***************
** Arguments **
***************
backbone: 
config_file: configs/trainers/ProDA/vit_b16_ep50_c4_BZ4_ProDA.yaml
dataset_config_file: configs/datasets/caltech101.yaml
eval_only: False
head: 
load_epoch: None
model_dir: 
no_train: False
opts: ['DATASET.NUM_SHOTS', '16', 'DATASET.SUBSAMPLE_CLASSES', 'base']
output_dir: output/base2new/train_base/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed3
resume: 
root: /mnt/hdd/DATA
seed: 3
source_domains: None
target_domains: None
trainer: ProDA
transforms: None
************
** Config **
************
DATALOADER:
  K_TRANSFORMS: 1
  NUM_WORKERS: 8
  RETURN_IMG0: False
  TEST:
    BATCH_SIZE: 100
    SAMPLER: SequentialSampler
  TRAIN_U:
    BATCH_SIZE: 32
    N_DOMAIN: 0
    N_INS: 16
    SAME_AS_X: True
    SAMPLER: RandomSampler
  TRAIN_X:
    BATCH_SIZE: 4
    N_DOMAIN: 0
    N_INS: 16
    SAMPLER: RandomSampler
DATASET:
  ALL_AS_UNLABELED: False
  CIFAR_C_LEVEL: 1
  CIFAR_C_TYPE: 
  NAME: Caltech101
  NUM_LABELED: -1
  NUM_SHOTS: 16
  ROOT: /mnt/hdd/DATA
  SOURCE_DOMAINS: ()
  STL10_FOLD: -1
  SUBSAMPLE_CLASSES: base
  TARGET_DOMAINS: ()
  VAL_PERCENT: 0.1
INPUT:
  COLORJITTER_B: 0.4
  COLORJITTER_C: 0.4
  COLORJITTER_H: 0.1
  COLORJITTER_S: 0.4
  CROP_PADDING: 4
  CUTOUT_LEN: 16
  CUTOUT_N: 1
  GB_K: 21
  GB_P: 0.5
  GN_MEAN: 0.0
  GN_STD: 0.15
  INTERPOLATION: bicubic
  NO_TRANSFORM: False
  PIXEL_MEAN: [0.48145466, 0.4578275, 0.40821073]
  PIXEL_STD: [0.26862954, 0.26130258, 0.27577711]
  RANDAUGMENT_M: 10
  RANDAUGMENT_N: 2
  RGS_P: 0.2
  RRCROP_SCALE: (0.08, 1.0)
  SIZE: (224, 224)
  TRANSFORMS: ('random_resized_crop', 'random_flip', 'normalize')
MODEL:
  BACKBONE:
    NAME: ViT-B/16
    PRETRAINED: True
  HEAD:
    ACTIVATION: relu
    BN: True
    DROPOUT: 0.0
    HIDDEN_LAYERS: ()
    NAME: 
  INIT_WEIGHTS: 
OPTIM:
  ADAM_BETA1: 0.9
  ADAM_BETA2: 0.999
  BASE_LR_MULT: 0.1
  GAMMA: 0.1
  LR: 0.002
  LR_SCHEDULER: cosine
  MAX_EPOCH: 50
  MOMENTUM: 0.9
  NAME: sgd
  NEW_LAYERS: ()
  RMSPROP_ALPHA: 0.99
  SGD_DAMPNING: 0
  SGD_NESTEROV: False
  STAGED_LR: False
  STEPSIZE: (-1,)
  WARMUP_CONS_LR: 1e-05
  WARMUP_EPOCH: 5
  WARMUP_MIN_LR: 1e-05
  WARMUP_RECOUNT: True
  WARMUP_TYPE: constant
  WEIGHT_DECAY: 0.0005
OUTPUT_DIR: output/base2new/train_base/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed3
RESUME: 
SEED: 3
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ProDA
  ProDA:
    N_CTX: 4
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14) 12.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.36

Python version: 3.11.2 (main, Mar 13 2023, 12:18:29) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-6.5.13-3-pve-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA A800 80GB PCIe
GPU 1: NVIDIA A800 80GB PCIe

Nvidia driver version: 525.147.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      46 bits physical, 57 bits virtual
Byte Order:                         Little Endian
CPU(s):                             64
On-line CPU(s) list:                18,20,22,23,25-27,29,31,32,34,37,46-49
Off-line CPU(s) list:               0-17,19,21,24,28,30,33,35,36,38-45,50-63
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 16
Socket(s):                          2
Stepping:                           6
CPU(s) scaling MHz:                 98%
CPU max MHz:                        3500.0000
CPU min MHz:                        800.0000
BogoMIPS:                           5800.00
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 invpcid_single intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                     VT-x
L1d cache:                          1.5 MiB (32 instances)
L1i cache:                          1 MiB (32 instances)
L2 cache:                           40 MiB (32 instances)
L3 cache:                           48 MiB (2 instances)
NUMA node(s):                       2
NUMA node0 CPU(s):                  0-15,32-47
NUMA node1 CPU(s):                  16-31,48-63
Vulnerability Gather data sampling: Vulnerable: No microcode
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass:    Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Enhanced / Automatic IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected

Versions of relevant libraries:
[pip3] flake8==3.7.9
[pip3] flake8==3.7.9
[pip3] numpy==1.26.4
[pip3] torch==2.2.1
[pip3] torchaudio==2.2.1
[pip3] torchvision==0.17.1
[pip3] triton==2.2.0
[conda] Could not collect
        Pillow (10.2.0)

Loading trainer: ProDA
Loading dataset: Caltech101
Reading split from /mnt/hdd/DATA/caltech-101/split_zhou_Caltech101.json
Loading preprocessed few-shot data from /mnt/hdd/DATA/caltech-101/split_fewshot/shot_16_shuffled-seed_3.pkl
SUBSAMPLE BASE CLASSES!
Building transform_train
+ random resized crop (size=(224, 224), scale=(0.08, 1.0))
+ random flip
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
Building transform_test
+ resize the smaller edge to 224
+ 224x224 center crop
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
---------  ----------
Dataset    Caltech101
# classes  50
# train_x  800
# val      200
# test     1,344
---------  ----------
Loading CLIP (backbone: ViT-B/16)
Building custom CLIP
Turning off gradients in both the image and the text encoder
Parameters to be updated: {'prompt_learner.ctx'}
Loading evaluator: Classification
No checkpoint found, train from scratch
Initialize tensorboard (log_dir=output/base2new/train_base/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed3/tensorboard)
epoch [1/50] batch [20/200] time 1.123 (1.679) data 0.000 (0.033) loss 1.1206 (1.3376) lr 1.0000e-05 eta 4:39:16
epoch [1/50] batch [40/200] time 1.114 (1.398) data 0.000 (0.017) loss 1.9386 (1.2909) lr 1.0000e-05 eta 3:52:01
epoch [1/50] batch [60/200] time 1.117 (1.300) data 0.000 (0.011) loss 1.7003 (1.2520) lr 1.0000e-05 eta 3:35:26
epoch [1/50] batch [80/200] time 1.107 (1.254) data 0.000 (0.009) loss 0.8864 (1.2453) lr 1.0000e-05 eta 3:27:17
epoch [1/50] batch [100/200] time 1.124 (1.227) data 0.008 (0.007) loss 3.6727 (1.2346) lr 1.0000e-05 eta 3:22:30
epoch [1/50] batch [120/200] time 1.121 (1.208) data 0.000 (0.006) loss 2.8708 (1.2423) lr 1.0000e-05 eta 3:18:53
epoch [1/50] batch [140/200] time 1.110 (1.195) data 0.000 (0.005) loss 1.2351 (1.2361) lr 1.0000e-05 eta 3:16:21
epoch [1/50] batch [160/200] time 1.113 (1.184) data 0.000 (0.005) loss 0.9846 (1.2540) lr 1.0000e-05 eta 3:14:10
epoch [1/50] batch [180/200] time 1.118 (1.176) data 0.000 (0.004) loss 0.5592 (1.2400) lr 1.0000e-05 eta 3:12:31
epoch [1/50] batch [200/200] time 1.123 (1.170) data 0.000 (0.004) loss 2.9933 (1.2224) lr 1.0000e-05 eta 3:11:10
epoch [2/50] batch [20/200] time 1.136 (1.115) data 0.000 (0.023) loss 0.1189 (0.7930) lr 1.0000e-05 eta 3:01:46
epoch [2/50] batch [40/200] time 1.129 (1.126) data 0.000 (0.012) loss 0.0952 (0.9592) lr 1.0000e-05 eta 3:03:11
epoch [2/50] batch [60/200] time 1.139 (1.128) data 0.000 (0.008) loss 0.0589 (0.9874) lr 1.0000e-05 eta 3:03:01
epoch [2/50] batch [80/200] time 1.130 (1.129) data 0.000 (0.006) loss 0.5943 (0.9239) lr 1.0000e-05 eta 3:02:58
epoch [2/50] batch [100/200] time 0.846 (1.117) data 0.000 (0.005) loss 0.5134 (0.8843) lr 1.0000e-05 eta 3:00:31
epoch [2/50] batch [120/200] time 1.146 (1.121) data 0.000 (0.004) loss 0.2197 (0.9251) lr 1.0000e-05 eta 3:00:47
epoch [2/50] batch [140/200] time 1.121 (1.123) data 0.000 (0.004) loss 0.4805 (0.8979) lr 1.0000e-05 eta 3:00:44
epoch [2/50] batch [160/200] time 1.146 (1.123) data 0.000 (0.003) loss 0.7337 (0.8996) lr 1.0000e-05 eta 3:00:26
epoch [2/50] batch [180/200] time 1.129 (1.124) data 0.000 (0.003) loss 0.0277 (0.9094) lr 1.0000e-05 eta 3:00:16
epoch [2/50] batch [200/200] time 0.833 (1.095) data 0.000 (0.003) loss 0.7503 (0.9062) lr 1.0000e-05 eta 2:55:16
epoch [3/50] batch [20/200] time 0.862 (0.879) data 0.000 (0.028) loss 0.5061 (0.8135) lr 1.0000e-05 eta 2:20:20
epoch [3/50] batch [40/200] time 0.935 (0.983) data 0.000 (0.014) loss 0.1543 (0.8567) lr 1.0000e-05 eta 2:36:34
epoch [3/50] batch [60/200] time 1.130 (1.011) data 0.000 (0.009) loss 1.8126 (0.8996) lr 1.0000e-05 eta 2:40:43
epoch [3/50] batch [80/200] time 1.088 (1.025) data 0.000 (0.007) loss 0.1502 (0.9086) lr 1.0000e-05 eta 2:42:34
epoch [3/50] batch [100/200] time 1.049 (1.029) data 0.000 (0.006) loss 1.5679 (0.9221) lr 1.0000e-05 eta 2:42:52
epoch [3/50] batch [120/200] time 1.133 (1.039) data 0.000 (0.005) loss 0.4655 (0.9433) lr 1.0000e-05 eta 2:44:06
epoch [3/50] batch [140/200] time 0.831 (1.009) data 0.000 (0.004) loss 0.0606 (0.9304) lr 1.0000e-05 eta 2:39:02
epoch [3/50] batch [160/200] time 1.038 (0.989) data 0.000 (0.004) loss 0.8215 (0.9213) lr 1.0000e-05 eta 2:35:32
epoch [3/50] batch [180/200] time 0.908 (0.989) data 0.000 (0.004) loss 0.1874 (0.9129) lr 1.0000e-05 eta 2:35:18
epoch [3/50] batch [200/200] time 1.035 (0.988) data 0.000 (0.003) loss 0.7144 (0.9171) lr 1.0000e-05 eta 2:34:43
epoch [4/50] batch [20/200] time 1.032 (1.019) data 0.000 (0.031) loss 1.2174 (1.1502) lr 1.0000e-05 eta 2:39:19
epoch [4/50] batch [40/200] time 0.842 (0.991) data 0.000 (0.016) loss 0.8034 (0.9211) lr 1.0000e-05 eta 2:34:36
epoch [4/50] batch [60/200] time 1.011 (0.982) data 0.000 (0.011) loss 1.3133 (0.8693) lr 1.0000e-05 eta 2:32:53
epoch [4/50] batch [80/200] time 1.014 (0.981) data 0.009 (0.008) loss 1.8101 (0.8591) lr 1.0000e-05 eta 2:32:19
epoch [4/50] batch [100/200] time 0.836 (0.968) data 0.000 (0.007) loss 0.7989 (0.8725) lr 1.0000e-05 eta 2:30:01
epoch [4/50] batch [120/200] time 0.851 (0.947) data 0.000 (0.006) loss 1.3416 (0.9146) lr 1.0000e-05 eta 2:26:24
epoch [4/50] batch [140/200] time 0.880 (0.934) data 0.000 (0.005) loss 0.9381 (0.9130) lr 1.0000e-05 eta 2:24:05
epoch [4/50] batch [160/200] time 0.854 (0.921) data 0.000 (0.004) loss 0.1814 (0.8892) lr 1.0000e-05 eta 2:21:54
epoch [4/50] batch [180/200] time 0.976 (0.918) data 0.000 (0.004) loss 0.4159 (0.8829) lr 1.0000e-05 eta 2:21:02
epoch [4/50] batch [200/200] time 1.028 (0.929) data 0.000 (0.004) loss 0.0514 (0.9102) lr 1.0000e-05 eta 2:22:24
epoch [5/50] batch [20/200] time 1.030 (1.063) data 0.000 (0.027) loss 0.0904 (0.9210) lr 1.0000e-05 eta 2:42:34
epoch [5/50] batch [40/200] time 1.028 (1.030) data 0.000 (0.014) loss 1.1387 (0.9530) lr 1.0000e-05 eta 2:37:11
epoch [5/50] batch [60/200] time 1.026 (1.022) data 0.000 (0.009) loss 0.1474 (0.8982) lr 1.0000e-05 eta 2:35:38
epoch [5/50] batch [80/200] time 1.034 (1.022) data 0.000 (0.007) loss 0.3629 (0.9406) lr 1.0000e-05 eta 2:35:16
epoch [5/50] batch [100/200] time 0.802 (1.018) data 0.000 (0.006) loss 0.0605 (0.9286) lr 1.0000e-05 eta 2:34:24
epoch [5/50] batch [120/200] time 1.042 (1.013) data 0.000 (0.005) loss 0.8050 (0.8912) lr 1.0000e-05 eta 2:33:22
epoch [5/50] batch [140/200] time 0.924 (1.013) data 0.000 (0.004) loss 0.7604 (0.9065) lr 1.0000e-05 eta 2:32:56
epoch [5/50] batch [160/200] time 1.030 (1.014) data 0.000 (0.004) loss 0.8920 (0.9098) lr 1.0000e-05 eta 2:32:45
epoch [5/50] batch [180/200] time 1.030 (1.013) data 0.000 (0.003) loss 1.0076 (0.9191) lr 1.0000e-05 eta 2:32:17
epoch [5/50] batch [200/200] time 1.035 (1.012) data 0.000 (0.003) loss 1.0874 (0.8971) lr 2.0000e-03 eta 2:31:50
epoch [6/50] batch [20/200] time 0.909 (1.045) data 0.000 (0.033) loss 1.2270 (1.0792) lr 2.0000e-03 eta 2:36:22
epoch [6/50] batch [40/200] time 1.032 (1.031) data 0.000 (0.017) loss 1.3963 (0.9148) lr 2.0000e-03 eta 2:34:00
epoch [6/50] batch [60/200] time 1.026 (1.016) data 0.000 (0.011) loss 1.3977 (0.9617) lr 2.0000e-03 eta 2:31:19
epoch [6/50] batch [80/200] time 1.031 (1.013) data 0.000 (0.009) loss 0.1428 (0.9180) lr 2.0000e-03 eta 2:30:31
epoch [6/50] batch [100/200] time 1.022 (1.014) data 0.000 (0.007) loss 0.0752 (0.8628) lr 2.0000e-03 eta 2:30:24
epoch [6/50] batch [120/200] time 1.025 (1.015) data 0.000 (0.006) loss 2.8781 (0.8562) lr 2.0000e-03 eta 2:30:10
epoch [6/50] batch [140/200] time 1.048 (1.016) data 0.000 (0.005) loss 1.0823 (0.8399) lr 2.0000e-03 eta 2:29:58
epoch [6/50] batch [160/200] time 0.843 (1.015) data 0.000 (0.004) loss 1.5405 (0.8222) lr 2.0000e-03 eta 2:29:31
epoch [6/50] batch [180/200] time 1.031 (1.016) data 0.000 (0.004) loss 0.3145 (0.8231) lr 2.0000e-03 eta 2:29:24
epoch [6/50] batch [200/200] time 1.037 (1.016) data 0.000 (0.004) loss 0.5534 (0.7993) lr 1.9980e-03 eta 2:29:01
epoch [7/50] batch [20/200] time 1.038 (1.038) data 0.000 (0.028) loss 1.6751 (0.6874) lr 1.9980e-03 eta 2:31:55
epoch [7/50] batch [40/200] time 0.866 (1.027) data 0.000 (0.014) loss 0.0613 (0.6665) lr 1.9980e-03 eta 2:29:58
epoch [7/50] batch [60/200] time 1.026 (1.023) data 0.000 (0.009) loss 0.3087 (0.6809) lr 1.9980e-03 eta 2:29:00
epoch [7/50] batch [80/200] time 1.031 (1.023) data 0.000 (0.007) loss 0.0154 (0.6111) lr 1.9980e-03 eta 2:28:38
epoch [7/50] batch [100/200] time 1.026 (1.020) data 0.000 (0.006) loss 0.0095 (0.6044) lr 1.9980e-03 eta 2:27:52
epoch [7/50] batch [120/200] time 1.022 (1.022) data 0.000 (0.005) loss 2.1835 (0.6182) lr 1.9980e-03 eta 2:27:54
epoch [7/50] batch [140/200] time 0.581 (1.002) data 0.000 (0.004) loss 1.4098 (0.6324) lr 1.9980e-03 eta 2:24:38
epoch [7/50] batch [160/200] time 0.849 (0.983) data 0.002 (0.004) loss 0.0458 (0.5999) lr 1.9980e-03 eta 2:21:29
epoch [7/50] batch [180/200] time 0.834 (0.972) data 0.000 (0.003) loss 1.1717 (0.6142) lr 1.9980e-03 eta 2:19:39
epoch [7/50] batch [200/200] time 0.846 (0.958) data 0.000 (0.003) loss 1.2150 (0.6138) lr 1.9921e-03 eta 2:17:16
epoch [8/50] batch [20/200] time 0.999 (0.968) data 0.000 (0.028) loss 0.1062 (0.4675) lr 1.9921e-03 eta 2:18:27
epoch [8/50] batch [40/200] time 1.008 (0.951) data 0.000 (0.014) loss 0.0218 (0.4742) lr 1.9921e-03 eta 2:15:41
epoch [8/50] batch [60/200] time 0.997 (0.955) data 0.001 (0.010) loss 0.4043 (0.4794) lr 1.9921e-03 eta 2:15:59
epoch [8/50] batch [80/200] time 0.994 (0.960) data 0.003 (0.007) loss 1.3821 (0.5109) lr 1.9921e-03 eta 2:16:21
epoch [8/50] batch [100/200] time 0.837 (0.944) data 0.000 (0.006) loss 1.0981 (0.5171) lr 1.9921e-03 eta 2:13:41
epoch [8/50] batch [120/200] time 0.850 (0.926) data 0.000 (0.005) loss 0.0164 (0.5088) lr 1.9921e-03 eta 2:10:55
epoch [8/50] batch [140/200] time 0.910 (0.919) data 0.000 (0.004) loss 0.0082 (0.5207) lr 1.9921e-03 eta 2:09:36
epoch [8/50] batch [160/200] time 0.855 (0.910) data 0.003 (0.004) loss 0.3881 (0.5407) lr 1.9921e-03 eta 2:07:56
epoch [8/50] batch [180/200] time 1.029 (0.907) data 0.000 (0.004) loss 4.1539 (0.6046) lr 1.9921e-03 eta 2:07:12
epoch [8/50] batch [200/200] time 1.033 (0.918) data 0.000 (0.003) loss 0.3704 (0.5939) lr 1.9823e-03 eta 2:08:33
epoch [9/50] batch [20/200] time 1.040 (1.059) data 0.000 (0.028) loss 1.2500 (0.6184) lr 1.9823e-03 eta 2:27:57
epoch [9/50] batch [40/200] time 1.037 (1.024) data 0.000 (0.014) loss 0.3509 (0.5517) lr 1.9823e-03 eta 2:22:41
epoch [9/50] batch [60/200] time 1.039 (1.022) data 0.000 (0.010) loss 0.0345 (0.4974) lr 1.9823e-03 eta 2:22:03
epoch [9/50] batch [80/200] time 1.056 (1.017) data 0.000 (0.007) loss 0.7403 (0.4764) lr 1.9823e-03 eta 2:20:59
epoch [9/50] batch [100/200] time 1.046 (1.020) data 0.000 (0.006) loss 0.0221 (0.4475) lr 1.9823e-03 eta 2:21:06
epoch [9/50] batch [120/200] time 1.048 (1.022) data 0.000 (0.005) loss 0.3854 (0.4491) lr 1.9823e-03 eta 2:21:04
epoch [9/50] batch [140/200] time 0.918 (1.021) data 0.001 (0.004) loss 0.0017 (0.4453) lr 1.9823e-03 eta 2:20:30
epoch [9/50] batch [160/200] time 1.037 (1.022) data 0.000 (0.004) loss 0.2544 (0.4480) lr 1.9823e-03 eta 2:20:22
epoch [9/50] batch [180/200] time 1.037 (1.020) data 0.000 (0.003) loss 0.8262 (0.4657) lr 1.9823e-03 eta 2:19:47
epoch [9/50] batch [200/200] time 1.048 (1.020) data 0.000 (0.003) loss 0.4215 (0.4831) lr 1.9686e-03 eta 2:19:24
epoch [10/50] batch [20/200] time 0.540 (1.006) data 0.000 (0.027) loss 0.4180 (0.7720) lr 1.9686e-03 eta 2:17:06
epoch [10/50] batch [40/200] time 1.118 (1.050) data 0.000 (0.014) loss 1.3471 (0.5772) lr 1.9686e-03 eta 2:22:46
epoch [10/50] batch [60/200] time 0.845 (1.025) data 0.000 (0.009) loss 1.0433 (0.5546) lr 1.9686e-03 eta 2:19:01
epoch [10/50] batch [80/200] time 0.838 (0.976) data 0.000 (0.007) loss 0.2141 (0.5864) lr 1.9686e-03 eta 2:12:04
epoch [10/50] batch [100/200] time 1.134 (0.975) data 0.006 (0.006) loss 0.2155 (0.5821) lr 1.9686e-03 eta 2:11:37
epoch [10/50] batch [120/200] time 0.555 (0.992) data 0.000 (0.005) loss 0.0948 (0.5760) lr 1.9686e-03 eta 2:13:33
epoch [10/50] batch [140/200] time 0.558 (0.968) data 0.000 (0.005) loss 0.6819 (0.5415) lr 1.9686e-03 eta 2:10:03
epoch [10/50] batch [160/200] time 1.038 (0.960) data 0.000 (0.004) loss 0.3084 (0.5508) lr 1.9686e-03 eta 2:08:34
epoch [10/50] batch [180/200] time 0.856 (0.967) data 0.000 (0.004) loss 0.1470 (0.5309) lr 1.9686e-03 eta 2:09:13
epoch [10/50] batch [200/200] time 1.031 (0.971) data 0.000 (0.003) loss 0.7531 (0.5342) lr 1.9511e-03 eta 2:09:25
epoch [11/50] batch [20/200] time 1.041 (1.044) data 0.000 (0.029) loss 0.0467 (0.5465) lr 1.9511e-03 eta 2:18:50
epoch [11/50] batch [40/200] time 1.023 (1.013) data 0.000 (0.015) loss 0.6179 (0.5321) lr 1.9511e-03 eta 2:14:19
epoch [11/50] batch [60/200] time 1.034 (1.020) data 0.000 (0.010) loss 0.0247 (0.5235) lr 1.9511e-03 eta 2:15:02
epoch [11/50] batch [80/200] time 1.040 (1.015) data 0.005 (0.008) loss 0.0793 (0.5728) lr 1.9511e-03 eta 2:14:01
epoch [11/50] batch [100/200] time 1.033 (1.010) data 0.000 (0.006) loss 0.0093 (0.5272) lr 1.9511e-03 eta 2:12:57
epoch [11/50] batch [120/200] time 0.851 (1.012) data 0.000 (0.005) loss 0.6174 (0.5138) lr 1.9511e-03 eta 2:12:56
epoch [11/50] batch [140/200] time 1.045 (1.010) data 0.000 (0.005) loss 0.5954 (0.5384) lr 1.9511e-03 eta 2:12:22
epoch [11/50] batch [160/200] time 1.032 (1.010) data 0.000 (0.004) loss 0.5672 (0.5350) lr 1.9511e-03 eta 2:11:54
epoch [11/50] batch [180/200] time 0.870 (1.010) data 0.000 (0.004) loss 0.2711 (0.5287) lr 1.9511e-03 eta 2:11:37
epoch [11/50] batch [200/200] time 1.031 (1.011) data 0.000 (0.003) loss 0.1048 (0.5228) lr 1.9298e-03 eta 2:11:28
epoch [12/50] batch [20/200] time 1.029 (1.032) data 0.004 (0.032) loss 0.1133 (0.5976) lr 1.9298e-03 eta 2:13:47
epoch [12/50] batch [40/200] time 1.020 (1.011) data 0.000 (0.016) loss 0.7970 (0.5994) lr 1.9298e-03 eta 2:10:47
epoch [12/50] batch [60/200] time 0.996 (1.018) data 0.001 (0.011) loss 0.3471 (0.5207) lr 1.9298e-03 eta 2:11:17
epoch [12/50] batch [80/200] time 1.027 (1.011) data 0.000 (0.009) loss 0.0035 (0.4994) lr 1.9298e-03 eta 2:10:04
epoch [12/50] batch [100/200] time 1.037 (1.012) data 0.000 (0.007) loss 0.0020 (0.5424) lr 1.9298e-03 eta 2:09:50
epoch [12/50] batch [120/200] time 0.848 (1.011) data 0.000 (0.006) loss 0.4414 (0.5345) lr 1.9298e-03 eta 2:09:26
epoch [12/50] batch [140/200] time 1.038 (1.012) data 0.000 (0.005) loss 0.3274 (0.5151) lr 1.9298e-03 eta 2:09:09
epoch [12/50] batch [160/200] time 1.033 (1.011) data 0.000 (0.004) loss 0.5523 (0.5136) lr 1.9298e-03 eta 2:08:47
epoch [12/50] batch [180/200] time 1.037 (1.010) data 0.000 (0.004) loss 0.3046 (0.5525) lr 1.9298e-03 eta 2:08:16
epoch [12/50] batch [200/200] time 1.030 (1.013) data 0.000 (0.004) loss 0.8723 (0.5365) lr 1.9048e-03 eta 2:08:16
epoch [13/50] batch [20/200] time 0.912 (1.033) data 0.000 (0.028) loss 0.0104 (0.5939) lr 1.9048e-03 eta 2:10:30
epoch [13/50] batch [40/200] time 1.041 (1.022) data 0.000 (0.014) loss 0.2389 (0.5612) lr 1.9048e-03 eta 2:08:49
epoch [13/50] batch [60/200] time 1.037 (1.019) data 0.000 (0.010) loss 0.2912 (0.5606) lr 1.9048e-03 eta 2:08:02
epoch [13/50] batch [80/200] time 1.043 (1.021) data 0.000 (0.007) loss 0.0145 (0.5169) lr 1.9048e-03 eta 2:08:01
epoch [13/50] batch [100/200] time 0.821 (0.998) data 0.000 (0.006) loss 0.8277 (0.4847) lr 1.9048e-03 eta 2:04:44
epoch [13/50] batch [120/200] time 0.833 (0.970) data 0.000 (0.005) loss 0.0631 (0.4803) lr 1.9048e-03 eta 2:00:53
epoch [13/50] batch [140/200] time 0.841 (0.957) data 0.000 (0.004) loss 0.0038 (0.4838) lr 1.9048e-03 eta 1:59:00
epoch [13/50] batch [160/200] time 0.840 (0.943) data 0.000 (0.004) loss 0.5066 (0.4775) lr 1.9048e-03 eta 1:56:56
epoch [13/50] batch [180/200] time 1.101 (0.942) data 0.005 (0.004) loss 0.0384 (0.5046) lr 1.9048e-03 eta 1:56:27
epoch [13/50] batch [200/200] time 1.086 (0.956) data 0.000 (0.003) loss 0.0152 (0.5114) lr 1.8763e-03 eta 1:57:57
epoch [14/50] batch [20/200] time 1.083 (1.108) data 0.000 (0.029) loss 0.7055 (0.2739) lr 1.8763e-03 eta 2:16:14
epoch [14/50] batch [40/200] time 1.088 (1.098) data 0.000 (0.015) loss 0.0433 (0.3866) lr 1.8763e-03 eta 2:14:38
epoch [14/50] batch [60/200] time 1.084 (1.094) data 0.000 (0.010) loss 1.2489 (0.4197) lr 1.8763e-03 eta 2:13:48
epoch [14/50] batch [80/200] time 1.085 (1.090) data 0.000 (0.008) loss 0.3420 (0.4441) lr 1.8763e-03 eta 2:13:01
epoch [14/50] batch [100/200] time 1.087 (1.090) data 0.000 (0.006) loss 0.9582 (0.4268) lr 1.8763e-03 eta 2:12:39
epoch [14/50] batch [120/200] time 1.079 (1.088) data 0.000 (0.005) loss 0.3944 (0.4271) lr 1.8763e-03 eta 2:12:03
epoch [14/50] batch [140/200] time 1.098 (1.088) data 0.000 (0.005) loss 1.5695 (0.5073) lr 1.8763e-03 eta 2:11:39
epoch [14/50] batch [160/200] time 1.092 (1.087) data 0.000 (0.004) loss 0.0693 (0.4995) lr 1.8763e-03 eta 2:11:09
epoch [14/50] batch [180/200] time 1.020 (1.081) data 0.000 (0.004) loss 0.8796 (0.5052) lr 1.8763e-03 eta 2:10:06
epoch [14/50] batch [200/200] time 1.106 (1.079) data 0.000 (0.003) loss 0.0051 (0.5125) lr 1.8443e-03 eta 2:09:29
epoch [15/50] batch [20/200] time 1.106 (1.126) data 0.000 (0.029) loss 0.8423 (0.6015) lr 1.8443e-03 eta 2:14:41
epoch [15/50] batch [40/200] time 1.108 (1.117) data 0.000 (0.015) loss 2.2407 (0.5107) lr 1.8443e-03 eta 2:13:15
epoch [15/50] batch [60/200] time 1.116 (1.111) data 0.001 (0.010) loss 0.4401 (0.5387) lr 1.8443e-03 eta 2:12:11
epoch [15/50] batch [80/200] time 1.092 (1.096) data 0.000 (0.008) loss 0.7131 (0.5229) lr 1.8443e-03 eta 2:10:05
epoch [15/50] batch [100/200] time 1.090 (1.094) data 0.000 (0.006) loss 0.2525 (0.5187) lr 1.8443e-03 eta 2:09:28
epoch [15/50] batch [120/200] time 1.080 (1.091) data 0.000 (0.005) loss 0.5023 (0.5162) lr 1.8443e-03 eta 2:08:46
epoch [15/50] batch [140/200] time 1.096 (1.090) data 0.000 (0.005) loss 0.5287 (0.4762) lr 1.8443e-03 eta 2:08:12
epoch [15/50] batch [160/200] time 1.083 (1.088) data 0.000 (0.004) loss 0.4556 (0.4788) lr 1.8443e-03 eta 2:07:39
epoch [15/50] batch [180/200] time 1.099 (1.087) data 0.000 (0.004) loss 0.0130 (0.4677) lr 1.8443e-03 eta 2:07:10
epoch [15/50] batch [200/200] time 1.083 (1.080) data 0.000 (0.003) loss 2.5807 (0.4795) lr 1.8090e-03 eta 2:06:01
epoch [16/50] batch [20/200] time 1.095 (1.104) data 0.000 (0.029) loss 0.0198 (0.2476) lr 1.8090e-03 eta 2:08:26
epoch [16/50] batch [40/200] time 1.078 (1.095) data 0.000 (0.015) loss 0.0041 (0.3715) lr 1.8090e-03 eta 2:06:58
epoch [16/50] batch [60/200] time 1.086 (1.093) data 0.000 (0.010) loss 0.0159 (0.3835) lr 1.8090e-03 eta 2:06:28
epoch [16/50] batch [80/200] time 1.087 (1.090) data 0.000 (0.008) loss 0.0074 (0.4130) lr 1.8090e-03 eta 2:05:43
epoch [16/50] batch [100/200] time 1.093 (1.090) data 0.000 (0.006) loss 0.0073 (0.4087) lr 1.8090e-03 eta 2:05:23
epoch [16/50] batch [120/200] time 1.087 (1.088) data 0.000 (0.005) loss 1.0351 (0.4159) lr 1.8090e-03 eta 2:04:48
epoch [16/50] batch [140/200] time 1.084 (1.088) data 0.000 (0.004) loss 0.2055 (0.4060) lr 1.8090e-03 eta 2:04:24
epoch [16/50] batch [160/200] time 1.093 (1.088) data 0.000 (0.004) loss 0.2316 (0.4326) lr 1.8090e-03 eta 2:04:00
epoch [16/50] batch [180/200] time 1.092 (1.087) data 0.000 (0.004) loss 1.7045 (0.4734) lr 1.8090e-03 eta 2:03:32
epoch [16/50] batch [200/200] time 0.834 (1.081) data 0.000 (0.003) loss 2.1641 (0.4706) lr 1.7705e-03 eta 2:02:29
epoch [17/50] batch [20/200] time 1.094 (1.109) data 0.000 (0.027) loss 0.4576 (0.5459) lr 1.7705e-03 eta 2:05:15
epoch [17/50] batch [40/200] time 1.089 (1.098) data 0.000 (0.014) loss 0.0837 (0.4361) lr 1.7705e-03 eta 2:03:43
epoch [17/50] batch [60/200] time 1.091 (1.091) data 0.000 (0.009) loss 0.0129 (0.4693) lr 1.7705e-03 eta 2:02:33
epoch [17/50] batch [80/200] time 1.091 (1.090) data 0.000 (0.007) loss 1.4773 (0.4197) lr 1.7705e-03 eta 2:02:01
epoch [17/50] batch [100/200] time 1.099 (1.090) data 0.000 (0.006) loss 0.0857 (0.4528) lr 1.7705e-03 eta 2:01:40
epoch [17/50] batch [120/200] time 1.086 (1.088) data 0.000 (0.005) loss 1.7554 (0.4822) lr 1.7705e-03 eta 2:01:05
epoch [17/50] batch [140/200] time 1.086 (1.088) data 0.000 (0.004) loss 1.1125 (0.4455) lr 1.7705e-03 eta 2:00:44
epoch [17/50] batch [160/200] time 1.096 (1.087) data 0.000 (0.004) loss 0.9555 (0.4226) lr 1.7705e-03 eta 2:00:17
epoch [17/50] batch [180/200] time 1.094 (1.087) data 0.000 (0.003) loss 0.0708 (0.4252) lr 1.7705e-03 eta 1:59:57
epoch [17/50] batch [200/200] time 1.096 (1.087) data 0.000 (0.003) loss 0.0298 (0.4472) lr 1.7290e-03 eta 1:59:37
epoch [18/50] batch [20/200] time 1.090 (1.031) data 0.000 (0.031) loss 0.4330 (0.3657) lr 1.7290e-03 eta 1:53:05
epoch [18/50] batch [40/200] time 1.089 (1.060) data 0.000 (0.016) loss 0.8674 (0.4303) lr 1.7290e-03 eta 1:55:51
epoch [18/50] batch [60/200] time 1.084 (1.066) data 0.000 (0.011) loss 0.0760 (0.4193) lr 1.7290e-03 eta 1:56:10
epoch [18/50] batch [80/200] time 1.088 (1.071) data 0.000 (0.008) loss 0.0142 (0.4333) lr 1.7290e-03 eta 1:56:23
epoch [18/50] batch [100/200] time 0.924 (1.073) data 0.000 (0.007) loss 0.0021 (0.4466) lr 1.7290e-03 eta 1:56:13
epoch [18/50] batch [120/200] time 1.087 (1.075) data 0.001 (0.006) loss 1.1180 (0.4458) lr 1.7290e-03 eta 1:56:06
epoch [18/50] batch [140/200] time 1.082 (1.077) data 0.000 (0.005) loss 0.0303 (0.4381) lr 1.7290e-03 eta 1:55:56
epoch [18/50] batch [160/200] time 1.092 (1.077) data 0.000 (0.004) loss 0.7742 (0.4570) lr 1.7290e-03 eta 1:55:34
epoch [18/50] batch [180/200] time 1.088 (1.078) data 0.000 (0.004) loss 0.6144 (0.4546) lr 1.7290e-03 eta 1:55:20
epoch [18/50] batch [200/200] time 1.069 (1.078) data 0.000 (0.003) loss 0.0012 (0.4810) lr 1.6845e-03 eta 1:54:57
epoch [19/50] batch [20/200] time 1.090 (1.045) data 0.000 (0.029) loss 0.5197 (0.4145) lr 1.6845e-03 eta 1:51:07
epoch [19/50] batch [40/200] time 1.086 (1.066) data 0.000 (0.015) loss 0.3020 (0.4784) lr 1.6845e-03 eta 1:52:57
epoch [19/50] batch [60/200] time 1.088 (1.070) data 0.000 (0.010) loss 1.2043 (0.4364) lr 1.6845e-03 eta 1:53:05
epoch [19/50] batch [80/200] time 1.092 (1.075) data 0.000 (0.007) loss 0.0978 (0.4638) lr 1.6845e-03 eta 1:53:10
epoch [19/50] batch [100/200] time 1.077 (1.075) data 0.000 (0.006) loss 0.0056 (0.4194) lr 1.6845e-03 eta 1:52:53
epoch [19/50] batch [120/200] time 1.091 (1.077) data 0.000 (0.005) loss 0.0260 (0.4324) lr 1.6845e-03 eta 1:52:43
epoch [19/50] batch [140/200] time 1.079 (1.078) data 0.000 (0.004) loss 0.5116 (0.4162) lr 1.6845e-03 eta 1:52:30
epoch [19/50] batch [160/200] time 1.090 (1.079) data 0.000 (0.004) loss 0.6841 (0.4274) lr 1.6845e-03 eta 1:52:10
epoch [19/50] batch [180/200] time 1.094 (1.080) data 0.000 (0.004) loss 0.6796 (0.4523) lr 1.6845e-03 eta 1:51:56
epoch [19/50] batch [200/200] time 1.097 (1.080) data 0.000 (0.003) loss 0.5745 (0.4485) lr 1.6374e-03 eta 1:51:35
epoch [20/50] batch [20/200] time 0.896 (1.110) data 0.000 (0.029) loss 1.3043 (0.4289) lr 1.6374e-03 eta 1:54:18
epoch [20/50] batch [40/200] time 1.091 (1.072) data 0.000 (0.015) loss 0.1763 (0.5379) lr 1.6374e-03 eta 1:50:03
epoch [20/50] batch [60/200] time 1.079 (1.077) data 0.000 (0.010) loss 0.0417 (0.5601) lr 1.6374e-03 eta 1:50:13
epoch [20/50] batch [80/200] time 1.093 (1.080) data 0.000 (0.008) loss 0.0412 (0.5200) lr 1.6374e-03 eta 1:50:10
epoch [20/50] batch [100/200] time 1.100 (1.076) data 0.000 (0.006) loss 0.0783 (0.5359) lr 1.6374e-03 eta 1:49:21
epoch [20/50] batch [120/200] time 1.118 (1.081) data 0.000 (0.005) loss 1.6195 (0.5254) lr 1.6374e-03 eta 1:49:34
epoch [20/50] batch [140/200] time 1.115 (1.084) data 0.003 (0.005) loss 0.2285 (0.5229) lr 1.6374e-03 eta 1:49:27
epoch [20/50] batch [160/200] time 1.110 (1.087) data 0.000 (0.004) loss 0.2874 (0.5233) lr 1.6374e-03 eta 1:49:23
epoch [20/50] batch [180/200] time 1.105 (1.087) data 0.015 (0.004) loss 0.0720 (0.5359) lr 1.6374e-03 eta 1:49:04
epoch [20/50] batch [200/200] time 1.096 (1.086) data 0.000 (0.004) loss 1.8724 (0.5351) lr 1.5878e-03 eta 1:48:37
epoch [21/50] batch [20/200] time 1.092 (1.103) data 0.000 (0.027) loss 1.3577 (0.4682) lr 1.5878e-03 eta 1:49:57
epoch [21/50] batch [40/200] time 1.086 (1.044) data 0.000 (0.014) loss 0.6581 (0.4727) lr 1.5878e-03 eta 1:43:41
epoch [21/50] batch [60/200] time 1.086 (1.056) data 0.000 (0.009) loss 1.2575 (0.5392) lr 1.5878e-03 eta 1:44:31
epoch [21/50] batch [80/200] time 0.964 (1.062) data 0.010 (0.007) loss 0.2061 (0.5665) lr 1.5878e-03 eta 1:44:44
epoch [21/50] batch [100/200] time 1.106 (1.068) data 0.000 (0.006) loss 0.0194 (0.5416) lr 1.5878e-03 eta 1:45:03
epoch [21/50] batch [120/200] time 1.083 (1.073) data 0.000 (0.005) loss 0.4946 (0.5289) lr 1.5878e-03 eta 1:45:06
epoch [21/50] batch [140/200] time 1.095 (1.076) data 0.000 (0.004) loss 0.0877 (0.5282) lr 1.5878e-03 eta 1:45:04
epoch [21/50] batch [160/200] time 1.096 (1.076) data 0.000 (0.004) loss 0.7046 (0.5043) lr 1.5878e-03 eta 1:44:46
epoch [21/50] batch [180/200] time 1.088 (1.078) data 0.000 (0.003) loss 1.2118 (0.5003) lr 1.5878e-03 eta 1:44:33
epoch [21/50] batch [200/200] time 1.099 (1.079) data 0.000 (0.003) loss 0.4070 (0.5077) lr 1.5358e-03 eta 1:44:16
epoch [22/50] batch [20/200] time 1.095 (1.107) data 0.000 (0.028) loss 0.2459 (0.3434) lr 1.5358e-03 eta 1:46:40
epoch [22/50] batch [40/200] time 0.846 (1.081) data 0.010 (0.015) loss 0.1524 (0.4386) lr 1.5358e-03 eta 1:43:47
epoch [22/50] batch [60/200] time 1.089 (1.064) data 0.000 (0.010) loss 0.0250 (0.4259) lr 1.5358e-03 eta 1:41:49
epoch [22/50] batch [80/200] time 1.088 (1.070) data 0.000 (0.008) loss 1.0419 (0.4139) lr 1.5358e-03 eta 1:42:02
epoch [22/50] batch [100/200] time 1.087 (1.072) data 0.000 (0.006) loss 0.1702 (0.4232) lr 1.5358e-03 eta 1:41:49
epoch [22/50] batch [120/200] time 1.069 (1.075) data 0.000 (0.005) loss 0.4090 (0.4342) lr 1.5358e-03 eta 1:41:44
epoch [22/50] batch [140/200] time 1.090 (1.077) data 0.000 (0.005) loss 0.1609 (0.4301) lr 1.5358e-03 eta 1:41:35
epoch [22/50] batch [160/200] time 1.077 (1.077) data 0.000 (0.004) loss 0.0010 (0.4436) lr 1.5358e-03 eta 1:41:14
epoch [22/50] batch [180/200] time 1.095 (1.078) data 0.000 (0.004) loss 1.8175 (0.4591) lr 1.5358e-03 eta 1:41:00
epoch [22/50] batch [200/200] time 1.085 (1.078) data 0.000 (0.003) loss 0.8293 (0.4620) lr 1.4818e-03 eta 1:40:37
epoch [23/50] batch [20/200] time 1.087 (1.117) data 0.000 (0.028) loss 0.0056 (0.3705) lr 1.4818e-03 eta 1:43:53
epoch [23/50] batch [40/200] time 1.090 (1.104) data 0.000 (0.014) loss 1.6991 (0.3885) lr 1.4818e-03 eta 1:42:16
epoch [23/50] batch [60/200] time 1.082 (1.076) data 0.000 (0.010) loss 0.4209 (0.4283) lr 1.4818e-03 eta 1:39:22
epoch [23/50] batch [80/200] time 1.083 (1.080) data 0.000 (0.007) loss 0.3417 (0.4646) lr 1.4818e-03 eta 1:39:19
epoch [23/50] batch [100/200] time 1.086 (1.080) data 0.000 (0.006) loss 0.8350 (0.5058) lr 1.4818e-03 eta 1:39:00
epoch [23/50] batch [120/200] time 1.082 (1.082) data 0.000 (0.005) loss 0.0028 (0.4789) lr 1.4818e-03 eta 1:38:47
epoch [23/50] batch [140/200] time 0.906 (1.081) data 0.000 (0.004) loss 0.0562 (0.4658) lr 1.4818e-03 eta 1:38:23
epoch [23/50] batch [160/200] time 1.082 (1.082) data 0.000 (0.004) loss 1.3596 (0.4780) lr 1.4818e-03 eta 1:38:05
epoch [23/50] batch [180/200] time 1.096 (1.082) data 0.000 (0.003) loss 0.3791 (0.4851) lr 1.4818e-03 eta 1:37:46
epoch [23/50] batch [200/200] time 1.085 (1.082) data 0.000 (0.003) loss 1.4156 (0.5004) lr 1.4258e-03 eta 1:37:24
epoch [24/50] batch [20/200] time 1.077 (1.121) data 0.000 (0.029) loss 0.0291 (0.4105) lr 1.4258e-03 eta 1:40:28
epoch [24/50] batch [40/200] time 1.101 (1.099) data 0.000 (0.015) loss 0.8191 (0.4824) lr 1.4258e-03 eta 1:38:09
epoch [24/50] batch [60/200] time 0.960 (1.080) data 0.001 (0.010) loss 0.1773 (0.5199) lr 1.4258e-03 eta 1:36:08
epoch [24/50] batch [80/200] time 1.084 (1.077) data 0.000 (0.008) loss 1.0332 (0.5222) lr 1.4258e-03 eta 1:35:27
epoch [24/50] batch [100/200] time 1.080 (1.076) data 0.000 (0.006) loss 0.9786 (0.5134) lr 1.4258e-03 eta 1:35:03
epoch [24/50] batch [120/200] time 1.094 (1.078) data 0.000 (0.005) loss 1.0456 (0.5134) lr 1.4258e-03 eta 1:34:52
epoch [24/50] batch [140/200] time 1.091 (1.078) data 0.007 (0.005) loss 0.5460 (0.4836) lr 1.4258e-03 eta 1:34:29
epoch [24/50] batch [160/200] time 1.097 (1.079) data 0.000 (0.004) loss 0.8716 (0.4882) lr 1.4258e-03 eta 1:34:16
epoch [24/50] batch [180/200] time 1.103 (1.080) data 0.000 (0.004) loss 0.0066 (0.4569) lr 1.4258e-03 eta 1:33:59
epoch [24/50] batch [200/200] time 1.107 (1.080) data 0.000 (0.003) loss 0.6734 (0.4653) lr 1.3681e-03 eta 1:33:38
epoch [25/50] batch [20/200] time 1.102 (1.115) data 0.000 (0.028) loss 0.3621 (0.5446) lr 1.3681e-03 eta 1:36:14
epoch [25/50] batch [40/200] time 1.095 (1.095) data 0.000 (0.014) loss 0.0054 (0.5362) lr 1.3681e-03 eta 1:34:11
epoch [25/50] batch [60/200] time 1.083 (1.093) data 0.000 (0.010) loss 0.1078 (0.5207) lr 1.3681e-03 eta 1:33:39
epoch [25/50] batch [80/200] time 1.086 (1.075) data 0.000 (0.007) loss 0.6059 (0.4673) lr 1.3681e-03 eta 1:31:43
epoch [25/50] batch [100/200] time 1.088 (1.077) data 0.000 (0.006) loss 0.6560 (0.4900) lr 1.3681e-03 eta 1:31:32
epoch [25/50] batch [120/200] time 1.087 (1.079) data 0.002 (0.005) loss 0.8246 (0.4928) lr 1.3681e-03 eta 1:31:20
epoch [25/50] batch [140/200] time 1.100 (1.078) data 0.000 (0.005) loss 0.7125 (0.5361) lr 1.3681e-03 eta 1:30:56
epoch [25/50] batch [160/200] time 1.089 (1.080) data 0.000 (0.004) loss 0.3131 (0.5423) lr 1.3681e-03 eta 1:30:40
epoch [25/50] batch [180/200] time 1.083 (1.080) data 0.000 (0.004) loss 0.3433 (0.5235) lr 1.3681e-03 eta 1:30:19
epoch [25/50] batch [200/200] time 1.097 (1.081) data 0.000 (0.003) loss 0.0001 (0.5106) lr 1.3090e-03 eta 1:30:03
epoch [26/50] batch [20/200] time 1.024 (1.091) data 0.000 (0.027) loss 0.0224 (0.2494) lr 1.3090e-03 eta 1:30:33
epoch [26/50] batch [40/200] time 1.099 (1.098) data 0.000 (0.014) loss 0.3933 (0.3614) lr 1.3090e-03 eta 1:30:47
epoch [26/50] batch [60/200] time 1.095 (1.103) data 0.001 (0.009) loss 0.4663 (0.3605) lr 1.3090e-03 eta 1:30:48
epoch [26/50] batch [80/200] time 1.124 (1.090) data 0.000 (0.008) loss 0.0044 (0.3664) lr 1.3090e-03 eta 1:29:23
epoch [26/50] batch [100/200] time 1.091 (1.078) data 0.000 (0.006) loss 0.0085 (0.3730) lr 1.3090e-03 eta 1:28:04
epoch [26/50] batch [120/200] time 1.078 (1.079) data 0.000 (0.005) loss 1.7367 (0.3936) lr 1.3090e-03 eta 1:27:43
epoch [26/50] batch [140/200] time 1.092 (1.080) data 0.000 (0.005) loss 0.2033 (0.3840) lr 1.3090e-03 eta 1:27:27
epoch [26/50] batch [160/200] time 1.103 (1.079) data 0.000 (0.004) loss 0.0276 (0.3909) lr 1.3090e-03 eta 1:27:04
epoch [26/50] batch [180/200] time 1.083 (1.080) data 0.000 (0.004) loss 1.8487 (0.4012) lr 1.3090e-03 eta 1:26:43
epoch [26/50] batch [200/200] time 1.086 (1.079) data 0.000 (0.003) loss 0.5589 (0.4022) lr 1.2487e-03 eta 1:26:20
epoch [27/50] batch [20/200] time 1.089 (1.109) data 0.000 (0.028) loss 1.5702 (0.6351) lr 1.2487e-03 eta 1:28:19
epoch [27/50] batch [40/200] time 1.095 (1.092) data 0.000 (0.014) loss 1.5130 (0.5648) lr 1.2487e-03 eta 1:26:36
epoch [27/50] batch [60/200] time 1.112 (1.093) data 0.001 (0.010) loss 0.0061 (0.5797) lr 1.2487e-03 eta 1:26:22
epoch [27/50] batch [80/200] time 1.087 (1.094) data 0.000 (0.007) loss 0.1196 (0.5792) lr 1.2487e-03 eta 1:26:04
epoch [27/50] batch [100/200] time 1.097 (1.080) data 0.000 (0.006) loss 0.1008 (0.5421) lr 1.2487e-03 eta 1:24:35
epoch [27/50] batch [120/200] time 1.104 (1.082) data 0.000 (0.005) loss 0.2626 (0.5090) lr 1.2487e-03 eta 1:24:25
epoch [27/50] batch [140/200] time 1.095 (1.085) data 0.000 (0.004) loss 1.5009 (0.5070) lr 1.2487e-03 eta 1:24:14
epoch [27/50] batch [160/200] time 1.088 (1.084) data 0.000 (0.004) loss 0.2057 (0.4957) lr 1.2487e-03 eta 1:23:49
epoch [27/50] batch [180/200] time 1.087 (1.084) data 0.000 (0.003) loss 0.6218 (0.4924) lr 1.2487e-03 eta 1:23:29
epoch [27/50] batch [200/200] time 1.095 (1.085) data 0.000 (0.003) loss 0.0248 (0.4779) lr 1.1874e-03 eta 1:23:11
epoch [28/50] batch [20/200] time 1.086 (1.106) data 0.000 (0.029) loss 0.0061 (0.3905) lr 1.1874e-03 eta 1:24:23
epoch [28/50] batch [40/200] time 1.088 (1.097) data 0.000 (0.015) loss 0.0232 (0.4598) lr 1.1874e-03 eta 1:23:23
epoch [28/50] batch [60/200] time 1.086 (1.092) data 0.000 (0.010) loss 0.0184 (0.4881) lr 1.1874e-03 eta 1:22:37
epoch [28/50] batch [80/200] time 1.085 (1.091) data 0.000 (0.007) loss 0.0422 (0.4661) lr 1.1874e-03 eta 1:22:13
epoch [28/50] batch [100/200] time 0.811 (1.075) data 0.000 (0.006) loss 1.1343 (0.5039) lr 1.1874e-03 eta 1:20:38
epoch [28/50] batch [120/200] time 1.091 (1.076) data 0.000 (0.005) loss 0.2541 (0.5081) lr 1.1874e-03 eta 1:20:19
epoch [28/50] batch [140/200] time 1.089 (1.078) data 0.000 (0.004) loss 0.0080 (0.4770) lr 1.1874e-03 eta 1:20:06
epoch [28/50] batch [160/200] time 1.069 (1.078) data 0.000 (0.004) loss 0.4131 (0.4503) lr 1.1874e-03 eta 1:19:46
epoch [28/50] batch [180/200] time 1.086 (1.079) data 0.000 (0.003) loss 0.0049 (0.4499) lr 1.1874e-03 eta 1:19:28
epoch [28/50] batch [200/200] time 1.097 (1.079) data 0.000 (0.003) loss 0.0013 (0.4291) lr 1.1253e-03 eta 1:19:06
epoch [29/50] batch [20/200] time 1.084 (1.120) data 0.000 (0.032) loss 0.3988 (0.4703) lr 1.1253e-03 eta 1:21:44
epoch [29/50] batch [40/200] time 1.087 (1.104) data 0.000 (0.016) loss 0.0103 (0.4534) lr 1.1253e-03 eta 1:20:11
epoch [29/50] batch [60/200] time 1.089 (1.096) data 0.000 (0.011) loss 0.0120 (0.4627) lr 1.1253e-03 eta 1:19:16
epoch [29/50] batch [80/200] time 1.093 (1.093) data 0.000 (0.008) loss 1.0559 (0.4418) lr 1.1253e-03 eta 1:18:42
epoch [29/50] batch [100/200] time 1.094 (1.091) data 0.011 (0.007) loss 0.6640 (0.4262) lr 1.1253e-03 eta 1:18:10
epoch [29/50] batch [120/200] time 1.088 (1.082) data 0.000 (0.006) loss 0.6170 (0.4340) lr 1.1253e-03 eta 1:17:09
epoch [29/50] batch [140/200] time 0.987 (1.082) data 0.000 (0.005) loss 1.5450 (0.4308) lr 1.1253e-03 eta 1:16:49
epoch [29/50] batch [160/200] time 1.092 (1.083) data 0.000 (0.004) loss 0.2335 (0.4574) lr 1.1253e-03 eta 1:16:31
epoch [29/50] batch [180/200] time 1.085 (1.083) data 0.000 (0.004) loss 0.3202 (0.4705) lr 1.1253e-03 eta 1:16:12
epoch [29/50] batch [200/200] time 1.075 (1.083) data 0.000 (0.004) loss 0.2477 (0.4701) lr 1.0628e-03 eta 1:15:48
epoch [30/50] batch [20/200] time 1.084 (1.121) data 0.000 (0.031) loss 0.0066 (0.2671) lr 1.0628e-03 eta 1:18:07
epoch [30/50] batch [40/200] time 1.100 (1.100) data 0.000 (0.016) loss 0.0864 (0.3887) lr 1.0628e-03 eta 1:16:16
epoch [30/50] batch [60/200] time 1.099 (1.096) data 0.000 (0.011) loss 0.0911 (0.4101) lr 1.0628e-03 eta 1:15:38
epoch [30/50] batch [80/200] time 1.080 (1.094) data 0.000 (0.008) loss 0.0185 (0.3828) lr 1.0628e-03 eta 1:15:09
epoch [30/50] batch [100/200] time 1.088 (1.091) data 0.000 (0.007) loss 0.3761 (0.3943) lr 1.0628e-03 eta 1:14:34
epoch [30/50] batch [120/200] time 1.087 (1.081) data 0.000 (0.006) loss 0.5176 (0.4433) lr 1.0628e-03 eta 1:13:29
epoch [30/50] batch [140/200] time 1.080 (1.081) data 0.000 (0.005) loss 0.0297 (0.4380) lr 1.0628e-03 eta 1:13:07
epoch [30/50] batch [160/200] time 1.082 (1.082) data 0.000 (0.004) loss 0.0793 (0.4277) lr 1.0628e-03 eta 1:12:51
epoch [30/50] batch [180/200] time 1.088 (1.082) data 0.000 (0.004) loss 0.1157 (0.4379) lr 1.0628e-03 eta 1:12:31
epoch [30/50] batch [200/200] time 1.090 (1.082) data 0.000 (0.003) loss 2.0032 (0.4450) lr 1.0000e-03 eta 1:12:09
epoch [31/50] batch [20/200] time 1.086 (1.116) data 0.000 (0.029) loss 0.7059 (0.3733) lr 1.0000e-03 eta 1:14:02
epoch [31/50] batch [40/200] time 1.083 (1.097) data 0.000 (0.015) loss 0.7927 (0.3882) lr 1.0000e-03 eta 1:12:24
epoch [31/50] batch [60/200] time 1.083 (1.094) data 0.000 (0.010) loss 1.3861 (0.4476) lr 1.0000e-03 eta 1:11:51
epoch [31/50] batch [80/200] time 1.098 (1.091) data 0.000 (0.007) loss 0.0558 (0.4718) lr 1.0000e-03 eta 1:11:16
epoch [31/50] batch [100/200] time 1.093 (1.091) data 0.004 (0.006) loss 0.5147 (0.4907) lr 1.0000e-03 eta 1:10:53
epoch [31/50] batch [120/200] time 0.561 (1.083) data 0.000 (0.005) loss 0.3260 (0.4653) lr 1.0000e-03 eta 1:10:01
epoch [31/50] batch [140/200] time 0.860 (1.053) data 0.000 (0.005) loss 0.5444 (0.4653) lr 1.0000e-03 eta 1:07:45
epoch [31/50] batch [160/200] time 0.994 (1.037) data 0.000 (0.004) loss 0.2910 (0.4345) lr 1.0000e-03 eta 1:06:21
epoch [31/50] batch [180/200] time 0.865 (1.022) data 0.000 (0.004) loss 0.0023 (0.4301) lr 1.0000e-03 eta 1:05:02
epoch [31/50] batch [200/200] time 0.870 (1.014) data 0.000 (0.003) loss 1.9334 (0.4210) lr 9.3721e-04 eta 1:04:13
epoch [32/50] batch [20/200] time 0.862 (0.936) data 0.000 (0.029) loss 2.0965 (0.6036) lr 9.3721e-04 eta 0:58:59
epoch [32/50] batch [40/200] time 0.837 (0.899) data 0.000 (0.015) loss 0.0044 (0.5403) lr 9.3721e-04 eta 0:56:21
epoch [32/50] batch [60/200] time 0.836 (0.882) data 0.001 (0.010) loss 0.8142 (0.4919) lr 9.3721e-04 eta 0:54:57
epoch [32/50] batch [80/200] time 0.972 (0.884) data 0.000 (0.008) loss 0.2128 (0.4585) lr 9.3721e-04 eta 0:54:48
epoch [32/50] batch [100/200] time 0.890 (0.886) data 0.000 (0.007) loss 0.0147 (0.4204) lr 9.3721e-04 eta 0:54:39
epoch [32/50] batch [120/200] time 0.966 (0.890) data 0.000 (0.006) loss 0.0262 (0.4507) lr 9.3721e-04 eta 0:54:33
epoch [32/50] batch [140/200] time 0.827 (0.892) data 0.000 (0.005) loss 0.2763 (0.4303) lr 9.3721e-04 eta 0:54:23
epoch [32/50] batch [160/200] time 0.840 (0.890) data 0.000 (0.004) loss 0.9027 (0.4703) lr 9.3721e-04 eta 0:53:58
epoch [32/50] batch [180/200] time 0.848 (0.883) data 0.000 (0.004) loss 0.2290 (0.4722) lr 9.3721e-04 eta 0:53:16
epoch [32/50] batch [200/200] time 1.071 (0.889) data 0.000 (0.004) loss 0.0047 (0.4615) lr 8.7467e-04 eta 0:53:19
epoch [33/50] batch [20/200] time 1.074 (1.084) data 0.000 (0.030) loss 0.2972 (0.3856) lr 8.7467e-04 eta 1:04:42
epoch [33/50] batch [40/200] time 1.027 (1.067) data 0.000 (0.015) loss 0.6636 (0.3668) lr 8.7467e-04 eta 1:03:16
epoch [33/50] batch [60/200] time 1.059 (1.055) data 0.000 (0.010) loss 1.0090 (0.4320) lr 8.7467e-04 eta 1:02:13
epoch [33/50] batch [80/200] time 1.086 (1.054) data 0.000 (0.008) loss 0.0457 (0.4402) lr 8.7467e-04 eta 1:01:49
epoch [33/50] batch [100/200] time 1.060 (1.057) data 0.000 (0.006) loss 1.3434 (0.4644) lr 8.7467e-04 eta 1:01:39
epoch [33/50] batch [120/200] time 0.976 (1.056) data 0.000 (0.005) loss 0.0905 (0.4664) lr 8.7467e-04 eta 1:01:15
epoch [33/50] batch [140/200] time 1.063 (1.055) data 0.000 (0.005) loss 0.7320 (0.4552) lr 8.7467e-04 eta 1:00:51
epoch [33/50] batch [160/200] time 1.065 (1.057) data 0.000 (0.004) loss 0.0045 (0.4519) lr 8.7467e-04 eta 1:00:37
epoch [33/50] batch [180/200] time 1.063 (1.059) data 0.000 (0.004) loss 0.7021 (0.4527) lr 8.7467e-04 eta 1:00:22
epoch [33/50] batch [200/200] time 1.074 (1.056) data 0.000 (0.003) loss 0.2295 (0.4560) lr 8.1262e-04 eta 0:59:50
epoch [34/50] batch [20/200] time 1.058 (1.100) data 0.000 (0.028) loss 2.2022 (0.4143) lr 8.1262e-04 eta 1:01:57
epoch [34/50] batch [40/200] time 1.065 (1.079) data 0.000 (0.014) loss 0.0027 (0.4441) lr 8.1262e-04 eta 1:00:24
epoch [34/50] batch [60/200] time 1.065 (1.059) data 0.000 (0.010) loss 0.2456 (0.4994) lr 8.1262e-04 eta 0:58:57
epoch [34/50] batch [80/200] time 1.061 (1.057) data 0.000 (0.007) loss 0.2781 (0.4534) lr 8.1262e-04 eta 0:58:30
epoch [34/50] batch [100/200] time 1.051 (1.058) data 0.000 (0.006) loss 1.0392 (0.4350) lr 8.1262e-04 eta 0:58:12
epoch [34/50] batch [120/200] time 0.836 (1.057) data 0.000 (0.005) loss 0.0608 (0.4434) lr 8.1262e-04 eta 0:57:45
epoch [34/50] batch [140/200] time 1.066 (1.054) data 0.000 (0.005) loss 0.0054 (0.4430) lr 8.1262e-04 eta 0:57:16
epoch [34/50] batch [160/200] time 1.056 (1.055) data 0.000 (0.004) loss 1.0373 (0.4443) lr 8.1262e-04 eta 0:56:58
epoch [34/50] batch [180/200] time 1.064 (1.055) data 0.000 (0.004) loss 1.3752 (0.4266) lr 8.1262e-04 eta 0:56:35
epoch [34/50] batch [200/200] time 1.059 (1.052) data 0.000 (0.003) loss 0.8496 (0.4182) lr 7.5131e-04 eta 0:56:06
epoch [35/50] batch [20/200] time 1.060 (1.089) data 0.000 (0.030) loss 0.4165 (0.3443) lr 7.5131e-04 eta 0:57:42
epoch [35/50] batch [40/200] time 1.050 (1.070) data 0.000 (0.015) loss 0.9262 (0.3481) lr 7.5131e-04 eta 0:56:22
epoch [35/50] batch [60/200] time 1.116 (1.041) data 0.001 (0.010) loss 0.0034 (0.3550) lr 7.5131e-04 eta 0:54:27
epoch [35/50] batch [80/200] time 0.833 (1.008) data 0.000 (0.008) loss 0.8456 (0.4233) lr 7.5131e-04 eta 0:52:26
epoch [35/50] batch [100/200] time 0.857 (0.977) data 0.000 (0.007) loss 0.3533 (0.4289) lr 7.5131e-04 eta 0:50:28
epoch [35/50] batch [120/200] time 0.775 (0.973) data 0.000 (0.006) loss 0.0500 (0.4879) lr 7.5131e-04 eta 0:49:55
epoch [35/50] batch [140/200] time 0.830 (0.952) data 0.000 (0.005) loss 0.3706 (0.4694) lr 7.5131e-04 eta 0:48:33
epoch [35/50] batch [160/200] time 1.055 (0.949) data 0.000 (0.004) loss 0.0329 (0.4915) lr 7.5131e-04 eta 0:48:03
epoch [35/50] batch [180/200] time 1.051 (0.955) data 0.000 (0.004) loss 0.1329 (0.4742) lr 7.5131e-04 eta 0:48:04
epoch [35/50] batch [200/200] time 1.035 (0.963) data 0.000 (0.004) loss 0.0040 (0.4627) lr 6.9098e-04 eta 0:48:10
epoch [36/50] batch [20/200] time 1.026 (1.058) data 0.000 (0.040) loss 0.0048 (0.3926) lr 6.9098e-04 eta 0:52:32
epoch [36/50] batch [40/200] time 1.047 (1.040) data 0.000 (0.020) loss 0.0766 (0.4731) lr 6.9098e-04 eta 0:51:17
epoch [36/50] batch [60/200] time 1.036 (1.030) data 0.001 (0.014) loss 0.0227 (0.4764) lr 6.9098e-04 eta 0:50:28
epoch [36/50] batch [80/200] time 0.912 (1.026) data 0.000 (0.010) loss 1.0192 (0.4334) lr 6.9098e-04 eta 0:49:55
epoch [36/50] batch [100/200] time 1.036 (1.028) data 0.000 (0.008) loss 0.0107 (0.4475) lr 6.9098e-04 eta 0:49:42
epoch [36/50] batch [120/200] time 1.039 (1.025) data 0.000 (0.007) loss 0.0702 (0.4541) lr 6.9098e-04 eta 0:49:11
epoch [36/50] batch [140/200] time 0.831 (1.017) data 0.000 (0.006) loss 0.0009 (0.4571) lr 6.9098e-04 eta 0:48:30
epoch [36/50] batch [160/200] time 0.853 (0.995) data 0.000 (0.005) loss 0.5324 (0.4214) lr 6.9098e-04 eta 0:47:07
epoch [36/50] batch [180/200] time 0.829 (0.980) data 0.000 (0.005) loss 0.8703 (0.4021) lr 6.9098e-04 eta 0:46:03
epoch [36/50] batch [200/200] time 0.855 (0.966) data 0.000 (0.004) loss 0.0320 (0.3829) lr 6.3188e-04 eta 0:45:04
epoch [37/50] batch [20/200] time 0.995 (0.897) data 0.003 (0.029) loss 0.4476 (0.4646) lr 6.3188e-04 eta 0:41:32
epoch [37/50] batch [40/200] time 0.981 (0.883) data 0.000 (0.015) loss 0.0221 (0.4647) lr 6.3188e-04 eta 0:40:37
epoch [37/50] batch [60/200] time 1.149 (0.902) data 0.001 (0.010) loss 0.1466 (0.5337) lr 6.3188e-04 eta 0:41:11
epoch [37/50] batch [80/200] time 0.852 (0.903) data 0.000 (0.007) loss 0.2198 (0.5460) lr 6.3188e-04 eta 0:40:55
epoch [37/50] batch [100/200] time 0.871 (0.897) data 0.000 (0.006) loss 0.0173 (0.5328) lr 6.3188e-04 eta 0:40:21
epoch [37/50] batch [120/200] time 0.838 (0.893) data 0.000 (0.005) loss 0.2900 (0.5284) lr 6.3188e-04 eta 0:39:54
epoch [37/50] batch [140/200] time 0.850 (0.886) data 0.000 (0.005) loss 0.0213 (0.5112) lr 6.3188e-04 eta 0:39:17
epoch [37/50] batch [160/200] time 1.039 (0.894) data 0.000 (0.004) loss 0.9186 (0.4990) lr 6.3188e-04 eta 0:39:20
epoch [37/50] batch [180/200] time 1.031 (0.906) data 0.000 (0.004) loss 0.2955 (0.4972) lr 6.3188e-04 eta 0:39:32
epoch [37/50] batch [200/200] time 0.961 (0.918) data 0.000 (0.003) loss 0.3156 (0.5095) lr 5.7422e-04 eta 0:39:47
epoch [38/50] batch [20/200] time 1.045 (1.084) data 0.001 (0.056) loss 0.2126 (0.3662) lr 5.7422e-04 eta 0:46:37
epoch [38/50] batch [40/200] time 1.038 (1.036) data 0.000 (0.028) loss 0.0041 (0.4060) lr 5.7422e-04 eta 0:44:13
epoch [38/50] batch [60/200] time 1.038 (1.017) data 0.001 (0.019) loss 0.0169 (0.3922) lr 5.7422e-04 eta 0:43:02
epoch [38/50] batch [80/200] time 1.047 (1.021) data 0.002 (0.014) loss 1.2986 (0.3999) lr 5.7422e-04 eta 0:42:54
epoch [38/50] batch [100/200] time 1.030 (1.013) data 0.001 (0.012) loss 0.0482 (0.3979) lr 5.7422e-04 eta 0:42:11
epoch [38/50] batch [120/200] time 1.030 (1.011) data 0.000 (0.010) loss 0.1208 (0.4086) lr 5.7422e-04 eta 0:41:47
epoch [38/50] batch [140/200] time 0.827 (1.011) data 0.000 (0.008) loss 0.0109 (0.3976) lr 5.7422e-04 eta 0:41:28
epoch [38/50] batch [160/200] time 1.045 (1.012) data 0.000 (0.007) loss 0.4212 (0.3900) lr 5.7422e-04 eta 0:41:10
epoch [38/50] batch [180/200] time 0.831 (1.004) data 0.000 (0.007) loss 0.4671 (0.4005) lr 5.7422e-04 eta 0:40:29
epoch [38/50] batch [200/200] time 0.846 (0.986) data 0.000 (0.006) loss 0.0040 (0.4022) lr 5.1825e-04 eta 0:39:26
epoch [39/50] batch [20/200] time 0.822 (0.911) data 0.000 (0.036) loss 1.2349 (0.4407) lr 5.1825e-04 eta 0:36:07
epoch [39/50] batch [40/200] time 0.743 (0.871) data 0.000 (0.018) loss 0.3939 (0.4191) lr 5.1825e-04 eta 0:34:15
epoch [39/50] batch [60/200] time 1.116 (0.880) data 0.001 (0.013) loss 0.9795 (0.4310) lr 5.1825e-04 eta 0:34:18
epoch [39/50] batch [80/200] time 1.115 (0.935) data 0.000 (0.010) loss 0.0079 (0.4037) lr 5.1825e-04 eta 0:36:10
epoch [39/50] batch [100/200] time 1.106 (0.969) data 0.000 (0.008) loss 0.2215 (0.4538) lr 5.1825e-04 eta 0:37:07
epoch [39/50] batch [120/200] time 1.103 (0.990) data 0.000 (0.007) loss 0.8970 (0.4297) lr 5.1825e-04 eta 0:37:37
epoch [39/50] batch [140/200] time 0.913 (1.005) data 0.000 (0.006) loss 0.9326 (0.4407) lr 5.1825e-04 eta 0:37:52
epoch [39/50] batch [160/200] time 1.109 (1.019) data 0.000 (0.005) loss 0.4650 (0.4358) lr 5.1825e-04 eta 0:38:01
epoch [39/50] batch [180/200] time 1.133 (1.028) data 0.004 (0.004) loss 0.0434 (0.4317) lr 5.1825e-04 eta 0:38:02
epoch [39/50] batch [200/200] time 1.119 (1.038) data 0.000 (0.004) loss 0.1800 (0.4410) lr 4.6417e-04 eta 0:38:02
epoch [40/50] batch [20/200] time 1.130 (1.150) data 0.000 (0.028) loss 0.1212 (0.5325) lr 4.6417e-04 eta 0:41:48
epoch [40/50] batch [40/200] time 1.128 (1.137) data 0.000 (0.014) loss 0.4156 (0.4779) lr 4.6417e-04 eta 0:40:55
epoch [40/50] batch [60/200] time 1.109 (1.132) data 0.000 (0.010) loss 0.0666 (0.5065) lr 4.6417e-04 eta 0:40:21
epoch [40/50] batch [80/200] time 1.130 (1.129) data 0.000 (0.007) loss 0.2500 (0.5098) lr 4.6417e-04 eta 0:39:53
epoch [40/50] batch [100/200] time 1.103 (1.127) data 0.002 (0.006) loss 0.0160 (0.4353) lr 4.6417e-04 eta 0:39:27
epoch [40/50] batch [120/200] time 1.121 (1.126) data 0.000 (0.005) loss 1.4979 (0.4666) lr 4.6417e-04 eta 0:39:02
epoch [40/50] batch [140/200] time 1.122 (1.125) data 0.000 (0.004) loss 0.2346 (0.4834) lr 4.6417e-04 eta 0:38:37
epoch [40/50] batch [160/200] time 1.116 (1.125) data 0.000 (0.004) loss 0.0098 (0.4860) lr 4.6417e-04 eta 0:38:14
epoch [40/50] batch [180/200] time 1.132 (1.125) data 0.000 (0.003) loss 0.2568 (0.4820) lr 4.6417e-04 eta 0:37:51
epoch [40/50] batch [200/200] time 1.116 (1.123) data 0.000 (0.003) loss 0.0626 (0.4727) lr 4.1221e-04 eta 0:37:25
epoch [41/50] batch [20/200] time 1.108 (1.141) data 0.000 (0.029) loss 1.0425 (0.3631) lr 4.1221e-04 eta 0:37:38
epoch [41/50] batch [40/200] time 1.117 (1.123) data 0.000 (0.015) loss 0.2334 (0.4272) lr 4.1221e-04 eta 0:36:41
epoch [41/50] batch [60/200] time 1.113 (1.119) data 0.001 (0.010) loss 0.0007 (0.4253) lr 4.1221e-04 eta 0:36:11
epoch [41/50] batch [80/200] time 1.102 (1.116) data 0.000 (0.008) loss 0.5131 (0.3963) lr 4.1221e-04 eta 0:35:43
epoch [41/50] batch [100/200] time 1.108 (1.113) data 0.000 (0.006) loss 0.0232 (0.3733) lr 4.1221e-04 eta 0:35:15
epoch [41/50] batch [120/200] time 1.119 (1.113) data 0.000 (0.005) loss 1.4192 (0.3887) lr 4.1221e-04 eta 0:34:52
epoch [41/50] batch [140/200] time 1.115 (1.112) data 0.000 (0.005) loss 2.3437 (0.4113) lr 4.1221e-04 eta 0:34:27
epoch [41/50] batch [160/200] time 1.102 (1.112) data 0.000 (0.004) loss 0.0476 (0.4011) lr 4.1221e-04 eta 0:34:05
epoch [41/50] batch [180/200] time 1.102 (1.111) data 0.000 (0.004) loss 0.0131 (0.4002) lr 4.1221e-04 eta 0:33:42
epoch [41/50] batch [200/200] time 1.119 (1.110) data 0.000 (0.003) loss 0.9103 (0.4046) lr 3.6258e-04 eta 0:33:18
epoch [42/50] batch [20/200] time 1.108 (1.137) data 0.000 (0.028) loss 0.2841 (0.3731) lr 3.6258e-04 eta 0:33:44
epoch [42/50] batch [40/200] time 1.120 (1.122) data 0.000 (0.014) loss 1.1033 (0.4669) lr 3.6258e-04 eta 0:32:55
epoch [42/50] batch [60/200] time 1.109 (1.120) data 0.001 (0.010) loss 0.1254 (0.4732) lr 3.6258e-04 eta 0:32:29
epoch [42/50] batch [80/200] time 1.095 (1.115) data 0.000 (0.007) loss 0.9393 (0.4407) lr 3.6258e-04 eta 0:31:58
epoch [42/50] batch [100/200] time 1.120 (1.114) data 0.000 (0.006) loss 0.9020 (0.4848) lr 3.6258e-04 eta 0:31:33
epoch [42/50] batch [120/200] time 1.114 (1.113) data 0.000 (0.005) loss 0.5737 (0.5110) lr 3.6258e-04 eta 0:31:10
epoch [42/50] batch [140/200] time 1.120 (1.112) data 0.000 (0.004) loss 0.8228 (0.4935) lr 3.6258e-04 eta 0:30:46
epoch [42/50] batch [160/200] time 1.131 (1.111) data 0.000 (0.004) loss 0.0289 (0.4891) lr 3.6258e-04 eta 0:30:22
epoch [42/50] batch [180/200] time 1.133 (1.113) data 0.000 (0.004) loss 0.0306 (0.4650) lr 3.6258e-04 eta 0:30:03
epoch [42/50] batch [200/200] time 1.146 (1.116) data 0.000 (0.003) loss 0.0529 (0.4686) lr 3.1545e-04 eta 0:29:44
epoch [43/50] batch [20/200] time 1.140 (1.171) data 0.000 (0.032) loss 0.1553 (0.5097) lr 3.1545e-04 eta 0:30:50
epoch [43/50] batch [40/200] time 1.110 (1.114) data 0.000 (0.016) loss 0.0439 (0.5509) lr 3.1545e-04 eta 0:28:57
epoch [43/50] batch [60/200] time 1.108 (1.113) data 0.000 (0.011) loss 0.0194 (0.5669) lr 3.1545e-04 eta 0:28:33
epoch [43/50] batch [80/200] time 1.118 (1.110) data 0.000 (0.008) loss 0.8861 (0.5596) lr 3.1545e-04 eta 0:28:07
epoch [43/50] batch [100/200] time 1.109 (1.111) data 0.000 (0.007) loss 0.0337 (0.5701) lr 3.1545e-04 eta 0:27:46
epoch [43/50] batch [120/200] time 1.009 (1.110) data 0.000 (0.006) loss 0.0143 (0.5283) lr 3.1545e-04 eta 0:27:23
epoch [43/50] batch [140/200] time 1.112 (1.110) data 0.000 (0.005) loss 0.0228 (0.4992) lr 3.1545e-04 eta 0:27:00
epoch [43/50] batch [160/200] time 1.114 (1.110) data 0.000 (0.005) loss 0.4722 (0.4694) lr 3.1545e-04 eta 0:26:38
epoch [43/50] batch [180/200] time 1.119 (1.109) data 0.000 (0.004) loss 0.1339 (0.4591) lr 3.1545e-04 eta 0:26:15
epoch [43/50] batch [200/200] time 1.124 (1.110) data 0.000 (0.004) loss 1.0916 (0.4743) lr 2.7103e-04 eta 0:25:54
epoch [44/50] batch [20/200] time 1.126 (1.135) data 0.000 (0.029) loss 0.3118 (0.4326) lr 2.7103e-04 eta 0:26:06
epoch [44/50] batch [40/200] time 1.113 (1.124) data 0.000 (0.015) loss 0.0508 (0.3871) lr 2.7103e-04 eta 0:25:28
epoch [44/50] batch [60/200] time 1.110 (1.121) data 0.000 (0.010) loss 0.6831 (0.4370) lr 2.7103e-04 eta 0:25:02
epoch [44/50] batch [80/200] time 0.847 (1.110) data 0.000 (0.007) loss 0.0091 (0.4440) lr 2.7103e-04 eta 0:24:24
epoch [44/50] batch [100/200] time 1.131 (1.113) data 0.000 (0.006) loss 2.3160 (0.4734) lr 2.7103e-04 eta 0:24:07
epoch [44/50] batch [120/200] time 1.127 (1.116) data 0.000 (0.005) loss 1.3846 (0.4936) lr 2.7103e-04 eta 0:23:48
epoch [44/50] batch [140/200] time 1.130 (1.119) data 0.000 (0.005) loss 0.0081 (0.4955) lr 2.7103e-04 eta 0:23:29
epoch [44/50] batch [160/200] time 1.139 (1.121) data 0.000 (0.004) loss 0.3790 (0.4824) lr 2.7103e-04 eta 0:23:10
epoch [44/50] batch [180/200] time 1.115 (1.117) data 0.000 (0.004) loss 0.0434 (0.4856) lr 2.7103e-04 eta 0:22:42
epoch [44/50] batch [200/200] time 1.105 (1.116) data 0.000 (0.003) loss 0.0064 (0.4778) lr 2.2949e-04 eta 0:22:19
epoch [45/50] batch [20/200] time 1.111 (1.129) data 0.000 (0.028) loss 0.0561 (0.4040) lr 2.2949e-04 eta 0:22:11
epoch [45/50] batch [40/200] time 1.109 (1.119) data 0.000 (0.014) loss 0.0243 (0.4228) lr 2.2949e-04 eta 0:21:38
epoch [45/50] batch [60/200] time 1.108 (1.115) data 0.001 (0.010) loss 0.1618 (0.4901) lr 2.2949e-04 eta 0:21:10
epoch [45/50] batch [80/200] time 1.105 (1.115) data 0.000 (0.007) loss 0.0304 (0.4848) lr 2.2949e-04 eta 0:20:48
epoch [45/50] batch [100/200] time 1.102 (1.113) data 0.000 (0.006) loss 1.0122 (0.5128) lr 2.2949e-04 eta 0:20:24
epoch [45/50] batch [120/200] time 1.111 (1.112) data 0.000 (0.005) loss 0.0289 (0.5028) lr 2.2949e-04 eta 0:20:00
epoch [45/50] batch [140/200] time 1.119 (1.112) data 0.000 (0.004) loss 1.3050 (0.4876) lr 2.2949e-04 eta 0:19:38
epoch [45/50] batch [160/200] time 1.117 (1.111) data 0.000 (0.004) loss 0.0032 (0.4857) lr 2.2949e-04 eta 0:19:15
epoch [45/50] batch [180/200] time 1.057 (1.111) data 0.000 (0.003) loss 0.6684 (0.4597) lr 2.2949e-04 eta 0:18:52
epoch [45/50] batch [200/200] time 1.117 (1.111) data 0.000 (0.003) loss 0.0294 (0.4635) lr 1.9098e-04 eta 0:18:30
epoch [46/50] batch [20/200] time 1.118 (1.134) data 0.000 (0.029) loss 0.0690 (0.3372) lr 1.9098e-04 eta 0:18:31
epoch [46/50] batch [40/200] time 1.109 (1.119) data 0.000 (0.015) loss 0.0361 (0.3995) lr 1.9098e-04 eta 0:17:53
epoch [46/50] batch [60/200] time 1.103 (1.113) data 0.000 (0.010) loss 0.0964 (0.3719) lr 1.9098e-04 eta 0:17:25
epoch [46/50] batch [80/200] time 1.114 (1.111) data 0.000 (0.008) loss 0.0104 (0.3710) lr 1.9098e-04 eta 0:17:02
epoch [46/50] batch [100/200] time 1.039 (1.111) data 0.000 (0.006) loss 0.4283 (0.3277) lr 1.9098e-04 eta 0:16:39
epoch [46/50] batch [120/200] time 1.114 (1.110) data 0.000 (0.005) loss 0.4539 (0.3393) lr 1.9098e-04 eta 0:16:16
epoch [46/50] batch [140/200] time 1.102 (1.108) data 0.001 (0.005) loss 0.0012 (0.3552) lr 1.9098e-04 eta 0:15:52
epoch [46/50] batch [160/200] time 1.124 (1.106) data 0.001 (0.004) loss 0.1786 (0.3917) lr 1.9098e-04 eta 0:15:28
epoch [46/50] batch [180/200] time 1.118 (1.107) data 0.001 (0.004) loss 0.0015 (0.3997) lr 1.9098e-04 eta 0:15:08
epoch [46/50] batch [200/200] time 1.131 (1.109) data 0.000 (0.003) loss 0.0163 (0.3948) lr 1.5567e-04 eta 0:14:47
epoch [47/50] batch [20/200] time 1.122 (1.160) data 0.000 (0.036) loss 0.0316 (0.4033) lr 1.5567e-04 eta 0:15:04
epoch [47/50] batch [40/200] time 1.118 (1.141) data 0.000 (0.018) loss 0.9229 (0.4625) lr 1.5567e-04 eta 0:14:27
epoch [47/50] batch [60/200] time 1.134 (1.134) data 0.001 (0.012) loss 0.5708 (0.4504) lr 1.5567e-04 eta 0:13:59
epoch [47/50] batch [80/200] time 1.113 (1.131) data 0.000 (0.010) loss 0.0020 (0.4714) lr 1.5567e-04 eta 0:13:34
epoch [47/50] batch [100/200] time 1.127 (1.129) data 0.000 (0.008) loss 0.0589 (0.4670) lr 1.5567e-04 eta 0:13:10
epoch [47/50] batch [120/200] time 1.116 (1.129) data 0.000 (0.007) loss 0.8486 (0.4631) lr 1.5567e-04 eta 0:12:47
epoch [47/50] batch [140/200] time 1.116 (1.127) data 0.000 (0.006) loss 0.1430 (0.4475) lr 1.5567e-04 eta 0:12:24
epoch [47/50] batch [160/200] time 1.134 (1.126) data 0.000 (0.005) loss 1.2921 (0.4518) lr 1.5567e-04 eta 0:12:00
epoch [47/50] batch [180/200] time 1.126 (1.126) data 0.000 (0.005) loss 0.0114 (0.4537) lr 1.5567e-04 eta 0:11:38
epoch [47/50] batch [200/200] time 1.131 (1.126) data 0.000 (0.004) loss 1.7497 (0.4569) lr 1.2369e-04 eta 0:11:15
epoch [48/50] batch [20/200] time 1.118 (1.156) data 0.000 (0.037) loss 1.1470 (0.2572) lr 1.2369e-04 eta 0:11:10
epoch [48/50] batch [40/200] time 1.125 (1.139) data 0.000 (0.019) loss 1.4606 (0.3614) lr 1.2369e-04 eta 0:10:37
epoch [48/50] batch [60/200] time 1.144 (1.119) data 0.000 (0.013) loss 0.5252 (0.3609) lr 1.2369e-04 eta 0:10:04
epoch [48/50] batch [80/200] time 1.141 (1.125) data 0.000 (0.010) loss 1.0000 (0.3908) lr 1.2369e-04 eta 0:09:44
epoch [48/50] batch [100/200] time 1.143 (1.125) data 0.000 (0.008) loss 0.2030 (0.3693) lr 1.2369e-04 eta 0:09:22
epoch [48/50] batch [120/200] time 1.141 (1.127) data 0.000 (0.007) loss 0.0084 (0.3773) lr 1.2369e-04 eta 0:09:00
epoch [48/50] batch [140/200] time 1.112 (1.125) data 0.000 (0.006) loss 0.7949 (0.3890) lr 1.2369e-04 eta 0:08:37
epoch [48/50] batch [160/200] time 1.114 (1.122) data 0.000 (0.006) loss 1.0554 (0.3879) lr 1.2369e-04 eta 0:08:13
epoch [48/50] batch [180/200] time 1.109 (1.122) data 0.000 (0.005) loss 1.2842 (0.4262) lr 1.2369e-04 eta 0:07:51
epoch [48/50] batch [200/200] time 1.106 (1.120) data 0.000 (0.005) loss 0.9912 (0.4226) lr 9.5173e-05 eta 0:07:28
epoch [49/50] batch [20/200] time 1.091 (1.157) data 0.000 (0.049) loss 0.4351 (0.3591) lr 9.5173e-05 eta 0:07:19
epoch [49/50] batch [40/200] time 1.109 (1.128) data 0.000 (0.025) loss 1.3394 (0.4133) lr 9.5173e-05 eta 0:06:46
epoch [49/50] batch [60/200] time 1.121 (1.122) data 0.001 (0.017) loss 0.8697 (0.4335) lr 9.5173e-05 eta 0:06:21
epoch [49/50] batch [80/200] time 1.138 (1.121) data 0.000 (0.013) loss 1.3774 (0.5143) lr 9.5173e-05 eta 0:05:58
epoch [49/50] batch [100/200] time 1.124 (1.118) data 0.000 (0.011) loss 0.1212 (0.5089) lr 9.5173e-05 eta 0:05:35
epoch [49/50] batch [120/200] time 1.110 (1.118) data 0.000 (0.009) loss 0.0017 (0.4651) lr 9.5173e-05 eta 0:05:12
epoch [49/50] batch [140/200] time 1.116 (1.115) data 0.000 (0.008) loss 0.5734 (0.4656) lr 9.5173e-05 eta 0:04:49
epoch [49/50] batch [160/200] time 1.107 (1.114) data 0.000 (0.007) loss 0.0692 (0.4464) lr 9.5173e-05 eta 0:04:27
epoch [49/50] batch [180/200] time 1.119 (1.114) data 0.000 (0.006) loss 1.0351 (0.4412) lr 9.5173e-05 eta 0:04:05
epoch [49/50] batch [200/200] time 1.128 (1.112) data 0.000 (0.006) loss 0.0018 (0.4397) lr 7.0224e-05 eta 0:03:42
epoch [50/50] batch [20/200] time 1.134 (1.174) data 0.000 (0.036) loss 0.3685 (0.3553) lr 7.0224e-05 eta 0:03:31
epoch [50/50] batch [40/200] time 1.135 (1.149) data 0.000 (0.019) loss 0.0004 (0.3734) lr 7.0224e-05 eta 0:03:03
epoch [50/50] batch [60/200] time 1.132 (1.145) data 0.004 (0.013) loss 0.1512 (0.3964) lr 7.0224e-05 eta 0:02:40
epoch [50/50] batch [80/200] time 1.118 (1.127) data 0.011 (0.010) loss 1.6543 (0.4278) lr 7.0224e-05 eta 0:02:15
epoch [50/50] batch [100/200] time 1.102 (1.124) data 0.002 (0.008) loss 0.9218 (0.4313) lr 7.0224e-05 eta 0:01:52
epoch [50/50] batch [120/200] time 1.106 (1.122) data 0.000 (0.007) loss 0.9432 (0.4131) lr 7.0224e-05 eta 0:01:29
epoch [50/50] batch [140/200] time 1.105 (1.118) data 0.000 (0.006) loss 1.6486 (0.4478) lr 7.0224e-05 eta 0:01:07
epoch [50/50] batch [160/200] time 1.117 (1.117) data 0.000 (0.005) loss 0.8474 (0.4446) lr 7.0224e-05 eta 0:00:44
epoch [50/50] batch [180/200] time 1.110 (1.116) data 0.000 (0.005) loss 0.0235 (0.4455) lr 7.0224e-05 eta 0:00:22
epoch [50/50] batch [200/200] time 1.122 (1.115) data 0.000 (0.004) loss 1.2638 (0.4387) lr 4.8943e-05 eta 0:00:00
Checkpoint saved to output/base2new/train_base/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed3/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 1,344
* correct: 1,323
* accuracy: 98.44%
* error: 1.56%
* macro_f1: 97.82%
Elapsed: 2:58:04
