***************
** 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/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: 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/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:                 99%
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_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    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/seed3/tensorboard)
epoch [1/50] batch [20/204] time 0.249 (0.385) data 0.000 (0.030) loss 0.4014 (1.2357) lr 1.0000e-05 eta 1:05:17
epoch [1/50] batch [40/204] time 0.250 (0.317) data 0.000 (0.015) loss 0.2023 (1.2125) lr 1.0000e-05 eta 0:53:44
epoch [1/50] batch [60/204] time 0.251 (0.295) data 0.000 (0.010) loss 2.1775 (1.2318) lr 1.0000e-05 eta 0:49:48
epoch [1/50] batch [80/204] time 0.247 (0.283) data 0.000 (0.008) loss 1.2495 (1.1204) lr 1.0000e-05 eta 0:47:47
epoch [1/50] batch [100/204] time 0.253 (0.277) data 0.000 (0.006) loss 0.1523 (1.0785) lr 1.0000e-05 eta 0:46:35
epoch [1/50] batch [120/204] time 0.249 (0.272) data 0.000 (0.005) loss 1.3030 (1.1059) lr 1.0000e-05 eta 0:45:45
epoch [1/50] batch [140/204] time 0.246 (0.269) data 0.000 (0.004) loss 0.8730 (1.0751) lr 1.0000e-05 eta 0:45:07
epoch [1/50] batch [160/204] time 0.247 (0.267) data 0.000 (0.004) loss 0.2546 (1.0246) lr 1.0000e-05 eta 0:44:38
epoch [1/50] batch [180/204] time 0.247 (0.265) data 0.000 (0.003) loss 0.9764 (1.0060) lr 1.0000e-05 eta 0:44:14
epoch [1/50] batch [200/204] time 0.253 (0.264) data 0.000 (0.003) loss 0.0780 (1.0209) lr 1.0000e-05 eta 0:43:55
epoch [2/50] batch [20/204] time 0.252 (0.276) data 0.000 (0.026) loss 2.0666 (1.2580) lr 1.0000e-05 eta 0:45:57
epoch [2/50] batch [40/204] time 0.244 (0.264) data 0.000 (0.013) loss 0.4333 (1.1398) lr 1.0000e-05 eta 0:43:50
epoch [2/50] batch [60/204] time 0.245 (0.260) data 0.000 (0.009) loss 0.0236 (1.0459) lr 1.0000e-05 eta 0:43:00
epoch [2/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.007) loss 0.4507 (0.9632) lr 1.0000e-05 eta 0:42:32
epoch [2/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.005) loss 1.6226 (1.0030) lr 1.0000e-05 eta 0:42:15
epoch [2/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.2611 (1.0115) lr 1.0000e-05 eta 0:42:03
epoch [2/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.4118 (0.9880) lr 1.0000e-05 eta 0:41:51
epoch [2/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.8239 (0.9634) lr 1.0000e-05 eta 0:41:42
epoch [2/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.0368 (0.9470) lr 1.0000e-05 eta 0:41:33
epoch [2/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.7651 (0.9335) lr 1.0000e-05 eta 0:41:25
epoch [3/50] batch [20/204] time 0.251 (0.277) data 0.000 (0.025) loss 1.3229 (0.8543) lr 1.0000e-05 eta 0:45:07
epoch [3/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.5761 (0.8161) lr 1.0000e-05 eta 0:42:56
epoch [3/50] batch [60/204] time 0.251 (0.260) data 0.000 (0.009) loss 1.7479 (0.8347) lr 1.0000e-05 eta 0:42:10
epoch [3/50] batch [80/204] time 0.248 (0.258) data 0.000 (0.006) loss 0.6551 (0.8900) lr 1.0000e-05 eta 0:41:41
epoch [3/50] batch [100/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.4841 (0.8636) lr 1.0000e-05 eta 0:41:22
epoch [3/50] batch [120/204] time 0.256 (0.255) data 0.000 (0.004) loss 1.6411 (0.8488) lr 1.0000e-05 eta 0:41:09
epoch [3/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.004) loss 1.3892 (0.8309) lr 1.0000e-05 eta 0:41:00
epoch [3/50] batch [160/204] time 0.248 (0.254) data 0.000 (0.003) loss 1.4547 (0.8261) lr 1.0000e-05 eta 0:40:50
epoch [3/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.2609 (0.8011) lr 1.0000e-05 eta 0:40:43
epoch [3/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.003) loss 1.2006 (0.8234) lr 1.0000e-05 eta 0:40:35
epoch [4/50] batch [20/204] time 0.253 (0.278) data 0.000 (0.026) loss 0.4149 (0.7433) lr 1.0000e-05 eta 0:44:22
epoch [4/50] batch [40/204] time 0.253 (0.265) data 0.000 (0.013) loss 2.5738 (0.7601) lr 1.0000e-05 eta 0:42:10
epoch [4/50] batch [60/204] time 0.253 (0.261) data 0.000 (0.009) loss 1.0492 (0.7168) lr 1.0000e-05 eta 0:41:22
epoch [4/50] batch [80/204] time 0.253 (0.258) data 0.000 (0.007) loss 1.0989 (0.7693) lr 1.0000e-05 eta 0:40:55
epoch [4/50] batch [100/204] time 0.251 (0.257) data 0.000 (0.005) loss 0.5683 (0.7862) lr 1.0000e-05 eta 0:40:37
epoch [4/50] batch [120/204] time 0.249 (0.256) data 0.000 (0.005) loss 0.3964 (0.7848) lr 1.0000e-05 eta 0:40:22
epoch [4/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.1564 (0.7705) lr 1.0000e-05 eta 0:40:11
epoch [4/50] batch [160/204] time 0.256 (0.255) data 0.002 (0.003) loss 1.2203 (0.7801) lr 1.0000e-05 eta 0:40:02
epoch [4/50] batch [180/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1320 (0.7606) lr 1.0000e-05 eta 0:39:54
epoch [4/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 1.4708 (0.7615) lr 1.0000e-05 eta 0:39:46
epoch [5/50] batch [20/204] time 0.248 (0.278) data 0.000 (0.026) loss 1.3371 (0.9704) lr 1.0000e-05 eta 0:43:22
epoch [5/50] batch [40/204] time 0.255 (0.265) data 0.000 (0.013) loss 0.8933 (0.7921) lr 1.0000e-05 eta 0:41:13
epoch [5/50] batch [60/204] time 0.250 (0.260) data 0.000 (0.009) loss 1.0363 (0.7419) lr 1.0000e-05 eta 0:40:24
epoch [5/50] batch [80/204] time 0.257 (0.258) data 0.000 (0.007) loss 0.2721 (0.7639) lr 1.0000e-05 eta 0:40:00
epoch [5/50] batch [100/204] time 0.249 (0.257) data 0.000 (0.005) loss 0.0593 (0.7683) lr 1.0000e-05 eta 0:39:44
epoch [5/50] batch [120/204] time 0.248 (0.256) data 0.000 (0.005) loss 0.1976 (0.7458) lr 1.0000e-05 eta 0:39:31
epoch [5/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.5502 (0.7578) lr 1.0000e-05 eta 0:39:20
epoch [5/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 2.6055 (0.7894) lr 1.0000e-05 eta 0:39:11
epoch [5/50] batch [180/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.5754 (0.7797) lr 1.0000e-05 eta 0:39:03
epoch [5/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.003) loss 2.4239 (0.7771) lr 1.0000e-05 eta 0:38:55
epoch [6/50] batch [20/204] time 0.249 (0.278) data 0.000 (0.026) loss 0.8544 (0.9561) lr 2.0000e-03 eta 0:42:28
epoch [6/50] batch [40/204] time 0.248 (0.265) data 0.000 (0.013) loss 1.5350 (0.8642) lr 2.0000e-03 eta 0:40:24
epoch [6/50] batch [60/204] time 0.254 (0.261) data 0.000 (0.009) loss 0.0473 (0.7883) lr 2.0000e-03 eta 0:39:37
epoch [6/50] batch [80/204] time 0.251 (0.259) data 0.000 (0.007) loss 0.2404 (0.8080) lr 2.0000e-03 eta 0:39:12
epoch [6/50] batch [100/204] time 0.248 (0.257) data 0.000 (0.005) loss 1.0080 (0.7921) lr 2.0000e-03 eta 0:38:55
epoch [6/50] batch [120/204] time 0.254 (0.256) data 0.000 (0.005) loss 0.0839 (0.7813) lr 2.0000e-03 eta 0:38:42
epoch [6/50] batch [140/204] time 0.249 (0.256) data 0.000 (0.004) loss 0.1634 (0.7873) lr 2.0000e-03 eta 0:38:31
epoch [6/50] batch [160/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.2831 (0.7838) lr 2.0000e-03 eta 0:38:21
epoch [6/50] batch [180/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.2844 (0.7636) lr 2.0000e-03 eta 0:38:13
epoch [6/50] batch [200/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.3192 (0.7699) lr 2.0000e-03 eta 0:38:05
epoch [7/50] batch [20/204] time 0.254 (0.278) data 0.000 (0.026) loss 0.1617 (0.6249) lr 1.9980e-03 eta 0:41:26
epoch [7/50] batch [40/204] time 0.254 (0.265) data 0.000 (0.013) loss 0.5935 (0.5605) lr 1.9980e-03 eta 0:39:25
epoch [7/50] batch [60/204] time 0.252 (0.261) data 0.000 (0.009) loss 0.0227 (0.5764) lr 1.9980e-03 eta 0:38:43
epoch [7/50] batch [80/204] time 0.248 (0.258) data 0.000 (0.007) loss 0.3174 (0.7000) lr 1.9980e-03 eta 0:38:19
epoch [7/50] batch [100/204] time 0.249 (0.257) data 0.000 (0.005) loss 0.4967 (0.6830) lr 1.9980e-03 eta 0:38:01
epoch [7/50] batch [120/204] time 0.254 (0.256) data 0.000 (0.004) loss 1.0616 (0.6696) lr 1.9980e-03 eta 0:37:49
epoch [7/50] batch [140/204] time 0.253 (0.256) data 0.000 (0.004) loss 0.2025 (0.6809) lr 1.9980e-03 eta 0:37:39
epoch [7/50] batch [160/204] time 0.250 (0.255) data 0.000 (0.003) loss 0.0096 (0.6699) lr 1.9980e-03 eta 0:37:30
epoch [7/50] batch [180/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.8316 (0.6832) lr 1.9980e-03 eta 0:37:21
epoch [7/50] batch [200/204] time 0.246 (0.255) data 0.000 (0.003) loss 0.8941 (0.6762) lr 1.9980e-03 eta 0:37:13
epoch [8/50] batch [20/204] time 0.251 (0.277) data 0.000 (0.026) loss 0.3876 (0.4530) lr 1.9921e-03 eta 0:40:28
epoch [8/50] batch [40/204] time 0.254 (0.265) data 0.000 (0.013) loss 0.5770 (0.4837) lr 1.9921e-03 eta 0:38:30
epoch [8/50] batch [60/204] time 0.249 (0.260) data 0.000 (0.009) loss 0.8792 (0.4805) lr 1.9921e-03 eta 0:37:48
epoch [8/50] batch [80/204] time 0.252 (0.258) data 0.000 (0.007) loss 0.0710 (0.4209) lr 1.9921e-03 eta 0:37:26
epoch [8/50] batch [100/204] time 0.255 (0.257) data 0.000 (0.005) loss 0.3619 (0.4452) lr 1.9921e-03 eta 0:37:09
epoch [8/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.004) loss 1.5564 (0.4586) lr 1.9921e-03 eta 0:36:57
epoch [8/50] batch [140/204] time 0.250 (0.256) data 0.000 (0.004) loss 0.1113 (0.4825) lr 1.9921e-03 eta 0:36:48
epoch [8/50] batch [160/204] time 0.249 (0.255) data 0.000 (0.003) loss 0.0811 (0.5154) lr 1.9921e-03 eta 0:36:39
epoch [8/50] batch [180/204] time 0.252 (0.255) data 0.000 (0.003) loss 1.3268 (0.5415) lr 1.9921e-03 eta 0:36:31
epoch [8/50] batch [200/204] time 0.250 (0.255) data 0.000 (0.003) loss 0.1308 (0.5657) lr 1.9921e-03 eta 0:36:23
epoch [9/50] batch [20/204] time 0.251 (0.277) data 0.000 (0.026) loss 1.8898 (0.7436) lr 1.9823e-03 eta 0:39:29
epoch [9/50] batch [40/204] time 0.247 (0.264) data 0.000 (0.013) loss 0.1301 (0.7300) lr 1.9823e-03 eta 0:37:34
epoch [9/50] batch [60/204] time 0.255 (0.261) data 0.000 (0.009) loss 0.0917 (0.6605) lr 1.9823e-03 eta 0:36:56
epoch [9/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.3813 (0.6451) lr 1.9823e-03 eta 0:36:32
epoch [9/50] batch [100/204] time 0.255 (0.257) data 0.000 (0.005) loss 0.5118 (0.6084) lr 1.9823e-03 eta 0:36:16
epoch [9/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.004) loss 0.3980 (0.6047) lr 1.9823e-03 eta 0:36:05
epoch [9/50] batch [140/204] time 0.249 (0.256) data 0.000 (0.004) loss 0.9675 (0.5873) lr 1.9823e-03 eta 0:35:55
epoch [9/50] batch [160/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.7961 (0.5897) lr 1.9823e-03 eta 0:35:45
epoch [9/50] batch [180/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.9606 (0.5890) lr 1.9823e-03 eta 0:35:38
epoch [9/50] batch [200/204] time 0.248 (0.255) data 0.000 (0.003) loss 1.8938 (0.5908) lr 1.9823e-03 eta 0:35:30
epoch [10/50] batch [20/204] time 0.252 (0.278) data 0.000 (0.026) loss 0.4465 (0.5330) lr 1.9686e-03 eta 0:38:41
epoch [10/50] batch [40/204] time 0.252 (0.265) data 0.000 (0.013) loss 1.1066 (0.5244) lr 1.9686e-03 eta 0:36:47
epoch [10/50] batch [60/204] time 0.254 (0.261) data 0.000 (0.009) loss 0.4601 (0.5167) lr 1.9686e-03 eta 0:36:03
epoch [10/50] batch [80/204] time 0.248 (0.258) data 0.000 (0.007) loss 0.0136 (0.5249) lr 1.9686e-03 eta 0:35:40
epoch [10/50] batch [100/204] time 0.254 (0.257) data 0.000 (0.005) loss 0.0383 (0.5124) lr 1.9686e-03 eta 0:35:23
epoch [10/50] batch [120/204] time 0.252 (0.256) data 0.000 (0.005) loss 0.0449 (0.5474) lr 1.9686e-03 eta 0:35:11
epoch [10/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.6580 (0.5404) lr 1.9686e-03 eta 0:35:00
epoch [10/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.4555 (0.5293) lr 1.9686e-03 eta 0:34:53
epoch [10/50] batch [180/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.1608 (0.5388) lr 1.9686e-03 eta 0:34:44
epoch [10/50] batch [200/204] time 0.249 (0.254) data 0.000 (0.003) loss 2.7024 (0.5478) lr 1.9686e-03 eta 0:34:36
epoch [11/50] batch [20/204] time 0.251 (0.278) data 0.000 (0.026) loss 0.3660 (0.4652) lr 1.9511e-03 eta 0:37:45
epoch [11/50] batch [40/204] time 0.255 (0.265) data 0.000 (0.013) loss 0.8994 (0.4993) lr 1.9511e-03 eta 0:35:52
epoch [11/50] batch [60/204] time 0.251 (0.260) data 0.000 (0.009) loss 1.3208 (0.5314) lr 1.9511e-03 eta 0:35:09
epoch [11/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 1.3547 (0.5935) lr 1.9511e-03 eta 0:34:47
epoch [11/50] batch [100/204] time 0.249 (0.257) data 0.000 (0.005) loss 0.1222 (0.5966) lr 1.9511e-03 eta 0:34:33
epoch [11/50] batch [120/204] time 0.255 (0.256) data 0.000 (0.005) loss 2.1116 (0.6185) lr 1.9511e-03 eta 0:34:21
epoch [11/50] batch [140/204] time 0.254 (0.256) data 0.000 (0.004) loss 0.7427 (0.6223) lr 1.9511e-03 eta 0:34:12
epoch [11/50] batch [160/204] time 0.249 (0.255) data 0.000 (0.003) loss 0.0194 (0.6255) lr 1.9511e-03 eta 0:34:03
epoch [11/50] batch [180/204] time 0.256 (0.255) data 0.000 (0.003) loss 0.0378 (0.6027) lr 1.9511e-03 eta 0:33:54
epoch [11/50] batch [200/204] time 0.247 (0.255) data 0.000 (0.003) loss 0.1187 (0.5987) lr 1.9511e-03 eta 0:33:47
epoch [12/50] batch [20/204] time 0.252 (0.278) data 0.000 (0.025) loss 0.0839 (0.7165) lr 1.9298e-03 eta 0:36:43
epoch [12/50] batch [40/204] time 0.255 (0.265) data 0.000 (0.013) loss 1.8633 (0.6611) lr 1.9298e-03 eta 0:34:58
epoch [12/50] batch [60/204] time 0.255 (0.261) data 0.001 (0.009) loss 0.2981 (0.5524) lr 1.9298e-03 eta 0:34:18
epoch [12/50] batch [80/204] time 0.255 (0.259) data 0.000 (0.007) loss 0.0725 (0.5572) lr 1.9298e-03 eta 0:33:57
epoch [12/50] batch [100/204] time 0.255 (0.257) data 0.000 (0.005) loss 0.1399 (0.5518) lr 1.9298e-03 eta 0:33:42
epoch [12/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.004) loss 1.8128 (0.5609) lr 1.9298e-03 eta 0:33:29
epoch [12/50] batch [140/204] time 0.254 (0.256) data 0.000 (0.004) loss 0.0278 (0.5566) lr 1.9298e-03 eta 0:33:19
epoch [12/50] batch [160/204] time 0.258 (0.255) data 0.003 (0.003) loss 0.0584 (0.5420) lr 1.9298e-03 eta 0:33:11
epoch [12/50] batch [180/204] time 0.253 (0.255) data 0.000 (0.003) loss 1.4610 (0.5527) lr 1.9298e-03 eta 0:33:03
epoch [12/50] batch [200/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.0390 (0.5779) lr 1.9298e-03 eta 0:32:55
epoch [13/50] batch [20/204] time 0.249 (0.276) data 0.000 (0.024) loss 1.5218 (0.5820) lr 1.9048e-03 eta 0:35:36
epoch [13/50] batch [40/204] time 0.248 (0.264) data 0.000 (0.012) loss 0.9988 (0.5710) lr 1.9048e-03 eta 0:33:57
epoch [13/50] batch [60/204] time 0.254 (0.260) data 0.000 (0.008) loss 0.0696 (0.5244) lr 1.9048e-03 eta 0:33:20
epoch [13/50] batch [80/204] time 0.248 (0.258) data 0.000 (0.006) loss 0.0222 (0.4734) lr 1.9048e-03 eta 0:32:59
epoch [13/50] batch [100/204] time 0.255 (0.257) data 0.000 (0.005) loss 1.2673 (0.5619) lr 1.9048e-03 eta 0:32:44
epoch [13/50] batch [120/204] time 0.252 (0.256) data 0.000 (0.004) loss 0.4800 (0.5384) lr 1.9048e-03 eta 0:32:34
epoch [13/50] batch [140/204] time 0.256 (0.256) data 0.000 (0.004) loss 0.1764 (0.5152) lr 1.9048e-03 eta 0:32:25
epoch [13/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.6090 (0.5042) lr 1.9048e-03 eta 0:32:16
epoch [13/50] batch [180/204] time 0.256 (0.255) data 0.002 (0.003) loss 1.2785 (0.5259) lr 1.9048e-03 eta 0:32:08
epoch [13/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.5091 (0.5315) lr 1.9048e-03 eta 0:32:01
epoch [14/50] batch [20/204] time 0.251 (0.278) data 0.000 (0.026) loss 0.9802 (0.5428) lr 1.8763e-03 eta 0:34:53
epoch [14/50] batch [40/204] time 0.253 (0.265) data 0.000 (0.013) loss 0.6448 (0.6150) lr 1.8763e-03 eta 0:33:06
epoch [14/50] batch [60/204] time 0.253 (0.261) data 0.000 (0.009) loss 0.2377 (0.5541) lr 1.8763e-03 eta 0:32:33
epoch [14/50] batch [80/204] time 0.245 (0.259) data 0.000 (0.007) loss 0.2337 (0.5171) lr 1.8763e-03 eta 0:32:10
epoch [14/50] batch [100/204] time 0.253 (0.257) data 0.000 (0.005) loss 0.5164 (0.5438) lr 1.8763e-03 eta 0:31:55
epoch [14/50] batch [120/204] time 0.254 (0.256) data 0.000 (0.004) loss 0.1077 (0.5154) lr 1.8763e-03 eta 0:31:44
epoch [14/50] batch [140/204] time 0.248 (0.256) data 0.000 (0.004) loss 1.0084 (0.4979) lr 1.8763e-03 eta 0:31:33
epoch [14/50] batch [160/204] time 0.250 (0.255) data 0.000 (0.003) loss 0.3551 (0.5119) lr 1.8763e-03 eta 0:31:24
epoch [14/50] batch [180/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.7193 (0.5295) lr 1.8763e-03 eta 0:31:16
epoch [14/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.003) loss 1.3644 (0.5440) lr 1.8763e-03 eta 0:31:08
epoch [15/50] batch [20/204] time 0.250 (0.276) data 0.000 (0.026) loss 0.1630 (0.5695) lr 1.8443e-03 eta 0:33:42
epoch [15/50] batch [40/204] time 0.251 (0.265) data 0.000 (0.013) loss 0.8155 (0.5828) lr 1.8443e-03 eta 0:32:12
epoch [15/50] batch [60/204] time 0.247 (0.260) data 0.000 (0.009) loss 0.5132 (0.6295) lr 1.8443e-03 eta 0:31:34
epoch [15/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.007) loss 1.1585 (0.6576) lr 1.8443e-03 eta 0:31:12
epoch [15/50] batch [100/204] time 0.260 (0.257) data 0.000 (0.005) loss 0.0100 (0.6362) lr 1.8443e-03 eta 0:30:58
epoch [15/50] batch [120/204] time 0.254 (0.256) data 0.000 (0.005) loss 0.1141 (0.6009) lr 1.8443e-03 eta 0:30:47
epoch [15/50] batch [140/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.5563 (0.5972) lr 1.8443e-03 eta 0:30:38
epoch [15/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 1.1657 (0.5946) lr 1.8443e-03 eta 0:30:29
epoch [15/50] batch [180/204] time 0.257 (0.254) data 0.000 (0.003) loss 1.2314 (0.5970) lr 1.8443e-03 eta 0:30:22
epoch [15/50] batch [200/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.6088 (0.6020) lr 1.8443e-03 eta 0:30:14
epoch [16/50] batch [20/204] time 0.248 (0.278) data 0.000 (0.026) loss 0.5705 (0.5992) lr 1.8090e-03 eta 0:32:59
epoch [16/50] batch [40/204] time 0.254 (0.265) data 0.000 (0.013) loss 0.2911 (0.5158) lr 1.8090e-03 eta 0:31:19
epoch [16/50] batch [60/204] time 0.246 (0.260) data 0.000 (0.009) loss 0.0445 (0.4958) lr 1.8090e-03 eta 0:30:42
epoch [16/50] batch [80/204] time 0.255 (0.258) data 0.000 (0.007) loss 0.1819 (0.5256) lr 1.8090e-03 eta 0:30:21
epoch [16/50] batch [100/204] time 0.254 (0.257) data 0.000 (0.005) loss 0.0779 (0.5659) lr 1.8090e-03 eta 0:30:06
epoch [16/50] batch [120/204] time 0.246 (0.256) data 0.000 (0.005) loss 0.0819 (0.5445) lr 1.8090e-03 eta 0:29:55
epoch [16/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.4244 (0.5188) lr 1.8090e-03 eta 0:29:45
epoch [16/50] batch [160/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.6616 (0.5200) lr 1.8090e-03 eta 0:29:36
epoch [16/50] batch [180/204] time 0.250 (0.254) data 0.000 (0.003) loss 1.0311 (0.5474) lr 1.8090e-03 eta 0:29:28
epoch [16/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0476 (0.5662) lr 1.8090e-03 eta 0:29:20
epoch [17/50] batch [20/204] time 0.248 (0.277) data 0.000 (0.026) loss 0.4779 (0.5709) lr 1.7705e-03 eta 0:31:55
epoch [17/50] batch [40/204] time 0.248 (0.264) data 0.000 (0.013) loss 0.1380 (0.5765) lr 1.7705e-03 eta 0:30:22
epoch [17/50] batch [60/204] time 0.250 (0.260) data 0.000 (0.009) loss 0.0743 (0.5087) lr 1.7705e-03 eta 0:29:46
epoch [17/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.0324 (0.5407) lr 1.7705e-03 eta 0:29:24
epoch [17/50] batch [100/204] time 0.251 (0.256) data 0.000 (0.005) loss 1.4315 (0.5664) lr 1.7705e-03 eta 0:29:11
epoch [17/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.0983 (0.5368) lr 1.7705e-03 eta 0:29:01
epoch [17/50] batch [140/204] time 0.255 (0.255) data 0.000 (0.004) loss 1.2765 (0.5379) lr 1.7705e-03 eta 0:28:52
epoch [17/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.2212 (0.5489) lr 1.7705e-03 eta 0:28:44
epoch [17/50] batch [180/204] time 0.246 (0.254) data 0.000 (0.003) loss 0.1533 (0.5687) lr 1.7705e-03 eta 0:28:36
epoch [17/50] batch [200/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.0683 (0.5625) lr 1.7705e-03 eta 0:28:29
epoch [18/50] batch [20/204] time 0.254 (0.276) data 0.000 (0.025) loss 0.0393 (0.4739) lr 1.7290e-03 eta 0:30:54
epoch [18/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.013) loss 0.0986 (0.5075) lr 1.7290e-03 eta 0:29:27
epoch [18/50] batch [60/204] time 0.252 (0.260) data 0.000 (0.009) loss 0.2106 (0.5557) lr 1.7290e-03 eta 0:28:52
epoch [18/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.007) loss 0.6458 (0.5745) lr 1.7290e-03 eta 0:28:32
epoch [18/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.0419 (0.5296) lr 1.7290e-03 eta 0:28:20
epoch [18/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.0586 (0.5283) lr 1.7290e-03 eta 0:28:09
epoch [18/50] batch [140/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.0768 (0.5210) lr 1.7290e-03 eta 0:27:58
epoch [18/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.3389 (0.5394) lr 1.7290e-03 eta 0:27:49
epoch [18/50] batch [180/204] time 0.244 (0.254) data 0.000 (0.003) loss 1.8177 (0.5443) lr 1.7290e-03 eta 0:27:42
epoch [18/50] batch [200/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.4190 (0.5386) lr 1.7290e-03 eta 0:27:34
epoch [19/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.026) loss 0.8742 (0.5237) lr 1.6845e-03 eta 0:29:59
epoch [19/50] batch [40/204] time 0.252 (0.263) data 0.000 (0.013) loss 1.8676 (0.6327) lr 1.6845e-03 eta 0:28:28
epoch [19/50] batch [60/204] time 0.247 (0.259) data 0.000 (0.009) loss 0.0419 (0.6597) lr 1.6845e-03 eta 0:27:55
epoch [19/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.0334 (0.6321) lr 1.6845e-03 eta 0:27:36
epoch [19/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.5137 (0.6138) lr 1.6845e-03 eta 0:27:23
epoch [19/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.004) loss 1.7491 (0.6143) lr 1.6845e-03 eta 0:27:12
epoch [19/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.6703 (0.5748) lr 1.6845e-03 eta 0:27:03
epoch [19/50] batch [160/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.2109 (0.5679) lr 1.6845e-03 eta 0:26:55
epoch [19/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.9838 (0.5868) lr 1.6845e-03 eta 0:26:48
epoch [19/50] batch [200/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.9333 (0.5714) lr 1.6845e-03 eta 0:26:40
epoch [20/50] batch [20/204] time 0.252 (0.276) data 0.000 (0.025) loss 0.8558 (0.7619) lr 1.6374e-03 eta 0:28:58
epoch [20/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.013) loss 0.0261 (0.7017) lr 1.6374e-03 eta 0:27:34
epoch [20/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.008) loss 0.6447 (0.6076) lr 1.6374e-03 eta 0:27:03
epoch [20/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.0228 (0.6009) lr 1.6374e-03 eta 0:26:44
epoch [20/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.8930 (0.5903) lr 1.6374e-03 eta 0:26:31
epoch [20/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 1.5493 (0.5772) lr 1.6374e-03 eta 0:26:21
epoch [20/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.004) loss 1.4941 (0.5458) lr 1.6374e-03 eta 0:26:13
epoch [20/50] batch [160/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.8973 (0.5210) lr 1.6374e-03 eta 0:26:05
epoch [20/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.5485 (0.5130) lr 1.6374e-03 eta 0:25:58
epoch [20/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.1651 (0.4982) lr 1.6374e-03 eta 0:25:51
epoch [21/50] batch [20/204] time 0.252 (0.276) data 0.000 (0.025) loss 0.2263 (0.5503) lr 1.5878e-03 eta 0:28:06
epoch [21/50] batch [40/204] time 0.251 (0.263) data 0.000 (0.013) loss 1.9116 (0.5299) lr 1.5878e-03 eta 0:26:41
epoch [21/50] batch [60/204] time 0.250 (0.259) data 0.001 (0.008) loss 0.1754 (0.5642) lr 1.5878e-03 eta 0:26:09
epoch [21/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.0027 (0.5458) lr 1.5878e-03 eta 0:25:51
epoch [21/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.0881 (0.4971) lr 1.5878e-03 eta 0:25:39
epoch [21/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.4166 (0.5563) lr 1.5878e-03 eta 0:25:29
epoch [21/50] batch [140/204] time 0.255 (0.254) data 0.000 (0.004) loss 0.5257 (0.5638) lr 1.5878e-03 eta 0:25:21
epoch [21/50] batch [160/204] time 0.251 (0.254) data 0.003 (0.003) loss 0.5076 (0.5548) lr 1.5878e-03 eta 0:25:14
epoch [21/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.1522 (0.5336) lr 1.5878e-03 eta 0:25:07
epoch [21/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.1000 (0.5446) lr 1.5878e-03 eta 0:25:00
epoch [22/50] batch [20/204] time 0.250 (0.276) data 0.000 (0.025) loss 0.0186 (0.4271) lr 1.5358e-03 eta 0:27:08
epoch [22/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.2154 (0.4216) lr 1.5358e-03 eta 0:25:53
epoch [22/50] batch [60/204] time 0.250 (0.260) data 0.000 (0.009) loss 0.7458 (0.4399) lr 1.5358e-03 eta 0:25:21
epoch [22/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.0434 (0.4592) lr 1.5358e-03 eta 0:25:04
epoch [22/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.1381 (0.4643) lr 1.5358e-03 eta 0:24:51
epoch [22/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.8523 (0.4840) lr 1.5358e-03 eta 0:24:40
epoch [22/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.3892 (0.4913) lr 1.5358e-03 eta 0:24:32
epoch [22/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.1281 (0.4889) lr 1.5358e-03 eta 0:24:24
epoch [22/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.2451 (0.4726) lr 1.5358e-03 eta 0:24:18
epoch [22/50] batch [200/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.9327 (0.4804) lr 1.5358e-03 eta 0:24:11
epoch [23/50] batch [20/204] time 0.255 (0.276) data 0.000 (0.025) loss 0.2115 (0.4687) lr 1.4818e-03 eta 0:26:12
epoch [23/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.1662 (0.5517) lr 1.4818e-03 eta 0:24:56
epoch [23/50] batch [60/204] time 0.250 (0.259) data 0.000 (0.008) loss 1.8948 (0.5854) lr 1.4818e-03 eta 0:24:26
epoch [23/50] batch [80/204] time 0.244 (0.257) data 0.000 (0.006) loss 0.0499 (0.6019) lr 1.4818e-03 eta 0:24:08
epoch [23/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.005) loss 0.0197 (0.5749) lr 1.4818e-03 eta 0:23:56
epoch [23/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.0146 (0.5618) lr 1.4818e-03 eta 0:23:47
epoch [23/50] batch [140/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.0421 (0.5540) lr 1.4818e-03 eta 0:23:38
epoch [23/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 1.6006 (0.5494) lr 1.4818e-03 eta 0:23:31
epoch [23/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.6635 (0.5380) lr 1.4818e-03 eta 0:23:24
epoch [23/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.003) loss 1.5436 (0.5529) lr 1.4818e-03 eta 0:23:17
epoch [24/50] batch [20/204] time 0.248 (0.278) data 0.000 (0.027) loss 1.1299 (0.3683) lr 1.4258e-03 eta 0:25:23
epoch [24/50] batch [40/204] time 0.254 (0.264) data 0.000 (0.014) loss 0.3503 (0.4646) lr 1.4258e-03 eta 0:24:04
epoch [24/50] batch [60/204] time 0.247 (0.259) data 0.000 (0.009) loss 0.7176 (0.5006) lr 1.4258e-03 eta 0:23:33
epoch [24/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.3189 (0.4943) lr 1.4258e-03 eta 0:23:15
epoch [24/50] batch [100/204] time 0.252 (0.256) data 0.000 (0.006) loss 0.0748 (0.4553) lr 1.4258e-03 eta 0:23:03
epoch [24/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.005) loss 0.2363 (0.4772) lr 1.4258e-03 eta 0:22:53
epoch [24/50] batch [140/204] time 0.245 (0.254) data 0.000 (0.004) loss 0.1093 (0.5100) lr 1.4258e-03 eta 0:22:44
epoch [24/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.004) loss 0.0358 (0.5221) lr 1.4258e-03 eta 0:22:36
epoch [24/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.2908 (0.5150) lr 1.4258e-03 eta 0:22:29
epoch [24/50] batch [200/204] time 0.245 (0.253) data 0.000 (0.003) loss 0.1324 (0.5205) lr 1.4258e-03 eta 0:22:23
epoch [25/50] batch [20/204] time 0.250 (0.276) data 0.000 (0.026) loss 0.0713 (0.5695) lr 1.3681e-03 eta 0:24:18
epoch [25/50] batch [40/204] time 0.254 (0.263) data 0.000 (0.013) loss 0.1609 (0.5367) lr 1.3681e-03 eta 0:23:05
epoch [25/50] batch [60/204] time 0.254 (0.259) data 0.000 (0.009) loss 1.4860 (0.5948) lr 1.3681e-03 eta 0:22:37
epoch [25/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.2476 (0.5828) lr 1.3681e-03 eta 0:22:22
epoch [25/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.4621 (0.6071) lr 1.3681e-03 eta 0:22:10
epoch [25/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.8483 (0.5775) lr 1.3681e-03 eta 0:22:01
epoch [25/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.6882 (0.5656) lr 1.3681e-03 eta 0:21:52
epoch [25/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.7258 (0.5736) lr 1.3681e-03 eta 0:21:46
epoch [25/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.4952 (0.5693) lr 1.3681e-03 eta 0:21:38
epoch [25/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.4714 (0.5481) lr 1.3681e-03 eta 0:21:31
epoch [26/50] batch [20/204] time 0.248 (0.276) data 0.000 (0.025) loss 1.0199 (0.5142) lr 1.3090e-03 eta 0:23:19
epoch [26/50] batch [40/204] time 0.250 (0.263) data 0.000 (0.013) loss 0.0181 (0.4713) lr 1.3090e-03 eta 0:22:11
epoch [26/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.009) loss 0.4423 (0.5388) lr 1.3090e-03 eta 0:21:46
epoch [26/50] batch [80/204] time 0.252 (0.257) data 0.000 (0.006) loss 0.0223 (0.4995) lr 1.3090e-03 eta 0:21:30
epoch [26/50] batch [100/204] time 0.256 (0.256) data 0.000 (0.005) loss 1.0770 (0.5274) lr 1.3090e-03 eta 0:21:18
epoch [26/50] batch [120/204] time 0.246 (0.255) data 0.000 (0.004) loss 0.1376 (0.5205) lr 1.3090e-03 eta 0:21:09
epoch [26/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.0896 (0.5194) lr 1.3090e-03 eta 0:21:00
epoch [26/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.9992 (0.5194) lr 1.3090e-03 eta 0:20:53
epoch [26/50] batch [180/204] time 0.244 (0.253) data 0.000 (0.003) loss 1.1753 (0.5105) lr 1.3090e-03 eta 0:20:46
epoch [26/50] batch [200/204] time 0.243 (0.253) data 0.000 (0.003) loss 0.4046 (0.5353) lr 1.3090e-03 eta 0:20:39
epoch [27/50] batch [20/204] time 0.247 (0.276) data 0.000 (0.026) loss 0.6235 (0.5716) lr 1.2487e-03 eta 0:22:24
epoch [27/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.013) loss 0.0727 (0.4703) lr 1.2487e-03 eta 0:21:18
epoch [27/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.009) loss 0.1327 (0.4239) lr 1.2487e-03 eta 0:20:53
epoch [27/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.8108 (0.4780) lr 1.2487e-03 eta 0:20:36
epoch [27/50] batch [100/204] time 0.246 (0.256) data 0.000 (0.005) loss 1.2708 (0.4943) lr 1.2487e-03 eta 0:20:25
epoch [27/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.0166 (0.4828) lr 1.2487e-03 eta 0:20:16
epoch [27/50] batch [140/204] time 0.247 (0.254) data 0.000 (0.004) loss 2.0039 (0.5045) lr 1.2487e-03 eta 0:20:07
epoch [27/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.1062 (0.5281) lr 1.2487e-03 eta 0:20:00
epoch [27/50] batch [180/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.9338 (0.5381) lr 1.2487e-03 eta 0:19:53
epoch [27/50] batch [200/204] time 0.251 (0.253) data 0.000 (0.003) loss 1.3574 (0.5434) lr 1.2487e-03 eta 0:19:47
epoch [28/50] batch [20/204] time 0.247 (0.276) data 0.000 (0.026) loss 0.3034 (0.3981) lr 1.1874e-03 eta 0:21:31
epoch [28/50] batch [40/204] time 0.246 (0.264) data 0.000 (0.013) loss 0.6126 (0.5059) lr 1.1874e-03 eta 0:20:27
epoch [28/50] batch [60/204] time 0.257 (0.260) data 0.000 (0.009) loss 0.3461 (0.4513) lr 1.1874e-03 eta 0:20:03
epoch [28/50] batch [80/204] time 0.260 (0.258) data 0.000 (0.007) loss 1.6809 (0.5016) lr 1.1874e-03 eta 0:19:51
epoch [28/50] batch [100/204] time 0.250 (0.258) data 0.000 (0.006) loss 0.3683 (0.4547) lr 1.1874e-03 eta 0:19:44
epoch [28/50] batch [120/204] time 0.260 (0.258) data 0.000 (0.005) loss 1.4006 (0.5050) lr 1.1874e-03 eta 0:19:37
epoch [28/50] batch [140/204] time 0.251 (0.257) data 0.000 (0.004) loss 0.6120 (0.5421) lr 1.1874e-03 eta 0:19:30
epoch [28/50] batch [160/204] time 0.255 (0.257) data 0.000 (0.004) loss 0.5920 (0.5180) lr 1.1874e-03 eta 0:19:26
epoch [28/50] batch [180/204] time 0.254 (0.257) data 0.000 (0.003) loss 0.0327 (0.4908) lr 1.1874e-03 eta 0:19:18
epoch [28/50] batch [200/204] time 0.252 (0.256) data 0.000 (0.003) loss 0.4399 (0.4878) lr 1.1874e-03 eta 0:19:11
epoch [29/50] batch [20/204] time 0.252 (0.278) data 0.000 (0.026) loss 0.1533 (0.5242) lr 1.1253e-03 eta 0:20:41
epoch [29/50] batch [40/204] time 0.262 (0.265) data 0.000 (0.013) loss 0.1503 (0.4042) lr 1.1253e-03 eta 0:19:37
epoch [29/50] batch [60/204] time 0.251 (0.262) data 0.000 (0.009) loss 0.6034 (0.4161) lr 1.1253e-03 eta 0:19:17
epoch [29/50] batch [80/204] time 0.253 (0.259) data 0.000 (0.007) loss 0.6418 (0.4735) lr 1.1253e-03 eta 0:19:00
epoch [29/50] batch [100/204] time 0.248 (0.257) data 0.000 (0.005) loss 0.1078 (0.4318) lr 1.1253e-03 eta 0:18:49
epoch [29/50] batch [120/204] time 0.255 (0.257) data 0.000 (0.004) loss 0.8337 (0.4319) lr 1.1253e-03 eta 0:18:41
epoch [29/50] batch [140/204] time 0.247 (0.256) data 0.000 (0.004) loss 0.0317 (0.4165) lr 1.1253e-03 eta 0:18:33
epoch [29/50] batch [160/204] time 0.254 (0.256) data 0.000 (0.003) loss 0.0625 (0.4401) lr 1.1253e-03 eta 0:18:26
epoch [29/50] batch [180/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.0157 (0.4340) lr 1.1253e-03 eta 0:18:19
epoch [29/50] batch [200/204] time 0.250 (0.255) data 0.000 (0.003) loss 0.0365 (0.4454) lr 1.1253e-03 eta 0:18:12
epoch [30/50] batch [20/204] time 0.252 (0.277) data 0.000 (0.026) loss 1.0675 (0.6633) lr 1.0628e-03 eta 0:19:42
epoch [30/50] batch [40/204] time 0.269 (0.264) data 0.000 (0.013) loss 0.0408 (0.5700) lr 1.0628e-03 eta 0:18:42
epoch [30/50] batch [60/204] time 0.252 (0.260) data 0.000 (0.009) loss 0.1464 (0.4649) lr 1.0628e-03 eta 0:18:18
epoch [30/50] batch [80/204] time 0.246 (0.258) data 0.000 (0.007) loss 2.0918 (0.4892) lr 1.0628e-03 eta 0:18:04
epoch [30/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.0755 (0.4681) lr 1.0628e-03 eta 0:17:52
epoch [30/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.005) loss 1.2152 (0.5054) lr 1.0628e-03 eta 0:17:43
epoch [30/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.6739 (0.5086) lr 1.0628e-03 eta 0:17:35
epoch [30/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 1.2309 (0.5335) lr 1.0628e-03 eta 0:17:28
epoch [30/50] batch [180/204] time 0.251 (0.254) data 0.001 (0.003) loss 0.1080 (0.5315) lr 1.0628e-03 eta 0:17:21
epoch [30/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.003) loss 0.9715 (0.5362) lr 1.0628e-03 eta 0:17:15
epoch [31/50] batch [20/204] time 0.246 (0.278) data 0.000 (0.027) loss 0.0450 (0.3703) lr 1.0000e-03 eta 0:18:48
epoch [31/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.0233 (0.4676) lr 1.0000e-03 eta 0:17:47
epoch [31/50] batch [60/204] time 0.249 (0.259) data 0.000 (0.009) loss 0.9751 (0.5045) lr 1.0000e-03 eta 0:17:22
epoch [31/50] batch [80/204] time 0.252 (0.257) data 0.000 (0.007) loss 0.0524 (0.4949) lr 1.0000e-03 eta 0:17:09
epoch [31/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.6629 (0.5412) lr 1.0000e-03 eta 0:16:58
epoch [31/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.005) loss 2.0282 (0.5319) lr 1.0000e-03 eta 0:16:50
epoch [31/50] batch [140/204] time 0.247 (0.255) data 0.000 (0.004) loss 1.4798 (0.5256) lr 1.0000e-03 eta 0:16:42
epoch [31/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.004) loss 0.0403 (0.5153) lr 1.0000e-03 eta 0:16:35
epoch [31/50] batch [180/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.3173 (0.5221) lr 1.0000e-03 eta 0:16:29
epoch [31/50] batch [200/204] time 0.246 (0.253) data 0.000 (0.003) loss 0.6785 (0.5270) lr 1.0000e-03 eta 0:16:22
epoch [32/50] batch [20/204] time 0.251 (0.276) data 0.000 (0.025) loss 0.0207 (0.3015) lr 9.3721e-04 eta 0:17:44
epoch [32/50] batch [40/204] time 0.247 (0.263) data 0.000 (0.013) loss 1.3724 (0.4629) lr 9.3721e-04 eta 0:16:50
epoch [32/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.009) loss 1.0209 (0.4445) lr 9.3721e-04 eta 0:16:28
epoch [32/50] batch [80/204] time 0.252 (0.257) data 0.000 (0.006) loss 0.2360 (0.4453) lr 9.3721e-04 eta 0:16:15
epoch [32/50] batch [100/204] time 0.245 (0.256) data 0.000 (0.005) loss 1.1526 (0.4581) lr 9.3721e-04 eta 0:16:05
epoch [32/50] batch [120/204] time 0.256 (0.255) data 0.000 (0.004) loss 1.0232 (0.4945) lr 9.3721e-04 eta 0:15:57
epoch [32/50] batch [140/204] time 0.254 (0.254) data 0.000 (0.004) loss 0.0993 (0.4987) lr 9.3721e-04 eta 0:15:50
epoch [32/50] batch [160/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1793 (0.4771) lr 9.3721e-04 eta 0:15:43
epoch [32/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0549 (0.4944) lr 9.3721e-04 eta 0:15:37
epoch [32/50] batch [200/204] time 0.253 (0.253) data 0.000 (0.003) loss 1.4333 (0.4833) lr 9.3721e-04 eta 0:15:30
epoch [33/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.025) loss 0.7814 (0.3601) lr 8.7467e-04 eta 0:16:51
epoch [33/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 1.4083 (0.4455) lr 8.7467e-04 eta 0:15:59
epoch [33/50] batch [60/204] time 0.249 (0.259) data 0.000 (0.009) loss 0.5156 (0.4910) lr 8.7467e-04 eta 0:15:36
epoch [33/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.2702 (0.5062) lr 8.7467e-04 eta 0:15:22
epoch [33/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.3129 (0.5456) lr 8.7467e-04 eta 0:15:13
epoch [33/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.4392 (0.5475) lr 8.7467e-04 eta 0:15:06
epoch [33/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.3434 (0.5562) lr 8.7467e-04 eta 0:14:59
epoch [33/50] batch [160/204] time 0.256 (0.254) data 0.000 (0.003) loss 0.0924 (0.5685) lr 8.7467e-04 eta 0:14:52
epoch [33/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0088 (0.5346) lr 8.7467e-04 eta 0:14:45
epoch [33/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.1978 (0.5288) lr 8.7467e-04 eta 0:14:39
epoch [34/50] batch [20/204] time 0.252 (0.277) data 0.000 (0.025) loss 0.3215 (0.5330) lr 8.1262e-04 eta 0:15:53
epoch [34/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.013) loss 0.4605 (0.5802) lr 8.1262e-04 eta 0:15:03
epoch [34/50] batch [60/204] time 0.244 (0.259) data 0.000 (0.009) loss 0.8469 (0.5778) lr 8.1262e-04 eta 0:14:43
epoch [34/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 1.2906 (0.5459) lr 8.1262e-04 eta 0:14:32
epoch [34/50] batch [100/204] time 0.249 (0.256) data 0.000 (0.005) loss 1.3623 (0.5633) lr 8.1262e-04 eta 0:14:22
epoch [34/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.0484 (0.5612) lr 8.1262e-04 eta 0:14:15
epoch [34/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0060 (0.5498) lr 8.1262e-04 eta 0:14:08
epoch [34/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.6748 (0.5358) lr 8.1262e-04 eta 0:14:01
epoch [34/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1922 (0.5298) lr 8.1262e-04 eta 0:13:55
epoch [34/50] batch [200/204] time 0.245 (0.254) data 0.000 (0.003) loss 0.4136 (0.5318) lr 8.1262e-04 eta 0:13:49
epoch [35/50] batch [20/204] time 0.254 (0.276) data 0.000 (0.025) loss 1.1936 (0.4463) lr 7.5131e-04 eta 0:14:55
epoch [35/50] batch [40/204] time 0.246 (0.264) data 0.000 (0.012) loss 1.1931 (0.5228) lr 7.5131e-04 eta 0:14:10
epoch [35/50] batch [60/204] time 0.253 (0.260) data 0.000 (0.008) loss 0.7652 (0.5343) lr 7.5131e-04 eta 0:13:51
epoch [35/50] batch [80/204] time 0.250 (0.258) data 0.000 (0.006) loss 1.9927 (0.5147) lr 7.5131e-04 eta 0:13:40
epoch [35/50] batch [100/204] time 0.246 (0.257) data 0.000 (0.005) loss 0.0841 (0.5143) lr 7.5131e-04 eta 0:13:31
epoch [35/50] batch [120/204] time 0.252 (0.256) data 0.000 (0.004) loss 0.0772 (0.5080) lr 7.5131e-04 eta 0:13:24
epoch [35/50] batch [140/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.0437 (0.5349) lr 7.5131e-04 eta 0:13:16
epoch [35/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.0866 (0.5414) lr 7.5131e-04 eta 0:13:10
epoch [35/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.003) loss 1.2882 (0.5431) lr 7.5131e-04 eta 0:13:04
epoch [35/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0502 (0.5426) lr 7.5131e-04 eta 0:12:57
epoch [36/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.025) loss 0.0196 (0.8875) lr 6.9098e-04 eta 0:14:00
epoch [36/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.013) loss 0.0705 (0.6812) lr 6.9098e-04 eta 0:13:16
epoch [36/50] batch [60/204] time 0.254 (0.260) data 0.000 (0.009) loss 0.1367 (0.6086) lr 6.9098e-04 eta 0:12:58
epoch [36/50] batch [80/204] time 0.249 (0.258) data 0.000 (0.006) loss 0.0415 (0.5771) lr 6.9098e-04 eta 0:12:47
epoch [36/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.2920 (0.5325) lr 6.9098e-04 eta 0:12:38
epoch [36/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.5459 (0.5384) lr 6.9098e-04 eta 0:12:31
epoch [36/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 1.8470 (0.5350) lr 6.9098e-04 eta 0:12:24
epoch [36/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.0997 (0.5376) lr 6.9098e-04 eta 0:12:17
epoch [36/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1143 (0.5347) lr 6.9098e-04 eta 0:12:11
epoch [36/50] batch [200/204] time 0.246 (0.254) data 0.000 (0.003) loss 1.0490 (0.5551) lr 6.9098e-04 eta 0:12:05
epoch [37/50] batch [20/204] time 0.253 (0.276) data 0.000 (0.025) loss 0.0118 (0.5292) lr 6.3188e-04 eta 0:13:02
epoch [37/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.013) loss 1.3696 (0.5152) lr 6.3188e-04 eta 0:12:21
epoch [37/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.008) loss 0.6686 (0.4758) lr 6.3188e-04 eta 0:12:04
epoch [37/50] batch [80/204] time 0.247 (0.257) data 0.000 (0.006) loss 0.4554 (0.4355) lr 6.3188e-04 eta 0:11:53
epoch [37/50] batch [100/204] time 0.248 (0.256) data 0.000 (0.005) loss 1.4530 (0.4513) lr 6.3188e-04 eta 0:11:44
epoch [37/50] batch [120/204] time 0.251 (0.255) data 0.000 (0.004) loss 1.8531 (0.4714) lr 6.3188e-04 eta 0:11:37
epoch [37/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.2720 (0.4884) lr 6.3188e-04 eta 0:11:30
epoch [37/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.0812 (0.4653) lr 6.3188e-04 eta 0:11:24
epoch [37/50] batch [180/204] time 0.249 (0.253) data 0.000 (0.003) loss 0.0096 (0.4841) lr 6.3188e-04 eta 0:11:18
epoch [37/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.0200 (0.4946) lr 6.3188e-04 eta 0:11:12
epoch [38/50] batch [20/204] time 0.247 (0.276) data 0.000 (0.025) loss 0.0637 (0.4592) lr 5.7422e-04 eta 0:12:05
epoch [38/50] batch [40/204] time 0.252 (0.263) data 0.000 (0.013) loss 1.3707 (0.5241) lr 5.7422e-04 eta 0:11:27
epoch [38/50] batch [60/204] time 0.247 (0.259) data 0.000 (0.008) loss 0.4741 (0.4832) lr 5.7422e-04 eta 0:11:11
epoch [38/50] batch [80/204] time 0.256 (0.257) data 0.000 (0.006) loss 0.1525 (0.4485) lr 5.7422e-04 eta 0:11:01
epoch [38/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.1396 (0.4497) lr 5.7422e-04 eta 0:10:53
epoch [38/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.7667 (0.4756) lr 5.7422e-04 eta 0:10:45
epoch [38/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.2800 (0.4669) lr 5.7422e-04 eta 0:10:39
epoch [38/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.0413 (0.4726) lr 5.7422e-04 eta 0:10:33
epoch [38/50] batch [180/204] time 0.249 (0.254) data 0.002 (0.003) loss 0.4045 (0.4677) lr 5.7422e-04 eta 0:10:27
epoch [38/50] batch [200/204] time 0.258 (0.253) data 0.000 (0.003) loss 0.2749 (0.4870) lr 5.7422e-04 eta 0:10:21
epoch [39/50] batch [20/204] time 0.254 (0.277) data 0.000 (0.026) loss 1.1772 (0.6328) lr 5.1825e-04 eta 0:11:12
epoch [39/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.013) loss 0.0570 (0.4871) lr 5.1825e-04 eta 0:10:36
epoch [39/50] batch [60/204] time 0.249 (0.260) data 0.000 (0.009) loss 0.3695 (0.5176) lr 5.1825e-04 eta 0:10:20
epoch [39/50] batch [80/204] time 0.246 (0.258) data 0.000 (0.007) loss 0.0096 (0.5038) lr 5.1825e-04 eta 0:10:10
epoch [39/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.7847 (0.4626) lr 5.1825e-04 eta 0:10:02
epoch [39/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.004) loss 0.3643 (0.4999) lr 5.1825e-04 eta 0:09:55
epoch [39/50] batch [140/204] time 0.249 (0.255) data 0.000 (0.004) loss 0.9479 (0.5014) lr 5.1825e-04 eta 0:09:48
epoch [39/50] batch [160/204] time 0.251 (0.255) data 0.000 (0.003) loss 2.2295 (0.5535) lr 5.1825e-04 eta 0:09:42
epoch [39/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.9195 (0.5542) lr 5.1825e-04 eta 0:09:36
epoch [39/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1410 (0.5331) lr 5.1825e-04 eta 0:09:30
epoch [40/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.026) loss 0.9011 (0.3325) lr 4.6417e-04 eta 0:10:15
epoch [40/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.2278 (0.4406) lr 4.6417e-04 eta 0:09:41
epoch [40/50] batch [60/204] time 0.253 (0.260) data 0.000 (0.009) loss 0.2471 (0.4632) lr 4.6417e-04 eta 0:09:27
epoch [40/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 1.3506 (0.4516) lr 4.6417e-04 eta 0:09:18
epoch [40/50] batch [100/204] time 0.251 (0.257) data 0.000 (0.006) loss 0.1060 (0.4054) lr 4.6417e-04 eta 0:09:10
epoch [40/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.4689 (0.4534) lr 4.6417e-04 eta 0:09:03
epoch [40/50] batch [140/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.0067 (0.4715) lr 4.6417e-04 eta 0:08:56
epoch [40/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.004) loss 0.0069 (0.4704) lr 4.6417e-04 eta 0:08:50
epoch [40/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.1575 (0.4639) lr 4.6417e-04 eta 0:08:44
epoch [40/50] batch [200/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.0281 (0.4578) lr 4.6417e-04 eta 0:08:38
epoch [41/50] batch [20/204] time 0.248 (0.277) data 0.000 (0.026) loss 0.2307 (0.5959) lr 4.1221e-04 eta 0:09:19
epoch [41/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.1830 (0.4917) lr 4.1221e-04 eta 0:08:48
epoch [41/50] batch [60/204] time 0.250 (0.260) data 0.000 (0.009) loss 0.0155 (0.4907) lr 4.1221e-04 eta 0:08:34
epoch [41/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.007) loss 2.0069 (0.4681) lr 4.1221e-04 eta 0:08:25
epoch [41/50] batch [100/204] time 0.251 (0.256) data 0.000 (0.005) loss 1.3269 (0.4730) lr 4.1221e-04 eta 0:08:17
epoch [41/50] batch [120/204] time 0.249 (0.255) data 0.000 (0.004) loss 0.0205 (0.4783) lr 4.1221e-04 eta 0:08:10
epoch [41/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0044 (0.4760) lr 4.1221e-04 eta 0:08:04
epoch [41/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.3887 (0.4966) lr 4.1221e-04 eta 0:07:58
epoch [41/50] batch [180/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0220 (0.4909) lr 4.1221e-04 eta 0:07:52
epoch [41/50] batch [200/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.0097 (0.4713) lr 4.1221e-04 eta 0:07:46
epoch [42/50] batch [20/204] time 0.248 (0.277) data 0.000 (0.026) loss 1.6080 (0.6015) lr 3.6258e-04 eta 0:08:23
epoch [42/50] batch [40/204] time 0.246 (0.264) data 0.000 (0.013) loss 0.2032 (0.4769) lr 3.6258e-04 eta 0:07:54
epoch [42/50] batch [60/204] time 0.254 (0.260) data 0.000 (0.009) loss 0.2335 (0.4485) lr 3.6258e-04 eta 0:07:41
epoch [42/50] batch [80/204] time 0.249 (0.258) data 0.000 (0.007) loss 0.1684 (0.4508) lr 3.6258e-04 eta 0:07:32
epoch [42/50] batch [100/204] time 0.248 (0.256) data 0.000 (0.005) loss 0.5316 (0.4571) lr 3.6258e-04 eta 0:07:25
epoch [42/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.0537 (0.4421) lr 3.6258e-04 eta 0:07:18
epoch [42/50] batch [140/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.9969 (0.4779) lr 3.6258e-04 eta 0:07:12
epoch [42/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0903 (0.4890) lr 3.6258e-04 eta 0:07:06
epoch [42/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.1448 (0.4871) lr 3.6258e-04 eta 0:07:00
epoch [42/50] batch [200/204] time 0.256 (0.254) data 0.000 (0.003) loss 0.0888 (0.4786) lr 3.6258e-04 eta 0:06:55
epoch [43/50] batch [20/204] time 0.254 (0.276) data 0.000 (0.025) loss 0.1530 (0.4130) lr 3.1545e-04 eta 0:07:24
epoch [43/50] batch [40/204] time 0.247 (0.264) data 0.000 (0.012) loss 2.0327 (0.4629) lr 3.1545e-04 eta 0:06:59
epoch [43/50] batch [60/204] time 0.255 (0.260) data 0.000 (0.008) loss 1.0718 (0.4166) lr 3.1545e-04 eta 0:06:48
epoch [43/50] batch [80/204] time 0.246 (0.258) data 0.000 (0.006) loss 0.1492 (0.4422) lr 3.1545e-04 eta 0:06:39
epoch [43/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.7017 (0.4461) lr 3.1545e-04 eta 0:06:32
epoch [43/50] batch [120/204] time 0.248 (0.256) data 0.000 (0.004) loss 0.0397 (0.4570) lr 3.1545e-04 eta 0:06:26
epoch [43/50] batch [140/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.0723 (0.4341) lr 3.1545e-04 eta 0:06:20
epoch [43/50] batch [160/204] time 0.247 (0.255) data 0.000 (0.003) loss 0.0302 (0.4395) lr 3.1545e-04 eta 0:06:14
epoch [43/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.1027 (0.4299) lr 3.1545e-04 eta 0:06:09
epoch [43/50] batch [200/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1611 (0.4265) lr 3.1545e-04 eta 0:06:03
epoch [44/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.026) loss 1.4047 (0.3954) lr 2.7103e-04 eta 0:06:30
epoch [44/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.0387 (0.3740) lr 2.7103e-04 eta 0:06:06
epoch [44/50] batch [60/204] time 0.247 (0.260) data 0.000 (0.009) loss 0.9495 (0.4245) lr 2.7103e-04 eta 0:05:55
epoch [44/50] batch [80/204] time 0.250 (0.257) data 0.000 (0.007) loss 1.4795 (0.4520) lr 2.7103e-04 eta 0:05:47
epoch [44/50] batch [100/204] time 0.249 (0.256) data 0.000 (0.005) loss 0.5979 (0.4528) lr 2.7103e-04 eta 0:05:40
epoch [44/50] batch [120/204] time 0.246 (0.255) data 0.000 (0.005) loss 1.6644 (0.4841) lr 2.7103e-04 eta 0:05:33
epoch [44/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.0203 (0.5128) lr 2.7103e-04 eta 0:05:28
epoch [44/50] batch [160/204] time 0.249 (0.254) data 0.000 (0.003) loss 1.6770 (0.5527) lr 2.7103e-04 eta 0:05:22
epoch [44/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0164 (0.5286) lr 2.7103e-04 eta 0:05:16
epoch [44/50] batch [200/204] time 0.259 (0.254) data 0.000 (0.003) loss 0.0242 (0.5063) lr 2.7103e-04 eta 0:05:11
epoch [45/50] batch [20/204] time 0.254 (0.277) data 0.000 (0.026) loss 0.2072 (0.3330) lr 2.2949e-04 eta 0:05:34
epoch [45/50] batch [40/204] time 0.255 (0.265) data 0.000 (0.013) loss 1.6648 (0.4128) lr 2.2949e-04 eta 0:05:13
epoch [45/50] batch [60/204] time 0.254 (0.260) data 0.000 (0.009) loss 0.7247 (0.4644) lr 2.2949e-04 eta 0:05:02
epoch [45/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.2556 (0.4797) lr 2.2949e-04 eta 0:04:55
epoch [45/50] batch [100/204] time 0.247 (0.257) data 0.000 (0.005) loss 1.5193 (0.4840) lr 2.2949e-04 eta 0:04:48
epoch [45/50] batch [120/204] time 0.248 (0.256) data 0.000 (0.004) loss 0.1911 (0.4829) lr 2.2949e-04 eta 0:04:42
epoch [45/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.0601 (0.4800) lr 2.2949e-04 eta 0:04:36
epoch [45/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.5094 (0.4665) lr 2.2949e-04 eta 0:04:31
epoch [45/50] batch [180/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.0615 (0.4794) lr 2.2949e-04 eta 0:04:25
epoch [45/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0087 (0.4814) lr 2.2949e-04 eta 0:04:20
epoch [46/50] batch [20/204] time 0.253 (0.277) data 0.000 (0.025) loss 0.1651 (0.2996) lr 1.9098e-04 eta 0:04:36
epoch [46/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.7459 (0.4511) lr 1.9098e-04 eta 0:04:18
epoch [46/50] batch [60/204] time 0.251 (0.260) data 0.000 (0.009) loss 1.9254 (0.5190) lr 1.9098e-04 eta 0:04:09
epoch [46/50] batch [80/204] time 0.253 (0.258) data 0.000 (0.007) loss 0.2367 (0.5102) lr 1.9098e-04 eta 0:04:02
epoch [46/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.005) loss 2.7787 (0.5371) lr 1.9098e-04 eta 0:03:55
epoch [46/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.0503 (0.5185) lr 1.9098e-04 eta 0:03:49
epoch [46/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.0424 (0.5346) lr 1.9098e-04 eta 0:03:44
epoch [46/50] batch [160/204] time 0.245 (0.254) data 0.000 (0.003) loss 0.4315 (0.5315) lr 1.9098e-04 eta 0:03:38
epoch [46/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 1.4799 (0.5048) lr 1.9098e-04 eta 0:03:33
epoch [46/50] batch [200/204] time 0.249 (0.254) data 0.000 (0.003) loss 0.0566 (0.4926) lr 1.9098e-04 eta 0:03:28
epoch [47/50] batch [20/204] time 0.253 (0.276) data 0.000 (0.025) loss 0.0271 (0.4330) lr 1.5567e-04 eta 0:03:39
epoch [47/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.0482 (0.4393) lr 1.5567e-04 eta 0:03:24
epoch [47/50] batch [60/204] time 0.257 (0.259) data 0.000 (0.008) loss 0.3116 (0.4348) lr 1.5567e-04 eta 0:03:16
epoch [47/50] batch [80/204] time 0.252 (0.257) data 0.000 (0.006) loss 0.0603 (0.4814) lr 1.5567e-04 eta 0:03:09
epoch [47/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.005) loss 0.6626 (0.4904) lr 1.5567e-04 eta 0:03:03
epoch [47/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.0889 (0.5130) lr 1.5567e-04 eta 0:02:57
epoch [47/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.0422 (0.5117) lr 1.5567e-04 eta 0:02:52
epoch [47/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.8944 (0.5156) lr 1.5567e-04 eta 0:02:46
epoch [47/50] batch [180/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.9944 (0.5285) lr 1.5567e-04 eta 0:02:41
epoch [47/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.7085 (0.5193) lr 1.5567e-04 eta 0:02:36
epoch [48/50] batch [20/204] time 0.251 (0.277) data 0.000 (0.026) loss 0.2001 (0.7027) lr 1.2369e-04 eta 0:02:43
epoch [48/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.013) loss 0.0934 (0.7557) lr 1.2369e-04 eta 0:02:30
epoch [48/50] batch [60/204] time 0.254 (0.259) data 0.000 (0.009) loss 0.0717 (0.6811) lr 1.2369e-04 eta 0:02:23
epoch [48/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.0960 (0.6127) lr 1.2369e-04 eta 0:02:16
epoch [48/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.2351 (0.6025) lr 1.2369e-04 eta 0:02:11
epoch [48/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.1829 (0.5524) lr 1.2369e-04 eta 0:02:05
epoch [48/50] batch [140/204] time 0.251 (0.255) data 0.000 (0.004) loss 1.1765 (0.5443) lr 1.2369e-04 eta 0:02:00
epoch [48/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.5425 (0.5113) lr 1.2369e-04 eta 0:01:55
epoch [48/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.3412 (0.5073) lr 1.2369e-04 eta 0:01:49
epoch [48/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.5757 (0.4934) lr 1.2369e-04 eta 0:01:44
epoch [49/50] batch [20/204] time 0.252 (0.277) data 0.000 (0.026) loss 0.2802 (0.3288) lr 9.5173e-05 eta 0:01:47
epoch [49/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.013) loss 0.4622 (0.4617) lr 9.5173e-05 eta 0:01:37
epoch [49/50] batch [60/204] time 0.254 (0.260) data 0.000 (0.009) loss 0.0052 (0.4496) lr 9.5173e-05 eta 0:01:30
epoch [49/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.007) loss 0.7511 (0.5441) lr 9.5173e-05 eta 0:01:24
epoch [49/50] batch [100/204] time 0.254 (0.256) data 0.000 (0.005) loss 0.0122 (0.5294) lr 9.5173e-05 eta 0:01:18
epoch [49/50] batch [120/204] time 0.248 (0.256) data 0.000 (0.004) loss 0.1164 (0.5351) lr 9.5173e-05 eta 0:01:13
epoch [49/50] batch [140/204] time 0.248 (0.255) data 0.000 (0.004) loss 1.7727 (0.5300) lr 9.5173e-05 eta 0:01:08
epoch [49/50] batch [160/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.1504 (0.5243) lr 9.5173e-05 eta 0:01:03
epoch [49/50] batch [180/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.4218 (0.5212) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.1984 (0.5105) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.253 (0.276) data 0.000 (0.025) loss 0.3098 (0.4944) lr 7.0224e-05 eta 0:00:50
epoch [50/50] batch [40/204] time 0.253 (0.264) data 0.000 (0.013) loss 0.0524 (0.4446) lr 7.0224e-05 eta 0:00:43
epoch [50/50] batch [60/204] time 0.255 (0.260) data 0.000 (0.009) loss 0.2647 (0.4225) lr 7.0224e-05 eta 0:00:37
epoch [50/50] batch [80/204] time 0.248 (0.258) data 0.000 (0.007) loss 0.0256 (0.4409) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.7719 (0.4837) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.249 (0.256) data 0.000 (0.004) loss 0.0532 (0.5181) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.253 (0.256) data 0.000 (0.004) loss 0.2147 (0.5077) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.3042 (0.5127) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.1501 (0.4948) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0067 (0.4867) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/food101/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: 15,300
* correct: 14,138
* accuracy: 92.41%
* error: 7.59%
* macro_f1: 92.40%
Elapsed: 0:44:33
