   Step: 5569, LR: 1.3810525547800286e-08, Loss: 0.09081151336431503
2024-08-05T05:45:38.128793402Z 
 98%|█████████▊| 5570/5712 [13:07:29<19:46,  8.36s/it]08/04/2024 22:45:38 - INFO - __main__ -   Step: 5570, LR: 1.3713246917483401e-08, Loss: 0.07073813676834106
2024-08-05T05:45:46.807356664Z 
 98%|█████████▊| 5571/5712 [13:07:37<19:51,  8.45s/it]08/04/2024 22:45:46 - INFO - __main__ -   Step: 5571, LR: 1.3615968287166517e-08, Loss: 0.08677128702402115
2024-08-05T05:45:55.191299050Z 
 98%|█████████▊| 5572/5712 [13:07:46<19:40,  8.43s/it]08/04/2024 22:45:55 - INFO - __main__ -   Step: 5572, LR: 1.3518689656849633e-08, Loss: 0.04549989104270935
2024-08-05T05:46:03.908199567Z 
 98%|█████████▊| 5573/5712 [13:07:55<19:43,  8.52s/it]08/04/2024 22:46:03 - INFO - __main__ -   Step: 5573, LR: 1.3421411026532745e-08, Loss: 0.0835266262292862
2024-08-05T05:46:12.208371291Z 
 98%|█████████▊| 5574/5712 [13:08:03<19:26,  8.45s/it]08/04/2024 22:46:12 - INFO - __main__ -   Step: 5574, LR: 1.332413239621586e-08, Loss: 0.07949195802211761
2024-08-05T05:46:20.779695771Z 
 98%|█████████▊| 5575/5712 [13:08:11<19:22,  8.49s/it]08/04/2024 22:46:20 - INFO - __main__ -   Step: 5575, LR: 1.3226853765898976e-08, Loss: 0.04226331412792206
2024-08-05T05:46:28.900308612Z 
 98%|█████████▊| 5576/5712 [13:08:20<18:59,  8.38s/it]08/04/2024 22:46:28 - INFO - __main__ -   Step: 5576, LR: 1.3129575135582092e-08, Loss: 0.05903464928269386
2024-08-05T05:46:37.482525845Z 
 98%|█████████▊| 5577/5712 [13:08:28<18:59,  8.44s/it]08/04/2024 22:46:37 - INFO - __main__ -   Step: 5577, LR: 1.3032296505265204e-08, Loss: 0.0657009482383728
2024-08-05T05:46:45.583637495Z 
 98%|█████████▊| 5578/5712 [13:08:36<18:37,  8.34s/it]08/04/2024 22:46:45 - INFO - __main__ -   Step: 5578, LR: 1.293501787494832e-08, Loss: 0.12740755081176758
2024-08-05T05:46:53.829082763Z 
 98%|█████████▊| 5579/5712 [13:08:44<18:25,  8.31s/it]08/04/2024 22:46:53 - INFO - __main__ -   Step: 5579, LR: 1.2837739244631435e-08, Loss: 0.070771723985672
2024-08-05T05:47:02.041313148Z 
 98%|█████████▊| 5580/5712 [13:08:53<18:13,  8.28s/it]08/04/2024 22:47:02 - INFO - __main__ -   Step: 5580, LR: 1.274046061431455e-08, Loss: 0.09818893671035767
2024-08-05T05:47:11.712707260Z 
 98%|█████████▊| 5581/5712 [13:09:02<18:59,  8.70s/it]08/04/2024 22:47:11 - INFO - __main__ -   Step: 5581, LR: 1.2643181983997665e-08, Loss: 0.06598403304815292
2024-08-05T05:47:19.953344536Z 
 98%|█████████▊| 5582/5712 [13:09:11<18:32,  8.56s/it]08/04/2024 22:47:19 - INFO - __main__ -   Step: 5582, LR: 1.2545903353680778e-08, Loss: 0.07974685728549957
2024-08-05T05:47:28.330896920Z 
 98%|█████████▊| 5583/5712 [13:09:19<18:17,  8.51s/it]08/04/2024 22:47:28 - INFO - __main__ -   Step: 5583, LR: 1.2448624723363894e-08, Loss: 0.06610307842493057
2024-08-05T05:47:37.304661037Z 
 98%|█████████▊| 5584/5712 [13:09:28<18:26,  8.65s/it]08/04/2024 22:47:37 - INFO - __main__ -   Step: 5584, LR: 1.235134609304701e-08, Loss: 0.08419138193130493
2024-08-05T05:47:45.291145085Z 
 98%|█████████▊| 5585/5712 [13:09:36<17:52,  8.45s/it]08/04/2024 22:47:45 - INFO - __main__ -   Step: 5585, LR: 1.2254067462730125e-08, Loss: 0.04429402947425842
2024-08-05T05:47:53.787068418Z 
 98%|█████████▊| 5586/5712 [13:09:44<17:46,  8.46s/it]08/04/2024 22:47:53 - INFO - __main__ -   Step: 5586, LR: 1.2156788832413239e-08, Loss: 0.0585252046585083
2024-08-05T05:48:02.107637142Z 
 98%|█████████▊| 5587/5712 [13:09:53<17:32,  8.42s/it]08/04/2024 22:48:02 - INFO - __main__ -   Step: 5587, LR: 1.2059510202096353e-08, Loss: 0.06146400421857834
2024-08-05T05:48:10.782993717Z 
 98%|█████████▊| 5588/5712 [13:10:01<17:33,  8.50s/it]08/04/2024 22:48:10 - INFO - __main__ -   Step: 5588, LR: 1.1962231571779469e-08, Loss: 0.05915028229355812
2024-08-05T05:48:19.195010806Z 
 98%|█████████▊| 5589/5712 [13:10:10<17:21,  8.47s/it]08/04/2024 22:48:19 - INFO - __main__ -   Step: 5589, LR: 1.1864952941462584e-08, Loss: 0.09056355059146881
2024-08-05T05:48:27.839992471Z 
 98%|█████████▊| 5590/5712 [13:10:18<17:19,  8.52s/it]08/04/2024 22:48:27 - INFO - __main__ -   Step: 5590, LR: 1.1767674311145698e-08, Loss: 0.04144858568906784
2024-08-05T05:48:35.836692408Z 
 98%|█████████▊| 5591/5712 [13:10:26<16:52,  8.37s/it]08/04/2024 22:48:35 - INFO - __main__ -   Step: 5591, LR: 1.1670395680828814e-08, Loss: 0.0320395864546299
2024-08-05T05:48:44.210227288Z 
 98%|█████████▊| 5592/5712 [13:10:35<16:44,  8.37s/it]08/04/2024 22:48:44 - INFO - __main__ -   Step: 5592, LR: 1.1573117050511928e-08, Loss: 0.033597007393836975
2024-08-05T05:48:52.680435406Z 
 98%|█████████▊| 5593/5712 [13:10:43<16:39,  8.40s/it]08/04/2024 22:48:52 - INFO - __main__ -   Step: 5593, LR: 1.1475838420195043e-08, Loss: 0.09161576628684998
2024-08-05T05:49:01.117205689Z 
 98%|█████████▊| 5594/5712 [13:10:52<16:32,  8.41s/it]08/04/2024 22:49:01 - INFO - __main__ -   Step: 5594, LR: 1.1378559789878159e-08, Loss: 0.06256259232759476
2024-08-05T05:49:09.671627844Z 
 98%|█████████▊| 5595/5712 [13:11:00<16:29,  8.45s/it]08/04/2024 22:49:09 - INFO - __main__ -   Step: 5595, LR: 1.1281281159561273e-08, Loss: 0.015315060503780842
2024-08-05T05:49:18.050986261Z 
 98%|█████████▊| 5596/5712 [13:11:09<16:18,  8.43s/it]08/04/2024 22:49:18 - INFO - __main__ -   Step: 5596, LR: 1.1184002529244387e-08, Loss: 0.029181763529777527
2024-08-05T05:49:26.552765813Z 
 98%|█████████▊| 5597/5712 [13:11:17<16:12,  8.45s/it]08/04/2024 22:49:26 - INFO - __main__ -   Step: 5597, LR: 1.1086723898927502e-08, Loss: 0.037407174706459045
2024-08-05T05:49:35.856099503Z 
 98%|█████████▊| 5598/5712 [13:11:27<16:32,  8.71s/it]08/04/2024 22:49:35 - INFO - __main__ -   Step: 5598, LR: 1.0989445268610618e-08, Loss: 0.06533727794885635
2024-08-05T05:49:44.391983879Z 
 98%|█████████▊| 5599/5712 [13:11:35<16:18,  8.66s/it]08/04/2024 22:49:44 - INFO - __main__ -   Step: 5599, LR: 1.0892166638293732e-08, Loss: 0.06282825767993927
2024-08-05T05:49:52.561323469Z 
 98%|█████████▊| 5600/5712 [13:11:43<15:53,  8.51s/it]08/04/2024 22:49:52 - INFO - __main__ -   Step: 5600, LR: 1.0794888007976847e-08, Loss: 0.04408363997936249
2024-08-05T05:50:00.965286467Z 
 98%|█████████▊| 5601/5712 [13:11:52<15:41,  8.48s/it]08/04/2024 22:50:00 - INFO - __main__ -   Step: 5601, LR: 1.0697609377659961e-08, Loss: 0.1669832170009613
2024-08-05T05:50:09.243583234Z 
 98%|█████████▊| 5602/5712 [13:12:00<15:26,  8.42s/it]08/04/2024 22:50:09 - INFO - __main__ -   Step: 5602, LR: 1.0600330747343077e-08, Loss: 0.07165227830410004
2024-08-05T05:50:17.432684780Z 
 98%|█████████▊| 5603/5712 [13:12:08<15:10,  8.35s/it]08/04/2024 22:50:17 - INFO - __main__ -   Step: 5603, LR: 1.0503052117026193e-08, Loss: 0.06188585236668587
2024-08-05T05:50:25.938981805Z 
 98%|█████████▊| 5604/5712 [13:12:17<15:06,  8.40s/it]08/04/2024 22:50:25 - INFO - __main__ -   Step: 5604, LR: 1.0405773486709307e-08, Loss: 0.07504280656576157
2024-08-05T05:50:34.381203134Z 
 98%|█████████▊| 5605/5712 [13:12:25<14:59,  8.41s/it]08/04/2024 22:50:34 - INFO - __main__ -   Step: 5605, LR: 1.0308494856392422e-08, Loss: 0.0334530770778656
2024-08-05T05:50:43.180061261Z 
 98%|█████████▊| 5606/5712 [13:12:34<15:03,  8.53s/it]08/04/2024 22:50:43 - INFO - __main__ -   Step: 5606, LR: 1.0211216226075536e-08, Loss: 0.1435604691505432
2024-08-05T05:50:51.628064106Z 
 98%|█████████▊| 5607/5712 [13:12:42<14:52,  8.50s/it]08/04/2024 22:50:51 - INFO - __main__ -   Step: 5607, LR: 1.0113937595758652e-08, Loss: 0.03783651441335678
2024-08-05T05:50:59.949668149Z 
 98%|█████████▊| 5608/5712 [13:12:51<14:38,  8.45s/it]08/04/2024 22:50:59 - INFO - __main__ -   Step: 5608, LR: 1.0016658965441766e-08, Loss: 0.07145564258098602
2024-08-05T05:51:07.907212235Z 
 98%|█████████▊| 5609/5712 [13:12:59<14:15,  8.30s/it]08/04/2024 22:51:07 - INFO - __main__ -   Step: 5609, LR: 9.919380335124881e-09, Loss: 0.06974905729293823
2024-08-05T05:51:16.281394809Z 
 98%|█████████▊| 5610/5712 [13:13:07<14:08,  8.32s/it]08/04/2024 22:51:16 - INFO - __main__ -   Step: 5610, LR: 9.822101704807997e-09, Loss: 0.10361313074827194
2024-08-05T05:51:24.554808828Z 
 98%|█████████▊| 5611/5712 [13:13:15<13:59,  8.31s/it]08/04/2024 22:51:24 - INFO - __main__ -   Step: 5611, LR: 9.72482307449111e-09, Loss: 0.05484819784760475
2024-08-05T05:51:33.333475616Z 
 98%|█████████▊| 5612/5712 [13:13:24<14:04,  8.45s/it]08/04/2024 22:51:33 - INFO - __main__ -   Step: 5612, LR: 9.627544444174225e-09, Loss: 0.06129232421517372
2024-08-05T05:51:41.643830336Z 
 98%|█████████▊| 5613/5712 [13:13:32<13:52,  8.41s/it]08/04/2024 22:51:41 - INFO - __main__ -   Step: 5613, LR: 9.53026581385734e-09, Loss: 0.13953900337219238
2024-08-05T05:51:49.996379354Z 
 98%|█████████▊| 5614/5712 [13:13:41<13:42,  8.39s/it]08/04/2024 22:51:49 - INFO - __main__ -   Step: 5614, LR: 9.432987183540456e-09, Loss: 0.06547069549560547
2024-08-05T05:51:59.638138027Z 
 98%|█████████▊| 5615/5712 [13:13:50<14:10,  8.77s/it]08/04/2024 22:51:59 - INFO - __main__ -   Step: 5615, LR: 9.33570855322357e-09, Loss: 0.07728435844182968
2024-08-05T05:52:08.110192235Z 
 98%|█████████▊| 5616/5712 [13:13:59<13:53,  8.68s/it]08/04/2024 22:52:08 - INFO - __main__ -   Step: 5616, LR: 9.238429922906685e-09, Loss: 0.1361255943775177
2024-08-05T05:52:16.105268652Z 
 98%|█████████▊| 5617/5712 [13:14:07<13:24,  8.47s/it]08/04/2024 22:52:16 - INFO - __main__ -   Step: 5617, LR: 9.1411512925898e-09, Loss: 0.06753053516149521
2024-08-05T05:52:24.606004773Z 
 98%|█████████▊| 5618/5712 [13:14:15<13:17,  8.48s/it]08/04/2024 22:52:24 - INFO - __main__ -   Step: 5618, LR: 9.043872662272915e-09, Loss: 0.058664366602897644
2024-08-05T05:52:32.790333032Z 
 98%|█████████▊| 5619/5712 [13:14:23<13:00,  8.39s/it]08/04/2024 22:52:32 - INFO - __main__ -   Step: 5619, LR: 8.94659403195603e-09, Loss: 0.03882469981908798
2024-08-05T05:52:41.513823327Z 
 98%|█████████▊| 5620/5712 [13:14:32<13:01,  8.49s/it]08/04/2024 22:52:41 - INFO - __main__ -   Step: 5620, LR: 8.849315401639144e-09, Loss: 0.16010375320911407
2024-08-05T05:52:49.949843430Z 
 98%|█████████▊| 5621/5712 [13:14:41<12:51,  8.47s/it]08/04/2024 22:52:49 - INFO - __main__ -   Step: 5621, LR: 8.752036771322258e-09, Loss: 0.15801066160202026
2024-08-05T05:52:58.327490909Z 
 98%|█████████▊| 5622/5712 [13:14:49<12:40,  8.45s/it]08/04/2024 22:52:58 - INFO - __main__ -   Step: 5622, LR: 8.654758141005374e-09, Loss: 0.04870021343231201
2024-08-05T05:53:07.121677162Z 
 98%|█████████▊| 5623/5712 [13:14:58<12:40,  8.55s/it]08/04/2024 22:53:07 - INFO - __main__ -   Step: 5623, LR: 8.55747951068849e-09, Loss: 0.04762527346611023
2024-08-05T05:53:16.141279645Z 
 98%|█████████▊| 5624/5712 [13:15:07<12:44,  8.69s/it]08/04/2024 22:53:16 - INFO - __main__ -   Step: 5624, LR: 8.460200880371605e-09, Loss: 0.024660194292664528
2024-08-05T05:53:24.407305799Z 
 98%|█████████▊| 5625/5712 [13:15:15<12:25,  8.56s/it]08/04/2024 22:53:24 - INFO - __main__ -   Step: 5625, LR: 8.362922250054719e-09, Loss: 0.03904936462640762
2024-08-05T05:53:32.552236977Z 
 98%|█████████▊| 5626/5712 [13:15:23<12:05,  8.44s/it]08/04/2024 22:53:32 - INFO - __main__ -   Step: 5626, LR: 8.265643619737833e-09, Loss: 0.1272471845149994
2024-08-05T05:53:40.493144539Z 
 99%|█████████▊| 5627/5712 [13:15:31<11:44,  8.29s/it]08/04/2024 22:53:40 - INFO - __main__ -   Step: 5627, LR: 8.168364989420949e-09, Loss: 0.09317341446876526
2024-08-05T05:53:48.902803474Z 
 99%|█████████▊| 5628/5712 [13:15:40<11:39,  8.32s/it]08/04/2024 22:53:48 - INFO - __main__ -   Step: 5628, LR: 8.071086359104064e-09, Loss: 0.07343835383653641
2024-08-05T05:53:57.172572385Z 
 99%|█████████▊| 5629/5712 [13:15:48<11:29,  8.31s/it]08/04/2024 22:53:57 - INFO - __main__ -   Step: 5629, LR: 7.97380772878718e-09, Loss: 0.07883131504058838
2024-08-05T05:54:05.604087220Z 
 99%|█████████▊| 5630/5712 [13:15:56<11:24,  8.35s/it]08/04/2024 22:54:05 - INFO - __main__ -   Step: 5630, LR: 7.876529098470292e-09, Loss: 0.06947624683380127
2024-08-05T05:54:14.297981386Z 
 99%|█████████▊| 5631/5712 [13:16:05<11:24,  8.45s/it]08/04/2024 22:54:14 - INFO - __main__ -   Step: 5631, LR: 7.779250468153408e-09, Loss: 0.06552411615848541
2024-08-05T05:54:24.049669695Z 
 99%|█████████▊| 5632/5712 [13:16:15<11:47,  8.84s/it]08/04/2024 22:54:24 - INFO - __main__ -   Step: 5632, LR: 7.681971837836523e-09, Loss: 0.0760883167386055
2024-08-05T05:54:33.113350104Z 
 99%|█████████▊| 5633/5712 [13:16:24<11:43,  8.91s/it]08/04/2024 22:54:33 - INFO - __main__ -   Step: 5633, LR: 7.584693207519637e-09, Loss: 0.102166086435318
2024-08-05T05:54:41.063599069Z 
 99%|█████████▊| 5634/5712 [13:16:32<11:12,  8.62s/it]08/04/2024 22:54:41 - INFO - __main__ -   Step: 5634, LR: 7.487414577202753e-09, Loss: 0.0610928013920784
2024-08-05T05:54:49.620675874Z 
 99%|█████████▊| 5635/5712 [13:16:40<11:02,  8.60s/it]08/04/2024 22:54:49 - INFO - __main__ -   Step: 5635, LR: 7.390135946885868e-09, Loss: 0.10950648784637451
2024-08-05T05:54:57.734308861Z 
 99%|█████████▊| 5636/5712 [13:16:48<10:42,  8.46s/it]08/04/2024 22:54:57 - INFO - __main__ -   Step: 5636, LR: 7.292857316568982e-09, Loss: 0.08065849542617798
2024-08-05T05:55:06.323753373Z 
 99%|█████████▊| 5637/5712 [13:16:57<10:37,  8.50s/it]08/04/2024 22:55:06 - INFO - __main__ -   Step: 5637, LR: 7.195578686252098e-09, Loss: 0.10205882787704468
2024-08-05T05:55:15.208282140Z 
 99%|█████████▊| 5638/5712 [13:17:06<10:37,  8.61s/it]08/04/2024 22:55:15 - INFO - __main__ -   Step: 5638, LR: 7.098300055935212e-09, Loss: 0.06359019875526428
2024-08-05T05:55:23.708094382Z 
 99%|█████████▊| 5639/5712 [13:17:14<10:26,  8.58s/it]08/04/2024 22:55:23 - INFO - __main__ -   Step: 5639, LR: 7.001021425618327e-09, Loss: 0.0908006802201271
2024-08-05T05:55:32.360320698Z 
 99%|█████████▊| 5640/5712 [13:17:23<10:19,  8.60s/it]08/04/2024 22:55:32 - INFO - __main__ -   Step: 5640, LR: 6.903742795301441e-09, Loss: 0.051016490906476974
2024-08-05T05:55:40.965192647Z 
 99%|█████████▉| 5641/5712 [13:17:32<10:10,  8.60s/it]08/04/2024 22:55:40 - INFO - __main__ -   Step: 5641, LR: 6.806464164984557e-09, Loss: 0.03374733775854111
2024-08-05T05:55:49.141360404Z 
 99%|█████████▉| 5642/5712 [13:17:40<09:53,  8.47s/it]08/04/2024 22:55:49 - INFO - __main__ -   Step: 5642, LR: 6.709185534667672e-09, Loss: 0.051580142229795456
2024-08-05T05:55:57.396559941Z 
 99%|█████████▉| 5643/5712 [13:17:48<09:40,  8.41s/it]08/04/2024 22:55:57 - INFO - __main__ -   Step: 5643, LR: 6.611906904350786e-09, Loss: 0.06196065619587898
2024-08-05T05:56:05.941086115Z 
 99%|█████████▉| 5644/5712 [13:17:57<09:34,  8.45s/it]08/04/2024 22:56:05 - INFO - __main__ -   Step: 5644, LR: 6.514628274033901e-09, Loss: 0.07141086459159851
2024-08-05T05:56:14.286163907Z 
 99%|█████████▉| 5645/5712 [13:18:05<09:24,  8.42s/it]08/04/2024 22:56:14 - INFO - __main__ -   Step: 5645, LR: 6.417349643717016e-09, Loss: 0.053045302629470825
2024-08-05T05:56:22.210747859Z 
 99%|█████████▉| 5646/5712 [13:18:13<09:05,  8.27s/it]08/04/2024 22:56:22 - INFO - __main__ -   Step: 5646, LR: 6.3200710134001315e-09, Loss: 0.0736321359872818
2024-08-05T05:56:30.611508274Z 
 99%|█████████▉| 5647/5712 [13:18:21<09:00,  8.31s/it]08/04/2024 22:56:30 - INFO - __main__ -   Step: 5647, LR: 6.2227923830832455e-09, Loss: 0.06561204791069031
2024-08-05T05:56:38.991817752Z 
 99%|█████████▉| 5648/5712 [13:18:30<08:53,  8.33s/it]08/04/2024 22:56:38 - INFO - __main__ -   Step: 5648, LR: 6.125513752766361e-09, Loss: 0.07625466585159302
2024-08-05T05:56:48.585485102Z 
 99%|█████████▉| 5649/5712 [13:18:39<09:08,  8.71s/it]08/04/2024 22:56:48 - INFO - __main__ -   Step: 5649, LR: 6.028235122449476e-09, Loss: 0.0896771103143692
2024-08-05T05:56:56.714490171Z 
 99%|█████████▉| 5650/5712 [13:18:47<08:49,  8.54s/it]08/04/2024 22:56:56 - INFO - __main__ -   Step: 5650, LR: 5.9309564921325906e-09, Loss: 0.07003083825111389
2024-08-05T05:57:04.881818586Z 
 99%|█████████▉| 5651/5712 [13:18:56<08:33,  8.42s/it]08/04/2024 22:57:04 - INFO - __main__ -   Step: 5651, LR: 5.833677861815705e-09, Loss: 0.06845619529485703
2024-08-05T05:57:13.114911417Z 
 99%|█████████▉| 5652/5712 [13:19:04<08:22,  8.37s/it]08/04/2024 22:57:13 - INFO - __main__ -   Step: 5652, LR: 5.73639923149882e-09, Loss: 0.0600106380879879
2024-08-05T05:57:21.439887324Z 
 99%|█████████▉| 5653/5712 [13:19:12<08:12,  8.35s/it]08/04/2024 22:57:21 - INFO - __main__ -   Step: 5653, LR: 5.639120601181935e-09, Loss: 0.08094173669815063
2024-08-05T05:57:29.734934652Z 
 99%|█████████▉| 5654/5712 [13:19:20<08:03,  8.34s/it]08/04/2024 22:57:29 - INFO - __main__ -   Step: 5654, LR: 5.5418419708650504e-09, Loss: 0.049871038645505905
2024-08-05T05:57:37.975333304Z 
 99%|█████████▉| 5655/5712 [13:19:29<07:53,  8.31s/it]08/04/2024 22:57:37 - INFO - __main__ -   Step: 5655, LR: 5.444563340548164e-09, Loss: 0.059068068861961365
2024-08-05T05:57:46.997393959Z 
 99%|█████████▉| 5656/5712 [13:19:38<07:57,  8.52s/it]08/04/2024 22:57:46 - INFO - __main__ -   Step: 5656, LR: 5.34728471023128e-09, Loss: 0.08390351384878159
2024-08-05T05:57:55.307437066Z 
 99%|█████████▉| 5657/5712 [13:19:46<07:45,  8.46s/it]08/04/2024 22:57:55 - INFO - __main__ -   Step: 5657, LR: 5.250006079914395e-09, Loss: 0.15137358009815216
2024-08-05T05:58:03.962107862Z 
 99%|█████████▉| 5658/5712 [13:19:55<07:39,  8.52s/it]08/04/2024 22:58:03 - INFO - __main__ -   Step: 5658, LR: 5.1527274495975095e-09, Loss: 0.09031777083873749
2024-08-05T05:58:11.867982860Z 
 99%|█████████▉| 5659/5712 [13:20:03<07:21,  8.33s/it]08/04/2024 22:58:11 - INFO - __main__ -   Step: 5659, LR: 5.055448819280624e-09, Loss: 0.07945504784584045
2024-08-05T05:58:20.440994848Z 
 99%|█████████▉| 5660/5712 [13:20:11<07:17,  8.41s/it]08/04/2024 22:58:20 - INFO - __main__ -   Step: 5660, LR: 4.958170188963739e-09, Loss: 0.08112490177154541
2024-08-05T05:58:28.836996000Z 
 99%|█████████▉| 5661/5712 [13:20:19<07:08,  8.40s/it]08/04/2024 22:58:28 - INFO - __main__ -   Step: 5661, LR: 4.860891558646855e-09, Loss: 0.06524112820625305
2024-08-05T05:58:37.078677590Z 
 99%|█████████▉| 5662/5712 [13:20:28<06:57,  8.35s/it]08/04/2024 22:58:37 - INFO - __main__ -   Step: 5662, LR: 4.7636129283299685e-09, Loss: 0.04841693118214607
2024-08-05T05:58:45.630552206Z 
 99%|█████████▉| 5663/5712 [13:20:36<06:52,  8.41s/it]08/04/2024 22:58:45 - INFO - __main__ -   Step: 5663, LR: 4.666334298013084e-09, Loss: 0.055319469422101974
2024-08-05T05:58:54.053698426Z 
 99%|█████████▉| 5664/5712 [13:20:45<06:43,  8.42s/it]08/04/2024 22:58:54 - INFO - __main__ -   Step: 5664, LR: 4.569055667696198e-09, Loss: 0.07868802547454834
2024-08-05T05:59:02.911307220Z 
 99%|█████████▉| 5665/5712 [13:20:54<06:41,  8.55s/it]08/04/2024 22:59:02 - INFO - __main__ -   Step: 5665, LR: 4.471777037379314e-09, Loss: 0.07258389890193939
2024-08-05T05:59:12.245220903Z 
 99%|█████████▉| 5666/5712 [13:21:03<06:44,  8.78s/it]08/04/2024 22:59:12 - INFO - __main__ -   Step: 5666, LR: 4.374498407062428e-09, Loss: 0.037016820162534714
2024-08-05T05:59:20.811731550Z 
 99%|█████████▉| 5667/5712 [13:21:11<06:32,  8.72s/it]08/04/2024 22:59:20 - INFO - __main__ -   Step: 5667, LR: 4.277219776745543e-09, Loss: 0.038994114845991135
2024-08-05T05:59:28.961736681Z 
 99%|█████████▉| 5668/5712 [13:21:20<06:16,  8.55s/it]08/04/2024 22:59:28 - INFO - __main__ -   Step: 5668, LR: 4.179941146428659e-09, Loss: 0.0469529964029789
2024-08-05T05:59:37.393448534Z 
 99%|█████████▉| 5669/5712 [13:21:28<06:06,  8.51s/it]08/04/2024 22:59:37 - INFO - __main__ -   Step: 5669, LR: 4.082662516111773e-09, Loss: 0.06427833437919617
2024-08-05T05:59:45.630388504Z 
 99%|█████████▉| 5670/5712 [13:21:36<05:54,  8.43s/it]08/04/2024 22:59:45 - INFO - __main__ -   Step: 5670, LR: 3.985383885794888e-09, Loss: 0.03420384228229523
2024-08-05T05:59:54.024262344Z 
 99%|█████████▉| 5671/5712 [13:21:45<05:45,  8.42s/it]08/04/2024 22:59:54 - INFO - __main__ -   Step: 5671, LR: 3.888105255478002e-09, Loss: 0.05094783753156662
2024-08-05T06:00:02.408321783Z 
 99%|█████████▉| 5672/5712 [13:21:53<05:36,  8.41s/it]08/04/2024 23:00:02 - INFO - __main__ -   Step: 5672, LR: 3.790826625161118e-09, Loss: 0.05808119475841522
2024-08-05T06:00:11.875478936Z 
 99%|█████████▉| 5673/5712 [13:22:03<05:40,  8.73s/it]08/04/2024 23:00:11 - INFO - __main__ -   Step: 5673, LR: 3.6935479948442326e-09, Loss: 0.0883137434720993
2024-08-05T06:00:20.548619594Z 
 99%|█████████▉| 5674/5712 [13:22:11<05:30,  8.71s/it]08/04/2024 23:00:20 - INFO - __main__ -   Step: 5674, LR: 3.5962693645273473e-09, Loss: 0.07472231984138489
2024-08-05T06:00:29.257664418Z 
 99%|█████████▉| 5675/5712 [13:22:20<05:22,  8.71s/it]08/04/2024 23:00:29 - INFO - __main__ -   Step: 5675, LR: 3.498990734210462e-09, Loss: 0.07285664975643158
2024-08-05T06:00:37.193112480Z 
 99%|█████████▉| 5676/5712 [13:22:28<05:05,  8.48s/it]08/04/2024 23:00:37 - INFO - __main__ -   Step: 5676, LR: 3.401712103893577e-09, Loss: 0.0681401938199997
2024-08-05T06:00:45.372435595Z 
 99%|█████████▉| 5677/5712 [13:22:36<04:53,  8.39s/it]08/04/2024 23:00:45 - INFO - __main__ -   Step: 5677, LR: 3.304433473576692e-09, Loss: 0.04601214826107025
2024-08-05T06:00:53.913834526Z 
 99%|█████████▉| 5678/5712 [13:22:45<04:46,  8.43s/it]08/04/2024 23:00:53 - INFO - __main__ -   Step: 5678, LR: 3.207154843259807e-09, Loss: 0.1396818310022354
2024-08-05T06:01:02.092776754Z 
 99%|█████████▉| 5679/5712 [13:22:53<04:35,  8.36s/it]08/04/2024 23:01:02 - INFO - __main__ -   Step: 5679, LR: 3.1098762129429216e-09, Loss: 0.04804780334234238
2024-08-05T06:01:10.271450335Z 
 99%|█████████▉| 5680/5712 [13:23:01<04:25,  8.30s/it]08/04/2024 23:01:10 - INFO - __main__ -   Step: 5680, LR: 3.0125975826260363e-09, Loss: 0.052350543439388275
2024-08-05T06:01:18.795119126Z 
 99%|█████████▉| 5681/5712 [13:23:09<04:19,  8.37s/it]08/04/2024 23:01:18 - INFO - __main__ -   Step: 5681, LR: 2.915318952309151e-09, Loss: 0.08436904102563858
2024-08-05T06:01:27.949417866Z 
 99%|█████████▉| 5682/5712 [13:23:19<04:18,  8.61s/it]08/04/2024 23:01:27 - INFO - __main__ -   Step: 5682, LR: 2.818040321992266e-09, Loss: 0.05993553251028061
2024-08-05T06:01:37.125390689Z 
 99%|█████████▉| 5683/5712 [13:23:28<04:14,  8.78s/it]08/04/2024 23:01:37 - INFO - __main__ -   Step: 5683, LR: 2.7207616916753814e-09, Loss: 0.05636456981301308
2024-08-05T06:01:45.127521223Z 
100%|█████████▉| 5684/5712 [13:23:36<03:59,  8.54s/it]08/04/2024 23:01:45 - INFO - __main__ -   Step: 5684, LR: 2.623483061358496e-09, Loss: 0.07114432752132416
2024-08-05T06:01:53.398786887Z 
100%|█████████▉| 5685/5712 [13:23:44<03:48,  8.46s/it]08/04/2024 23:01:53 - INFO - __main__ -   Step: 5685, LR: 2.526204431041611e-09, Loss: 0.06092192232608795
2024-08-05T06:02:01.923528549Z 
100%|█████████▉| 5686/5712 [13:23:53<03:40,  8.48s/it]08/04/2024 23:02:01 - INFO - __main__ -   Step: 5686, LR: 2.4289258007247257e-09, Loss: 0.06537182629108429
2024-08-05T06:02:10.607543439Z 
100%|█████████▉| 5687/5712 [13:24:01<03:33,  8.54s/it]08/04/2024 23:02:10 - INFO - __main__ -   Step: 5687, LR: 2.3316471704078405e-09, Loss: 0.06045355647802353
2024-08-05T06:02:18.838896932Z 
100%|█████████▉| 5688/5712 [13:24:09<03:22,  8.45s/it]08/04/2024 23:02:18 - INFO - __main__ -   Step: 5688, LR: 2.2343685400909552e-09, Loss: 0.0594867542386055
2024-08-05T06:02:27.136115523Z 
100%|█████████▉| 5689/5712 [13:24:18<03:13,  8.40s/it]08/04/2024 23:02:27 - INFO - __main__ -   Step: 5689, LR: 2.1370899097740704e-09, Loss: 0.05188818275928497
2024-08-05T06:02:35.768397360Z 
100%|█████████▉| 5690/5712 [13:24:26<03:06,  8.47s/it]08/04/2024 23:02:35 - INFO - __main__ -   Step: 5690, LR: 2.039811279457185e-09, Loss: 0.10931949317455292
2024-08-05T06:02:44.365094273Z 
100%|█████████▉| 5691/5712 [13:24:35<02:58,  8.51s/it]08/04/2024 23:02:44 - INFO - __main__ -   Step: 5691, LR: 1.9425326491403e-09, Loss: 0.0927199125289917
2024-08-05T06:02:53.872596549Z 
100%|█████████▉| 5692/5712 [13:24:45<02:56,  8.81s/it]08/04/2024 23:02:53 - INFO - __main__ -   Step: 5692, LR: 1.845254018823415e-09, Loss: 0.0857459008693695
2024-08-05T06:03:01.861556133Z 
100%|█████████▉| 5693/5712 [13:24:53<02:42,  8.56s/it]08/04/2024 23:03:01 - INFO - __main__ -   Step: 5693, LR: 1.7479753885065297e-09, Loss: 0.06738698482513428
2024-08-05T06:03:10.644017753Z 
100%|█████████▉| 5694/5712 [13:25:01<02:35,  8.63s/it]08/04/2024 23:03:10 - INFO - __main__ -   Step: 5694, LR: 1.6506967581896446e-09, Loss: 0.055930715054273605
2024-08-05T06:03:18.823752192Z 
100%|█████████▉| 5695/5712 [13:25:09<02:24,  8.49s/it]08/04/2024 23:03:18 - INFO - __main__ -   Step: 5695, LR: 1.5534181278727594e-09, Loss: 0.09572270512580872
2024-08-05T06:03:27.015286785Z 
100%|█████████▉| 5696/5712 [13:25:18<02:14,  8.40s/it]08/04/2024 23:03:27 - INFO - __main__ -   Step: 5696, LR: 1.4561394975558744e-09, Loss: 0.06070326268672943
2024-08-05T06:03:35.507666416Z 
100%|█████████▉| 5697/5712 [13:25:26<02:06,  8.43s/it]08/04/2024 23:03:35 - INFO - __main__ -   Step: 5697, LR: 1.3588608672389893e-09, Loss: 0.03944176062941551
2024-08-05T06:03:44.156376850Z 
100%|█████████▉| 5698/5712 [13:25:35<01:58,  8.50s/it]08/04/2024 23:03:44 - INFO - __main__ -   Step: 5698, LR: 1.2615822369221041e-09, Loss: 0.13922026753425598
2024-08-05T06:03:52.629635999Z 
100%|█████████▉| 5699/5712 [13:25:43<01:50,  8.49s/it]08/04/2024 23:03:52 - INFO - __main__ -   Step: 5699, LR: 1.1643036066052189e-09, Loss: 0.020953383296728134
2024-08-05T06:04:01.820358895Z 
100%|█████████▉| 5700/5712 [13:25:52<01:44,  8.70s/it]08/04/2024 23:04:01 - INFO - __main__ -   Step: 5700, LR: 1.0670249762883336e-09, Loss: 0.06294028460979462
2024-08-05T06:04:09.902885376Z 
100%|█████████▉| 5701/5712 [13:26:01<01:33,  8.51s/it]08/04/2024 23:04:09 - INFO - __main__ -   Step: 5701, LR: 9.697463459714486e-10, Loss: 0.09799689054489136
2024-08-05T06:04:18.325694612Z 
100%|█████████▉| 5702/5712 [13:26:09<01:24,  8.49s/it]08/04/2024 23:04:18 - INFO - __main__ -   Step: 5702, LR: 8.724677156545635e-10, Loss: 0.08558700233697891
2024-08-05T06:04:27.252303532Z 
100%|█████████▉| 5703/5712 [13:26:18<01:17,  8.62s/it]08/04/2024 23:04:27 - INFO - __main__ -   Step: 5703, LR: 7.751890853376784e-10, Loss: 0.06691920757293701
2024-08-05T06:04:35.210660946Z 
100%|█████████▉| 5704/5712 [13:26:26<01:07,  8.42s/it]08/04/2024 23:04:35 - INFO - __main__ -   Step: 5704, LR: 6.779104550207932e-10, Loss: 0.08103983104228973
2024-08-05T06:04:43.196140240Z 
100%|█████████▉| 5705/5712 [13:26:34<00:58,  8.29s/it]08/04/2024 23:04:43 - INFO - __main__ -   Step: 5705, LR: 5.806318247039082e-10, Loss: 0.094042107462883
2024-08-05T06:04:52.592258189Z 
100%|█████████▉| 5706/5712 [13:26:43<00:51,  8.62s/it]08/04/2024 23:04:52 - INFO - __main__ -   Step: 5706, LR: 4.83353194387023e-10, Loss: 0.06434842199087143
2024-08-05T06:05:00.860610992Z 
100%|█████████▉| 5707/5712 [13:26:52<00:42,  8.52s/it]08/04/2024 23:05:00 - INFO - __main__ -   Step: 5707, LR: 3.860745640701379e-10, Loss: 0.06615093350410461
2024-08-05T06:05:09.355175587Z 
100%|█████████▉| 5708/5712 [13:27:00<00:34,  8.51s/it]08/04/2024 23:05:09 - INFO - __main__ -   Step: 5708, LR: 2.8879593375325277e-10, Loss: 0.07286016643047333
2024-08-05T06:05:18.003561246Z 
100%|█████████▉| 5709/5712 [13:27:09<00:25,  8.55s/it]08/04/2024 23:05:18 - INFO - __main__ -   Step: 5709, LR: 1.9151730343636763e-10, Loss: 0.07219953835010529
2024-08-05T06:05:26.193190977Z 
100%|█████████▉| 5710/5712 [13:27:17<00:16,  8.44s/it]08/04/2024 23:05:26 - INFO - __main__ -   Step: 5710, LR: 9.423867311948247e-11, Loss: 0.04851269721984863
2024-08-05T06:05:35.166744074Z 
100%|█████████▉| 5711/5712 [13:27:26<00:08,  8.60s/it]08/04/2024 23:05:35 - INFO - __main__ -   Step: 5711, LR: 0.0, Loss: 0.08426735550165176
2024-08-05T06:05:43.533417932Z 
100%|██████████| 5712/5712 [13:27:34<00:00,  8.53s/it]08/04/2024 23:05:43 - INFO - __main__ -   Step: 5712, LR: 0.0, Loss: 0.03724200651049614
2024-08-05T06:05:52.461488491Z Configuration saved in /output/epoch_2/config.json
2024-08-05T06:05:52.461733612Z Configuration saved in /output/epoch_2/generation_config.json
2024-08-05T06:06:02.727939149Z The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at /output/epoch_2/pytorch_model.bin.index.json.
2024-08-05T06:06:02.747843472Z tokenizer config file saved in /output/tokenizer_config.json
2024-08-05T06:06:02.747856811Z Special tokens file saved in /output/special_tokens_map.json
2024-08-05T06:06:05.981838073Z Configuration saved in /output/config.json
2024-08-05T06:06:05.981869222Z Configuration saved in /output/generation_config.json
2024-08-05T06:06:16.132585899Z The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at /output/pytorch_model.bin.index.json.
2024-08-05T06:06:16.152573130Z 
100%|██████████| 5712/5712 [13:28:07<00:00,  8.49s/it]
2024-08-05T06:06:19.626116576Z jupiter-cs-aus-134:100:640 [5] NCCL INFO [Service thread] Connection closed by localRank 7
2024-08-05T06:06:19.626152054Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 7
2024-08-05T06:06:19.626160706Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 7
2024-08-05T06:06:19.626174797Z jupiter-cs-aus-134:100:405 [5] NCCL INFO [Service thread] Connection closed by localRank 7
2024-08-05T06:06:19.718091873Z jupiter-cs-aus-134:100:640 [5] NCCL INFO [Service thread] Connection closed by localRank 2
2024-08-05T06:06:19.718096808Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 2
2024-08-05T06:06:19.718098459Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 4
2024-08-05T06:06:19.718100277Z jupiter-cs-aus-134:100:640 [5] NCCL INFO [Service thread] Connection closed by localRank 4
2024-08-05T06:06:19.718209554Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 2
2024-08-05T06:06:19.718211197Z jupiter-cs-aus-134:100:405 [5] NCCL INFO [Service thread] Connection closed by localRank 2
2024-08-05T06:06:19.718212787Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 3
2024-08-05T06:06:19.718230651Z jupiter-cs-aus-134:100:640 [5] NCCL INFO [Service thread] Connection closed by localRank 3
2024-08-05T06:06:19.718309993Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 4
2024-08-05T06:06:19.718328639Z jupiter-cs-aus-134:100:405 [5] NCCL INFO [Service thread] Connection closed by localRank 4
2024-08-05T06:06:19.718471950Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 3
2024-08-05T06:06:19.718474274Z jupiter-cs-aus-134:100:405 [5] NCCL INFO [Service thread] Connection closed by localRank 3
2024-08-05T06:06:19.916672680Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 1
2024-08-05T06:06:19.916756900Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 1
2024-08-05T06:06:20.036894464Z jupiter-cs-aus-134:101:641 [6] NCCL INFO [Service thread] Connection closed by localRank 5
2024-08-05T06:06:20.036922484Z jupiter-cs-aus-134:101:401 [6] NCCL INFO [Service thread] Connection closed by localRank 5
2024-08-05T06:06:22.586604165Z [93m [WARNING] [0m async_io requires the dev libaio .so object and headers but these were not found.
2024-08-05T06:06:22.586625787Z [93m [WARNING] [0m async_io: please install the libaio-dev package with apt
2024-08-05T06:06:22.586628253Z [93m [WARNING] [0m If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
2024-08-05T06:06:22.586629865Z [93m [WARNING] [0m Please specify the CUTLASS repo directory as environment variable $CUTLASS_PATH
2024-08-05T06:06:22.586631622Z [93m [WARNING] [0m sparse_attn requires a torch version >= 1.5 and < 2.0 but detected 2.3
2024-08-05T06:06:22.586633003Z [93m [WARNING] [0m using untested triton version (2.3.0), only 1.0.0 is known to be compatible
