***************
** 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/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: 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/seed2
RESUME: 
SEED: 2
TEST:
  COMPUTE_CMAT: False
  EVALUATOR: Classification
  FINAL_MODEL: last_step
  NO_TEST: False
  PER_CLASS_RESULT: False
  SPLIT: test
TRAIN:
  CHECKPOINT_FREQ: 0
  COUNT_ITER: train_x
  PRINT_FREQ: 20
TRAINER:
  CDAC:
    CLASS_LR_MULTI: 10
    P_THRESH: 0.95
    RAMPUP_COEF: 30
    RAMPUP_ITRS: 1000
    STRONG_TRANSFORMS: ()
    TOPK_MATCH: 5
  COCOOP:
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  COOP:
    CLASS_TOKEN_POSITION: end
    CSC: False
    CTX_INIT: 
    N_CTX: 16
    PREC: fp16
  CROSSGRAD:
    ALPHA_D: 0.5
    ALPHA_F: 0.5
    EPS_D: 1.0
    EPS_F: 1.0
  DAEL:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DAELDG:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 0.5
  DDAIG:
    ALPHA: 0.5
    CLAMP: False
    CLAMP_MAX: 1.0
    CLAMP_MIN: -1.0
    G_ARCH: 
    LMDA: 0.3
    WARMUP: 0
  DOMAINMIX:
    ALPHA: 1.0
    BETA: 1.0
    TYPE: crossdomain
  ENTMIN:
    LMDA: 0.001
  FIXMATCH:
    CONF_THRE: 0.95
    STRONG_TRANSFORMS: ()
    WEIGHT_U: 1.0
  IVLP:
    CTX_INIT: a photo of a
    N_CTX_TEXT: 2
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_TEXT: 9
    PROMPT_DEPTH_VISION: 9
  M3SDA:
    LMDA: 0.5
    N_STEP_F: 4
  MAPLE:
    CTX_INIT: a photo of a
    N_CTX: 4
    PREC: fp16
    PROMPT_DEPTH: 9
  MCD:
    N_STEP_F: 4
  MEANTEACHER:
    EMA_ALPHA: 0.999
    RAMPUP: 5
    WEIGHT_U: 1.0
  MIXMATCH:
    MIXUP_BETA: 0.75
    RAMPUP: 20000
    TEMP: 2.0
    WEIGHT_U: 100.0
  MME:
    LMDA: 0.1
  NAME: ProDA
  ProDA:
    N_CTX: 4
    N_PROMPT: 32
    PREC: fp16
  SE:
    CONF_THRE: 0.95
    EMA_ALPHA: 0.999
    RAMPUP: 300
  VPT:
    CTX_INIT: a photo of a
    N_CTX_VISION: 2
    PREC: fp16
    PROMPT_DEPTH_VISION: 1
USE_CUDA: True
VERBOSE: True
VERSION: 1
Collecting env info ...
** System info **
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A

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

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

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

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

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

Loading trainer: ProDA
Loading dataset: 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_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    OxfordFlowers
# classes  51
# train_x  816
# val      204
# test     1,176
---------  -------------
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/seed2/tensorboard)
epoch [1/50] batch [20/204] time 0.247 (0.376) data 0.000 (0.028) loss 2.9108 (3.0744) lr 1.0000e-05 eta 1:03:52
epoch [1/50] batch [40/204] time 0.249 (0.312) data 0.000 (0.014) loss 0.9533 (2.6065) lr 1.0000e-05 eta 0:52:48
epoch [1/50] batch [60/204] time 0.245 (0.290) data 0.000 (0.009) loss 1.6200 (2.4904) lr 1.0000e-05 eta 0:49:05
epoch [1/50] batch [80/204] time 0.249 (0.280) data 0.000 (0.007) loss 1.5559 (2.3034) lr 1.0000e-05 eta 0:47:10
epoch [1/50] batch [100/204] time 0.250 (0.273) data 0.000 (0.006) loss 2.2942 (2.3205) lr 1.0000e-05 eta 0:45:59
epoch [1/50] batch [120/204] time 0.248 (0.269) data 0.000 (0.005) loss 1.5536 (2.4124) lr 1.0000e-05 eta 0:45:09
epoch [1/50] batch [140/204] time 0.250 (0.266) data 0.000 (0.004) loss 0.5756 (2.2836) lr 1.0000e-05 eta 0:44:32
epoch [1/50] batch [160/204] time 0.249 (0.263) data 0.000 (0.004) loss 1.9513 (2.2870) lr 1.0000e-05 eta 0:44:04
epoch [1/50] batch [180/204] time 0.244 (0.262) data 0.000 (0.003) loss 1.4732 (2.2406) lr 1.0000e-05 eta 0:43:40
epoch [1/50] batch [200/204] time 0.250 (0.260) data 0.000 (0.003) loss 0.6781 (2.1572) lr 1.0000e-05 eta 0:43:21
epoch [2/50] batch [20/204] time 0.245 (0.265) data 0.000 (0.017) loss 0.8716 (1.9826) lr 1.0000e-05 eta 0:44:04
epoch [2/50] batch [40/204] time 0.242 (0.256) data 0.000 (0.009) loss 1.0714 (1.6526) lr 1.0000e-05 eta 0:42:32
epoch [2/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 1.3791 (1.8432) lr 1.0000e-05 eta 0:41:59
epoch [2/50] batch [80/204] time 0.251 (0.252) data 0.000 (0.004) loss 4.6225 (1.8173) lr 1.0000e-05 eta 0:41:42
epoch [2/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.4925 (1.6958) lr 1.0000e-05 eta 0:41:29
epoch [2/50] batch [120/204] time 0.255 (0.251) data 0.005 (0.003) loss 0.6684 (1.7740) lr 1.0000e-05 eta 0:41:20
epoch [2/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.6659 (1.8381) lr 1.0000e-05 eta 0:41:11
epoch [2/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.5436 (1.8233) lr 1.0000e-05 eta 0:41:03
epoch [2/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 2.1432 (1.8052) lr 1.0000e-05 eta 0:40:56
epoch [2/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.7167 (1.8102) lr 1.0000e-05 eta 0:40:49
epoch [3/50] batch [20/204] time 0.248 (0.265) data 0.000 (0.016) loss 2.7139 (1.7011) lr 1.0000e-05 eta 0:43:10
epoch [3/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.008) loss 2.6383 (1.5783) lr 1.0000e-05 eta 0:41:45
epoch [3/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 1.7009 (1.6670) lr 1.0000e-05 eta 0:41:11
epoch [3/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.004) loss 3.8359 (1.7620) lr 1.0000e-05 eta 0:40:52
epoch [3/50] batch [100/204] time 0.242 (0.252) data 0.000 (0.003) loss 1.0551 (1.6867) lr 1.0000e-05 eta 0:40:38
epoch [3/50] batch [120/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.7403 (1.6261) lr 1.0000e-05 eta 0:40:29
epoch [3/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.3466 (1.6396) lr 1.0000e-05 eta 0:40:20
epoch [3/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 1.0185 (1.6684) lr 1.0000e-05 eta 0:40:13
epoch [3/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 2.8620 (1.6837) lr 1.0000e-05 eta 0:40:06
epoch [3/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 2.1767 (1.7026) lr 1.0000e-05 eta 0:39:59
epoch [4/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.017) loss 1.5791 (1.4326) lr 1.0000e-05 eta 0:42:24
epoch [4/50] batch [40/204] time 0.253 (0.257) data 0.000 (0.008) loss 0.1196 (1.3100) lr 1.0000e-05 eta 0:40:58
epoch [4/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.0957 (1.4567) lr 1.0000e-05 eta 0:40:26
epoch [4/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.6264 (1.5296) lr 1.0000e-05 eta 0:40:08
epoch [4/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.003) loss 3.5929 (1.5416) lr 1.0000e-05 eta 0:39:53
epoch [4/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 3.0477 (1.6113) lr 1.0000e-05 eta 0:39:42
epoch [4/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 2.0878 (1.5399) lr 1.0000e-05 eta 0:39:32
epoch [4/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 2.3986 (1.5733) lr 1.0000e-05 eta 0:39:24
epoch [4/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.4206 (1.5443) lr 1.0000e-05 eta 0:39:16
epoch [4/50] batch [200/204] time 0.248 (0.250) data 0.000 (0.002) loss 2.8390 (1.5412) lr 1.0000e-05 eta 0:39:09
epoch [5/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 1.7294 (1.3939) lr 1.0000e-05 eta 0:41:26
epoch [5/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.5621 (1.4908) lr 1.0000e-05 eta 0:40:00
epoch [5/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.6122 (1.4874) lr 1.0000e-05 eta 0:39:26
epoch [5/50] batch [80/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.9909 (1.4000) lr 1.0000e-05 eta 0:39:08
epoch [5/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 1.8089 (1.4057) lr 1.0000e-05 eta 0:38:55
epoch [5/50] batch [120/204] time 0.249 (0.251) data 0.000 (0.003) loss 2.2035 (1.4276) lr 1.0000e-05 eta 0:38:45
epoch [5/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 3.2014 (1.4933) lr 1.0000e-05 eta 0:38:37
epoch [5/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.1744 (1.5281) lr 1.0000e-05 eta 0:38:29
epoch [5/50] batch [180/204] time 0.244 (0.250) data 0.000 (0.002) loss 1.8815 (1.5073) lr 1.0000e-05 eta 0:38:22
epoch [5/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 2.4496 (1.5238) lr 1.0000e-05 eta 0:38:15
epoch [6/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 3.4296 (1.8012) lr 2.0000e-03 eta 0:40:35
epoch [6/50] batch [40/204] time 0.243 (0.257) data 0.000 (0.009) loss 1.6043 (1.7658) lr 2.0000e-03 eta 0:39:09
epoch [6/50] batch [60/204] time 0.248 (0.254) data 0.000 (0.006) loss 2.3435 (1.6786) lr 2.0000e-03 eta 0:38:38
epoch [6/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.2235 (1.7096) lr 2.0000e-03 eta 0:38:20
epoch [6/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.003) loss 3.1237 (1.6133) lr 2.0000e-03 eta 0:38:08
epoch [6/50] batch [120/204] time 0.251 (0.251) data 0.000 (0.003) loss 3.3589 (1.6157) lr 2.0000e-03 eta 0:37:58
epoch [6/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.8047 (1.5392) lr 2.0000e-03 eta 0:37:50
epoch [6/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 1.9959 (1.5029) lr 2.0000e-03 eta 0:37:42
epoch [6/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.3220 (1.4608) lr 2.0000e-03 eta 0:37:35
epoch [6/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 1.3238 (1.4455) lr 2.0000e-03 eta 0:37:27
epoch [7/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.017) loss 2.4553 (1.4389) lr 1.9980e-03 eta 0:39:49
epoch [7/50] batch [40/204] time 0.246 (0.258) data 0.000 (0.009) loss 0.0659 (1.3510) lr 1.9980e-03 eta 0:38:23
epoch [7/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.1473 (1.2050) lr 1.9980e-03 eta 0:37:52
epoch [7/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.5051 (1.0694) lr 1.9980e-03 eta 0:37:32
epoch [7/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.0861 (1.0582) lr 1.9980e-03 eta 0:37:18
epoch [7/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.003) loss 0.8853 (1.1018) lr 1.9980e-03 eta 0:37:09
epoch [7/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3368 (1.0805) lr 1.9980e-03 eta 0:37:01
epoch [7/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.7513 (1.0555) lr 1.9980e-03 eta 0:36:52
epoch [7/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.8070 (1.0676) lr 1.9980e-03 eta 0:36:45
epoch [7/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.7074 (1.0718) lr 1.9980e-03 eta 0:36:37
epoch [8/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.6762 (1.1977) lr 1.9921e-03 eta 0:38:50
epoch [8/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 1.1212 (0.9645) lr 1.9921e-03 eta 0:37:31
epoch [8/50] batch [60/204] time 0.246 (0.255) data 0.000 (0.006) loss 1.1058 (1.0096) lr 1.9921e-03 eta 0:37:00
epoch [8/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.0302 (0.9996) lr 1.9921e-03 eta 0:36:41
epoch [8/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.6890 (1.0521) lr 1.9921e-03 eta 0:36:27
epoch [8/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.7137 (1.0590) lr 1.9921e-03 eta 0:36:17
epoch [8/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.6220 (1.0599) lr 1.9921e-03 eta 0:36:09
epoch [8/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1172 (1.0420) lr 1.9921e-03 eta 0:36:01
epoch [8/50] batch [180/204] time 0.250 (0.251) data 0.001 (0.002) loss 1.2125 (1.0252) lr 1.9921e-03 eta 0:35:53
epoch [8/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 1.9700 (1.0120) lr 1.9921e-03 eta 0:35:46
epoch [9/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.017) loss 1.8325 (1.0815) lr 1.9823e-03 eta 0:37:55
epoch [9/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.9207 (0.9329) lr 1.9823e-03 eta 0:36:35
epoch [9/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.1021 (0.8986) lr 1.9823e-03 eta 0:36:06
epoch [9/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.004) loss 1.2911 (0.8920) lr 1.9823e-03 eta 0:35:46
epoch [9/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 1.1882 (0.9266) lr 1.9823e-03 eta 0:35:32
epoch [9/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1630 (0.9075) lr 1.9823e-03 eta 0:35:22
epoch [9/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.5448 (0.8655) lr 1.9823e-03 eta 0:35:15
epoch [9/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 2.4564 (0.8948) lr 1.9823e-03 eta 0:35:07
epoch [9/50] batch [180/204] time 0.249 (0.250) data 0.000 (0.002) loss 2.5180 (0.9067) lr 1.9823e-03 eta 0:35:01
epoch [9/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.2361 (0.9116) lr 1.9823e-03 eta 0:34:54
epoch [10/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 0.8959 (0.9685) lr 1.9686e-03 eta 0:36:58
epoch [10/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 0.4032 (0.9451) lr 1.9686e-03 eta 0:35:41
epoch [10/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.8867 (0.8165) lr 1.9686e-03 eta 0:35:13
epoch [10/50] batch [80/204] time 0.243 (0.253) data 0.000 (0.004) loss 1.2471 (0.8188) lr 1.9686e-03 eta 0:34:55
epoch [10/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.4413 (0.8126) lr 1.9686e-03 eta 0:34:43
epoch [10/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.9027 (0.8276) lr 1.9686e-03 eta 0:34:34
epoch [10/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.1142 (0.8166) lr 1.9686e-03 eta 0:34:26
epoch [10/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.4243 (0.8191) lr 1.9686e-03 eta 0:34:18
epoch [10/50] batch [180/204] time 0.252 (0.251) data 0.000 (0.002) loss 1.2045 (0.8120) lr 1.9686e-03 eta 0:34:11
epoch [10/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.2983 (0.8207) lr 1.9686e-03 eta 0:34:04
epoch [11/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.3900 (0.8405) lr 1.9511e-03 eta 0:36:04
epoch [11/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.9488 (0.8605) lr 1.9511e-03 eta 0:34:48
epoch [11/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.6349 (0.8672) lr 1.9511e-03 eta 0:34:20
epoch [11/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.004) loss 1.6872 (0.8616) lr 1.9511e-03 eta 0:34:05
epoch [11/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.2868 (0.7947) lr 1.9511e-03 eta 0:33:53
epoch [11/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.8119 (0.8115) lr 1.9511e-03 eta 0:33:43
epoch [11/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.5088 (0.7872) lr 1.9511e-03 eta 0:33:35
epoch [11/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.8239 (0.8072) lr 1.9511e-03 eta 0:33:28
epoch [11/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.002) loss 1.0216 (0.8183) lr 1.9511e-03 eta 0:33:21
epoch [11/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 1.4878 (0.8188) lr 1.9511e-03 eta 0:33:14
epoch [12/50] batch [20/204] time 0.252 (0.267) data 0.000 (0.017) loss 0.3990 (0.7584) lr 1.9298e-03 eta 0:35:20
epoch [12/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 0.3543 (0.6577) lr 1.9298e-03 eta 0:34:01
epoch [12/50] batch [60/204] time 0.246 (0.255) data 0.000 (0.006) loss 2.0152 (0.7907) lr 1.9298e-03 eta 0:33:32
epoch [12/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.1369 (0.7772) lr 1.9298e-03 eta 0:33:14
epoch [12/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 1.1817 (0.8213) lr 1.9298e-03 eta 0:33:01
epoch [12/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.6558 (0.8337) lr 1.9298e-03 eta 0:32:52
epoch [12/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4586 (0.8060) lr 1.9298e-03 eta 0:32:43
epoch [12/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.3768 (0.7932) lr 1.9298e-03 eta 0:32:35
epoch [12/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.7895 (0.8060) lr 1.9298e-03 eta 0:32:28
epoch [12/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.7651 (0.8099) lr 1.9298e-03 eta 0:32:21
epoch [13/50] batch [20/204] time 0.250 (0.266) data 0.000 (0.017) loss 0.0728 (0.8787) lr 1.9048e-03 eta 0:34:14
epoch [13/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.2708 (0.9217) lr 1.9048e-03 eta 0:32:58
epoch [13/50] batch [60/204] time 0.242 (0.254) data 0.000 (0.006) loss 1.0077 (0.8188) lr 1.9048e-03 eta 0:32:31
epoch [13/50] batch [80/204] time 0.248 (0.252) data 0.000 (0.004) loss 1.8795 (0.8294) lr 1.9048e-03 eta 0:32:16
epoch [13/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.1201 (0.7787) lr 1.9048e-03 eta 0:32:05
epoch [13/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.5683 (0.7957) lr 1.9048e-03 eta 0:31:56
epoch [13/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4866 (0.7701) lr 1.9048e-03 eta 0:31:48
epoch [13/50] batch [160/204] time 0.251 (0.250) data 0.000 (0.002) loss 2.5751 (0.7711) lr 1.9048e-03 eta 0:31:40
epoch [13/50] batch [180/204] time 0.246 (0.250) data 0.000 (0.002) loss 1.2282 (0.7631) lr 1.9048e-03 eta 0:31:33
epoch [13/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.7765 (0.7705) lr 1.9048e-03 eta 0:31:26
epoch [14/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.018) loss 0.3273 (0.5023) lr 1.8763e-03 eta 0:33:21
epoch [14/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.3746 (0.5610) lr 1.8763e-03 eta 0:32:06
epoch [14/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.8770 (0.6204) lr 1.8763e-03 eta 0:31:40
epoch [14/50] batch [80/204] time 0.248 (0.252) data 0.000 (0.005) loss 0.3629 (0.5910) lr 1.8763e-03 eta 0:31:24
epoch [14/50] batch [100/204] time 0.250 (0.251) data 0.000 (0.004) loss 0.4080 (0.6135) lr 1.8763e-03 eta 0:31:12
epoch [14/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 1.1616 (0.6400) lr 1.8763e-03 eta 0:31:03
epoch [14/50] batch [140/204] time 0.245 (0.250) data 0.000 (0.003) loss 0.7979 (0.6423) lr 1.8763e-03 eta 0:30:54
epoch [14/50] batch [160/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.5558 (0.7012) lr 1.8763e-03 eta 0:30:48
epoch [14/50] batch [180/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.3342 (0.7182) lr 1.8763e-03 eta 0:30:41
epoch [14/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.3562 (0.7128) lr 1.8763e-03 eta 0:30:35
epoch [15/50] batch [20/204] time 0.244 (0.265) data 0.000 (0.017) loss 0.1855 (0.6149) lr 1.8443e-03 eta 0:32:22
epoch [15/50] batch [40/204] time 0.244 (0.257) data 0.000 (0.009) loss 0.6914 (0.6551) lr 1.8443e-03 eta 0:31:14
epoch [15/50] batch [60/204] time 0.244 (0.254) data 0.000 (0.006) loss 0.1639 (0.5909) lr 1.8443e-03 eta 0:30:49
epoch [15/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.2886 (0.6255) lr 1.8443e-03 eta 0:30:35
epoch [15/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.003) loss 1.1827 (0.6304) lr 1.8443e-03 eta 0:30:24
epoch [15/50] batch [120/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.4293 (0.6453) lr 1.8443e-03 eta 0:30:14
epoch [15/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.8787 (0.6649) lr 1.8443e-03 eta 0:30:06
epoch [15/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.7867 (0.6841) lr 1.8443e-03 eta 0:29:59
epoch [15/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.4032 (0.6747) lr 1.8443e-03 eta 0:29:51
epoch [15/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.1832 (0.6774) lr 1.8443e-03 eta 0:29:44
epoch [16/50] batch [20/204] time 0.245 (0.265) data 0.000 (0.017) loss 1.2601 (0.8691) lr 1.8090e-03 eta 0:31:29
epoch [16/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 0.0977 (0.6689) lr 1.8090e-03 eta 0:30:23
epoch [16/50] batch [60/204] time 0.248 (0.254) data 0.000 (0.006) loss 0.0824 (0.6899) lr 1.8090e-03 eta 0:29:55
epoch [16/50] batch [80/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.0878 (0.6404) lr 1.8090e-03 eta 0:29:41
epoch [16/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.2247 (0.6851) lr 1.8090e-03 eta 0:29:30
epoch [16/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.3385 (0.6718) lr 1.8090e-03 eta 0:29:21
epoch [16/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3575 (0.6891) lr 1.8090e-03 eta 0:29:14
epoch [16/50] batch [160/204] time 0.251 (0.250) data 0.000 (0.002) loss 1.0028 (0.6897) lr 1.8090e-03 eta 0:29:07
epoch [16/50] batch [180/204] time 0.243 (0.250) data 0.000 (0.002) loss 0.6877 (0.6791) lr 1.8090e-03 eta 0:29:00
epoch [16/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.3302 (0.6714) lr 1.8090e-03 eta 0:28:54
epoch [17/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.017) loss 1.4003 (0.6225) lr 1.7705e-03 eta 0:30:38
epoch [17/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.6155 (0.7359) lr 1.7705e-03 eta 0:29:31
epoch [17/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 1.0216 (0.7814) lr 1.7705e-03 eta 0:29:06
epoch [17/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.004) loss 0.2471 (0.7296) lr 1.7705e-03 eta 0:28:52
epoch [17/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.8029 (0.7620) lr 1.7705e-03 eta 0:28:39
epoch [17/50] batch [120/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1964 (0.7604) lr 1.7705e-03 eta 0:28:31
epoch [17/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.5449 (0.7337) lr 1.7705e-03 eta 0:28:23
epoch [17/50] batch [160/204] time 0.251 (0.250) data 0.000 (0.002) loss 1.4877 (0.7152) lr 1.7705e-03 eta 0:28:17
epoch [17/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.1996 (0.6944) lr 1.7705e-03 eta 0:28:10
epoch [17/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.5044 (0.6822) lr 1.7705e-03 eta 0:28:04
epoch [18/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.1628 (0.8701) lr 1.7290e-03 eta 0:29:45
epoch [18/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.3904 (0.7068) lr 1.7290e-03 eta 0:28:38
epoch [18/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.7721 (0.6970) lr 1.7290e-03 eta 0:28:14
epoch [18/50] batch [80/204] time 0.243 (0.253) data 0.000 (0.004) loss 0.1334 (0.6928) lr 1.7290e-03 eta 0:28:01
epoch [18/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.4900 (0.6961) lr 1.7290e-03 eta 0:27:50
epoch [18/50] batch [120/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0636 (0.6653) lr 1.7290e-03 eta 0:27:41
epoch [18/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.7840 (0.6512) lr 1.7290e-03 eta 0:27:33
epoch [18/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.9442 (0.6290) lr 1.7290e-03 eta 0:27:26
epoch [18/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.4374 (0.6465) lr 1.7290e-03 eta 0:27:20
epoch [18/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.5163 (0.6462) lr 1.7290e-03 eta 0:27:14
epoch [19/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.1868 (0.5414) lr 1.6845e-03 eta 0:28:54
epoch [19/50] batch [40/204] time 0.251 (0.258) data 0.000 (0.009) loss 0.4635 (0.5331) lr 1.6845e-03 eta 0:27:54
epoch [19/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.9428 (0.5719) lr 1.6845e-03 eta 0:27:28
epoch [19/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.9045 (0.5644) lr 1.6845e-03 eta 0:27:13
epoch [19/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.0613 (0.5827) lr 1.6845e-03 eta 0:27:02
epoch [19/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.3152 (0.5867) lr 1.6845e-03 eta 0:26:52
epoch [19/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 1.0565 (0.5947) lr 1.6845e-03 eta 0:26:45
epoch [19/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.7646 (0.6006) lr 1.6845e-03 eta 0:26:37
epoch [19/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0695 (0.6063) lr 1.6845e-03 eta 0:26:31
epoch [19/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.0418 (0.6151) lr 1.6845e-03 eta 0:26:24
epoch [20/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.8579 (0.5263) lr 1.6374e-03 eta 0:27:55
epoch [20/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.3558 (0.5544) lr 1.6374e-03 eta 0:26:56
epoch [20/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.6808 (0.5652) lr 1.6374e-03 eta 0:26:31
epoch [20/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.1200 (0.5345) lr 1.6374e-03 eta 0:26:17
epoch [20/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.1995 (0.5389) lr 1.6374e-03 eta 0:26:06
epoch [20/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.0866 (0.5252) lr 1.6374e-03 eta 0:25:57
epoch [20/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.7912 (0.5873) lr 1.6374e-03 eta 0:25:50
epoch [20/50] batch [160/204] time 0.251 (0.250) data 0.000 (0.002) loss 1.4252 (0.5857) lr 1.6374e-03 eta 0:25:43
epoch [20/50] batch [180/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.9891 (0.5830) lr 1.6374e-03 eta 0:25:37
epoch [20/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.8576 (0.5698) lr 1.6374e-03 eta 0:25:30
epoch [21/50] batch [20/204] time 0.244 (0.266) data 0.000 (0.017) loss 0.3992 (0.5731) lr 1.5878e-03 eta 0:27:02
epoch [21/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.2820 (0.6492) lr 1.5878e-03 eta 0:26:04
epoch [21/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.1147 (0.6456) lr 1.5878e-03 eta 0:25:43
epoch [21/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.6571 (0.6152) lr 1.5878e-03 eta 0:25:28
epoch [21/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.1187 (0.6102) lr 1.5878e-03 eta 0:25:17
epoch [21/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.3863 (0.5983) lr 1.5878e-03 eta 0:25:08
epoch [21/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.2106 (0.6111) lr 1.5878e-03 eta 0:25:00
epoch [21/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.1287 (0.5846) lr 1.5878e-03 eta 0:24:54
epoch [21/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.1111 (0.5788) lr 1.5878e-03 eta 0:24:47
epoch [21/50] batch [200/204] time 0.246 (0.250) data 0.000 (0.002) loss 0.6472 (0.5845) lr 1.5878e-03 eta 0:24:41
epoch [22/50] batch [20/204] time 0.249 (0.266) data 0.000 (0.017) loss 0.6768 (0.5584) lr 1.5358e-03 eta 0:26:05
epoch [22/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 0.6759 (0.5113) lr 1.5358e-03 eta 0:25:10
epoch [22/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.0660 (0.5182) lr 1.5358e-03 eta 0:24:48
epoch [22/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.3693 (0.5510) lr 1.5358e-03 eta 0:24:35
epoch [22/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.8944 (0.5894) lr 1.5358e-03 eta 0:24:25
epoch [22/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.4729 (0.5717) lr 1.5358e-03 eta 0:24:16
epoch [22/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.1389 (0.5756) lr 1.5358e-03 eta 0:24:08
epoch [22/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.2372 (0.5753) lr 1.5358e-03 eta 0:24:02
epoch [22/50] batch [180/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.8852 (0.5948) lr 1.5358e-03 eta 0:23:55
epoch [22/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.2400 (0.5953) lr 1.5358e-03 eta 0:23:49
epoch [23/50] batch [20/204] time 0.245 (0.266) data 0.000 (0.018) loss 0.5763 (0.4667) lr 1.4818e-03 eta 0:25:12
epoch [23/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 0.2385 (0.5025) lr 1.4818e-03 eta 0:24:19
epoch [23/50] batch [60/204] time 0.246 (0.254) data 0.000 (0.006) loss 0.7650 (0.5456) lr 1.4818e-03 eta 0:23:56
epoch [23/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.005) loss 0.1654 (0.5754) lr 1.4818e-03 eta 0:23:43
epoch [23/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.6928 (0.5359) lr 1.4818e-03 eta 0:23:33
epoch [23/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.0925 (0.5563) lr 1.4818e-03 eta 0:23:25
epoch [23/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.7408 (0.5702) lr 1.4818e-03 eta 0:23:18
epoch [23/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.7549 (0.5579) lr 1.4818e-03 eta 0:23:11
epoch [23/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.0377 (0.5542) lr 1.4818e-03 eta 0:23:05
epoch [23/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 4.2391 (0.5615) lr 1.4818e-03 eta 0:22:58
epoch [24/50] batch [20/204] time 0.250 (0.266) data 0.000 (0.017) loss 0.4783 (0.5671) lr 1.4258e-03 eta 0:24:17
epoch [24/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.4766 (0.5095) lr 1.4258e-03 eta 0:23:24
epoch [24/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.3649 (0.5816) lr 1.4258e-03 eta 0:23:04
epoch [24/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.004) loss 1.5980 (0.6035) lr 1.4258e-03 eta 0:22:51
epoch [24/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.3599 (0.5890) lr 1.4258e-03 eta 0:22:42
epoch [24/50] batch [120/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.0966 (0.5717) lr 1.4258e-03 eta 0:22:34
epoch [24/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.9688 (0.5625) lr 1.4258e-03 eta 0:22:27
epoch [24/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0202 (0.5416) lr 1.4258e-03 eta 0:22:20
epoch [24/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.002) loss 1.2132 (0.5492) lr 1.4258e-03 eta 0:22:15
epoch [24/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.4872 (0.5404) lr 1.4258e-03 eta 0:22:08
epoch [25/50] batch [20/204] time 0.245 (0.267) data 0.000 (0.017) loss 1.2626 (0.7977) lr 1.3681e-03 eta 0:23:29
epoch [25/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.1012 (0.6276) lr 1.3681e-03 eta 0:22:37
epoch [25/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.1772 (0.5916) lr 1.3681e-03 eta 0:22:16
epoch [25/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0211 (0.5574) lr 1.3681e-03 eta 0:22:03
epoch [25/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.3026 (0.5503) lr 1.3681e-03 eta 0:21:53
epoch [25/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 1.1807 (0.5454) lr 1.3681e-03 eta 0:21:45
epoch [25/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 0.1879 (0.5409) lr 1.3681e-03 eta 0:21:38
epoch [25/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 1.5157 (0.5420) lr 1.3681e-03 eta 0:21:31
epoch [25/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.2441 (0.5480) lr 1.3681e-03 eta 0:21:25
epoch [25/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.3735 (0.5473) lr 1.3681e-03 eta 0:21:18
epoch [26/50] batch [20/204] time 0.245 (0.266) data 0.000 (0.017) loss 0.8782 (0.4708) lr 1.3090e-03 eta 0:22:31
epoch [26/50] batch [40/204] time 0.244 (0.258) data 0.000 (0.009) loss 0.7720 (0.4703) lr 1.3090e-03 eta 0:21:43
epoch [26/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.1008 (0.4740) lr 1.3090e-03 eta 0:21:22
epoch [26/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.004) loss 0.3765 (0.4989) lr 1.3090e-03 eta 0:21:09
epoch [26/50] batch [100/204] time 0.244 (0.252) data 0.000 (0.004) loss 0.8971 (0.5068) lr 1.3090e-03 eta 0:20:59
epoch [26/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4908 (0.4902) lr 1.3090e-03 eta 0:20:51
epoch [26/50] batch [140/204] time 0.245 (0.251) data 0.000 (0.003) loss 1.4070 (0.4942) lr 1.3090e-03 eta 0:20:43
epoch [26/50] batch [160/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.7830 (0.4989) lr 1.3090e-03 eta 0:20:37
epoch [26/50] batch [180/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.1047 (0.4927) lr 1.3090e-03 eta 0:20:30
epoch [26/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.0649 (0.5006) lr 1.3090e-03 eta 0:20:24
epoch [27/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.017) loss 0.5456 (0.4145) lr 1.2487e-03 eta 0:21:35
epoch [27/50] batch [40/204] time 0.245 (0.256) data 0.000 (0.009) loss 1.6933 (0.5152) lr 1.2487e-03 eta 0:20:45
epoch [27/50] batch [60/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.0300 (0.4978) lr 1.2487e-03 eta 0:20:26
epoch [27/50] batch [80/204] time 0.250 (0.252) data 0.000 (0.004) loss 1.9934 (0.5341) lr 1.2487e-03 eta 0:20:14
epoch [27/50] batch [100/204] time 0.248 (0.251) data 0.000 (0.004) loss 1.3651 (0.5139) lr 1.2487e-03 eta 0:20:05
epoch [27/50] batch [120/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1291 (0.5261) lr 1.2487e-03 eta 0:19:58
epoch [27/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.5170 (0.4992) lr 1.2487e-03 eta 0:19:51
epoch [27/50] batch [160/204] time 0.248 (0.250) data 0.000 (0.002) loss 1.2813 (0.4984) lr 1.2487e-03 eta 0:19:45
epoch [27/50] batch [180/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.1662 (0.4956) lr 1.2487e-03 eta 0:19:39
epoch [27/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.4406 (0.4955) lr 1.2487e-03 eta 0:19:33
epoch [28/50] batch [20/204] time 0.245 (0.265) data 0.000 (0.018) loss 0.1166 (0.4834) lr 1.1874e-03 eta 0:20:39
epoch [28/50] batch [40/204] time 0.242 (0.256) data 0.000 (0.009) loss 0.8072 (0.5823) lr 1.1874e-03 eta 0:19:52
epoch [28/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.3117 (0.4834) lr 1.1874e-03 eta 0:19:36
epoch [28/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.7238 (0.4553) lr 1.1874e-03 eta 0:19:25
epoch [28/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.2195 (0.4410) lr 1.1874e-03 eta 0:19:15
epoch [28/50] batch [120/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.0767 (0.4232) lr 1.1874e-03 eta 0:19:08
epoch [28/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.0922 (0.4384) lr 1.1874e-03 eta 0:19:01
epoch [28/50] batch [160/204] time 0.251 (0.250) data 0.000 (0.002) loss 1.1244 (0.4567) lr 1.1874e-03 eta 0:18:55
epoch [28/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.3137 (0.4616) lr 1.1874e-03 eta 0:18:49
epoch [28/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.3134 (0.4701) lr 1.1874e-03 eta 0:18:43
epoch [29/50] batch [20/204] time 0.252 (0.267) data 0.000 (0.017) loss 0.0423 (0.4860) lr 1.1253e-03 eta 0:19:52
epoch [29/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.3963 (0.5673) lr 1.1253e-03 eta 0:19:07
epoch [29/50] batch [60/204] time 0.252 (0.255) data 0.000 (0.006) loss 0.1275 (0.5127) lr 1.1253e-03 eta 0:18:47
epoch [29/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.5218 (0.4964) lr 1.1253e-03 eta 0:18:36
epoch [29/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.1781 (0.4730) lr 1.1253e-03 eta 0:18:27
epoch [29/50] batch [120/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.6301 (0.4686) lr 1.1253e-03 eta 0:18:19
epoch [29/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.6669 (0.4858) lr 1.1253e-03 eta 0:18:12
epoch [29/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.8391 (0.4631) lr 1.1253e-03 eta 0:18:06
epoch [29/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.4032 (0.4710) lr 1.1253e-03 eta 0:18:00
epoch [29/50] batch [200/204] time 0.247 (0.251) data 0.000 (0.002) loss 0.0167 (0.4784) lr 1.1253e-03 eta 0:17:54
epoch [30/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.8890 (0.4891) lr 1.0628e-03 eta 0:18:53
epoch [30/50] batch [40/204] time 0.254 (0.257) data 0.000 (0.009) loss 0.6924 (0.4912) lr 1.0628e-03 eta 0:18:11
epoch [30/50] batch [60/204] time 0.249 (0.254) data 0.000 (0.006) loss 0.1456 (0.4751) lr 1.0628e-03 eta 0:17:54
epoch [30/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.1094 (0.5255) lr 1.0628e-03 eta 0:17:43
epoch [30/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 1.4094 (0.5148) lr 1.0628e-03 eta 0:17:35
epoch [30/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.0944 (0.5140) lr 1.0628e-03 eta 0:17:27
epoch [30/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.6149 (0.5192) lr 1.0628e-03 eta 0:17:21
epoch [30/50] batch [160/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.4435 (0.5134) lr 1.0628e-03 eta 0:17:14
epoch [30/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.0825 (0.5060) lr 1.0628e-03 eta 0:17:08
epoch [30/50] batch [200/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.3422 (0.4964) lr 1.0628e-03 eta 0:17:03
epoch [31/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.017) loss 0.3384 (0.4161) lr 1.0000e-03 eta 0:18:00
epoch [31/50] batch [40/204] time 0.252 (0.258) data 0.000 (0.009) loss 0.0991 (0.3897) lr 1.0000e-03 eta 0:17:20
epoch [31/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 1.0770 (0.4057) lr 1.0000e-03 eta 0:17:03
epoch [31/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.1463 (0.4736) lr 1.0000e-03 eta 0:16:53
epoch [31/50] batch [100/204] time 0.243 (0.252) data 0.000 (0.004) loss 0.3553 (0.4481) lr 1.0000e-03 eta 0:16:44
epoch [31/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.1811 (0.4549) lr 1.0000e-03 eta 0:16:37
epoch [31/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.4001 (0.4340) lr 1.0000e-03 eta 0:16:30
epoch [31/50] batch [160/204] time 0.245 (0.251) data 0.000 (0.002) loss 1.1338 (0.4681) lr 1.0000e-03 eta 0:16:24
epoch [31/50] batch [180/204] time 0.245 (0.251) data 0.000 (0.002) loss 0.0538 (0.4559) lr 1.0000e-03 eta 0:16:17
epoch [31/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.1067 (0.4593) lr 1.0000e-03 eta 0:16:11
epoch [32/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.9372 (0.4175) lr 9.3721e-04 eta 0:17:06
epoch [32/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 0.8830 (0.5303) lr 9.3721e-04 eta 0:16:27
epoch [32/50] batch [60/204] time 0.246 (0.255) data 0.000 (0.006) loss 0.5548 (0.5379) lr 9.3721e-04 eta 0:16:11
epoch [32/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.9523 (0.5273) lr 9.3721e-04 eta 0:16:00
epoch [32/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.2929 (0.4865) lr 9.3721e-04 eta 0:15:52
epoch [32/50] batch [120/204] time 0.243 (0.252) data 0.000 (0.003) loss 0.9227 (0.5010) lr 9.3721e-04 eta 0:15:45
epoch [32/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.2696 (0.4916) lr 9.3721e-04 eta 0:15:39
epoch [32/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.2678 (0.4777) lr 9.3721e-04 eta 0:15:32
epoch [32/50] batch [180/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.0523 (0.4672) lr 9.3721e-04 eta 0:15:26
epoch [32/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 1.1087 (0.4734) lr 9.3721e-04 eta 0:15:20
epoch [33/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.018) loss 0.0391 (0.4076) lr 8.7467e-04 eta 0:16:11
epoch [33/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.0770 (0.3845) lr 8.7467e-04 eta 0:15:33
epoch [33/50] batch [60/204] time 0.246 (0.254) data 0.000 (0.006) loss 1.3989 (0.3992) lr 8.7467e-04 eta 0:15:17
epoch [33/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.3075 (0.3792) lr 8.7467e-04 eta 0:15:08
epoch [33/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.1397 (0.3974) lr 8.7467e-04 eta 0:15:00
epoch [33/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.2118 (0.3998) lr 8.7467e-04 eta 0:14:53
epoch [33/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.4008 (0.4094) lr 8.7467e-04 eta 0:14:47
epoch [33/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1803 (0.4095) lr 8.7467e-04 eta 0:14:41
epoch [33/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.3955 (0.4321) lr 8.7467e-04 eta 0:14:35
epoch [33/50] batch [200/204] time 0.248 (0.250) data 0.000 (0.002) loss 0.0629 (0.4409) lr 8.7467e-04 eta 0:14:29
epoch [34/50] batch [20/204] time 0.246 (0.266) data 0.000 (0.017) loss 1.9627 (0.4086) lr 8.1262e-04 eta 0:15:17
epoch [34/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 0.1839 (0.5280) lr 8.1262e-04 eta 0:14:42
epoch [34/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.0546 (0.5042) lr 8.1262e-04 eta 0:14:27
epoch [34/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 1.0078 (0.4876) lr 8.1262e-04 eta 0:14:17
epoch [34/50] batch [100/204] time 0.248 (0.252) data 0.000 (0.004) loss 0.0516 (0.4561) lr 8.1262e-04 eta 0:14:09
epoch [34/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.0994 (0.4492) lr 8.1262e-04 eta 0:14:02
epoch [34/50] batch [140/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1779 (0.4291) lr 8.1262e-04 eta 0:13:56
epoch [34/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.7178 (0.4256) lr 8.1262e-04 eta 0:13:49
epoch [34/50] batch [180/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.5876 (0.4272) lr 8.1262e-04 eta 0:13:44
epoch [34/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 0.8232 (0.4421) lr 8.1262e-04 eta 0:13:38
epoch [35/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.018) loss 0.7432 (0.3586) lr 7.5131e-04 eta 0:14:26
epoch [35/50] batch [40/204] time 0.247 (0.258) data 0.000 (0.009) loss 0.6519 (0.3726) lr 7.5131e-04 eta 0:13:52
epoch [35/50] batch [60/204] time 0.251 (0.255) data 0.000 (0.006) loss 0.1831 (0.4177) lr 7.5131e-04 eta 0:13:37
epoch [35/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.9050 (0.4424) lr 7.5131e-04 eta 0:13:26
epoch [35/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.1785 (0.4646) lr 7.5131e-04 eta 0:13:18
epoch [35/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.003) loss 0.0478 (0.4462) lr 7.5131e-04 eta 0:13:11
epoch [35/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.7570 (0.4510) lr 7.5131e-04 eta 0:13:05
epoch [35/50] batch [160/204] time 0.252 (0.251) data 0.000 (0.002) loss 0.5000 (0.4745) lr 7.5131e-04 eta 0:12:59
epoch [35/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0924 (0.4752) lr 7.5131e-04 eta 0:12:53
epoch [35/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.8804 (0.4890) lr 7.5131e-04 eta 0:12:47
epoch [36/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.017) loss 0.2648 (0.3383) lr 6.9098e-04 eta 0:13:30
epoch [36/50] batch [40/204] time 0.248 (0.258) data 0.000 (0.009) loss 0.1247 (0.3257) lr 6.9098e-04 eta 0:12:58
epoch [36/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 0.3100 (0.3604) lr 6.9098e-04 eta 0:12:44
epoch [36/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.004) loss 1.3123 (0.4049) lr 6.9098e-04 eta 0:12:34
epoch [36/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.003) loss 0.1587 (0.3915) lr 6.9098e-04 eta 0:12:26
epoch [36/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.0377 (0.3830) lr 6.9098e-04 eta 0:12:20
epoch [36/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 1.4005 (0.3921) lr 6.9098e-04 eta 0:12:13
epoch [36/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0708 (0.3936) lr 6.9098e-04 eta 0:12:07
epoch [36/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.0528 (0.3916) lr 6.9098e-04 eta 0:12:02
epoch [36/50] batch [200/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.8507 (0.3951) lr 6.9098e-04 eta 0:11:56
epoch [37/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.017) loss 0.9360 (0.5310) lr 6.3188e-04 eta 0:12:36
epoch [37/50] batch [40/204] time 0.245 (0.258) data 0.000 (0.009) loss 0.3986 (0.4259) lr 6.3188e-04 eta 0:12:06
epoch [37/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.6019 (0.3924) lr 6.3188e-04 eta 0:11:51
epoch [37/50] batch [80/204] time 0.244 (0.253) data 0.000 (0.004) loss 0.6580 (0.3809) lr 6.3188e-04 eta 0:11:42
epoch [37/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.3599 (0.3911) lr 6.3188e-04 eta 0:11:34
epoch [37/50] batch [120/204] time 0.248 (0.252) data 0.000 (0.003) loss 0.4433 (0.3880) lr 6.3188e-04 eta 0:11:28
epoch [37/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 1.5215 (0.3850) lr 6.3188e-04 eta 0:11:22
epoch [37/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.1820 (0.4110) lr 6.3188e-04 eta 0:11:16
epoch [37/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1294 (0.4077) lr 6.3188e-04 eta 0:11:11
epoch [37/50] batch [200/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.7290 (0.4184) lr 6.3188e-04 eta 0:11:05
epoch [38/50] batch [20/204] time 0.250 (0.267) data 0.000 (0.017) loss 0.2869 (0.5973) lr 5.7422e-04 eta 0:11:42
epoch [38/50] batch [40/204] time 0.246 (0.258) data 0.000 (0.009) loss 0.0152 (0.5421) lr 5.7422e-04 eta 0:11:14
epoch [38/50] batch [60/204] time 0.251 (0.256) data 0.000 (0.006) loss 0.1176 (0.4810) lr 5.7422e-04 eta 0:11:02
epoch [38/50] batch [80/204] time 0.251 (0.254) data 0.000 (0.004) loss 0.2379 (0.4686) lr 5.7422e-04 eta 0:10:53
epoch [38/50] batch [100/204] time 0.243 (0.253) data 0.000 (0.004) loss 0.4913 (0.4558) lr 5.7422e-04 eta 0:10:45
epoch [38/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.2715 (0.4492) lr 5.7422e-04 eta 0:10:38
epoch [38/50] batch [140/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.0467 (0.4452) lr 5.7422e-04 eta 0:10:32
epoch [38/50] batch [160/204] time 0.242 (0.251) data 0.000 (0.002) loss 0.1098 (0.4282) lr 5.7422e-04 eta 0:10:25
epoch [38/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.4274 (0.4170) lr 5.7422e-04 eta 0:10:20
epoch [38/50] batch [200/204] time 0.243 (0.251) data 0.000 (0.002) loss 0.4852 (0.4170) lr 5.7422e-04 eta 0:10:14
epoch [39/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.8550 (0.5327) lr 5.1825e-04 eta 0:10:46
epoch [39/50] batch [40/204] time 0.245 (0.258) data 0.000 (0.009) loss 0.1762 (0.4702) lr 5.1825e-04 eta 0:10:20
epoch [39/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.6926 (0.4730) lr 5.1825e-04 eta 0:10:09
epoch [39/50] batch [80/204] time 0.249 (0.253) data 0.000 (0.004) loss 0.6596 (0.4828) lr 5.1825e-04 eta 0:10:00
epoch [39/50] batch [100/204] time 0.249 (0.252) data 0.000 (0.004) loss 0.0588 (0.5374) lr 5.1825e-04 eta 0:09:52
epoch [39/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 1.0572 (0.5300) lr 5.1825e-04 eta 0:09:46
epoch [39/50] batch [140/204] time 0.246 (0.251) data 0.000 (0.003) loss 0.9780 (0.5170) lr 5.1825e-04 eta 0:09:40
epoch [39/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.1555 (0.4965) lr 5.1825e-04 eta 0:09:34
epoch [39/50] batch [180/204] time 0.248 (0.251) data 0.000 (0.002) loss 0.3025 (0.4901) lr 5.1825e-04 eta 0:09:28
epoch [39/50] batch [200/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.7518 (0.4699) lr 5.1825e-04 eta 0:09:23
epoch [40/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.018) loss 0.1311 (0.3251) lr 4.6417e-04 eta 0:09:51
epoch [40/50] batch [40/204] time 0.251 (0.257) data 0.000 (0.009) loss 0.1797 (0.3846) lr 4.6417e-04 eta 0:09:26
epoch [40/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 0.3526 (0.3605) lr 4.6417e-04 eta 0:09:15
epoch [40/50] batch [80/204] time 0.250 (0.253) data 0.000 (0.004) loss 0.3840 (0.3649) lr 4.6417e-04 eta 0:09:07
epoch [40/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.0728 (0.3908) lr 4.6417e-04 eta 0:09:00
epoch [40/50] batch [120/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1825 (0.3763) lr 4.6417e-04 eta 0:08:53
epoch [40/50] batch [140/204] time 0.242 (0.251) data 0.000 (0.003) loss 0.0564 (0.3629) lr 4.6417e-04 eta 0:08:47
epoch [40/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.0702 (0.3578) lr 4.6417e-04 eta 0:08:42
epoch [40/50] batch [180/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.3033 (0.3548) lr 4.6417e-04 eta 0:08:36
epoch [40/50] batch [200/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.1345 (0.3576) lr 4.6417e-04 eta 0:08:30
epoch [41/50] batch [20/204] time 0.248 (0.266) data 0.000 (0.017) loss 0.1788 (0.5944) lr 4.1221e-04 eta 0:08:57
epoch [41/50] batch [40/204] time 0.245 (0.257) data 0.000 (0.009) loss 0.6286 (0.5263) lr 4.1221e-04 eta 0:08:34
epoch [41/50] batch [60/204] time 0.250 (0.254) data 0.000 (0.006) loss 0.1579 (0.4680) lr 4.1221e-04 eta 0:08:23
epoch [41/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.004) loss 0.0382 (0.4506) lr 4.1221e-04 eta 0:08:15
epoch [41/50] batch [100/204] time 0.252 (0.252) data 0.000 (0.004) loss 0.8085 (0.4179) lr 4.1221e-04 eta 0:08:09
epoch [41/50] batch [120/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.0296 (0.4148) lr 4.1221e-04 eta 0:08:02
epoch [41/50] batch [140/204] time 0.250 (0.251) data 0.000 (0.003) loss 0.1031 (0.4091) lr 4.1221e-04 eta 0:07:56
epoch [41/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1463 (0.4355) lr 4.1221e-04 eta 0:07:51
epoch [41/50] batch [180/204] time 0.249 (0.250) data 0.000 (0.002) loss 0.1888 (0.4205) lr 4.1221e-04 eta 0:07:45
epoch [41/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.0925 (0.4277) lr 4.1221e-04 eta 0:07:40
epoch [42/50] batch [20/204] time 0.249 (0.266) data 0.000 (0.018) loss 0.7625 (0.4371) lr 3.6258e-04 eta 0:08:03
epoch [42/50] batch [40/204] time 0.250 (0.257) data 0.000 (0.009) loss 1.0079 (0.3916) lr 3.6258e-04 eta 0:07:41
epoch [42/50] batch [60/204] time 0.251 (0.254) data 0.000 (0.006) loss 1.6866 (0.4121) lr 3.6258e-04 eta 0:07:30
epoch [42/50] batch [80/204] time 0.245 (0.252) data 0.000 (0.005) loss 0.1373 (0.3908) lr 3.6258e-04 eta 0:07:23
epoch [42/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 1.0223 (0.4028) lr 3.6258e-04 eta 0:07:16
epoch [42/50] batch [120/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.1033 (0.4055) lr 3.6258e-04 eta 0:07:10
epoch [42/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3535 (0.3817) lr 3.6258e-04 eta 0:07:05
epoch [42/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.0762 (0.3715) lr 3.6258e-04 eta 0:06:59
epoch [42/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.0660 (0.3838) lr 3.6258e-04 eta 0:06:54
epoch [42/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.2195 (0.3859) lr 3.6258e-04 eta 0:06:49
epoch [43/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 0.3262 (0.5726) lr 3.1545e-04 eta 0:07:08
epoch [43/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.3347 (0.5226) lr 3.1545e-04 eta 0:06:49
epoch [43/50] batch [60/204] time 0.245 (0.254) data 0.000 (0.006) loss 0.4214 (0.4603) lr 3.1545e-04 eta 0:06:39
epoch [43/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.1314 (0.3991) lr 3.1545e-04 eta 0:06:32
epoch [43/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.1071 (0.3911) lr 3.1545e-04 eta 0:06:26
epoch [43/50] batch [120/204] time 0.247 (0.251) data 0.000 (0.003) loss 0.3992 (0.4162) lr 3.1545e-04 eta 0:06:20
epoch [43/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1229 (0.3942) lr 3.1545e-04 eta 0:06:14
epoch [43/50] batch [160/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.1560 (0.3908) lr 3.1545e-04 eta 0:06:08
epoch [43/50] batch [180/204] time 0.245 (0.250) data 0.000 (0.002) loss 0.7526 (0.4102) lr 3.1545e-04 eta 0:06:03
epoch [43/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.1260 (0.4092) lr 3.1545e-04 eta 0:05:58
epoch [44/50] batch [20/204] time 0.245 (0.267) data 0.000 (0.018) loss 0.1127 (0.4165) lr 2.7103e-04 eta 0:06:15
epoch [44/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.6989 (0.3713) lr 2.7103e-04 eta 0:05:57
epoch [44/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.1606 (0.3764) lr 2.7103e-04 eta 0:05:48
epoch [44/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.005) loss 0.4262 (0.3732) lr 2.7103e-04 eta 0:05:41
epoch [44/50] batch [100/204] time 0.246 (0.252) data 0.000 (0.004) loss 0.1130 (0.3529) lr 2.7103e-04 eta 0:05:34
epoch [44/50] batch [120/204] time 0.246 (0.252) data 0.000 (0.003) loss 0.3524 (0.3912) lr 2.7103e-04 eta 0:05:29
epoch [44/50] batch [140/204] time 0.249 (0.251) data 0.000 (0.003) loss 0.1063 (0.3896) lr 2.7103e-04 eta 0:05:23
epoch [44/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0955 (0.3842) lr 2.7103e-04 eta 0:05:18
epoch [44/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1387 (0.3849) lr 2.7103e-04 eta 0:05:12
epoch [44/50] batch [200/204] time 0.247 (0.250) data 0.000 (0.002) loss 1.8681 (0.3907) lr 2.7103e-04 eta 0:05:07
epoch [45/50] batch [20/204] time 0.251 (0.266) data 0.000 (0.017) loss 1.2897 (0.6507) lr 2.2949e-04 eta 0:05:19
epoch [45/50] batch [40/204] time 0.249 (0.257) data 0.000 (0.009) loss 1.1459 (0.4826) lr 2.2949e-04 eta 0:05:04
epoch [45/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.4964 (0.4935) lr 2.2949e-04 eta 0:04:56
epoch [45/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.3145 (0.4517) lr 2.2949e-04 eta 0:04:49
epoch [45/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.0346 (0.4241) lr 2.2949e-04 eta 0:04:43
epoch [45/50] batch [120/204] time 0.252 (0.252) data 0.000 (0.003) loss 0.0348 (0.4312) lr 2.2949e-04 eta 0:04:37
epoch [45/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0696 (0.4093) lr 2.2949e-04 eta 0:04:32
epoch [45/50] batch [160/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.7800 (0.4062) lr 2.2949e-04 eta 0:04:26
epoch [45/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0557 (0.4293) lr 2.2949e-04 eta 0:04:21
epoch [45/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.3917 (0.4183) lr 2.2949e-04 eta 0:04:16
epoch [46/50] batch [20/204] time 0.243 (0.266) data 0.000 (0.017) loss 0.0758 (0.4149) lr 1.9098e-04 eta 0:04:26
epoch [46/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 0.0488 (0.3539) lr 1.9098e-04 eta 0:04:12
epoch [46/50] batch [60/204] time 0.252 (0.255) data 0.000 (0.006) loss 0.5529 (0.3917) lr 1.9098e-04 eta 0:04:04
epoch [46/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0857 (0.3845) lr 1.9098e-04 eta 0:03:58
epoch [46/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.0423 (0.3705) lr 1.9098e-04 eta 0:03:52
epoch [46/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.5289 (0.3728) lr 1.9098e-04 eta 0:03:46
epoch [46/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.3697 (0.3740) lr 1.9098e-04 eta 0:03:41
epoch [46/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.1650 (0.3624) lr 1.9098e-04 eta 0:03:35
epoch [46/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.1496 (0.3919) lr 1.9098e-04 eta 0:03:30
epoch [46/50] batch [200/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.1011 (0.3961) lr 1.9098e-04 eta 0:03:25
epoch [47/50] batch [20/204] time 0.245 (0.266) data 0.000 (0.017) loss 0.0695 (0.2952) lr 1.5567e-04 eta 0:03:32
epoch [47/50] batch [40/204] time 0.250 (0.258) data 0.000 (0.009) loss 0.8859 (0.3639) lr 1.5567e-04 eta 0:03:19
epoch [47/50] batch [60/204] time 0.250 (0.255) data 0.000 (0.006) loss 0.2020 (0.3489) lr 1.5567e-04 eta 0:03:12
epoch [47/50] batch [80/204] time 0.246 (0.253) data 0.000 (0.004) loss 0.8102 (0.3978) lr 1.5567e-04 eta 0:03:06
epoch [47/50] batch [100/204] time 0.251 (0.252) data 0.000 (0.004) loss 0.7073 (0.4087) lr 1.5567e-04 eta 0:03:00
epoch [47/50] batch [120/204] time 0.250 (0.252) data 0.000 (0.003) loss 0.1599 (0.3840) lr 1.5567e-04 eta 0:02:55
epoch [47/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.1791 (0.3751) lr 1.5567e-04 eta 0:02:49
epoch [47/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.1005 (0.3618) lr 1.5567e-04 eta 0:02:44
epoch [47/50] batch [180/204] time 0.250 (0.251) data 0.000 (0.002) loss 0.2482 (0.3428) lr 1.5567e-04 eta 0:02:39
epoch [47/50] batch [200/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.1239 (0.3619) lr 1.5567e-04 eta 0:02:34
epoch [48/50] batch [20/204] time 0.251 (0.267) data 0.000 (0.017) loss 0.2389 (0.4680) lr 1.2369e-04 eta 0:02:37
epoch [48/50] batch [40/204] time 0.246 (0.257) data 0.000 (0.009) loss 1.1486 (0.4010) lr 1.2369e-04 eta 0:02:27
epoch [48/50] batch [60/204] time 0.249 (0.255) data 0.000 (0.006) loss 0.0967 (0.4184) lr 1.2369e-04 eta 0:02:20
epoch [48/50] batch [80/204] time 0.245 (0.253) data 0.000 (0.004) loss 0.7216 (0.4224) lr 1.2369e-04 eta 0:02:14
epoch [48/50] batch [100/204] time 0.245 (0.252) data 0.000 (0.004) loss 0.7075 (0.4003) lr 1.2369e-04 eta 0:02:09
epoch [48/50] batch [120/204] time 0.251 (0.252) data 0.000 (0.003) loss 0.6415 (0.4023) lr 1.2369e-04 eta 0:02:03
epoch [48/50] batch [140/204] time 0.251 (0.251) data 0.000 (0.003) loss 0.0876 (0.3896) lr 1.2369e-04 eta 0:01:58
epoch [48/50] batch [160/204] time 0.246 (0.251) data 0.000 (0.002) loss 0.3177 (0.3886) lr 1.2369e-04 eta 0:01:53
epoch [48/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.6003 (0.3931) lr 1.2369e-04 eta 0:01:48
epoch [48/50] batch [200/204] time 0.251 (0.250) data 0.000 (0.002) loss 0.7696 (0.3972) lr 1.2369e-04 eta 0:01:43
epoch [49/50] batch [20/204] time 0.250 (0.266) data 0.000 (0.017) loss 0.1685 (0.2922) lr 9.5173e-05 eta 0:01:43
epoch [49/50] batch [40/204] time 0.249 (0.258) data 0.000 (0.009) loss 0.0278 (0.3012) lr 9.5173e-05 eta 0:01:34
epoch [49/50] batch [60/204] time 0.245 (0.255) data 0.000 (0.006) loss 0.0899 (0.2816) lr 9.5173e-05 eta 0:01:28
epoch [49/50] batch [80/204] time 0.251 (0.253) data 0.000 (0.004) loss 0.0764 (0.2980) lr 9.5173e-05 eta 0:01:23
epoch [49/50] batch [100/204] time 0.250 (0.252) data 0.000 (0.004) loss 0.1342 (0.3032) lr 9.5173e-05 eta 0:01:17
epoch [49/50] batch [120/204] time 0.249 (0.252) data 0.000 (0.003) loss 0.6942 (0.3210) lr 9.5173e-05 eta 0:01:12
epoch [49/50] batch [140/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.2846 (0.3200) lr 9.5173e-05 eta 0:01:07
epoch [49/50] batch [160/204] time 0.242 (0.251) data 0.000 (0.002) loss 0.7592 (0.3429) lr 9.5173e-05 eta 0:01:02
epoch [49/50] batch [180/204] time 0.251 (0.251) data 0.000 (0.002) loss 0.0855 (0.3761) lr 9.5173e-05 eta 0:00:57
epoch [49/50] batch [200/204] time 0.242 (0.250) data 0.000 (0.002) loss 0.0488 (0.3660) lr 9.5173e-05 eta 0:00:52
epoch [50/50] batch [20/204] time 0.247 (0.265) data 0.000 (0.017) loss 0.1240 (0.5314) lr 7.0224e-05 eta 0:00:48
epoch [50/50] batch [40/204] time 0.248 (0.257) data 0.000 (0.009) loss 0.2100 (0.4296) lr 7.0224e-05 eta 0:00:42
epoch [50/50] batch [60/204] time 0.247 (0.254) data 0.000 (0.006) loss 0.0301 (0.4083) lr 7.0224e-05 eta 0:00:36
epoch [50/50] batch [80/204] time 0.248 (0.253) data 0.000 (0.004) loss 0.4460 (0.3893) lr 7.0224e-05 eta 0:00:31
epoch [50/50] batch [100/204] time 0.244 (0.252) data 0.000 (0.004) loss 0.6302 (0.3790) lr 7.0224e-05 eta 0:00:26
epoch [50/50] batch [120/204] time 0.248 (0.251) data 0.000 (0.003) loss 0.3976 (0.3660) lr 7.0224e-05 eta 0:00:21
epoch [50/50] batch [140/204] time 0.243 (0.251) data 0.000 (0.003) loss 0.1259 (0.3554) lr 7.0224e-05 eta 0:00:16
epoch [50/50] batch [160/204] time 0.249 (0.251) data 0.000 (0.002) loss 0.2806 (0.3856) lr 7.0224e-05 eta 0:00:11
epoch [50/50] batch [180/204] time 0.250 (0.250) data 0.000 (0.002) loss 0.1028 (0.3995) lr 7.0224e-05 eta 0:00:06
epoch [50/50] batch [200/204] time 0.244 (0.250) data 0.000 (0.002) loss 0.5404 (0.4012) lr 7.0224e-05 eta 0:00:01
Checkpoint saved to output/base2new/train_base/oxford_flowers/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: 1,176
* correct: 1,145
* accuracy: 97.36%
* error: 2.64%
* macro_f1: 97.41%
Elapsed: 0:43:21
