***************
** Arguments **
***************
backbone: 
config_file: configs/trainers/ProDA/vit_b16_ep50_c4_BZ4_ProDA.yaml
dataset_config_file: configs/datasets/oxford_flowers.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/oxford_flowers/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: OxfordFlowers
  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/oxford_flowers/vit_b16_ep50_c4_BZ4_ProDA/seed3
RESUME: 
SEED: 3
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ProDA
  ProDA:
    N_CTX: 4
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

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

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

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

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

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

Loading trainer: ProDA
Loading dataset: OxfordFlowers
Reading split from /mnt/hdd/DATA/oxford_flowers/split_zhou_OxfordFlowers.json
Loading preprocessed few-shot data from /mnt/hdd/DATA/oxford_flowers/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    OxfordFlowers
# classes  51
# train_x  816
# val      204
# test     1,241
---------  -------------
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/oxford_flowers/vit_b16_ep50_c4_BZ4_ProDA/seed3/tensorboard)
epoch [1/50] batch [20/204] time 0.246 (0.374) data 0.000 (0.025) loss 5.7068 (3.0667) lr 1.0000e-05 eta 1:03:26
epoch [1/50] batch [40/204] time 0.249 (0.311) data 0.000 (0.013) loss 4.8203 (2.9771) lr 1.0000e-05 eta 0:52:36
epoch [1/50] batch [60/204] time 0.249 (0.289) data 0.000 (0.008) loss 4.3572 (2.9991) lr 1.0000e-05 eta 0:48:53
epoch [1/50] batch [80/204] time 0.243 (0.279) data 0.000 (0.006) loss 4.6202 (2.8484) lr 1.0000e-05 eta 0:46:59
epoch [1/50] batch [100/204] time 0.249 (0.272) data 0.000 (0.005) loss 0.9438 (2.8037) lr 1.0000e-05 eta 0:45:51
epoch [1/50] batch [120/204] time 0.245 (0.268) data 0.000 (0.004) loss 0.8779 (2.7148) lr 1.0000e-05 eta 0:45:03
epoch [1/50] batch [140/204] time 0.245 (0.265) data 0.000 (0.004) loss 1.2685 (2.6842) lr 1.0000e-05 eta 0:44:27
epoch [1/50] batch [160/204] time 0.244 (0.263) data 0.000 (0.003) loss 4.1677 (2.6064) lr 1.0000e-05 eta 0:44:00
epoch [1/50] batch [180/204] time 0.244 (0.261) data 0.000 (0.003) loss 1.4524 (2.5656) lr 1.0000e-05 eta 0:43:37
epoch [1/50] batch [200/204] time 0.249 (0.260) data 0.000 (0.003) loss 0.2335 (2.4766) lr 1.0000e-05 eta 0:43:19
epoch [2/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.019) loss 1.6368 (2.1368) lr 1.0000e-05 eta 0:44:27
epoch [2/50] batch [40/204] time 0.242 (0.258) data 0.000 (0.010) loss 1.5969 (2.1193) lr 1.0000e-05 eta 0:42:45
epoch [2/50] batch [60/204] time 0.241 (0.254) data 0.000 (0.006) loss 1.5822 (2.1274) lr 1.0000e-05 eta 0:42:06
epoch [2/50] batch [80/204] time 0.244 (0.253) data 0.000 (0.005) loss 6.5598 (2.1473) lr 1.0000e-05 eta 0:41:45
epoch [2/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.9498 (2.0351) lr 1.0000e-05 eta 0:41:31
epoch [2/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 2.1586 (2.0675) lr 1.0000e-05 eta 0:41:21
epoch [2/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.0865 (2.0696) lr 1.0000e-05 eta 0:41:11
epoch [2/50] batch [160/204] time 0.250 (0.250) data 0.000 (0.003) loss 3.0202 (2.0583) lr 1.0000e-05 eta 0:41:03
epoch [2/50] batch [180/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.1244 (2.0634) lr 1.0000e-05 eta 0:40:55
epoch [2/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 4.4994 (2.0627) lr 1.0000e-05 eta 0:40:47
epoch [3/50] batch [20/204] time 0.249 (0.267) data 0.000 (0.018) loss 2.2913 (1.9849) lr 1.0000e-05 eta 0:43:28
epoch [3/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.3186 (1.8362) lr 1.0000e-05 eta 0:41:52
epoch [3/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.7423 (1.8603) lr 1.0000e-05 eta 0:41:18
epoch [3/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.005) loss 3.2962 (1.7813) lr 1.0000e-05 eta 0:40:56
epoch [3/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 2.7328 (1.9312) lr 1.0000e-05 eta 0:40:41
epoch [3/50] batch [120/204] time 0.251 (0.251) data 0.000 (0.003) loss 2.0038 (1.9911) lr 1.0000e-05 eta 0:40:30
epoch [3/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 2.8844 (1.9965) lr 1.0000e-05 eta 0:40:22
epoch [3/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 1.3124 (2.0090) lr 1.0000e-05 eta 0:40:13
epoch [3/50] batch [180/204] time 0.252 (0.250) data 0.000 (0.002) loss 0.4046 (1.9330) lr 1.0000e-05 eta 0:40:06
epoch [3/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 1.6581 (1.8899) lr 1.0000e-05 eta 0:39:59
epoch [4/50] batch [20/204] time 0.251 (0.268) data 0.000 (0.018) loss 4.0727 (2.2431) lr 1.0000e-05 eta 0:42:40
epoch [4/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 1.9399 (2.0714) lr 1.0000e-05 eta 0:41:02
epoch [4/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 2.1102 (2.1446) lr 1.0000e-05 eta 0:40:27
epoch [4/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 1.0616 (2.0264) lr 1.0000e-05 eta 0:40:05
epoch [4/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.2925 (1.9488) lr 1.0000e-05 eta 0:39:50
epoch [4/50] batch [120/204] time 0.246 (0.251) data 0.000 (0.003) loss 2.3490 (1.9519) lr 1.0000e-05 eta 0:39:38
epoch [4/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 6.5930 (1.9158) lr 1.0000e-05 eta 0:39:29
epoch [4/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.8223 (1.8374) lr 1.0000e-05 eta 0:39:22
epoch [4/50] batch [180/204] time 0.242 (0.250) data 0.000 (0.002) loss 3.1738 (1.8590) lr 1.0000e-05 eta 0:39:15
epoch [4/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.6692 (1.8719) lr 1.0000e-05 eta 0:39:08
epoch [5/50] batch [20/204] time 0.245 (0.267) data 0.000 (0.018) loss 2.5271 (1.4738) lr 1.0000e-05 eta 0:41:35
epoch [5/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 3.6293 (1.5983) lr 1.0000e-05 eta 0:40:04
epoch [5/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 1.0188 (1.5996) lr 1.0000e-05 eta 0:39:29
epoch [5/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 2.4524 (1.6583) lr 1.0000e-05 eta 0:39:12
epoch [5/50] batch [100/204] time 0.243 (0.252) data 0.000 (0.004) loss 1.3937 (1.6820) lr 1.0000e-05 eta 0:38:58
epoch [5/50] batch [120/204] time 0.246 (0.251) data 0.000 (0.003) loss 2.8558 (1.7455) lr 1.0000e-05 eta 0:38:48
epoch [5/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.9622 (1.8163) lr 1.0000e-05 eta 0:38:39
epoch [5/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 5.2672 (1.8295) lr 1.0000e-05 eta 0:38:32
epoch [5/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 1.6352 (1.7806) lr 1.0000e-05 eta 0:38:25
epoch [5/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 1.4599 (1.7821) lr 1.0000e-05 eta 0:38:17
epoch [6/50] batch [20/204] time 0.246 (0.267) data 0.000 (0.018) loss 1.6430 (1.8891) lr 2.0000e-03 eta 0:40:43
epoch [6/50] batch [40/204] time 0.246 (0.258) data 0.000 (0.009) loss 0.6177 (2.0196) lr 2.0000e-03 eta 0:39:15
epoch [6/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 1.8426 (1.8737) lr 2.0000e-03 eta 0:38:41
epoch [6/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.005) loss 2.6085 (1.8109) lr 2.0000e-03 eta 0:38:22
epoch [6/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.6374 (1.7471) lr 2.0000e-03 eta 0:38:10
epoch [6/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.2660 (1.7273) lr 2.0000e-03 eta 0:37:59
epoch [6/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.0322 (1.7045) lr 2.0000e-03 eta 0:37:49
epoch [6/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.4286 (1.6777) lr 2.0000e-03 eta 0:37:41
epoch [6/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.8174 (1.6614) lr 2.0000e-03 eta 0:37:34
epoch [6/50] batch [200/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.8537 (1.6296) lr 2.0000e-03 eta 0:37:27
epoch [7/50] batch [20/204] time 0.252 (0.267) data 0.000 (0.018) loss 0.4855 (1.2443) lr 1.9980e-03 eta 0:39:52
epoch [7/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 1.7949 (1.2619) lr 1.9980e-03 eta 0:38:23
epoch [7/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.8481 (1.1983) lr 1.9980e-03 eta 0:37:52
epoch [7/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.005) loss 2.1471 (1.2711) lr 1.9980e-03 eta 0:37:32
epoch [7/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.9004 (1.2494) lr 1.9980e-03 eta 0:37:17
epoch [7/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 2.5350 (1.2735) lr 1.9980e-03 eta 0:37:07
epoch [7/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.3495 (1.2558) lr 1.9980e-03 eta 0:36:59
epoch [7/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.2823 (1.2577) lr 1.9980e-03 eta 0:36:50
epoch [7/50] batch [180/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.0632 (1.2694) lr 1.9980e-03 eta 0:36:43
epoch [7/50] batch [200/204] time 0.241 (0.250) data 0.000 (0.002) loss 0.1991 (1.2378) lr 1.9980e-03 eta 0:36:35
epoch [8/50] batch [20/204] time 0.249 (0.268) data 0.000 (0.018) loss 1.9859 (1.0047) lr 1.9921e-03 eta 0:39:05
epoch [8/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 1.0718 (1.0480) lr 1.9921e-03 eta 0:37:32
epoch [8/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 1.1315 (1.1678) lr 1.9921e-03 eta 0:36:59
epoch [8/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.005) loss 0.5104 (1.1427) lr 1.9921e-03 eta 0:36:42
epoch [8/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.7141 (1.1297) lr 1.9921e-03 eta 0:36:27
epoch [8/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.4292 (1.1273) lr 1.9921e-03 eta 0:36:17
epoch [8/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.8465 (1.1325) lr 1.9921e-03 eta 0:36:08
epoch [8/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.7187 (1.0903) lr 1.9921e-03 eta 0:36:00
epoch [8/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.9280 (1.0787) lr 1.9921e-03 eta 0:35:53
epoch [8/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.6857 (1.0993) lr 1.9921e-03 eta 0:35:45
epoch [9/50] batch [20/204] time 0.248 (0.267) data 0.000 (0.019) loss 2.0696 (1.0793) lr 1.9823e-03 eta 0:38:01
epoch [9/50] batch [40/204] time 0.243 (0.258) data 0.000 (0.009) loss 0.5014 (1.1359) lr 1.9823e-03 eta 0:36:36
epoch [9/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 0.2953 (1.0359) lr 1.9823e-03 eta 0:36:08
epoch [9/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.8882 (1.1084) lr 1.9823e-03 eta 0:35:48
epoch [9/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 2.7036 (1.0828) lr 1.9823e-03 eta 0:35:35
epoch [9/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.003) loss 3.1380 (1.1254) lr 1.9823e-03 eta 0:35:25
epoch [9/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.8046 (1.1104) lr 1.9823e-03 eta 0:35:16
epoch [9/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.7563 (1.0854) lr 1.9823e-03 eta 0:35:08
epoch [9/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.0355 (1.0584) lr 1.9823e-03 eta 0:35:01
epoch [9/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 1.2892 (1.0518) lr 1.9823e-03 eta 0:34:54
epoch [10/50] batch [20/204] time 0.249 (0.267) data 0.000 (0.018) loss 0.5502 (0.8875) lr 1.9686e-03 eta 0:37:05
epoch [10/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 2.4295 (0.9888) lr 1.9686e-03 eta 0:35:45
epoch [10/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.7974 (1.0038) lr 1.9686e-03 eta 0:35:13
epoch [10/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.005) loss 0.6290 (1.0123) lr 1.9686e-03 eta 0:34:55
epoch [10/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.3265 (0.9990) lr 1.9686e-03 eta 0:34:42
epoch [10/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.0827 (1.0137) lr 1.9686e-03 eta 0:34:32
epoch [10/50] batch [140/204] time 0.244 (0.251) data 0.000 (0.003) loss 0.2265 (1.0000) lr 1.9686e-03 eta 0:34:22
epoch [10/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.7328 (0.9733) lr 1.9686e-03 eta 0:34:15
epoch [10/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.1935 (0.9954) lr 1.9686e-03 eta 0:34:07
epoch [10/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 1.5901 (0.9906) lr 1.9686e-03 eta 0:34:00
epoch [11/50] batch [20/204] time 0.249 (0.266) data 0.000 (0.018) loss 0.9155 (1.0908) lr 1.9511e-03 eta 0:36:08
epoch [11/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 1.3533 (0.9698) lr 1.9511e-03 eta 0:34:49
epoch [11/50] batch [60/204] time 0.248 (0.254) data 0.000 (0.006) loss 1.1687 (1.0554) lr 1.9511e-03 eta 0:34:18
epoch [11/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.6126 (1.0558) lr 1.9511e-03 eta 0:34:02
epoch [11/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.2290 (1.0127) lr 1.9511e-03 eta 0:33:50
epoch [11/50] batch [120/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0719 (0.9708) lr 1.9511e-03 eta 0:33:41
epoch [11/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3016 (0.9477) lr 1.9511e-03 eta 0:33:33
epoch [11/50] batch [160/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.4525 (0.9393) lr 1.9511e-03 eta 0:33:25
epoch [11/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 2.2602 (0.9618) lr 1.9511e-03 eta 0:33:18
epoch [11/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 1.2592 (0.9459) lr 1.9511e-03 eta 0:33:11
epoch [12/50] batch [20/204] time 0.249 (0.267) data 0.000 (0.018) loss 0.7311 (1.0473) lr 1.9298e-03 eta 0:35:20
epoch [12/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.7439 (0.9485) lr 1.9298e-03 eta 0:34:01
epoch [12/50] batch [60/204] time 0.257 (0.255) data 0.000 (0.006) loss 0.8276 (0.9132) lr 1.9298e-03 eta 0:33:31
epoch [12/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 1.8274 (0.9675) lr 1.9298e-03 eta 0:33:15
epoch [12/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.4950 (0.9409) lr 1.9298e-03 eta 0:33:02
epoch [12/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.5034 (0.9002) lr 1.9298e-03 eta 0:32:51
epoch [12/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.2174 (0.9074) lr 1.9298e-03 eta 0:32:42
epoch [12/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 1.6847 (0.9038) lr 1.9298e-03 eta 0:32:35
epoch [12/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 1.2290 (0.9239) lr 1.9298e-03 eta 0:32:28
epoch [12/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.6208 (0.8983) lr 1.9298e-03 eta 0:32:20
epoch [13/50] batch [20/204] time 0.246 (0.267) data 0.000 (0.018) loss 0.9990 (1.0841) lr 1.9048e-03 eta 0:34:22
epoch [13/50] batch [40/204] time 0.246 (0.258) data 0.000 (0.009) loss 0.4806 (0.9419) lr 1.9048e-03 eta 0:33:09
epoch [13/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 1.0252 (0.9332) lr 1.9048e-03 eta 0:32:41
epoch [13/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.005) loss 1.2683 (0.9536) lr 1.9048e-03 eta 0:32:23
epoch [13/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.0342 (0.9269) lr 1.9048e-03 eta 0:32:10
epoch [13/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.3089 (0.9152) lr 1.9048e-03 eta 0:32:02
epoch [13/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.5417 (0.9106) lr 1.9048e-03 eta 0:31:53
epoch [13/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.9812 (0.9199) lr 1.9048e-03 eta 0:31:46
epoch [13/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.8648 (0.9490) lr 1.9048e-03 eta 0:31:39
epoch [13/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.2138 (0.9222) lr 1.9048e-03 eta 0:31:32
epoch [14/50] batch [20/204] time 0.249 (0.268) data 0.000 (0.018) loss 0.3402 (0.7964) lr 1.8763e-03 eta 0:33:38
epoch [14/50] batch [40/204] time 0.253 (0.258) data 0.000 (0.009) loss 1.4569 (0.7746) lr 1.8763e-03 eta 0:32:19
epoch [14/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.006) loss 1.0856 (0.8610) lr 1.8763e-03 eta 0:31:53
epoch [14/50] batch [80/204] time 0.244 (0.254) data 0.000 (0.005) loss 0.3716 (0.8236) lr 1.8763e-03 eta 0:31:36
epoch [14/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.4812 (0.7827) lr 1.8763e-03 eta 0:31:25
epoch [14/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.6356 (0.7854) lr 1.8763e-03 eta 0:31:15
epoch [14/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.8788 (0.7956) lr 1.8763e-03 eta 0:31:06
epoch [14/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.002) loss 0.1990 (0.7857) lr 1.8763e-03 eta 0:30:58
epoch [14/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.8695 (0.7797) lr 1.8763e-03 eta 0:30:51
epoch [14/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.3617 (0.7908) lr 1.8763e-03 eta 0:30:43
epoch [15/50] batch [20/204] time 0.249 (0.266) data 0.000 (0.018) loss 1.6165 (1.0784) lr 1.8443e-03 eta 0:32:29
epoch [15/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.1887 (0.8611) lr 1.8443e-03 eta 0:31:21
epoch [15/50] batch [60/204] time 0.246 (0.254) data 0.000 (0.006) loss 1.0928 (0.7731) lr 1.8443e-03 eta 0:30:53
epoch [15/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.9699 (0.7526) lr 1.8443e-03 eta 0:30:37
epoch [15/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.3798 (0.7452) lr 1.8443e-03 eta 0:30:25
epoch [15/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 1.5817 (0.7655) lr 1.8443e-03 eta 0:30:17
epoch [15/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.5925 (0.7987) lr 1.8443e-03 eta 0:30:09
epoch [15/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 1.3198 (0.7721) lr 1.8443e-03 eta 0:30:01
epoch [15/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.6456 (0.7493) lr 1.8443e-03 eta 0:29:54
epoch [15/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.6364 (0.7530) lr 1.8443e-03 eta 0:29:47
epoch [16/50] batch [20/204] time 0.245 (0.268) data 0.000 (0.018) loss 0.6149 (0.6002) lr 1.8090e-03 eta 0:31:45
epoch [16/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.0845 (0.7134) lr 1.8090e-03 eta 0:30:31
epoch [16/50] batch [60/204] time 0.244 (0.255) data 0.000 (0.006) loss 1.5571 (0.7317) lr 1.8090e-03 eta 0:30:05
epoch [16/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.3790 (0.7433) lr 1.8090e-03 eta 0:29:48
epoch [16/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.1860 (0.7436) lr 1.8090e-03 eta 0:29:36
epoch [16/50] batch [120/204] time 0.243 (0.252) data 0.000 (0.003) loss 1.5459 (0.7621) lr 1.8090e-03 eta 0:29:28
epoch [16/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.2625 (0.7483) lr 1.8090e-03 eta 0:29:20
epoch [16/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.4380 (0.7494) lr 1.8090e-03 eta 0:29:12
epoch [16/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.5025 (0.7508) lr 1.8090e-03 eta 0:29:05
epoch [16/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.3201 (0.7250) lr 1.8090e-03 eta 0:28:58
epoch [17/50] batch [20/204] time 0.245 (0.267) data 0.000 (0.018) loss 0.5506 (0.6209) lr 1.7705e-03 eta 0:30:43
epoch [17/50] batch [40/204] time 0.245 (0.258) data 0.000 (0.009) loss 0.5613 (0.6414) lr 1.7705e-03 eta 0:29:38
epoch [17/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 2.7615 (0.6680) lr 1.7705e-03 eta 0:29:11
epoch [17/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.004) loss 1.1380 (0.6651) lr 1.7705e-03 eta 0:28:55
epoch [17/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.2852 (0.7111) lr 1.7705e-03 eta 0:28:45
epoch [17/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.4295 (0.7125) lr 1.7705e-03 eta 0:28:35
epoch [17/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.9742 (0.7198) lr 1.7705e-03 eta 0:28:28
epoch [17/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.5322 (0.7031) lr 1.7705e-03 eta 0:28:20
epoch [17/50] batch [180/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.3283 (0.6840) lr 1.7705e-03 eta 0:28:13
epoch [17/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.7130 (0.6922) lr 1.7705e-03 eta 0:28:06
epoch [18/50] batch [20/204] time 0.252 (0.267) data 0.000 (0.018) loss 0.8850 (0.7119) lr 1.7290e-03 eta 0:29:52
epoch [18/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 1.1470 (0.7581) lr 1.7290e-03 eta 0:28:46
epoch [18/50] batch [60/204] time 0.252 (0.255) data 0.000 (0.006) loss 0.9640 (0.7411) lr 1.7290e-03 eta 0:28:22
epoch [18/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.005) loss 0.9211 (0.7310) lr 1.7290e-03 eta 0:28:07
epoch [18/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.9199 (0.7198) lr 1.7290e-03 eta 0:27:57
epoch [18/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.9794 (0.7185) lr 1.7290e-03 eta 0:27:46
epoch [18/50] batch [140/204] time 0.248 (0.252) data 0.000 (0.003) loss 2.0378 (0.7201) lr 1.7290e-03 eta 0:27:38
epoch [18/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.3048 (0.7082) lr 1.7290e-03 eta 0:27:30
epoch [18/50] batch [180/204] time 0.243 (0.251) data 0.000 (0.002) loss 0.4508 (0.7048) lr 1.7290e-03 eta 0:27:23
epoch [18/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.2711 (0.7005) lr 1.7290e-03 eta 0:27:16
epoch [19/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.019) loss 0.2881 (0.7342) lr 1.6845e-03 eta 0:28:58
epoch [19/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 1.3835 (0.6893) lr 1.6845e-03 eta 0:27:50
epoch [19/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.1458 (0.6773) lr 1.6845e-03 eta 0:27:25
epoch [19/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.0626 (0.6552) lr 1.6845e-03 eta 0:27:10
epoch [19/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.1481 (0.6793) lr 1.6845e-03 eta 0:27:00
epoch [19/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.5759 (0.6753) lr 1.6845e-03 eta 0:26:50
epoch [19/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.3443 (0.6637) lr 1.6845e-03 eta 0:26:42
epoch [19/50] batch [160/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.3939 (0.6495) lr 1.6845e-03 eta 0:26:35
epoch [19/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.1501 (0.6363) lr 1.6845e-03 eta 0:26:28
epoch [19/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.3069 (0.6454) lr 1.6845e-03 eta 0:26:22
epoch [20/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 1.8210 (0.7099) lr 1.6374e-03 eta 0:27:58
epoch [20/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.1741 (0.6594) lr 1.6374e-03 eta 0:26:58
epoch [20/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.5211 (0.6115) lr 1.6374e-03 eta 0:26:34
epoch [20/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 1.7044 (0.6634) lr 1.6374e-03 eta 0:26:19
epoch [20/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.6955 (0.6236) lr 1.6374e-03 eta 0:26:09
epoch [20/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.4386 (0.6178) lr 1.6374e-03 eta 0:26:00
epoch [20/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1197 (0.6421) lr 1.6374e-03 eta 0:25:53
epoch [20/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.7049 (0.6189) lr 1.6374e-03 eta 0:25:46
epoch [20/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.8691 (0.6065) lr 1.6374e-03 eta 0:25:39
epoch [20/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 1.7092 (0.6295) lr 1.6374e-03 eta 0:25:32
epoch [21/50] batch [20/204] time 0.250 (0.268) data 0.000 (0.018) loss 1.3870 (0.5969) lr 1.5878e-03 eta 0:27:11
epoch [21/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 0.8013 (0.6358) lr 1.5878e-03 eta 0:26:07
epoch [21/50] batch [60/204] time 0.247 (0.254) data 0.000 (0.006) loss 0.3636 (0.6747) lr 1.5878e-03 eta 0:25:42
epoch [21/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.3942 (0.6495) lr 1.5878e-03 eta 0:25:29
epoch [21/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 2.2267 (0.7008) lr 1.5878e-03 eta 0:25:18
epoch [21/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.5946 (0.6916) lr 1.5878e-03 eta 0:25:10
epoch [21/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.4677 (0.6763) lr 1.5878e-03 eta 0:25:03
epoch [21/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.1373 (0.6604) lr 1.5878e-03 eta 0:24:56
epoch [21/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.3012 (0.6441) lr 1.5878e-03 eta 0:24:49
epoch [21/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.4323 (0.6305) lr 1.5878e-03 eta 0:24:42
epoch [22/50] batch [20/204] time 0.248 (0.267) data 0.000 (0.018) loss 0.2084 (0.6157) lr 1.5358e-03 eta 0:26:12
epoch [22/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.0139 (0.7218) lr 1.5358e-03 eta 0:25:15
epoch [22/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.0697 (0.7007) lr 1.5358e-03 eta 0:24:53
epoch [22/50] batch [80/204] time 0.249 (0.254) data 0.000 (0.005) loss 0.1078 (0.6244) lr 1.5358e-03 eta 0:24:39
epoch [22/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.0293 (0.6130) lr 1.5358e-03 eta 0:24:28
epoch [22/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.1924 (0.6025) lr 1.5358e-03 eta 0:24:19
epoch [22/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.3033 (0.6099) lr 1.5358e-03 eta 0:24:11
epoch [22/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1606 (0.5975) lr 1.5358e-03 eta 0:24:04
epoch [22/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 1.7798 (0.6030) lr 1.5358e-03 eta 0:23:57
epoch [22/50] batch [200/204] time 0.243 (0.250) data 0.000 (0.002) loss 1.0946 (0.5942) lr 1.5358e-03 eta 0:23:51
epoch [23/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 0.0677 (0.5942) lr 1.4818e-03 eta 0:25:12
epoch [23/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.2383 (0.5870) lr 1.4818e-03 eta 0:24:17
epoch [23/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.5493 (0.6068) lr 1.4818e-03 eta 0:23:55
epoch [23/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.0863 (0.5953) lr 1.4818e-03 eta 0:23:42
epoch [23/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.5542 (0.6118) lr 1.4818e-03 eta 0:23:33
epoch [23/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.2833 (0.5848) lr 1.4818e-03 eta 0:23:25
epoch [23/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.2914 (0.5862) lr 1.4818e-03 eta 0:23:18
epoch [23/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.0158 (0.5881) lr 1.4818e-03 eta 0:23:11
epoch [23/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.9744 (0.5939) lr 1.4818e-03 eta 0:23:05
epoch [23/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 1.6887 (0.6027) lr 1.4818e-03 eta 0:22:59
epoch [24/50] batch [20/204] time 0.246 (0.267) data 0.000 (0.018) loss 1.2651 (0.5907) lr 1.4258e-03 eta 0:24:24
epoch [24/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.1092 (0.5161) lr 1.4258e-03 eta 0:23:29
epoch [24/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.2498 (0.5095) lr 1.4258e-03 eta 0:23:06
epoch [24/50] batch [80/204] time 0.252 (0.253) data 0.000 (0.005) loss 0.1801 (0.5477) lr 1.4258e-03 eta 0:22:52
epoch [24/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.6370 (0.5568) lr 1.4258e-03 eta 0:22:43
epoch [24/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.0581 (0.5833) lr 1.4258e-03 eta 0:22:35
epoch [24/50] batch [140/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.6575 (0.6018) lr 1.4258e-03 eta 0:22:27
epoch [24/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 2.1151 (0.6168) lr 1.4258e-03 eta 0:22:20
epoch [24/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.4271 (0.6193) lr 1.4258e-03 eta 0:22:14
epoch [24/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.2650 (0.6122) lr 1.4258e-03 eta 0:22:07
epoch [25/50] batch [20/204] time 0.248 (0.267) data 0.000 (0.018) loss 0.9484 (0.4684) lr 1.3681e-03 eta 0:23:28
epoch [25/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.1477 (0.5079) lr 1.3681e-03 eta 0:22:34
epoch [25/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.6013 (0.4934) lr 1.3681e-03 eta 0:22:12
epoch [25/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.2062 (0.5596) lr 1.3681e-03 eta 0:22:00
epoch [25/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.5709 (0.5756) lr 1.3681e-03 eta 0:21:51
epoch [25/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.2061 (0.5616) lr 1.3681e-03 eta 0:21:43
epoch [25/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 2.0438 (0.5700) lr 1.3681e-03 eta 0:21:35
epoch [25/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 1.0609 (0.5623) lr 1.3681e-03 eta 0:21:29
epoch [25/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.5455 (0.5609) lr 1.3681e-03 eta 0:21:23
epoch [25/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.1791 (0.5615) lr 1.3681e-03 eta 0:21:16
epoch [26/50] batch [20/204] time 0.246 (0.267) data 0.000 (0.019) loss 0.9615 (0.6548) lr 1.3090e-03 eta 0:22:36
epoch [26/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.4441 (0.7175) lr 1.3090e-03 eta 0:21:44
epoch [26/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.3384 (0.6539) lr 1.3090e-03 eta 0:21:23
epoch [26/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 1.4325 (0.6139) lr 1.3090e-03 eta 0:21:11
epoch [26/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.4585 (0.5933) lr 1.3090e-03 eta 0:21:01
epoch [26/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.6326 (0.6075) lr 1.3090e-03 eta 0:20:53
epoch [26/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.9248 (0.6057) lr 1.3090e-03 eta 0:20:46
epoch [26/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.6576 (0.6014) lr 1.3090e-03 eta 0:20:39
epoch [26/50] batch [180/204] time 0.242 (0.251) data 0.000 (0.002) loss 0.5273 (0.6127) lr 1.3090e-03 eta 0:20:33
epoch [26/50] batch [200/204] time 0.242 (0.250) data 0.000 (0.002) loss 0.2097 (0.6057) lr 1.3090e-03 eta 0:20:26
epoch [27/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.018) loss 0.2144 (0.6045) lr 1.2487e-03 eta 0:21:36
epoch [27/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.5784 (0.5410) lr 1.2487e-03 eta 0:20:50
epoch [27/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 1.7165 (0.5439) lr 1.2487e-03 eta 0:20:31
epoch [27/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.9108 (0.5755) lr 1.2487e-03 eta 0:20:17
epoch [27/50] batch [100/204] time 0.242 (0.252) data 0.000 (0.004) loss 0.0306 (0.5386) lr 1.2487e-03 eta 0:20:08
epoch [27/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.1696 (0.5299) lr 1.2487e-03 eta 0:20:00
epoch [27/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.2480 (0.5405) lr 1.2487e-03 eta 0:19:53
epoch [27/50] batch [160/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.4235 (0.5366) lr 1.2487e-03 eta 0:19:46
epoch [27/50] batch [180/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.4708 (0.5203) lr 1.2487e-03 eta 0:19:40
epoch [27/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.4545 (0.5267) lr 1.2487e-03 eta 0:19:34
epoch [28/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.018) loss 0.4901 (0.4842) lr 1.1874e-03 eta 0:20:44
epoch [28/50] batch [40/204] time 0.245 (0.257) data 0.000 (0.009) loss 0.1896 (0.5402) lr 1.1874e-03 eta 0:19:56
epoch [28/50] batch [60/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.9980 (0.5187) lr 1.1874e-03 eta 0:19:38
epoch [28/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.005) loss 0.0643 (0.5458) lr 1.1874e-03 eta 0:19:27
epoch [28/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.8879 (0.5413) lr 1.1874e-03 eta 0:19:18
epoch [28/50] batch [120/204] time 0.243 (0.252) data 0.000 (0.003) loss 0.5478 (0.5355) lr 1.1874e-03 eta 0:19:10
epoch [28/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1272 (0.5179) lr 1.1874e-03 eta 0:19:03
epoch [28/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.3525 (0.5225) lr 1.1874e-03 eta 0:18:56
epoch [28/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.0342 (0.5036) lr 1.1874e-03 eta 0:18:51
epoch [28/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.8691 (0.5018) lr 1.1874e-03 eta 0:18:45
epoch [29/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 1.3848 (0.5890) lr 1.1253e-03 eta 0:19:49
epoch [29/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 2.0102 (0.6121) lr 1.1253e-03 eta 0:19:05
epoch [29/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.1762 (0.5758) lr 1.1253e-03 eta 0:18:47
epoch [29/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 1.1110 (0.5441) lr 1.1253e-03 eta 0:18:34
epoch [29/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.4684 (0.5343) lr 1.1253e-03 eta 0:18:25
epoch [29/50] batch [120/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.2300 (0.5380) lr 1.1253e-03 eta 0:18:18
epoch [29/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.2886 (0.5517) lr 1.1253e-03 eta 0:18:11
epoch [29/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.0605 (0.5478) lr 1.1253e-03 eta 0:18:04
epoch [29/50] batch [180/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.5481 (0.5727) lr 1.1253e-03 eta 0:17:58
epoch [29/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.9572 (0.5663) lr 1.1253e-03 eta 0:17:52
epoch [30/50] batch [20/204] time 0.251 (0.268) data 0.000 (0.018) loss 0.3049 (0.4507) lr 1.0628e-03 eta 0:19:01
epoch [30/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.4014 (0.4836) lr 1.0628e-03 eta 0:18:15
epoch [30/50] batch [60/204] time 0.252 (0.255) data 0.001 (0.006) loss 0.2099 (0.5433) lr 1.0628e-03 eta 0:17:57
epoch [30/50] batch [80/204] time 0.243 (0.254) data 0.000 (0.005) loss 1.2342 (0.5370) lr 1.0628e-03 eta 0:17:46
epoch [30/50] batch [100/204] time 0.255 (0.252) data 0.000 (0.004) loss 1.2701 (0.5148) lr 1.0628e-03 eta 0:17:36
epoch [30/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.9882 (0.5283) lr 1.0628e-03 eta 0:17:28
epoch [30/50] batch [140/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.3017 (0.5300) lr 1.0628e-03 eta 0:17:21
epoch [30/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 1.0735 (0.5290) lr 1.0628e-03 eta 0:17:15
epoch [30/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.5849 (0.5270) lr 1.0628e-03 eta 0:17:08
epoch [30/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.2848 (0.5147) lr 1.0628e-03 eta 0:17:02
epoch [31/50] batch [20/204] time 0.245 (0.267) data 0.000 (0.018) loss 0.0622 (0.4652) lr 1.0000e-03 eta 0:18:04
epoch [31/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.9593 (0.5749) lr 1.0000e-03 eta 0:17:21
epoch [31/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.1973 (0.5573) lr 1.0000e-03 eta 0:17:03
epoch [31/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.1891 (0.5333) lr 1.0000e-03 eta 0:16:52
epoch [31/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.5849 (0.5079) lr 1.0000e-03 eta 0:16:44
epoch [31/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.0480 (0.4934) lr 1.0000e-03 eta 0:16:37
epoch [31/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.3250 (0.4772) lr 1.0000e-03 eta 0:16:30
epoch [31/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 1.7845 (0.4728) lr 1.0000e-03 eta 0:16:24
epoch [31/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.2855 (0.4731) lr 1.0000e-03 eta 0:16:18
epoch [31/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.5396 (0.4909) lr 1.0000e-03 eta 0:16:12
epoch [32/50] batch [20/204] time 0.250 (0.267) data 0.000 (0.018) loss 0.2418 (0.4464) lr 9.3721e-04 eta 0:17:08
epoch [32/50] batch [40/204] time 0.245 (0.258) data 0.000 (0.009) loss 0.4946 (0.4536) lr 9.3721e-04 eta 0:16:28
epoch [32/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.0781 (0.4708) lr 9.3721e-04 eta 0:16:11
epoch [32/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.3091 (0.4650) lr 9.3721e-04 eta 0:16:00
epoch [32/50] batch [100/204] time 0.241 (0.252) data 0.000 (0.004) loss 0.0567 (0.4582) lr 9.3721e-04 eta 0:15:51
epoch [32/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.0931 (0.4388) lr 9.3721e-04 eta 0:15:44
epoch [32/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.2862 (0.4400) lr 9.3721e-04 eta 0:15:37
epoch [32/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.1913 (0.4382) lr 9.3721e-04 eta 0:15:31
epoch [32/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.4971 (0.4501) lr 9.3721e-04 eta 0:15:25
epoch [32/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.8916 (0.4565) lr 9.3721e-04 eta 0:15:19
epoch [33/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.019) loss 0.1329 (0.5085) lr 8.7467e-04 eta 0:16:16
epoch [33/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.2301 (0.4247) lr 8.7467e-04 eta 0:15:37
epoch [33/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 1.3530 (0.4447) lr 8.7467e-04 eta 0:15:20
epoch [33/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.2459 (0.4670) lr 8.7467e-04 eta 0:15:09
epoch [33/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.5851 (0.4755) lr 8.7467e-04 eta 0:15:01
epoch [33/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.5215 (0.4818) lr 8.7467e-04 eta 0:14:54
epoch [33/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3642 (0.4684) lr 8.7467e-04 eta 0:14:47
epoch [33/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.1231 (0.4808) lr 8.7467e-04 eta 0:14:41
epoch [33/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1157 (0.4745) lr 8.7467e-04 eta 0:14:35
epoch [33/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 1.4441 (0.4933) lr 8.7467e-04 eta 0:14:29
epoch [34/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 1.1347 (0.6303) lr 8.1262e-04 eta 0:15:20
epoch [34/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.2327 (0.5900) lr 8.1262e-04 eta 0:14:43
epoch [34/50] batch [60/204] time 0.243 (0.255) data 0.000 (0.006) loss 0.0429 (0.5274) lr 8.1262e-04 eta 0:14:28
epoch [34/50] batch [80/204] time 0.252 (0.253) data 0.000 (0.005) loss 0.1954 (0.5125) lr 8.1262e-04 eta 0:14:17
epoch [34/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.9426 (0.4677) lr 8.1262e-04 eta 0:14:09
epoch [34/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.6240 (0.4919) lr 8.1262e-04 eta 0:14:02
epoch [34/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 3.1784 (0.5231) lr 8.1262e-04 eta 0:13:56
epoch [34/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.6552 (0.5186) lr 8.1262e-04 eta 0:13:50
epoch [34/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.3857 (0.5187) lr 8.1262e-04 eta 0:13:44
epoch [34/50] batch [200/204] time 0.242 (0.251) data 0.000 (0.002) loss 0.3504 (0.5049) lr 8.1262e-04 eta 0:13:38
epoch [35/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 0.3051 (0.2168) lr 7.5131e-04 eta 0:14:25
epoch [35/50] batch [40/204] time 0.243 (0.258) data 0.000 (0.009) loss 0.6239 (0.4272) lr 7.5131e-04 eta 0:13:50
epoch [35/50] batch [60/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.2623 (0.3857) lr 7.5131e-04 eta 0:13:35
epoch [35/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.3543 (0.4183) lr 7.5131e-04 eta 0:13:25
epoch [35/50] batch [100/204] time 0.242 (0.252) data 0.000 (0.004) loss 0.1163 (0.3976) lr 7.5131e-04 eta 0:13:17
epoch [35/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.9094 (0.4137) lr 7.5131e-04 eta 0:13:10
epoch [35/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.4615 (0.4343) lr 7.5131e-04 eta 0:13:04
epoch [35/50] batch [160/204] time 0.247 (0.251) data 0.000 (0.002) loss 1.6360 (0.4373) lr 7.5131e-04 eta 0:12:58
epoch [35/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.1313 (0.4463) lr 7.5131e-04 eta 0:12:52
epoch [35/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.9452 (0.4591) lr 7.5131e-04 eta 0:12:46
epoch [36/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 0.2817 (0.6544) lr 6.9098e-04 eta 0:13:30
epoch [36/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.7010 (0.5700) lr 6.9098e-04 eta 0:12:57
epoch [36/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.1945 (0.4997) lr 6.9098e-04 eta 0:12:43
epoch [36/50] batch [80/204] time 0.244 (0.253) data 0.000 (0.005) loss 0.3224 (0.4806) lr 6.9098e-04 eta 0:12:33
epoch [36/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.5723 (0.4920) lr 6.9098e-04 eta 0:12:25
epoch [36/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.2826 (0.4937) lr 6.9098e-04 eta 0:12:19
epoch [36/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.0503 (0.4733) lr 6.9098e-04 eta 0:12:13
epoch [36/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.0392 (0.4774) lr 6.9098e-04 eta 0:12:07
epoch [36/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.6373 (0.4886) lr 6.9098e-04 eta 0:12:01
epoch [36/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.4471 (0.4666) lr 6.9098e-04 eta 0:11:55
epoch [37/50] batch [20/204] time 0.250 (0.266) data 0.000 (0.018) loss 0.1966 (0.4154) lr 6.3188e-04 eta 0:12:35
epoch [37/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.1743 (0.3512) lr 6.3188e-04 eta 0:12:03
epoch [37/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.2579 (0.3828) lr 6.3188e-04 eta 0:11:50
epoch [37/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.1744 (0.4241) lr 6.3188e-04 eta 0:11:40
epoch [37/50] batch [100/204] time 0.245 (0.251) data 0.000 (0.004) loss 0.4907 (0.4314) lr 6.3188e-04 eta 0:11:32
epoch [37/50] batch [120/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.2225 (0.4378) lr 6.3188e-04 eta 0:11:26
epoch [37/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.1582 (0.4318) lr 6.3188e-04 eta 0:11:20
epoch [37/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.3082 (0.4653) lr 6.3188e-04 eta 0:11:14
epoch [37/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.8935 (0.4676) lr 6.3188e-04 eta 0:11:09
epoch [37/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.4525 (0.4516) lr 6.3188e-04 eta 0:11:03
epoch [38/50] batch [20/204] time 0.246 (0.267) data 0.000 (0.018) loss 0.8037 (0.4141) lr 5.7422e-04 eta 0:11:42
epoch [38/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.9276 (0.4979) lr 5.7422e-04 eta 0:11:12
epoch [38/50] batch [60/204] time 0.246 (0.255) data 0.000 (0.006) loss 0.6996 (0.4569) lr 5.7422e-04 eta 0:11:00
epoch [38/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.5506 (0.5057) lr 5.7422e-04 eta 0:10:50
epoch [38/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.8713 (0.4933) lr 5.7422e-04 eta 0:10:43
epoch [38/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.3597 (0.4818) lr 5.7422e-04 eta 0:10:37
epoch [38/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0763 (0.4741) lr 5.7422e-04 eta 0:10:31
epoch [38/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.1253 (0.5018) lr 5.7422e-04 eta 0:10:25
epoch [38/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.0601 (0.4921) lr 5.7422e-04 eta 0:10:19
epoch [38/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.7203 (0.5000) lr 5.7422e-04 eta 0:10:13
epoch [39/50] batch [20/204] time 0.250 (0.266) data 0.000 (0.018) loss 0.7950 (0.5189) lr 5.1825e-04 eta 0:10:47
epoch [39/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.1209 (0.4609) lr 5.1825e-04 eta 0:10:19
epoch [39/50] batch [60/204] time 0.246 (0.254) data 0.000 (0.006) loss 1.0599 (0.4366) lr 5.1825e-04 eta 0:10:07
epoch [39/50] batch [80/204] time 0.242 (0.253) data 0.000 (0.005) loss 0.9044 (0.4129) lr 5.1825e-04 eta 0:09:58
epoch [39/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.0896 (0.4281) lr 5.1825e-04 eta 0:09:51
epoch [39/50] batch [120/204] time 0.247 (0.251) data 0.000 (0.003) loss 0.0645 (0.4524) lr 5.1825e-04 eta 0:09:44
epoch [39/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.2194 (0.4542) lr 5.1825e-04 eta 0:09:38
epoch [39/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.2162 (0.4450) lr 5.1825e-04 eta 0:09:32
epoch [39/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.6590 (0.4663) lr 5.1825e-04 eta 0:09:27
epoch [39/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.7776 (0.4574) lr 5.1825e-04 eta 0:09:21
epoch [40/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 0.8002 (0.5077) lr 4.6417e-04 eta 0:09:53
epoch [40/50] batch [40/204] time 0.252 (0.258) data 0.000 (0.009) loss 0.3763 (0.4512) lr 4.6417e-04 eta 0:09:28
epoch [40/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 1.2225 (0.4956) lr 4.6417e-04 eta 0:09:16
epoch [40/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.005) loss 0.2310 (0.4670) lr 4.6417e-04 eta 0:09:08
epoch [40/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.3084 (0.4713) lr 4.6417e-04 eta 0:09:01
epoch [40/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.2634 (0.4885) lr 4.6417e-04 eta 0:08:54
epoch [40/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1110 (0.4781) lr 4.6417e-04 eta 0:08:48
epoch [40/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.0195 (0.4758) lr 4.6417e-04 eta 0:08:42
epoch [40/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.0289 (0.4571) lr 4.6417e-04 eta 0:08:36
epoch [40/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.1643 (0.4491) lr 4.6417e-04 eta 0:08:31
epoch [41/50] batch [20/204] time 0.244 (0.267) data 0.000 (0.018) loss 0.5041 (0.3850) lr 4.1221e-04 eta 0:08:58
epoch [41/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.2264 (0.3818) lr 4.1221e-04 eta 0:08:35
epoch [41/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.1345 (0.4454) lr 4.1221e-04 eta 0:08:23
epoch [41/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.1922 (0.3968) lr 4.1221e-04 eta 0:08:15
epoch [41/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.0376 (0.3821) lr 4.1221e-04 eta 0:08:08
epoch [41/50] batch [120/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.5819 (0.3904) lr 4.1221e-04 eta 0:08:02
epoch [41/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1261 (0.3760) lr 4.1221e-04 eta 0:07:56
epoch [41/50] batch [160/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.3124 (0.4005) lr 4.1221e-04 eta 0:07:50
epoch [41/50] batch [180/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.0385 (0.3942) lr 4.1221e-04 eta 0:07:45
epoch [41/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 1.0364 (0.3933) lr 4.1221e-04 eta 0:07:39
epoch [42/50] batch [20/204] time 0.245 (0.266) data 0.000 (0.018) loss 0.6553 (0.4252) lr 3.6258e-04 eta 0:08:02
epoch [42/50] batch [40/204] time 0.243 (0.257) data 0.000 (0.009) loss 0.3270 (0.3636) lr 3.6258e-04 eta 0:07:41
epoch [42/50] batch [60/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.4728 (0.4359) lr 3.6258e-04 eta 0:07:31
epoch [42/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.0293 (0.4040) lr 3.6258e-04 eta 0:07:23
epoch [42/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.7337 (0.4204) lr 3.6258e-04 eta 0:07:17
epoch [42/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.2840 (0.4173) lr 3.6258e-04 eta 0:07:11
epoch [42/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.0300 (0.4141) lr 3.6258e-04 eta 0:07:05
epoch [42/50] batch [160/204] time 0.253 (0.251) data 0.000 (0.002) loss 0.2966 (0.4248) lr 3.6258e-04 eta 0:06:59
epoch [42/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.2546 (0.4129) lr 3.6258e-04 eta 0:06:54
epoch [42/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.2109 (0.4172) lr 3.6258e-04 eta 0:06:49
epoch [43/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 0.1792 (0.4625) lr 3.1545e-04 eta 0:07:09
epoch [43/50] batch [40/204] time 0.245 (0.257) data 0.000 (0.009) loss 0.6289 (0.4815) lr 3.1545e-04 eta 0:06:49
epoch [43/50] batch [60/204] time 0.248 (0.255) data 0.000 (0.006) loss 1.4839 (0.5137) lr 3.1545e-04 eta 0:06:40
epoch [43/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.005) loss 0.0977 (0.4731) lr 3.1545e-04 eta 0:06:32
epoch [43/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.1122 (0.4770) lr 3.1545e-04 eta 0:06:26
epoch [43/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.2468 (0.4909) lr 3.1545e-04 eta 0:06:20
epoch [43/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.5068 (0.4877) lr 3.1545e-04 eta 0:06:14
epoch [43/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.2653 (0.4823) lr 3.1545e-04 eta 0:06:08
epoch [43/50] batch [180/204] time 0.246 (0.250) data 0.000 (0.002) loss 0.0594 (0.4655) lr 3.1545e-04 eta 0:06:03
epoch [43/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.7888 (0.4640) lr 3.1545e-04 eta 0:05:58
epoch [44/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 0.2209 (0.3398) lr 2.7103e-04 eta 0:06:15
epoch [44/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.1027 (0.4039) lr 2.7103e-04 eta 0:05:57
epoch [44/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.1018 (0.3867) lr 2.7103e-04 eta 0:05:47
epoch [44/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.005) loss 2.0727 (0.4121) lr 2.7103e-04 eta 0:05:40
epoch [44/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.9259 (0.4397) lr 2.7103e-04 eta 0:05:34
epoch [44/50] batch [120/204] time 0.244 (0.251) data 0.000 (0.003) loss 0.1361 (0.4412) lr 2.7103e-04 eta 0:05:28
epoch [44/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.2256 (0.4410) lr 2.7103e-04 eta 0:05:23
epoch [44/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.8120 (0.4551) lr 2.7103e-04 eta 0:05:18
epoch [44/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.6804 (0.4681) lr 2.7103e-04 eta 0:05:12
epoch [44/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.1280 (0.4405) lr 2.7103e-04 eta 0:05:07
epoch [45/50] batch [20/204] time 0.251 (0.268) data 0.000 (0.018) loss 0.3213 (0.4273) lr 2.2949e-04 eta 0:05:22
epoch [45/50] batch [40/204] time 0.252 (0.258) data 0.000 (0.009) loss 0.5666 (0.4329) lr 2.2949e-04 eta 0:05:05
epoch [45/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.0299 (0.5253) lr 2.2949e-04 eta 0:04:57
epoch [45/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.0805 (0.4764) lr 2.2949e-04 eta 0:04:49
epoch [45/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.004) loss 0.1184 (0.4813) lr 2.2949e-04 eta 0:04:43
epoch [45/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.2332 (0.4542) lr 2.2949e-04 eta 0:04:38
epoch [45/50] batch [140/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.1025 (0.4371) lr 2.2949e-04 eta 0:04:32
epoch [45/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.3150 (0.4413) lr 2.2949e-04 eta 0:04:27
epoch [45/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.0326 (0.4303) lr 2.2949e-04 eta 0:04:22
epoch [45/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 1.0151 (0.4216) lr 2.2949e-04 eta 0:04:16
epoch [46/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 3.1221 (0.6166) lr 1.9098e-04 eta 0:04:27
epoch [46/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.0895 (0.5102) lr 1.9098e-04 eta 0:04:12
epoch [46/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.3567 (0.4371) lr 1.9098e-04 eta 0:04:04
epoch [46/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.5325 (0.4246) lr 1.9098e-04 eta 0:03:58
epoch [46/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.4692 (0.4043) lr 1.9098e-04 eta 0:03:52
epoch [46/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.5104 (0.4109) lr 1.9098e-04 eta 0:03:46
epoch [46/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.3823 (0.4168) lr 1.9098e-04 eta 0:03:41
epoch [46/50] batch [160/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.0521 (0.3942) lr 1.9098e-04 eta 0:03:35
epoch [46/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1510 (0.3932) lr 1.9098e-04 eta 0:03:30
epoch [46/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.1189 (0.3820) lr 1.9098e-04 eta 0:03:25
epoch [47/50] batch [20/204] time 0.249 (0.267) data 0.000 (0.018) loss 0.0744 (0.3473) lr 1.5567e-04 eta 0:03:32
epoch [47/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.4641 (0.4421) lr 1.5567e-04 eta 0:03:20
epoch [47/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.3041 (0.4035) lr 1.5567e-04 eta 0:03:12
epoch [47/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.3290 (0.4336) lr 1.5567e-04 eta 0:03:06
epoch [47/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.4349 (0.4481) lr 1.5567e-04 eta 0:03:00
epoch [47/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.3009 (0.4383) lr 1.5567e-04 eta 0:02:55
epoch [47/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4402 (0.4451) lr 1.5567e-04 eta 0:02:49
epoch [47/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1523 (0.4422) lr 1.5567e-04 eta 0:02:44
epoch [47/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.0245 (0.4316) lr 1.5567e-04 eta 0:02:39
epoch [47/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.2995 (0.4368) lr 1.5567e-04 eta 0:02:34
epoch [48/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.018) loss 0.8814 (0.6123) lr 1.2369e-04 eta 0:02:37
epoch [48/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.0912 (0.4985) lr 1.2369e-04 eta 0:02:26
epoch [48/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.0469 (0.4521) lr 1.2369e-04 eta 0:02:20
epoch [48/50] batch [80/204] time 0.251 (0.252) data 0.000 (0.005) loss 0.1367 (0.4467) lr 1.2369e-04 eta 0:02:14
epoch [48/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.0346 (0.3902) lr 1.2369e-04 eta 0:02:08
epoch [48/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.9371 (0.3799) lr 1.2369e-04 eta 0:02:03
epoch [48/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.8319 (0.3749) lr 1.2369e-04 eta 0:01:58
epoch [48/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.4754 (0.3823) lr 1.2369e-04 eta 0:01:53
epoch [48/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.1905 (0.3774) lr 1.2369e-04 eta 0:01:48
epoch [48/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.4016 (0.3894) lr 1.2369e-04 eta 0:01:43
epoch [49/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.018) loss 0.5560 (0.4071) lr 9.5173e-05 eta 0:01:43
epoch [49/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.4719 (0.4563) lr 9.5173e-05 eta 0:01:34
epoch [49/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 0.5608 (0.4304) lr 9.5173e-05 eta 0:01:28
epoch [49/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.5650 (0.4443) lr 9.5173e-05 eta 0:01:23
epoch [49/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.1590 (0.4393) lr 9.5173e-05 eta 0:01:17
epoch [49/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.003) loss 1.3647 (0.4495) lr 9.5173e-05 eta 0:01:12
epoch [49/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.5008 (0.4376) lr 9.5173e-05 eta 0:01:07
epoch [49/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.4110 (0.4410) lr 9.5173e-05 eta 0:01:02
epoch [49/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.7082 (0.4330) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.0631 (0.4371) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.248 (0.267) data 0.000 (0.019) loss 0.5289 (0.3902) lr 7.0224e-05 eta 0:00:49
epoch [50/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.5335 (0.4191) lr 7.0224e-05 eta 0:00:42
epoch [50/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.9959 (0.4279) lr 7.0224e-05 eta 0:00:36
epoch [50/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.5383 (0.4415) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.3491 (0.4371) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.3473 (0.4385) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.4355 (0.4430) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.3132 (0.4392) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.3368 (0.4380) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.0392 (0.4478) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/oxford_flowers/vit_b16_ep50_c4_BZ4_ProDA/seed3/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 1,241
* correct: 1,205
* accuracy: 97.10%
* error: 2.90%
* macro_f1: 96.85%
Elapsed: 0:43:21
