***************
** 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/seed1
resume: 
root: /mnt/hdd/DATA
seed: 1
source_domains: None
target_domains: None
trainer: ProDA
transforms: None
************
** Config **
************
DATALOADER:
  K_TRANSFORMS: 1
  NUM_WORKERS: 8
  RETURN_IMG0: False
  TEST:
    BATCH_SIZE: 100
    SAMPLER: SequentialSampler
  TRAIN_U:
    BATCH_SIZE: 32
    N_DOMAIN: 0
    N_INS: 16
    SAME_AS_X: True
    SAMPLER: RandomSampler
  TRAIN_X:
    BATCH_SIZE: 4
    N_DOMAIN: 0
    N_INS: 16
    SAMPLER: RandomSampler
DATASET:
  ALL_AS_UNLABELED: False
  CIFAR_C_LEVEL: 1
  CIFAR_C_TYPE: 
  NAME: 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/seed1
RESUME: 
SEED: 1
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ProDA
  ProDA:
    N_CTX: 4
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

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

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

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

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

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

Loading trainer: ProDA
Loading dataset: 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_1.pkl
SUBSAMPLE BASE CLASSES!
Building transform_train
+ random resized crop (size=(224, 224), scale=(0.08, 1.0))
+ random flip
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
Building transform_test
+ resize the smaller edge to 224
+ 224x224 center crop
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
---------  -------------
Dataset    OxfordFlowers
# classes  51
# train_x  816
# val      204
# test     1,225
---------  -------------
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/seed1/tensorboard)
epoch [1/50] batch [20/204] time 0.243 (0.378) data 0.000 (0.027) loss 0.8480 (2.5613) lr 1.0000e-05 eta 1:04:04
epoch [1/50] batch [40/204] time 0.249 (0.312) data 0.000 (0.014) loss 3.4214 (2.5734) lr 1.0000e-05 eta 0:52:48
epoch [1/50] batch [60/204] time 0.243 (0.290) data 0.000 (0.009) loss 1.5894 (2.4017) lr 1.0000e-05 eta 0:49:04
epoch [1/50] batch [80/204] time 0.244 (0.279) data 0.000 (0.007) loss 1.2733 (2.4633) lr 1.0000e-05 eta 0:47:08
epoch [1/50] batch [100/204] time 0.250 (0.273) data 0.000 (0.006) loss 2.6366 (2.5409) lr 1.0000e-05 eta 0:45:58
epoch [1/50] batch [120/204] time 0.249 (0.269) data 0.000 (0.005) loss 2.2644 (2.4639) lr 1.0000e-05 eta 0:45:09
epoch [1/50] batch [140/204] time 0.245 (0.266) data 0.000 (0.004) loss 4.1806 (2.4036) lr 1.0000e-05 eta 0:44:31
epoch [1/50] batch [160/204] time 0.246 (0.263) data 0.000 (0.004) loss 1.3863 (2.3059) lr 1.0000e-05 eta 0:44:03
epoch [1/50] batch [180/204] time 0.243 (0.262) data 0.000 (0.003) loss 2.6742 (2.3063) lr 1.0000e-05 eta 0:43:40
epoch [1/50] batch [200/204] time 0.251 (0.260) data 0.000 (0.003) loss 1.9736 (2.3114) lr 1.0000e-05 eta 0:43:20
epoch [2/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.022) loss 1.1894 (1.9228) lr 1.0000e-05 eta 0:44:53
epoch [2/50] batch [40/204] time 0.258 (0.259) data 0.007 (0.011) loss 2.5009 (1.7885) lr 1.0000e-05 eta 0:42:59
epoch [2/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.008) loss 1.2144 (1.7555) lr 1.0000e-05 eta 0:42:14
epoch [2/50] batch [80/204] time 0.244 (0.253) data 0.000 (0.006) loss 3.1653 (1.8932) lr 1.0000e-05 eta 0:41:51
epoch [2/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.005) loss 0.3386 (1.9879) lr 1.0000e-05 eta 0:41:35
epoch [2/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.004) loss 4.8200 (1.9899) lr 1.0000e-05 eta 0:41:23
epoch [2/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 4.8694 (1.9877) lr 1.0000e-05 eta 0:41:13
epoch [2/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.9010 (2.0160) lr 1.0000e-05 eta 0:41:04
epoch [2/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.003) loss 4.4627 (2.0026) lr 1.0000e-05 eta 0:40:57
epoch [2/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 1.3115 (1.9568) lr 1.0000e-05 eta 0:40:49
epoch [3/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 2.1796 (1.7154) lr 1.0000e-05 eta 0:44:08
epoch [3/50] batch [40/204] time 0.250 (0.259) data 0.000 (0.011) loss 0.0900 (1.8308) lr 1.0000e-05 eta 0:42:08
epoch [3/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 6.1648 (1.9386) lr 1.0000e-05 eta 0:41:28
epoch [3/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.006) loss 1.0052 (1.8771) lr 1.0000e-05 eta 0:41:05
epoch [3/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.005) loss 2.5094 (1.8395) lr 1.0000e-05 eta 0:40:50
epoch [3/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 1.3972 (1.8900) lr 1.0000e-05 eta 0:40:37
epoch [3/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 2.2947 (1.8682) lr 1.0000e-05 eta 0:40:27
epoch [3/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.003) loss 2.3333 (1.8925) lr 1.0000e-05 eta 0:40:19
epoch [3/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4542 (1.8309) lr 1.0000e-05 eta 0:40:11
epoch [3/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 1.2666 (1.8131) lr 1.0000e-05 eta 0:40:03
epoch [4/50] batch [20/204] time 0.245 (0.271) data 0.000 (0.022) loss 1.1227 (1.9212) lr 1.0000e-05 eta 0:43:12
epoch [4/50] batch [40/204] time 0.248 (0.259) data 0.000 (0.011) loss 1.9932 (2.0035) lr 1.0000e-05 eta 0:41:17
epoch [4/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.008) loss 2.2057 (2.0407) lr 1.0000e-05 eta 0:40:37
epoch [4/50] batch [80/204] time 0.249 (0.254) data 0.000 (0.006) loss 3.1917 (2.0223) lr 1.0000e-05 eta 0:40:17
epoch [4/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.1094 (1.9466) lr 1.0000e-05 eta 0:40:00
epoch [4/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.7930 (1.9612) lr 1.0000e-05 eta 0:39:48
epoch [4/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.6509 (1.9252) lr 1.0000e-05 eta 0:39:37
epoch [4/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.6744 (1.8439) lr 1.0000e-05 eta 0:39:28
epoch [4/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.003) loss 2.5120 (1.8456) lr 1.0000e-05 eta 0:39:20
epoch [4/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 1.0770 (1.8142) lr 1.0000e-05 eta 0:39:12
epoch [5/50] batch [20/204] time 0.245 (0.271) data 0.000 (0.022) loss 2.6346 (1.4313) lr 1.0000e-05 eta 0:42:14
epoch [5/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 2.4754 (1.6903) lr 1.0000e-05 eta 0:40:24
epoch [5/50] batch [60/204] time 0.254 (0.256) data 0.000 (0.007) loss 2.7024 (1.7347) lr 1.0000e-05 eta 0:39:46
epoch [5/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.006) loss 4.9743 (1.8390) lr 1.0000e-05 eta 0:39:23
epoch [5/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.1570 (1.7714) lr 1.0000e-05 eta 0:39:07
epoch [5/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.4273 (1.7782) lr 1.0000e-05 eta 0:38:55
epoch [5/50] batch [140/204] time 0.250 (0.252) data 0.000 (0.003) loss 1.8104 (1.7422) lr 1.0000e-05 eta 0:38:46
epoch [5/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.2418 (1.7632) lr 1.0000e-05 eta 0:38:38
epoch [5/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.1644 (1.7844) lr 1.0000e-05 eta 0:38:29
epoch [5/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 1.7096 (1.7537) lr 1.0000e-05 eta 0:38:21
epoch [6/50] batch [20/204] time 0.245 (0.271) data 0.000 (0.022) loss 0.6316 (1.7311) lr 2.0000e-03 eta 0:41:22
epoch [6/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 1.2594 (1.6655) lr 2.0000e-03 eta 0:39:36
epoch [6/50] batch [60/204] time 0.246 (0.256) data 0.000 (0.007) loss 2.0515 (1.7134) lr 2.0000e-03 eta 0:38:55
epoch [6/50] batch [80/204] time 0.244 (0.254) data 0.000 (0.006) loss 1.1822 (1.6887) lr 2.0000e-03 eta 0:38:35
epoch [6/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.005) loss 3.3122 (1.6852) lr 2.0000e-03 eta 0:38:19
epoch [6/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 2.8263 (1.6523) lr 2.0000e-03 eta 0:38:06
epoch [6/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 2.2997 (1.6326) lr 2.0000e-03 eta 0:37:57
epoch [6/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.3282 (1.6139) lr 2.0000e-03 eta 0:37:47
epoch [6/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.8754 (1.6362) lr 2.0000e-03 eta 0:37:39
epoch [6/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 2.4492 (1.6215) lr 2.0000e-03 eta 0:37:30
epoch [7/50] batch [20/204] time 0.249 (0.272) data 0.000 (0.022) loss 1.7647 (1.1114) lr 1.9980e-03 eta 0:40:33
epoch [7/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 1.8040 (1.3673) lr 1.9980e-03 eta 0:38:47
epoch [7/50] batch [60/204] time 0.250 (0.257) data 0.000 (0.008) loss 0.1583 (1.3130) lr 1.9980e-03 eta 0:38:08
epoch [7/50] batch [80/204] time 0.247 (0.255) data 0.000 (0.006) loss 1.2529 (1.2929) lr 1.9980e-03 eta 0:37:46
epoch [7/50] batch [100/204] time 0.252 (0.254) data 0.000 (0.005) loss 0.3135 (1.3546) lr 1.9980e-03 eta 0:37:30
epoch [7/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.9868 (1.3553) lr 1.9980e-03 eta 0:37:18
epoch [7/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.4272 (1.3305) lr 1.9980e-03 eta 0:37:08
epoch [7/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.5004 (1.3278) lr 1.9980e-03 eta 0:37:00
epoch [7/50] batch [180/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.6239 (1.3073) lr 1.9980e-03 eta 0:36:52
epoch [7/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.7467 (1.3105) lr 1.9980e-03 eta 0:36:43
epoch [8/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.021) loss 1.6414 (1.5013) lr 1.9921e-03 eta 0:39:23
epoch [8/50] batch [40/204] time 0.248 (0.259) data 0.000 (0.011) loss 3.6912 (1.3724) lr 1.9921e-03 eta 0:37:43
epoch [8/50] batch [60/204] time 0.246 (0.256) data 0.000 (0.007) loss 1.2926 (1.3371) lr 1.9921e-03 eta 0:37:08
epoch [8/50] batch [80/204] time 0.249 (0.254) data 0.000 (0.005) loss 1.0630 (1.3301) lr 1.9921e-03 eta 0:36:48
epoch [8/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.2119 (1.3131) lr 1.9921e-03 eta 0:36:34
epoch [8/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.3283 (1.2508) lr 1.9921e-03 eta 0:36:22
epoch [8/50] batch [140/204] time 0.250 (0.252) data 0.000 (0.003) loss 1.0355 (1.2512) lr 1.9921e-03 eta 0:36:14
epoch [8/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.2875 (1.2518) lr 1.9921e-03 eta 0:36:05
epoch [8/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.5876 (1.2232) lr 1.9921e-03 eta 0:35:57
epoch [8/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 1.3752 (1.2100) lr 1.9921e-03 eta 0:35:49
epoch [9/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.5705 (1.0305) lr 1.9823e-03 eta 0:38:37
epoch [9/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 0.7484 (1.0795) lr 1.9823e-03 eta 0:36:55
epoch [9/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.007) loss 0.2847 (1.1393) lr 1.9823e-03 eta 0:36:19
epoch [9/50] batch [80/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.0571 (1.0669) lr 1.9823e-03 eta 0:35:58
epoch [9/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.2575 (1.0750) lr 1.9823e-03 eta 0:35:44
epoch [9/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.7138 (1.0972) lr 1.9823e-03 eta 0:35:32
epoch [9/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 1.6374 (1.0895) lr 1.9823e-03 eta 0:35:22
epoch [9/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.4747 (1.0783) lr 1.9823e-03 eta 0:35:13
epoch [9/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.4246 (1.1167) lr 1.9823e-03 eta 0:35:05
epoch [9/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.4331 (1.1203) lr 1.9823e-03 eta 0:34:58
epoch [10/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.5393 (1.0519) lr 1.9686e-03 eta 0:37:38
epoch [10/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 0.7110 (1.1074) lr 1.9686e-03 eta 0:36:00
epoch [10/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.6988 (1.0434) lr 1.9686e-03 eta 0:35:27
epoch [10/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.005) loss 0.7503 (1.0828) lr 1.9686e-03 eta 0:35:05
epoch [10/50] batch [100/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.6235 (1.0780) lr 1.9686e-03 eta 0:34:50
epoch [10/50] batch [120/204] time 0.252 (0.252) data 0.000 (0.004) loss 1.6383 (1.0794) lr 1.9686e-03 eta 0:34:39
epoch [10/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.0839 (1.0625) lr 1.9686e-03 eta 0:34:30
epoch [10/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.003) loss 1.3325 (1.0570) lr 1.9686e-03 eta 0:34:22
epoch [10/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.003) loss 1.1088 (1.0650) lr 1.9686e-03 eta 0:34:14
epoch [10/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.1821 (1.0694) lr 1.9686e-03 eta 0:34:06
epoch [11/50] batch [20/204] time 0.250 (0.271) data 0.000 (0.022) loss 0.7321 (0.9693) lr 1.9511e-03 eta 0:36:43
epoch [11/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 1.3991 (0.9821) lr 1.9511e-03 eta 0:35:09
epoch [11/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 2.1175 (0.9960) lr 1.9511e-03 eta 0:34:34
epoch [11/50] batch [80/204] time 0.246 (0.254) data 0.000 (0.006) loss 0.6751 (0.9796) lr 1.9511e-03 eta 0:34:14
epoch [11/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.3960 (0.9971) lr 1.9511e-03 eta 0:34:00
epoch [11/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.7081 (1.0188) lr 1.9511e-03 eta 0:33:48
epoch [11/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 1.0236 (1.0322) lr 1.9511e-03 eta 0:33:39
epoch [11/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.2763 (1.0349) lr 1.9511e-03 eta 0:33:31
epoch [11/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.0368 (1.0093) lr 1.9511e-03 eta 0:33:23
epoch [11/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.9975 (1.0178) lr 1.9511e-03 eta 0:33:16
epoch [12/50] batch [20/204] time 0.249 (0.270) data 0.000 (0.021) loss 0.2982 (0.8200) lr 1.9298e-03 eta 0:35:42
epoch [12/50] batch [40/204] time 0.251 (0.259) data 0.000 (0.011) loss 0.7999 (0.9839) lr 1.9298e-03 eta 0:34:13
epoch [12/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 1.8497 (0.9480) lr 1.9298e-03 eta 0:33:39
epoch [12/50] batch [80/204] time 0.242 (0.254) data 0.000 (0.005) loss 0.9362 (0.9053) lr 1.9298e-03 eta 0:33:18
epoch [12/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.2779 (0.8969) lr 1.9298e-03 eta 0:33:05
epoch [12/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.8138 (0.9379) lr 1.9298e-03 eta 0:32:55
epoch [12/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.4660 (0.9226) lr 1.9298e-03 eta 0:32:46
epoch [12/50] batch [160/204] time 0.242 (0.251) data 0.000 (0.003) loss 0.5993 (0.8857) lr 1.9298e-03 eta 0:32:39
epoch [12/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 1.3120 (0.9086) lr 1.9298e-03 eta 0:32:32
epoch [12/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.7272 (0.9098) lr 1.9298e-03 eta 0:32:24
epoch [13/50] batch [20/204] time 0.248 (0.270) data 0.000 (0.022) loss 0.2591 (0.8840) lr 1.9048e-03 eta 0:34:45
epoch [13/50] batch [40/204] time 0.248 (0.259) data 0.000 (0.011) loss 0.7624 (0.8705) lr 1.9048e-03 eta 0:33:19
epoch [13/50] batch [60/204] time 0.248 (0.255) data 0.000 (0.007) loss 0.1573 (0.9267) lr 1.9048e-03 eta 0:32:45
epoch [13/50] batch [80/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.3130 (0.9472) lr 1.9048e-03 eta 0:32:26
epoch [13/50] batch [100/204] time 0.254 (0.253) data 0.000 (0.004) loss 1.4882 (0.9406) lr 1.9048e-03 eta 0:32:14
epoch [13/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.3749 (0.9026) lr 1.9048e-03 eta 0:32:05
epoch [13/50] batch [140/204] time 0.242 (0.252) data 0.000 (0.003) loss 0.5841 (0.9292) lr 1.9048e-03 eta 0:31:55
epoch [13/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.003) loss 2.0292 (0.9112) lr 1.9048e-03 eta 0:31:48
epoch [13/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.5137 (0.9009) lr 1.9048e-03 eta 0:31:40
epoch [13/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 1.4944 (0.9016) lr 1.9048e-03 eta 0:31:33
epoch [14/50] batch [20/204] time 0.250 (0.271) data 0.000 (0.022) loss 1.5663 (1.0320) lr 1.8763e-03 eta 0:33:58
epoch [14/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 1.2142 (0.9011) lr 1.8763e-03 eta 0:32:30
epoch [14/50] batch [60/204] time 0.241 (0.256) data 0.000 (0.007) loss 0.4427 (0.8741) lr 1.8763e-03 eta 0:31:55
epoch [14/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 1.3691 (0.8981) lr 1.8763e-03 eta 0:31:38
epoch [14/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.1557 (0.8763) lr 1.8763e-03 eta 0:31:24
epoch [14/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.6075 (0.8842) lr 1.8763e-03 eta 0:31:13
epoch [14/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.4231 (0.8540) lr 1.8763e-03 eta 0:31:04
epoch [14/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.0511 (0.8492) lr 1.8763e-03 eta 0:30:56
epoch [14/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.3835 (0.8581) lr 1.8763e-03 eta 0:30:48
epoch [14/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 1.0872 (0.8700) lr 1.8763e-03 eta 0:30:41
epoch [15/50] batch [20/204] time 0.245 (0.271) data 0.000 (0.022) loss 0.5944 (0.8310) lr 1.8443e-03 eta 0:33:06
epoch [15/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 0.2585 (0.8733) lr 1.8443e-03 eta 0:31:38
epoch [15/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 1.8604 (0.8820) lr 1.8443e-03 eta 0:31:05
epoch [15/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.3885 (0.8318) lr 1.8443e-03 eta 0:30:46
epoch [15/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.1839 (0.8028) lr 1.8443e-03 eta 0:30:33
epoch [15/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.5087 (0.7659) lr 1.8443e-03 eta 0:30:22
epoch [15/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.8488 (0.7733) lr 1.8443e-03 eta 0:30:13
epoch [15/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.7194 (0.7689) lr 1.8443e-03 eta 0:30:05
epoch [15/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.8469 (0.7781) lr 1.8443e-03 eta 0:29:58
epoch [15/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.7710 (0.7593) lr 1.8443e-03 eta 0:29:51
epoch [16/50] batch [20/204] time 0.245 (0.271) data 0.000 (0.022) loss 0.5033 (0.7902) lr 1.8090e-03 eta 0:32:12
epoch [16/50] batch [40/204] time 0.249 (0.260) data 0.000 (0.011) loss 0.1912 (0.8586) lr 1.8090e-03 eta 0:30:44
epoch [16/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.2914 (0.8971) lr 1.8090e-03 eta 0:30:11
epoch [16/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.6058 (0.8157) lr 1.8090e-03 eta 0:29:53
epoch [16/50] batch [100/204] time 0.243 (0.253) data 0.000 (0.005) loss 0.9823 (0.8185) lr 1.8090e-03 eta 0:29:40
epoch [16/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.5700 (0.7895) lr 1.8090e-03 eta 0:29:30
epoch [16/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.6542 (0.7940) lr 1.8090e-03 eta 0:29:21
epoch [16/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.9849 (0.7981) lr 1.8090e-03 eta 0:29:13
epoch [16/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.5984 (0.7902) lr 1.8090e-03 eta 0:29:06
epoch [16/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 1.0270 (0.7668) lr 1.8090e-03 eta 0:28:59
epoch [17/50] batch [20/204] time 0.251 (0.272) data 0.000 (0.022) loss 0.4232 (0.6907) lr 1.7705e-03 eta 0:31:18
epoch [17/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 0.1040 (0.7655) lr 1.7705e-03 eta 0:29:52
epoch [17/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.008) loss 1.4554 (0.7139) lr 1.7705e-03 eta 0:29:20
epoch [17/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.9738 (0.7137) lr 1.7705e-03 eta 0:29:01
epoch [17/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.005) loss 0.9630 (0.7377) lr 1.7705e-03 eta 0:28:49
epoch [17/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.2486 (0.7207) lr 1.7705e-03 eta 0:28:38
epoch [17/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.6988 (0.7138) lr 1.7705e-03 eta 0:28:29
epoch [17/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.4693 (0.7031) lr 1.7705e-03 eta 0:28:22
epoch [17/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.4482 (0.7085) lr 1.7705e-03 eta 0:28:15
epoch [17/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 1.0861 (0.7129) lr 1.7705e-03 eta 0:28:08
epoch [18/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.022) loss 1.3419 (0.7482) lr 1.7290e-03 eta 0:30:14
epoch [18/50] batch [40/204] time 0.242 (0.259) data 0.000 (0.011) loss 0.6748 (0.7926) lr 1.7290e-03 eta 0:28:54
epoch [18/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.007) loss 1.0636 (0.7674) lr 1.7290e-03 eta 0:28:24
epoch [18/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.006) loss 0.3590 (0.7716) lr 1.7290e-03 eta 0:28:05
epoch [18/50] batch [100/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.6846 (0.8076) lr 1.7290e-03 eta 0:27:53
epoch [18/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.004) loss 0.1034 (0.7878) lr 1.7290e-03 eta 0:27:42
epoch [18/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.2136 (0.7724) lr 1.7290e-03 eta 0:27:34
epoch [18/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.003) loss 2.0932 (0.7768) lr 1.7290e-03 eta 0:27:26
epoch [18/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.003) loss 0.4562 (0.7539) lr 1.7290e-03 eta 0:27:20
epoch [18/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 1.8089 (0.7554) lr 1.7290e-03 eta 0:27:13
epoch [19/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 1.7761 (0.7264) lr 1.6845e-03 eta 0:29:24
epoch [19/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 0.2442 (0.6597) lr 1.6845e-03 eta 0:28:06
epoch [19/50] batch [60/204] time 0.245 (0.256) data 0.000 (0.007) loss 0.3294 (0.6863) lr 1.6845e-03 eta 0:27:34
epoch [19/50] batch [80/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.6547 (0.7265) lr 1.6845e-03 eta 0:27:17
epoch [19/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.5058 (0.6888) lr 1.6845e-03 eta 0:27:04
epoch [19/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.3099 (0.6739) lr 1.6845e-03 eta 0:26:54
epoch [19/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.2181 (0.6744) lr 1.6845e-03 eta 0:26:46
epoch [19/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.0886 (0.6830) lr 1.6845e-03 eta 0:26:38
epoch [19/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.0958 (0.6916) lr 1.6845e-03 eta 0:26:31
epoch [19/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.8110 (0.6885) lr 1.6845e-03 eta 0:26:24
epoch [20/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.022) loss 0.1300 (0.5990) lr 1.6374e-03 eta 0:28:19
epoch [20/50] batch [40/204] time 0.250 (0.259) data 0.000 (0.011) loss 0.1817 (0.6072) lr 1.6374e-03 eta 0:27:07
epoch [20/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.007) loss 0.1810 (0.5857) lr 1.6374e-03 eta 0:26:39
epoch [20/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.1789 (0.6841) lr 1.6374e-03 eta 0:26:23
epoch [20/50] batch [100/204] time 0.246 (0.253) data 0.000 (0.005) loss 0.3025 (0.6670) lr 1.6374e-03 eta 0:26:11
epoch [20/50] batch [120/204] time 0.242 (0.252) data 0.000 (0.004) loss 0.7408 (0.6491) lr 1.6374e-03 eta 0:26:02
epoch [20/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.3673 (0.6486) lr 1.6374e-03 eta 0:25:53
epoch [20/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.8120 (0.6315) lr 1.6374e-03 eta 0:25:46
epoch [20/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.7987 (0.6454) lr 1.6374e-03 eta 0:25:39
epoch [20/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 1.0993 (0.6497) lr 1.6374e-03 eta 0:25:32
epoch [21/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.022) loss 0.2151 (0.6223) lr 1.5878e-03 eta 0:27:27
epoch [21/50] batch [40/204] time 0.250 (0.259) data 0.000 (0.011) loss 1.3679 (0.6442) lr 1.5878e-03 eta 0:26:16
epoch [21/50] batch [60/204] time 0.245 (0.256) data 0.000 (0.007) loss 0.9678 (0.6185) lr 1.5878e-03 eta 0:25:49
epoch [21/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.2505 (0.5906) lr 1.5878e-03 eta 0:25:32
epoch [21/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.5646 (0.6104) lr 1.5878e-03 eta 0:25:21
epoch [21/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.004) loss 1.0317 (0.6084) lr 1.5878e-03 eta 0:25:12
epoch [21/50] batch [140/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.4894 (0.5903) lr 1.5878e-03 eta 0:25:04
epoch [21/50] batch [160/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.1497 (0.5713) lr 1.5878e-03 eta 0:24:56
epoch [21/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.7909 (0.5752) lr 1.5878e-03 eta 0:24:50
epoch [21/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.6859 (0.5908) lr 1.5878e-03 eta 0:24:43
epoch [22/50] batch [20/204] time 0.251 (0.272) data 0.000 (0.022) loss 1.1340 (0.9096) lr 1.5358e-03 eta 0:26:41
epoch [22/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.011) loss 0.3101 (0.7106) lr 1.5358e-03 eta 0:25:26
epoch [22/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.008) loss 1.3496 (0.7192) lr 1.5358e-03 eta 0:24:59
epoch [22/50] batch [80/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.1299 (0.7042) lr 1.5358e-03 eta 0:24:43
epoch [22/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.9809 (0.7076) lr 1.5358e-03 eta 0:24:32
epoch [22/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.8735 (0.6886) lr 1.5358e-03 eta 0:24:23
epoch [22/50] batch [140/204] time 0.248 (0.252) data 0.000 (0.003) loss 1.1113 (0.6768) lr 1.5358e-03 eta 0:24:14
epoch [22/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.1951 (0.6801) lr 1.5358e-03 eta 0:24:07
epoch [22/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.5708 (0.6690) lr 1.5358e-03 eta 0:24:00
epoch [22/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.6318 (0.6548) lr 1.5358e-03 eta 0:23:54
epoch [23/50] batch [20/204] time 0.250 (0.270) data 0.000 (0.022) loss 0.1688 (0.5227) lr 1.4818e-03 eta 0:25:36
epoch [23/50] batch [40/204] time 0.242 (0.259) data 0.000 (0.011) loss 0.0355 (0.4855) lr 1.4818e-03 eta 0:24:29
epoch [23/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.007) loss 1.1746 (0.5119) lr 1.4818e-03 eta 0:24:03
epoch [23/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.6741 (0.5580) lr 1.4818e-03 eta 0:23:49
epoch [23/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.2637 (0.5898) lr 1.4818e-03 eta 0:23:38
epoch [23/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.4766 (0.6032) lr 1.4818e-03 eta 0:23:29
epoch [23/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.1412 (0.6431) lr 1.4818e-03 eta 0:23:22
epoch [23/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.6811 (0.6393) lr 1.4818e-03 eta 0:23:14
epoch [23/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.2985 (0.6408) lr 1.4818e-03 eta 0:23:08
epoch [23/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.0756 (0.6316) lr 1.4818e-03 eta 0:23:01
epoch [24/50] batch [20/204] time 0.246 (0.272) data 0.000 (0.022) loss 0.0056 (0.5730) lr 1.4258e-03 eta 0:24:50
epoch [24/50] batch [40/204] time 0.250 (0.260) data 0.000 (0.011) loss 0.5334 (0.5353) lr 1.4258e-03 eta 0:23:42
epoch [24/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.2705 (0.5327) lr 1.4258e-03 eta 0:23:16
epoch [24/50] batch [80/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.2136 (0.5604) lr 1.4258e-03 eta 0:22:59
epoch [24/50] batch [100/204] time 0.244 (0.253) data 0.000 (0.005) loss 0.6482 (0.5746) lr 1.4258e-03 eta 0:22:48
epoch [24/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.9403 (0.5756) lr 1.4258e-03 eta 0:22:38
epoch [24/50] batch [140/204] time 0.248 (0.252) data 0.000 (0.003) loss 0.6333 (0.5717) lr 1.4258e-03 eta 0:22:31
epoch [24/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.7306 (0.5807) lr 1.4258e-03 eta 0:22:24
epoch [24/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1527 (0.5827) lr 1.4258e-03 eta 0:22:17
epoch [24/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.6229 (0.5980) lr 1.4258e-03 eta 0:22:10
epoch [25/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.022) loss 0.5359 (0.7615) lr 1.3681e-03 eta 0:23:47
epoch [25/50] batch [40/204] time 0.248 (0.259) data 0.000 (0.011) loss 0.1486 (0.6831) lr 1.3681e-03 eta 0:22:44
epoch [25/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.007) loss 0.2014 (0.6753) lr 1.3681e-03 eta 0:22:21
epoch [25/50] batch [80/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.0514 (0.6326) lr 1.3681e-03 eta 0:22:06
epoch [25/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.5123 (0.5874) lr 1.3681e-03 eta 0:21:54
epoch [25/50] batch [120/204] time 0.247 (0.252) data 0.000 (0.004) loss 1.5838 (0.6105) lr 1.3681e-03 eta 0:21:46
epoch [25/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.7664 (0.5888) lr 1.3681e-03 eta 0:21:38
epoch [25/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.6792 (0.5784) lr 1.3681e-03 eta 0:21:31
epoch [25/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.003) loss 1.0130 (0.5828) lr 1.3681e-03 eta 0:21:24
epoch [25/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 1.3579 (0.6059) lr 1.3681e-03 eta 0:21:18
epoch [26/50] batch [20/204] time 0.248 (0.270) data 0.000 (0.021) loss 0.5064 (0.6018) lr 1.3090e-03 eta 0:22:52
epoch [26/50] batch [40/204] time 0.251 (0.259) data 0.000 (0.011) loss 0.3135 (0.5392) lr 1.3090e-03 eta 0:21:53
epoch [26/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.5518 (0.4951) lr 1.3090e-03 eta 0:21:29
epoch [26/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.005) loss 0.2108 (0.5337) lr 1.3090e-03 eta 0:21:15
epoch [26/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.5404 (0.5238) lr 1.3090e-03 eta 0:21:04
epoch [26/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 1.1852 (0.5235) lr 1.3090e-03 eta 0:20:54
epoch [26/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.6949 (0.5430) lr 1.3090e-03 eta 0:20:47
epoch [26/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1365 (0.5665) lr 1.3090e-03 eta 0:20:40
epoch [26/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.2376 (0.5596) lr 1.3090e-03 eta 0:20:33
epoch [26/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.9270 (0.5634) lr 1.3090e-03 eta 0:20:27
epoch [27/50] batch [20/204] time 0.248 (0.271) data 0.000 (0.022) loss 0.2576 (0.4468) lr 1.2487e-03 eta 0:22:00
epoch [27/50] batch [40/204] time 0.249 (0.260) data 0.000 (0.011) loss 0.5398 (0.5426) lr 1.2487e-03 eta 0:21:00
epoch [27/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.9898 (0.5652) lr 1.2487e-03 eta 0:20:38
epoch [27/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.7971 (0.5490) lr 1.2487e-03 eta 0:20:23
epoch [27/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.1163 (0.5566) lr 1.2487e-03 eta 0:20:14
epoch [27/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.2309 (0.5511) lr 1.2487e-03 eta 0:20:05
epoch [27/50] batch [140/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.3166 (0.5675) lr 1.2487e-03 eta 0:19:58
epoch [27/50] batch [160/204] time 0.242 (0.252) data 0.000 (0.003) loss 0.7360 (0.5462) lr 1.2487e-03 eta 0:19:51
epoch [27/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1134 (0.5308) lr 1.2487e-03 eta 0:19:45
epoch [27/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.1280 (0.5376) lr 1.2487e-03 eta 0:19:38
epoch [28/50] batch [20/204] time 0.245 (0.270) data 0.000 (0.021) loss 0.8568 (0.7353) lr 1.1874e-03 eta 0:20:59
epoch [28/50] batch [40/204] time 0.243 (0.259) data 0.000 (0.011) loss 0.1145 (0.6177) lr 1.1874e-03 eta 0:20:04
epoch [28/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.007) loss 0.5752 (0.5753) lr 1.1874e-03 eta 0:19:43
epoch [28/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.005) loss 1.0533 (0.5912) lr 1.1874e-03 eta 0:19:30
epoch [28/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.004) loss 0.0773 (0.5862) lr 1.1874e-03 eta 0:19:20
epoch [28/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 1.3452 (0.5710) lr 1.1874e-03 eta 0:19:12
epoch [28/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.8819 (0.5607) lr 1.1874e-03 eta 0:19:05
epoch [28/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1769 (0.5692) lr 1.1874e-03 eta 0:18:57
epoch [28/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.5581 (0.5657) lr 1.1874e-03 eta 0:18:51
epoch [28/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.2318 (0.5583) lr 1.1874e-03 eta 0:18:45
epoch [29/50] batch [20/204] time 0.243 (0.270) data 0.000 (0.022) loss 0.9846 (0.5232) lr 1.1253e-03 eta 0:20:05
epoch [29/50] batch [40/204] time 0.251 (0.259) data 0.000 (0.011) loss 0.0846 (0.6202) lr 1.1253e-03 eta 0:19:12
epoch [29/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.5320 (0.6253) lr 1.1253e-03 eta 0:18:52
epoch [29/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.1908 (0.6879) lr 1.1253e-03 eta 0:18:38
epoch [29/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0693 (0.6515) lr 1.1253e-03 eta 0:18:28
epoch [29/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.1654 (0.6249) lr 1.1253e-03 eta 0:18:20
epoch [29/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.0895 (0.6227) lr 1.1253e-03 eta 0:18:12
epoch [29/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.2941 (0.6039) lr 1.1253e-03 eta 0:18:06
epoch [29/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.3123 (0.5900) lr 1.1253e-03 eta 0:18:00
epoch [29/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 1.1776 (0.5972) lr 1.1253e-03 eta 0:17:53
epoch [30/50] batch [20/204] time 0.245 (0.270) data 0.000 (0.021) loss 0.4583 (0.4126) lr 1.0628e-03 eta 0:19:10
epoch [30/50] batch [40/204] time 0.245 (0.259) data 0.000 (0.011) loss 0.1897 (0.4490) lr 1.0628e-03 eta 0:18:19
epoch [30/50] batch [60/204] time 0.243 (0.255) data 0.000 (0.007) loss 0.6681 (0.4723) lr 1.0628e-03 eta 0:17:58
epoch [30/50] batch [80/204] time 0.249 (0.254) data 0.000 (0.005) loss 0.1214 (0.4363) lr 1.0628e-03 eta 0:17:46
epoch [30/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.004) loss 1.4475 (0.4634) lr 1.0628e-03 eta 0:17:36
epoch [30/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.7631 (0.4844) lr 1.0628e-03 eta 0:17:29
epoch [30/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.3661 (0.4709) lr 1.0628e-03 eta 0:17:22
epoch [30/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.5539 (0.4863) lr 1.0628e-03 eta 0:17:16
epoch [30/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.2261 (0.4929) lr 1.0628e-03 eta 0:17:09
epoch [30/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.3658 (0.5072) lr 1.0628e-03 eta 0:17:03
epoch [31/50] batch [20/204] time 0.250 (0.272) data 0.000 (0.022) loss 0.8659 (0.4390) lr 1.0000e-03 eta 0:18:22
epoch [31/50] batch [40/204] time 0.245 (0.260) data 0.000 (0.011) loss 0.2852 (0.4990) lr 1.0000e-03 eta 0:17:30
epoch [31/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.1379 (0.4982) lr 1.0000e-03 eta 0:17:08
epoch [31/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.7426 (0.5309) lr 1.0000e-03 eta 0:16:56
epoch [31/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.1690 (0.5372) lr 1.0000e-03 eta 0:16:46
epoch [31/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.1720 (0.5314) lr 1.0000e-03 eta 0:16:38
epoch [31/50] batch [140/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.3446 (0.5363) lr 1.0000e-03 eta 0:16:31
epoch [31/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3612 (0.5424) lr 1.0000e-03 eta 0:16:24
epoch [31/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.1757 (0.5226) lr 1.0000e-03 eta 0:16:18
epoch [31/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 1.1270 (0.5433) lr 1.0000e-03 eta 0:16:12
epoch [32/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.023) loss 0.1522 (0.3037) lr 9.3721e-04 eta 0:17:24
epoch [32/50] batch [40/204] time 0.245 (0.260) data 0.000 (0.011) loss 0.1554 (0.3485) lr 9.3721e-04 eta 0:16:36
epoch [32/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.008) loss 1.3204 (0.4649) lr 9.3721e-04 eta 0:16:17
epoch [32/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.0902 (0.4549) lr 9.3721e-04 eta 0:16:04
epoch [32/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.2229 (0.4478) lr 9.3721e-04 eta 0:15:55
epoch [32/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.7907 (0.4503) lr 9.3721e-04 eta 0:15:47
epoch [32/50] batch [140/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.6658 (0.4583) lr 9.3721e-04 eta 0:15:40
epoch [32/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.5906 (0.4641) lr 9.3721e-04 eta 0:15:33
epoch [32/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.6234 (0.4653) lr 9.3721e-04 eta 0:15:27
epoch [32/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.0415 (0.4610) lr 9.3721e-04 eta 0:15:21
epoch [33/50] batch [20/204] time 0.250 (0.271) data 0.000 (0.022) loss 0.6877 (0.5331) lr 8.7467e-04 eta 0:16:29
epoch [33/50] batch [40/204] time 0.244 (0.260) data 0.000 (0.011) loss 1.1552 (0.5878) lr 8.7467e-04 eta 0:15:43
epoch [33/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.008) loss 1.7343 (0.5534) lr 8.7467e-04 eta 0:15:25
epoch [33/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.7611 (0.5538) lr 8.7467e-04 eta 0:15:13
epoch [33/50] batch [100/204] time 0.249 (0.253) data 0.000 (0.005) loss 0.1482 (0.5516) lr 8.7467e-04 eta 0:15:04
epoch [33/50] batch [120/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.3336 (0.5512) lr 8.7467e-04 eta 0:14:56
epoch [33/50] batch [140/204] time 0.247 (0.252) data 0.000 (0.003) loss 0.6439 (0.5303) lr 8.7467e-04 eta 0:14:49
epoch [33/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.2235 (0.5211) lr 8.7467e-04 eta 0:14:43
epoch [33/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.3416 (0.5443) lr 8.7467e-04 eta 0:14:37
epoch [33/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.6331 (0.5231) lr 8.7467e-04 eta 0:14:31
epoch [34/50] batch [20/204] time 0.251 (0.272) data 0.000 (0.023) loss 0.0608 (0.5034) lr 8.1262e-04 eta 0:15:38
epoch [34/50] batch [40/204] time 0.250 (0.261) data 0.000 (0.011) loss 0.2714 (0.4835) lr 8.1262e-04 eta 0:14:53
epoch [34/50] batch [60/204] time 0.248 (0.257) data 0.000 (0.008) loss 0.5613 (0.4841) lr 8.1262e-04 eta 0:14:34
epoch [34/50] batch [80/204] time 0.248 (0.255) data 0.000 (0.006) loss 0.0727 (0.4955) lr 8.1262e-04 eta 0:14:22
epoch [34/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.005) loss 1.1627 (0.5219) lr 8.1262e-04 eta 0:14:13
epoch [34/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0843 (0.5226) lr 8.1262e-04 eta 0:14:05
epoch [34/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.0521 (0.5173) lr 8.1262e-04 eta 0:13:58
epoch [34/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.3609 (0.5009) lr 8.1262e-04 eta 0:13:52
epoch [34/50] batch [180/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.1806 (0.4988) lr 8.1262e-04 eta 0:13:46
epoch [34/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.1965 (0.4981) lr 8.1262e-04 eta 0:13:40
epoch [35/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.4997 (0.5673) lr 7.5131e-04 eta 0:14:38
epoch [35/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 0.2758 (0.6248) lr 7.5131e-04 eta 0:13:57
epoch [35/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.007) loss 0.1396 (0.5584) lr 7.5131e-04 eta 0:13:40
epoch [35/50] batch [80/204] time 0.246 (0.254) data 0.000 (0.006) loss 0.1975 (0.5004) lr 7.5131e-04 eta 0:13:29
epoch [35/50] batch [100/204] time 0.243 (0.253) data 0.000 (0.005) loss 0.9411 (0.5394) lr 7.5131e-04 eta 0:13:20
epoch [35/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 1.1645 (0.5343) lr 7.5131e-04 eta 0:13:12
epoch [35/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.3090 (0.5202) lr 7.5131e-04 eta 0:13:05
epoch [35/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.0180 (0.5105) lr 7.5131e-04 eta 0:12:59
epoch [35/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0472 (0.5309) lr 7.5131e-04 eta 0:12:53
epoch [35/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.5387 (0.5210) lr 7.5131e-04 eta 0:12:47
epoch [36/50] batch [20/204] time 0.252 (0.271) data 0.000 (0.023) loss 0.4898 (0.5850) lr 6.9098e-04 eta 0:13:43
epoch [36/50] batch [40/204] time 0.242 (0.259) data 0.000 (0.011) loss 1.1687 (0.4901) lr 6.9098e-04 eta 0:13:02
epoch [36/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.008) loss 0.5111 (0.5074) lr 6.9098e-04 eta 0:12:46
epoch [36/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.006) loss 0.6930 (0.4935) lr 6.9098e-04 eta 0:12:35
epoch [36/50] batch [100/204] time 0.248 (0.252) data 0.000 (0.005) loss 0.0623 (0.4853) lr 6.9098e-04 eta 0:12:27
epoch [36/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.8925 (0.4876) lr 6.9098e-04 eta 0:12:19
epoch [36/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.9258 (0.4766) lr 6.9098e-04 eta 0:12:13
epoch [36/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.1731 (0.4806) lr 6.9098e-04 eta 0:12:07
epoch [36/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.2618 (0.4881) lr 6.9098e-04 eta 0:12:01
epoch [36/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.1866 (0.4831) lr 6.9098e-04 eta 0:11:55
epoch [37/50] batch [20/204] time 0.245 (0.270) data 0.000 (0.022) loss 0.1883 (0.4731) lr 6.3188e-04 eta 0:12:46
epoch [37/50] batch [40/204] time 0.242 (0.259) data 0.000 (0.011) loss 0.5951 (0.4800) lr 6.3188e-04 eta 0:12:10
epoch [37/50] batch [60/204] time 0.244 (0.256) data 0.000 (0.007) loss 0.8221 (0.5230) lr 6.3188e-04 eta 0:11:54
epoch [37/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.6819 (0.5210) lr 6.3188e-04 eta 0:11:44
epoch [37/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.2485 (0.4900) lr 6.3188e-04 eta 0:11:36
epoch [37/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.3689 (0.4942) lr 6.3188e-04 eta 0:11:29
epoch [37/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.2751 (0.5057) lr 6.3188e-04 eta 0:11:23
epoch [37/50] batch [160/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.1776 (0.5039) lr 6.3188e-04 eta 0:11:17
epoch [37/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.0142 (0.5070) lr 6.3188e-04 eta 0:11:11
epoch [37/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.1186 (0.4954) lr 6.3188e-04 eta 0:11:05
epoch [38/50] batch [20/204] time 0.246 (0.270) data 0.000 (0.022) loss 0.0961 (0.4504) lr 5.7422e-04 eta 0:11:50
epoch [38/50] batch [40/204] time 0.248 (0.259) data 0.000 (0.011) loss 0.4359 (0.4574) lr 5.7422e-04 eta 0:11:15
epoch [38/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.007) loss 0.0891 (0.3995) lr 5.7422e-04 eta 0:11:02
epoch [38/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.006) loss 1.3709 (0.4146) lr 5.7422e-04 eta 0:10:52
epoch [38/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.005) loss 0.1848 (0.4342) lr 5.7422e-04 eta 0:10:44
epoch [38/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.1030 (0.4201) lr 5.7422e-04 eta 0:10:37
epoch [38/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.5634 (0.4325) lr 5.7422e-04 eta 0:10:31
epoch [38/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.4628 (0.4407) lr 5.7422e-04 eta 0:10:25
epoch [38/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.7409 (0.4727) lr 5.7422e-04 eta 0:10:19
epoch [38/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 2.4984 (0.4822) lr 5.7422e-04 eta 0:10:14
epoch [39/50] batch [20/204] time 0.248 (0.271) data 0.000 (0.022) loss 0.0739 (0.4234) lr 5.1825e-04 eta 0:10:57
epoch [39/50] batch [40/204] time 0.248 (0.260) data 0.000 (0.011) loss 0.0184 (0.4176) lr 5.1825e-04 eta 0:10:24
epoch [39/50] batch [60/204] time 0.245 (0.256) data 0.000 (0.007) loss 0.0574 (0.3874) lr 5.1825e-04 eta 0:10:10
epoch [39/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.3022 (0.4353) lr 5.1825e-04 eta 0:10:01
epoch [39/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.4312 (0.4773) lr 5.1825e-04 eta 0:09:53
epoch [39/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.004) loss 1.4499 (0.5165) lr 5.1825e-04 eta 0:09:46
epoch [39/50] batch [140/204] time 0.248 (0.252) data 0.000 (0.003) loss 1.2190 (0.5337) lr 5.1825e-04 eta 0:09:40
epoch [39/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.5973 (0.5257) lr 5.1825e-04 eta 0:09:34
epoch [39/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.2081 (0.4929) lr 5.1825e-04 eta 0:09:29
epoch [39/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.0805 (0.4801) lr 5.1825e-04 eta 0:09:23
epoch [40/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.022) loss 1.9945 (0.5156) lr 4.6417e-04 eta 0:10:01
epoch [40/50] batch [40/204] time 0.252 (0.259) data 0.000 (0.011) loss 1.6022 (0.5028) lr 4.6417e-04 eta 0:09:31
epoch [40/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.0515 (0.5076) lr 4.6417e-04 eta 0:09:18
epoch [40/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.006) loss 0.1039 (0.4832) lr 4.6417e-04 eta 0:09:09
epoch [40/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.1095 (0.4932) lr 4.6417e-04 eta 0:09:02
epoch [40/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.0589 (0.5026) lr 4.6417e-04 eta 0:08:55
epoch [40/50] batch [140/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.3818 (0.4967) lr 4.6417e-04 eta 0:08:49
epoch [40/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.3946 (0.5012) lr 4.6417e-04 eta 0:08:43
epoch [40/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1757 (0.4825) lr 4.6417e-04 eta 0:08:37
epoch [40/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.3263 (0.4725) lr 4.6417e-04 eta 0:08:32
epoch [41/50] batch [20/204] time 0.249 (0.271) data 0.000 (0.022) loss 0.1184 (0.5328) lr 4.1221e-04 eta 0:09:07
epoch [41/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.011) loss 0.4499 (0.4691) lr 4.1221e-04 eta 0:08:39
epoch [41/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.007) loss 0.8275 (0.4842) lr 4.1221e-04 eta 0:08:26
epoch [41/50] batch [80/204] time 0.252 (0.254) data 0.000 (0.006) loss 0.0279 (0.4573) lr 4.1221e-04 eta 0:08:18
epoch [41/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.0832 (0.4611) lr 4.1221e-04 eta 0:08:11
epoch [41/50] batch [120/204] time 0.252 (0.253) data 0.000 (0.004) loss 0.3654 (0.4670) lr 4.1221e-04 eta 0:08:04
epoch [41/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.6688 (0.4471) lr 4.1221e-04 eta 0:07:59
epoch [41/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.8603 (0.4321) lr 4.1221e-04 eta 0:07:53
epoch [41/50] batch [180/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.3417 (0.4361) lr 4.1221e-04 eta 0:07:47
epoch [41/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.4364 (0.4483) lr 4.1221e-04 eta 0:07:42
epoch [42/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.022) loss 0.4609 (0.5059) lr 3.6258e-04 eta 0:08:11
epoch [42/50] batch [40/204] time 0.250 (0.259) data 0.000 (0.011) loss 0.7363 (0.4900) lr 3.6258e-04 eta 0:07:45
epoch [42/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.007) loss 0.1358 (0.5213) lr 3.6258e-04 eta 0:07:33
epoch [42/50] batch [80/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.8879 (0.5148) lr 3.6258e-04 eta 0:07:25
epoch [42/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.2267 (0.5157) lr 3.6258e-04 eta 0:07:19
epoch [42/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.3648 (0.5098) lr 3.6258e-04 eta 0:07:13
epoch [42/50] batch [140/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.1534 (0.4956) lr 3.6258e-04 eta 0:07:07
epoch [42/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.0874 (0.4802) lr 3.6258e-04 eta 0:07:01
epoch [42/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.8873 (0.4739) lr 3.6258e-04 eta 0:06:56
epoch [42/50] batch [200/204] time 0.246 (0.251) data 0.000 (0.002) loss 1.0318 (0.4735) lr 3.6258e-04 eta 0:06:50
epoch [43/50] batch [20/204] time 0.251 (0.270) data 0.000 (0.021) loss 0.3221 (0.3558) lr 3.1545e-04 eta 0:07:15
epoch [43/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.011) loss 0.1384 (0.4585) lr 3.1545e-04 eta 0:06:53
epoch [43/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.2752 (0.5040) lr 3.1545e-04 eta 0:06:42
epoch [43/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.005) loss 0.1067 (0.4778) lr 3.1545e-04 eta 0:06:34
epoch [43/50] batch [100/204] time 0.252 (0.253) data 0.000 (0.004) loss 0.1589 (0.4557) lr 3.1545e-04 eta 0:06:27
epoch [43/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.2467 (0.4335) lr 3.1545e-04 eta 0:06:21
epoch [43/50] batch [140/204] time 0.256 (0.252) data 0.000 (0.003) loss 0.3329 (0.4405) lr 3.1545e-04 eta 0:06:15
epoch [43/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.1005 (0.4385) lr 3.1545e-04 eta 0:06:10
epoch [43/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.9862 (0.4341) lr 3.1545e-04 eta 0:06:04
epoch [43/50] batch [200/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.2785 (0.4263) lr 3.1545e-04 eta 0:05:59
epoch [44/50] batch [20/204] time 0.250 (0.271) data 0.000 (0.022) loss 0.1617 (0.3714) lr 2.7103e-04 eta 0:06:21
epoch [44/50] batch [40/204] time 0.249 (0.260) data 0.000 (0.011) loss 0.2893 (0.3424) lr 2.7103e-04 eta 0:06:00
epoch [44/50] batch [60/204] time 0.248 (0.256) data 0.000 (0.007) loss 0.0946 (0.3790) lr 2.7103e-04 eta 0:05:50
epoch [44/50] batch [80/204] time 0.248 (0.254) data 0.000 (0.006) loss 0.4697 (0.3943) lr 2.7103e-04 eta 0:05:42
epoch [44/50] batch [100/204] time 0.250 (0.253) data 0.000 (0.004) loss 1.0713 (0.4235) lr 2.7103e-04 eta 0:05:36
epoch [44/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.004) loss 0.1221 (0.4216) lr 2.7103e-04 eta 0:05:30
epoch [44/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.1261 (0.4387) lr 2.7103e-04 eta 0:05:24
epoch [44/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.9108 (0.4520) lr 2.7103e-04 eta 0:05:18
epoch [44/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.0755 (0.4529) lr 2.7103e-04 eta 0:05:13
epoch [44/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.2611 (0.4661) lr 2.7103e-04 eta 0:05:08
epoch [45/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.4947 (0.3279) lr 2.2949e-04 eta 0:05:26
epoch [45/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.011) loss 0.3669 (0.3748) lr 2.2949e-04 eta 0:05:07
epoch [45/50] batch [60/204] time 0.250 (0.256) data 0.000 (0.007) loss 0.0928 (0.4408) lr 2.2949e-04 eta 0:04:57
epoch [45/50] batch [80/204] time 0.246 (0.254) data 0.000 (0.006) loss 0.1258 (0.4790) lr 2.2949e-04 eta 0:04:50
epoch [45/50] batch [100/204] time 0.252 (0.253) data 0.000 (0.004) loss 1.9599 (0.4934) lr 2.2949e-04 eta 0:04:44
epoch [45/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.6610 (0.4871) lr 2.2949e-04 eta 0:04:38
epoch [45/50] batch [140/204] time 0.247 (0.252) data 0.000 (0.003) loss 1.1627 (0.4857) lr 2.2949e-04 eta 0:04:33
epoch [45/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.0465 (0.5077) lr 2.2949e-04 eta 0:04:27
epoch [45/50] batch [180/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.0440 (0.4978) lr 2.2949e-04 eta 0:04:22
epoch [45/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.0881 (0.5062) lr 2.2949e-04 eta 0:04:17
epoch [46/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.7357 (0.4164) lr 1.9098e-04 eta 0:04:31
epoch [46/50] batch [40/204] time 0.246 (0.260) data 0.000 (0.011) loss 0.2952 (0.4130) lr 1.9098e-04 eta 0:04:14
epoch [46/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.008) loss 0.3646 (0.4331) lr 1.9098e-04 eta 0:04:06
epoch [46/50] batch [80/204] time 0.246 (0.254) data 0.000 (0.006) loss 0.1604 (0.4464) lr 1.9098e-04 eta 0:03:59
epoch [46/50] batch [100/204] time 0.245 (0.253) data 0.000 (0.005) loss 0.3487 (0.4426) lr 1.9098e-04 eta 0:03:52
epoch [46/50] batch [120/204] time 0.253 (0.253) data 0.000 (0.004) loss 0.1938 (0.4573) lr 1.9098e-04 eta 0:03:47
epoch [46/50] batch [140/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.0477 (0.4322) lr 1.9098e-04 eta 0:03:41
epoch [46/50] batch [160/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.4000 (0.4368) lr 1.9098e-04 eta 0:03:36
epoch [46/50] batch [180/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.3598 (0.4292) lr 1.9098e-04 eta 0:03:31
epoch [46/50] batch [200/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.2675 (0.4414) lr 1.9098e-04 eta 0:03:25
epoch [47/50] batch [20/204] time 0.249 (0.272) data 0.000 (0.022) loss 0.9204 (0.5496) lr 1.5567e-04 eta 0:03:36
epoch [47/50] batch [40/204] time 0.248 (0.260) data 0.000 (0.011) loss 0.1460 (0.5285) lr 1.5567e-04 eta 0:03:21
epoch [47/50] batch [60/204] time 0.252 (0.256) data 0.000 (0.007) loss 0.2971 (0.4976) lr 1.5567e-04 eta 0:03:13
epoch [47/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.2991 (0.4854) lr 1.5567e-04 eta 0:03:07
epoch [47/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.9699 (0.4817) lr 1.5567e-04 eta 0:03:01
epoch [47/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.4471 (0.4846) lr 1.5567e-04 eta 0:02:55
epoch [47/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.1730 (0.4749) lr 1.5567e-04 eta 0:02:50
epoch [47/50] batch [160/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.7314 (0.4801) lr 1.5567e-04 eta 0:02:45
epoch [47/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.5314 (0.4761) lr 1.5567e-04 eta 0:02:39
epoch [47/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.9411 (0.4694) lr 1.5567e-04 eta 0:02:34
epoch [48/50] batch [20/204] time 0.253 (0.271) data 0.000 (0.022) loss 0.9599 (0.4222) lr 1.2369e-04 eta 0:02:40
epoch [48/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 0.1873 (0.3884) lr 1.2369e-04 eta 0:02:28
epoch [48/50] batch [60/204] time 0.245 (0.256) data 0.000 (0.008) loss 1.6659 (0.4448) lr 1.2369e-04 eta 0:02:21
epoch [48/50] batch [80/204] time 0.244 (0.254) data 0.000 (0.006) loss 0.1861 (0.4558) lr 1.2369e-04 eta 0:02:15
epoch [48/50] batch [100/204] time 0.249 (0.253) data 0.000 (0.005) loss 0.4531 (0.4576) lr 1.2369e-04 eta 0:02:09
epoch [48/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.2783 (0.4446) lr 1.2369e-04 eta 0:02:04
epoch [48/50] batch [140/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.2953 (0.4395) lr 1.2369e-04 eta 0:01:58
epoch [48/50] batch [160/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.6254 (0.4461) lr 1.2369e-04 eta 0:01:53
epoch [48/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.1382 (0.4342) lr 1.2369e-04 eta 0:01:48
epoch [48/50] batch [200/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.8613 (0.4523) lr 1.2369e-04 eta 0:01:43
epoch [49/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.9250 (0.5339) lr 9.5173e-05 eta 0:01:45
epoch [49/50] batch [40/204] time 0.251 (0.260) data 0.000 (0.011) loss 0.6132 (0.4610) lr 9.5173e-05 eta 0:01:35
epoch [49/50] batch [60/204] time 0.249 (0.257) data 0.000 (0.007) loss 0.1869 (0.4536) lr 9.5173e-05 eta 0:01:29
epoch [49/50] batch [80/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.0625 (0.4842) lr 9.5173e-05 eta 0:01:23
epoch [49/50] batch [100/204] time 0.246 (0.254) data 0.000 (0.005) loss 1.6458 (0.4733) lr 9.5173e-05 eta 0:01:18
epoch [49/50] batch [120/204] time 0.249 (0.253) data 0.000 (0.004) loss 0.5232 (0.4619) lr 9.5173e-05 eta 0:01:12
epoch [49/50] batch [140/204] time 0.249 (0.252) data 0.000 (0.003) loss 1.9164 (0.4643) lr 9.5173e-05 eta 0:01:07
epoch [49/50] batch [160/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.3958 (0.4516) lr 9.5173e-05 eta 0:01:02
epoch [49/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.003) loss 0.3867 (0.4667) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.4218 (0.4606) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.251 (0.271) data 0.000 (0.022) loss 0.2426 (0.4727) lr 7.0224e-05 eta 0:00:49
epoch [50/50] batch [40/204] time 0.244 (0.260) data 0.000 (0.011) loss 0.0588 (0.3921) lr 7.0224e-05 eta 0:00:42
epoch [50/50] batch [60/204] time 0.249 (0.256) data 0.000 (0.008) loss 0.3877 (0.4206) lr 7.0224e-05 eta 0:00:36
epoch [50/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.9259 (0.4140) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.4793 (0.4629) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0512 (0.4557) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.247 (0.252) data 0.000 (0.003) loss 0.1160 (0.4810) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.2221 (0.4646) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.0178 (0.4651) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.244 (0.251) data 0.000 (0.002) loss 0.4853 (0.4757) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/oxford_flowers/vit_b16_ep50_c4_BZ4_ProDA/seed1/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 1,225
* correct: 1,197
* accuracy: 97.71%
* error: 2.29%
* macro_f1: 97.54%
Elapsed: 0:43:25
