***************
** Arguments **
***************
backbone: 
config_file: configs/trainers/ProDA/vit_b16_ep50_c4_BZ4_ProDA.yaml
dataset_config_file: configs/datasets/caltech101.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/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed2
resume: 
root: /mnt/hdd/DATA
seed: 2
source_domains: None
target_domains: None
trainer: ProDA
transforms: None
************
** Config **
************
DATALOADER:
  K_TRANSFORMS: 1
  NUM_WORKERS: 8
  RETURN_IMG0: False
  TEST:
    BATCH_SIZE: 100
    SAMPLER: SequentialSampler
  TRAIN_U:
    BATCH_SIZE: 32
    N_DOMAIN: 0
    N_INS: 16
    SAME_AS_X: True
    SAMPLER: RandomSampler
  TRAIN_X:
    BATCH_SIZE: 4
    N_DOMAIN: 0
    N_INS: 16
    SAMPLER: RandomSampler
DATASET:
  ALL_AS_UNLABELED: False
  CIFAR_C_LEVEL: 1
  CIFAR_C_TYPE: 
  NAME: Caltech101
  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/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed2
RESUME: 
SEED: 2
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ProDA
  ProDA:
    N_CTX: 4
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

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

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

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

CPU:
Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      46 bits physical, 57 bits virtual
Byte Order:                         Little Endian
CPU(s):                             64
On-line CPU(s) list:                18,20,22,23,25-27,29,31,32,34,37,46-49
Off-line CPU(s) list:               0-17,19,21,24,28,30,33,35,36,38-45,50-63
Vendor ID:                          GenuineIntel
Model name:                         Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
CPU family:                         6
Model:                              106
Thread(s) per core:                 2
Core(s) per socket:                 16
Socket(s):                          2
Stepping:                           6
CPU(s) scaling MHz:                 97%
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: Caltech101
Reading split from /mnt/hdd/DATA/caltech-101/split_zhou_Caltech101.json
Loading preprocessed few-shot data from /mnt/hdd/DATA/caltech-101/split_fewshot/shot_16_shuffled-seed_2.pkl
SUBSAMPLE BASE CLASSES!
Building transform_train
+ random resized crop (size=(224, 224), scale=(0.08, 1.0))
+ random flip
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
Building transform_test
+ resize the smaller edge to 224
+ 224x224 center crop
+ to torch tensor of range [0, 1]
+ normalization (mean=[0.48145466, 0.4578275, 0.40821073], std=[0.26862954, 0.26130258, 0.27577711])
---------  ----------
Dataset    Caltech101
# classes  50
# train_x  800
# val      200
# test     1,500
---------  ----------
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/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed2/tensorboard)
epoch [1/50] batch [20/200] time 0.738 (1.041) data 0.000 (0.053) loss 0.5775 (0.9870) lr 1.0000e-05 eta 2:53:10
epoch [1/50] batch [40/200] time 0.743 (0.862) data 0.000 (0.027) loss 1.1757 (0.9855) lr 1.0000e-05 eta 2:23:01
epoch [1/50] batch [60/200] time 0.738 (0.820) data 0.000 (0.018) loss 1.5785 (1.0006) lr 1.0000e-05 eta 2:15:48
epoch [1/50] batch [80/200] time 0.749 (0.786) data 0.000 (0.014) loss 0.2134 (0.9683) lr 1.0000e-05 eta 2:09:57
epoch [1/50] batch [100/200] time 0.713 (0.767) data 0.000 (0.011) loss 1.5910 (0.9961) lr 1.0000e-05 eta 2:06:28
epoch [1/50] batch [120/200] time 0.755 (0.763) data 0.000 (0.009) loss 0.7920 (1.0006) lr 1.0000e-05 eta 2:05:35
epoch [1/50] batch [140/200] time 0.753 (0.752) data 0.000 (0.008) loss 0.3651 (0.9813) lr 1.0000e-05 eta 2:03:31
epoch [1/50] batch [160/200] time 0.549 (0.749) data 0.000 (0.007) loss 0.0728 (0.9616) lr 1.0000e-05 eta 2:02:50
epoch [1/50] batch [180/200] time 0.748 (0.744) data 0.000 (0.006) loss 0.4671 (0.9738) lr 1.0000e-05 eta 2:01:43
epoch [1/50] batch [200/200] time 0.745 (0.737) data 0.000 (0.006) loss 1.4995 (0.9861) lr 1.0000e-05 eta 2:00:27
epoch [2/50] batch [20/200] time 0.732 (0.773) data 0.000 (0.032) loss 0.2231 (0.7309) lr 1.0000e-05 eta 2:05:57
epoch [2/50] batch [40/200] time 0.752 (0.737) data 0.000 (0.016) loss 0.8775 (0.6833) lr 1.0000e-05 eta 1:59:56
epoch [2/50] batch [60/200] time 0.742 (0.726) data 0.000 (0.011) loss 0.7116 (0.7759) lr 1.0000e-05 eta 1:57:46
epoch [2/50] batch [80/200] time 0.745 (0.730) data 0.000 (0.008) loss 0.6362 (0.8243) lr 1.0000e-05 eta 1:58:10
epoch [2/50] batch [100/200] time 0.531 (0.702) data 0.000 (0.007) loss 1.3395 (0.8076) lr 1.0000e-05 eta 1:53:30
epoch [2/50] batch [120/200] time 0.576 (0.675) data 0.009 (0.006) loss 1.9062 (0.7996) lr 1.0000e-05 eta 1:48:52
epoch [2/50] batch [140/200] time 0.538 (0.636) data 0.012 (0.005) loss 0.2769 (0.8001) lr 1.0000e-05 eta 1:42:26
epoch [2/50] batch [160/200] time 0.568 (0.630) data 0.000 (0.005) loss 1.5332 (0.8100) lr 1.0000e-05 eta 1:41:15
epoch [2/50] batch [180/200] time 0.555 (0.621) data 0.000 (0.004) loss 1.0384 (0.8090) lr 1.0000e-05 eta 1:39:31
epoch [2/50] batch [200/200] time 0.572 (0.614) data 0.000 (0.004) loss 0.1825 (0.8128) lr 1.0000e-05 eta 1:38:17
epoch [3/50] batch [20/200] time 0.649 (0.730) data 0.000 (0.042) loss 0.4712 (1.1014) lr 1.0000e-05 eta 1:56:31
epoch [3/50] batch [40/200] time 0.777 (0.761) data 0.000 (0.021) loss 1.2131 (1.0093) lr 1.0000e-05 eta 2:01:13
epoch [3/50] batch [60/200] time 0.792 (0.771) data 0.001 (0.014) loss 1.7022 (0.9380) lr 1.0000e-05 eta 2:02:36
epoch [3/50] batch [80/200] time 0.799 (0.777) data 0.000 (0.011) loss 0.8408 (0.8969) lr 1.0000e-05 eta 2:03:15
epoch [3/50] batch [100/200] time 0.790 (0.780) data 0.000 (0.009) loss 1.9248 (0.9067) lr 1.0000e-05 eta 2:03:29
epoch [3/50] batch [120/200] time 0.779 (0.782) data 0.000 (0.007) loss 0.0020 (0.8872) lr 1.0000e-05 eta 2:03:36
epoch [3/50] batch [140/200] time 0.789 (0.784) data 0.000 (0.006) loss 1.9412 (0.8678) lr 1.0000e-05 eta 2:03:35
epoch [3/50] batch [160/200] time 0.791 (0.785) data 0.000 (0.006) loss 0.1746 (0.8483) lr 1.0000e-05 eta 2:03:29
epoch [3/50] batch [180/200] time 0.787 (0.786) data 0.000 (0.005) loss 0.7816 (0.8397) lr 1.0000e-05 eta 2:03:20
epoch [3/50] batch [200/200] time 0.793 (0.786) data 0.000 (0.005) loss 0.6105 (0.8502) lr 1.0000e-05 eta 2:03:11
epoch [4/50] batch [20/200] time 0.532 (0.682) data 0.000 (0.031) loss 1.7021 (0.7976) lr 1.0000e-05 eta 1:46:39
epoch [4/50] batch [40/200] time 0.791 (0.716) data 0.000 (0.016) loss 0.0350 (0.6316) lr 1.0000e-05 eta 1:51:42
epoch [4/50] batch [60/200] time 0.792 (0.742) data 0.001 (0.011) loss 0.6788 (0.6295) lr 1.0000e-05 eta 1:55:26
epoch [4/50] batch [80/200] time 0.799 (0.755) data 0.000 (0.008) loss 1.1788 (0.6573) lr 1.0000e-05 eta 1:57:19
epoch [4/50] batch [100/200] time 0.803 (0.763) data 0.000 (0.007) loss 0.9814 (0.6963) lr 1.0000e-05 eta 1:58:13
epoch [4/50] batch [120/200] time 0.788 (0.769) data 0.000 (0.005) loss 0.1753 (0.6895) lr 1.0000e-05 eta 1:58:51
epoch [4/50] batch [140/200] time 0.790 (0.772) data 0.000 (0.005) loss 0.6648 (0.7259) lr 1.0000e-05 eta 1:59:11
epoch [4/50] batch [160/200] time 0.791 (0.775) data 0.000 (0.004) loss 1.1198 (0.7458) lr 1.0000e-05 eta 1:59:20
epoch [4/50] batch [180/200] time 0.796 (0.777) data 0.000 (0.004) loss 0.3055 (0.7512) lr 1.0000e-05 eta 1:59:24
epoch [4/50] batch [200/200] time 0.790 (0.779) data 0.000 (0.003) loss 0.0582 (0.7572) lr 1.0000e-05 eta 1:59:25
epoch [5/50] batch [20/200] time 0.783 (0.831) data 0.000 (0.036) loss 2.1245 (0.9413) lr 1.0000e-05 eta 2:07:09
epoch [5/50] batch [40/200] time 0.540 (0.761) data 0.000 (0.018) loss 0.2602 (0.7077) lr 1.0000e-05 eta 1:56:08
epoch [5/50] batch [60/200] time 0.818 (0.765) data 0.009 (0.013) loss 0.2211 (0.6721) lr 1.0000e-05 eta 1:56:30
epoch [5/50] batch [80/200] time 0.799 (0.773) data 0.000 (0.010) loss 1.3700 (0.6976) lr 1.0000e-05 eta 1:57:25
epoch [5/50] batch [100/200] time 0.789 (0.777) data 0.000 (0.008) loss 0.1474 (0.6963) lr 1.0000e-05 eta 1:57:54
epoch [5/50] batch [120/200] time 0.800 (0.780) data 0.000 (0.007) loss 0.2360 (0.6979) lr 1.0000e-05 eta 1:58:05
epoch [5/50] batch [140/200] time 0.784 (0.782) data 0.000 (0.006) loss 0.0378 (0.6736) lr 1.0000e-05 eta 1:58:09
epoch [5/50] batch [160/200] time 0.799 (0.784) data 0.000 (0.005) loss 0.4605 (0.6825) lr 1.0000e-05 eta 1:58:09
epoch [5/50] batch [180/200] time 0.799 (0.785) data 0.000 (0.005) loss 0.3201 (0.6800) lr 1.0000e-05 eta 1:58:04
epoch [5/50] batch [200/200] time 0.797 (0.786) data 0.000 (0.004) loss 0.0234 (0.6750) lr 2.0000e-03 eta 1:57:55
epoch [6/50] batch [20/200] time 0.788 (0.831) data 0.000 (0.036) loss 0.6148 (0.7885) lr 2.0000e-03 eta 2:04:19
epoch [6/50] batch [40/200] time 0.814 (0.813) data 0.001 (0.018) loss 2.1228 (0.9261) lr 2.0000e-03 eta 2:01:21
epoch [6/50] batch [60/200] time 0.783 (0.765) data 0.000 (0.012) loss 0.0108 (0.8463) lr 2.0000e-03 eta 1:53:58
epoch [6/50] batch [80/200] time 0.798 (0.772) data 0.000 (0.009) loss 0.0962 (0.7878) lr 2.0000e-03 eta 1:54:48
epoch [6/50] batch [100/200] time 0.802 (0.777) data 0.000 (0.007) loss 0.1823 (0.7723) lr 2.0000e-03 eta 1:55:16
epoch [6/50] batch [120/200] time 0.801 (0.780) data 0.000 (0.006) loss 0.1490 (0.7596) lr 2.0000e-03 eta 1:55:26
epoch [6/50] batch [140/200] time 0.780 (0.781) data 0.002 (0.006) loss 0.0727 (0.7200) lr 2.0000e-03 eta 1:55:22
epoch [6/50] batch [160/200] time 0.789 (0.782) data 0.000 (0.005) loss 1.6170 (0.7141) lr 2.0000e-03 eta 1:55:14
epoch [6/50] batch [180/200] time 0.750 (0.783) data 0.000 (0.004) loss 0.5798 (0.7209) lr 2.0000e-03 eta 1:55:03
epoch [6/50] batch [200/200] time 0.797 (0.784) data 0.000 (0.004) loss 0.0548 (0.7018) lr 1.9980e-03 eta 1:54:57
epoch [7/50] batch [20/200] time 0.801 (0.831) data 0.000 (0.036) loss 0.5522 (0.4168) lr 1.9980e-03 eta 2:01:37
epoch [7/50] batch [40/200] time 0.795 (0.813) data 0.000 (0.019) loss 0.0123 (0.4365) lr 1.9980e-03 eta 1:58:42
epoch [7/50] batch [60/200] time 0.782 (0.807) data 0.003 (0.013) loss 1.4572 (0.5408) lr 1.9980e-03 eta 1:57:33
epoch [7/50] batch [80/200] time 0.801 (0.773) data 0.000 (0.010) loss 0.4011 (0.5358) lr 1.9980e-03 eta 1:52:20
epoch [7/50] batch [100/200] time 0.792 (0.777) data 0.000 (0.008) loss 0.3446 (0.5103) lr 1.9980e-03 eta 1:52:36
epoch [7/50] batch [120/200] time 0.773 (0.779) data 0.000 (0.007) loss 0.0192 (0.5236) lr 1.9980e-03 eta 1:52:40
epoch [7/50] batch [140/200] time 0.802 (0.781) data 0.000 (0.006) loss 0.0913 (0.5328) lr 1.9980e-03 eta 1:52:42
epoch [7/50] batch [160/200] time 0.800 (0.783) data 0.000 (0.005) loss 0.0029 (0.5387) lr 1.9980e-03 eta 1:52:41
epoch [7/50] batch [180/200] time 0.797 (0.784) data 0.000 (0.005) loss 0.1137 (0.5217) lr 1.9980e-03 eta 1:52:36
epoch [7/50] batch [200/200] time 0.789 (0.785) data 0.000 (0.004) loss 0.0076 (0.5113) lr 1.9921e-03 eta 1:52:29
epoch [8/50] batch [20/200] time 0.801 (0.852) data 0.000 (0.059) loss 0.0225 (0.6328) lr 1.9921e-03 eta 2:01:53
epoch [8/50] batch [40/200] time 0.507 (0.816) data 0.000 (0.030) loss 0.6090 (0.6565) lr 1.9921e-03 eta 1:56:29
epoch [8/50] batch [60/200] time 0.807 (0.804) data 0.000 (0.020) loss 0.0059 (0.6067) lr 1.9921e-03 eta 1:54:28
epoch [8/50] batch [80/200] time 0.531 (0.800) data 0.000 (0.015) loss 0.1472 (0.6101) lr 1.9921e-03 eta 1:53:32
epoch [8/50] batch [100/200] time 0.819 (0.783) data 0.000 (0.012) loss 0.0313 (0.5938) lr 1.9921e-03 eta 1:50:53
epoch [8/50] batch [120/200] time 0.810 (0.787) data 0.000 (0.010) loss 0.0249 (0.5707) lr 1.9921e-03 eta 1:51:14
epoch [8/50] batch [140/200] time 0.808 (0.780) data 0.000 (0.009) loss 0.9255 (0.5801) lr 1.9921e-03 eta 1:50:01
epoch [8/50] batch [160/200] time 0.806 (0.782) data 0.000 (0.008) loss 0.5814 (0.5606) lr 1.9921e-03 eta 1:50:01
epoch [8/50] batch [180/200] time 0.793 (0.784) data 0.000 (0.007) loss 0.5789 (0.5517) lr 1.9921e-03 eta 1:49:57
epoch [8/50] batch [200/200] time 0.794 (0.784) data 0.000 (0.006) loss 0.0021 (0.5504) lr 1.9823e-03 eta 1:49:49
epoch [9/50] batch [20/200] time 0.808 (0.828) data 0.008 (0.030) loss 0.0652 (0.6150) lr 1.9823e-03 eta 1:55:35
epoch [9/50] batch [40/200] time 0.784 (0.811) data 0.011 (0.016) loss 0.2776 (0.5515) lr 1.9823e-03 eta 1:52:56
epoch [9/50] batch [60/200] time 0.792 (0.806) data 0.000 (0.011) loss 0.0067 (0.5794) lr 1.9823e-03 eta 1:52:01
epoch [9/50] batch [80/200] time 0.797 (0.803) data 0.000 (0.009) loss 0.4707 (0.5204) lr 1.9823e-03 eta 1:51:17
epoch [9/50] batch [100/200] time 0.504 (0.783) data 0.001 (0.007) loss 0.0246 (0.4680) lr 1.9823e-03 eta 1:48:15
epoch [9/50] batch [120/200] time 0.797 (0.780) data 0.000 (0.006) loss 0.5109 (0.4864) lr 1.9823e-03 eta 1:47:35
epoch [9/50] batch [140/200] time 0.798 (0.781) data 0.000 (0.005) loss 0.0912 (0.4759) lr 1.9823e-03 eta 1:47:34
epoch [9/50] batch [160/200] time 0.789 (0.783) data 0.000 (0.005) loss 0.0023 (0.4776) lr 1.9823e-03 eta 1:47:30
epoch [9/50] batch [180/200] time 0.809 (0.784) data 0.000 (0.004) loss 0.0115 (0.4975) lr 1.9823e-03 eta 1:47:24
epoch [9/50] batch [200/200] time 0.796 (0.785) data 0.000 (0.004) loss 0.0094 (0.5018) lr 1.9686e-03 eta 1:47:19
epoch [10/50] batch [20/200] time 0.798 (0.828) data 0.000 (0.033) loss 1.6272 (0.4856) lr 1.9686e-03 eta 1:52:50
epoch [10/50] batch [40/200] time 0.802 (0.814) data 0.000 (0.017) loss 0.0772 (0.4142) lr 1.9686e-03 eta 1:50:39
epoch [10/50] batch [60/200] time 0.808 (0.807) data 0.013 (0.012) loss 0.7800 (0.4460) lr 1.9686e-03 eta 1:49:29
epoch [10/50] batch [80/200] time 0.802 (0.804) data 0.000 (0.009) loss 0.6755 (0.5014) lr 1.9686e-03 eta 1:48:50
epoch [10/50] batch [100/200] time 0.807 (0.801) data 0.000 (0.008) loss 0.1426 (0.4935) lr 1.9686e-03 eta 1:48:09
epoch [10/50] batch [120/200] time 0.537 (0.781) data 0.000 (0.007) loss 0.6859 (0.4635) lr 1.9686e-03 eta 1:45:09
epoch [10/50] batch [140/200] time 0.522 (0.746) data 0.000 (0.006) loss 0.0231 (0.4696) lr 1.9686e-03 eta 1:40:11
epoch [10/50] batch [160/200] time 0.528 (0.724) data 0.000 (0.005) loss 0.1234 (0.4509) lr 1.9686e-03 eta 1:36:57
epoch [10/50] batch [180/200] time 0.525 (0.706) data 0.000 (0.005) loss 0.0217 (0.4586) lr 1.9686e-03 eta 1:34:21
epoch [10/50] batch [200/200] time 0.528 (0.692) data 0.000 (0.004) loss 0.3087 (0.4758) lr 1.9511e-03 eta 1:32:12
epoch [11/50] batch [20/200] time 0.534 (0.607) data 0.000 (0.038) loss 0.7728 (0.4840) lr 1.9511e-03 eta 1:20:42
epoch [11/50] batch [40/200] time 0.536 (0.593) data 0.000 (0.019) loss 0.1913 (0.4187) lr 1.9511e-03 eta 1:18:40
epoch [11/50] batch [60/200] time 0.683 (0.594) data 0.001 (0.013) loss 0.0209 (0.4066) lr 1.9511e-03 eta 1:18:38
epoch [11/50] batch [80/200] time 0.660 (0.588) data 0.000 (0.010) loss 0.1459 (0.3661) lr 1.9511e-03 eta 1:17:40
epoch [11/50] batch [100/200] time 0.536 (0.588) data 0.000 (0.008) loss 0.5626 (0.3785) lr 1.9511e-03 eta 1:17:23
epoch [11/50] batch [120/200] time 0.556 (0.579) data 0.000 (0.007) loss 0.8948 (0.4271) lr 1.9511e-03 eta 1:16:02
epoch [11/50] batch [140/200] time 0.537 (0.574) data 0.000 (0.006) loss 0.6058 (0.4097) lr 1.9511e-03 eta 1:15:09
epoch [11/50] batch [160/200] time 0.827 (0.574) data 0.000 (0.005) loss 0.5985 (0.4145) lr 1.9511e-03 eta 1:14:57
epoch [11/50] batch [180/200] time 0.524 (0.573) data 0.000 (0.004) loss 0.0428 (0.4063) lr 1.9511e-03 eta 1:14:43
epoch [11/50] batch [200/200] time 0.536 (0.575) data 0.000 (0.004) loss 0.0307 (0.3968) lr 1.9298e-03 eta 1:14:46
epoch [12/50] batch [20/200] time 0.604 (0.631) data 0.000 (0.035) loss 0.9674 (0.7118) lr 1.9298e-03 eta 1:21:51
epoch [12/50] batch [40/200] time 0.530 (0.596) data 0.000 (0.017) loss 0.3190 (0.7097) lr 1.9298e-03 eta 1:17:01
epoch [12/50] batch [60/200] time 0.534 (0.593) data 0.001 (0.012) loss 0.3996 (0.6205) lr 1.9298e-03 eta 1:16:26
epoch [12/50] batch [80/200] time 0.546 (0.593) data 0.000 (0.009) loss 0.7825 (0.5896) lr 1.9298e-03 eta 1:16:18
epoch [12/50] batch [100/200] time 0.512 (0.579) data 0.000 (0.007) loss 0.0034 (0.6432) lr 1.9298e-03 eta 1:14:17
epoch [12/50] batch [120/200] time 0.556 (0.573) data 0.000 (0.006) loss 0.0403 (0.5936) lr 1.9298e-03 eta 1:13:22
epoch [12/50] batch [140/200] time 0.769 (0.591) data 0.000 (0.005) loss 0.0067 (0.5936) lr 1.9298e-03 eta 1:15:28
epoch [12/50] batch [160/200] time 0.762 (0.614) data 0.000 (0.005) loss 0.0192 (0.5757) lr 1.9298e-03 eta 1:18:07
epoch [12/50] batch [180/200] time 0.762 (0.631) data 0.000 (0.004) loss 0.6243 (0.5546) lr 1.9298e-03 eta 1:20:06
epoch [12/50] batch [200/200] time 0.769 (0.639) data 0.000 (0.004) loss 0.7179 (0.5342) lr 1.9048e-03 eta 1:20:55
epoch [13/50] batch [20/200] time 0.762 (0.803) data 0.000 (0.035) loss 1.0146 (0.5417) lr 1.9048e-03 eta 1:41:28
epoch [13/50] batch [40/200] time 0.763 (0.787) data 0.000 (0.018) loss 1.7893 (0.4532) lr 1.9048e-03 eta 1:39:10
epoch [13/50] batch [60/200] time 0.783 (0.781) data 0.000 (0.012) loss 0.0025 (0.3931) lr 1.9048e-03 eta 1:38:06
epoch [13/50] batch [80/200] time 0.766 (0.766) data 0.000 (0.009) loss 0.2205 (0.4314) lr 1.9048e-03 eta 1:36:01
epoch [13/50] batch [100/200] time 0.764 (0.766) data 0.000 (0.007) loss 0.6660 (0.4143) lr 1.9048e-03 eta 1:35:45
epoch [13/50] batch [120/200] time 0.756 (0.766) data 0.000 (0.006) loss 0.0045 (0.3858) lr 1.9048e-03 eta 1:35:32
epoch [13/50] batch [140/200] time 0.775 (0.761) data 0.000 (0.005) loss 0.1431 (0.3847) lr 1.9048e-03 eta 1:34:35
epoch [13/50] batch [160/200] time 0.792 (0.755) data 0.000 (0.005) loss 0.1103 (0.3906) lr 1.9048e-03 eta 1:33:36
epoch [13/50] batch [180/200] time 0.773 (0.758) data 0.000 (0.004) loss 0.8868 (0.3941) lr 1.9048e-03 eta 1:33:42
epoch [13/50] batch [200/200] time 0.786 (0.760) data 0.000 (0.004) loss 0.8372 (0.3922) lr 1.8763e-03 eta 1:33:43
epoch [14/50] batch [20/200] time 0.791 (0.751) data 0.000 (0.037) loss 0.0787 (0.3668) lr 1.8763e-03 eta 1:32:20
epoch [14/50] batch [40/200] time 0.767 (0.725) data 0.000 (0.019) loss 0.5408 (0.3574) lr 1.8763e-03 eta 1:28:52
epoch [14/50] batch [60/200] time 0.771 (0.737) data 0.001 (0.013) loss 0.0165 (0.3514) lr 1.8763e-03 eta 1:30:08
epoch [14/50] batch [80/200] time 0.641 (0.734) data 0.000 (0.010) loss 0.4938 (0.3640) lr 1.8763e-03 eta 1:29:30
epoch [14/50] batch [100/200] time 0.754 (0.739) data 0.000 (0.008) loss 0.5148 (0.3622) lr 1.8763e-03 eta 1:29:56
epoch [14/50] batch [120/200] time 0.756 (0.743) data 0.000 (0.007) loss 0.6694 (0.3587) lr 1.8763e-03 eta 1:30:07
epoch [14/50] batch [140/200] time 0.765 (0.746) data 0.000 (0.006) loss 0.5330 (0.4052) lr 1.8763e-03 eta 1:30:15
epoch [14/50] batch [160/200] time 0.770 (0.740) data 0.000 (0.005) loss 0.0367 (0.4100) lr 1.8763e-03 eta 1:29:19
epoch [14/50] batch [180/200] time 0.776 (0.743) data 0.000 (0.005) loss 2.1852 (0.4484) lr 1.8763e-03 eta 1:29:28
epoch [14/50] batch [200/200] time 0.763 (0.746) data 0.000 (0.004) loss 0.2315 (0.4422) lr 1.8443e-03 eta 1:29:30
epoch [15/50] batch [20/200] time 0.718 (0.771) data 0.000 (0.034) loss 0.0086 (0.5906) lr 1.8443e-03 eta 1:32:18
epoch [15/50] batch [40/200] time 0.762 (0.760) data 0.003 (0.017) loss 0.0084 (0.5256) lr 1.8443e-03 eta 1:30:38
epoch [15/50] batch [60/200] time 0.773 (0.762) data 0.000 (0.012) loss 0.1055 (0.5029) lr 1.8443e-03 eta 1:30:41
epoch [15/50] batch [80/200] time 0.770 (0.763) data 0.000 (0.009) loss 0.3253 (0.5418) lr 1.8443e-03 eta 1:30:33
epoch [15/50] batch [100/200] time 0.756 (0.753) data 0.000 (0.007) loss 1.2663 (0.5462) lr 1.8443e-03 eta 1:29:08
epoch [15/50] batch [120/200] time 0.759 (0.756) data 0.000 (0.006) loss 1.2869 (0.5344) lr 1.8443e-03 eta 1:29:09
epoch [15/50] batch [140/200] time 0.762 (0.757) data 0.000 (0.005) loss 0.1921 (0.5264) lr 1.8443e-03 eta 1:29:04
epoch [15/50] batch [160/200] time 0.774 (0.758) data 0.000 (0.004) loss 0.0773 (0.4971) lr 1.8443e-03 eta 1:28:57
epoch [15/50] batch [180/200] time 0.682 (0.742) data 0.000 (0.004) loss 0.8080 (0.4951) lr 1.8443e-03 eta 1:26:49
epoch [15/50] batch [200/200] time 0.540 (0.728) data 0.000 (0.004) loss 0.0072 (0.4782) lr 1.8090e-03 eta 1:24:53
epoch [16/50] batch [20/200] time 0.558 (0.574) data 0.000 (0.033) loss 0.8851 (0.3665) lr 1.8090e-03 eta 1:06:47
epoch [16/50] batch [40/200] time 0.642 (0.563) data 0.000 (0.017) loss 0.6130 (0.3731) lr 1.8090e-03 eta 1:05:17
epoch [16/50] batch [60/200] time 0.544 (0.592) data 0.000 (0.012) loss 0.0064 (0.3255) lr 1.8090e-03 eta 1:08:25
epoch [16/50] batch [80/200] time 0.548 (0.576) data 0.000 (0.009) loss 0.8281 (0.4122) lr 1.8090e-03 eta 1:06:26
epoch [16/50] batch [100/200] time 0.742 (0.580) data 0.000 (0.007) loss 1.4308 (0.4733) lr 1.8090e-03 eta 1:06:43
epoch [16/50] batch [120/200] time 0.742 (0.607) data 0.000 (0.006) loss 0.1568 (0.4742) lr 1.8090e-03 eta 1:09:35
epoch [16/50] batch [140/200] time 0.732 (0.621) data 0.000 (0.005) loss 0.0430 (0.4504) lr 1.8090e-03 eta 1:10:59
epoch [16/50] batch [160/200] time 0.730 (0.632) data 0.001 (0.005) loss 0.0382 (0.4446) lr 1.8090e-03 eta 1:12:02
epoch [16/50] batch [180/200] time 0.738 (0.644) data 0.000 (0.004) loss 0.5175 (0.4606) lr 1.8090e-03 eta 1:13:11
epoch [16/50] batch [200/200] time 0.751 (0.651) data 0.000 (0.004) loss 0.0026 (0.4568) lr 1.7705e-03 eta 1:13:45
epoch [17/50] batch [20/200] time 0.741 (0.719) data 0.000 (0.033) loss 2.0847 (0.3653) lr 1.7705e-03 eta 1:21:15
epoch [17/50] batch [40/200] time 0.535 (0.723) data 0.000 (0.017) loss 1.3188 (0.4277) lr 1.7705e-03 eta 1:21:29
epoch [17/50] batch [60/200] time 0.739 (0.717) data 0.001 (0.011) loss 0.0074 (0.4657) lr 1.7705e-03 eta 1:20:33
epoch [17/50] batch [80/200] time 0.733 (0.711) data 0.000 (0.009) loss 1.4416 (0.4710) lr 1.7705e-03 eta 1:19:35
epoch [17/50] batch [100/200] time 0.746 (0.716) data 0.000 (0.007) loss 0.0467 (0.4633) lr 1.7705e-03 eta 1:19:56
epoch [17/50] batch [120/200] time 0.729 (0.714) data 0.000 (0.006) loss 0.0034 (0.4594) lr 1.7705e-03 eta 1:19:30
epoch [17/50] batch [140/200] time 0.745 (0.714) data 0.000 (0.005) loss 0.0049 (0.4393) lr 1.7705e-03 eta 1:19:13
epoch [17/50] batch [160/200] time 0.739 (0.717) data 0.000 (0.005) loss 0.2063 (0.4322) lr 1.7705e-03 eta 1:19:23
epoch [17/50] batch [180/200] time 0.530 (0.704) data 0.000 (0.004) loss 0.1825 (0.4204) lr 1.7705e-03 eta 1:17:42
epoch [17/50] batch [200/200] time 0.525 (0.687) data 0.000 (0.004) loss 0.2409 (0.4260) lr 1.7290e-03 eta 1:15:36
epoch [18/50] batch [20/200] time 0.564 (0.585) data 0.002 (0.035) loss 0.7471 (0.5666) lr 1.7290e-03 eta 1:04:11
epoch [18/50] batch [40/200] time 0.553 (0.575) data 0.000 (0.018) loss 0.8650 (0.5331) lr 1.7290e-03 eta 1:02:49
epoch [18/50] batch [60/200] time 0.544 (0.564) data 0.000 (0.012) loss 0.0036 (0.5640) lr 1.7290e-03 eta 1:01:30
epoch [18/50] batch [80/200] time 0.528 (0.567) data 0.000 (0.009) loss 0.0111 (0.5022) lr 1.7290e-03 eta 1:01:39
epoch [18/50] batch [100/200] time 0.682 (0.572) data 0.000 (0.007) loss 0.0455 (0.4904) lr 1.7290e-03 eta 1:01:59
epoch [18/50] batch [120/200] time 0.547 (0.588) data 0.000 (0.006) loss 0.3203 (0.4703) lr 1.7290e-03 eta 1:03:29
epoch [18/50] batch [140/200] time 0.544 (0.581) data 0.004 (0.005) loss 0.1232 (0.4509) lr 1.7290e-03 eta 1:02:30
epoch [18/50] batch [160/200] time 0.554 (0.577) data 0.000 (0.005) loss 0.0008 (0.4343) lr 1.7290e-03 eta 1:01:53
epoch [18/50] batch [180/200] time 0.540 (0.584) data 0.000 (0.004) loss 1.1127 (0.4440) lr 1.7290e-03 eta 1:02:28
epoch [18/50] batch [200/200] time 0.524 (0.579) data 0.000 (0.004) loss 0.0011 (0.4264) lr 1.6845e-03 eta 1:01:47
epoch [19/50] batch [20/200] time 0.679 (0.594) data 0.000 (0.034) loss 0.1441 (0.5804) lr 1.6845e-03 eta 1:03:09
epoch [19/50] batch [40/200] time 0.751 (0.668) data 0.000 (0.017) loss 0.8717 (0.5112) lr 1.6845e-03 eta 1:10:45
epoch [19/50] batch [60/200] time 0.749 (0.625) data 0.001 (0.012) loss 0.0015 (0.5429) lr 1.6845e-03 eta 1:05:59
epoch [19/50] batch [80/200] time 0.755 (0.656) data 0.000 (0.009) loss 0.2878 (0.5548) lr 1.6845e-03 eta 1:09:08
epoch [19/50] batch [100/200] time 0.732 (0.661) data 0.000 (0.007) loss 0.7645 (0.4995) lr 1.6845e-03 eta 1:09:24
epoch [19/50] batch [120/200] time 0.558 (0.672) data 0.000 (0.006) loss 0.0029 (0.5073) lr 1.6845e-03 eta 1:10:19
epoch [19/50] batch [140/200] time 0.743 (0.672) data 0.000 (0.005) loss 0.0810 (0.4912) lr 1.6845e-03 eta 1:10:05
epoch [19/50] batch [160/200] time 0.743 (0.672) data 0.000 (0.005) loss 0.2225 (0.4711) lr 1.6845e-03 eta 1:09:51
epoch [19/50] batch [180/200] time 0.751 (0.679) data 0.000 (0.004) loss 0.6006 (0.4791) lr 1.6845e-03 eta 1:10:22
epoch [19/50] batch [200/200] time 0.732 (0.678) data 0.000 (0.004) loss 0.0013 (0.4885) lr 1.6374e-03 eta 1:10:04
epoch [20/50] batch [20/200] time 0.536 (0.718) data 0.000 (0.034) loss 0.0117 (0.4985) lr 1.6374e-03 eta 1:13:56
epoch [20/50] batch [40/200] time 0.748 (0.713) data 0.000 (0.017) loss 0.4522 (0.3888) lr 1.6374e-03 eta 1:13:11
epoch [20/50] batch [60/200] time 0.736 (0.707) data 0.000 (0.012) loss 0.5866 (0.3818) lr 1.6374e-03 eta 1:12:23
epoch [20/50] batch [80/200] time 0.602 (0.714) data 0.000 (0.009) loss 0.1685 (0.4125) lr 1.6374e-03 eta 1:12:51
epoch [20/50] batch [100/200] time 0.744 (0.712) data 0.000 (0.007) loss 0.0062 (0.4175) lr 1.6374e-03 eta 1:12:20
epoch [20/50] batch [120/200] time 0.544 (0.701) data 0.000 (0.006) loss 0.0036 (0.4135) lr 1.6374e-03 eta 1:11:01
epoch [20/50] batch [140/200] time 0.538 (0.684) data 0.000 (0.005) loss 0.0495 (0.4034) lr 1.6374e-03 eta 1:09:04
epoch [20/50] batch [160/200] time 0.506 (0.666) data 0.000 (0.005) loss 1.3410 (0.3874) lr 1.6374e-03 eta 1:07:04
epoch [20/50] batch [180/200] time 0.822 (0.655) data 0.000 (0.004) loss 1.1486 (0.4042) lr 1.6374e-03 eta 1:05:41
epoch [20/50] batch [200/200] time 0.528 (0.645) data 0.000 (0.004) loss 0.0263 (0.4118) lr 1.5878e-03 eta 1:04:30
epoch [21/50] batch [20/200] time 0.552 (0.571) data 0.000 (0.033) loss 0.0076 (0.3313) lr 1.5878e-03 eta 0:56:53
epoch [21/50] batch [40/200] time 0.820 (0.615) data 0.000 (0.017) loss 1.7120 (0.4952) lr 1.5878e-03 eta 1:01:04
epoch [21/50] batch [60/200] time 0.833 (0.684) data 0.000 (0.011) loss 0.0754 (0.4625) lr 1.5878e-03 eta 1:07:41
epoch [21/50] batch [80/200] time 0.810 (0.717) data 0.000 (0.009) loss 0.0012 (0.5143) lr 1.5878e-03 eta 1:10:42
epoch [21/50] batch [100/200] time 0.791 (0.736) data 0.000 (0.007) loss 0.4503 (0.4933) lr 1.5878e-03 eta 1:12:23
epoch [21/50] batch [120/200] time 0.832 (0.750) data 0.000 (0.006) loss 0.4900 (0.4790) lr 1.5878e-03 eta 1:13:28
epoch [21/50] batch [140/200] time 0.815 (0.760) data 0.000 (0.005) loss 0.0718 (0.4784) lr 1.5878e-03 eta 1:14:12
epoch [21/50] batch [160/200] time 0.798 (0.766) data 0.000 (0.004) loss 0.0460 (0.4563) lr 1.5878e-03 eta 1:14:35
epoch [21/50] batch [180/200] time 0.822 (0.771) data 0.000 (0.004) loss 0.1567 (0.4460) lr 1.5878e-03 eta 1:14:48
epoch [21/50] batch [200/200] time 0.812 (0.775) data 0.000 (0.004) loss 0.4380 (0.4310) lr 1.5358e-03 eta 1:14:57
epoch [22/50] batch [20/200] time 0.814 (0.852) data 0.000 (0.033) loss 1.7963 (0.4277) lr 1.5358e-03 eta 1:22:06
epoch [22/50] batch [40/200] time 0.812 (0.834) data 0.000 (0.017) loss 0.0266 (0.3626) lr 1.5358e-03 eta 1:20:04
epoch [22/50] batch [60/200] time 0.829 (0.828) data 0.001 (0.011) loss 0.0029 (0.3636) lr 1.5358e-03 eta 1:19:13
epoch [22/50] batch [80/200] time 0.810 (0.824) data 0.000 (0.009) loss 0.0075 (0.3593) lr 1.5358e-03 eta 1:18:34
epoch [22/50] batch [100/200] time 0.794 (0.822) data 0.000 (0.007) loss 0.0928 (0.3492) lr 1.5358e-03 eta 1:18:06
epoch [22/50] batch [120/200] time 0.818 (0.822) data 0.000 (0.006) loss 0.0393 (0.3405) lr 1.5358e-03 eta 1:17:48
epoch [22/50] batch [140/200] time 0.817 (0.821) data 0.000 (0.005) loss 0.1235 (0.3452) lr 1.5358e-03 eta 1:17:27
epoch [22/50] batch [160/200] time 0.826 (0.821) data 0.000 (0.005) loss 0.0568 (0.3687) lr 1.5358e-03 eta 1:17:08
epoch [22/50] batch [180/200] time 0.828 (0.820) data 0.000 (0.004) loss 0.1300 (0.3559) lr 1.5358e-03 eta 1:16:50
epoch [22/50] batch [200/200] time 0.821 (0.820) data 0.000 (0.004) loss 0.1382 (0.3533) lr 1.4818e-03 eta 1:16:31
epoch [23/50] batch [20/200] time 0.798 (0.844) data 0.000 (0.033) loss 0.0012 (0.6764) lr 1.4818e-03 eta 1:18:30
epoch [23/50] batch [40/200] time 0.818 (0.829) data 0.000 (0.016) loss 1.4278 (0.4836) lr 1.4818e-03 eta 1:16:49
epoch [23/50] batch [60/200] time 0.816 (0.825) data 0.000 (0.011) loss 0.0004 (0.4279) lr 1.4818e-03 eta 1:16:12
epoch [23/50] batch [80/200] time 0.819 (0.823) data 0.000 (0.008) loss 0.0426 (0.4110) lr 1.4818e-03 eta 1:15:41
epoch [23/50] batch [100/200] time 0.813 (0.821) data 0.000 (0.007) loss 0.0797 (0.3966) lr 1.4818e-03 eta 1:15:14
epoch [23/50] batch [120/200] time 0.807 (0.819) data 0.000 (0.006) loss 0.0025 (0.4157) lr 1.4818e-03 eta 1:14:50
epoch [23/50] batch [140/200] time 0.813 (0.820) data 0.000 (0.005) loss 1.6968 (0.4233) lr 1.4818e-03 eta 1:14:36
epoch [23/50] batch [160/200] time 0.815 (0.820) data 0.000 (0.004) loss 0.0005 (0.4138) lr 1.4818e-03 eta 1:14:20
epoch [23/50] batch [180/200] time 0.821 (0.820) data 0.000 (0.004) loss 0.0787 (0.4025) lr 1.4818e-03 eta 1:14:03
epoch [23/50] batch [200/200] time 0.821 (0.820) data 0.000 (0.004) loss 1.0927 (0.4176) lr 1.4258e-03 eta 1:13:45
epoch [24/50] batch [20/200] time 0.818 (0.854) data 0.000 (0.033) loss 0.0026 (0.5962) lr 1.4258e-03 eta 1:16:35
epoch [24/50] batch [40/200] time 0.810 (0.837) data 0.000 (0.017) loss 0.0089 (0.4819) lr 1.4258e-03 eta 1:14:48
epoch [24/50] batch [60/200] time 0.821 (0.831) data 0.000 (0.011) loss 0.5661 (0.4058) lr 1.4258e-03 eta 1:13:57
epoch [24/50] batch [80/200] time 0.824 (0.828) data 0.000 (0.009) loss 0.0035 (0.3696) lr 1.4258e-03 eta 1:13:24
epoch [24/50] batch [100/200] time 0.817 (0.825) data 0.000 (0.007) loss 0.5445 (0.4358) lr 1.4258e-03 eta 1:12:53
epoch [24/50] batch [120/200] time 0.826 (0.824) data 0.000 (0.006) loss 0.0041 (0.3976) lr 1.4258e-03 eta 1:12:32
epoch [24/50] batch [140/200] time 0.824 (0.824) data 0.000 (0.005) loss 0.4703 (0.4105) lr 1.4258e-03 eta 1:12:11
epoch [24/50] batch [160/200] time 0.805 (0.817) data 0.000 (0.004) loss 0.3546 (0.4446) lr 1.4258e-03 eta 1:11:20
epoch [24/50] batch [180/200] time 0.831 (0.819) data 0.002 (0.004) loss 2.0713 (0.4604) lr 1.4258e-03 eta 1:11:15
epoch [24/50] batch [200/200] time 0.817 (0.821) data 0.000 (0.004) loss 0.0272 (0.4393) lr 1.3681e-03 eta 1:11:07
epoch [25/50] batch [20/200] time 0.823 (0.872) data 0.000 (0.037) loss 1.6268 (0.3260) lr 1.3681e-03 eta 1:15:18
epoch [25/50] batch [40/200] time 0.538 (0.830) data 0.000 (0.019) loss 0.3482 (0.3991) lr 1.3681e-03 eta 1:11:20
epoch [25/50] batch [60/200] time 0.824 (0.822) data 0.001 (0.013) loss 0.0029 (0.3740) lr 1.3681e-03 eta 1:10:26
epoch [25/50] batch [80/200] time 0.807 (0.820) data 0.000 (0.010) loss 0.8591 (0.3916) lr 1.3681e-03 eta 1:09:59
epoch [25/50] batch [100/200] time 0.792 (0.819) data 0.000 (0.008) loss 0.0152 (0.3932) lr 1.3681e-03 eta 1:09:34
epoch [25/50] batch [120/200] time 0.813 (0.818) data 0.000 (0.007) loss 0.0160 (0.3775) lr 1.3681e-03 eta 1:09:15
epoch [25/50] batch [140/200] time 0.825 (0.818) data 0.000 (0.006) loss 0.0515 (0.3744) lr 1.3681e-03 eta 1:09:01
epoch [25/50] batch [160/200] time 0.804 (0.818) data 0.000 (0.005) loss 0.0986 (0.4070) lr 1.3681e-03 eta 1:08:42
epoch [25/50] batch [180/200] time 0.817 (0.818) data 0.000 (0.004) loss 0.7796 (0.4096) lr 1.3681e-03 eta 1:08:24
epoch [25/50] batch [200/200] time 0.821 (0.817) data 0.000 (0.004) loss 0.0401 (0.4075) lr 1.3090e-03 eta 1:08:07
epoch [26/50] batch [20/200] time 0.840 (0.856) data 0.000 (0.036) loss 0.9313 (0.4617) lr 1.3090e-03 eta 1:11:00
epoch [26/50] batch [40/200] time 0.827 (0.840) data 0.000 (0.018) loss 0.2288 (0.4795) lr 1.3090e-03 eta 1:09:25
epoch [26/50] batch [60/200] time 0.793 (0.817) data 0.001 (0.013) loss 0.0310 (0.4228) lr 1.3090e-03 eta 1:07:14
epoch [26/50] batch [80/200] time 0.830 (0.822) data 0.000 (0.009) loss 0.0443 (0.4054) lr 1.3090e-03 eta 1:07:25
epoch [26/50] batch [100/200] time 0.840 (0.825) data 0.000 (0.008) loss 0.8633 (0.4050) lr 1.3090e-03 eta 1:07:24
epoch [26/50] batch [120/200] time 0.838 (0.827) data 0.000 (0.006) loss 0.2520 (0.3674) lr 1.3090e-03 eta 1:07:17
epoch [26/50] batch [140/200] time 0.836 (0.829) data 0.000 (0.006) loss 0.1984 (0.3662) lr 1.3090e-03 eta 1:07:08
epoch [26/50] batch [160/200] time 0.827 (0.823) data 0.000 (0.005) loss 0.1783 (0.3771) lr 1.3090e-03 eta 1:06:23
epoch [26/50] batch [180/200] time 0.819 (0.823) data 0.000 (0.004) loss 0.0620 (0.3925) lr 1.3090e-03 eta 1:06:05
epoch [26/50] batch [200/200] time 0.805 (0.822) data 0.000 (0.004) loss 0.5629 (0.3863) lr 1.2487e-03 eta 1:05:44
epoch [27/50] batch [20/200] time 0.810 (0.847) data 0.000 (0.033) loss 0.4680 (0.3777) lr 1.2487e-03 eta 1:07:30
epoch [27/50] batch [40/200] time 0.802 (0.830) data 0.000 (0.017) loss 1.3690 (0.4188) lr 1.2487e-03 eta 1:05:51
epoch [27/50] batch [60/200] time 0.820 (0.825) data 0.000 (0.011) loss 0.2962 (0.4074) lr 1.2487e-03 eta 1:05:08
epoch [27/50] batch [80/200] time 0.823 (0.824) data 0.000 (0.009) loss 0.3183 (0.3779) lr 1.2487e-03 eta 1:04:48
epoch [27/50] batch [100/200] time 0.831 (0.824) data 0.000 (0.007) loss 0.9678 (0.3622) lr 1.2487e-03 eta 1:04:32
epoch [27/50] batch [120/200] time 0.806 (0.823) data 0.000 (0.006) loss 0.0019 (0.3854) lr 1.2487e-03 eta 1:04:10
epoch [27/50] batch [140/200] time 0.816 (0.822) data 0.000 (0.005) loss 0.9728 (0.3963) lr 1.2487e-03 eta 1:03:50
epoch [27/50] batch [160/200] time 0.820 (0.821) data 0.000 (0.004) loss 1.3530 (0.4144) lr 1.2487e-03 eta 1:03:31
epoch [27/50] batch [180/200] time 0.829 (0.822) data 0.000 (0.004) loss 0.0013 (0.3961) lr 1.2487e-03 eta 1:03:16
epoch [27/50] batch [200/200] time 0.816 (0.822) data 0.000 (0.004) loss 0.0370 (0.3992) lr 1.1874e-03 eta 1:03:00
epoch [28/50] batch [20/200] time 0.826 (0.853) data 0.000 (0.033) loss 0.0589 (0.2927) lr 1.1874e-03 eta 1:05:08
epoch [28/50] batch [40/200] time 0.815 (0.837) data 0.000 (0.017) loss 0.0696 (0.4331) lr 1.1874e-03 eta 1:03:34
epoch [28/50] batch [60/200] time 0.809 (0.829) data 0.000 (0.011) loss 0.6047 (0.4419) lr 1.1874e-03 eta 1:02:41
epoch [28/50] batch [80/200] time 0.802 (0.824) data 0.000 (0.008) loss 0.0123 (0.4279) lr 1.1874e-03 eta 1:02:04
epoch [28/50] batch [100/200] time 0.817 (0.823) data 0.000 (0.007) loss 0.4079 (0.3603) lr 1.1874e-03 eta 1:01:42
epoch [28/50] batch [120/200] time 0.801 (0.822) data 0.000 (0.006) loss 0.0401 (0.3560) lr 1.1874e-03 eta 1:01:22
epoch [28/50] batch [140/200] time 0.804 (0.821) data 0.000 (0.005) loss 0.4211 (0.4019) lr 1.1874e-03 eta 1:01:01
epoch [28/50] batch [160/200] time 0.809 (0.820) data 0.000 (0.004) loss 0.1062 (0.3827) lr 1.1874e-03 eta 1:00:39
epoch [28/50] batch [180/200] time 0.803 (0.819) data 0.000 (0.004) loss 0.0004 (0.3734) lr 1.1874e-03 eta 1:00:21
epoch [28/50] batch [200/200] time 0.829 (0.819) data 0.000 (0.004) loss 0.0477 (0.3853) lr 1.1253e-03 eta 1:00:05
epoch [29/50] batch [20/200] time 0.809 (0.852) data 0.000 (0.032) loss 0.8226 (0.5717) lr 1.1253e-03 eta 1:02:10
epoch [29/50] batch [40/200] time 0.803 (0.834) data 0.000 (0.017) loss 0.0110 (0.3612) lr 1.1253e-03 eta 1:00:34
epoch [29/50] batch [60/200] time 0.810 (0.827) data 0.001 (0.011) loss 1.5082 (0.3960) lr 1.1253e-03 eta 0:59:50
epoch [29/50] batch [80/200] time 0.829 (0.825) data 0.000 (0.008) loss 0.4393 (0.4058) lr 1.1253e-03 eta 0:59:23
epoch [29/50] batch [100/200] time 0.813 (0.823) data 0.000 (0.007) loss 1.4404 (0.3892) lr 1.1253e-03 eta 0:59:00
epoch [29/50] batch [120/200] time 0.818 (0.822) data 0.000 (0.006) loss 0.0010 (0.4044) lr 1.1253e-03 eta 0:58:36
epoch [29/50] batch [140/200] time 0.821 (0.821) data 0.000 (0.005) loss 0.2345 (0.3726) lr 1.1253e-03 eta 0:58:17
epoch [29/50] batch [160/200] time 0.817 (0.820) data 0.000 (0.004) loss 2.4295 (0.4011) lr 1.1253e-03 eta 0:57:56
epoch [29/50] batch [180/200] time 0.815 (0.819) data 0.000 (0.004) loss 0.0191 (0.3847) lr 1.1253e-03 eta 0:57:37
epoch [29/50] batch [200/200] time 0.820 (0.819) data 0.000 (0.004) loss 0.6089 (0.3915) lr 1.0628e-03 eta 0:57:18
epoch [30/50] batch [20/200] time 0.816 (0.854) data 0.000 (0.033) loss 0.0008 (0.3998) lr 1.0628e-03 eta 0:59:30
epoch [30/50] batch [40/200] time 0.817 (0.836) data 0.000 (0.017) loss 1.4768 (0.3843) lr 1.0628e-03 eta 0:57:59
epoch [30/50] batch [60/200] time 0.582 (0.826) data 0.000 (0.011) loss 0.3805 (0.3870) lr 1.0628e-03 eta 0:56:59
epoch [30/50] batch [80/200] time 0.842 (0.820) data 0.000 (0.009) loss 0.0033 (0.3575) lr 1.0628e-03 eta 0:56:17
epoch [30/50] batch [100/200] time 0.833 (0.824) data 0.000 (0.007) loss 0.0027 (0.3613) lr 1.0628e-03 eta 0:56:18
epoch [30/50] batch [120/200] time 0.828 (0.825) data 0.000 (0.006) loss 0.0788 (0.3723) lr 1.0628e-03 eta 0:56:07
epoch [30/50] batch [140/200] time 0.823 (0.826) data 0.000 (0.005) loss 0.0092 (0.3617) lr 1.0628e-03 eta 0:55:52
epoch [30/50] batch [160/200] time 0.814 (0.823) data 0.000 (0.005) loss 0.3542 (0.3762) lr 1.0628e-03 eta 0:55:23
epoch [30/50] batch [180/200] time 0.828 (0.822) data 0.000 (0.004) loss 0.0112 (0.3826) lr 1.0628e-03 eta 0:55:04
epoch [30/50] batch [200/200] time 0.808 (0.821) data 0.000 (0.004) loss 1.1496 (0.3914) lr 1.0000e-03 eta 0:54:45
epoch [31/50] batch [20/200] time 0.808 (0.848) data 0.000 (0.032) loss 0.0017 (0.3356) lr 1.0000e-03 eta 0:56:15
epoch [31/50] batch [40/200] time 0.833 (0.835) data 0.000 (0.017) loss 0.2517 (0.2946) lr 1.0000e-03 eta 0:55:06
epoch [31/50] batch [60/200] time 0.823 (0.829) data 0.001 (0.011) loss 0.0043 (0.4069) lr 1.0000e-03 eta 0:54:26
epoch [31/50] batch [80/200] time 0.811 (0.826) data 0.000 (0.008) loss 1.1922 (0.4786) lr 1.0000e-03 eta 0:53:56
epoch [31/50] batch [100/200] time 0.826 (0.824) data 0.000 (0.007) loss 0.6693 (0.4647) lr 1.0000e-03 eta 0:53:32
epoch [31/50] batch [120/200] time 0.836 (0.823) data 0.000 (0.006) loss 0.0076 (0.4351) lr 1.0000e-03 eta 0:53:11
epoch [31/50] batch [140/200] time 0.824 (0.823) data 0.000 (0.005) loss 0.0090 (0.4165) lr 1.0000e-03 eta 0:52:56
epoch [31/50] batch [160/200] time 0.820 (0.822) data 0.000 (0.004) loss 0.5722 (0.4190) lr 1.0000e-03 eta 0:52:38
epoch [31/50] batch [180/200] time 0.838 (0.815) data 0.000 (0.004) loss 0.2917 (0.4055) lr 1.0000e-03 eta 0:51:53
epoch [31/50] batch [200/200] time 0.832 (0.817) data 0.000 (0.004) loss 0.4767 (0.4150) lr 9.3721e-04 eta 0:51:45
epoch [32/50] batch [20/200] time 0.837 (0.873) data 0.000 (0.038) loss 1.0122 (0.4160) lr 9.3721e-04 eta 0:55:01
epoch [32/50] batch [40/200] time 0.840 (0.858) data 0.000 (0.019) loss 0.0083 (0.3658) lr 9.3721e-04 eta 0:53:44
epoch [32/50] batch [60/200] time 0.820 (0.831) data 0.000 (0.013) loss 0.0166 (0.4702) lr 9.3721e-04 eta 0:51:46
epoch [32/50] batch [80/200] time 0.801 (0.826) data 0.000 (0.010) loss 1.2626 (0.4927) lr 9.3721e-04 eta 0:51:14
epoch [32/50] batch [100/200] time 0.815 (0.825) data 0.000 (0.008) loss 0.0261 (0.4922) lr 9.3721e-04 eta 0:50:51
epoch [32/50] batch [120/200] time 0.800 (0.823) data 0.000 (0.007) loss 0.6897 (0.4757) lr 9.3721e-04 eta 0:50:28
epoch [32/50] batch [140/200] time 0.820 (0.822) data 0.000 (0.006) loss 0.5448 (0.4346) lr 9.3721e-04 eta 0:50:08
epoch [32/50] batch [160/200] time 0.821 (0.821) data 0.000 (0.005) loss 0.0076 (0.4346) lr 9.3721e-04 eta 0:49:49
epoch [32/50] batch [180/200] time 0.811 (0.821) data 0.000 (0.004) loss 0.0666 (0.4450) lr 9.3721e-04 eta 0:49:30
epoch [32/50] batch [200/200] time 0.815 (0.820) data 0.000 (0.004) loss 0.7181 (0.4492) lr 8.7467e-04 eta 0:49:11
epoch [33/50] batch [20/200] time 0.817 (0.850) data 0.000 (0.034) loss 1.1224 (0.4620) lr 8.7467e-04 eta 0:50:42
epoch [33/50] batch [40/200] time 0.801 (0.833) data 0.000 (0.017) loss 0.6353 (0.4126) lr 8.7467e-04 eta 0:49:26
epoch [33/50] batch [60/200] time 0.820 (0.828) data 0.001 (0.012) loss 0.1555 (0.3736) lr 8.7467e-04 eta 0:48:50
epoch [33/50] batch [80/200] time 0.806 (0.824) data 0.000 (0.009) loss 0.0240 (0.3525) lr 8.7467e-04 eta 0:48:22
epoch [33/50] batch [100/200] time 0.810 (0.823) data 0.000 (0.007) loss 0.0510 (0.4006) lr 8.7467e-04 eta 0:47:58
epoch [33/50] batch [120/200] time 0.817 (0.821) data 0.000 (0.006) loss 0.0221 (0.3695) lr 8.7467e-04 eta 0:47:37
epoch [33/50] batch [140/200] time 0.801 (0.820) data 0.000 (0.005) loss 0.4646 (0.3921) lr 8.7467e-04 eta 0:47:17
epoch [33/50] batch [160/200] time 0.824 (0.820) data 0.000 (0.005) loss 0.0376 (0.3739) lr 8.7467e-04 eta 0:47:00
epoch [33/50] batch [180/200] time 0.829 (0.820) data 0.000 (0.004) loss 0.1162 (0.4098) lr 8.7467e-04 eta 0:46:44
epoch [33/50] batch [200/200] time 0.828 (0.820) data 0.000 (0.004) loss 0.2543 (0.4061) lr 8.1262e-04 eta 0:46:27
epoch [34/50] batch [20/200] time 0.825 (0.854) data 0.000 (0.036) loss 0.3568 (0.4505) lr 8.1262e-04 eta 0:48:07
epoch [34/50] batch [40/200] time 0.815 (0.834) data 0.000 (0.018) loss 0.0123 (0.5542) lr 8.1262e-04 eta 0:46:43
epoch [34/50] batch [60/200] time 0.815 (0.830) data 0.001 (0.012) loss 0.0040 (0.4676) lr 8.1262e-04 eta 0:46:13
epoch [34/50] batch [80/200] time 0.812 (0.827) data 0.000 (0.009) loss 0.3463 (0.4753) lr 8.1262e-04 eta 0:45:46
epoch [34/50] batch [100/200] time 0.819 (0.826) data 0.000 (0.008) loss 0.0910 (0.4548) lr 8.1262e-04 eta 0:45:25
epoch [34/50] batch [120/200] time 0.821 (0.825) data 0.000 (0.006) loss 0.0124 (0.4279) lr 8.1262e-04 eta 0:45:05
epoch [34/50] batch [140/200] time 0.817 (0.824) data 0.000 (0.006) loss 0.0011 (0.4142) lr 8.1262e-04 eta 0:44:45
epoch [34/50] batch [160/200] time 0.823 (0.823) data 0.000 (0.005) loss 0.0437 (0.4091) lr 8.1262e-04 eta 0:44:27
epoch [34/50] batch [180/200] time 0.819 (0.823) data 0.000 (0.004) loss 0.0516 (0.4094) lr 8.1262e-04 eta 0:44:08
epoch [34/50] batch [200/200] time 0.834 (0.822) data 0.000 (0.004) loss 0.1308 (0.4196) lr 7.5131e-04 eta 0:43:50
epoch [35/50] batch [20/200] time 0.820 (0.851) data 0.000 (0.033) loss 0.2379 (0.2328) lr 7.5131e-04 eta 0:45:06
epoch [35/50] batch [40/200] time 0.833 (0.835) data 0.000 (0.017) loss 0.0007 (0.2419) lr 7.5131e-04 eta 0:43:58
epoch [35/50] batch [60/200] time 0.825 (0.831) data 0.000 (0.011) loss 0.5836 (0.2813) lr 7.5131e-04 eta 0:43:29
epoch [35/50] batch [80/200] time 0.808 (0.827) data 0.000 (0.009) loss 0.1144 (0.2983) lr 7.5131e-04 eta 0:43:00
epoch [35/50] batch [100/200] time 0.815 (0.826) data 0.000 (0.007) loss 0.2619 (0.3137) lr 7.5131e-04 eta 0:42:39
epoch [35/50] batch [120/200] time 0.811 (0.824) data 0.000 (0.006) loss 0.7807 (0.2873) lr 7.5131e-04 eta 0:42:18
epoch [35/50] batch [140/200] time 0.823 (0.824) data 0.000 (0.005) loss 0.3764 (0.2936) lr 7.5131e-04 eta 0:42:00
epoch [35/50] batch [160/200] time 0.823 (0.823) data 0.000 (0.004) loss 0.4867 (0.2841) lr 7.5131e-04 eta 0:41:42
epoch [35/50] batch [180/200] time 0.825 (0.819) data 0.000 (0.004) loss 0.6574 (0.2914) lr 7.5131e-04 eta 0:41:14
epoch [35/50] batch [200/200] time 0.846 (0.822) data 0.000 (0.004) loss 0.4804 (0.3327) lr 6.9098e-04 eta 0:41:05
epoch [36/50] batch [20/200] time 0.838 (0.875) data 0.000 (0.035) loss 0.0497 (0.1133) lr 6.9098e-04 eta 0:43:26
epoch [36/50] batch [40/200] time 0.852 (0.857) data 0.005 (0.018) loss 0.0032 (0.3216) lr 6.9098e-04 eta 0:42:15
epoch [36/50] batch [60/200] time 0.820 (0.836) data 0.000 (0.012) loss 0.0001 (0.3767) lr 6.9098e-04 eta 0:40:57
epoch [36/50] batch [80/200] time 0.799 (0.831) data 0.000 (0.009) loss 0.0762 (0.3721) lr 6.9098e-04 eta 0:40:25
epoch [36/50] batch [100/200] time 0.814 (0.828) data 0.000 (0.007) loss 0.0016 (0.3676) lr 6.9098e-04 eta 0:40:02
epoch [36/50] batch [120/200] time 0.818 (0.827) data 0.000 (0.006) loss 0.2362 (0.3515) lr 6.9098e-04 eta 0:39:41
epoch [36/50] batch [140/200] time 0.816 (0.826) data 0.000 (0.005) loss 0.1711 (0.3470) lr 6.9098e-04 eta 0:39:22
epoch [36/50] batch [160/200] time 0.820 (0.825) data 0.000 (0.005) loss 0.9755 (0.3853) lr 6.9098e-04 eta 0:39:03
epoch [36/50] batch [180/200] time 0.815 (0.824) data 0.000 (0.004) loss 0.1199 (0.3833) lr 6.9098e-04 eta 0:38:42
epoch [36/50] batch [200/200] time 0.816 (0.823) data 0.000 (0.004) loss 0.0034 (0.3863) lr 6.3188e-04 eta 0:38:24
epoch [37/50] batch [20/200] time 0.827 (0.857) data 0.000 (0.033) loss 0.0192 (0.3411) lr 6.3188e-04 eta 0:39:42
epoch [37/50] batch [40/200] time 0.815 (0.839) data 0.000 (0.017) loss 0.2592 (0.2999) lr 6.3188e-04 eta 0:38:36
epoch [37/50] batch [60/200] time 0.807 (0.831) data 0.000 (0.011) loss 1.0519 (0.3602) lr 6.3188e-04 eta 0:37:58
epoch [37/50] batch [80/200] time 0.829 (0.819) data 0.000 (0.009) loss 2.1980 (0.4241) lr 6.3188e-04 eta 0:37:07
epoch [37/50] batch [100/200] time 0.852 (0.823) data 0.000 (0.007) loss 0.0116 (0.3904) lr 6.3188e-04 eta 0:37:02
epoch [37/50] batch [120/200] time 0.845 (0.826) data 0.000 (0.006) loss 0.0093 (0.4005) lr 6.3188e-04 eta 0:36:52
epoch [37/50] batch [140/200] time 0.834 (0.828) data 0.000 (0.005) loss 0.1508 (0.3930) lr 6.3188e-04 eta 0:36:41
epoch [37/50] batch [160/200] time 0.609 (0.828) data 0.000 (0.005) loss 0.5645 (0.4260) lr 6.3188e-04 eta 0:36:25
epoch [37/50] batch [180/200] time 0.821 (0.821) data 0.000 (0.004) loss 1.1922 (0.4245) lr 6.3188e-04 eta 0:35:51
epoch [37/50] batch [200/200] time 0.824 (0.820) data 0.000 (0.004) loss 0.3915 (0.4057) lr 5.7422e-04 eta 0:35:32
epoch [38/50] batch [20/200] time 0.790 (0.845) data 0.000 (0.035) loss 0.0005 (0.4529) lr 5.7422e-04 eta 0:36:20
epoch [38/50] batch [40/200] time 0.819 (0.830) data 0.000 (0.018) loss 0.1617 (0.4963) lr 5.7422e-04 eta 0:35:24
epoch [38/50] batch [60/200] time 0.820 (0.825) data 0.000 (0.012) loss 0.1311 (0.4969) lr 5.7422e-04 eta 0:34:56
epoch [38/50] batch [80/200] time 0.807 (0.823) data 0.000 (0.009) loss 0.2386 (0.4726) lr 5.7422e-04 eta 0:34:33
epoch [38/50] batch [100/200] time 0.832 (0.822) data 0.000 (0.007) loss 0.0911 (0.4301) lr 5.7422e-04 eta 0:34:15
epoch [38/50] batch [120/200] time 0.830 (0.822) data 0.000 (0.006) loss 0.2427 (0.4419) lr 5.7422e-04 eta 0:33:59
epoch [38/50] batch [140/200] time 0.804 (0.821) data 0.000 (0.005) loss 0.0007 (0.4339) lr 5.7422e-04 eta 0:33:40
epoch [38/50] batch [160/200] time 0.813 (0.820) data 0.000 (0.005) loss 0.0056 (0.3903) lr 5.7422e-04 eta 0:33:20
epoch [38/50] batch [180/200] time 0.822 (0.820) data 0.000 (0.004) loss 0.0023 (0.3903) lr 5.7422e-04 eta 0:33:04
epoch [38/50] batch [200/200] time 0.813 (0.820) data 0.000 (0.004) loss 1.8722 (0.3973) lr 5.1825e-04 eta 0:32:48
epoch [39/50] batch [20/200] time 0.826 (0.855) data 0.000 (0.033) loss 0.1974 (0.4376) lr 5.1825e-04 eta 0:33:55
epoch [39/50] batch [40/200] time 0.818 (0.835) data 0.000 (0.016) loss 0.1955 (0.4133) lr 5.1825e-04 eta 0:32:51
epoch [39/50] batch [60/200] time 0.813 (0.829) data 0.001 (0.011) loss 0.4799 (0.3881) lr 5.1825e-04 eta 0:32:18
epoch [39/50] batch [80/200] time 0.822 (0.826) data 0.000 (0.008) loss 0.0436 (0.3963) lr 5.1825e-04 eta 0:31:55
epoch [39/50] batch [100/200] time 0.816 (0.825) data 0.000 (0.007) loss 0.0057 (0.3430) lr 5.1825e-04 eta 0:31:37
epoch [39/50] batch [120/200] time 0.826 (0.824) data 0.000 (0.006) loss 0.0422 (0.3328) lr 5.1825e-04 eta 0:31:18
epoch [39/50] batch [140/200] time 0.810 (0.823) data 0.000 (0.005) loss 0.0187 (0.3618) lr 5.1825e-04 eta 0:30:59
epoch [39/50] batch [160/200] time 0.810 (0.822) data 0.000 (0.004) loss 0.1855 (0.3838) lr 5.1825e-04 eta 0:30:41
epoch [39/50] batch [180/200] time 0.818 (0.821) data 0.000 (0.004) loss 1.6470 (0.3892) lr 5.1825e-04 eta 0:30:22
epoch [39/50] batch [200/200] time 0.821 (0.821) data 0.000 (0.004) loss 0.1330 (0.3852) lr 4.6417e-04 eta 0:30:06
epoch [40/50] batch [20/200] time 0.806 (0.853) data 0.000 (0.034) loss 0.2257 (0.4733) lr 4.6417e-04 eta 0:30:59
epoch [40/50] batch [40/200] time 0.808 (0.833) data 0.000 (0.017) loss 1.1255 (0.3708) lr 4.6417e-04 eta 0:29:58
epoch [40/50] batch [60/200] time 0.797 (0.829) data 0.000 (0.012) loss 0.3131 (0.3069) lr 4.6417e-04 eta 0:29:34
epoch [40/50] batch [80/200] time 0.817 (0.827) data 0.000 (0.009) loss 0.3680 (0.3289) lr 4.6417e-04 eta 0:29:13
epoch [40/50] batch [100/200] time 0.837 (0.825) data 0.002 (0.007) loss 0.5551 (0.3255) lr 4.6417e-04 eta 0:28:52
epoch [40/50] batch [120/200] time 0.819 (0.824) data 0.000 (0.006) loss 0.5090 (0.3381) lr 4.6417e-04 eta 0:28:34
epoch [40/50] batch [140/200] time 0.800 (0.823) data 0.000 (0.005) loss 0.3654 (0.3516) lr 4.6417e-04 eta 0:28:15
epoch [40/50] batch [160/200] time 0.812 (0.822) data 0.000 (0.005) loss 1.0564 (0.3789) lr 4.6417e-04 eta 0:27:56
epoch [40/50] batch [180/200] time 0.801 (0.821) data 0.000 (0.004) loss 0.0070 (0.3647) lr 4.6417e-04 eta 0:27:38
epoch [40/50] batch [200/200] time 0.820 (0.820) data 0.000 (0.004) loss 0.0099 (0.3620) lr 4.1221e-04 eta 0:27:20
epoch [41/50] batch [20/200] time 0.826 (0.853) data 0.000 (0.036) loss 0.6256 (0.4175) lr 4.1221e-04 eta 0:28:09
epoch [41/50] batch [40/200] time 0.814 (0.835) data 0.000 (0.018) loss 0.0081 (0.4705) lr 4.1221e-04 eta 0:27:17
epoch [41/50] batch [60/200] time 0.818 (0.829) data 0.000 (0.012) loss 0.2858 (0.4606) lr 4.1221e-04 eta 0:26:48
epoch [41/50] batch [80/200] time 0.830 (0.818) data 0.000 (0.009) loss 0.0379 (0.4422) lr 4.1221e-04 eta 0:26:09
epoch [41/50] batch [100/200] time 0.832 (0.822) data 0.000 (0.007) loss 0.0150 (0.4366) lr 4.1221e-04 eta 0:26:00
epoch [41/50] batch [120/200] time 0.816 (0.824) data 0.000 (0.006) loss 0.0110 (0.4094) lr 4.1221e-04 eta 0:25:48
epoch [41/50] batch [140/200] time 0.836 (0.826) data 0.000 (0.005) loss 0.1989 (0.3643) lr 4.1221e-04 eta 0:25:35
epoch [41/50] batch [160/200] time 0.802 (0.822) data 0.000 (0.005) loss 0.0003 (0.3690) lr 4.1221e-04 eta 0:25:12
epoch [41/50] batch [180/200] time 0.811 (0.821) data 0.000 (0.004) loss 0.0729 (0.3718) lr 4.1221e-04 eta 0:24:54
epoch [41/50] batch [200/200] time 0.813 (0.821) data 0.000 (0.004) loss 0.6697 (0.3835) lr 3.6258e-04 eta 0:24:37
epoch [42/50] batch [20/200] time 0.820 (0.846) data 0.000 (0.033) loss 0.0053 (0.3511) lr 3.6258e-04 eta 0:25:06
epoch [42/50] batch [40/200] time 0.810 (0.833) data 0.000 (0.016) loss 1.1006 (0.3547) lr 3.6258e-04 eta 0:24:25
epoch [42/50] batch [60/200] time 0.825 (0.829) data 0.001 (0.012) loss 0.2092 (0.3718) lr 3.6258e-04 eta 0:24:01
epoch [42/50] batch [80/200] time 0.816 (0.825) data 0.000 (0.009) loss 1.6626 (0.3932) lr 3.6258e-04 eta 0:23:38
epoch [42/50] batch [100/200] time 0.820 (0.822) data 0.000 (0.007) loss 0.2149 (0.3600) lr 3.6258e-04 eta 0:23:18
epoch [42/50] batch [120/200] time 0.831 (0.821) data 0.000 (0.006) loss 0.4627 (0.3780) lr 3.6258e-04 eta 0:22:59
epoch [42/50] batch [140/200] time 0.819 (0.821) data 0.000 (0.005) loss 0.9084 (0.3802) lr 3.6258e-04 eta 0:22:43
epoch [42/50] batch [160/200] time 0.810 (0.820) data 0.000 (0.005) loss 1.0784 (0.3834) lr 3.6258e-04 eta 0:22:25
epoch [42/50] batch [180/200] time 0.814 (0.820) data 0.004 (0.004) loss 1.5852 (0.3869) lr 3.6258e-04 eta 0:22:07
epoch [42/50] batch [200/200] time 0.845 (0.816) data 0.000 (0.004) loss 0.0112 (0.3716) lr 3.1545e-04 eta 0:21:45
epoch [43/50] batch [20/200] time 0.840 (0.874) data 0.000 (0.039) loss 0.3685 (0.2713) lr 3.1545e-04 eta 0:23:00
epoch [43/50] batch [40/200] time 0.843 (0.854) data 0.000 (0.020) loss 0.6591 (0.2906) lr 3.1545e-04 eta 0:22:12
epoch [43/50] batch [60/200] time 0.853 (0.850) data 0.006 (0.014) loss 0.0109 (0.2997) lr 3.1545e-04 eta 0:21:48
epoch [43/50] batch [80/200] time 0.809 (0.838) data 0.000 (0.010) loss 0.0153 (0.3102) lr 3.1545e-04 eta 0:21:13
epoch [43/50] batch [100/200] time 0.817 (0.835) data 0.000 (0.008) loss 0.0762 (0.3143) lr 3.1545e-04 eta 0:20:52
epoch [43/50] batch [120/200] time 0.815 (0.832) data 0.000 (0.007) loss 0.0052 (0.3449) lr 3.1545e-04 eta 0:20:30
epoch [43/50] batch [140/200] time 0.818 (0.829) data 0.000 (0.006) loss 0.5783 (0.3447) lr 3.1545e-04 eta 0:20:10
epoch [43/50] batch [160/200] time 0.796 (0.828) data 0.000 (0.005) loss 1.3362 (0.3567) lr 3.1545e-04 eta 0:19:52
epoch [43/50] batch [180/200] time 0.814 (0.827) data 0.000 (0.005) loss 0.0095 (0.4136) lr 3.1545e-04 eta 0:19:34
epoch [43/50] batch [200/200] time 0.834 (0.826) data 0.000 (0.004) loss 0.0669 (0.4005) lr 2.7103e-04 eta 0:19:16
epoch [44/50] batch [20/200] time 0.826 (0.851) data 0.000 (0.035) loss 0.3891 (0.3464) lr 2.7103e-04 eta 0:19:33
epoch [44/50] batch [40/200] time 0.811 (0.833) data 0.000 (0.018) loss 0.1608 (0.3139) lr 2.7103e-04 eta 0:18:53
epoch [44/50] batch [60/200] time 0.803 (0.827) data 0.000 (0.012) loss 0.0133 (0.3270) lr 2.7103e-04 eta 0:18:28
epoch [44/50] batch [80/200] time 0.812 (0.825) data 0.000 (0.009) loss 0.0700 (0.3577) lr 2.7103e-04 eta 0:18:08
epoch [44/50] batch [100/200] time 0.814 (0.823) data 0.000 (0.007) loss 0.0088 (0.3802) lr 2.7103e-04 eta 0:17:49
epoch [44/50] batch [120/200] time 0.816 (0.821) data 0.000 (0.006) loss 0.0007 (0.3628) lr 2.7103e-04 eta 0:17:31
epoch [44/50] batch [140/200] time 0.819 (0.820) data 0.000 (0.005) loss 1.5689 (0.3648) lr 2.7103e-04 eta 0:17:13
epoch [44/50] batch [160/200] time 0.811 (0.820) data 0.000 (0.005) loss 0.4937 (0.3855) lr 2.7103e-04 eta 0:16:57
epoch [44/50] batch [180/200] time 0.825 (0.820) data 0.000 (0.004) loss 0.0465 (0.3562) lr 2.7103e-04 eta 0:16:40
epoch [44/50] batch [200/200] time 0.833 (0.820) data 0.000 (0.004) loss 0.0226 (0.3513) lr 2.2949e-04 eta 0:16:23
epoch [45/50] batch [20/200] time 0.820 (0.851) data 0.000 (0.034) loss 0.0215 (0.3183) lr 2.2949e-04 eta 0:16:43
epoch [45/50] batch [40/200] time 0.827 (0.833) data 0.000 (0.017) loss 0.8075 (0.2811) lr 2.2949e-04 eta 0:16:05
epoch [45/50] batch [60/200] time 0.808 (0.828) data 0.000 (0.012) loss 0.0159 (0.3700) lr 2.2949e-04 eta 0:15:43
epoch [45/50] batch [80/200] time 0.820 (0.824) data 0.000 (0.009) loss 0.0956 (0.3920) lr 2.2949e-04 eta 0:15:22
epoch [45/50] batch [100/200] time 0.822 (0.823) data 0.000 (0.007) loss 0.6079 (0.4087) lr 2.2949e-04 eta 0:15:04
epoch [45/50] batch [120/200] time 0.823 (0.822) data 0.000 (0.006) loss 0.0007 (0.4125) lr 2.2949e-04 eta 0:14:47
epoch [45/50] batch [140/200] time 0.813 (0.821) data 0.000 (0.005) loss 0.0043 (0.4091) lr 2.2949e-04 eta 0:14:30
epoch [45/50] batch [160/200] time 0.814 (0.821) data 0.000 (0.005) loss 0.9256 (0.3947) lr 2.2949e-04 eta 0:14:13
epoch [45/50] batch [180/200] time 0.827 (0.820) data 0.000 (0.004) loss 0.5935 (0.3963) lr 2.2949e-04 eta 0:13:56
epoch [45/50] batch [200/200] time 0.818 (0.820) data 0.000 (0.004) loss 0.3528 (0.3788) lr 1.9098e-04 eta 0:13:39
epoch [46/50] batch [20/200] time 0.820 (0.849) data 0.000 (0.033) loss 0.0017 (0.2800) lr 1.9098e-04 eta 0:13:51
epoch [46/50] batch [40/200] time 0.829 (0.837) data 0.000 (0.017) loss 0.5318 (0.3808) lr 1.9098e-04 eta 0:13:23
epoch [46/50] batch [60/200] time 0.807 (0.829) data 0.000 (0.011) loss 0.2818 (0.3695) lr 1.9098e-04 eta 0:12:59
epoch [46/50] batch [80/200] time 0.812 (0.825) data 0.000 (0.009) loss 0.0349 (0.3942) lr 1.9098e-04 eta 0:12:38
epoch [46/50] batch [100/200] time 0.816 (0.825) data 0.004 (0.007) loss 0.0054 (0.3707) lr 1.9098e-04 eta 0:12:22
epoch [46/50] batch [120/200] time 0.808 (0.823) data 0.000 (0.006) loss 0.0733 (0.3760) lr 1.9098e-04 eta 0:12:04
epoch [46/50] batch [140/200] time 0.807 (0.822) data 0.000 (0.005) loss 0.0442 (0.3896) lr 1.9098e-04 eta 0:11:46
epoch [46/50] batch [160/200] time 0.827 (0.821) data 0.000 (0.005) loss 0.0008 (0.3889) lr 1.9098e-04 eta 0:11:30
epoch [46/50] batch [180/200] time 0.845 (0.817) data 0.000 (0.004) loss 0.1077 (0.4029) lr 1.9098e-04 eta 0:11:09
epoch [46/50] batch [200/200] time 0.827 (0.819) data 0.000 (0.004) loss 0.1947 (0.3955) lr 1.5567e-04 eta 0:10:55
epoch [47/50] batch [20/200] time 0.846 (0.868) data 0.000 (0.034) loss 0.0372 (0.1998) lr 1.5567e-04 eta 0:11:17
epoch [47/50] batch [40/200] time 0.838 (0.851) data 0.000 (0.017) loss 0.0844 (0.2901) lr 1.5567e-04 eta 0:10:46
epoch [47/50] batch [60/200] time 0.832 (0.832) data 0.001 (0.011) loss 0.0177 (0.2977) lr 1.5567e-04 eta 0:10:15
epoch [47/50] batch [80/200] time 0.815 (0.829) data 0.000 (0.009) loss 0.9727 (0.3410) lr 1.5567e-04 eta 0:09:56
epoch [47/50] batch [100/200] time 0.825 (0.825) data 0.000 (0.007) loss 0.0946 (0.3338) lr 1.5567e-04 eta 0:09:37
epoch [47/50] batch [120/200] time 0.822 (0.824) data 0.000 (0.006) loss 0.9492 (0.3387) lr 1.5567e-04 eta 0:09:20
epoch [47/50] batch [140/200] time 0.827 (0.823) data 0.000 (0.005) loss 1.3172 (0.3609) lr 1.5567e-04 eta 0:09:02
epoch [47/50] batch [160/200] time 0.825 (0.823) data 0.000 (0.004) loss 0.1522 (0.3662) lr 1.5567e-04 eta 0:08:46
epoch [47/50] batch [180/200] time 0.812 (0.822) data 0.000 (0.004) loss 0.0068 (0.3694) lr 1.5567e-04 eta 0:08:29
epoch [47/50] batch [200/200] time 0.816 (0.821) data 0.000 (0.004) loss 1.4151 (0.3730) lr 1.2369e-04 eta 0:08:12
epoch [48/50] batch [20/200] time 0.813 (0.857) data 0.000 (0.033) loss 1.1673 (0.3175) lr 1.2369e-04 eta 0:08:16
epoch [48/50] batch [40/200] time 0.815 (0.836) data 0.000 (0.017) loss 0.0063 (0.2654) lr 1.2369e-04 eta 0:07:48
epoch [48/50] batch [60/200] time 0.815 (0.829) data 0.005 (0.011) loss 0.7747 (0.3329) lr 1.2369e-04 eta 0:07:27
epoch [48/50] batch [80/200] time 0.824 (0.826) data 0.000 (0.009) loss 0.2531 (0.3568) lr 1.2369e-04 eta 0:07:09
epoch [48/50] batch [100/200] time 0.844 (0.818) data 0.000 (0.007) loss 0.3597 (0.3523) lr 1.2369e-04 eta 0:06:48
epoch [48/50] batch [120/200] time 0.855 (0.822) data 0.010 (0.006) loss 0.0015 (0.3561) lr 1.2369e-04 eta 0:06:34
epoch [48/50] batch [140/200] time 0.836 (0.824) data 0.000 (0.005) loss 0.0006 (0.3549) lr 1.2369e-04 eta 0:06:19
epoch [48/50] batch [160/200] time 0.849 (0.825) data 0.000 (0.005) loss 1.1386 (0.3539) lr 1.2369e-04 eta 0:06:03
epoch [48/50] batch [180/200] time 0.539 (0.822) data 0.000 (0.004) loss 0.8391 (0.3626) lr 1.2369e-04 eta 0:05:45
epoch [48/50] batch [200/200] time 0.808 (0.819) data 0.000 (0.004) loss 0.4208 (0.3649) lr 9.5173e-05 eta 0:05:27
epoch [49/50] batch [20/200] time 0.833 (0.852) data 0.000 (0.033) loss 0.8413 (0.3830) lr 9.5173e-05 eta 0:05:23
epoch [49/50] batch [40/200] time 0.824 (0.836) data 0.000 (0.017) loss 0.0117 (0.3757) lr 9.5173e-05 eta 0:05:00
epoch [49/50] batch [60/200] time 0.819 (0.829) data 0.001 (0.011) loss 0.5928 (0.4235) lr 9.5173e-05 eta 0:04:41
epoch [49/50] batch [80/200] time 0.813 (0.826) data 0.000 (0.009) loss 1.1475 (0.4109) lr 9.5173e-05 eta 0:04:24
epoch [49/50] batch [100/200] time 0.817 (0.824) data 0.000 (0.007) loss 0.3960 (0.3834) lr 9.5173e-05 eta 0:04:07
epoch [49/50] batch [120/200] time 0.828 (0.823) data 0.000 (0.006) loss 0.1994 (0.3755) lr 9.5173e-05 eta 0:03:50
epoch [49/50] batch [140/200] time 0.825 (0.822) data 0.000 (0.005) loss 0.0928 (0.3676) lr 9.5173e-05 eta 0:03:33
epoch [49/50] batch [160/200] time 0.819 (0.821) data 0.004 (0.005) loss 0.0047 (0.3571) lr 9.5173e-05 eta 0:03:17
epoch [49/50] batch [180/200] time 0.804 (0.821) data 0.000 (0.004) loss 1.1835 (0.3634) lr 9.5173e-05 eta 0:03:00
epoch [49/50] batch [200/200] time 0.816 (0.820) data 0.000 (0.004) loss 0.1138 (0.3631) lr 7.0224e-05 eta 0:02:44
epoch [50/50] batch [20/200] time 0.821 (0.846) data 0.000 (0.032) loss 0.0167 (0.3358) lr 7.0224e-05 eta 0:02:32
epoch [50/50] batch [40/200] time 0.822 (0.832) data 0.000 (0.017) loss 0.0452 (0.2644) lr 7.0224e-05 eta 0:02:13
epoch [50/50] batch [60/200] time 0.830 (0.826) data 0.001 (0.012) loss 0.0113 (0.3181) lr 7.0224e-05 eta 0:01:55
epoch [50/50] batch [80/200] time 0.802 (0.824) data 0.000 (0.009) loss 0.8936 (0.3242) lr 7.0224e-05 eta 0:01:38
epoch [50/50] batch [100/200] time 0.822 (0.823) data 0.000 (0.007) loss 0.1676 (0.3136) lr 7.0224e-05 eta 0:01:22
epoch [50/50] batch [120/200] time 0.832 (0.822) data 0.010 (0.006) loss 0.9233 (0.3204) lr 7.0224e-05 eta 0:01:05
epoch [50/50] batch [140/200] time 0.812 (0.821) data 0.000 (0.005) loss 0.0536 (0.3440) lr 7.0224e-05 eta 0:00:49
epoch [50/50] batch [160/200] time 0.821 (0.821) data 0.003 (0.005) loss 0.0033 (0.3481) lr 7.0224e-05 eta 0:00:32
epoch [50/50] batch [180/200] time 1.114 (0.843) data 0.000 (0.004) loss 0.0039 (0.3546) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [200/200] time 1.110 (0.870) data 0.000 (0.004) loss 0.7875 (0.3704) lr 4.8943e-05 eta 0:00:00
Checkpoint saved to output/base2new/train_base/caltech101/vit_b16_ep50_c4_BZ4_ProDA/seed2/prompt_learner/model.pth.tar-50
Finish training
Deploy the last-epoch model
Evaluate on the *test* set
=> result
* total: 1,500
* correct: 1,490
* accuracy: 99.33%
* error: 0.67%
* macro_f1: 98.72%
Elapsed: 2:11:41
