***************
** Arguments **
***************
backbone: 
config_file: configs/trainers/ProDA/vit_b16_ep50_c4_BZ4_ProDA.yaml
dataset_config_file: configs/datasets/food101.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/food101/vit_b16_ep50_c4_BZ4_ProDA/seed1
resume: 
root: /mnt/hdd/DATA
seed: 1
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: Food101
  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/food101/vit_b16_ep50_c4_BZ4_ProDA/seed1
RESUME: 
SEED: 1
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: Food101
Reading split from /mnt/hdd/DATA/food-101/split_zhou_Food101.json
Loading preprocessed few-shot data from /mnt/hdd/DATA/food-101/split_fewshot/shot_16_shuffled-seed_1.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    Food101
# classes  51
# train_x  816
# val      204
# test     15,300
---------  -------
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/food101/vit_b16_ep50_c4_BZ4_ProDA/seed1/tensorboard)
epoch [1/50] batch [20/204] time 0.244 (0.379) data 0.000 (0.028) loss 0.5606 (1.2488) lr 1.0000e-05 eta 1:04:18
epoch [1/50] batch [40/204] time 0.250 (0.313) data 0.000 (0.014) loss 1.7985 (1.2242) lr 1.0000e-05 eta 0:53:02
epoch [1/50] batch [60/204] time 0.244 (0.292) data 0.000 (0.009) loss 1.3831 (1.2153) lr 1.0000e-05 eta 0:49:17
epoch [1/50] batch [80/204] time 0.245 (0.281) data 0.000 (0.007) loss 1.1089 (1.1514) lr 1.0000e-05 eta 0:47:21
epoch [1/50] batch [100/204] time 0.251 (0.274) data 0.000 (0.006) loss 0.8421 (1.1196) lr 1.0000e-05 eta 0:46:11
epoch [1/50] batch [120/204] time 0.250 (0.270) data 0.000 (0.005) loss 1.1216 (1.1050) lr 1.0000e-05 eta 0:45:22
epoch [1/50] batch [140/204] time 0.245 (0.267) data 0.000 (0.004) loss 1.2914 (1.0622) lr 1.0000e-05 eta 0:44:45
epoch [1/50] batch [160/204] time 0.248 (0.265) data 0.000 (0.004) loss 1.0905 (1.0442) lr 1.0000e-05 eta 0:44:18
epoch [1/50] batch [180/204] time 0.245 (0.263) data 0.000 (0.003) loss 0.2731 (1.0522) lr 1.0000e-05 eta 0:43:55
epoch [1/50] batch [200/204] time 0.251 (0.262) data 0.000 (0.003) loss 1.9258 (1.0338) lr 1.0000e-05 eta 0:43:36
epoch [2/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.020) loss 3.6069 (1.2382) lr 1.0000e-05 eta 0:44:57
epoch [2/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 1.9227 (1.1161) lr 1.0000e-05 eta 0:43:11
epoch [2/50] batch [60/204] time 0.252 (0.257) data 0.000 (0.007) loss 2.4550 (1.0759) lr 1.0000e-05 eta 0:42:29
epoch [2/50] batch [80/204] time 0.246 (0.255) data 0.000 (0.005) loss 0.9692 (0.9797) lr 1.0000e-05 eta 0:42:08
epoch [2/50] batch [100/204] time 0.247 (0.254) data 0.000 (0.004) loss 1.1844 (0.9873) lr 1.0000e-05 eta 0:41:54
epoch [2/50] batch [120/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.4085 (0.9183) lr 1.0000e-05 eta 0:41:41
epoch [2/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.7089 (0.9141) lr 1.0000e-05 eta 0:41:31
epoch [2/50] batch [160/204] time 0.252 (0.252) data 0.000 (0.003) loss 2.0436 (0.9375) lr 1.0000e-05 eta 0:41:22
epoch [2/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.6715 (0.9497) lr 1.0000e-05 eta 0:41:15
epoch [2/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 2.4253 (0.9537) lr 1.0000e-05 eta 0:41:07
epoch [3/50] batch [20/204] time 0.254 (0.271) data 0.000 (0.020) loss 0.3880 (1.0433) lr 1.0000e-05 eta 0:44:06
epoch [3/50] batch [40/204] time 0.253 (0.260) data 0.000 (0.010) loss 0.6808 (0.9380) lr 1.0000e-05 eta 0:42:20
epoch [3/50] batch [60/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.2310 (0.8950) lr 1.0000e-05 eta 0:41:44
epoch [3/50] batch [80/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.8953 (0.8876) lr 1.0000e-05 eta 0:41:24
epoch [3/50] batch [100/204] time 0.256 (0.255) data 0.000 (0.004) loss 0.1086 (0.8496) lr 1.0000e-05 eta 0:41:10
epoch [3/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.004) loss 2.0101 (0.8703) lr 1.0000e-05 eta 0:40:59
epoch [3/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.9648 (0.8577) lr 1.0000e-05 eta 0:40:49
epoch [3/50] batch [160/204] time 0.251 (0.253) data 0.000 (0.003) loss 1.0831 (0.8365) lr 1.0000e-05 eta 0:40:40
epoch [3/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.2996 (0.8414) lr 1.0000e-05 eta 0:40:32
epoch [3/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.1241 (0.8504) lr 1.0000e-05 eta 0:40:24
epoch [4/50] batch [20/204] time 0.247 (0.270) data 0.000 (0.019) loss 2.1331 (1.1612) lr 1.0000e-05 eta 0:43:08
epoch [4/50] batch [40/204] time 0.250 (0.261) data 0.000 (0.010) loss 0.4619 (0.8959) lr 1.0000e-05 eta 0:41:27
epoch [4/50] batch [60/204] time 0.254 (0.257) data 0.000 (0.007) loss 1.1752 (0.9207) lr 1.0000e-05 eta 0:40:52
epoch [4/50] batch [80/204] time 0.250 (0.256) data 0.000 (0.005) loss 1.7691 (0.9324) lr 1.0000e-05 eta 0:40:31
epoch [4/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.5954 (0.9572) lr 1.0000e-05 eta 0:40:15
epoch [4/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.2408 (0.9296) lr 1.0000e-05 eta 0:40:04
epoch [4/50] batch [140/204] time 0.245 (0.253) data 0.000 (0.003) loss 0.2855 (0.9101) lr 1.0000e-05 eta 0:39:52
epoch [4/50] batch [160/204] time 0.247 (0.253) data 0.000 (0.003) loss 1.0510 (0.9159) lr 1.0000e-05 eta 0:39:43
epoch [4/50] batch [180/204] time 0.255 (0.253) data 0.000 (0.002) loss 1.2129 (0.9156) lr 1.0000e-05 eta 0:39:36
epoch [4/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 0.2371 (0.9070) lr 1.0000e-05 eta 0:39:29
epoch [5/50] batch [20/204] time 0.246 (0.269) data 0.000 (0.019) loss 0.3061 (0.7364) lr 1.0000e-05 eta 0:42:00
epoch [5/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 0.3416 (0.8119) lr 1.0000e-05 eta 0:40:29
epoch [5/50] batch [60/204] time 0.252 (0.257) data 0.000 (0.007) loss 0.8889 (0.7509) lr 1.0000e-05 eta 0:39:54
epoch [5/50] batch [80/204] time 0.250 (0.255) data 0.000 (0.005) loss 0.7049 (0.7228) lr 1.0000e-05 eta 0:39:36
epoch [5/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 1.8747 (0.7999) lr 1.0000e-05 eta 0:39:21
epoch [5/50] batch [120/204] time 0.252 (0.254) data 0.000 (0.003) loss 1.9475 (0.7999) lr 1.0000e-05 eta 0:39:10
epoch [5/50] batch [140/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.1315 (0.8187) lr 1.0000e-05 eta 0:39:01
epoch [5/50] batch [160/204] time 0.252 (0.253) data 0.000 (0.003) loss 2.7041 (0.8095) lr 1.0000e-05 eta 0:38:53
epoch [5/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.2226 (0.8184) lr 1.0000e-05 eta 0:38:44
epoch [5/50] batch [200/204] time 0.246 (0.252) data 0.000 (0.002) loss 0.1047 (0.8407) lr 1.0000e-05 eta 0:38:37
epoch [6/50] batch [20/204] time 0.246 (0.270) data 0.000 (0.019) loss 1.2339 (0.8450) lr 2.0000e-03 eta 0:41:10
epoch [6/50] batch [40/204] time 0.254 (0.260) data 0.000 (0.010) loss 1.0283 (1.0305) lr 2.0000e-03 eta 0:39:37
epoch [6/50] batch [60/204] time 0.247 (0.256) data 0.000 (0.006) loss 1.3319 (0.9001) lr 2.0000e-03 eta 0:38:59
epoch [6/50] batch [80/204] time 0.246 (0.256) data 0.000 (0.005) loss 0.0469 (0.8657) lr 2.0000e-03 eta 0:38:45
epoch [6/50] batch [100/204] time 0.257 (0.255) data 0.003 (0.004) loss 0.8011 (0.8743) lr 2.0000e-03 eta 0:38:34
epoch [6/50] batch [120/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.4690 (0.8562) lr 2.0000e-03 eta 0:38:24
epoch [6/50] batch [140/204] time 0.257 (0.254) data 0.000 (0.003) loss 2.2636 (0.8577) lr 2.0000e-03 eta 0:38:18
epoch [6/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0556 (0.8222) lr 2.0000e-03 eta 0:38:11
epoch [6/50] batch [180/204] time 0.249 (0.254) data 0.000 (0.002) loss 1.5297 (0.8281) lr 2.0000e-03 eta 0:38:04
epoch [6/50] batch [200/204] time 0.251 (0.254) data 0.000 (0.002) loss 0.7279 (0.8126) lr 2.0000e-03 eta 0:37:57
epoch [7/50] batch [20/204] time 0.256 (0.278) data 0.000 (0.024) loss 0.7759 (0.8246) lr 1.9980e-03 eta 0:41:28
epoch [7/50] batch [40/204] time 0.254 (0.266) data 0.000 (0.012) loss 0.7707 (0.7142) lr 1.9980e-03 eta 0:39:33
epoch [7/50] batch [60/204] time 0.254 (0.261) data 0.000 (0.008) loss 2.1443 (0.6758) lr 1.9980e-03 eta 0:38:49
epoch [7/50] batch [80/204] time 0.253 (0.259) data 0.000 (0.006) loss 0.0802 (0.7149) lr 1.9980e-03 eta 0:38:26
epoch [7/50] batch [100/204] time 0.255 (0.258) data 0.000 (0.005) loss 0.9782 (0.7279) lr 1.9980e-03 eta 0:38:10
epoch [7/50] batch [120/204] time 0.252 (0.257) data 0.000 (0.004) loss 0.2522 (0.7634) lr 1.9980e-03 eta 0:37:57
epoch [7/50] batch [140/204] time 0.247 (0.256) data 0.000 (0.004) loss 0.0940 (0.7162) lr 1.9980e-03 eta 0:37:44
epoch [7/50] batch [160/204] time 0.251 (0.256) data 0.000 (0.003) loss 1.5132 (0.7110) lr 1.9980e-03 eta 0:37:33
epoch [7/50] batch [180/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.8172 (0.7133) lr 1.9980e-03 eta 0:37:24
epoch [7/50] batch [200/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.0131 (0.7079) lr 1.9980e-03 eta 0:37:14
epoch [8/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.020) loss 0.7364 (0.6347) lr 1.9921e-03 eta 0:39:27
epoch [8/50] batch [40/204] time 0.251 (0.261) data 0.000 (0.010) loss 1.2372 (0.7727) lr 1.9921e-03 eta 0:37:55
epoch [8/50] batch [60/204] time 0.249 (0.258) data 0.000 (0.007) loss 0.2110 (0.7280) lr 1.9921e-03 eta 0:37:27
epoch [8/50] batch [80/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.3180 (0.7242) lr 1.9921e-03 eta 0:37:08
epoch [8/50] batch [100/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.1319 (0.7579) lr 1.9921e-03 eta 0:36:54
epoch [8/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.0634 (0.7166) lr 1.9921e-03 eta 0:36:43
epoch [8/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.2275 (0.7040) lr 1.9921e-03 eta 0:36:34
epoch [8/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.7702 (0.6831) lr 1.9921e-03 eta 0:36:25
epoch [8/50] batch [180/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.0674 (0.6805) lr 1.9921e-03 eta 0:36:17
epoch [8/50] batch [200/204] time 0.249 (0.253) data 0.000 (0.002) loss 1.1540 (0.6769) lr 1.9921e-03 eta 0:36:10
epoch [9/50] batch [20/204] time 0.253 (0.270) data 0.000 (0.019) loss 0.1669 (0.5465) lr 1.9823e-03 eta 0:38:25
epoch [9/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.9089 (0.6071) lr 1.9823e-03 eta 0:37:02
epoch [9/50] batch [60/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.5713 (0.6446) lr 1.9823e-03 eta 0:36:30
epoch [9/50] batch [80/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.0535 (0.6231) lr 1.9823e-03 eta 0:36:12
epoch [9/50] batch [100/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.6919 (0.6880) lr 1.9823e-03 eta 0:36:00
epoch [9/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.1754 (0.6867) lr 1.9823e-03 eta 0:35:49
epoch [9/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.4708 (0.6913) lr 1.9823e-03 eta 0:35:39
epoch [9/50] batch [160/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.2635 (0.7020) lr 1.9823e-03 eta 0:35:31
epoch [9/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.3626 (0.6829) lr 1.9823e-03 eta 0:35:24
epoch [9/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 1.1880 (0.6684) lr 1.9823e-03 eta 0:35:17
epoch [10/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.019) loss 0.6654 (0.5899) lr 1.9686e-03 eta 0:37:33
epoch [10/50] batch [40/204] time 0.252 (0.261) data 0.000 (0.010) loss 0.6945 (0.7243) lr 1.9686e-03 eta 0:36:08
epoch [10/50] batch [60/204] time 0.251 (0.258) data 0.000 (0.006) loss 0.6954 (0.6884) lr 1.9686e-03 eta 0:35:38
epoch [10/50] batch [80/204] time 0.252 (0.256) data 0.000 (0.005) loss 1.6456 (0.6560) lr 1.9686e-03 eta 0:35:19
epoch [10/50] batch [100/204] time 0.251 (0.255) data 0.000 (0.004) loss 1.2091 (0.6642) lr 1.9686e-03 eta 0:35:04
epoch [10/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.6311 (0.6277) lr 1.9686e-03 eta 0:34:53
epoch [10/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.7742 (0.6241) lr 1.9686e-03 eta 0:34:45
epoch [10/50] batch [160/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.3336 (0.6381) lr 1.9686e-03 eta 0:34:37
epoch [10/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.6446 (0.6357) lr 1.9686e-03 eta 0:34:29
epoch [10/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 0.9117 (0.6330) lr 1.9686e-03 eta 0:34:20
epoch [11/50] batch [20/204] time 0.253 (0.270) data 0.000 (0.019) loss 1.7431 (0.5280) lr 1.9511e-03 eta 0:36:36
epoch [11/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 0.1353 (0.4816) lr 1.9511e-03 eta 0:35:13
epoch [11/50] batch [60/204] time 0.250 (0.257) data 0.000 (0.007) loss 0.1830 (0.4934) lr 1.9511e-03 eta 0:34:42
epoch [11/50] batch [80/204] time 0.247 (0.255) data 0.000 (0.005) loss 1.0845 (0.5084) lr 1.9511e-03 eta 0:34:23
epoch [11/50] batch [100/204] time 0.249 (0.254) data 0.000 (0.004) loss 1.2473 (0.5856) lr 1.9511e-03 eta 0:34:10
epoch [11/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.1268 (0.5905) lr 1.9511e-03 eta 0:33:59
epoch [11/50] batch [140/204] time 0.248 (0.253) data 0.000 (0.003) loss 0.8686 (0.5811) lr 1.9511e-03 eta 0:33:51
epoch [11/50] batch [160/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.1588 (0.6027) lr 1.9511e-03 eta 0:33:43
epoch [11/50] batch [180/204] time 0.246 (0.253) data 0.000 (0.002) loss 0.3338 (0.5899) lr 1.9511e-03 eta 0:33:36
epoch [11/50] batch [200/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.0441 (0.5963) lr 1.9511e-03 eta 0:33:29
epoch [12/50] batch [20/204] time 0.261 (0.271) data 0.008 (0.020) loss 0.8443 (0.6972) lr 1.9298e-03 eta 0:35:48
epoch [12/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 2.0399 (0.5806) lr 1.9298e-03 eta 0:34:21
epoch [12/50] batch [60/204] time 0.249 (0.257) data 0.000 (0.007) loss 0.2650 (0.5935) lr 1.9298e-03 eta 0:33:48
epoch [12/50] batch [80/204] time 0.245 (0.255) data 0.000 (0.005) loss 0.9816 (0.6142) lr 1.9298e-03 eta 0:33:29
epoch [12/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.0170 (0.5948) lr 1.9298e-03 eta 0:33:16
epoch [12/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.004) loss 1.1924 (0.5942) lr 1.9298e-03 eta 0:33:07
epoch [12/50] batch [140/204] time 0.251 (0.253) data 0.000 (0.003) loss 1.7229 (0.5989) lr 1.9298e-03 eta 0:32:58
epoch [12/50] batch [160/204] time 0.244 (0.253) data 0.000 (0.003) loss 1.7301 (0.6185) lr 1.9298e-03 eta 0:32:50
epoch [12/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 1.0249 (0.6645) lr 1.9298e-03 eta 0:32:43
epoch [12/50] batch [200/204] time 0.248 (0.252) data 0.000 (0.002) loss 0.0882 (0.6705) lr 1.9298e-03 eta 0:32:36
epoch [13/50] batch [20/204] time 0.249 (0.268) data 0.000 (0.019) loss 0.0164 (0.9383) lr 1.9048e-03 eta 0:34:34
epoch [13/50] batch [40/204] time 0.251 (0.259) data 0.000 (0.009) loss 0.4342 (0.7708) lr 1.9048e-03 eta 0:33:19
epoch [13/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.006) loss 0.0295 (0.7444) lr 1.9048e-03 eta 0:32:51
epoch [13/50] batch [80/204] time 0.247 (0.255) data 0.000 (0.005) loss 0.2500 (0.6795) lr 1.9048e-03 eta 0:32:34
epoch [13/50] batch [100/204] time 0.251 (0.254) data 0.000 (0.004) loss 0.7792 (0.6395) lr 1.9048e-03 eta 0:32:23
epoch [13/50] batch [120/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.6984 (0.6532) lr 1.9048e-03 eta 0:32:14
epoch [13/50] batch [140/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.0507 (0.6368) lr 1.9048e-03 eta 0:32:06
epoch [13/50] batch [160/204] time 0.250 (0.253) data 0.000 (0.003) loss 1.1844 (0.6251) lr 1.9048e-03 eta 0:31:59
epoch [13/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.3025 (0.6399) lr 1.9048e-03 eta 0:31:51
epoch [13/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 0.2228 (0.6217) lr 1.9048e-03 eta 0:31:43
epoch [14/50] batch [20/204] time 0.252 (0.271) data 0.000 (0.019) loss 0.7950 (0.5353) lr 1.8763e-03 eta 0:33:56
epoch [14/50] batch [40/204] time 0.254 (0.260) data 0.000 (0.010) loss 1.2841 (0.6086) lr 1.8763e-03 eta 0:32:35
epoch [14/50] batch [60/204] time 0.244 (0.257) data 0.000 (0.007) loss 0.0595 (0.6543) lr 1.8763e-03 eta 0:32:02
epoch [14/50] batch [80/204] time 0.246 (0.255) data 0.000 (0.005) loss 1.0526 (0.6508) lr 1.8763e-03 eta 0:31:46
epoch [14/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.6034 (0.6509) lr 1.8763e-03 eta 0:31:32
epoch [14/50] batch [120/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.3488 (0.6901) lr 1.8763e-03 eta 0:31:22
epoch [14/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.1197 (0.6521) lr 1.8763e-03 eta 0:31:12
epoch [14/50] batch [160/204] time 0.256 (0.252) data 0.000 (0.003) loss 0.1251 (0.6390) lr 1.8763e-03 eta 0:31:05
epoch [14/50] batch [180/204] time 0.245 (0.252) data 0.000 (0.002) loss 0.5504 (0.6553) lr 1.8763e-03 eta 0:30:57
epoch [14/50] batch [200/204] time 0.249 (0.252) data 0.000 (0.002) loss 0.0214 (0.6706) lr 1.8763e-03 eta 0:30:50
epoch [15/50] batch [20/204] time 0.247 (0.270) data 0.000 (0.019) loss 0.7891 (0.5822) lr 1.8443e-03 eta 0:32:54
epoch [15/50] batch [40/204] time 0.253 (0.260) data 0.000 (0.010) loss 1.5795 (0.5435) lr 1.8443e-03 eta 0:31:39
epoch [15/50] batch [60/204] time 0.249 (0.257) data 0.000 (0.006) loss 1.5919 (0.6067) lr 1.8443e-03 eta 0:31:09
epoch [15/50] batch [80/204] time 0.251 (0.255) data 0.000 (0.005) loss 0.5256 (0.6121) lr 1.8443e-03 eta 0:30:52
epoch [15/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.8182 (0.5956) lr 1.8443e-03 eta 0:30:39
epoch [15/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.003) loss 0.8856 (0.6250) lr 1.8443e-03 eta 0:30:29
epoch [15/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.5933 (0.6012) lr 1.8443e-03 eta 0:30:20
epoch [15/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 1.2204 (0.6177) lr 1.8443e-03 eta 0:30:12
epoch [15/50] batch [180/204] time 0.250 (0.252) data 0.000 (0.002) loss 0.7401 (0.6142) lr 1.8443e-03 eta 0:30:05
epoch [15/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 1.2466 (0.6029) lr 1.8443e-03 eta 0:29:58
epoch [16/50] batch [20/204] time 0.249 (0.269) data 0.000 (0.019) loss 1.2021 (0.8015) lr 1.8090e-03 eta 0:31:54
epoch [16/50] batch [40/204] time 0.249 (0.259) data 0.000 (0.009) loss 0.2527 (0.7305) lr 1.8090e-03 eta 0:30:42
epoch [16/50] batch [60/204] time 0.252 (0.256) data 0.000 (0.006) loss 0.7293 (0.7462) lr 1.8090e-03 eta 0:30:12
epoch [16/50] batch [80/204] time 0.252 (0.254) data 0.000 (0.005) loss 2.0322 (0.7030) lr 1.8090e-03 eta 0:29:56
epoch [16/50] batch [100/204] time 0.244 (0.253) data 0.000 (0.004) loss 0.1430 (0.6520) lr 1.8090e-03 eta 0:29:44
epoch [16/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.0558 (0.6017) lr 1.8090e-03 eta 0:29:35
epoch [16/50] batch [140/204] time 0.249 (0.253) data 0.000 (0.003) loss 1.2151 (0.5786) lr 1.8090e-03 eta 0:29:27
epoch [16/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.3229 (0.5663) lr 1.8090e-03 eta 0:29:21
epoch [16/50] batch [180/204] time 0.247 (0.252) data 0.000 (0.002) loss 0.0263 (0.5825) lr 1.8090e-03 eta 0:29:15
epoch [16/50] batch [200/204] time 0.259 (0.252) data 0.003 (0.002) loss 1.5155 (0.5949) lr 1.8090e-03 eta 0:29:09
epoch [17/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.019) loss 1.0017 (0.6578) lr 1.7705e-03 eta 0:31:08
epoch [17/50] batch [40/204] time 0.253 (0.260) data 0.000 (0.009) loss 0.1548 (0.7037) lr 1.7705e-03 eta 0:29:54
epoch [17/50] batch [60/204] time 0.250 (0.257) data 0.000 (0.006) loss 0.1505 (0.7128) lr 1.7705e-03 eta 0:29:27
epoch [17/50] batch [80/204] time 0.251 (0.255) data 0.000 (0.005) loss 0.3852 (0.6676) lr 1.7705e-03 eta 0:29:10
epoch [17/50] batch [100/204] time 0.251 (0.254) data 0.000 (0.004) loss 0.0839 (0.6311) lr 1.7705e-03 eta 0:28:59
epoch [17/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.3034 (0.6125) lr 1.7705e-03 eta 0:28:49
epoch [17/50] batch [140/204] time 0.251 (0.253) data 0.000 (0.003) loss 1.2030 (0.5962) lr 1.7705e-03 eta 0:28:41
epoch [17/50] batch [160/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.1643 (0.5832) lr 1.7705e-03 eta 0:28:33
epoch [17/50] batch [180/204] time 0.248 (0.253) data 0.000 (0.002) loss 1.2178 (0.5824) lr 1.7705e-03 eta 0:28:26
epoch [17/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 0.3150 (0.6037) lr 1.7705e-03 eta 0:28:19
epoch [18/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.019) loss 0.1453 (0.4079) lr 1.7290e-03 eta 0:30:10
epoch [18/50] batch [40/204] time 0.245 (0.260) data 0.000 (0.010) loss 0.0534 (0.5901) lr 1.7290e-03 eta 0:28:59
epoch [18/50] batch [60/204] time 0.247 (0.257) data 0.001 (0.007) loss 1.5867 (0.6317) lr 1.7290e-03 eta 0:28:35
epoch [18/50] batch [80/204] time 0.252 (0.256) data 0.000 (0.005) loss 0.3300 (0.6157) lr 1.7290e-03 eta 0:28:20
epoch [18/50] batch [100/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.1648 (0.6162) lr 1.7290e-03 eta 0:28:08
epoch [18/50] batch [120/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1076 (0.5954) lr 1.7290e-03 eta 0:27:58
epoch [18/50] batch [140/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.3353 (0.6061) lr 1.7290e-03 eta 0:27:49
epoch [18/50] batch [160/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.3837 (0.6011) lr 1.7290e-03 eta 0:27:43
epoch [18/50] batch [180/204] time 0.246 (0.253) data 0.000 (0.002) loss 0.2465 (0.5843) lr 1.7290e-03 eta 0:27:35
epoch [18/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 1.3409 (0.5767) lr 1.7290e-03 eta 0:27:29
epoch [19/50] batch [20/204] time 0.264 (0.272) data 0.000 (0.020) loss 1.6390 (0.4923) lr 1.6845e-03 eta 0:29:28
epoch [19/50] batch [40/204] time 0.252 (0.261) data 0.000 (0.010) loss 0.7014 (0.5673) lr 1.6845e-03 eta 0:28:14
epoch [19/50] batch [60/204] time 0.248 (0.258) data 0.001 (0.007) loss 1.5208 (0.6059) lr 1.6845e-03 eta 0:27:47
epoch [19/50] batch [80/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.0755 (0.6060) lr 1.6845e-03 eta 0:27:32
epoch [19/50] batch [100/204] time 0.247 (0.255) data 0.000 (0.004) loss 1.0116 (0.5700) lr 1.6845e-03 eta 0:27:19
epoch [19/50] batch [120/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.2242 (0.5550) lr 1.6845e-03 eta 0:27:10
epoch [19/50] batch [140/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0258 (0.5597) lr 1.6845e-03 eta 0:27:02
epoch [19/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.8516 (0.6045) lr 1.6845e-03 eta 0:26:55
epoch [19/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.6657 (0.6312) lr 1.6845e-03 eta 0:26:47
epoch [19/50] batch [200/204] time 0.251 (0.253) data 0.000 (0.002) loss 0.6575 (0.6374) lr 1.6845e-03 eta 0:26:40
epoch [20/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.020) loss 0.9139 (0.5604) lr 1.6374e-03 eta 0:28:19
epoch [20/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 0.4145 (0.5720) lr 1.6374e-03 eta 0:27:13
epoch [20/50] batch [60/204] time 0.247 (0.257) data 0.000 (0.007) loss 0.0284 (0.5683) lr 1.6374e-03 eta 0:26:47
epoch [20/50] batch [80/204] time 0.254 (0.255) data 0.000 (0.005) loss 0.1491 (0.6027) lr 1.6374e-03 eta 0:26:32
epoch [20/50] batch [100/204] time 0.246 (0.254) data 0.000 (0.004) loss 0.5181 (0.6298) lr 1.6374e-03 eta 0:26:22
epoch [20/50] batch [120/204] time 0.244 (0.253) data 0.000 (0.003) loss 0.7649 (0.6057) lr 1.6374e-03 eta 0:26:12
epoch [20/50] batch [140/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.3523 (0.6115) lr 1.6374e-03 eta 0:26:04
epoch [20/50] batch [160/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.1058 (0.6096) lr 1.6374e-03 eta 0:25:56
epoch [20/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.4001 (0.6018) lr 1.6374e-03 eta 0:25:49
epoch [20/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 0.2391 (0.5971) lr 1.6374e-03 eta 0:25:42
epoch [21/50] batch [20/204] time 0.252 (0.269) data 0.000 (0.019) loss 1.0829 (0.7487) lr 1.5878e-03 eta 0:27:20
epoch [21/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.010) loss 0.8544 (0.6363) lr 1.5878e-03 eta 0:26:19
epoch [21/50] batch [60/204] time 0.246 (0.257) data 0.000 (0.007) loss 0.0110 (0.5814) lr 1.5878e-03 eta 0:25:55
epoch [21/50] batch [80/204] time 0.251 (0.255) data 0.000 (0.005) loss 0.0806 (0.5814) lr 1.5878e-03 eta 0:25:39
epoch [21/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.1788 (0.6167) lr 1.5878e-03 eta 0:25:29
epoch [21/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.3463 (0.6599) lr 1.5878e-03 eta 0:25:20
epoch [21/50] batch [140/204] time 0.248 (0.253) data 0.000 (0.003) loss 1.6379 (0.6823) lr 1.5878e-03 eta 0:25:14
epoch [21/50] batch [160/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.4855 (0.6647) lr 1.5878e-03 eta 0:25:06
epoch [21/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.7154 (0.6648) lr 1.5878e-03 eta 0:24:59
epoch [21/50] batch [200/204] time 0.249 (0.252) data 0.000 (0.002) loss 0.0111 (0.6689) lr 1.5878e-03 eta 0:24:52
epoch [22/50] batch [20/204] time 0.254 (0.270) data 0.003 (0.020) loss 0.6782 (0.5060) lr 1.5358e-03 eta 0:26:33
epoch [22/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.010) loss 0.4138 (0.5383) lr 1.5358e-03 eta 0:25:25
epoch [22/50] batch [60/204] time 0.252 (0.256) data 0.000 (0.007) loss 1.3766 (0.5463) lr 1.5358e-03 eta 0:25:01
epoch [22/50] batch [80/204] time 0.250 (0.255) data 0.000 (0.005) loss 0.0473 (0.5146) lr 1.5358e-03 eta 0:24:46
epoch [22/50] batch [100/204] time 0.246 (0.254) data 0.000 (0.004) loss 0.0647 (0.5158) lr 1.5358e-03 eta 0:24:36
epoch [22/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.2079 (0.5647) lr 1.5358e-03 eta 0:24:28
epoch [22/50] batch [140/204] time 0.260 (0.253) data 0.000 (0.003) loss 0.0760 (0.5696) lr 1.5358e-03 eta 0:24:21
epoch [22/50] batch [160/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.0333 (0.5549) lr 1.5358e-03 eta 0:24:13
epoch [22/50] batch [180/204] time 0.249 (0.252) data 0.000 (0.002) loss 1.2226 (0.5508) lr 1.5358e-03 eta 0:24:07
epoch [22/50] batch [200/204] time 0.247 (0.252) data 0.000 (0.002) loss 0.0378 (0.5498) lr 1.5358e-03 eta 0:24:01
epoch [23/50] batch [20/204] time 0.252 (0.269) data 0.000 (0.019) loss 0.0713 (0.4078) lr 1.4818e-03 eta 0:25:32
epoch [23/50] batch [40/204] time 0.249 (0.259) data 0.000 (0.010) loss 0.2321 (0.5625) lr 1.4818e-03 eta 0:24:31
epoch [23/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.007) loss 0.1629 (0.5428) lr 1.4818e-03 eta 0:24:07
epoch [23/50] batch [80/204] time 0.255 (0.255) data 0.000 (0.005) loss 1.6696 (0.5555) lr 1.4818e-03 eta 0:23:55
epoch [23/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.3609 (0.5672) lr 1.4818e-03 eta 0:23:45
epoch [23/50] batch [120/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.0533 (0.5445) lr 1.4818e-03 eta 0:23:36
epoch [23/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 1.0804 (0.5672) lr 1.4818e-03 eta 0:23:29
epoch [23/50] batch [160/204] time 0.255 (0.253) data 0.000 (0.003) loss 1.4663 (0.5771) lr 1.4818e-03 eta 0:23:21
epoch [23/50] batch [180/204] time 0.246 (0.252) data 0.000 (0.002) loss 0.0093 (0.5868) lr 1.4818e-03 eta 0:23:15
epoch [23/50] batch [200/204] time 0.247 (0.252) data 0.000 (0.002) loss 0.4001 (0.5953) lr 1.4818e-03 eta 0:23:08
epoch [24/50] batch [20/204] time 0.245 (0.269) data 0.000 (0.020) loss 1.0355 (0.4993) lr 1.4258e-03 eta 0:24:37
epoch [24/50] batch [40/204] time 0.253 (0.259) data 0.002 (0.010) loss 0.1714 (0.5538) lr 1.4258e-03 eta 0:23:38
epoch [24/50] batch [60/204] time 0.250 (0.257) data 0.000 (0.007) loss 0.3644 (0.5760) lr 1.4258e-03 eta 0:23:19
epoch [24/50] batch [80/204] time 0.247 (0.255) data 0.000 (0.005) loss 2.0707 (0.5894) lr 1.4258e-03 eta 0:23:05
epoch [24/50] batch [100/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.6303 (0.6077) lr 1.4258e-03 eta 0:22:56
epoch [24/50] batch [120/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.3167 (0.6170) lr 1.4258e-03 eta 0:22:48
epoch [24/50] batch [140/204] time 0.253 (0.254) data 0.003 (0.003) loss 0.2571 (0.6045) lr 1.4258e-03 eta 0:22:41
epoch [24/50] batch [160/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.0418 (0.6020) lr 1.4258e-03 eta 0:22:34
epoch [24/50] batch [180/204] time 0.254 (0.253) data 0.000 (0.002) loss 0.0387 (0.5707) lr 1.4258e-03 eta 0:22:28
epoch [24/50] batch [200/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.3031 (0.5765) lr 1.4258e-03 eta 0:22:22
epoch [25/50] batch [20/204] time 0.253 (0.272) data 0.000 (0.020) loss 0.4408 (0.5414) lr 1.3681e-03 eta 0:23:58
epoch [25/50] batch [40/204] time 0.251 (0.262) data 0.000 (0.010) loss 0.2012 (0.5476) lr 1.3681e-03 eta 0:22:58
epoch [25/50] batch [60/204] time 0.254 (0.259) data 0.001 (0.007) loss 0.0434 (0.5673) lr 1.3681e-03 eta 0:22:37
epoch [25/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.005) loss 1.0006 (0.5438) lr 1.3681e-03 eta 0:22:22
epoch [25/50] batch [100/204] time 0.252 (0.256) data 0.000 (0.004) loss 0.0987 (0.5539) lr 1.3681e-03 eta 0:22:10
epoch [25/50] batch [120/204] time 0.249 (0.255) data 0.000 (0.004) loss 0.2955 (0.6354) lr 1.3681e-03 eta 0:22:00
epoch [25/50] batch [140/204] time 0.246 (0.254) data 0.000 (0.003) loss 0.6769 (0.6280) lr 1.3681e-03 eta 0:21:51
epoch [25/50] batch [160/204] time 0.246 (0.253) data 0.000 (0.003) loss 1.0115 (0.6221) lr 1.3681e-03 eta 0:21:43
epoch [25/50] batch [180/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.6898 (0.6265) lr 1.3681e-03 eta 0:21:36
epoch [25/50] batch [200/204] time 0.244 (0.253) data 0.000 (0.002) loss 0.0919 (0.6193) lr 1.3681e-03 eta 0:21:28
epoch [26/50] batch [20/204] time 0.249 (0.269) data 0.000 (0.019) loss 0.0453 (0.5194) lr 1.3090e-03 eta 0:22:46
epoch [26/50] batch [40/204] time 0.252 (0.259) data 0.000 (0.009) loss 0.0784 (0.5563) lr 1.3090e-03 eta 0:21:51
epoch [26/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.006) loss 0.9914 (0.5908) lr 1.3090e-03 eta 0:21:29
epoch [26/50] batch [80/204] time 0.252 (0.254) data 0.000 (0.005) loss 0.4354 (0.5778) lr 1.3090e-03 eta 0:21:17
epoch [26/50] batch [100/204] time 0.254 (0.254) data 0.000 (0.004) loss 0.6101 (0.6348) lr 1.3090e-03 eta 0:21:07
epoch [26/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.1284 (0.6172) lr 1.3090e-03 eta 0:20:59
epoch [26/50] batch [140/204] time 0.255 (0.253) data 0.000 (0.003) loss 0.0422 (0.6004) lr 1.3090e-03 eta 0:20:52
epoch [26/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.0975 (0.6278) lr 1.3090e-03 eta 0:20:45
epoch [26/50] batch [180/204] time 0.258 (0.252) data 0.003 (0.002) loss 1.1777 (0.6489) lr 1.3090e-03 eta 0:20:39
epoch [26/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 0.6330 (0.6382) lr 1.3090e-03 eta 0:20:33
epoch [27/50] batch [20/204] time 0.248 (0.269) data 0.000 (0.019) loss 0.7456 (0.6472) lr 1.2487e-03 eta 0:21:51
epoch [27/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.009) loss 0.6974 (0.6745) lr 1.2487e-03 eta 0:21:00
epoch [27/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.006) loss 1.4329 (0.6003) lr 1.2487e-03 eta 0:20:39
epoch [27/50] batch [80/204] time 0.257 (0.255) data 0.000 (0.005) loss 0.2633 (0.5709) lr 1.2487e-03 eta 0:20:27
epoch [27/50] batch [100/204] time 0.251 (0.254) data 0.000 (0.004) loss 1.2115 (0.5446) lr 1.2487e-03 eta 0:20:17
epoch [27/50] batch [120/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.4902 (0.5647) lr 1.2487e-03 eta 0:20:09
epoch [27/50] batch [140/204] time 0.250 (0.253) data 0.000 (0.003) loss 1.5460 (0.5746) lr 1.2487e-03 eta 0:20:02
epoch [27/50] batch [160/204] time 0.247 (0.253) data 0.000 (0.003) loss 1.0037 (0.5517) lr 1.2487e-03 eta 0:19:56
epoch [27/50] batch [180/204] time 0.249 (0.252) data 0.000 (0.002) loss 0.4710 (0.5598) lr 1.2487e-03 eta 0:19:50
epoch [27/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 0.0142 (0.5692) lr 1.2487e-03 eta 0:19:43
epoch [28/50] batch [20/204] time 0.246 (0.269) data 0.000 (0.020) loss 1.2731 (0.7191) lr 1.1874e-03 eta 0:20:57
epoch [28/50] batch [40/204] time 0.243 (0.260) data 0.000 (0.010) loss 0.4638 (0.5632) lr 1.1874e-03 eta 0:20:07
epoch [28/50] batch [60/204] time 0.246 (0.257) data 0.000 (0.007) loss 1.3624 (0.5509) lr 1.1874e-03 eta 0:19:48
epoch [28/50] batch [80/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.2649 (0.5572) lr 1.1874e-03 eta 0:19:35
epoch [28/50] batch [100/204] time 0.246 (0.254) data 0.000 (0.004) loss 0.7388 (0.5854) lr 1.1874e-03 eta 0:19:25
epoch [28/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.004) loss 0.0334 (0.5895) lr 1.1874e-03 eta 0:19:17
epoch [28/50] batch [140/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.4339 (0.5870) lr 1.1874e-03 eta 0:19:10
epoch [28/50] batch [160/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.2414 (0.6066) lr 1.1874e-03 eta 0:19:03
epoch [28/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.0538 (0.6177) lr 1.1874e-03 eta 0:18:57
epoch [28/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 1.1450 (0.6254) lr 1.1874e-03 eta 0:18:51
epoch [29/50] batch [20/204] time 0.244 (0.269) data 0.000 (0.020) loss 0.8433 (0.4494) lr 1.1253e-03 eta 0:20:00
epoch [29/50] batch [40/204] time 0.255 (0.259) data 0.000 (0.010) loss 0.0683 (0.6223) lr 1.1253e-03 eta 0:19:12
epoch [29/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.007) loss 0.0937 (0.6368) lr 1.1253e-03 eta 0:18:53
epoch [29/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.005) loss 0.0127 (0.6447) lr 1.1253e-03 eta 0:18:41
epoch [29/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.0451 (0.6079) lr 1.1253e-03 eta 0:18:32
epoch [29/50] batch [120/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.9029 (0.6071) lr 1.1253e-03 eta 0:18:23
epoch [29/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 1.6357 (0.6195) lr 1.1253e-03 eta 0:18:16
epoch [29/50] batch [160/204] time 0.254 (0.252) data 0.000 (0.003) loss 0.5736 (0.6041) lr 1.1253e-03 eta 0:18:10
epoch [29/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 1.1709 (0.5964) lr 1.1253e-03 eta 0:18:04
epoch [29/50] batch [200/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.3518 (0.5871) lr 1.1253e-03 eta 0:17:58
epoch [30/50] batch [20/204] time 0.246 (0.269) data 0.000 (0.019) loss 0.5862 (0.4494) lr 1.0628e-03 eta 0:19:05
epoch [30/50] batch [40/204] time 0.246 (0.259) data 0.000 (0.010) loss 0.0532 (0.4730) lr 1.0628e-03 eta 0:18:19
epoch [30/50] batch [60/204] time 0.244 (0.256) data 0.000 (0.007) loss 0.0292 (0.4551) lr 1.0628e-03 eta 0:18:00
epoch [30/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.005) loss 1.2354 (0.5238) lr 1.0628e-03 eta 0:17:47
epoch [30/50] batch [100/204] time 0.247 (0.253) data 0.000 (0.004) loss 0.0640 (0.5154) lr 1.0628e-03 eta 0:17:39
epoch [30/50] batch [120/204] time 0.252 (0.253) data 0.003 (0.003) loss 1.8974 (0.5674) lr 1.0628e-03 eta 0:17:32
epoch [30/50] batch [140/204] time 0.247 (0.252) data 0.000 (0.003) loss 0.2093 (0.5440) lr 1.0628e-03 eta 0:17:25
epoch [30/50] batch [160/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.0127 (0.5484) lr 1.0628e-03 eta 0:17:19
epoch [30/50] batch [180/204] time 0.253 (0.252) data 0.000 (0.002) loss 0.7207 (0.5314) lr 1.0628e-03 eta 0:17:13
epoch [30/50] batch [200/204] time 0.255 (0.252) data 0.000 (0.002) loss 1.8564 (0.5406) lr 1.0628e-03 eta 0:17:07
epoch [31/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.020) loss 0.4812 (0.5098) lr 1.0000e-03 eta 0:18:16
epoch [31/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.010) loss 0.1827 (0.5864) lr 1.0000e-03 eta 0:17:29
epoch [31/50] batch [60/204] time 0.251 (0.257) data 0.000 (0.007) loss 1.3459 (0.5777) lr 1.0000e-03 eta 0:17:11
epoch [31/50] batch [80/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.9241 (0.5401) lr 1.0000e-03 eta 0:16:58
epoch [31/50] batch [100/204] time 0.255 (0.254) data 0.000 (0.004) loss 0.8520 (0.6218) lr 1.0000e-03 eta 0:16:49
epoch [31/50] batch [120/204] time 0.245 (0.253) data 0.000 (0.003) loss 0.0936 (0.6217) lr 1.0000e-03 eta 0:16:42
epoch [31/50] batch [140/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.1671 (0.6206) lr 1.0000e-03 eta 0:16:35
epoch [31/50] batch [160/204] time 0.253 (0.252) data 0.000 (0.003) loss 0.0506 (0.6027) lr 1.0000e-03 eta 0:16:29
epoch [31/50] batch [180/204] time 0.251 (0.252) data 0.000 (0.002) loss 0.5896 (0.6009) lr 1.0000e-03 eta 0:16:23
epoch [31/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 2.0572 (0.6091) lr 1.0000e-03 eta 0:16:17
epoch [32/50] batch [20/204] time 0.254 (0.269) data 0.000 (0.019) loss 0.5060 (0.3763) lr 9.3721e-04 eta 0:17:18
epoch [32/50] batch [40/204] time 0.246 (0.259) data 0.000 (0.010) loss 0.0819 (0.5326) lr 9.3721e-04 eta 0:16:35
epoch [32/50] batch [60/204] time 0.252 (0.256) data 0.000 (0.007) loss 0.0377 (0.4861) lr 9.3721e-04 eta 0:16:17
epoch [32/50] batch [80/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.2189 (0.5252) lr 9.3721e-04 eta 0:16:06
epoch [32/50] batch [100/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.3261 (0.5516) lr 9.3721e-04 eta 0:15:57
epoch [32/50] batch [120/204] time 0.246 (0.253) data 0.000 (0.003) loss 1.5681 (0.6295) lr 9.3721e-04 eta 0:15:49
epoch [32/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.1687 (0.6407) lr 9.3721e-04 eta 0:15:42
epoch [32/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.8410 (0.6238) lr 9.3721e-04 eta 0:15:36
epoch [32/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.1599 (0.6245) lr 9.3721e-04 eta 0:15:30
epoch [32/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.1412 (0.6049) lr 9.3721e-04 eta 0:15:24
epoch [33/50] batch [20/204] time 0.251 (0.269) data 0.000 (0.019) loss 1.3786 (0.4848) lr 8.7467e-04 eta 0:16:23
epoch [33/50] batch [40/204] time 0.247 (0.260) data 0.000 (0.010) loss 0.6405 (0.4633) lr 8.7467e-04 eta 0:15:43
epoch [33/50] batch [60/204] time 0.251 (0.257) data 0.000 (0.007) loss 0.1290 (0.5430) lr 8.7467e-04 eta 0:15:29
epoch [33/50] batch [80/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.1916 (0.5238) lr 8.7467e-04 eta 0:15:17
epoch [33/50] batch [100/204] time 0.249 (0.254) data 0.000 (0.004) loss 0.0554 (0.5383) lr 8.7467e-04 eta 0:15:08
epoch [33/50] batch [120/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.0338 (0.5826) lr 8.7467e-04 eta 0:15:00
epoch [33/50] batch [140/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.6022 (0.5588) lr 8.7467e-04 eta 0:14:53
epoch [33/50] batch [160/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.4521 (0.5759) lr 8.7467e-04 eta 0:14:46
epoch [33/50] batch [180/204] time 0.253 (0.252) data 0.004 (0.002) loss 0.7466 (0.5620) lr 8.7467e-04 eta 0:14:41
epoch [33/50] batch [200/204] time 0.250 (0.252) data 0.000 (0.002) loss 2.3860 (0.5498) lr 8.7467e-04 eta 0:14:35
epoch [34/50] batch [20/204] time 0.253 (0.270) data 0.000 (0.020) loss 0.0255 (0.5507) lr 8.1262e-04 eta 0:15:29
epoch [34/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 0.6809 (0.4958) lr 8.1262e-04 eta 0:14:50
epoch [34/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.0134 (0.5067) lr 8.1262e-04 eta 0:14:33
epoch [34/50] batch [80/204] time 0.249 (0.255) data 0.000 (0.005) loss 1.0574 (0.4767) lr 8.1262e-04 eta 0:14:23
epoch [34/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.3669 (0.4790) lr 8.1262e-04 eta 0:14:15
epoch [34/50] batch [120/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.7005 (0.5068) lr 8.1262e-04 eta 0:14:07
epoch [34/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.1628 (0.5157) lr 8.1262e-04 eta 0:14:00
epoch [34/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.2027 (0.5345) lr 8.1262e-04 eta 0:13:54
epoch [34/50] batch [180/204] time 0.243 (0.252) data 0.000 (0.002) loss 0.3502 (0.5427) lr 8.1262e-04 eta 0:13:49
epoch [34/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 1.0433 (0.5610) lr 8.1262e-04 eta 0:13:43
epoch [35/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.020) loss 1.8112 (0.5607) lr 7.5131e-04 eta 0:14:38
epoch [35/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.0086 (0.4836) lr 7.5131e-04 eta 0:14:01
epoch [35/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.007) loss 0.7159 (0.5604) lr 7.5131e-04 eta 0:13:45
epoch [35/50] batch [80/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.1726 (0.5271) lr 7.5131e-04 eta 0:13:34
epoch [35/50] batch [100/204] time 0.244 (0.255) data 0.000 (0.004) loss 1.0161 (0.5111) lr 7.5131e-04 eta 0:13:25
epoch [35/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.0464 (0.4999) lr 7.5131e-04 eta 0:13:17
epoch [35/50] batch [140/204] time 0.249 (0.253) data 0.000 (0.003) loss 1.1606 (0.5055) lr 7.5131e-04 eta 0:13:10
epoch [35/50] batch [160/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.1044 (0.5169) lr 7.5131e-04 eta 0:13:04
epoch [35/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.3511 (0.5538) lr 7.5131e-04 eta 0:12:59
epoch [35/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 0.0305 (0.5752) lr 7.5131e-04 eta 0:12:53
epoch [36/50] batch [20/204] time 0.250 (0.269) data 0.000 (0.019) loss 0.8218 (0.7514) lr 6.9098e-04 eta 0:13:37
epoch [36/50] batch [40/204] time 0.245 (0.259) data 0.000 (0.010) loss 0.4458 (0.6897) lr 6.9098e-04 eta 0:13:03
epoch [36/50] batch [60/204] time 0.252 (0.257) data 0.000 (0.007) loss 0.6075 (0.7458) lr 6.9098e-04 eta 0:12:49
epoch [36/50] batch [80/204] time 0.250 (0.255) data 0.000 (0.005) loss 0.1397 (0.6645) lr 6.9098e-04 eta 0:12:39
epoch [36/50] batch [100/204] time 0.250 (0.254) data 0.000 (0.004) loss 0.1386 (0.6745) lr 6.9098e-04 eta 0:12:31
epoch [36/50] batch [120/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.2700 (0.6371) lr 6.9098e-04 eta 0:12:24
epoch [36/50] batch [140/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.4876 (0.6043) lr 6.9098e-04 eta 0:12:18
epoch [36/50] batch [160/204] time 0.248 (0.253) data 0.000 (0.003) loss 0.6053 (0.5944) lr 6.9098e-04 eta 0:12:13
epoch [36/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.002) loss 0.4053 (0.5961) lr 6.9098e-04 eta 0:12:07
epoch [36/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 0.7964 (0.5943) lr 6.9098e-04 eta 0:12:01
epoch [37/50] batch [20/204] time 0.247 (0.270) data 0.000 (0.019) loss 0.1446 (0.3058) lr 6.3188e-04 eta 0:12:45
epoch [37/50] batch [40/204] time 0.244 (0.260) data 0.000 (0.010) loss 0.0252 (0.4465) lr 6.3188e-04 eta 0:12:12
epoch [37/50] batch [60/204] time 0.246 (0.257) data 0.000 (0.007) loss 0.4945 (0.5257) lr 6.3188e-04 eta 0:11:58
epoch [37/50] batch [80/204] time 0.251 (0.255) data 0.000 (0.005) loss 0.3456 (0.5218) lr 6.3188e-04 eta 0:11:47
epoch [37/50] batch [100/204] time 0.246 (0.254) data 0.000 (0.004) loss 1.1074 (0.5700) lr 6.3188e-04 eta 0:11:40
epoch [37/50] batch [120/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.1023 (0.5874) lr 6.3188e-04 eta 0:11:33
epoch [37/50] batch [140/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.1525 (0.5972) lr 6.3188e-04 eta 0:11:27
epoch [37/50] batch [160/204] time 0.244 (0.253) data 0.000 (0.003) loss 0.0989 (0.6232) lr 6.3188e-04 eta 0:11:20
epoch [37/50] batch [180/204] time 0.250 (0.252) data 0.000 (0.002) loss 1.4259 (0.6130) lr 6.3188e-04 eta 0:11:15
epoch [37/50] batch [200/204] time 0.245 (0.252) data 0.000 (0.002) loss 1.6108 (0.6271) lr 6.3188e-04 eta 0:11:09
epoch [38/50] batch [20/204] time 0.246 (0.269) data 0.000 (0.020) loss 0.0467 (0.6441) lr 5.7422e-04 eta 0:11:48
epoch [38/50] batch [40/204] time 0.250 (0.259) data 0.000 (0.010) loss 0.8200 (0.7888) lr 5.7422e-04 eta 0:11:17
epoch [38/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.007) loss 1.0666 (0.7230) lr 5.7422e-04 eta 0:11:04
epoch [38/50] batch [80/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.0223 (0.6426) lr 5.7422e-04 eta 0:10:54
epoch [38/50] batch [100/204] time 0.247 (0.254) data 0.000 (0.004) loss 1.3302 (0.6211) lr 5.7422e-04 eta 0:10:47
epoch [38/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.8934 (0.6047) lr 5.7422e-04 eta 0:10:40
epoch [38/50] batch [140/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.0406 (0.6259) lr 5.7422e-04 eta 0:10:34
epoch [38/50] batch [160/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.4998 (0.6518) lr 5.7422e-04 eta 0:10:28
epoch [38/50] batch [180/204] time 0.246 (0.252) data 0.000 (0.002) loss 1.1802 (0.6466) lr 5.7422e-04 eta 0:10:22
epoch [38/50] batch [200/204] time 0.253 (0.252) data 0.008 (0.002) loss 0.4037 (0.6459) lr 5.7422e-04 eta 0:10:17
epoch [39/50] batch [20/204] time 0.249 (0.270) data 0.000 (0.019) loss 0.0427 (0.5683) lr 5.1825e-04 eta 0:10:55
epoch [39/50] batch [40/204] time 0.249 (0.260) data 0.000 (0.010) loss 0.3924 (0.6423) lr 5.1825e-04 eta 0:10:25
epoch [39/50] batch [60/204] time 0.247 (0.256) data 0.000 (0.007) loss 0.2218 (0.5798) lr 5.1825e-04 eta 0:10:12
epoch [39/50] batch [80/204] time 0.254 (0.255) data 0.000 (0.005) loss 0.0592 (0.5496) lr 5.1825e-04 eta 0:10:03
epoch [39/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.3168 (0.5463) lr 5.1825e-04 eta 0:09:55
epoch [39/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.003) loss 2.0429 (0.6126) lr 5.1825e-04 eta 0:09:49
epoch [39/50] batch [140/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.0107 (0.5867) lr 5.1825e-04 eta 0:09:43
epoch [39/50] batch [160/204] time 0.260 (0.253) data 0.000 (0.003) loss 0.0395 (0.5831) lr 5.1825e-04 eta 0:09:37
epoch [39/50] batch [180/204] time 0.256 (0.252) data 0.000 (0.002) loss 0.8530 (0.5885) lr 5.1825e-04 eta 0:09:32
epoch [39/50] batch [200/204] time 0.248 (0.252) data 0.000 (0.002) loss 0.0107 (0.5725) lr 5.1825e-04 eta 0:09:26
epoch [40/50] batch [20/204] time 0.253 (0.270) data 0.000 (0.019) loss 0.0951 (0.4507) lr 4.6417e-04 eta 0:10:00
epoch [40/50] batch [40/204] time 0.252 (0.260) data 0.000 (0.010) loss 1.3081 (0.4819) lr 4.6417e-04 eta 0:09:32
epoch [40/50] batch [60/204] time 0.251 (0.257) data 0.000 (0.007) loss 0.0173 (0.5551) lr 4.6417e-04 eta 0:09:20
epoch [40/50] batch [80/204] time 0.250 (0.255) data 0.000 (0.005) loss 0.7677 (0.5908) lr 4.6417e-04 eta 0:09:11
epoch [40/50] batch [100/204] time 0.251 (0.254) data 0.000 (0.004) loss 0.4373 (0.5748) lr 4.6417e-04 eta 0:09:04
epoch [40/50] batch [120/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.0557 (0.5689) lr 4.6417e-04 eta 0:08:57
epoch [40/50] batch [140/204] time 0.251 (0.253) data 0.000 (0.003) loss 0.5942 (0.5553) lr 4.6417e-04 eta 0:08:51
epoch [40/50] batch [160/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.4286 (0.5554) lr 4.6417e-04 eta 0:08:46
epoch [40/50] batch [180/204] time 0.253 (0.252) data 0.000 (0.002) loss 2.1582 (0.5685) lr 4.6417e-04 eta 0:08:40
epoch [40/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 0.4634 (0.5675) lr 4.6417e-04 eta 0:08:35
epoch [41/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.019) loss 0.1617 (0.6558) lr 4.1221e-04 eta 0:09:05
epoch [41/50] batch [40/204] time 0.249 (0.260) data 0.000 (0.010) loss 0.2426 (0.6145) lr 4.1221e-04 eta 0:08:39
epoch [41/50] batch [60/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.0935 (0.5590) lr 4.1221e-04 eta 0:08:28
epoch [41/50] batch [80/204] time 0.253 (0.255) data 0.000 (0.005) loss 0.4528 (0.5134) lr 4.1221e-04 eta 0:08:19
epoch [41/50] batch [100/204] time 0.254 (0.254) data 0.000 (0.004) loss 0.6428 (0.5004) lr 4.1221e-04 eta 0:08:13
epoch [41/50] batch [120/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.1275 (0.5363) lr 4.1221e-04 eta 0:08:07
epoch [41/50] batch [140/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.9223 (0.5369) lr 4.1221e-04 eta 0:08:01
epoch [41/50] batch [160/204] time 0.255 (0.253) data 0.000 (0.003) loss 0.7999 (0.5702) lr 4.1221e-04 eta 0:07:56
epoch [41/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.3862 (0.5763) lr 4.1221e-04 eta 0:07:50
epoch [41/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 1.5767 (0.5813) lr 4.1221e-04 eta 0:07:45
epoch [42/50] batch [20/204] time 0.254 (0.272) data 0.000 (0.019) loss 0.1385 (0.5051) lr 3.6258e-04 eta 0:08:13
epoch [42/50] batch [40/204] time 0.254 (0.263) data 0.000 (0.010) loss 0.6099 (0.5839) lr 3.6258e-04 eta 0:07:51
epoch [42/50] batch [60/204] time 0.254 (0.259) data 0.000 (0.007) loss 1.7872 (0.6716) lr 3.6258e-04 eta 0:07:40
epoch [42/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.005) loss 0.0387 (0.6301) lr 3.6258e-04 eta 0:07:32
epoch [42/50] batch [100/204] time 0.256 (0.256) data 0.000 (0.004) loss 0.4311 (0.5902) lr 3.6258e-04 eta 0:07:25
epoch [42/50] batch [120/204] time 0.256 (0.256) data 0.000 (0.003) loss 0.0188 (0.5781) lr 3.6258e-04 eta 0:07:19
epoch [42/50] batch [140/204] time 0.248 (0.256) data 0.000 (0.003) loss 0.5209 (0.5983) lr 3.6258e-04 eta 0:07:13
epoch [42/50] batch [160/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.2316 (0.5761) lr 3.6258e-04 eta 0:07:07
epoch [42/50] batch [180/204] time 0.254 (0.255) data 0.000 (0.002) loss 0.3991 (0.5769) lr 3.6258e-04 eta 0:07:02
epoch [42/50] batch [200/204] time 0.247 (0.255) data 0.000 (0.002) loss 0.0074 (0.5813) lr 3.6258e-04 eta 0:06:56
epoch [43/50] batch [20/204] time 0.253 (0.272) data 0.000 (0.021) loss 0.0790 (0.7005) lr 3.1545e-04 eta 0:07:19
epoch [43/50] batch [40/204] time 0.247 (0.263) data 0.000 (0.011) loss 0.9279 (0.6347) lr 3.1545e-04 eta 0:06:57
epoch [43/50] batch [60/204] time 0.259 (0.259) data 0.005 (0.007) loss 0.0063 (0.6311) lr 3.1545e-04 eta 0:06:46
epoch [43/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.005) loss 0.2157 (0.6065) lr 3.1545e-04 eta 0:06:39
epoch [43/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.004) loss 0.1385 (0.6108) lr 3.1545e-04 eta 0:06:32
epoch [43/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.004) loss 0.2672 (0.5763) lr 3.1545e-04 eta 0:06:26
epoch [43/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.2070 (0.5702) lr 3.1545e-04 eta 0:06:20
epoch [43/50] batch [160/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.4549 (0.5598) lr 3.1545e-04 eta 0:06:14
epoch [43/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.3376 (0.5745) lr 3.1545e-04 eta 0:06:08
epoch [43/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.002) loss 0.9791 (0.5680) lr 3.1545e-04 eta 0:06:03
epoch [44/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.020) loss 0.1843 (0.7393) lr 2.7103e-04 eta 0:06:20
epoch [44/50] batch [40/204] time 0.251 (0.261) data 0.000 (0.010) loss 0.0704 (0.5639) lr 2.7103e-04 eta 0:06:01
epoch [44/50] batch [60/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.0224 (0.5357) lr 2.7103e-04 eta 0:05:52
epoch [44/50] batch [80/204] time 0.250 (0.256) data 0.000 (0.005) loss 1.0384 (0.5121) lr 2.7103e-04 eta 0:05:45
epoch [44/50] batch [100/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.6738 (0.5328) lr 2.7103e-04 eta 0:05:39
epoch [44/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.2317 (0.5140) lr 2.7103e-04 eta 0:05:33
epoch [44/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.2551 (0.4928) lr 2.7103e-04 eta 0:05:27
epoch [44/50] batch [160/204] time 0.261 (0.254) data 0.000 (0.003) loss 0.4996 (0.5128) lr 2.7103e-04 eta 0:05:21
epoch [44/50] batch [180/204] time 0.251 (0.253) data 0.000 (0.002) loss 0.8330 (0.5278) lr 2.7103e-04 eta 0:05:16
epoch [44/50] batch [200/204] time 0.246 (0.253) data 0.000 (0.002) loss 0.0308 (0.5339) lr 2.7103e-04 eta 0:05:10
epoch [45/50] batch [20/204] time 0.253 (0.273) data 0.000 (0.020) loss 0.0579 (0.3964) lr 2.2949e-04 eta 0:05:29
epoch [45/50] batch [40/204] time 0.248 (0.262) data 0.000 (0.010) loss 2.1501 (0.4178) lr 2.2949e-04 eta 0:05:10
epoch [45/50] batch [60/204] time 0.251 (0.258) data 0.000 (0.007) loss 1.0322 (0.5523) lr 2.2949e-04 eta 0:05:00
epoch [45/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.005) loss 0.2970 (0.5257) lr 2.2949e-04 eta 0:04:53
epoch [45/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.004) loss 0.0737 (0.5603) lr 2.2949e-04 eta 0:04:47
epoch [45/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 1.0865 (0.5422) lr 2.2949e-04 eta 0:04:41
epoch [45/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.0259 (0.5650) lr 2.2949e-04 eta 0:04:36
epoch [45/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1978 (0.5489) lr 2.2949e-04 eta 0:04:30
epoch [45/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.002) loss 0.1759 (0.5590) lr 2.2949e-04 eta 0:04:25
epoch [45/50] batch [200/204] time 0.249 (0.254) data 0.000 (0.002) loss 0.6301 (0.5588) lr 2.2949e-04 eta 0:04:19
epoch [46/50] batch [20/204] time 0.252 (0.272) data 0.000 (0.020) loss 1.3389 (0.6284) lr 1.9098e-04 eta 0:04:31
epoch [46/50] batch [40/204] time 0.247 (0.261) data 0.000 (0.010) loss 0.1121 (0.4865) lr 1.9098e-04 eta 0:04:15
epoch [46/50] batch [60/204] time 0.252 (0.258) data 0.000 (0.007) loss 0.3685 (0.4933) lr 1.9098e-04 eta 0:04:07
epoch [46/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.005) loss 0.2656 (0.5036) lr 1.9098e-04 eta 0:04:01
epoch [46/50] batch [100/204] time 0.248 (0.256) data 0.000 (0.004) loss 0.4633 (0.4977) lr 1.9098e-04 eta 0:03:55
epoch [46/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.3987 (0.5645) lr 1.9098e-04 eta 0:03:49
epoch [46/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.3828 (0.5946) lr 1.9098e-04 eta 0:03:43
epoch [46/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.9466 (0.5715) lr 1.9098e-04 eta 0:03:38
epoch [46/50] batch [180/204] time 0.245 (0.253) data 0.000 (0.002) loss 0.0244 (0.5788) lr 1.9098e-04 eta 0:03:32
epoch [46/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.9046 (0.5943) lr 1.9098e-04 eta 0:03:27
epoch [47/50] batch [20/204] time 0.250 (0.271) data 0.000 (0.019) loss 0.0319 (0.3138) lr 1.5567e-04 eta 0:03:35
epoch [47/50] batch [40/204] time 0.251 (0.261) data 0.000 (0.010) loss 0.7263 (0.4551) lr 1.5567e-04 eta 0:03:22
epoch [47/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.007) loss 0.7271 (0.4774) lr 1.5567e-04 eta 0:03:14
epoch [47/50] batch [80/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.7335 (0.4796) lr 1.5567e-04 eta 0:03:08
epoch [47/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0409 (0.4948) lr 1.5567e-04 eta 0:03:02
epoch [47/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1676 (0.5130) lr 1.5567e-04 eta 0:02:57
epoch [47/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.1085 (0.5095) lr 1.5567e-04 eta 0:02:51
epoch [47/50] batch [160/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.3523 (0.5242) lr 1.5567e-04 eta 0:02:46
epoch [47/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.0855 (0.5501) lr 1.5567e-04 eta 0:02:41
epoch [47/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.0141 (0.5482) lr 1.5567e-04 eta 0:02:35
epoch [48/50] batch [20/204] time 0.255 (0.269) data 0.000 (0.019) loss 0.7208 (0.6771) lr 1.2369e-04 eta 0:02:39
epoch [48/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.0142 (0.6695) lr 1.2369e-04 eta 0:02:29
epoch [48/50] batch [60/204] time 0.248 (0.257) data 0.000 (0.007) loss 0.2611 (0.6329) lr 1.2369e-04 eta 0:02:21
epoch [48/50] batch [80/204] time 0.245 (0.256) data 0.000 (0.005) loss 0.3277 (0.5979) lr 1.2369e-04 eta 0:02:16
epoch [48/50] batch [100/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.0309 (0.5816) lr 1.2369e-04 eta 0:02:10
epoch [48/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.3296 (0.5512) lr 1.2369e-04 eta 0:02:05
epoch [48/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.5091 (0.5462) lr 1.2369e-04 eta 0:01:59
epoch [48/50] batch [160/204] time 0.246 (0.254) data 0.000 (0.003) loss 0.2442 (0.5464) lr 1.2369e-04 eta 0:01:54
epoch [48/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.4502 (0.5439) lr 1.2369e-04 eta 0:01:49
epoch [48/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.2718 (0.5432) lr 1.2369e-04 eta 0:01:44
epoch [49/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.019) loss 0.2502 (0.4893) lr 9.5173e-05 eta 0:01:45
epoch [49/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.3698 (0.4871) lr 9.5173e-05 eta 0:01:36
epoch [49/50] batch [60/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.5137 (0.5935) lr 9.5173e-05 eta 0:01:29
epoch [49/50] batch [80/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.3550 (0.6400) lr 9.5173e-05 eta 0:01:23
epoch [49/50] batch [100/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.2583 (0.6078) lr 9.5173e-05 eta 0:01:18
epoch [49/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.3083 (0.5900) lr 9.5173e-05 eta 0:01:13
epoch [49/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.3667 (0.5947) lr 9.5173e-05 eta 0:01:07
epoch [49/50] batch [160/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.5506 (0.5890) lr 9.5173e-05 eta 0:01:02
epoch [49/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.0147 (0.5801) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.1466 (0.5828) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.252 (0.271) data 0.000 (0.020) loss 1.3943 (0.6081) lr 7.0224e-05 eta 0:00:49
epoch [50/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.010) loss 0.2758 (0.4959) lr 7.0224e-05 eta 0:00:42
epoch [50/50] batch [60/204] time 0.250 (0.257) data 0.000 (0.007) loss 0.1475 (0.5196) lr 7.0224e-05 eta 0:00:37
epoch [50/50] batch [80/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.7161 (0.5957) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.7085 (0.6016) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.2464 (0.5728) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.247 (0.254) data 0.000 (0.003) loss 1.2866 (0.5993) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.6792 (0.6165) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.249 (0.253) data 0.000 (0.002) loss 0.0598 (0.6212) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.002) loss 0.9065 (0.6006) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/food101/vit_b16_ep50_c4_BZ4_ProDA/seed1/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 15,300
* correct: 13,789
* accuracy: 90.12%
* error: 9.88%
* macro_f1: 90.07%
Elapsed: 0:44:17
