***************
** 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/seed2
resume: 
root: /mnt/hdd/DATA
seed: 2
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/seed2
RESUME: 
SEED: 2
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_2.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/seed2/tensorboard)
epoch [1/50] batch [20/204] time 0.248 (0.381) data 0.000 (0.028) loss 0.9979 (1.4246) lr 1.0000e-05 eta 1:04:36
epoch [1/50] batch [40/204] time 0.252 (0.315) data 0.000 (0.014) loss 1.0148 (1.2751) lr 1.0000e-05 eta 0:53:19
epoch [1/50] batch [60/204] time 0.245 (0.293) data 0.000 (0.010) loss 1.4354 (1.1623) lr 1.0000e-05 eta 0:49:32
epoch [1/50] batch [80/204] time 0.252 (0.282) data 0.000 (0.007) loss 2.5722 (1.0865) lr 1.0000e-05 eta 0:47:36
epoch [1/50] batch [100/204] time 0.251 (0.276) data 0.000 (0.006) loss 0.7381 (1.0543) lr 1.0000e-05 eta 0:46:25
epoch [1/50] batch [120/204] time 0.249 (0.271) data 0.000 (0.005) loss 0.7571 (1.0338) lr 1.0000e-05 eta 0:45:36
epoch [1/50] batch [140/204] time 0.253 (0.268) data 0.000 (0.004) loss 1.2256 (1.0363) lr 1.0000e-05 eta 0:44:59
epoch [1/50] batch [160/204] time 0.251 (0.266) data 0.000 (0.004) loss 0.4482 (1.0324) lr 1.0000e-05 eta 0:44:30
epoch [1/50] batch [180/204] time 0.246 (0.264) data 0.000 (0.003) loss 1.8294 (1.0204) lr 1.0000e-05 eta 0:44:06
epoch [1/50] batch [200/204] time 0.251 (0.263) data 0.000 (0.003) loss 1.2030 (1.0015) lr 1.0000e-05 eta 0:43:47
epoch [2/50] batch [20/204] time 0.247 (0.270) data 0.000 (0.020) loss 0.4469 (0.8851) lr 1.0000e-05 eta 0:44:54
epoch [2/50] batch [40/204] time 0.245 (0.261) data 0.000 (0.010) loss 0.1967 (0.8826) lr 1.0000e-05 eta 0:43:18
epoch [2/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.007) loss 0.1483 (0.9179) lr 1.0000e-05 eta 0:42:38
epoch [2/50] batch [80/204] time 0.257 (0.256) data 0.000 (0.005) loss 0.1350 (0.9034) lr 1.0000e-05 eta 0:42:17
epoch [2/50] batch [100/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.0124 (0.9085) lr 1.0000e-05 eta 0:42:01
epoch [2/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.7288 (0.9015) lr 1.0000e-05 eta 0:41:51
epoch [2/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1138 (0.8851) lr 1.0000e-05 eta 0:41:41
epoch [2/50] batch [160/204] time 0.251 (0.253) data 0.000 (0.003) loss 1.4905 (0.8978) lr 1.0000e-05 eta 0:41:32
epoch [2/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.6894 (0.9016) lr 1.0000e-05 eta 0:41:25
epoch [2/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.6122 (0.9058) lr 1.0000e-05 eta 0:41:17
epoch [3/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.019) loss 0.6612 (0.7907) lr 1.0000e-05 eta 0:44:00
epoch [3/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.8612 (0.7344) lr 1.0000e-05 eta 0:42:25
epoch [3/50] batch [60/204] time 0.253 (0.257) data 0.000 (0.007) loss 1.6494 (0.7486) lr 1.0000e-05 eta 0:41:45
epoch [3/50] batch [80/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.3051 (0.7865) lr 1.0000e-05 eta 0:41:23
epoch [3/50] batch [100/204] time 0.259 (0.255) data 0.000 (0.004) loss 0.8538 (0.7982) lr 1.0000e-05 eta 0:41:10
epoch [3/50] batch [120/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0745 (0.7883) lr 1.0000e-05 eta 0:41:01
epoch [3/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.4631 (0.8109) lr 1.0000e-05 eta 0:40:50
epoch [3/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.9259 (0.8186) lr 1.0000e-05 eta 0:40:42
epoch [3/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 1.7972 (0.8158) lr 1.0000e-05 eta 0:40:35
epoch [3/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.2218 (0.8235) lr 1.0000e-05 eta 0:40:27
epoch [4/50] batch [20/204] time 0.247 (0.271) data 0.000 (0.020) loss 0.1221 (0.7172) lr 1.0000e-05 eta 0:43:08
epoch [4/50] batch [40/204] time 0.252 (0.261) data 0.000 (0.010) loss 0.2215 (0.8233) lr 1.0000e-05 eta 0:41:30
epoch [4/50] batch [60/204] time 0.248 (0.258) data 0.000 (0.007) loss 0.0670 (0.7793) lr 1.0000e-05 eta 0:40:53
epoch [4/50] batch [80/204] time 0.249 (0.256) data 0.000 (0.005) loss 1.5718 (0.8042) lr 1.0000e-05 eta 0:40:34
epoch [4/50] batch [100/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.7793 (0.8208) lr 1.0000e-05 eta 0:40:20
epoch [4/50] batch [120/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0497 (0.8309) lr 1.0000e-05 eta 0:40:09
epoch [4/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.7580 (0.8231) lr 1.0000e-05 eta 0:40:00
epoch [4/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 1.0165 (0.8392) lr 1.0000e-05 eta 0:39:51
epoch [4/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 1.0653 (0.8388) lr 1.0000e-05 eta 0:39:43
epoch [4/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 2.9719 (0.8433) lr 1.0000e-05 eta 0:39:36
epoch [5/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.019) loss 2.1942 (0.9118) lr 1.0000e-05 eta 0:42:09
epoch [5/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 1.4859 (0.8534) lr 1.0000e-05 eta 0:40:36
epoch [5/50] batch [60/204] time 0.247 (0.257) data 0.000 (0.006) loss 0.7428 (0.8317) lr 1.0000e-05 eta 0:40:00
epoch [5/50] batch [80/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.1654 (0.8664) lr 1.0000e-05 eta 0:39:41
epoch [5/50] batch [100/204] time 0.251 (0.255) data 0.000 (0.004) loss 1.3576 (0.8223) lr 1.0000e-05 eta 0:39:26
epoch [5/50] batch [120/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.7666 (0.8318) lr 1.0000e-05 eta 0:39:15
epoch [5/50] batch [140/204] time 0.250 (0.254) data 0.000 (0.003) loss 1.6481 (0.8463) lr 1.0000e-05 eta 0:39:07
epoch [5/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.2301 (0.8318) lr 1.0000e-05 eta 0:38:58
epoch [5/50] batch [180/204] time 0.245 (0.253) data 0.000 (0.002) loss 0.1378 (0.8498) lr 1.0000e-05 eta 0:38:51
epoch [5/50] batch [200/204] time 0.253 (0.253) data 0.000 (0.002) loss 1.2380 (0.8310) lr 1.0000e-05 eta 0:38:43
epoch [6/50] batch [20/204] time 0.259 (0.270) data 0.000 (0.019) loss 0.9226 (0.9582) lr 2.0000e-03 eta 0:41:12
epoch [6/50] batch [40/204] time 0.245 (0.260) data 0.000 (0.009) loss 0.6359 (0.9190) lr 2.0000e-03 eta 0:39:38
epoch [6/50] batch [60/204] time 0.251 (0.257) data 0.000 (0.006) loss 1.0013 (0.8361) lr 2.0000e-03 eta 0:39:06
epoch [6/50] batch [80/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.1049 (0.8554) lr 2.0000e-03 eta 0:38:47
epoch [6/50] batch [100/204] time 0.262 (0.255) data 0.000 (0.004) loss 0.8065 (0.8302) lr 2.0000e-03 eta 0:38:34
epoch [6/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.8206 (0.8304) lr 2.0000e-03 eta 0:38:23
epoch [6/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.5982 (0.7967) lr 2.0000e-03 eta 0:38:14
epoch [6/50] batch [160/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.0931 (0.7960) lr 2.0000e-03 eta 0:38:06
epoch [6/50] batch [180/204] time 0.254 (0.253) data 0.000 (0.002) loss 0.3717 (0.8120) lr 2.0000e-03 eta 0:37:58
epoch [6/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.4964 (0.7773) lr 2.0000e-03 eta 0:37:50
epoch [7/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.019) loss 0.8431 (0.8151) lr 1.9980e-03 eta 0:40:25
epoch [7/50] batch [40/204] time 0.248 (0.261) data 0.000 (0.009) loss 1.0291 (0.7295) lr 1.9980e-03 eta 0:38:52
epoch [7/50] batch [60/204] time 0.248 (0.258) data 0.000 (0.006) loss 0.2637 (0.7803) lr 1.9980e-03 eta 0:38:17
epoch [7/50] batch [80/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.5373 (0.7731) lr 1.9980e-03 eta 0:37:58
epoch [7/50] batch [100/204] time 0.247 (0.255) data 0.000 (0.004) loss 0.6285 (0.7547) lr 1.9980e-03 eta 0:37:43
epoch [7/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.8839 (0.7068) lr 1.9980e-03 eta 0:37:33
epoch [7/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.3815 (0.7047) lr 1.9980e-03 eta 0:37:24
epoch [7/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.002) loss 0.0093 (0.7036) lr 1.9980e-03 eta 0:37:16
epoch [7/50] batch [180/204] time 0.254 (0.253) data 0.000 (0.002) loss 0.2237 (0.7150) lr 1.9980e-03 eta 0:37:09
epoch [7/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.002) loss 0.0864 (0.7191) lr 1.9980e-03 eta 0:37:01
epoch [8/50] batch [20/204] time 0.255 (0.271) data 0.000 (0.019) loss 0.3345 (0.7045) lr 1.9921e-03 eta 0:39:28
epoch [8/50] batch [40/204] time 0.254 (0.261) data 0.000 (0.009) loss 1.1712 (0.7803) lr 1.9921e-03 eta 0:38:00
epoch [8/50] batch [60/204] time 0.247 (0.258) data 0.000 (0.006) loss 0.7659 (0.7711) lr 1.9921e-03 eta 0:37:26
epoch [8/50] batch [80/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.2513 (0.7262) lr 1.9921e-03 eta 0:37:08
epoch [8/50] batch [100/204] time 0.257 (0.255) data 0.000 (0.004) loss 1.1695 (0.7205) lr 1.9921e-03 eta 0:36:54
epoch [8/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.6623 (0.6894) lr 1.9921e-03 eta 0:36:43
epoch [8/50] batch [140/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0597 (0.6974) lr 1.9921e-03 eta 0:36:33
epoch [8/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.0489 (0.7201) lr 1.9921e-03 eta 0:36:25
epoch [8/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.2563 (0.7171) lr 1.9921e-03 eta 0:36:18
epoch [8/50] batch [200/204] time 0.256 (0.254) data 0.000 (0.002) loss 0.0957 (0.6920) lr 1.9921e-03 eta 0:36:13
epoch [9/50] batch [20/204] time 0.248 (0.273) data 0.000 (0.019) loss 0.1223 (0.6805) lr 1.9823e-03 eta 0:38:55
epoch [9/50] batch [40/204] time 0.255 (0.264) data 0.002 (0.010) loss 0.3084 (0.6809) lr 1.9823e-03 eta 0:37:28
epoch [9/50] batch [60/204] time 0.256 (0.260) data 0.000 (0.007) loss 0.5489 (0.5751) lr 1.9823e-03 eta 0:36:55
epoch [9/50] batch [80/204] time 0.253 (0.258) data 0.000 (0.005) loss 0.4912 (0.6077) lr 1.9823e-03 eta 0:36:31
epoch [9/50] batch [100/204] time 0.249 (0.257) data 0.000 (0.004) loss 2.5146 (0.6342) lr 1.9823e-03 eta 0:36:14
epoch [9/50] batch [120/204] time 0.255 (0.256) data 0.000 (0.003) loss 0.0412 (0.6295) lr 1.9823e-03 eta 0:36:02
epoch [9/50] batch [140/204] time 0.253 (0.256) data 0.000 (0.003) loss 0.6173 (0.6301) lr 1.9823e-03 eta 0:35:55
epoch [9/50] batch [160/204] time 0.249 (0.255) data 0.000 (0.003) loss 0.2831 (0.6452) lr 1.9823e-03 eta 0:35:47
epoch [9/50] batch [180/204] time 0.252 (0.255) data 0.000 (0.002) loss 0.3912 (0.6615) lr 1.9823e-03 eta 0:35:40
epoch [9/50] batch [200/204] time 0.253 (0.255) data 0.000 (0.002) loss 2.4583 (0.6423) lr 1.9823e-03 eta 0:35:32
epoch [10/50] batch [20/204] time 0.254 (0.271) data 0.000 (0.020) loss 1.8902 (0.8684) lr 1.9686e-03 eta 0:37:42
epoch [10/50] batch [40/204] time 0.249 (0.262) data 0.001 (0.010) loss 0.0192 (0.6563) lr 1.9686e-03 eta 0:36:17
epoch [10/50] batch [60/204] time 0.250 (0.259) data 0.000 (0.007) loss 1.9176 (0.7500) lr 1.9686e-03 eta 0:35:47
epoch [10/50] batch [80/204] time 0.249 (0.257) data 0.000 (0.005) loss 0.2597 (0.7236) lr 1.9686e-03 eta 0:35:29
epoch [10/50] batch [100/204] time 0.255 (0.256) data 0.000 (0.004) loss 0.5807 (0.7218) lr 1.9686e-03 eta 0:35:15
epoch [10/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.1416 (0.6903) lr 1.9686e-03 eta 0:35:04
epoch [10/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.7827 (0.6625) lr 1.9686e-03 eta 0:34:55
epoch [10/50] batch [160/204] time 0.256 (0.254) data 0.000 (0.003) loss 0.2912 (0.6798) lr 1.9686e-03 eta 0:34:47
epoch [10/50] batch [180/204] time 0.252 (0.254) data 0.000 (0.002) loss 0.0145 (0.6602) lr 1.9686e-03 eta 0:34:40
epoch [10/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.002) loss 1.1807 (0.6582) lr 1.9686e-03 eta 0:34:32
epoch [11/50] batch [20/204] time 0.252 (0.271) data 0.000 (0.019) loss 0.6075 (0.6572) lr 1.9511e-03 eta 0:36:42
epoch [11/50] batch [40/204] time 0.257 (0.262) data 0.000 (0.010) loss 0.2750 (0.7048) lr 1.9511e-03 eta 0:35:26
epoch [11/50] batch [60/204] time 0.250 (0.259) data 0.000 (0.007) loss 0.0328 (0.6303) lr 1.9511e-03 eta 0:34:57
epoch [11/50] batch [80/204] time 0.247 (0.257) data 0.000 (0.005) loss 1.2096 (0.6087) lr 1.9511e-03 eta 0:34:37
epoch [11/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.004) loss 0.3079 (0.5801) lr 1.9511e-03 eta 0:34:23
epoch [11/50] batch [120/204] time 0.266 (0.255) data 0.000 (0.003) loss 2.3593 (0.6103) lr 1.9511e-03 eta 0:34:12
epoch [11/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.1141 (0.6042) lr 1.9511e-03 eta 0:34:03
epoch [11/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1114 (0.6011) lr 1.9511e-03 eta 0:33:54
epoch [11/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.002) loss 0.1020 (0.6029) lr 1.9511e-03 eta 0:33:47
epoch [11/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.002) loss 0.0049 (0.5781) lr 1.9511e-03 eta 0:33:40
epoch [12/50] batch [20/204] time 0.252 (0.270) data 0.000 (0.019) loss 1.7594 (0.5558) lr 1.9298e-03 eta 0:35:46
epoch [12/50] batch [40/204] time 0.255 (0.261) data 0.000 (0.010) loss 0.5590 (0.6334) lr 1.9298e-03 eta 0:34:27
epoch [12/50] batch [60/204] time 0.248 (0.259) data 0.000 (0.006) loss 0.0202 (0.6168) lr 1.9298e-03 eta 0:34:03
epoch [12/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.005) loss 0.4901 (0.6241) lr 1.9298e-03 eta 0:33:48
epoch [12/50] batch [100/204] time 0.251 (0.257) data 0.000 (0.004) loss 0.9930 (0.6097) lr 1.9298e-03 eta 0:33:35
epoch [12/50] batch [120/204] time 0.255 (0.256) data 0.000 (0.003) loss 1.3243 (0.6079) lr 1.9298e-03 eta 0:33:27
epoch [12/50] batch [140/204] time 0.255 (0.256) data 0.000 (0.003) loss 0.2614 (0.5974) lr 1.9298e-03 eta 0:33:18
epoch [12/50] batch [160/204] time 0.249 (0.255) data 0.000 (0.003) loss 0.1012 (0.6193) lr 1.9298e-03 eta 0:33:10
epoch [12/50] batch [180/204] time 0.251 (0.255) data 0.000 (0.002) loss 0.8607 (0.6140) lr 1.9298e-03 eta 0:33:05
epoch [12/50] batch [200/204] time 0.251 (0.255) data 0.000 (0.002) loss 1.1116 (0.5987) lr 1.9298e-03 eta 0:32:57
epoch [13/50] batch [20/204] time 0.254 (0.272) data 0.000 (0.021) loss 0.3129 (0.6185) lr 1.9048e-03 eta 0:35:06
epoch [13/50] batch [40/204] time 0.251 (0.262) data 0.000 (0.011) loss 0.7481 (0.6226) lr 1.9048e-03 eta 0:33:42
epoch [13/50] batch [60/204] time 0.244 (0.259) data 0.000 (0.007) loss 0.9348 (0.6081) lr 1.9048e-03 eta 0:33:12
epoch [13/50] batch [80/204] time 0.249 (0.257) data 0.000 (0.006) loss 0.0765 (0.6146) lr 1.9048e-03 eta 0:32:51
epoch [13/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.3518 (0.5630) lr 1.9048e-03 eta 0:32:36
epoch [13/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 1.2462 (0.5744) lr 1.9048e-03 eta 0:32:24
epoch [13/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.6196 (0.5941) lr 1.9048e-03 eta 0:32:16
epoch [13/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0639 (0.5939) lr 1.9048e-03 eta 0:32:07
epoch [13/50] batch [180/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.1739 (0.5661) lr 1.9048e-03 eta 0:31:59
epoch [13/50] batch [200/204] time 0.251 (0.253) data 0.000 (0.002) loss 0.0600 (0.5844) lr 1.9048e-03 eta 0:31:51
epoch [14/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.020) loss 0.0202 (0.5120) lr 1.8763e-03 eta 0:33:52
epoch [14/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.010) loss 0.5136 (0.4882) lr 1.8763e-03 eta 0:32:31
epoch [14/50] batch [60/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.0504 (0.4721) lr 1.8763e-03 eta 0:32:01
epoch [14/50] batch [80/204] time 0.251 (0.255) data 0.000 (0.005) loss 1.4551 (0.5120) lr 1.8763e-03 eta 0:31:44
epoch [14/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.004) loss 0.0693 (0.5606) lr 1.8763e-03 eta 0:31:31
epoch [14/50] batch [120/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.6306 (0.5427) lr 1.8763e-03 eta 0:31:22
epoch [14/50] batch [140/204] time 0.247 (0.253) data 0.000 (0.003) loss 0.3420 (0.5598) lr 1.8763e-03 eta 0:31:13
epoch [14/50] batch [160/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.2787 (0.5720) lr 1.8763e-03 eta 0:31:06
epoch [14/50] batch [180/204] time 0.250 (0.252) data 0.000 (0.002) loss 1.5281 (0.5866) lr 1.8763e-03 eta 0:30:59
epoch [14/50] batch [200/204] time 0.251 (0.252) data 0.000 (0.002) loss 0.5967 (0.5960) lr 1.8763e-03 eta 0:30:52
epoch [15/50] batch [20/204] time 0.247 (0.269) data 0.000 (0.019) loss 0.3704 (0.8920) lr 1.8443e-03 eta 0:32:53
epoch [15/50] batch [40/204] time 0.248 (0.260) data 0.000 (0.010) loss 0.5517 (0.9414) lr 1.8443e-03 eta 0:31:39
epoch [15/50] batch [60/204] time 0.247 (0.257) data 0.001 (0.006) loss 0.0855 (0.8340) lr 1.8443e-03 eta 0:31:12
epoch [15/50] batch [80/204] time 0.251 (0.256) data 0.000 (0.005) loss 1.4413 (0.7819) lr 1.8443e-03 eta 0:30:57
epoch [15/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0414 (0.7491) lr 1.8443e-03 eta 0:30:46
epoch [15/50] batch [120/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.4053 (0.7272) lr 1.8443e-03 eta 0:30:36
epoch [15/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1094 (0.6751) lr 1.8443e-03 eta 0:30:28
epoch [15/50] batch [160/204] time 0.250 (0.253) data 0.000 (0.003) loss 1.2868 (0.6426) lr 1.8443e-03 eta 0:30:20
epoch [15/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.002) loss 0.3054 (0.6451) lr 1.8443e-03 eta 0:30:13
epoch [15/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.002) loss 2.2799 (0.6442) lr 1.8443e-03 eta 0:30:05
epoch [16/50] batch [20/204] time 0.246 (0.269) data 0.000 (0.019) loss 0.4860 (0.5591) lr 1.8090e-03 eta 0:31:58
epoch [16/50] batch [40/204] time 0.248 (0.260) data 0.000 (0.010) loss 0.4207 (0.5061) lr 1.8090e-03 eta 0:30:49
epoch [16/50] batch [60/204] time 0.251 (0.257) data 0.000 (0.006) loss 1.5167 (0.4710) lr 1.8090e-03 eta 0:30:20
epoch [16/50] batch [80/204] time 0.248 (0.256) data 0.000 (0.005) loss 0.5608 (0.5039) lr 1.8090e-03 eta 0:30:04
epoch [16/50] batch [100/204] time 0.248 (0.255) data 0.000 (0.004) loss 2.0208 (0.5452) lr 1.8090e-03 eta 0:29:52
epoch [16/50] batch [120/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1535 (0.5945) lr 1.8090e-03 eta 0:29:43
epoch [16/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.3949 (0.6000) lr 1.8090e-03 eta 0:29:36
epoch [16/50] batch [160/204] time 0.254 (0.253) data 0.000 (0.003) loss 0.2809 (0.5786) lr 1.8090e-03 eta 0:29:28
epoch [16/50] batch [180/204] time 0.245 (0.253) data 0.000 (0.002) loss 2.2048 (0.6157) lr 1.8090e-03 eta 0:29:21
epoch [16/50] batch [200/204] time 0.254 (0.253) data 0.000 (0.002) loss 1.8331 (0.6002) lr 1.8090e-03 eta 0:29:16
epoch [17/50] batch [20/204] time 0.251 (0.274) data 0.000 (0.019) loss 0.0222 (0.5943) lr 1.7705e-03 eta 0:31:35
epoch [17/50] batch [40/204] time 0.250 (0.263) data 0.000 (0.010) loss 0.1151 (0.4961) lr 1.7705e-03 eta 0:30:11
epoch [17/50] batch [60/204] time 0.247 (0.259) data 0.000 (0.006) loss 0.5027 (0.5809) lr 1.7705e-03 eta 0:29:41
epoch [17/50] batch [80/204] time 0.249 (0.257) data 0.000 (0.005) loss 0.2949 (0.5429) lr 1.7705e-03 eta 0:29:24
epoch [17/50] batch [100/204] time 0.248 (0.256) data 0.000 (0.004) loss 0.1509 (0.5676) lr 1.7705e-03 eta 0:29:10
epoch [17/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.003) loss 0.4952 (0.5588) lr 1.7705e-03 eta 0:29:06
epoch [17/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.2837 (0.5416) lr 1.7705e-03 eta 0:28:55
epoch [17/50] batch [160/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.1828 (0.5370) lr 1.7705e-03 eta 0:28:48
epoch [17/50] batch [180/204] time 0.248 (0.255) data 0.000 (0.002) loss 0.0560 (0.5255) lr 1.7705e-03 eta 0:28:40
epoch [17/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.002) loss 0.3383 (0.5397) lr 1.7705e-03 eta 0:28:33
epoch [18/50] batch [20/204] time 0.254 (0.271) data 0.000 (0.019) loss 2.5990 (0.8250) lr 1.7290e-03 eta 0:30:16
epoch [18/50] batch [40/204] time 0.254 (0.261) data 0.000 (0.009) loss 1.5045 (0.7201) lr 1.7290e-03 eta 0:29:04
epoch [18/50] batch [60/204] time 0.252 (0.258) data 0.000 (0.006) loss 0.1129 (0.7011) lr 1.7290e-03 eta 0:28:40
epoch [18/50] batch [80/204] time 0.246 (0.256) data 0.000 (0.005) loss 0.0295 (0.6399) lr 1.7290e-03 eta 0:28:26
epoch [18/50] batch [100/204] time 0.259 (0.256) data 0.000 (0.004) loss 0.0840 (0.6116) lr 1.7290e-03 eta 0:28:14
epoch [18/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.0182 (0.6309) lr 1.7290e-03 eta 0:28:04
epoch [18/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.1564 (0.6254) lr 1.7290e-03 eta 0:27:56
epoch [18/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.0609 (0.6181) lr 1.7290e-03 eta 0:27:48
epoch [18/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.1127 (0.5978) lr 1.7290e-03 eta 0:27:41
epoch [18/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.002) loss 0.5286 (0.5842) lr 1.7290e-03 eta 0:27:35
epoch [19/50] batch [20/204] time 0.254 (0.270) data 0.000 (0.019) loss 0.2812 (0.8197) lr 1.6845e-03 eta 0:29:20
epoch [19/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 0.0413 (0.6468) lr 1.6845e-03 eta 0:28:15
epoch [19/50] batch [60/204] time 0.266 (0.258) data 0.001 (0.007) loss 0.0165 (0.6038) lr 1.6845e-03 eta 0:27:50
epoch [19/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.005) loss 0.7984 (0.5662) lr 1.6845e-03 eta 0:27:34
epoch [19/50] batch [100/204] time 0.255 (0.256) data 0.000 (0.004) loss 0.0234 (0.5403) lr 1.6845e-03 eta 0:27:23
epoch [19/50] batch [120/204] time 0.258 (0.255) data 0.000 (0.003) loss 0.1492 (0.5233) lr 1.6845e-03 eta 0:27:13
epoch [19/50] batch [140/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.1475 (0.5286) lr 1.6845e-03 eta 0:27:05
epoch [19/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0705 (0.5249) lr 1.6845e-03 eta 0:26:57
epoch [19/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.002) loss 1.1461 (0.5448) lr 1.6845e-03 eta 0:26:50
epoch [19/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.002) loss 1.1861 (0.5372) lr 1.6845e-03 eta 0:26:43
epoch [20/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.019) loss 0.2106 (0.4181) lr 1.6374e-03 eta 0:28:26
epoch [20/50] batch [40/204] time 0.254 (0.261) data 0.000 (0.010) loss 1.1927 (0.6001) lr 1.6374e-03 eta 0:27:20
epoch [20/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.006) loss 0.0084 (0.5836) lr 1.6374e-03 eta 0:26:55
epoch [20/50] batch [80/204] time 0.249 (0.256) data 0.000 (0.005) loss 0.3151 (0.5398) lr 1.6374e-03 eta 0:26:38
epoch [20/50] batch [100/204] time 0.251 (0.255) data 0.000 (0.004) loss 2.8924 (0.5525) lr 1.6374e-03 eta 0:26:27
epoch [20/50] batch [120/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.0290 (0.5543) lr 1.6374e-03 eta 0:26:18
epoch [20/50] batch [140/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0487 (0.5334) lr 1.6374e-03 eta 0:26:10
epoch [20/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.1310 (0.5117) lr 1.6374e-03 eta 0:26:03
epoch [20/50] batch [180/204] time 0.248 (0.253) data 0.000 (0.002) loss 1.0072 (0.5141) lr 1.6374e-03 eta 0:25:56
epoch [20/50] batch [200/204] time 0.248 (0.253) data 0.000 (0.002) loss 0.9558 (0.5565) lr 1.6374e-03 eta 0:25:49
epoch [21/50] batch [20/204] time 0.248 (0.270) data 0.000 (0.019) loss 1.4226 (0.7388) lr 1.5878e-03 eta 0:27:29
epoch [21/50] batch [40/204] time 0.254 (0.261) data 0.000 (0.009) loss 0.0557 (0.6692) lr 1.5878e-03 eta 0:26:29
epoch [21/50] batch [60/204] time 0.255 (0.258) data 0.001 (0.006) loss 0.5725 (0.7221) lr 1.5878e-03 eta 0:26:06
epoch [21/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.005) loss 1.3581 (0.6824) lr 1.5878e-03 eta 0:25:49
epoch [21/50] batch [100/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.0592 (0.6871) lr 1.5878e-03 eta 0:25:37
epoch [21/50] batch [120/204] time 0.247 (0.255) data 0.000 (0.003) loss 0.7086 (0.6696) lr 1.5878e-03 eta 0:25:29
epoch [21/50] batch [140/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.2975 (0.6636) lr 1.5878e-03 eta 0:25:21
epoch [21/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.0074 (0.6207) lr 1.5878e-03 eta 0:25:13
epoch [21/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.1597 (0.5962) lr 1.5878e-03 eta 0:25:06
epoch [21/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.0111 (0.6052) lr 1.5878e-03 eta 0:25:00
epoch [22/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.019) loss 0.8196 (0.6026) lr 1.5358e-03 eta 0:26:33
epoch [22/50] batch [40/204] time 0.254 (0.261) data 0.000 (0.010) loss 0.7610 (0.5605) lr 1.5358e-03 eta 0:25:33
epoch [22/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.007) loss 0.0484 (0.5555) lr 1.5358e-03 eta 0:25:10
epoch [22/50] batch [80/204] time 0.252 (0.256) data 0.000 (0.005) loss 0.0326 (0.5583) lr 1.5358e-03 eta 0:24:56
epoch [22/50] batch [100/204] time 0.249 (0.256) data 0.000 (0.004) loss 1.7262 (0.6025) lr 1.5358e-03 eta 0:24:46
epoch [22/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.9065 (0.5716) lr 1.5358e-03 eta 0:24:36
epoch [22/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.6987 (0.5409) lr 1.5358e-03 eta 0:24:29
epoch [22/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.4398 (0.5508) lr 1.5358e-03 eta 0:24:22
epoch [22/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.002) loss 0.4781 (0.5489) lr 1.5358e-03 eta 0:24:15
epoch [22/50] batch [200/204] time 0.247 (0.254) data 0.000 (0.002) loss 0.0131 (0.5580) lr 1.5358e-03 eta 0:24:09
epoch [23/50] batch [20/204] time 0.248 (0.270) data 0.000 (0.019) loss 0.1634 (0.6376) lr 1.4818e-03 eta 0:25:38
epoch [23/50] batch [40/204] time 0.247 (0.261) data 0.000 (0.010) loss 2.0420 (0.6139) lr 1.4818e-03 eta 0:24:40
epoch [23/50] batch [60/204] time 0.247 (0.258) data 0.000 (0.007) loss 1.9166 (0.6524) lr 1.4818e-03 eta 0:24:16
epoch [23/50] batch [80/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.0306 (0.6385) lr 1.4818e-03 eta 0:24:03
epoch [23/50] batch [100/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.7428 (0.6314) lr 1.4818e-03 eta 0:23:52
epoch [23/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.3262 (0.6527) lr 1.4818e-03 eta 0:23:44
epoch [23/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.0796 (0.6390) lr 1.4818e-03 eta 0:23:37
epoch [23/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.7975 (0.6061) lr 1.4818e-03 eta 0:23:30
epoch [23/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.2055 (0.5882) lr 1.4818e-03 eta 0:23:24
epoch [23/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.002) loss 0.4106 (0.5739) lr 1.4818e-03 eta 0:23:17
epoch [24/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.019) loss 0.6243 (0.5015) lr 1.4258e-03 eta 0:24:44
epoch [24/50] batch [40/204] time 0.253 (0.261) data 0.000 (0.010) loss 1.5174 (0.5337) lr 1.4258e-03 eta 0:23:48
epoch [24/50] batch [60/204] time 0.254 (0.258) data 0.000 (0.007) loss 0.2801 (0.5574) lr 1.4258e-03 eta 0:23:26
epoch [24/50] batch [80/204] time 0.248 (0.256) data 0.000 (0.005) loss 0.1104 (0.5997) lr 1.4258e-03 eta 0:23:11
epoch [24/50] batch [100/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.4073 (0.5928) lr 1.4258e-03 eta 0:23:01
epoch [24/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.003) loss 0.0590 (0.5704) lr 1.4258e-03 eta 0:22:52
epoch [24/50] batch [140/204] time 0.255 (0.254) data 0.000 (0.003) loss 1.5407 (0.5997) lr 1.4258e-03 eta 0:22:45
epoch [24/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.4119 (0.5899) lr 1.4258e-03 eta 0:22:39
epoch [24/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.002) loss 0.0577 (0.5582) lr 1.4258e-03 eta 0:22:33
epoch [24/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.002) loss 0.0721 (0.5256) lr 1.4258e-03 eta 0:22:26
epoch [25/50] batch [20/204] time 0.246 (0.274) data 0.000 (0.024) loss 0.0466 (0.4340) lr 1.3681e-03 eta 0:24:09
epoch [25/50] batch [40/204] time 0.250 (0.265) data 0.000 (0.012) loss 0.0321 (0.3996) lr 1.3681e-03 eta 0:23:12
epoch [25/50] batch [60/204] time 0.248 (0.260) data 0.000 (0.008) loss 0.0350 (0.4664) lr 1.3681e-03 eta 0:22:43
epoch [25/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.006) loss 0.0821 (0.5138) lr 1.3681e-03 eta 0:22:26
epoch [25/50] batch [100/204] time 0.252 (0.256) data 0.000 (0.005) loss 1.8870 (0.4958) lr 1.3681e-03 eta 0:22:14
epoch [25/50] batch [120/204] time 0.252 (0.256) data 0.000 (0.004) loss 0.0687 (0.5276) lr 1.3681e-03 eta 0:22:05
epoch [25/50] batch [140/204] time 0.255 (0.256) data 0.000 (0.004) loss 1.4470 (0.5219) lr 1.3681e-03 eta 0:21:59
epoch [25/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.0121 (0.5031) lr 1.3681e-03 eta 0:21:52
epoch [25/50] batch [180/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.0402 (0.4977) lr 1.3681e-03 eta 0:21:45
epoch [25/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.2651 (0.5194) lr 1.3681e-03 eta 0:21:37
epoch [26/50] batch [20/204] time 0.248 (0.275) data 0.000 (0.025) loss 1.2688 (0.5908) lr 1.3090e-03 eta 0:23:19
epoch [26/50] batch [40/204] time 0.247 (0.263) data 0.000 (0.013) loss 0.4894 (0.6768) lr 1.3090e-03 eta 0:22:12
epoch [26/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.008) loss 0.4515 (0.6917) lr 1.3090e-03 eta 0:21:46
epoch [26/50] batch [80/204] time 0.250 (0.257) data 0.000 (0.006) loss 0.0901 (0.6245) lr 1.3090e-03 eta 0:21:31
epoch [26/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.0894 (0.6171) lr 1.3090e-03 eta 0:21:20
epoch [26/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.2174 (0.5999) lr 1.3090e-03 eta 0:21:11
epoch [26/50] batch [140/204] time 0.247 (0.255) data 0.000 (0.004) loss 1.0908 (0.5832) lr 1.3090e-03 eta 0:21:03
epoch [26/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1324 (0.5907) lr 1.3090e-03 eta 0:20:55
epoch [26/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.0147 (0.5924) lr 1.3090e-03 eta 0:20:49
epoch [26/50] batch [200/204] time 0.251 (0.254) data 0.000 (0.003) loss 1.5720 (0.5868) lr 1.3090e-03 eta 0:20:42
epoch [27/50] batch [20/204] time 0.250 (0.274) data 0.000 (0.023) loss 0.3355 (0.6433) lr 1.2487e-03 eta 0:22:15
epoch [27/50] batch [40/204] time 0.248 (0.263) data 0.000 (0.011) loss 0.3439 (0.6481) lr 1.2487e-03 eta 0:21:15
epoch [27/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.008) loss 0.0578 (0.5514) lr 1.2487e-03 eta 0:20:51
epoch [27/50] batch [80/204] time 0.273 (0.257) data 0.000 (0.006) loss 0.8324 (0.5372) lr 1.2487e-03 eta 0:20:38
epoch [27/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.1154 (0.4896) lr 1.2487e-03 eta 0:20:27
epoch [27/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0114 (0.4782) lr 1.2487e-03 eta 0:20:19
epoch [27/50] batch [140/204] time 0.256 (0.255) data 0.000 (0.003) loss 0.0576 (0.4998) lr 1.2487e-03 eta 0:20:12
epoch [27/50] batch [160/204] time 0.251 (0.255) data 0.000 (0.003) loss 0.3054 (0.5089) lr 1.2487e-03 eta 0:20:05
epoch [27/50] batch [180/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.3218 (0.5389) lr 1.2487e-03 eta 0:19:58
epoch [27/50] batch [200/204] time 0.251 (0.254) data 0.000 (0.002) loss 0.0330 (0.5342) lr 1.2487e-03 eta 0:19:51
epoch [28/50] batch [20/204] time 0.247 (0.275) data 0.000 (0.025) loss 0.1306 (0.6389) lr 1.1874e-03 eta 0:21:26
epoch [28/50] batch [40/204] time 0.246 (0.264) data 0.000 (0.013) loss 0.8564 (0.6600) lr 1.1874e-03 eta 0:20:27
epoch [28/50] batch [60/204] time 0.250 (0.260) data 0.000 (0.009) loss 0.0419 (0.5348) lr 1.1874e-03 eta 0:20:02
epoch [28/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.007) loss 0.5483 (0.5013) lr 1.1874e-03 eta 0:19:46
epoch [28/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 1.0167 (0.5267) lr 1.1874e-03 eta 0:19:35
epoch [28/50] batch [120/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.5113 (0.5742) lr 1.1874e-03 eta 0:19:26
epoch [28/50] batch [140/204] time 0.249 (0.255) data 0.000 (0.004) loss 2.0861 (0.5387) lr 1.1874e-03 eta 0:19:19
epoch [28/50] batch [160/204] time 0.253 (0.255) data 0.000 (0.003) loss 0.0898 (0.5168) lr 1.1874e-03 eta 0:19:13
epoch [28/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.4573 (0.5392) lr 1.1874e-03 eta 0:19:06
epoch [28/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0981 (0.5450) lr 1.1874e-03 eta 0:18:59
epoch [29/50] batch [20/204] time 0.253 (0.275) data 0.000 (0.023) loss 0.9048 (0.5808) lr 1.1253e-03 eta 0:20:28
epoch [29/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.012) loss 0.0421 (0.5267) lr 1.1253e-03 eta 0:19:30
epoch [29/50] batch [60/204] time 0.254 (0.259) data 0.000 (0.008) loss 0.7197 (0.5853) lr 1.1253e-03 eta 0:19:06
epoch [29/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.006) loss 0.8044 (0.6185) lr 1.1253e-03 eta 0:18:52
epoch [29/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.6721 (0.5708) lr 1.1253e-03 eta 0:18:42
epoch [29/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.2826 (0.5405) lr 1.1253e-03 eta 0:18:34
epoch [29/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.1989 (0.5165) lr 1.1253e-03 eta 0:18:26
epoch [29/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.2610 (0.5098) lr 1.1253e-03 eta 0:18:20
epoch [29/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.5895 (0.5114) lr 1.1253e-03 eta 0:18:14
epoch [29/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.002) loss 0.8356 (0.5007) lr 1.1253e-03 eta 0:18:07
epoch [30/50] batch [20/204] time 0.256 (0.275) data 0.000 (0.024) loss 0.2857 (0.3791) lr 1.0628e-03 eta 0:19:33
epoch [30/50] batch [40/204] time 0.253 (0.263) data 0.000 (0.012) loss 0.8544 (0.3516) lr 1.0628e-03 eta 0:18:37
epoch [30/50] batch [60/204] time 0.251 (0.259) data 0.000 (0.008) loss 1.1043 (0.4136) lr 1.0628e-03 eta 0:18:15
epoch [30/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.006) loss 0.7444 (0.4127) lr 1.0628e-03 eta 0:18:02
epoch [30/50] batch [100/204] time 0.251 (0.256) data 0.000 (0.005) loss 0.0609 (0.4114) lr 1.0628e-03 eta 0:17:52
epoch [30/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.004) loss 0.9079 (0.4353) lr 1.0628e-03 eta 0:17:44
epoch [30/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.1034 (0.4336) lr 1.0628e-03 eta 0:17:36
epoch [30/50] batch [160/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.0122 (0.4542) lr 1.0628e-03 eta 0:17:29
epoch [30/50] batch [180/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0073 (0.4728) lr 1.0628e-03 eta 0:17:23
epoch [30/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0722 (0.4897) lr 1.0628e-03 eta 0:17:17
epoch [31/50] batch [20/204] time 0.248 (0.275) data 0.000 (0.024) loss 0.7202 (0.6311) lr 1.0000e-03 eta 0:18:38
epoch [31/50] batch [40/204] time 0.254 (0.264) data 0.000 (0.012) loss 0.6568 (0.5577) lr 1.0000e-03 eta 0:17:46
epoch [31/50] batch [60/204] time 0.261 (0.260) data 0.000 (0.008) loss 0.0434 (0.6166) lr 1.0000e-03 eta 0:17:24
epoch [31/50] batch [80/204] time 0.249 (0.258) data 0.000 (0.006) loss 0.0578 (0.6250) lr 1.0000e-03 eta 0:17:11
epoch [31/50] batch [100/204] time 0.247 (0.257) data 0.000 (0.005) loss 0.6005 (0.6172) lr 1.0000e-03 eta 0:17:01
epoch [31/50] batch [120/204] time 0.254 (0.256) data 0.000 (0.004) loss 0.1757 (0.5987) lr 1.0000e-03 eta 0:16:53
epoch [31/50] batch [140/204] time 0.255 (0.255) data 0.000 (0.004) loss 0.7556 (0.6013) lr 1.0000e-03 eta 0:16:45
epoch [31/50] batch [160/204] time 0.248 (0.255) data 0.000 (0.003) loss 0.1436 (0.6110) lr 1.0000e-03 eta 0:16:39
epoch [31/50] batch [180/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.6102 (0.5967) lr 1.0000e-03 eta 0:16:32
epoch [31/50] batch [200/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.0322 (0.6015) lr 1.0000e-03 eta 0:16:26
epoch [32/50] batch [20/204] time 0.253 (0.274) data 0.000 (0.023) loss 0.9833 (0.4597) lr 9.3721e-04 eta 0:17:37
epoch [32/50] batch [40/204] time 0.248 (0.263) data 0.000 (0.012) loss 0.3314 (0.4957) lr 9.3721e-04 eta 0:16:48
epoch [32/50] batch [60/204] time 0.248 (0.259) data 0.000 (0.008) loss 0.3306 (0.4415) lr 9.3721e-04 eta 0:16:28
epoch [32/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.006) loss 1.0727 (0.5193) lr 9.3721e-04 eta 0:16:16
epoch [32/50] batch [100/204] time 0.257 (0.256) data 0.000 (0.005) loss 0.6194 (0.5423) lr 9.3721e-04 eta 0:16:07
epoch [32/50] batch [120/204] time 0.246 (0.256) data 0.000 (0.004) loss 0.3940 (0.5300) lr 9.3721e-04 eta 0:16:00
epoch [32/50] batch [140/204] time 0.249 (0.255) data 0.000 (0.004) loss 0.0215 (0.5193) lr 9.3721e-04 eta 0:15:53
epoch [32/50] batch [160/204] time 0.255 (0.255) data 0.000 (0.003) loss 0.3532 (0.5073) lr 9.3721e-04 eta 0:15:47
epoch [32/50] batch [180/204] time 0.252 (0.255) data 0.000 (0.003) loss 0.2964 (0.5135) lr 9.3721e-04 eta 0:15:41
epoch [32/50] batch [200/204] time 0.255 (0.254) data 0.000 (0.003) loss 0.4599 (0.5160) lr 9.3721e-04 eta 0:15:35
epoch [33/50] batch [20/204] time 0.247 (0.273) data 0.000 (0.023) loss 0.1214 (0.2938) lr 8.7467e-04 eta 0:16:38
epoch [33/50] batch [40/204] time 0.250 (0.262) data 0.000 (0.012) loss 0.3349 (0.4911) lr 8.7467e-04 eta 0:15:50
epoch [33/50] batch [60/204] time 0.247 (0.258) data 0.000 (0.008) loss 0.1280 (0.5415) lr 8.7467e-04 eta 0:15:30
epoch [33/50] batch [80/204] time 0.260 (0.257) data 0.000 (0.006) loss 0.7752 (0.5197) lr 8.7467e-04 eta 0:15:23
epoch [33/50] batch [100/204] time 0.252 (0.256) data 0.000 (0.005) loss 0.0136 (0.5246) lr 8.7467e-04 eta 0:15:14
epoch [33/50] batch [120/204] time 0.255 (0.255) data 0.000 (0.004) loss 0.5181 (0.5531) lr 8.7467e-04 eta 0:15:06
epoch [33/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.1175 (0.5796) lr 8.7467e-04 eta 0:15:00
epoch [33/50] batch [160/204] time 0.254 (0.255) data 0.000 (0.003) loss 0.0133 (0.5917) lr 8.7467e-04 eta 0:14:54
epoch [33/50] batch [180/204] time 0.249 (0.254) data 0.000 (0.003) loss 0.8242 (0.6164) lr 8.7467e-04 eta 0:14:48
epoch [33/50] batch [200/204] time 0.249 (0.254) data 0.000 (0.002) loss 0.0135 (0.6000) lr 8.7467e-04 eta 0:14:42
epoch [34/50] batch [20/204] time 0.247 (0.273) data 0.000 (0.023) loss 0.1284 (0.5547) lr 8.1262e-04 eta 0:15:41
epoch [34/50] batch [40/204] time 0.250 (0.262) data 0.000 (0.011) loss 0.0405 (0.5453) lr 8.1262e-04 eta 0:14:58
epoch [34/50] batch [60/204] time 0.247 (0.260) data 0.000 (0.008) loss 0.0274 (0.5720) lr 8.1262e-04 eta 0:14:45
epoch [34/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.9764 (0.5392) lr 8.1262e-04 eta 0:14:32
epoch [34/50] batch [100/204] time 0.250 (0.256) data 0.000 (0.005) loss 0.1892 (0.5334) lr 8.1262e-04 eta 0:14:22
epoch [34/50] batch [120/204] time 0.251 (0.255) data 0.000 (0.004) loss 0.0166 (0.5349) lr 8.1262e-04 eta 0:14:14
epoch [34/50] batch [140/204] time 0.255 (0.255) data 0.000 (0.003) loss 0.3401 (0.5299) lr 8.1262e-04 eta 0:14:07
epoch [34/50] batch [160/204] time 0.257 (0.254) data 0.000 (0.003) loss 0.2783 (0.5303) lr 8.1262e-04 eta 0:14:00
epoch [34/50] batch [180/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.1732 (0.5225) lr 8.1262e-04 eta 0:13:54
epoch [34/50] batch [200/204] time 0.254 (0.254) data 0.000 (0.002) loss 0.4666 (0.5215) lr 8.1262e-04 eta 0:13:48
epoch [35/50] batch [20/204] time 0.253 (0.274) data 0.000 (0.022) loss 0.2215 (0.3854) lr 7.5131e-04 eta 0:14:48
epoch [35/50] batch [40/204] time 0.248 (0.263) data 0.000 (0.011) loss 2.5179 (0.4426) lr 7.5131e-04 eta 0:14:06
epoch [35/50] batch [60/204] time 0.259 (0.259) data 0.000 (0.008) loss 0.0516 (0.4321) lr 7.5131e-04 eta 0:13:48
epoch [35/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 1.3870 (0.4427) lr 7.5131e-04 eta 0:13:36
epoch [35/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.2216 (0.4348) lr 7.5131e-04 eta 0:13:28
epoch [35/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 0.7812 (0.4947) lr 7.5131e-04 eta 0:13:21
epoch [35/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0679 (0.5006) lr 7.5131e-04 eta 0:13:14
epoch [35/50] batch [160/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.2026 (0.4843) lr 7.5131e-04 eta 0:13:08
epoch [35/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.3364 (0.4775) lr 7.5131e-04 eta 0:13:02
epoch [35/50] batch [200/204] time 0.258 (0.253) data 0.000 (0.002) loss 0.6968 (0.4990) lr 7.5131e-04 eta 0:12:55
epoch [36/50] batch [20/204] time 0.254 (0.274) data 0.000 (0.023) loss 0.0207 (0.5613) lr 6.9098e-04 eta 0:13:54
epoch [36/50] batch [40/204] time 0.250 (0.263) data 0.000 (0.012) loss 0.7553 (0.5317) lr 6.9098e-04 eta 0:13:13
epoch [36/50] batch [60/204] time 0.247 (0.259) data 0.000 (0.008) loss 0.5080 (0.4760) lr 6.9098e-04 eta 0:12:56
epoch [36/50] batch [80/204] time 0.250 (0.257) data 0.000 (0.006) loss 0.2050 (0.5055) lr 6.9098e-04 eta 0:12:45
epoch [36/50] batch [100/204] time 0.248 (0.255) data 0.000 (0.005) loss 0.8150 (0.5384) lr 6.9098e-04 eta 0:12:36
epoch [36/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.0308 (0.5258) lr 6.9098e-04 eta 0:12:29
epoch [36/50] batch [140/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.3691 (0.5389) lr 6.9098e-04 eta 0:12:22
epoch [36/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0306 (0.5297) lr 6.9098e-04 eta 0:12:16
epoch [36/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.6510 (0.5202) lr 6.9098e-04 eta 0:12:10
epoch [36/50] batch [200/204] time 0.247 (0.253) data 0.000 (0.002) loss 0.0135 (0.5098) lr 6.9098e-04 eta 0:12:03
epoch [37/50] batch [20/204] time 0.253 (0.274) data 0.000 (0.022) loss 0.3909 (0.6258) lr 6.3188e-04 eta 0:12:57
epoch [37/50] batch [40/204] time 0.247 (0.263) data 0.000 (0.011) loss 0.0089 (0.6390) lr 6.3188e-04 eta 0:12:20
epoch [37/50] batch [60/204] time 0.247 (0.258) data 0.000 (0.008) loss 0.0459 (0.6693) lr 6.3188e-04 eta 0:12:02
epoch [37/50] batch [80/204] time 0.246 (0.257) data 0.000 (0.006) loss 0.6330 (0.6306) lr 6.3188e-04 eta 0:11:52
epoch [37/50] batch [100/204] time 0.248 (0.255) data 0.000 (0.005) loss 0.6717 (0.5862) lr 6.3188e-04 eta 0:11:43
epoch [37/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.0029 (0.5627) lr 6.3188e-04 eta 0:11:36
epoch [37/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.1500 (0.6038) lr 6.3188e-04 eta 0:11:30
epoch [37/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.1724 (0.5851) lr 6.3188e-04 eta 0:11:24
epoch [37/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.0883 (0.5717) lr 6.3188e-04 eta 0:11:18
epoch [37/50] batch [200/204] time 0.250 (0.253) data 0.000 (0.002) loss 0.0544 (0.5606) lr 6.3188e-04 eta 0:11:12
epoch [38/50] batch [20/204] time 0.253 (0.273) data 0.000 (0.022) loss 1.2780 (0.6770) lr 5.7422e-04 eta 0:11:58
epoch [38/50] batch [40/204] time 0.248 (0.262) data 0.000 (0.011) loss 0.4259 (0.5725) lr 5.7422e-04 eta 0:11:24
epoch [38/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.007) loss 0.4594 (0.5747) lr 5.7422e-04 eta 0:11:10
epoch [38/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 1.6648 (0.5876) lr 5.7422e-04 eta 0:11:00
epoch [38/50] batch [100/204] time 0.244 (0.255) data 0.000 (0.005) loss 0.4020 (0.5970) lr 5.7422e-04 eta 0:10:52
epoch [38/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0119 (0.5743) lr 5.7422e-04 eta 0:10:44
epoch [38/50] batch [140/204] time 0.247 (0.254) data 0.000 (0.003) loss 0.0502 (0.5626) lr 5.7422e-04 eta 0:10:38
epoch [38/50] batch [160/204] time 0.245 (0.253) data 0.000 (0.003) loss 0.3217 (0.5579) lr 5.7422e-04 eta 0:10:31
epoch [38/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.5125 (0.5508) lr 5.7422e-04 eta 0:10:25
epoch [38/50] batch [200/204] time 0.246 (0.253) data 0.003 (0.002) loss 0.4527 (0.5627) lr 5.7422e-04 eta 0:10:19
epoch [39/50] batch [20/204] time 0.253 (0.275) data 0.000 (0.023) loss 0.3372 (0.5478) lr 5.1825e-04 eta 0:11:06
epoch [39/50] batch [40/204] time 0.247 (0.263) data 0.000 (0.011) loss 1.3986 (0.5610) lr 5.1825e-04 eta 0:10:33
epoch [39/50] batch [60/204] time 0.251 (0.259) data 0.001 (0.008) loss 2.1261 (0.5882) lr 5.1825e-04 eta 0:10:19
epoch [39/50] batch [80/204] time 0.250 (0.257) data 0.000 (0.006) loss 0.3853 (0.5980) lr 5.1825e-04 eta 0:10:08
epoch [39/50] batch [100/204] time 0.251 (0.256) data 0.000 (0.005) loss 1.1535 (0.5845) lr 5.1825e-04 eta 0:10:00
epoch [39/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 1.2174 (0.6198) lr 5.1825e-04 eta 0:09:54
epoch [39/50] batch [140/204] time 0.247 (0.255) data 0.000 (0.003) loss 1.2377 (0.6001) lr 5.1825e-04 eta 0:09:47
epoch [39/50] batch [160/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.6307 (0.5969) lr 5.1825e-04 eta 0:09:41
epoch [39/50] batch [180/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.6763 (0.5878) lr 5.1825e-04 eta 0:09:35
epoch [39/50] batch [200/204] time 0.257 (0.254) data 0.000 (0.002) loss 1.1404 (0.5953) lr 5.1825e-04 eta 0:09:30
epoch [40/50] batch [20/204] time 0.258 (0.275) data 0.000 (0.024) loss 1.0947 (0.3739) lr 4.6417e-04 eta 0:10:11
epoch [40/50] batch [40/204] time 0.252 (0.263) data 0.000 (0.012) loss 0.9027 (0.4320) lr 4.6417e-04 eta 0:09:39
epoch [40/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.008) loss 1.7739 (0.5223) lr 4.6417e-04 eta 0:09:25
epoch [40/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.7131 (0.5617) lr 4.6417e-04 eta 0:09:15
epoch [40/50] batch [100/204] time 0.260 (0.256) data 0.000 (0.005) loss 0.0880 (0.6125) lr 4.6417e-04 eta 0:09:08
epoch [40/50] batch [120/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.1045 (0.6324) lr 4.6417e-04 eta 0:09:01
epoch [40/50] batch [140/204] time 0.243 (0.254) data 0.000 (0.004) loss 1.5670 (0.6508) lr 4.6417e-04 eta 0:08:54
epoch [40/50] batch [160/204] time 0.246 (0.254) data 0.000 (0.003) loss 0.3585 (0.6488) lr 4.6417e-04 eta 0:08:48
epoch [40/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.6560 (0.6000) lr 4.6417e-04 eta 0:08:42
epoch [40/50] batch [200/204] time 0.251 (0.253) data 0.000 (0.003) loss 0.5005 (0.5865) lr 4.6417e-04 eta 0:08:36
epoch [41/50] batch [20/204] time 0.251 (0.274) data 0.000 (0.023) loss 2.2408 (0.5300) lr 4.1221e-04 eta 0:09:13
epoch [41/50] batch [40/204] time 0.244 (0.262) data 0.000 (0.012) loss 0.3361 (0.6183) lr 4.1221e-04 eta 0:08:43
epoch [41/50] batch [60/204] time 0.253 (0.258) data 0.000 (0.008) loss 0.4560 (0.4985) lr 4.1221e-04 eta 0:08:31
epoch [41/50] batch [80/204] time 0.247 (0.256) data 0.000 (0.006) loss 0.0332 (0.4889) lr 4.1221e-04 eta 0:08:22
epoch [41/50] batch [100/204] time 0.254 (0.255) data 0.000 (0.005) loss 0.9250 (0.5156) lr 4.1221e-04 eta 0:08:14
epoch [41/50] batch [120/204] time 0.250 (0.254) data 0.000 (0.004) loss 0.0477 (0.5069) lr 4.1221e-04 eta 0:08:08
epoch [41/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.2636 (0.5209) lr 4.1221e-04 eta 0:08:02
epoch [41/50] batch [160/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.4224 (0.5392) lr 4.1221e-04 eta 0:07:56
epoch [41/50] batch [180/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.1176 (0.5195) lr 4.1221e-04 eta 0:07:50
epoch [41/50] batch [200/204] time 0.245 (0.253) data 0.000 (0.002) loss 1.1623 (0.5129) lr 4.1221e-04 eta 0:07:44
epoch [42/50] batch [20/204] time 0.250 (0.275) data 0.000 (0.024) loss 0.7500 (0.7495) lr 3.6258e-04 eta 0:08:19
epoch [42/50] batch [40/204] time 0.254 (0.263) data 0.000 (0.012) loss 0.1245 (0.6311) lr 3.6258e-04 eta 0:07:51
epoch [42/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.008) loss 1.2114 (0.5731) lr 3.6258e-04 eta 0:07:39
epoch [42/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.006) loss 1.0880 (0.5571) lr 3.6258e-04 eta 0:07:30
epoch [42/50] batch [100/204] time 0.246 (0.256) data 0.000 (0.005) loss 0.7039 (0.5042) lr 3.6258e-04 eta 0:07:23
epoch [42/50] batch [120/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.0665 (0.5250) lr 3.6258e-04 eta 0:07:17
epoch [42/50] batch [140/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.0681 (0.5315) lr 3.6258e-04 eta 0:07:11
epoch [42/50] batch [160/204] time 0.250 (0.254) data 0.000 (0.003) loss 1.2794 (0.5153) lr 3.6258e-04 eta 0:07:05
epoch [42/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.2739 (0.5301) lr 3.6258e-04 eta 0:07:00
epoch [42/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0554 (0.5198) lr 3.6258e-04 eta 0:06:54
epoch [43/50] batch [20/204] time 0.253 (0.275) data 0.000 (0.024) loss 1.3038 (0.5043) lr 3.1545e-04 eta 0:07:22
epoch [43/50] batch [40/204] time 0.251 (0.263) data 0.000 (0.012) loss 0.0921 (0.5198) lr 3.1545e-04 eta 0:06:57
epoch [43/50] batch [60/204] time 0.248 (0.259) data 0.000 (0.008) loss 0.1151 (0.5015) lr 3.1545e-04 eta 0:06:46
epoch [43/50] batch [80/204] time 0.251 (0.258) data 0.000 (0.006) loss 0.1434 (0.5431) lr 3.1545e-04 eta 0:06:39
epoch [43/50] batch [100/204] time 0.253 (0.257) data 0.000 (0.005) loss 0.4172 (0.5197) lr 3.1545e-04 eta 0:06:32
epoch [43/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.8301 (0.5080) 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 0.1833 (0.5785) lr 3.1545e-04 eta 0:06:20
epoch [43/50] batch [160/204] time 0.255 (0.254) data 0.000 (0.003) loss 0.0562 (0.5525) 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 0.3735 (0.5503) lr 3.1545e-04 eta 0:06:08
epoch [43/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0844 (0.5481) lr 3.1545e-04 eta 0:06:03
epoch [44/50] batch [20/204] time 0.248 (0.276) data 0.000 (0.024) loss 0.3612 (0.5052) lr 2.7103e-04 eta 0:06:28
epoch [44/50] batch [40/204] time 0.254 (0.264) data 0.000 (0.012) loss 1.6667 (0.6226) lr 2.7103e-04 eta 0:06:05
epoch [44/50] batch [60/204] time 0.252 (0.259) data 0.000 (0.008) loss 0.1049 (0.6502) lr 2.7103e-04 eta 0:05:54
epoch [44/50] batch [80/204] time 0.254 (0.257) data 0.000 (0.006) loss 0.1497 (0.6333) lr 2.7103e-04 eta 0:05:46
epoch [44/50] batch [100/204] time 0.249 (0.256) data 0.000 (0.005) loss 0.0492 (0.5918) lr 2.7103e-04 eta 0:05:39
epoch [44/50] batch [120/204] time 0.248 (0.255) data 0.000 (0.004) loss 0.1788 (0.5382) lr 2.7103e-04 eta 0:05:33
epoch [44/50] batch [140/204] time 0.252 (0.255) data 0.000 (0.004) loss 0.1077 (0.5895) lr 2.7103e-04 eta 0:05:28
epoch [44/50] batch [160/204] time 0.261 (0.254) data 0.003 (0.003) loss 0.3825 (0.5887) 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 0.8107 (0.5835) lr 2.7103e-04 eta 0:05:17
epoch [44/50] batch [200/204] time 0.250 (0.254) data 0.000 (0.003) loss 0.2962 (0.5771) lr 2.7103e-04 eta 0:05:11
epoch [45/50] batch [20/204] time 0.254 (0.275) data 0.000 (0.023) loss 0.0107 (0.4023) lr 2.2949e-04 eta 0:05:30
epoch [45/50] batch [40/204] time 0.252 (0.264) data 0.000 (0.012) loss 1.4294 (0.5333) lr 2.2949e-04 eta 0:05:12
epoch [45/50] batch [60/204] time 0.249 (0.260) data 0.000 (0.008) loss 0.2016 (0.5245) lr 2.2949e-04 eta 0:05:02
epoch [45/50] batch [80/204] time 0.254 (0.258) data 0.000 (0.006) loss 0.4949 (0.5614) lr 2.2949e-04 eta 0:04:55
epoch [45/50] batch [100/204] time 0.255 (0.257) data 0.000 (0.005) loss 0.1613 (0.5448) lr 2.2949e-04 eta 0:04:48
epoch [45/50] batch [120/204] time 0.253 (0.256) data 0.000 (0.004) loss 0.5599 (0.5469) lr 2.2949e-04 eta 0:04:42
epoch [45/50] batch [140/204] time 0.255 (0.255) data 0.000 (0.004) loss 1.4064 (0.5501) lr 2.2949e-04 eta 0:04:36
epoch [45/50] batch [160/204] time 0.257 (0.255) data 0.000 (0.003) loss 1.0092 (0.5234) lr 2.2949e-04 eta 0:04:31
epoch [45/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.8174 (0.5456) lr 2.2949e-04 eta 0:04:25
epoch [45/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.5885 (0.5645) lr 2.2949e-04 eta 0:04:20
epoch [46/50] batch [20/204] time 0.245 (0.274) data 0.000 (0.024) loss 0.3861 (0.5518) lr 1.9098e-04 eta 0:04:34
epoch [46/50] batch [40/204] time 0.246 (0.262) data 0.000 (0.012) loss 1.1419 (0.4630) lr 1.9098e-04 eta 0:04:16
epoch [46/50] batch [60/204] time 0.251 (0.258) data 0.000 (0.008) loss 0.2500 (0.5637) lr 1.9098e-04 eta 0:04:08
epoch [46/50] batch [80/204] time 0.252 (0.256) data 0.000 (0.006) loss 0.4379 (0.5772) lr 1.9098e-04 eta 0:04:01
epoch [46/50] batch [100/204] time 0.252 (0.255) data 0.000 (0.005) loss 0.0327 (0.5482) lr 1.9098e-04 eta 0:03:54
epoch [46/50] batch [120/204] time 0.253 (0.254) data 0.000 (0.004) loss 0.0241 (0.5541) lr 1.9098e-04 eta 0:03:48
epoch [46/50] batch [140/204] time 0.255 (0.254) data 0.000 (0.004) loss 0.1955 (0.5576) lr 1.9098e-04 eta 0:03:43
epoch [46/50] batch [160/204] time 0.251 (0.253) data 0.000 (0.003) loss 0.0197 (0.5550) lr 1.9098e-04 eta 0:03:37
epoch [46/50] batch [180/204] time 0.253 (0.253) data 0.000 (0.003) loss 0.3849 (0.5707) lr 1.9098e-04 eta 0:03:32
epoch [46/50] batch [200/204] time 0.252 (0.253) data 0.000 (0.003) loss 0.3527 (0.5784) lr 1.9098e-04 eta 0:03:27
epoch [47/50] batch [20/204] time 0.250 (0.276) data 0.000 (0.024) loss 0.0988 (0.3579) lr 1.5567e-04 eta 0:03:39
epoch [47/50] batch [40/204] time 0.252 (0.263) data 0.000 (0.012) loss 0.0975 (0.4036) lr 1.5567e-04 eta 0:03:24
epoch [47/50] batch [60/204] time 0.253 (0.259) data 0.000 (0.008) loss 1.2638 (0.3949) lr 1.5567e-04 eta 0:03:15
epoch [47/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.006) loss 0.3559 (0.4245) lr 1.5567e-04 eta 0:03:09
epoch [47/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.2005 (0.4764) 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 0.0258 (0.4536) lr 1.5567e-04 eta 0:02:57
epoch [47/50] batch [140/204] time 0.253 (0.255) data 0.000 (0.004) loss 1.2722 (0.4652) lr 1.5567e-04 eta 0:02:52
epoch [47/50] batch [160/204] time 0.251 (0.254) data 0.000 (0.003) loss 0.0365 (0.4631) lr 1.5567e-04 eta 0:02:46
epoch [47/50] batch [180/204] time 0.254 (0.254) data 0.000 (0.003) loss 0.1378 (0.4471) lr 1.5567e-04 eta 0:02:41
epoch [47/50] batch [200/204] time 0.253 (0.254) data 0.000 (0.003) loss 0.0592 (0.4469) lr 1.5567e-04 eta 0:02:36
epoch [48/50] batch [20/204] time 0.254 (0.276) data 0.000 (0.024) loss 0.1223 (0.7039) lr 1.2369e-04 eta 0:02:43
epoch [48/50] batch [40/204] time 0.248 (0.264) data 0.000 (0.012) loss 0.0925 (0.5880) lr 1.2369e-04 eta 0:02:30
epoch [48/50] batch [60/204] time 0.250 (0.259) data 0.000 (0.008) loss 0.0109 (0.5386) lr 1.2369e-04 eta 0:02:23
epoch [48/50] batch [80/204] time 0.248 (0.257) data 0.000 (0.006) loss 1.5193 (0.5561) lr 1.2369e-04 eta 0:02:16
epoch [48/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.3129 (0.5622) lr 1.2369e-04 eta 0:02:11
epoch [48/50] batch [120/204] time 0.254 (0.255) data 0.000 (0.004) loss 1.0453 (0.5368) lr 1.2369e-04 eta 0:02:05
epoch [48/50] batch [140/204] time 0.254 (0.255) data 0.000 (0.004) loss 0.5154 (0.5326) lr 1.2369e-04 eta 0:02:00
epoch [48/50] batch [160/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.3273 (0.5225) lr 1.2369e-04 eta 0:01:55
epoch [48/50] batch [180/204] time 0.253 (0.254) data 0.000 (0.003) loss 1.5221 (0.5483) lr 1.2369e-04 eta 0:01:49
epoch [48/50] batch [200/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.0653 (0.5360) lr 1.2369e-04 eta 0:01:44
epoch [49/50] batch [20/204] time 0.255 (0.275) data 0.003 (0.024) loss 0.0496 (0.2910) lr 9.5173e-05 eta 0:01:46
epoch [49/50] batch [40/204] time 0.251 (0.264) data 0.000 (0.012) loss 0.0031 (0.3795) lr 9.5173e-05 eta 0:01:36
epoch [49/50] batch [60/204] time 0.249 (0.260) data 0.000 (0.008) loss 0.2227 (0.4799) lr 9.5173e-05 eta 0:01:30
epoch [49/50] batch [80/204] time 0.253 (0.257) data 0.000 (0.006) loss 0.0287 (0.4950) lr 9.5173e-05 eta 0:01:24
epoch [49/50] batch [100/204] time 0.253 (0.256) data 0.000 (0.005) loss 0.1309 (0.5066) lr 9.5173e-05 eta 0:01:18
epoch [49/50] batch [120/204] time 0.251 (0.256) data 0.000 (0.004) loss 0.0496 (0.5212) lr 9.5173e-05 eta 0:01:13
epoch [49/50] batch [140/204] time 0.246 (0.255) data 0.000 (0.004) loss 0.8724 (0.5605) lr 9.5173e-05 eta 0:01:08
epoch [49/50] batch [160/204] time 0.245 (0.255) data 0.000 (0.003) loss 0.0213 (0.5470) 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 0.1465 (0.5405) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.246 (0.254) data 0.000 (0.003) loss 0.0909 (0.5370) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.251 (0.275) data 0.000 (0.023) loss 0.8425 (0.5627) lr 7.0224e-05 eta 0:00:50
epoch [50/50] batch [40/204] time 0.252 (0.263) data 0.000 (0.012) loss 0.2149 (0.5672) lr 7.0224e-05 eta 0:00:43
epoch [50/50] batch [60/204] time 0.251 (0.259) data 0.000 (0.008) loss 0.0252 (0.5487) lr 7.0224e-05 eta 0:00:37
epoch [50/50] batch [80/204] time 0.251 (0.257) data 0.000 (0.006) loss 0.5481 (0.4951) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.247 (0.256) data 0.000 (0.005) loss 0.0790 (0.4943) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.250 (0.255) data 0.000 (0.004) loss 0.1032 (0.4914) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.246 (0.255) data 0.000 (0.004) loss 0.0611 (0.5117) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.252 (0.254) data 0.000 (0.003) loss 0.2455 (0.5134) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.256 (0.254) data 0.003 (0.003) loss 0.0105 (0.5272) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.248 (0.254) data 0.000 (0.003) loss 0.7602 (0.5278) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/food101/vit_b16_ep50_c4_BZ4_ProDA/seed2/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 15,300
* correct: 14,163
* accuracy: 92.57%
* error: 7.43%
* macro_f1: 92.56%
Elapsed: 0:44:29
