2023-07-26 14:15:51,620 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,621 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): XLMRobertaModel(
      (embeddings): XLMRobertaEmbeddings(
        (word_embeddings): Embedding(250003, 768)
        (position_embeddings): Embedding(514, 768, padding_idx=1)
        (token_type_embeddings): Embedding(1, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): XLMRobertaEncoder(
        (layer): ModuleList(
          (0): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (1): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (2): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (3): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (4): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (5): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (6): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (7): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (8): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (9): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (10): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (11): XLMRobertaLayer(
            (attention): XLMRobertaAttention(
              (self): XLMRobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): XLMRobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): XLMRobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): XLMRobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): XLMRobertaPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
  )
  (word_dropout): WordDropout(p=0.05)
  (locked_dropout): LockedDropout(p=0.5)
  (linear): Linear(in_features=768, out_features=158, bias=True)
  (loss_function): ViterbiLoss()
  (crf): CRF()
)"
2023-07-26 14:15:51,622 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,622 Corpus: "Corpus: 7767 train + 409 dev + 0 test sentences"
2023-07-26 14:15:51,622 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,622 Parameters:
2023-07-26 14:15:51,622  - learning_rate: "0.000050"
2023-07-26 14:15:51,622  - mini_batch_size: "32"
2023-07-26 14:15:51,622  - patience: "3"
2023-07-26 14:15:51,622  - anneal_factor: "0.5"
2023-07-26 14:15:51,622  - max_epochs: "50"
2023-07-26 14:15:51,622  - shuffle: "True"
2023-07-26 14:15:51,622  - train_with_dev: "False"
2023-07-26 14:15:51,622  - batch_growth_annealing: "False"
2023-07-26 14:15:51,622 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,622 Model training base path: "/scratch/skulick/ppchy-11-pos/xlmb-ck05-yid1/split_final/train"
2023-07-26 14:15:51,623 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,623 Device: cuda:0
2023-07-26 14:15:51,623 ----------------------------------------------------------------------------------------------------
2023-07-26 14:15:51,623 Embeddings storage mode: none
2023-07-26 14:15:51,623 ----------------------------------------------------------------------------------------------------
2023-07-26 14:16:43,612 epoch 1 - iter 24/243 - loss 5.78182875 - time (sec): 51.99 - samples/sec: 143.68 - lr: 0.000001
2023-07-26 14:17:33,864 epoch 1 - iter 48/243 - loss 5.72562134 - time (sec): 102.24 - samples/sec: 145.85 - lr: 0.000002
2023-07-26 14:18:18,655 epoch 1 - iter 72/243 - loss 5.61608578 - time (sec): 147.03 - samples/sec: 153.94 - lr: 0.000003
2023-07-26 14:19:03,423 epoch 1 - iter 96/243 - loss 5.47788448 - time (sec): 191.80 - samples/sec: 157.84 - lr: 0.000004
2023-07-26 14:19:48,078 epoch 1 - iter 120/243 - loss 5.26991238 - time (sec): 236.45 - samples/sec: 160.79 - lr: 0.000005
2023-07-26 14:20:32,722 epoch 1 - iter 144/243 - loss 5.07404788 - time (sec): 281.10 - samples/sec: 162.52 - lr: 0.000006
2023-07-26 14:21:18,887 epoch 1 - iter 168/243 - loss 4.86972776 - time (sec): 327.26 - samples/sec: 164.17 - lr: 0.000007
2023-07-26 14:22:07,928 epoch 1 - iter 192/243 - loss 4.66109804 - time (sec): 376.31 - samples/sec: 164.20 - lr: 0.000008
2023-07-26 14:22:56,658 epoch 1 - iter 216/243 - loss 4.44788101 - time (sec): 425.04 - samples/sec: 163.40 - lr: 0.000009
2023-07-26 14:23:45,642 epoch 1 - iter 240/243 - loss 4.23693631 - time (sec): 474.02 - samples/sec: 163.81 - lr: 0.000010
2023-07-26 14:23:51,273 ----------------------------------------------------------------------------------------------------
2023-07-26 14:23:51,273 EPOCH 1 done: loss 4.2141 - lr 0.000010
2023-07-26 14:23:53,076 Evaluating as a multi-label problem: False
2023-07-26 14:23:53,119 DEV : loss 1.6606154441833496 - f1-score (micro avg)  0.7017
2023-07-26 14:23:53,129 saving best model
2023-07-26 14:23:55,463 ----------------------------------------------------------------------------------------------------
2023-07-26 14:24:39,905 epoch 2 - iter 24/243 - loss 1.93643008 - time (sec): 44.44 - samples/sec: 172.43 - lr: 0.000011
2023-07-26 14:25:24,584 epoch 2 - iter 48/243 - loss 1.80170810 - time (sec): 89.12 - samples/sec: 174.28 - lr: 0.000012
2023-07-26 14:26:09,249 epoch 2 - iter 72/243 - loss 1.68553020 - time (sec): 133.79 - samples/sec: 174.97 - lr: 0.000013
2023-07-26 14:26:53,935 epoch 2 - iter 96/243 - loss 1.59018149 - time (sec): 178.47 - samples/sec: 175.90 - lr: 0.000014
2023-07-26 14:27:38,417 epoch 2 - iter 120/243 - loss 1.51168641 - time (sec): 222.95 - samples/sec: 176.47 - lr: 0.000015
2023-07-26 14:28:23,238 epoch 2 - iter 144/243 - loss 1.44496232 - time (sec): 267.77 - samples/sec: 176.24 - lr: 0.000016
2023-07-26 14:29:07,485 epoch 2 - iter 168/243 - loss 1.38343183 - time (sec): 312.02 - samples/sec: 175.74 - lr: 0.000017
2023-07-26 14:29:51,869 epoch 2 - iter 192/243 - loss 1.32848150 - time (sec): 356.41 - samples/sec: 175.52 - lr: 0.000018
2023-07-26 14:30:36,135 epoch 2 - iter 216/243 - loss 1.28678633 - time (sec): 400.67 - samples/sec: 174.52 - lr: 0.000019
2023-07-26 14:31:20,592 epoch 2 - iter 240/243 - loss 1.24063251 - time (sec): 445.13 - samples/sec: 174.61 - lr: 0.000020
2023-07-26 14:31:25,683 ----------------------------------------------------------------------------------------------------
2023-07-26 14:31:25,683 EPOCH 2 done: loss 1.2362 - lr 0.000020
2023-07-26 14:31:27,442 Evaluating as a multi-label problem: False
2023-07-26 14:31:27,484 DEV : loss 0.4555579721927643 - f1-score (micro avg)  0.9132
2023-07-26 14:31:27,494 saving best model
2023-07-26 14:31:30,740 ----------------------------------------------------------------------------------------------------
2023-07-26 14:32:15,374 epoch 3 - iter 24/243 - loss 0.80478615 - time (sec): 44.63 - samples/sec: 181.44 - lr: 0.000021
2023-07-26 14:32:59,817 epoch 3 - iter 48/243 - loss 0.76412570 - time (sec): 89.08 - samples/sec: 179.04 - lr: 0.000022
2023-07-26 14:33:44,386 epoch 3 - iter 72/243 - loss 0.74620943 - time (sec): 133.64 - samples/sec: 176.74 - lr: 0.000023
2023-07-26 14:34:28,788 epoch 3 - iter 96/243 - loss 0.72917808 - time (sec): 178.05 - samples/sec: 175.92 - lr: 0.000024
2023-07-26 14:35:13,386 epoch 3 - iter 120/243 - loss 0.72089137 - time (sec): 222.64 - samples/sec: 176.15 - lr: 0.000025
2023-07-26 14:35:57,934 epoch 3 - iter 144/243 - loss 0.70075087 - time (sec): 267.19 - samples/sec: 175.65 - lr: 0.000026
2023-07-26 14:36:42,264 epoch 3 - iter 168/243 - loss 0.68433087 - time (sec): 311.52 - samples/sec: 174.95 - lr: 0.000027
2023-07-26 14:37:26,778 epoch 3 - iter 192/243 - loss 0.67039041 - time (sec): 356.04 - samples/sec: 175.14 - lr: 0.000028
2023-07-26 14:38:11,135 epoch 3 - iter 216/243 - loss 0.66061953 - time (sec): 400.39 - samples/sec: 175.13 - lr: 0.000029
2023-07-26 14:38:55,563 epoch 3 - iter 240/243 - loss 0.65094446 - time (sec): 444.82 - samples/sec: 174.77 - lr: 0.000030
2023-07-26 14:39:00,596 ----------------------------------------------------------------------------------------------------
2023-07-26 14:39:00,596 EPOCH 3 done: loss 0.6499 - lr 0.000030
2023-07-26 14:39:02,334 Evaluating as a multi-label problem: False
2023-07-26 14:39:02,376 DEV : loss 0.247285857796669 - f1-score (micro avg)  0.9518
2023-07-26 14:39:02,385 saving best model
2023-07-26 14:39:05,730 ----------------------------------------------------------------------------------------------------
2023-07-26 14:39:50,093 epoch 4 - iter 24/243 - loss 0.55472967 - time (sec): 44.36 - samples/sec: 176.66 - lr: 0.000031
2023-07-26 14:40:34,562 epoch 4 - iter 48/243 - loss 0.52360637 - time (sec): 88.83 - samples/sec: 175.54 - lr: 0.000032
2023-07-26 14:41:19,307 epoch 4 - iter 72/243 - loss 0.51655667 - time (sec): 133.58 - samples/sec: 174.54 - lr: 0.000033
2023-07-26 14:42:05,307 epoch 4 - iter 96/243 - loss 0.51891961 - time (sec): 179.58 - samples/sec: 173.86 - lr: 0.000034
2023-07-26 14:42:54,480 epoch 4 - iter 120/243 - loss 0.50631556 - time (sec): 228.75 - samples/sec: 171.40 - lr: 0.000035
2023-07-26 14:43:43,446 epoch 4 - iter 144/243 - loss 0.50459545 - time (sec): 277.72 - samples/sec: 168.74 - lr: 0.000036
2023-07-26 14:44:32,519 epoch 4 - iter 168/243 - loss 0.50045519 - time (sec): 326.79 - samples/sec: 167.35 - lr: 0.000037
2023-07-26 14:45:21,599 epoch 4 - iter 192/243 - loss 0.49446570 - time (sec): 375.87 - samples/sec: 166.24 - lr: 0.000038
2023-07-26 14:46:10,542 epoch 4 - iter 216/243 - loss 0.49218271 - time (sec): 424.81 - samples/sec: 165.38 - lr: 0.000039
2023-07-26 14:46:59,284 epoch 4 - iter 240/243 - loss 0.49159525 - time (sec): 473.55 - samples/sec: 164.09 - lr: 0.000040
2023-07-26 14:47:04,893 ----------------------------------------------------------------------------------------------------
2023-07-26 14:47:04,893 EPOCH 4 done: loss 0.4917 - lr 0.000040
2023-07-26 14:47:06,684 Evaluating as a multi-label problem: False
2023-07-26 14:47:06,726 DEV : loss 0.18006576597690582 - f1-score (micro avg)  0.9648
2023-07-26 14:47:06,736 saving best model
2023-07-26 14:47:10,014 ----------------------------------------------------------------------------------------------------
2023-07-26 14:47:54,932 epoch 5 - iter 24/243 - loss 0.45058356 - time (sec): 44.92 - samples/sec: 173.25 - lr: 0.000041
2023-07-26 14:48:41,950 epoch 5 - iter 48/243 - loss 0.43329992 - time (sec): 91.94 - samples/sec: 169.29 - lr: 0.000042
2023-07-26 14:49:33,377 epoch 5 - iter 72/243 - loss 0.43373609 - time (sec): 143.36 - samples/sec: 163.90 - lr: 0.000043
2023-07-26 14:50:24,178 epoch 5 - iter 96/243 - loss 0.43090189 - time (sec): 194.16 - samples/sec: 160.68 - lr: 0.000044
2023-07-26 14:51:14,713 epoch 5 - iter 120/243 - loss 0.42730629 - time (sec): 244.70 - samples/sec: 158.36 - lr: 0.000045
2023-07-26 14:52:05,519 epoch 5 - iter 144/243 - loss 0.42510607 - time (sec): 295.50 - samples/sec: 157.71 - lr: 0.000046
2023-07-26 14:52:56,269 epoch 5 - iter 168/243 - loss 0.42354677 - time (sec): 346.25 - samples/sec: 157.30 - lr: 0.000047
2023-07-26 14:53:45,024 epoch 5 - iter 192/243 - loss 0.42562343 - time (sec): 395.01 - samples/sec: 157.75 - lr: 0.000048
2023-07-26 14:54:29,614 epoch 5 - iter 216/243 - loss 0.42329549 - time (sec): 439.60 - samples/sec: 159.49 - lr: 0.000049
2023-07-26 14:55:14,101 epoch 5 - iter 240/243 - loss 0.42313631 - time (sec): 484.09 - samples/sec: 160.63 - lr: 0.000050
2023-07-26 14:55:19,182 ----------------------------------------------------------------------------------------------------
2023-07-26 14:55:19,183 EPOCH 5 done: loss 0.4224 - lr 0.000050
2023-07-26 14:55:20,964 Evaluating as a multi-label problem: False
2023-07-26 14:55:21,010 DEV : loss 0.15854212641716003 - f1-score (micro avg)  0.9715
2023-07-26 14:55:21,021 saving best model
2023-07-26 14:55:24,373 ----------------------------------------------------------------------------------------------------
2023-07-26 14:56:09,000 epoch 6 - iter 24/243 - loss 0.38322411 - time (sec): 44.63 - samples/sec: 170.24 - lr: 0.000050
2023-07-26 14:56:53,917 epoch 6 - iter 48/243 - loss 0.38879490 - time (sec): 89.54 - samples/sec: 173.84 - lr: 0.000050
2023-07-26 14:57:38,715 epoch 6 - iter 72/243 - loss 0.39501775 - time (sec): 134.34 - samples/sec: 173.59 - lr: 0.000050
2023-07-26 14:58:23,414 epoch 6 - iter 96/243 - loss 0.39125526 - time (sec): 179.04 - samples/sec: 172.72 - lr: 0.000050
2023-07-26 14:59:08,294 epoch 6 - iter 120/243 - loss 0.38810381 - time (sec): 223.92 - samples/sec: 173.39 - lr: 0.000049
2023-07-26 14:59:53,048 epoch 6 - iter 144/243 - loss 0.38859919 - time (sec): 268.67 - samples/sec: 173.20 - lr: 0.000049
2023-07-26 15:00:37,709 epoch 6 - iter 168/243 - loss 0.39183603 - time (sec): 313.34 - samples/sec: 172.54 - lr: 0.000049
2023-07-26 15:01:22,620 epoch 6 - iter 192/243 - loss 0.39172498 - time (sec): 358.25 - samples/sec: 173.10 - lr: 0.000049
2023-07-26 15:02:07,658 epoch 6 - iter 216/243 - loss 0.38755663 - time (sec): 403.28 - samples/sec: 173.50 - lr: 0.000049
2023-07-26 15:02:52,481 epoch 6 - iter 240/243 - loss 0.38859503 - time (sec): 448.11 - samples/sec: 173.42 - lr: 0.000049
2023-07-26 15:02:57,605 ----------------------------------------------------------------------------------------------------
2023-07-26 15:02:57,605 EPOCH 6 done: loss 0.3889 - lr 0.000049
2023-07-26 15:02:59,359 Evaluating as a multi-label problem: False
2023-07-26 15:02:59,401 DEV : loss 0.1478930115699768 - f1-score (micro avg)  0.9729
2023-07-26 15:02:59,411 saving best model
2023-07-26 15:03:02,642 ----------------------------------------------------------------------------------------------------
2023-07-26 15:03:47,204 epoch 7 - iter 24/243 - loss 0.37119833 - time (sec): 44.56 - samples/sec: 170.57 - lr: 0.000049
2023-07-26 15:04:32,257 epoch 7 - iter 48/243 - loss 0.34925497 - time (sec): 89.61 - samples/sec: 170.90 - lr: 0.000049
2023-07-26 15:05:17,152 epoch 7 - iter 72/243 - loss 0.36339135 - time (sec): 134.51 - samples/sec: 170.74 - lr: 0.000049
2023-07-26 15:06:02,168 epoch 7 - iter 96/243 - loss 0.36053250 - time (sec): 179.53 - samples/sec: 172.30 - lr: 0.000048
2023-07-26 15:06:47,283 epoch 7 - iter 120/243 - loss 0.36487615 - time (sec): 224.64 - samples/sec: 173.25 - lr: 0.000048
2023-07-26 15:07:32,276 epoch 7 - iter 144/243 - loss 0.36319947 - time (sec): 269.63 - samples/sec: 173.36 - lr: 0.000048
2023-07-26 15:08:17,184 epoch 7 - iter 168/243 - loss 0.36321272 - time (sec): 314.54 - samples/sec: 173.50 - lr: 0.000048
2023-07-26 15:09:02,085 epoch 7 - iter 192/243 - loss 0.36447693 - time (sec): 359.44 - samples/sec: 173.23 - lr: 0.000048
2023-07-26 15:09:51,228 epoch 7 - iter 216/243 - loss 0.36744951 - time (sec): 408.59 - samples/sec: 171.35 - lr: 0.000048
2023-07-26 15:10:40,287 epoch 7 - iter 240/243 - loss 0.36634157 - time (sec): 457.64 - samples/sec: 169.91 - lr: 0.000048
2023-07-26 15:10:45,862 ----------------------------------------------------------------------------------------------------
2023-07-26 15:10:45,863 EPOCH 7 done: loss 0.3670 - lr 0.000048
2023-07-26 15:10:47,681 Evaluating as a multi-label problem: False
2023-07-26 15:10:47,726 DEV : loss 0.14240729808807373 - f1-score (micro avg)  0.9717
2023-07-26 15:10:47,736 ----------------------------------------------------------------------------------------------------
2023-07-26 15:11:32,421 epoch 8 - iter 24/243 - loss 0.35991738 - time (sec): 44.68 - samples/sec: 171.16 - lr: 0.000048
2023-07-26 15:12:16,856 epoch 8 - iter 48/243 - loss 0.34897131 - time (sec): 89.12 - samples/sec: 171.01 - lr: 0.000048
2023-07-26 15:13:01,243 epoch 8 - iter 72/243 - loss 0.34258107 - time (sec): 133.51 - samples/sec: 171.82 - lr: 0.000047
2023-07-26 15:13:45,557 epoch 8 - iter 96/243 - loss 0.34457191 - time (sec): 177.82 - samples/sec: 171.15 - lr: 0.000047
2023-07-26 15:14:33,081 epoch 8 - iter 120/243 - loss 0.34507195 - time (sec): 225.34 - samples/sec: 168.78 - lr: 0.000047
2023-07-26 15:15:23,807 epoch 8 - iter 144/243 - loss 0.34828898 - time (sec): 276.07 - samples/sec: 167.52 - lr: 0.000047
2023-07-26 15:16:16,673 epoch 8 - iter 168/243 - loss 0.34938445 - time (sec): 328.94 - samples/sec: 163.83 - lr: 0.000047
2023-07-26 15:17:08,647 epoch 8 - iter 192/243 - loss 0.34862273 - time (sec): 380.91 - samples/sec: 162.58 - lr: 0.000047
2023-07-26 15:17:59,292 epoch 8 - iter 216/243 - loss 0.34977990 - time (sec): 431.56 - samples/sec: 161.50 - lr: 0.000047
2023-07-26 15:18:48,823 epoch 8 - iter 240/243 - loss 0.34875804 - time (sec): 481.09 - samples/sec: 161.18 - lr: 0.000047
2023-07-26 15:18:54,694 ----------------------------------------------------------------------------------------------------
2023-07-26 15:18:54,694 EPOCH 8 done: loss 0.3496 - lr 0.000047
2023-07-26 15:18:56,484 Evaluating as a multi-label problem: False
2023-07-26 15:18:56,526 DEV : loss 0.13401205837726593 - f1-score (micro avg)  0.9752
2023-07-26 15:18:56,536 saving best model
2023-07-26 15:18:59,887 ----------------------------------------------------------------------------------------------------
2023-07-26 15:19:45,875 epoch 9 - iter 24/243 - loss 0.33211277 - time (sec): 45.99 - samples/sec: 171.57 - lr: 0.000047
2023-07-26 15:20:33,843 epoch 9 - iter 48/243 - loss 0.33508629 - time (sec): 93.96 - samples/sec: 171.82 - lr: 0.000046
2023-07-26 15:21:26,038 epoch 9 - iter 72/243 - loss 0.32662985 - time (sec): 146.15 - samples/sec: 162.61 - lr: 0.000046
2023-07-26 15:22:17,368 epoch 9 - iter 96/243 - loss 0.32958645 - time (sec): 197.48 - samples/sec: 159.51 - lr: 0.000046
2023-07-26 15:23:08,277 epoch 9 - iter 120/243 - loss 0.32364185 - time (sec): 248.39 - samples/sec: 157.62 - lr: 0.000046
2023-07-26 15:23:59,015 epoch 9 - iter 144/243 - loss 0.32701429 - time (sec): 299.13 - samples/sec: 156.28 - lr: 0.000046
2023-07-26 15:24:49,851 epoch 9 - iter 168/243 - loss 0.33017416 - time (sec): 349.96 - samples/sec: 155.73 - lr: 0.000046
2023-07-26 15:25:40,830 epoch 9 - iter 192/243 - loss 0.33104299 - time (sec): 400.94 - samples/sec: 156.11 - lr: 0.000046
2023-07-26 15:26:30,943 epoch 9 - iter 216/243 - loss 0.33454509 - time (sec): 451.06 - samples/sec: 155.81 - lr: 0.000046
2023-07-26 15:27:20,164 epoch 9 - iter 240/243 - loss 0.33386278 - time (sec): 500.28 - samples/sec: 155.37 - lr: 0.000046
2023-07-26 15:27:25,781 ----------------------------------------------------------------------------------------------------
2023-07-26 15:27:25,782 EPOCH 9 done: loss 0.3329 - lr 0.000046
2023-07-26 15:27:27,595 Evaluating as a multi-label problem: False
2023-07-26 15:27:27,637 DEV : loss 0.14190562069416046 - f1-score (micro avg)  0.9764
2023-07-26 15:27:27,647 saving best model
2023-07-26 15:27:31,002 ----------------------------------------------------------------------------------------------------
2023-07-26 15:28:16,088 epoch 10 - iter 24/243 - loss 0.34002265 - time (sec): 45.09 - samples/sec: 170.28 - lr: 0.000045
2023-07-26 15:29:00,810 epoch 10 - iter 48/243 - loss 0.33540108 - time (sec): 89.81 - samples/sec: 172.64 - lr: 0.000045
2023-07-26 15:29:45,833 epoch 10 - iter 72/243 - loss 0.33399184 - time (sec): 134.83 - samples/sec: 173.50 - lr: 0.000045
2023-07-26 15:30:30,533 epoch 10 - iter 96/243 - loss 0.32469492 - time (sec): 179.53 - samples/sec: 173.83 - lr: 0.000045
2023-07-26 15:31:15,030 epoch 10 - iter 120/243 - loss 0.32910415 - time (sec): 224.03 - samples/sec: 173.44 - lr: 0.000045
2023-07-26 15:31:59,646 epoch 10 - iter 144/243 - loss 0.32899582 - time (sec): 268.64 - samples/sec: 173.64 - lr: 0.000045
2023-07-26 15:32:44,609 epoch 10 - iter 168/243 - loss 0.33093813 - time (sec): 313.61 - samples/sec: 174.48 - lr: 0.000045
2023-07-26 15:33:29,306 epoch 10 - iter 192/243 - loss 0.33208597 - time (sec): 358.30 - samples/sec: 173.78 - lr: 0.000045
2023-07-26 15:34:14,223 epoch 10 - iter 216/243 - loss 0.33175324 - time (sec): 403.22 - samples/sec: 174.07 - lr: 0.000045
2023-07-26 15:34:58,900 epoch 10 - iter 240/243 - loss 0.33262740 - time (sec): 447.90 - samples/sec: 173.56 - lr: 0.000044
2023-07-26 15:35:04,010 ----------------------------------------------------------------------------------------------------
2023-07-26 15:35:04,010 EPOCH 10 done: loss 0.3321 - lr 0.000044
2023-07-26 15:35:06,264 Evaluating as a multi-label problem: False
2023-07-26 15:35:06,306 DEV : loss 0.1481310874223709 - f1-score (micro avg)  0.9734
2023-07-26 15:35:06,316 ----------------------------------------------------------------------------------------------------
2023-07-26 15:35:51,091 epoch 11 - iter 24/243 - loss 0.33230355 - time (sec): 44.77 - samples/sec: 172.33 - lr: 0.000044
2023-07-26 15:36:36,125 epoch 11 - iter 48/243 - loss 0.32441123 - time (sec): 89.81 - samples/sec: 170.71 - lr: 0.000044
2023-07-26 15:37:25,279 epoch 11 - iter 72/243 - loss 0.32514673 - time (sec): 138.96 - samples/sec: 167.78 - lr: 0.000044
2023-07-26 15:38:10,516 epoch 11 - iter 96/243 - loss 0.32235685 - time (sec): 184.20 - samples/sec: 169.57 - lr: 0.000044
2023-07-26 15:38:58,115 epoch 11 - iter 120/243 - loss 0.31705674 - time (sec): 231.80 - samples/sec: 167.98 - lr: 0.000044
2023-07-26 15:39:45,447 epoch 11 - iter 144/243 - loss 0.31351156 - time (sec): 279.13 - samples/sec: 166.74 - lr: 0.000044
2023-07-26 15:40:32,843 epoch 11 - iter 168/243 - loss 0.31453443 - time (sec): 326.53 - samples/sec: 166.47 - lr: 0.000044
2023-07-26 15:41:20,505 epoch 11 - iter 192/243 - loss 0.32048855 - time (sec): 374.19 - samples/sec: 166.74 - lr: 0.000044
2023-07-26 15:42:08,594 epoch 11 - iter 216/243 - loss 0.31914298 - time (sec): 422.28 - samples/sec: 166.07 - lr: 0.000043
2023-07-26 15:42:58,015 epoch 11 - iter 240/243 - loss 0.31938530 - time (sec): 471.70 - samples/sec: 164.83 - lr: 0.000043
2023-07-26 15:43:03,640 ----------------------------------------------------------------------------------------------------
2023-07-26 15:43:03,640 EPOCH 11 done: loss 0.3201 - lr 0.000043
2023-07-26 15:43:05,491 Evaluating as a multi-label problem: False
2023-07-26 15:43:05,538 DEV : loss 0.16022486984729767 - f1-score (micro avg)  0.9744
2023-07-26 15:43:05,549 ----------------------------------------------------------------------------------------------------
2023-07-26 15:43:51,010 epoch 12 - iter 24/243 - loss 0.30634651 - time (sec): 45.46 - samples/sec: 169.22 - lr: 0.000043
2023-07-26 15:44:35,828 epoch 12 - iter 48/243 - loss 0.32055500 - time (sec): 90.28 - samples/sec: 169.40 - lr: 0.000043
2023-07-26 15:45:20,616 epoch 12 - iter 72/243 - loss 0.31591461 - time (sec): 135.07 - samples/sec: 170.20 - lr: 0.000043
2023-07-26 15:46:05,323 epoch 12 - iter 96/243 - loss 0.31720616 - time (sec): 179.77 - samples/sec: 171.25 - lr: 0.000043
2023-07-26 15:46:50,172 epoch 12 - iter 120/243 - loss 0.31877634 - time (sec): 224.62 - samples/sec: 172.25 - lr: 0.000043
2023-07-26 15:47:34,948 epoch 12 - iter 144/243 - loss 0.31817728 - time (sec): 269.40 - samples/sec: 172.60 - lr: 0.000043
2023-07-26 15:48:19,648 epoch 12 - iter 168/243 - loss 0.31409341 - time (sec): 314.10 - samples/sec: 173.20 - lr: 0.000043
2023-07-26 15:49:04,450 epoch 12 - iter 192/243 - loss 0.31475214 - time (sec): 358.90 - samples/sec: 172.72 - lr: 0.000042
2023-07-26 15:49:49,156 epoch 12 - iter 216/243 - loss 0.31439205 - time (sec): 403.61 - samples/sec: 173.13 - lr: 0.000042
2023-07-26 15:50:33,925 epoch 12 - iter 240/243 - loss 0.31462372 - time (sec): 448.38 - samples/sec: 173.38 - lr: 0.000042
2023-07-26 15:50:39,009 ----------------------------------------------------------------------------------------------------
2023-07-26 15:50:39,009 EPOCH 12 done: loss 0.3146 - lr 0.000042
2023-07-26 15:50:40,760 Evaluating as a multi-label problem: False
2023-07-26 15:50:40,803 DEV : loss 0.17038877308368683 - f1-score (micro avg)  0.9764
2023-07-26 15:50:40,813 ----------------------------------------------------------------------------------------------------
2023-07-26 15:51:25,228 epoch 13 - iter 24/243 - loss 0.30871471 - time (sec): 44.42 - samples/sec: 169.20 - lr: 0.000042
2023-07-26 15:52:09,735 epoch 13 - iter 48/243 - loss 0.30951571 - time (sec): 88.92 - samples/sec: 169.92 - lr: 0.000042
2023-07-26 15:52:54,713 epoch 13 - iter 72/243 - loss 0.30146253 - time (sec): 133.90 - samples/sec: 170.69 - lr: 0.000042
2023-07-26 15:53:39,688 epoch 13 - iter 96/243 - loss 0.29818491 - time (sec): 178.88 - samples/sec: 171.59 - lr: 0.000042
2023-07-26 15:54:24,347 epoch 13 - iter 120/243 - loss 0.29829818 - time (sec): 223.53 - samples/sec: 171.45 - lr: 0.000042
2023-07-26 15:55:09,312 epoch 13 - iter 144/243 - loss 0.31111593 - time (sec): 268.50 - samples/sec: 171.76 - lr: 0.000042
2023-07-26 15:55:54,240 epoch 13 - iter 168/243 - loss 0.31147702 - time (sec): 313.43 - samples/sec: 171.94 - lr: 0.000041
2023-07-26 15:56:39,090 epoch 13 - iter 192/243 - loss 0.30976085 - time (sec): 358.28 - samples/sec: 172.90 - lr: 0.000041
2023-07-26 15:57:24,278 epoch 13 - iter 216/243 - loss 0.30904370 - time (sec): 403.46 - samples/sec: 173.00 - lr: 0.000041
2023-07-26 15:58:09,133 epoch 13 - iter 240/243 - loss 0.30572837 - time (sec): 448.32 - samples/sec: 173.40 - lr: 0.000041
2023-07-26 15:58:14,202 ----------------------------------------------------------------------------------------------------
2023-07-26 15:58:14,202 EPOCH 13 done: loss 0.3056 - lr 0.000041
2023-07-26 15:58:15,991 Evaluating as a multi-label problem: False
2023-07-26 15:58:16,034 DEV : loss 0.16180633008480072 - f1-score (micro avg)  0.9766
2023-07-26 15:58:16,044 saving best model
2023-07-26 15:58:19,355 ----------------------------------------------------------------------------------------------------
2023-07-26 15:59:06,668 epoch 14 - iter 24/243 - loss 0.28577045 - time (sec): 47.31 - samples/sec: 164.50 - lr: 0.000041
2023-07-26 15:59:56,998 epoch 14 - iter 48/243 - loss 0.28369661 - time (sec): 97.64 - samples/sec: 158.27 - lr: 0.000041
2023-07-26 16:00:51,211 epoch 14 - iter 72/243 - loss 0.29071442 - time (sec): 151.86 - samples/sec: 153.53 - lr: 0.000041
2023-07-26 16:01:43,557 epoch 14 - iter 96/243 - loss 0.29219267 - time (sec): 204.20 - samples/sec: 154.01 - lr: 0.000041
2023-07-26 16:02:32,810 epoch 14 - iter 120/243 - loss 0.29452027 - time (sec): 253.45 - samples/sec: 154.42 - lr: 0.000041
2023-07-26 16:03:22,073 epoch 14 - iter 144/243 - loss 0.28860385 - time (sec): 302.72 - samples/sec: 154.60 - lr: 0.000040
2023-07-26 16:04:11,432 epoch 14 - iter 168/243 - loss 0.29040567 - time (sec): 352.08 - samples/sec: 155.10 - lr: 0.000040
2023-07-26 16:05:00,439 epoch 14 - iter 192/243 - loss 0.29057669 - time (sec): 401.08 - samples/sec: 155.56 - lr: 0.000040
2023-07-26 16:05:49,734 epoch 14 - iter 216/243 - loss 0.29351512 - time (sec): 450.38 - samples/sec: 155.77 - lr: 0.000040
2023-07-26 16:06:38,920 epoch 14 - iter 240/243 - loss 0.29475470 - time (sec): 499.56 - samples/sec: 155.77 - lr: 0.000040
2023-07-26 16:06:44,452 ----------------------------------------------------------------------------------------------------
2023-07-26 16:06:44,452 EPOCH 14 done: loss 0.2946 - lr 0.000040
2023-07-26 16:06:46,282 Evaluating as a multi-label problem: False
2023-07-26 16:06:46,328 DEV : loss 0.1961415857076645 - f1-score (micro avg)  0.9729
2023-07-26 16:06:46,338 ----------------------------------------------------------------------------------------------------
2023-07-26 16:07:31,298 epoch 15 - iter 24/243 - loss 0.32628632 - time (sec): 44.96 - samples/sec: 171.98 - lr: 0.000040
2023-07-26 16:08:21,094 epoch 15 - iter 48/243 - loss 0.30408958 - time (sec): 94.76 - samples/sec: 164.10 - lr: 0.000040
2023-07-26 16:09:15,364 epoch 15 - iter 72/243 - loss 0.29750206 - time (sec): 149.03 - samples/sec: 157.51 - lr: 0.000040
2023-07-26 16:10:06,024 epoch 15 - iter 96/243 - loss 0.29760832 - time (sec): 199.69 - samples/sec: 155.97 - lr: 0.000040
2023-07-26 16:10:56,205 epoch 15 - iter 120/243 - loss 0.29974418 - time (sec): 249.87 - samples/sec: 155.76 - lr: 0.000039
2023-07-26 16:11:43,301 epoch 15 - iter 144/243 - loss 0.29904887 - time (sec): 296.96 - samples/sec: 157.05 - lr: 0.000039
2023-07-26 16:12:31,170 epoch 15 - iter 168/243 - loss 0.29894209 - time (sec): 344.83 - samples/sec: 157.73 - lr: 0.000039
2023-07-26 16:13:20,187 epoch 15 - iter 192/243 - loss 0.29754010 - time (sec): 393.85 - samples/sec: 157.85 - lr: 0.000039
2023-07-26 16:14:09,012 epoch 15 - iter 216/243 - loss 0.29884402 - time (sec): 442.67 - samples/sec: 157.79 - lr: 0.000039
2023-07-26 16:14:57,878 epoch 15 - iter 240/243 - loss 0.29706337 - time (sec): 491.54 - samples/sec: 158.08 - lr: 0.000039
2023-07-26 16:15:03,351 ----------------------------------------------------------------------------------------------------
2023-07-26 16:15:03,351 EPOCH 15 done: loss 0.2971 - lr 0.000039
2023-07-26 16:15:05,134 Evaluating as a multi-label problem: False
2023-07-26 16:15:05,176 DEV : loss 0.21415923535823822 - f1-score (micro avg)  0.9737
2023-07-26 16:15:05,186 ----------------------------------------------------------------------------------------------------
2023-07-26 16:15:50,049 epoch 16 - iter 24/243 - loss 0.32918671 - time (sec): 44.86 - samples/sec: 172.79 - lr: 0.000039
2023-07-26 16:16:34,768 epoch 16 - iter 48/243 - loss 0.30668793 - time (sec): 89.58 - samples/sec: 172.52 - lr: 0.000039
2023-07-26 16:17:19,891 epoch 16 - iter 72/243 - loss 0.30165600 - time (sec): 134.70 - samples/sec: 171.72 - lr: 0.000039
2023-07-26 16:18:09,624 epoch 16 - iter 96/243 - loss 0.29977956 - time (sec): 184.44 - samples/sec: 168.02 - lr: 0.000038
2023-07-26 16:18:58,935 epoch 16 - iter 120/243 - loss 0.29035278 - time (sec): 233.75 - samples/sec: 165.52 - lr: 0.000038
2023-07-26 16:19:48,358 epoch 16 - iter 144/243 - loss 0.28688344 - time (sec): 283.17 - samples/sec: 164.52 - lr: 0.000038
2023-07-26 16:20:37,728 epoch 16 - iter 168/243 - loss 0.28573744 - time (sec): 332.54 - samples/sec: 163.65 - lr: 0.000038
2023-07-26 16:21:26,994 epoch 16 - iter 192/243 - loss 0.28483557 - time (sec): 381.81 - samples/sec: 162.65 - lr: 0.000038
2023-07-26 16:22:16,480 epoch 16 - iter 216/243 - loss 0.28487700 - time (sec): 431.29 - samples/sec: 162.23 - lr: 0.000038
2023-07-26 16:23:05,837 epoch 16 - iter 240/243 - loss 0.28570848 - time (sec): 480.65 - samples/sec: 161.78 - lr: 0.000038
2023-07-26 16:23:11,437 ----------------------------------------------------------------------------------------------------
2023-07-26 16:23:11,437 EPOCH 16 done: loss 0.2858 - lr 0.000038
2023-07-26 16:23:13,234 Evaluating as a multi-label problem: False
2023-07-26 16:23:13,276 DEV : loss 0.17488490045070648 - f1-score (micro avg)  0.9764
2023-07-26 16:23:13,286 ----------------------------------------------------------------------------------------------------
2023-07-26 16:23:58,069 epoch 17 - iter 24/243 - loss 0.28223418 - time (sec): 44.78 - samples/sec: 169.35 - lr: 0.000038
2023-07-26 16:24:42,914 epoch 17 - iter 48/243 - loss 0.28773045 - time (sec): 89.63 - samples/sec: 170.29 - lr: 0.000038
2023-07-26 16:25:28,001 epoch 17 - iter 72/243 - loss 0.28949629 - time (sec): 134.72 - samples/sec: 171.86 - lr: 0.000037
2023-07-26 16:26:12,604 epoch 17 - iter 96/243 - loss 0.29081122 - time (sec): 179.32 - samples/sec: 172.97 - lr: 0.000037
2023-07-26 16:26:57,287 epoch 17 - iter 120/243 - loss 0.28910214 - time (sec): 224.00 - samples/sec: 173.28 - lr: 0.000037
2023-07-26 16:27:41,994 epoch 17 - iter 144/243 - loss 0.28813940 - time (sec): 268.71 - samples/sec: 173.98 - lr: 0.000037
2023-07-26 16:28:26,701 epoch 17 - iter 168/243 - loss 0.28649377 - time (sec): 313.42 - samples/sec: 174.08 - lr: 0.000037
2023-07-26 16:29:11,540 epoch 17 - iter 192/243 - loss 0.28690817 - time (sec): 358.25 - samples/sec: 174.44 - lr: 0.000037
2023-07-26 16:29:56,114 epoch 17 - iter 216/243 - loss 0.28529445 - time (sec): 402.83 - samples/sec: 173.78 - lr: 0.000037
2023-07-26 16:30:40,993 epoch 17 - iter 240/243 - loss 0.28495055 - time (sec): 447.71 - samples/sec: 173.50 - lr: 0.000037
2023-07-26 16:30:46,121 ----------------------------------------------------------------------------------------------------
2023-07-26 16:30:46,122 EPOCH 17 done: loss 0.2845 - lr 0.000037
2023-07-26 16:30:47,874 Evaluating as a multi-label problem: False
2023-07-26 16:30:47,918 DEV : loss 0.1961992233991623 - f1-score (micro avg)  0.9764
2023-07-26 16:30:47,928 ----------------------------------------------------------------------------------------------------
2023-07-26 16:31:33,170 epoch 18 - iter 24/243 - loss 0.28778804 - time (sec): 45.24 - samples/sec: 183.77 - lr: 0.000037
2023-07-26 16:32:17,561 epoch 18 - iter 48/243 - loss 0.28633144 - time (sec): 89.63 - samples/sec: 178.16 - lr: 0.000036
2023-07-26 16:33:02,262 epoch 18 - iter 72/243 - loss 0.28829018 - time (sec): 134.33 - samples/sec: 176.29 - lr: 0.000036
2023-07-26 16:33:47,023 epoch 18 - iter 96/243 - loss 0.28737825 - time (sec): 179.10 - samples/sec: 176.55 - lr: 0.000036
2023-07-26 16:34:31,632 epoch 18 - iter 120/243 - loss 0.28870528 - time (sec): 223.70 - samples/sec: 176.96 - lr: 0.000036
2023-07-26 16:35:16,249 epoch 18 - iter 144/243 - loss 0.28536506 - time (sec): 268.32 - samples/sec: 176.48 - lr: 0.000036
2023-07-26 16:36:01,090 epoch 18 - iter 168/243 - loss 0.28612314 - time (sec): 313.16 - samples/sec: 175.92 - lr: 0.000036
2023-07-26 16:36:46,062 epoch 18 - iter 192/243 - loss 0.28681958 - time (sec): 358.13 - samples/sec: 174.98 - lr: 0.000036
2023-07-26 16:37:31,063 epoch 18 - iter 216/243 - loss 0.28815101 - time (sec): 403.14 - samples/sec: 174.53 - lr: 0.000036
2023-07-26 16:38:19,082 epoch 18 - iter 240/243 - loss 0.28697818 - time (sec): 451.15 - samples/sec: 172.46 - lr: 0.000036
2023-07-26 16:38:24,758 ----------------------------------------------------------------------------------------------------
2023-07-26 16:38:24,759 EPOCH 18 done: loss 0.2865 - lr 0.000036
2023-07-26 16:38:27,073 Evaluating as a multi-label problem: False
2023-07-26 16:38:27,115 DEV : loss 0.18113288283348083 - f1-score (micro avg)  0.9781
2023-07-26 16:38:27,126 saving best model
2023-07-26 16:38:30,288 ----------------------------------------------------------------------------------------------------
2023-07-26 16:39:21,782 epoch 19 - iter 24/243 - loss 0.28138164 - time (sec): 51.49 - samples/sec: 154.23 - lr: 0.000036
2023-07-26 16:40:12,650 epoch 19 - iter 48/243 - loss 0.28992986 - time (sec): 102.36 - samples/sec: 150.35 - lr: 0.000035
2023-07-26 16:41:02,164 epoch 19 - iter 72/243 - loss 0.28244605 - time (sec): 151.88 - samples/sec: 152.82 - lr: 0.000035
2023-07-26 16:41:52,390 epoch 19 - iter 96/243 - loss 0.28642854 - time (sec): 202.10 - samples/sec: 152.66 - lr: 0.000035
2023-07-26 16:42:44,635 epoch 19 - iter 120/243 - loss 0.28768114 - time (sec): 254.35 - samples/sec: 151.96 - lr: 0.000035
2023-07-26 16:43:33,907 epoch 19 - iter 144/243 - loss 0.28722806 - time (sec): 303.62 - samples/sec: 153.22 - lr: 0.000035
2023-07-26 16:44:23,000 epoch 19 - iter 168/243 - loss 0.28477685 - time (sec): 352.71 - samples/sec: 154.35 - lr: 0.000035
2023-07-26 16:45:11,847 epoch 19 - iter 192/243 - loss 0.28564618 - time (sec): 401.56 - samples/sec: 155.01 - lr: 0.000035
2023-07-26 16:46:00,662 epoch 19 - iter 216/243 - loss 0.28166734 - time (sec): 450.37 - samples/sec: 155.14 - lr: 0.000035
2023-07-26 16:46:49,519 epoch 19 - iter 240/243 - loss 0.28044622 - time (sec): 499.23 - samples/sec: 155.64 - lr: 0.000035
2023-07-26 16:46:55,052 ----------------------------------------------------------------------------------------------------
2023-07-26 16:46:55,052 EPOCH 19 done: loss 0.2808 - lr 0.000035
2023-07-26 16:46:56,840 Evaluating as a multi-label problem: False
2023-07-26 16:46:56,881 DEV : loss 0.2043328434228897 - f1-score (micro avg)  0.9793
2023-07-26 16:46:56,891 saving best model
2023-07-26 16:47:00,311 ----------------------------------------------------------------------------------------------------
2023-07-26 16:47:53,948 epoch 20 - iter 24/243 - loss 0.28666954 - time (sec): 53.64 - samples/sec: 145.20 - lr: 0.000034
2023-07-26 16:48:47,747 epoch 20 - iter 48/243 - loss 0.29481761 - time (sec): 107.44 - samples/sec: 143.54 - lr: 0.000034
2023-07-26 16:49:41,712 epoch 20 - iter 72/243 - loss 0.29914317 - time (sec): 161.40 - samples/sec: 143.67 - lr: 0.000034
2023-07-26 16:50:34,164 epoch 20 - iter 96/243 - loss 0.29393948 - time (sec): 213.85 - samples/sec: 144.15 - lr: 0.000034
2023-07-26 16:51:26,758 epoch 20 - iter 120/243 - loss 0.29259273 - time (sec): 266.45 - samples/sec: 144.69 - lr: 0.000034
2023-07-26 16:52:19,496 epoch 20 - iter 144/243 - loss 0.29189521 - time (sec): 319.18 - samples/sec: 145.56 - lr: 0.000034
2023-07-26 16:53:12,248 epoch 20 - iter 168/243 - loss 0.29174956 - time (sec): 371.94 - samples/sec: 146.27 - lr: 0.000034
2023-07-26 16:54:04,770 epoch 20 - iter 192/243 - loss 0.28991116 - time (sec): 424.46 - samples/sec: 146.24 - lr: 0.000034
2023-07-26 16:54:57,220 epoch 20 - iter 216/243 - loss 0.28908421 - time (sec): 476.91 - samples/sec: 146.03 - lr: 0.000034
2023-07-26 16:55:50,110 epoch 20 - iter 240/243 - loss 0.28802142 - time (sec): 529.80 - samples/sec: 146.82 - lr: 0.000033
2023-07-26 16:55:56,063 ----------------------------------------------------------------------------------------------------
2023-07-26 16:55:56,064 EPOCH 20 done: loss 0.2884 - lr 0.000033
2023-07-26 16:55:58,153 Evaluating as a multi-label problem: False
2023-07-26 16:55:58,197 DEV : loss 0.17976026237010956 - f1-score (micro avg)  0.9798
2023-07-26 16:55:58,210 saving best model
2023-07-26 16:56:01,163 ----------------------------------------------------------------------------------------------------
2023-07-26 16:56:45,917 epoch 21 - iter 24/243 - loss 0.27074814 - time (sec): 44.75 - samples/sec: 174.64 - lr: 0.000033
2023-07-26 16:57:30,503 epoch 21 - iter 48/243 - loss 0.27757152 - time (sec): 89.34 - samples/sec: 172.96 - lr: 0.000033
2023-07-26 16:58:15,097 epoch 21 - iter 72/243 - loss 0.27454337 - time (sec): 133.93 - samples/sec: 173.08 - lr: 0.000033
2023-07-26 16:58:59,717 epoch 21 - iter 96/243 - loss 0.27609707 - time (sec): 178.55 - samples/sec: 172.80 - lr: 0.000033
2023-07-26 16:59:44,372 epoch 21 - iter 120/243 - loss 0.27224083 - time (sec): 223.21 - samples/sec: 172.96 - lr: 0.000033
2023-07-26 17:00:29,083 epoch 21 - iter 144/243 - loss 0.27850149 - time (sec): 267.92 - samples/sec: 172.72 - lr: 0.000033
2023-07-26 17:01:13,636 epoch 21 - iter 168/243 - loss 0.27696398 - time (sec): 312.47 - samples/sec: 172.79 - lr: 0.000033
2023-07-26 17:01:58,291 epoch 21 - iter 192/243 - loss 0.27664755 - time (sec): 357.13 - samples/sec: 172.80 - lr: 0.000033
2023-07-26 17:02:43,178 epoch 21 - iter 216/243 - loss 0.27558848 - time (sec): 402.01 - samples/sec: 173.76 - lr: 0.000032
2023-07-26 17:03:27,865 epoch 21 - iter 240/243 - loss 0.27583214 - time (sec): 446.70 - samples/sec: 173.99 - lr: 0.000032
2023-07-26 17:03:32,964 ----------------------------------------------------------------------------------------------------
2023-07-26 17:03:32,964 EPOCH 21 done: loss 0.2761 - lr 0.000032
2023-07-26 17:03:34,719 Evaluating as a multi-label problem: False
2023-07-26 17:03:34,761 DEV : loss 0.20532046258449554 - f1-score (micro avg)  0.9808
2023-07-26 17:03:34,770 saving best model
2023-07-26 17:03:38,172 ----------------------------------------------------------------------------------------------------
2023-07-26 17:04:22,817 epoch 22 - iter 24/243 - loss 0.27909847 - time (sec): 44.64 - samples/sec: 173.08 - lr: 0.000032
2023-07-26 17:05:07,696 epoch 22 - iter 48/243 - loss 0.27692541 - time (sec): 89.52 - samples/sec: 175.94 - lr: 0.000032
2023-07-26 17:05:52,516 epoch 22 - iter 72/243 - loss 0.27632545 - time (sec): 134.34 - samples/sec: 175.36 - lr: 0.000032
2023-07-26 17:06:37,349 epoch 22 - iter 96/243 - loss 0.27607549 - time (sec): 179.18 - samples/sec: 175.31 - lr: 0.000032
2023-07-26 17:07:22,028 epoch 22 - iter 120/243 - loss 0.27687957 - time (sec): 223.85 - samples/sec: 175.34 - lr: 0.000032
2023-07-26 17:08:06,628 epoch 22 - iter 144/243 - loss 0.27294774 - time (sec): 268.46 - samples/sec: 174.93 - lr: 0.000032
2023-07-26 17:08:51,184 epoch 22 - iter 168/243 - loss 0.27391471 - time (sec): 313.01 - samples/sec: 174.15 - lr: 0.000032
2023-07-26 17:09:35,805 epoch 22 - iter 192/243 - loss 0.27352263 - time (sec): 357.63 - samples/sec: 174.01 - lr: 0.000031
2023-07-26 17:10:20,566 epoch 22 - iter 216/243 - loss 0.27144978 - time (sec): 402.39 - samples/sec: 174.04 - lr: 0.000031
2023-07-26 17:11:05,178 epoch 22 - iter 240/243 - loss 0.27338785 - time (sec): 447.01 - samples/sec: 173.85 - lr: 0.000031
2023-07-26 17:11:10,275 ----------------------------------------------------------------------------------------------------
2023-07-26 17:11:10,275 EPOCH 22 done: loss 0.2738 - lr 0.000031
2023-07-26 17:11:12,042 Evaluating as a multi-label problem: False
2023-07-26 17:11:12,084 DEV : loss 0.20975473523139954 - f1-score (micro avg)  0.9771
2023-07-26 17:11:12,094 ----------------------------------------------------------------------------------------------------
2023-07-26 17:11:57,033 epoch 23 - iter 24/243 - loss 0.28534317 - time (sec): 44.94 - samples/sec: 175.57 - lr: 0.000031
2023-07-26 17:12:41,709 epoch 23 - iter 48/243 - loss 0.28084455 - time (sec): 89.61 - samples/sec: 173.42 - lr: 0.000031
2023-07-26 17:13:26,426 epoch 23 - iter 72/243 - loss 0.28011749 - time (sec): 134.33 - samples/sec: 173.68 - lr: 0.000031
2023-07-26 17:14:10,996 epoch 23 - iter 96/243 - loss 0.28443955 - time (sec): 178.90 - samples/sec: 173.25 - lr: 0.000031
2023-07-26 17:14:55,898 epoch 23 - iter 120/243 - loss 0.28290269 - time (sec): 223.80 - samples/sec: 173.90 - lr: 0.000031
2023-07-26 17:15:40,508 epoch 23 - iter 144/243 - loss 0.28079246 - time (sec): 268.41 - samples/sec: 173.44 - lr: 0.000031
2023-07-26 17:16:25,384 epoch 23 - iter 168/243 - loss 0.27982769 - time (sec): 313.29 - samples/sec: 173.93 - lr: 0.000030
2023-07-26 17:17:10,020 epoch 23 - iter 192/243 - loss 0.27685678 - time (sec): 357.93 - samples/sec: 173.50 - lr: 0.000030
2023-07-26 17:17:54,847 epoch 23 - iter 216/243 - loss 0.27359946 - time (sec): 402.75 - samples/sec: 173.94 - lr: 0.000030
2023-07-26 17:18:39,474 epoch 23 - iter 240/243 - loss 0.27378796 - time (sec): 447.38 - samples/sec: 173.62 - lr: 0.000030
2023-07-26 17:18:44,594 ----------------------------------------------------------------------------------------------------
2023-07-26 17:18:44,594 EPOCH 23 done: loss 0.2739 - lr 0.000030
2023-07-26 17:18:46,344 Evaluating as a multi-label problem: False
2023-07-26 17:18:46,386 DEV : loss 0.21456189453601837 - f1-score (micro avg)  0.9796
2023-07-26 17:18:46,395 ----------------------------------------------------------------------------------------------------
2023-07-26 17:19:31,051 epoch 24 - iter 24/243 - loss 0.28123621 - time (sec): 44.66 - samples/sec: 168.56 - lr: 0.000030
2023-07-26 17:20:15,553 epoch 24 - iter 48/243 - loss 0.27128197 - time (sec): 89.16 - samples/sec: 168.93 - lr: 0.000030
2023-07-26 17:21:00,218 epoch 24 - iter 72/243 - loss 0.26742573 - time (sec): 133.82 - samples/sec: 169.68 - lr: 0.000030
2023-07-26 17:21:44,804 epoch 24 - iter 96/243 - loss 0.27426501 - time (sec): 178.41 - samples/sec: 170.21 - lr: 0.000030
2023-07-26 17:22:29,693 epoch 24 - iter 120/243 - loss 0.26958800 - time (sec): 223.30 - samples/sec: 171.86 - lr: 0.000030
2023-07-26 17:23:14,736 epoch 24 - iter 144/243 - loss 0.27011544 - time (sec): 268.34 - samples/sec: 174.09 - lr: 0.000029
2023-07-26 17:23:59,891 epoch 24 - iter 168/243 - loss 0.26573691 - time (sec): 313.50 - samples/sec: 173.54 - lr: 0.000029
2023-07-26 17:24:44,440 epoch 24 - iter 192/243 - loss 0.26424698 - time (sec): 358.04 - samples/sec: 173.71 - lr: 0.000029
2023-07-26 17:25:28,792 epoch 24 - iter 216/243 - loss 0.26555746 - time (sec): 402.40 - samples/sec: 173.43 - lr: 0.000029
2023-07-26 17:26:13,338 epoch 24 - iter 240/243 - loss 0.26918457 - time (sec): 446.94 - samples/sec: 173.77 - lr: 0.000029
2023-07-26 17:26:18,446 ----------------------------------------------------------------------------------------------------
2023-07-26 17:26:18,447 EPOCH 24 done: loss 0.2696 - lr 0.000029
2023-07-26 17:26:20,206 Evaluating as a multi-label problem: False
2023-07-26 17:26:20,252 DEV : loss 0.21408958733081818 - f1-score (micro avg)  0.9788
2023-07-26 17:26:20,263 ----------------------------------------------------------------------------------------------------
2023-07-26 17:27:04,792 epoch 25 - iter 24/243 - loss 0.26057600 - time (sec): 44.53 - samples/sec: 175.66 - lr: 0.000029
2023-07-26 17:27:49,230 epoch 25 - iter 48/243 - loss 0.25988897 - time (sec): 88.97 - samples/sec: 175.54 - lr: 0.000029
2023-07-26 17:28:34,576 epoch 25 - iter 72/243 - loss 0.26336622 - time (sec): 134.31 - samples/sec: 174.81 - lr: 0.000029
2023-07-26 17:29:19,911 epoch 25 - iter 96/243 - loss 0.26126366 - time (sec): 179.65 - samples/sec: 174.70 - lr: 0.000029
2023-07-26 17:30:05,863 epoch 25 - iter 120/243 - loss 0.26114761 - time (sec): 225.60 - samples/sec: 173.32 - lr: 0.000028
2023-07-26 17:30:54,836 epoch 25 - iter 144/243 - loss 0.26019042 - time (sec): 274.57 - samples/sec: 170.53 - lr: 0.000028
2023-07-26 17:31:44,973 epoch 25 - iter 168/243 - loss 0.26060643 - time (sec): 324.71 - samples/sec: 168.00 - lr: 0.000028
2023-07-26 17:32:34,267 epoch 25 - iter 192/243 - loss 0.26158525 - time (sec): 374.00 - samples/sec: 167.12 - lr: 0.000028
2023-07-26 17:33:23,148 epoch 25 - iter 216/243 - loss 0.25965178 - time (sec): 422.89 - samples/sec: 165.83 - lr: 0.000028
2023-07-26 17:34:11,558 epoch 25 - iter 240/243 - loss 0.25991617 - time (sec): 471.29 - samples/sec: 165.08 - lr: 0.000028
2023-07-26 17:34:17,049 ----------------------------------------------------------------------------------------------------
2023-07-26 17:34:17,049 EPOCH 25 done: loss 0.2605 - lr 0.000028
2023-07-26 17:34:18,858 Evaluating as a multi-label problem: False
2023-07-26 17:34:18,901 DEV : loss 0.20778048038482666 - f1-score (micro avg)  0.9801
2023-07-26 17:34:18,911 ----------------------------------------------------------------------------------------------------
2023-07-26 17:35:06,124 epoch 26 - iter 24/243 - loss 0.25028245 - time (sec): 47.21 - samples/sec: 162.56 - lr: 0.000028
2023-07-26 17:35:56,450 epoch 26 - iter 48/243 - loss 0.26759368 - time (sec): 97.54 - samples/sec: 159.39 - lr: 0.000028
2023-07-26 17:36:48,254 epoch 26 - iter 72/243 - loss 0.26240750 - time (sec): 149.34 - samples/sec: 155.33 - lr: 0.000028
2023-07-26 17:37:37,860 epoch 26 - iter 96/243 - loss 0.26499737 - time (sec): 198.95 - samples/sec: 155.95 - lr: 0.000027
2023-07-26 17:38:26,594 epoch 26 - iter 120/243 - loss 0.26765442 - time (sec): 247.68 - samples/sec: 155.61 - lr: 0.000027
2023-07-26 17:39:15,951 epoch 26 - iter 144/243 - loss 0.26496660 - time (sec): 297.04 - samples/sec: 155.98 - lr: 0.000027
2023-07-26 17:40:04,512 epoch 26 - iter 168/243 - loss 0.26407033 - time (sec): 345.60 - samples/sec: 157.09 - lr: 0.000027
2023-07-26 17:40:52,402 epoch 26 - iter 192/243 - loss 0.26463487 - time (sec): 393.49 - samples/sec: 157.76 - lr: 0.000027
2023-07-26 17:41:40,356 epoch 26 - iter 216/243 - loss 0.26192074 - time (sec): 441.45 - samples/sec: 158.66 - lr: 0.000027
2023-07-26 17:42:28,247 epoch 26 - iter 240/243 - loss 0.26299030 - time (sec): 489.34 - samples/sec: 158.86 - lr: 0.000027
2023-07-26 17:42:33,832 ----------------------------------------------------------------------------------------------------
2023-07-26 17:42:33,833 EPOCH 26 done: loss 0.2631 - lr 0.000027
2023-07-26 17:42:35,630 Evaluating as a multi-label problem: False
2023-07-26 17:42:35,672 DEV : loss 0.22401468455791473 - f1-score (micro avg)  0.9786
2023-07-26 17:42:35,682 ----------------------------------------------------------------------------------------------------
2023-07-26 17:43:20,454 epoch 27 - iter 24/243 - loss 0.26639657 - time (sec): 44.77 - samples/sec: 182.81 - lr: 0.000027
2023-07-26 17:44:04,934 epoch 27 - iter 48/243 - loss 0.27451501 - time (sec): 89.25 - samples/sec: 178.70 - lr: 0.000027
2023-07-26 17:44:49,425 epoch 27 - iter 72/243 - loss 0.27289399 - time (sec): 133.74 - samples/sec: 176.62 - lr: 0.000026
2023-07-26 17:45:33,681 epoch 27 - iter 96/243 - loss 0.27091536 - time (sec): 178.00 - samples/sec: 175.50 - lr: 0.000026
2023-07-26 17:46:18,171 epoch 27 - iter 120/243 - loss 0.27191898 - time (sec): 222.49 - samples/sec: 173.82 - lr: 0.000026
2023-07-26 17:47:02,640 epoch 27 - iter 144/243 - loss 0.27013358 - time (sec): 266.96 - samples/sec: 173.92 - lr: 0.000026
2023-07-26 17:47:47,032 epoch 27 - iter 168/243 - loss 0.26766038 - time (sec): 311.35 - samples/sec: 173.58 - lr: 0.000026
2023-07-26 17:48:33,707 epoch 27 - iter 192/243 - loss 0.26602770 - time (sec): 358.02 - samples/sec: 173.06 - lr: 0.000026
2023-07-26 17:49:21,690 epoch 27 - iter 216/243 - loss 0.26757355 - time (sec): 406.01 - samples/sec: 171.85 - lr: 0.000026
2023-07-26 17:50:09,653 epoch 27 - iter 240/243 - loss 0.26544815 - time (sec): 453.97 - samples/sec: 171.19 - lr: 0.000026
2023-07-26 17:50:15,122 ----------------------------------------------------------------------------------------------------
2023-07-26 17:50:15,123 EPOCH 27 done: loss 0.2656 - lr 0.000026
2023-07-26 17:50:17,372 Evaluating as a multi-label problem: False
2023-07-26 17:50:17,414 DEV : loss 0.2324327975511551 - f1-score (micro avg)  0.9771
2023-07-26 17:50:17,424 ----------------------------------------------------------------------------------------------------
2023-07-26 17:51:02,154 epoch 28 - iter 24/243 - loss 0.26044359 - time (sec): 44.73 - samples/sec: 177.24 - lr: 0.000026
2023-07-26 17:51:46,725 epoch 28 - iter 48/243 - loss 0.25192260 - time (sec): 89.30 - samples/sec: 175.55 - lr: 0.000025
2023-07-26 17:52:31,357 epoch 28 - iter 72/243 - loss 0.24867911 - time (sec): 133.93 - samples/sec: 175.88 - lr: 0.000025
2023-07-26 17:53:15,933 epoch 28 - iter 96/243 - loss 0.25204485 - time (sec): 178.51 - samples/sec: 175.73 - lr: 0.000025
2023-07-26 17:54:00,443 epoch 28 - iter 120/243 - loss 0.24981817 - time (sec): 223.02 - samples/sec: 174.90 - lr: 0.000025
2023-07-26 17:54:44,958 epoch 28 - iter 144/243 - loss 0.25157168 - time (sec): 267.53 - samples/sec: 174.46 - lr: 0.000025
2023-07-26 17:55:29,493 epoch 28 - iter 168/243 - loss 0.25440998 - time (sec): 312.07 - samples/sec: 174.04 - lr: 0.000025
2023-07-26 17:56:13,998 epoch 28 - iter 192/243 - loss 0.25791455 - time (sec): 356.57 - samples/sec: 174.06 - lr: 0.000025
2023-07-26 17:56:58,663 epoch 28 - iter 216/243 - loss 0.26113615 - time (sec): 401.24 - samples/sec: 173.82 - lr: 0.000025
2023-07-26 17:57:43,598 epoch 28 - iter 240/243 - loss 0.26254906 - time (sec): 446.17 - samples/sec: 174.40 - lr: 0.000025
2023-07-26 17:57:48,629 ----------------------------------------------------------------------------------------------------
2023-07-26 17:57:48,629 EPOCH 28 done: loss 0.2628 - lr 0.000025
2023-07-26 17:57:50,384 Evaluating as a multi-label problem: False
2023-07-26 17:57:50,427 DEV : loss 0.21640333533287048 - f1-score (micro avg)  0.9803
2023-07-26 17:57:50,437 ----------------------------------------------------------------------------------------------------
2023-07-26 17:58:34,969 epoch 29 - iter 24/243 - loss 0.24833162 - time (sec): 44.53 - samples/sec: 173.47 - lr: 0.000024
2023-07-26 17:59:19,469 epoch 29 - iter 48/243 - loss 0.25554505 - time (sec): 89.03 - samples/sec: 173.26 - lr: 0.000024
2023-07-26 18:00:04,033 epoch 29 - iter 72/243 - loss 0.26313723 - time (sec): 133.60 - samples/sec: 173.10 - lr: 0.000024
2023-07-26 18:00:48,651 epoch 29 - iter 96/243 - loss 0.26456129 - time (sec): 178.21 - samples/sec: 173.90 - lr: 0.000024
2023-07-26 18:01:33,121 epoch 29 - iter 120/243 - loss 0.26539430 - time (sec): 222.68 - samples/sec: 173.48 - lr: 0.000024
2023-07-26 18:02:17,661 epoch 29 - iter 144/243 - loss 0.26756174 - time (sec): 267.22 - samples/sec: 173.79 - lr: 0.000024
2023-07-26 18:03:02,505 epoch 29 - iter 168/243 - loss 0.26309703 - time (sec): 312.07 - samples/sec: 174.46 - lr: 0.000024
2023-07-26 18:03:46,972 epoch 29 - iter 192/243 - loss 0.26532971 - time (sec): 356.53 - samples/sec: 173.68 - lr: 0.000024
2023-07-26 18:04:31,621 epoch 29 - iter 216/243 - loss 0.26648227 - time (sec): 401.18 - samples/sec: 173.71 - lr: 0.000024
2023-07-26 18:05:16,534 epoch 29 - iter 240/243 - loss 0.26528743 - time (sec): 446.10 - samples/sec: 174.44 - lr: 0.000023
2023-07-26 18:05:21,587 ----------------------------------------------------------------------------------------------------
2023-07-26 18:05:21,587 EPOCH 29 done: loss 0.2655 - lr 0.000023
2023-07-26 18:05:23,600 Evaluating as a multi-label problem: False
2023-07-26 18:05:23,646 DEV : loss 0.24248327314853668 - f1-score (micro avg)  0.9796
2023-07-26 18:05:23,660 ----------------------------------------------------------------------------------------------------
2023-07-26 18:06:12,165 epoch 30 - iter 24/243 - loss 0.26154968 - time (sec): 48.51 - samples/sec: 161.26 - lr: 0.000023
2023-07-26 18:07:02,942 epoch 30 - iter 48/243 - loss 0.27126768 - time (sec): 99.28 - samples/sec: 157.70 - lr: 0.000023
2023-07-26 18:07:57,979 epoch 30 - iter 72/243 - loss 0.27468039 - time (sec): 154.32 - samples/sec: 150.27 - lr: 0.000023
2023-07-26 18:08:53,322 epoch 30 - iter 96/243 - loss 0.27662270 - time (sec): 209.66 - samples/sec: 147.69 - lr: 0.000023
2023-07-26 18:09:48,639 epoch 30 - iter 120/243 - loss 0.27403633 - time (sec): 264.98 - samples/sec: 145.88 - lr: 0.000023
2023-07-26 18:10:40,050 epoch 30 - iter 144/243 - loss 0.27461637 - time (sec): 316.39 - samples/sec: 146.57 - lr: 0.000023
2023-07-26 18:11:29,552 epoch 30 - iter 168/243 - loss 0.26994770 - time (sec): 365.89 - samples/sec: 148.67 - lr: 0.000023
2023-07-26 18:12:18,746 epoch 30 - iter 192/243 - loss 0.26952319 - time (sec): 415.09 - samples/sec: 150.29 - lr: 0.000023
2023-07-26 18:13:07,757 epoch 30 - iter 216/243 - loss 0.26556592 - time (sec): 464.10 - samples/sec: 151.23 - lr: 0.000022
2023-07-26 18:13:56,449 epoch 30 - iter 240/243 - loss 0.26521277 - time (sec): 512.79 - samples/sec: 151.74 - lr: 0.000022
2023-07-26 18:14:01,871 ----------------------------------------------------------------------------------------------------
2023-07-26 18:14:01,871 EPOCH 30 done: loss 0.2653 - lr 0.000022
2023-07-26 18:14:03,693 Evaluating as a multi-label problem: False
2023-07-26 18:14:03,735 DEV : loss 0.23393450677394867 - f1-score (micro avg)  0.9776
2023-07-26 18:14:03,746 ----------------------------------------------------------------------------------------------------
2023-07-26 18:14:48,764 epoch 31 - iter 24/243 - loss 0.24073944 - time (sec): 45.02 - samples/sec: 179.77 - lr: 0.000022
2023-07-26 18:15:33,209 epoch 31 - iter 48/243 - loss 0.24507990 - time (sec): 89.46 - samples/sec: 173.00 - lr: 0.000022
2023-07-26 18:16:17,809 epoch 31 - iter 72/243 - loss 0.25127541 - time (sec): 134.06 - samples/sec: 173.96 - lr: 0.000022
2023-07-26 18:17:02,650 epoch 31 - iter 96/243 - loss 0.25526836 - time (sec): 178.90 - samples/sec: 175.19 - lr: 0.000022
2023-07-26 18:17:47,365 epoch 31 - iter 120/243 - loss 0.25884615 - time (sec): 223.62 - samples/sec: 174.90 - lr: 0.000022
2023-07-26 18:18:32,093 epoch 31 - iter 144/243 - loss 0.26107421 - time (sec): 268.35 - samples/sec: 174.71 - lr: 0.000022
2023-07-26 18:19:16,568 epoch 31 - iter 168/243 - loss 0.25772191 - time (sec): 312.82 - samples/sec: 174.07 - lr: 0.000022
2023-07-26 18:20:01,232 epoch 31 - iter 192/243 - loss 0.25843953 - time (sec): 357.49 - samples/sec: 174.12 - lr: 0.000021
2023-07-26 18:20:46,098 epoch 31 - iter 216/243 - loss 0.25940033 - time (sec): 402.35 - samples/sec: 174.28 - lr: 0.000021
2023-07-26 18:21:30,680 epoch 31 - iter 240/243 - loss 0.25924131 - time (sec): 446.93 - samples/sec: 173.95 - lr: 0.000021
2023-07-26 18:21:35,753 ----------------------------------------------------------------------------------------------------
2023-07-26 18:21:35,753 EPOCH 31 done: loss 0.2594 - lr 0.000021
2023-07-26 18:21:37,502 Evaluating as a multi-label problem: False
2023-07-26 18:21:37,544 DEV : loss 0.22774212062358856 - f1-score (micro avg)  0.9788
2023-07-26 18:21:37,554 ----------------------------------------------------------------------------------------------------
2023-07-26 18:22:22,282 epoch 32 - iter 24/243 - loss 0.25476998 - time (sec): 44.73 - samples/sec: 179.17 - lr: 0.000021
2023-07-26 18:23:07,025 epoch 32 - iter 48/243 - loss 0.25629909 - time (sec): 89.47 - samples/sec: 178.31 - lr: 0.000021
2023-07-26 18:23:51,761 epoch 32 - iter 72/243 - loss 0.25739595 - time (sec): 134.21 - samples/sec: 177.13 - lr: 0.000021
2023-07-26 18:24:36,312 epoch 32 - iter 96/243 - loss 0.26207122 - time (sec): 178.76 - samples/sec: 175.24 - lr: 0.000021
2023-07-26 18:25:20,955 epoch 32 - iter 120/243 - loss 0.26238445 - time (sec): 223.40 - samples/sec: 175.45 - lr: 0.000021
2023-07-26 18:26:05,680 epoch 32 - iter 144/243 - loss 0.26421827 - time (sec): 268.13 - samples/sec: 174.45 - lr: 0.000021
2023-07-26 18:26:50,600 epoch 32 - iter 168/243 - loss 0.26554256 - time (sec): 313.05 - samples/sec: 175.05 - lr: 0.000020
2023-07-26 18:27:37,550 epoch 32 - iter 192/243 - loss 0.26682748 - time (sec): 360.00 - samples/sec: 173.67 - lr: 0.000020
2023-07-26 18:28:26,938 epoch 32 - iter 216/243 - loss 0.26495455 - time (sec): 409.38 - samples/sec: 172.06 - lr: 0.000020
2023-07-26 18:29:15,763 epoch 32 - iter 240/243 - loss 0.26526827 - time (sec): 458.21 - samples/sec: 169.70 - lr: 0.000020
2023-07-26 18:29:21,316 ----------------------------------------------------------------------------------------------------
2023-07-26 18:29:21,316 EPOCH 32 done: loss 0.2646 - lr 0.000020
2023-07-26 18:29:23,143 Evaluating as a multi-label problem: False
2023-07-26 18:29:23,187 DEV : loss 0.22920973598957062 - f1-score (micro avg)  0.9793
2023-07-26 18:29:23,197 ----------------------------------------------------------------------------------------------------
2023-07-26 18:30:10,600 epoch 33 - iter 24/243 - loss 0.26866868 - time (sec): 47.40 - samples/sec: 165.35 - lr: 0.000020
2023-07-26 18:30:58,341 epoch 33 - iter 48/243 - loss 0.25914800 - time (sec): 95.14 - samples/sec: 161.12 - lr: 0.000020
2023-07-26 18:31:46,238 epoch 33 - iter 72/243 - loss 0.25631313 - time (sec): 143.04 - samples/sec: 161.25 - lr: 0.000020
2023-07-26 18:32:38,739 epoch 33 - iter 96/243 - loss 0.25455371 - time (sec): 195.54 - samples/sec: 158.90 - lr: 0.000020
2023-07-26 18:33:26,705 epoch 33 - iter 120/243 - loss 0.25585405 - time (sec): 243.51 - samples/sec: 159.48 - lr: 0.000020
2023-07-26 18:34:14,895 epoch 33 - iter 144/243 - loss 0.25945055 - time (sec): 291.70 - samples/sec: 159.74 - lr: 0.000019
2023-07-26 18:35:02,659 epoch 33 - iter 168/243 - loss 0.25932428 - time (sec): 339.46 - samples/sec: 159.76 - lr: 0.000019
2023-07-26 18:35:50,532 epoch 33 - iter 192/243 - loss 0.25851724 - time (sec): 387.33 - samples/sec: 160.31 - lr: 0.000019
2023-07-26 18:36:38,327 epoch 33 - iter 216/243 - loss 0.25678080 - time (sec): 435.13 - samples/sec: 160.50 - lr: 0.000019
2023-07-26 18:37:26,262 epoch 33 - iter 240/243 - loss 0.25562158 - time (sec): 483.06 - samples/sec: 160.86 - lr: 0.000019
2023-07-26 18:37:31,732 ----------------------------------------------------------------------------------------------------
2023-07-26 18:37:31,732 EPOCH 33 done: loss 0.2552 - lr 0.000019
2023-07-26 18:37:33,524 Evaluating as a multi-label problem: False
2023-07-26 18:37:33,566 DEV : loss 0.23627179861068726 - f1-score (micro avg)  0.9791
2023-07-26 18:37:33,576 ----------------------------------------------------------------------------------------------------
2023-07-26 18:38:18,104 epoch 34 - iter 24/243 - loss 0.27182899 - time (sec): 44.53 - samples/sec: 177.66 - lr: 0.000019
2023-07-26 18:39:02,789 epoch 34 - iter 48/243 - loss 0.27027922 - time (sec): 89.21 - samples/sec: 177.42 - lr: 0.000019
2023-07-26 18:39:47,401 epoch 34 - iter 72/243 - loss 0.26451951 - time (sec): 133.83 - samples/sec: 176.71 - lr: 0.000019
2023-07-26 18:40:31,661 epoch 34 - iter 96/243 - loss 0.26736759 - time (sec): 178.09 - samples/sec: 174.31 - lr: 0.000019
2023-07-26 18:41:16,196 epoch 34 - iter 120/243 - loss 0.26439071 - time (sec): 222.62 - samples/sec: 174.62 - lr: 0.000018
2023-07-26 18:42:00,770 epoch 34 - iter 144/243 - loss 0.26033732 - time (sec): 267.19 - samples/sec: 174.48 - lr: 0.000018
2023-07-26 18:42:45,441 epoch 34 - iter 168/243 - loss 0.25756053 - time (sec): 311.87 - samples/sec: 174.19 - lr: 0.000018
2023-07-26 18:43:30,194 epoch 34 - iter 192/243 - loss 0.26053780 - time (sec): 356.62 - samples/sec: 174.51 - lr: 0.000018
2023-07-26 18:44:14,725 epoch 34 - iter 216/243 - loss 0.26079037 - time (sec): 401.15 - samples/sec: 174.64 - lr: 0.000018
2023-07-26 18:44:59,292 epoch 34 - iter 240/243 - loss 0.25971768 - time (sec): 445.72 - samples/sec: 174.39 - lr: 0.000018
2023-07-26 18:45:04,380 ----------------------------------------------------------------------------------------------------
2023-07-26 18:45:04,380 EPOCH 34 done: loss 0.2595 - lr 0.000018
2023-07-26 18:45:06,131 Evaluating as a multi-label problem: False
2023-07-26 18:45:06,173 DEV : loss 0.23955273628234863 - f1-score (micro avg)  0.9796
2023-07-26 18:45:06,183 ----------------------------------------------------------------------------------------------------
2023-07-26 18:45:50,882 epoch 35 - iter 24/243 - loss 0.26701266 - time (sec): 44.70 - samples/sec: 178.66 - lr: 0.000018
2023-07-26 18:46:35,519 epoch 35 - iter 48/243 - loss 0.25211759 - time (sec): 89.34 - samples/sec: 175.67 - lr: 0.000018
2023-07-26 18:47:20,251 epoch 35 - iter 72/243 - loss 0.25876122 - time (sec): 134.07 - samples/sec: 175.92 - lr: 0.000018
2023-07-26 18:48:04,922 epoch 35 - iter 96/243 - loss 0.25751966 - time (sec): 178.74 - samples/sec: 175.77 - lr: 0.000017
2023-07-26 18:48:49,416 epoch 35 - iter 120/243 - loss 0.25782676 - time (sec): 223.23 - samples/sec: 174.59 - lr: 0.000017
2023-07-26 18:49:34,049 epoch 35 - iter 144/243 - loss 0.26020302 - time (sec): 267.87 - samples/sec: 174.72 - lr: 0.000017
2023-07-26 18:50:18,677 epoch 35 - iter 168/243 - loss 0.26431905 - time (sec): 312.49 - samples/sec: 175.29 - lr: 0.000017
2023-07-26 18:51:03,300 epoch 35 - iter 192/243 - loss 0.26060801 - time (sec): 357.12 - samples/sec: 175.10 - lr: 0.000017
2023-07-26 18:51:47,857 epoch 35 - iter 216/243 - loss 0.26100924 - time (sec): 401.67 - samples/sec: 174.60 - lr: 0.000017
2023-07-26 18:52:32,385 epoch 35 - iter 240/243 - loss 0.26071736 - time (sec): 446.20 - samples/sec: 174.23 - lr: 0.000017
2023-07-26 18:52:37,453 ----------------------------------------------------------------------------------------------------
2023-07-26 18:52:37,454 EPOCH 35 done: loss 0.2611 - lr 0.000017
2023-07-26 18:52:39,658 Evaluating as a multi-label problem: False
2023-07-26 18:52:39,699 DEV : loss 0.24450713396072388 - f1-score (micro avg)  0.9791
2023-07-26 18:52:39,709 ----------------------------------------------------------------------------------------------------
2023-07-26 18:53:24,264 epoch 36 - iter 24/243 - loss 0.27084705 - time (sec): 44.55 - samples/sec: 175.18 - lr: 0.000017
2023-07-26 18:54:08,663 epoch 36 - iter 48/243 - loss 0.25947400 - time (sec): 88.95 - samples/sec: 173.11 - lr: 0.000017
2023-07-26 18:54:53,501 epoch 36 - iter 72/243 - loss 0.25687195 - time (sec): 133.79 - samples/sec: 175.35 - lr: 0.000016
2023-07-26 18:55:37,893 epoch 36 - iter 96/243 - loss 0.25424198 - time (sec): 178.18 - samples/sec: 173.93 - lr: 0.000016
2023-07-26 18:56:22,286 epoch 36 - iter 120/243 - loss 0.25557169 - time (sec): 222.58 - samples/sec: 173.34 - lr: 0.000016
2023-07-26 18:57:15,000 epoch 36 - iter 144/243 - loss 0.25787383 - time (sec): 275.29 - samples/sec: 168.90 - lr: 0.000016
2023-07-26 18:58:08,183 epoch 36 - iter 168/243 - loss 0.25642415 - time (sec): 328.47 - samples/sec: 165.37 - lr: 0.000016
2023-07-26 18:59:02,250 epoch 36 - iter 192/243 - loss 0.25543523 - time (sec): 382.54 - samples/sec: 162.77 - lr: 0.000016
2023-07-26 18:59:53,084 epoch 36 - iter 216/243 - loss 0.25443060 - time (sec): 433.38 - samples/sec: 161.58 - lr: 0.000016
2023-07-26 19:00:41,508 epoch 36 - iter 240/243 - loss 0.25344304 - time (sec): 481.80 - samples/sec: 161.25 - lr: 0.000016
2023-07-26 19:00:47,029 ----------------------------------------------------------------------------------------------------
2023-07-26 19:00:47,029 EPOCH 36 done: loss 0.2536 - lr 0.000016
2023-07-26 19:00:48,817 Evaluating as a multi-label problem: False
2023-07-26 19:00:48,859 DEV : loss 0.2530966103076935 - f1-score (micro avg)  0.9788
2023-07-26 19:00:48,869 ----------------------------------------------------------------------------------------------------
2023-07-26 19:01:33,809 epoch 37 - iter 24/243 - loss 0.27190881 - time (sec): 44.94 - samples/sec: 183.74 - lr: 0.000016
2023-07-26 19:02:18,402 epoch 37 - iter 48/243 - loss 0.26681536 - time (sec): 89.53 - samples/sec: 178.86 - lr: 0.000015
2023-07-26 19:03:03,153 epoch 37 - iter 72/243 - loss 0.26204165 - time (sec): 134.28 - samples/sec: 177.43 - lr: 0.000015
2023-07-26 19:03:47,816 epoch 37 - iter 96/243 - loss 0.25844813 - time (sec): 178.95 - samples/sec: 176.20 - lr: 0.000015
2023-07-26 19:04:32,391 epoch 37 - iter 120/243 - loss 0.25889938 - time (sec): 223.52 - samples/sec: 174.82 - lr: 0.000015
2023-07-26 19:05:17,029 epoch 37 - iter 144/243 - loss 0.26222809 - time (sec): 268.16 - samples/sec: 175.18 - lr: 0.000015
2023-07-26 19:06:01,650 epoch 37 - iter 168/243 - loss 0.26407155 - time (sec): 312.78 - samples/sec: 174.91 - lr: 0.000015
2023-07-26 19:06:46,300 epoch 37 - iter 192/243 - loss 0.26361155 - time (sec): 357.43 - samples/sec: 174.83 - lr: 0.000015
2023-07-26 19:07:31,061 epoch 37 - iter 216/243 - loss 0.26668156 - time (sec): 402.19 - samples/sec: 174.78 - lr: 0.000015
2023-07-26 19:08:15,436 epoch 37 - iter 240/243 - loss 0.26504239 - time (sec): 446.57 - samples/sec: 174.15 - lr: 0.000015
2023-07-26 19:08:20,495 ----------------------------------------------------------------------------------------------------
2023-07-26 19:08:20,495 EPOCH 37 done: loss 0.2650 - lr 0.000015
2023-07-26 19:08:22,330 Evaluating as a multi-label problem: False
2023-07-26 19:08:22,374 DEV : loss 0.2624962031841278 - f1-score (micro avg)  0.9781
2023-07-26 19:08:22,384 ----------------------------------------------------------------------------------------------------
2023-07-26 19:09:06,629 epoch 38 - iter 24/243 - loss 0.26162759 - time (sec): 44.24 - samples/sec: 174.37 - lr: 0.000014
2023-07-26 19:09:51,176 epoch 38 - iter 48/243 - loss 0.26085357 - time (sec): 88.79 - samples/sec: 175.87 - lr: 0.000014
2023-07-26 19:10:35,702 epoch 38 - iter 72/243 - loss 0.25308808 - time (sec): 133.32 - samples/sec: 176.61 - lr: 0.000014
2023-07-26 19:11:19,948 epoch 38 - iter 96/243 - loss 0.25632516 - time (sec): 177.56 - samples/sec: 175.93 - lr: 0.000014
2023-07-26 19:12:04,580 epoch 38 - iter 120/243 - loss 0.25358337 - time (sec): 222.20 - samples/sec: 176.70 - lr: 0.000014
2023-07-26 19:12:48,992 epoch 38 - iter 144/243 - loss 0.25557088 - time (sec): 266.61 - samples/sec: 176.51 - lr: 0.000014
2023-07-26 19:13:33,435 epoch 38 - iter 168/243 - loss 0.25407854 - time (sec): 311.05 - samples/sec: 176.83 - lr: 0.000014
2023-07-26 19:14:17,541 epoch 38 - iter 192/243 - loss 0.25597339 - time (sec): 355.16 - samples/sec: 176.02 - lr: 0.000014
2023-07-26 19:15:01,826 epoch 38 - iter 216/243 - loss 0.25532730 - time (sec): 399.44 - samples/sec: 175.68 - lr: 0.000014
2023-07-26 19:15:45,905 epoch 38 - iter 240/243 - loss 0.25415245 - time (sec): 443.52 - samples/sec: 175.02 - lr: 0.000013
2023-07-26 19:15:51,052 ----------------------------------------------------------------------------------------------------
2023-07-26 19:15:51,053 EPOCH 38 done: loss 0.2542 - lr 0.000013
2023-07-26 19:15:52,801 Evaluating as a multi-label problem: False
2023-07-26 19:15:52,845 DEV : loss 0.24244999885559082 - f1-score (micro avg)  0.9788
2023-07-26 19:15:52,855 ----------------------------------------------------------------------------------------------------
2023-07-26 19:16:37,293 epoch 39 - iter 24/243 - loss 0.25336484 - time (sec): 44.44 - samples/sec: 176.50 - lr: 0.000013
2023-07-26 19:17:21,644 epoch 39 - iter 48/243 - loss 0.25897743 - time (sec): 88.79 - samples/sec: 177.38 - lr: 0.000013
2023-07-26 19:18:05,772 epoch 39 - iter 72/243 - loss 0.25769549 - time (sec): 132.92 - samples/sec: 175.31 - lr: 0.000013
2023-07-26 19:18:50,169 epoch 39 - iter 96/243 - loss 0.25751150 - time (sec): 177.31 - samples/sec: 175.93 - lr: 0.000013
2023-07-26 19:19:34,381 epoch 39 - iter 120/243 - loss 0.25315782 - time (sec): 221.53 - samples/sec: 175.24 - lr: 0.000013
2023-07-26 19:20:18,559 epoch 39 - iter 144/243 - loss 0.25233489 - time (sec): 265.70 - samples/sec: 174.74 - lr: 0.000013
2023-07-26 19:21:03,145 epoch 39 - iter 168/243 - loss 0.25114668 - time (sec): 310.29 - samples/sec: 174.33 - lr: 0.000013
2023-07-26 19:21:47,854 epoch 39 - iter 192/243 - loss 0.25185953 - time (sec): 355.00 - samples/sec: 174.12 - lr: 0.000013
2023-07-26 19:22:32,507 epoch 39 - iter 216/243 - loss 0.25746349 - time (sec): 399.65 - samples/sec: 174.90 - lr: 0.000012
2023-07-26 19:23:16,796 epoch 39 - iter 240/243 - loss 0.25680252 - time (sec): 443.94 - samples/sec: 174.98 - lr: 0.000012
2023-07-26 19:23:21,907 ----------------------------------------------------------------------------------------------------
2023-07-26 19:23:21,908 EPOCH 39 done: loss 0.2579 - lr 0.000012
2023-07-26 19:23:23,678 Evaluating as a multi-label problem: False
2023-07-26 19:23:23,719 DEV : loss 0.24615894258022308 - f1-score (micro avg)  0.9798
2023-07-26 19:23:23,729 ----------------------------------------------------------------------------------------------------
2023-07-26 19:24:08,073 epoch 40 - iter 24/243 - loss 0.24837758 - time (sec): 44.34 - samples/sec: 175.24 - lr: 0.000012
2023-07-26 19:24:52,448 epoch 40 - iter 48/243 - loss 0.24725040 - time (sec): 88.72 - samples/sec: 176.39 - lr: 0.000012
2023-07-26 19:25:37,011 epoch 40 - iter 72/243 - loss 0.25023824 - time (sec): 133.28 - samples/sec: 176.92 - lr: 0.000012
2023-07-26 19:26:21,296 epoch 40 - iter 96/243 - loss 0.24239002 - time (sec): 177.57 - samples/sec: 176.32 - lr: 0.000012
2023-07-26 19:27:05,481 epoch 40 - iter 120/243 - loss 0.24524267 - time (sec): 221.75 - samples/sec: 175.34 - lr: 0.000012
2023-07-26 19:27:49,791 epoch 40 - iter 144/243 - loss 0.24784591 - time (sec): 266.06 - samples/sec: 175.50 - lr: 0.000012
2023-07-26 19:28:34,155 epoch 40 - iter 168/243 - loss 0.24872740 - time (sec): 310.43 - samples/sec: 174.67 - lr: 0.000012
2023-07-26 19:29:18,697 epoch 40 - iter 192/243 - loss 0.25012412 - time (sec): 354.97 - samples/sec: 174.67 - lr: 0.000011
2023-07-26 19:30:03,191 epoch 40 - iter 216/243 - loss 0.25345259 - time (sec): 399.46 - samples/sec: 174.99 - lr: 0.000011
2023-07-26 19:30:47,560 epoch 40 - iter 240/243 - loss 0.25383699 - time (sec): 443.83 - samples/sec: 174.98 - lr: 0.000011
2023-07-26 19:30:52,654 ----------------------------------------------------------------------------------------------------
2023-07-26 19:30:52,655 EPOCH 40 done: loss 0.2540 - lr 0.000011
2023-07-26 19:30:54,396 Evaluating as a multi-label problem: False
2023-07-26 19:30:54,438 DEV : loss 0.2575598359107971 - f1-score (micro avg)  0.9791
2023-07-26 19:30:54,447 ----------------------------------------------------------------------------------------------------
2023-07-26 19:31:38,768 epoch 41 - iter 24/243 - loss 0.24306327 - time (sec): 44.32 - samples/sec: 175.47 - lr: 0.000011
2023-07-26 19:32:23,092 epoch 41 - iter 48/243 - loss 0.24156726 - time (sec): 88.64 - samples/sec: 175.50 - lr: 0.000011
2023-07-26 19:33:07,508 epoch 41 - iter 72/243 - loss 0.24869032 - time (sec): 133.06 - samples/sec: 177.14 - lr: 0.000011
2023-07-26 19:33:51,664 epoch 41 - iter 96/243 - loss 0.25072177 - time (sec): 177.22 - samples/sec: 175.38 - lr: 0.000011
2023-07-26 19:34:35,771 epoch 41 - iter 120/243 - loss 0.25396376 - time (sec): 221.32 - samples/sec: 174.35 - lr: 0.000011
2023-07-26 19:35:20,071 epoch 41 - iter 144/243 - loss 0.25095812 - time (sec): 265.62 - samples/sec: 174.83 - lr: 0.000011
2023-07-26 19:36:04,548 epoch 41 - iter 168/243 - loss 0.24810464 - time (sec): 310.10 - samples/sec: 175.56 - lr: 0.000010
2023-07-26 19:36:48,812 epoch 41 - iter 192/243 - loss 0.24879453 - time (sec): 354.36 - samples/sec: 175.37 - lr: 0.000010
2023-07-26 19:37:33,241 epoch 41 - iter 216/243 - loss 0.25177431 - time (sec): 398.79 - samples/sec: 175.79 - lr: 0.000010
2023-07-26 19:38:17,405 epoch 41 - iter 240/243 - loss 0.25152758 - time (sec): 442.96 - samples/sec: 175.50 - lr: 0.000010
2023-07-26 19:38:22,468 ----------------------------------------------------------------------------------------------------
2023-07-26 19:38:22,469 EPOCH 41 done: loss 0.2509 - lr 0.000010
2023-07-26 19:38:24,215 Evaluating as a multi-label problem: False
2023-07-26 19:38:24,257 DEV : loss 0.25127604603767395 - f1-score (micro avg)  0.9786
2023-07-26 19:38:24,267 ----------------------------------------------------------------------------------------------------
2023-07-26 19:39:08,271 epoch 42 - iter 24/243 - loss 0.25413425 - time (sec): 44.00 - samples/sec: 167.14 - lr: 0.000010
2023-07-26 19:39:52,711 epoch 42 - iter 48/243 - loss 0.25771203 - time (sec): 88.44 - samples/sec: 173.59 - lr: 0.000010
2023-07-26 19:40:37,013 epoch 42 - iter 72/243 - loss 0.25402986 - time (sec): 132.75 - samples/sec: 174.07 - lr: 0.000010
2023-07-26 19:41:21,464 epoch 42 - iter 96/243 - loss 0.25689370 - time (sec): 177.20 - samples/sec: 175.64 - lr: 0.000010
2023-07-26 19:42:05,507 epoch 42 - iter 120/243 - loss 0.25635789 - time (sec): 221.24 - samples/sec: 174.08 - lr: 0.000010
2023-07-26 19:42:49,881 epoch 42 - iter 144/243 - loss 0.25641142 - time (sec): 265.61 - samples/sec: 174.68 - lr: 0.000009
2023-07-26 19:43:34,200 epoch 42 - iter 168/243 - loss 0.25676110 - time (sec): 309.93 - samples/sec: 175.15 - lr: 0.000009
2023-07-26 19:44:18,472 epoch 42 - iter 192/243 - loss 0.25789268 - time (sec): 354.20 - samples/sec: 175.15 - lr: 0.000009
2023-07-26 19:45:02,833 epoch 42 - iter 216/243 - loss 0.25889165 - time (sec): 398.57 - samples/sec: 175.63 - lr: 0.000009
2023-07-26 19:45:47,116 epoch 42 - iter 240/243 - loss 0.25885055 - time (sec): 442.85 - samples/sec: 175.64 - lr: 0.000009
2023-07-26 19:45:52,133 ----------------------------------------------------------------------------------------------------
2023-07-26 19:45:52,133 EPOCH 42 done: loss 0.2584 - lr 0.000009
2023-07-26 19:45:54,001 Evaluating as a multi-label problem: False
2023-07-26 19:45:54,045 DEV : loss 0.2509002983570099 - f1-score (micro avg)  0.9776
2023-07-26 19:45:54,056 ----------------------------------------------------------------------------------------------------
2023-07-26 19:46:38,776 epoch 43 - iter 24/243 - loss 0.25656669 - time (sec): 44.72 - samples/sec: 175.88 - lr: 0.000009
2023-07-26 19:47:23,646 epoch 43 - iter 48/243 - loss 0.25713909 - time (sec): 89.59 - samples/sec: 179.17 - lr: 0.000009
2023-07-26 19:48:08,109 epoch 43 - iter 72/243 - loss 0.25209780 - time (sec): 134.05 - samples/sec: 176.45 - lr: 0.000009
2023-07-26 19:48:52,698 epoch 43 - iter 96/243 - loss 0.24509857 - time (sec): 178.64 - samples/sec: 175.75 - lr: 0.000009
2023-07-26 19:49:37,182 epoch 43 - iter 120/243 - loss 0.25000579 - time (sec): 223.13 - samples/sec: 174.94 - lr: 0.000008
2023-07-26 19:50:21,736 epoch 43 - iter 144/243 - loss 0.25295949 - time (sec): 267.68 - samples/sec: 175.08 - lr: 0.000008
2023-07-26 19:51:06,420 epoch 43 - iter 168/243 - loss 0.25493036 - time (sec): 312.36 - samples/sec: 175.74 - lr: 0.000008
2023-07-26 19:51:50,778 epoch 43 - iter 192/243 - loss 0.25313033 - time (sec): 356.72 - samples/sec: 174.71 - lr: 0.000008
2023-07-26 19:52:35,121 epoch 43 - iter 216/243 - loss 0.25255837 - time (sec): 401.06 - samples/sec: 174.20 - lr: 0.000008
2023-07-26 19:53:19,699 epoch 43 - iter 240/243 - loss 0.25326105 - time (sec): 445.64 - samples/sec: 174.52 - lr: 0.000008
2023-07-26 19:53:24,805 ----------------------------------------------------------------------------------------------------
2023-07-26 19:53:24,805 EPOCH 43 done: loss 0.2536 - lr 0.000008
2023-07-26 19:53:27,059 Evaluating as a multi-label problem: False
2023-07-26 19:53:27,103 DEV : loss 0.25337928533554077 - f1-score (micro avg)  0.9784
2023-07-26 19:53:27,114 ----------------------------------------------------------------------------------------------------
2023-07-26 19:54:11,472 epoch 44 - iter 24/243 - loss 0.22752064 - time (sec): 44.36 - samples/sec: 169.73 - lr: 0.000008
2023-07-26 19:54:55,919 epoch 44 - iter 48/243 - loss 0.23951614 - time (sec): 88.80 - samples/sec: 171.20 - lr: 0.000008
2023-07-26 19:55:40,452 epoch 44 - iter 72/243 - loss 0.23986022 - time (sec): 133.34 - samples/sec: 171.97 - lr: 0.000008
2023-07-26 19:56:25,023 epoch 44 - iter 96/243 - loss 0.24528781 - time (sec): 177.91 - samples/sec: 173.40 - lr: 0.000007
2023-07-26 19:57:09,511 epoch 44 - iter 120/243 - loss 0.24572088 - time (sec): 222.40 - samples/sec: 173.40 - lr: 0.000007
2023-07-26 19:57:54,163 epoch 44 - iter 144/243 - loss 0.24464183 - time (sec): 267.05 - samples/sec: 173.04 - lr: 0.000007
2023-07-26 19:58:39,149 epoch 44 - iter 168/243 - loss 0.24523592 - time (sec): 312.04 - samples/sec: 173.72 - lr: 0.000007
2023-07-26 19:59:23,881 epoch 44 - iter 192/243 - loss 0.24519757 - time (sec): 356.77 - samples/sec: 173.61 - lr: 0.000007
2023-07-26 20:00:08,665 epoch 44 - iter 216/243 - loss 0.24456227 - time (sec): 401.55 - samples/sec: 173.99 - lr: 0.000007
2023-07-26 20:00:53,278 epoch 44 - iter 240/243 - loss 0.24582873 - time (sec): 446.16 - samples/sec: 174.08 - lr: 0.000007
2023-07-26 20:00:58,393 ----------------------------------------------------------------------------------------------------
2023-07-26 20:00:58,393 EPOCH 44 done: loss 0.2462 - lr 0.000007
2023-07-26 20:01:00,158 Evaluating as a multi-label problem: False
2023-07-26 20:01:00,200 DEV : loss 0.25915977358818054 - f1-score (micro avg)  0.9784
2023-07-26 20:01:00,210 ----------------------------------------------------------------------------------------------------
2023-07-26 20:01:44,820 epoch 45 - iter 24/243 - loss 0.26201019 - time (sec): 44.61 - samples/sec: 176.98 - lr: 0.000007
2023-07-26 20:02:29,464 epoch 45 - iter 48/243 - loss 0.24779270 - time (sec): 89.25 - samples/sec: 174.35 - lr: 0.000007
2023-07-26 20:03:13,973 epoch 45 - iter 72/243 - loss 0.25012887 - time (sec): 133.76 - samples/sec: 174.72 - lr: 0.000006
2023-07-26 20:03:58,625 epoch 45 - iter 96/243 - loss 0.25289868 - time (sec): 178.41 - samples/sec: 174.60 - lr: 0.000006
2023-07-26 20:04:43,139 epoch 45 - iter 120/243 - loss 0.25326284 - time (sec): 222.93 - samples/sec: 174.12 - lr: 0.000006
2023-07-26 20:05:27,809 epoch 45 - iter 144/243 - loss 0.25373868 - time (sec): 267.60 - samples/sec: 174.76 - lr: 0.000006
2023-07-26 20:06:12,288 epoch 45 - iter 168/243 - loss 0.25215421 - time (sec): 312.08 - samples/sec: 174.53 - lr: 0.000006
2023-07-26 20:06:56,723 epoch 45 - iter 192/243 - loss 0.25175489 - time (sec): 356.51 - samples/sec: 174.02 - lr: 0.000006
2023-07-26 20:07:41,287 epoch 45 - iter 216/243 - loss 0.24952171 - time (sec): 401.08 - samples/sec: 174.05 - lr: 0.000006
2023-07-26 20:08:25,996 epoch 45 - iter 240/243 - loss 0.25004168 - time (sec): 445.79 - samples/sec: 174.41 - lr: 0.000006
2023-07-26 20:08:31,078 ----------------------------------------------------------------------------------------------------
2023-07-26 20:08:31,079 EPOCH 45 done: loss 0.2503 - lr 0.000006
2023-07-26 20:08:32,834 Evaluating as a multi-label problem: False
2023-07-26 20:08:32,877 DEV : loss 0.2550533413887024 - f1-score (micro avg)  0.9788
2023-07-26 20:08:32,887 ----------------------------------------------------------------------------------------------------
2023-07-26 20:09:17,479 epoch 46 - iter 24/243 - loss 0.24479678 - time (sec): 44.59 - samples/sec: 177.79 - lr: 0.000006
2023-07-26 20:10:02,067 epoch 46 - iter 48/243 - loss 0.24138586 - time (sec): 89.18 - samples/sec: 175.65 - lr: 0.000005
2023-07-26 20:10:46,638 epoch 46 - iter 72/243 - loss 0.24404064 - time (sec): 133.75 - samples/sec: 175.18 - lr: 0.000005
2023-07-26 20:11:31,127 epoch 46 - iter 96/243 - loss 0.24604064 - time (sec): 178.24 - samples/sec: 174.01 - lr: 0.000005
2023-07-26 20:12:15,792 epoch 46 - iter 120/243 - loss 0.24783294 - time (sec): 222.91 - samples/sec: 174.51 - lr: 0.000005
2023-07-26 20:13:00,505 epoch 46 - iter 144/243 - loss 0.24973562 - time (sec): 267.62 - samples/sec: 174.34 - lr: 0.000005
2023-07-26 20:13:45,181 epoch 46 - iter 168/243 - loss 0.24967162 - time (sec): 312.29 - samples/sec: 173.97 - lr: 0.000005
2023-07-26 20:14:30,156 epoch 46 - iter 192/243 - loss 0.25131667 - time (sec): 357.27 - samples/sec: 173.94 - lr: 0.000005
2023-07-26 20:15:14,977 epoch 46 - iter 216/243 - loss 0.25004815 - time (sec): 402.09 - samples/sec: 174.06 - lr: 0.000005
2023-07-26 20:15:59,586 epoch 46 - iter 240/243 - loss 0.24797003 - time (sec): 446.70 - samples/sec: 174.19 - lr: 0.000005
2023-07-26 20:16:04,601 ----------------------------------------------------------------------------------------------------
2023-07-26 20:16:04,602 EPOCH 46 done: loss 0.2475 - lr 0.000005
2023-07-26 20:16:06,359 Evaluating as a multi-label problem: False
2023-07-26 20:16:06,401 DEV : loss 0.2502936124801636 - f1-score (micro avg)  0.9796
2023-07-26 20:16:06,411 ----------------------------------------------------------------------------------------------------
2023-07-26 20:16:50,970 epoch 47 - iter 24/243 - loss 0.24652539 - time (sec): 44.56 - samples/sec: 177.11 - lr: 0.000004
2023-07-26 20:17:35,687 epoch 47 - iter 48/243 - loss 0.25432254 - time (sec): 89.28 - samples/sec: 178.43 - lr: 0.000004
2023-07-26 20:18:20,313 epoch 47 - iter 72/243 - loss 0.24907829 - time (sec): 133.90 - samples/sec: 178.67 - lr: 0.000004
2023-07-26 20:19:04,573 epoch 47 - iter 96/243 - loss 0.25143514 - time (sec): 178.16 - samples/sec: 175.41 - lr: 0.000004
2023-07-26 20:19:49,067 epoch 47 - iter 120/243 - loss 0.25195942 - time (sec): 222.66 - samples/sec: 174.82 - lr: 0.000004
2023-07-26 20:20:33,729 epoch 47 - iter 144/243 - loss 0.25140692 - time (sec): 267.32 - samples/sec: 175.12 - lr: 0.000004
2023-07-26 20:21:18,294 epoch 47 - iter 168/243 - loss 0.25098133 - time (sec): 311.88 - samples/sec: 175.27 - lr: 0.000004
2023-07-26 20:22:02,731 epoch 47 - iter 192/243 - loss 0.24903435 - time (sec): 356.32 - samples/sec: 174.38 - lr: 0.000004
2023-07-26 20:22:47,241 epoch 47 - iter 216/243 - loss 0.24707558 - time (sec): 400.83 - samples/sec: 174.35 - lr: 0.000004
2023-07-26 20:23:31,808 epoch 47 - iter 240/243 - loss 0.24996260 - time (sec): 445.40 - samples/sec: 174.50 - lr: 0.000003
2023-07-26 20:23:36,885 ----------------------------------------------------------------------------------------------------
2023-07-26 20:23:36,885 EPOCH 47 done: loss 0.2500 - lr 0.000003
2023-07-26 20:23:38,718 Evaluating as a multi-label problem: False
2023-07-26 20:23:38,760 DEV : loss 0.25260353088378906 - f1-score (micro avg)  0.9788
2023-07-26 20:23:38,770 ----------------------------------------------------------------------------------------------------
2023-07-26 20:24:23,284 epoch 48 - iter 24/243 - loss 0.26092477 - time (sec): 44.51 - samples/sec: 173.72 - lr: 0.000003
2023-07-26 20:25:07,731 epoch 48 - iter 48/243 - loss 0.26380496 - time (sec): 88.96 - samples/sec: 172.51 - lr: 0.000003
2023-07-26 20:25:52,549 epoch 48 - iter 72/243 - loss 0.26586966 - time (sec): 133.78 - samples/sec: 175.68 - lr: 0.000003
2023-07-26 20:26:37,081 epoch 48 - iter 96/243 - loss 0.26118560 - time (sec): 178.31 - samples/sec: 175.37 - lr: 0.000003
2023-07-26 20:27:21,769 epoch 48 - iter 120/243 - loss 0.25715945 - time (sec): 223.00 - samples/sec: 176.11 - lr: 0.000003
2023-07-26 20:28:06,589 epoch 48 - iter 144/243 - loss 0.25935501 - time (sec): 267.82 - samples/sec: 176.32 - lr: 0.000003
2023-07-26 20:28:51,230 epoch 48 - iter 168/243 - loss 0.25807126 - time (sec): 312.46 - samples/sec: 175.36 - lr: 0.000003
2023-07-26 20:29:35,872 epoch 48 - iter 192/243 - loss 0.25819322 - time (sec): 357.10 - samples/sec: 174.73 - lr: 0.000003
2023-07-26 20:30:20,621 epoch 48 - iter 216/243 - loss 0.25780077 - time (sec): 401.85 - samples/sec: 174.84 - lr: 0.000002
2023-07-26 20:31:05,115 epoch 48 - iter 240/243 - loss 0.25669533 - time (sec): 446.34 - samples/sec: 174.17 - lr: 0.000002
2023-07-26 20:31:10,189 ----------------------------------------------------------------------------------------------------
2023-07-26 20:31:10,189 EPOCH 48 done: loss 0.2562 - lr 0.000002
2023-07-26 20:31:11,946 Evaluating as a multi-label problem: False
2023-07-26 20:31:11,989 DEV : loss 0.2517630159854889 - f1-score (micro avg)  0.9793
2023-07-26 20:31:11,998 ----------------------------------------------------------------------------------------------------
2023-07-26 20:31:56,576 epoch 49 - iter 24/243 - loss 0.27952006 - time (sec): 44.58 - samples/sec: 171.79 - lr: 0.000002
2023-07-26 20:32:41,285 epoch 49 - iter 48/243 - loss 0.26483505 - time (sec): 89.29 - samples/sec: 172.32 - lr: 0.000002
2023-07-26 20:33:25,782 epoch 49 - iter 72/243 - loss 0.25971199 - time (sec): 133.78 - samples/sec: 171.90 - lr: 0.000002
2023-07-26 20:34:10,460 epoch 49 - iter 96/243 - loss 0.25971123 - time (sec): 178.46 - samples/sec: 173.31 - lr: 0.000002
2023-07-26 20:34:55,145 epoch 49 - iter 120/243 - loss 0.25121870 - time (sec): 223.15 - samples/sec: 174.45 - lr: 0.000002
2023-07-26 20:35:39,794 epoch 49 - iter 144/243 - loss 0.24985456 - time (sec): 267.80 - samples/sec: 174.14 - lr: 0.000002
2023-07-26 20:36:24,454 epoch 49 - iter 168/243 - loss 0.25019492 - time (sec): 312.46 - samples/sec: 173.74 - lr: 0.000002
2023-07-26 20:37:09,180 epoch 49 - iter 192/243 - loss 0.24964407 - time (sec): 357.18 - samples/sec: 174.05 - lr: 0.000001
2023-07-26 20:37:53,667 epoch 49 - iter 216/243 - loss 0.24966262 - time (sec): 401.67 - samples/sec: 173.91 - lr: 0.000001
2023-07-26 20:38:38,222 epoch 49 - iter 240/243 - loss 0.24839303 - time (sec): 446.22 - samples/sec: 173.82 - lr: 0.000001
2023-07-26 20:38:43,407 ----------------------------------------------------------------------------------------------------
2023-07-26 20:38:43,407 EPOCH 49 done: loss 0.2480 - lr 0.000001
2023-07-26 20:38:45,164 Evaluating as a multi-label problem: False
2023-07-26 20:38:45,206 DEV : loss 0.25181668996810913 - f1-score (micro avg)  0.9786
2023-07-26 20:38:45,216 ----------------------------------------------------------------------------------------------------
2023-07-26 20:39:30,103 epoch 50 - iter 24/243 - loss 0.26114983 - time (sec): 44.89 - samples/sec: 184.97 - lr: 0.000001
2023-07-26 20:40:14,469 epoch 50 - iter 48/243 - loss 0.24629344 - time (sec): 89.25 - samples/sec: 177.23 - lr: 0.000001
2023-07-26 20:40:58,962 epoch 50 - iter 72/243 - loss 0.24771674 - time (sec): 133.75 - samples/sec: 176.12 - lr: 0.000001
2023-07-26 20:41:43,633 epoch 50 - iter 96/243 - loss 0.24705085 - time (sec): 178.42 - samples/sec: 176.67 - lr: 0.000001
2023-07-26 20:42:28,058 epoch 50 - iter 120/243 - loss 0.24435267 - time (sec): 222.84 - samples/sec: 175.63 - lr: 0.000001
2023-07-26 20:43:12,552 epoch 50 - iter 144/243 - loss 0.24537610 - time (sec): 267.34 - samples/sec: 175.26 - lr: 0.000001
2023-07-26 20:43:57,183 epoch 50 - iter 168/243 - loss 0.24725247 - time (sec): 311.97 - samples/sec: 175.35 - lr: 0.000000
2023-07-26 20:44:42,166 epoch 50 - iter 192/243 - loss 0.24773009 - time (sec): 356.95 - samples/sec: 174.58 - lr: 0.000000
2023-07-26 20:45:27,096 epoch 50 - iter 216/243 - loss 0.24906212 - time (sec): 401.88 - samples/sec: 173.96 - lr: 0.000000
2023-07-26 20:46:12,548 epoch 50 - iter 240/243 - loss 0.24977353 - time (sec): 447.33 - samples/sec: 173.87 - lr: 0.000000
2023-07-26 20:46:17,709 ----------------------------------------------------------------------------------------------------
2023-07-26 20:46:17,709 EPOCH 50 done: loss 0.2503 - lr 0.000000
2023-07-26 20:46:19,451 Evaluating as a multi-label problem: False
2023-07-26 20:46:19,493 DEV : loss 0.2513697147369385 - f1-score (micro avg)  0.9784
2023-07-26 20:46:22,002 Test data not provided setting final score to 0