2022-08-06 15:12:29,180 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,182 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(42000, 768, padding_idx=0)
        (position_embeddings): Embedding(512, 768)
        (token_type_embeddings): Embedding(2, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): BertEncoder(
        (layer): ModuleList(
          (0): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (1): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (2): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (3): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (4): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (5): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (6): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (7): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (8): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (9): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (10): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (11): BertLayer(
            (attention): BertAttention(
              (self): BertSelfAttention(
                (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): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
  )
  (word_dropout): WordDropout(p=0.05)
  (locked_dropout): LockedDropout(p=0.5)
  (rnn): LSTM(768, 512, batch_first=True, bidirectional=True)
  (linear): Linear(in_features=1024, out_features=30, bias=True)
  (beta): 1.0
  (weights): None
  (weight_tensor) None
)"
2022-08-06 15:12:29,182 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,183 Corpus: "Corpus: 24000 train + 3000 dev + 3000 test sentences"
2022-08-06 15:12:29,183 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,183 Parameters:
2022-08-06 15:12:29,183  - learning_rate: "0.1"
2022-08-06 15:12:29,183  - mini_batch_size: "8"
2022-08-06 15:12:29,183  - patience: "3"
2022-08-06 15:12:29,183  - anneal_factor: "0.5"
2022-08-06 15:12:29,183  - max_epochs: "10"
2022-08-06 15:12:29,183  - shuffle: "True"
2022-08-06 15:12:29,183  - train_with_dev: "True"
2022-08-06 15:12:29,183  - batch_growth_annealing: "False"
2022-08-06 15:12:29,183 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,183 Model training base path: "data/pos-Uppsala/model"
2022-08-06 15:12:29,183 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,183 Device: cuda:0
2022-08-06 15:12:29,183 ----------------------------------------------------------------------------------------------------
2022-08-06 15:12:29,184 Embeddings storage mode: gpu
2022-08-06 15:12:29,185 ----------------------------------------------------------------------------------------------------
2022-08-06 15:13:18,972 epoch 1 - iter 337/3375 - loss 0.74289984 - samples/sec: 54.18 - lr: 0.100000
2022-08-06 15:14:15,036 epoch 1 - iter 674/3375 - loss 0.53599298 - samples/sec: 48.11 - lr: 0.100000
2022-08-06 15:15:12,610 epoch 1 - iter 1011/3375 - loss 0.45754038 - samples/sec: 46.85 - lr: 0.100000
2022-08-06 15:16:09,043 epoch 1 - iter 1348/3375 - loss 0.40111208 - samples/sec: 47.79 - lr: 0.100000
2022-08-06 15:17:04,137 epoch 1 - iter 1685/3375 - loss 0.36712663 - samples/sec: 48.96 - lr: 0.100000
2022-08-06 15:17:58,402 epoch 1 - iter 2022/3375 - loss 0.34049225 - samples/sec: 49.70 - lr: 0.100000
2022-08-06 15:18:55,276 epoch 1 - iter 2359/3375 - loss 0.32076226 - samples/sec: 47.42 - lr: 0.100000
2022-08-06 15:19:49,979 epoch 1 - iter 2696/3375 - loss 0.31015506 - samples/sec: 49.31 - lr: 0.100000
2022-08-06 15:20:48,410 epoch 1 - iter 3033/3375 - loss 0.29391699 - samples/sec: 46.16 - lr: 0.100000
2022-08-06 15:21:47,572 epoch 1 - iter 3370/3375 - loss 0.27989028 - samples/sec: 45.59 - lr: 0.100000
2022-08-06 15:21:48,555 ----------------------------------------------------------------------------------------------------
2022-08-06 15:21:48,555 EPOCH 1 done: loss 0.2795 - lr 0.1000000
2022-08-06 15:21:48,555 BAD EPOCHS (no improvement): 0
2022-08-06 15:21:48,555 ----------------------------------------------------------------------------------------------------
2022-08-06 15:22:45,590 epoch 2 - iter 337/3375 - loss 0.18085661 - samples/sec: 47.29 - lr: 0.100000
2022-08-06 15:23:42,698 epoch 2 - iter 674/3375 - loss 0.17216272 - samples/sec: 47.23 - lr: 0.100000
2022-08-06 15:24:38,534 epoch 2 - iter 1011/3375 - loss 0.16694117 - samples/sec: 48.31 - lr: 0.100000
2022-08-06 15:25:36,464 epoch 2 - iter 1348/3375 - loss 0.16500505 - samples/sec: 46.56 - lr: 0.100000
2022-08-06 15:26:32,174 epoch 2 - iter 1685/3375 - loss 0.16167195 - samples/sec: 48.42 - lr: 0.100000
2022-08-06 15:27:28,418 epoch 2 - iter 2022/3375 - loss 0.15991464 - samples/sec: 47.96 - lr: 0.100000
2022-08-06 15:28:30,730 epoch 2 - iter 2359/3375 - loss 0.15942296 - samples/sec: 43.29 - lr: 0.100000
2022-08-06 15:29:27,444 epoch 2 - iter 2696/3375 - loss 0.15779417 - samples/sec: 47.56 - lr: 0.100000
2022-08-06 15:30:25,187 epoch 2 - iter 3033/3375 - loss 0.15553239 - samples/sec: 46.71 - lr: 0.100000
2022-08-06 15:31:21,714 epoch 2 - iter 3370/3375 - loss 0.15352182 - samples/sec: 47.72 - lr: 0.100000
2022-08-06 15:31:22,712 ----------------------------------------------------------------------------------------------------
2022-08-06 15:31:22,712 EPOCH 2 done: loss 0.1537 - lr 0.1000000
2022-08-06 15:31:22,712 BAD EPOCHS (no improvement): 0
2022-08-06 15:31:22,712 ----------------------------------------------------------------------------------------------------
2022-08-06 15:32:23,790 epoch 3 - iter 337/3375 - loss 0.11867195 - samples/sec: 44.16 - lr: 0.100000
2022-08-06 15:33:21,161 epoch 3 - iter 674/3375 - loss 0.11878234 - samples/sec: 47.02 - lr: 0.100000
2022-08-06 15:34:20,702 epoch 3 - iter 1011/3375 - loss 0.11942785 - samples/sec: 45.31 - lr: 0.100000
2022-08-06 15:35:18,259 epoch 3 - iter 1348/3375 - loss 0.11958903 - samples/sec: 46.86 - lr: 0.100000
2022-08-06 15:36:16,967 epoch 3 - iter 1685/3375 - loss 0.11914369 - samples/sec: 45.94 - lr: 0.100000
2022-08-06 15:37:13,560 epoch 3 - iter 2022/3375 - loss 0.11916365 - samples/sec: 47.66 - lr: 0.100000
2022-08-06 15:38:10,624 epoch 3 - iter 2359/3375 - loss 0.12096981 - samples/sec: 47.27 - lr: 0.100000
2022-08-06 15:39:10,034 epoch 3 - iter 2696/3375 - loss 0.11987245 - samples/sec: 45.40 - lr: 0.100000
2022-08-06 15:40:07,877 epoch 3 - iter 3033/3375 - loss 0.11973164 - samples/sec: 46.63 - lr: 0.100000
2022-08-06 15:41:05,610 epoch 3 - iter 3370/3375 - loss 0.12003917 - samples/sec: 46.72 - lr: 0.100000
2022-08-06 15:41:06,450 ----------------------------------------------------------------------------------------------------
2022-08-06 15:41:06,450 EPOCH 3 done: loss 0.1200 - lr 0.1000000
2022-08-06 15:41:06,450 BAD EPOCHS (no improvement): 0
2022-08-06 15:41:06,451 ----------------------------------------------------------------------------------------------------
2022-08-06 15:42:04,442 epoch 4 - iter 337/3375 - loss 0.09805702 - samples/sec: 46.51 - lr: 0.100000
2022-08-06 15:43:05,164 epoch 4 - iter 674/3375 - loss 0.09888569 - samples/sec: 44.42 - lr: 0.100000
2022-08-06 15:44:02,546 epoch 4 - iter 1011/3375 - loss 0.10053644 - samples/sec: 47.01 - lr: 0.100000
2022-08-06 15:45:01,384 epoch 4 - iter 1348/3375 - loss 0.10119574 - samples/sec: 45.84 - lr: 0.100000
2022-08-06 15:46:00,229 epoch 4 - iter 1685/3375 - loss 0.10374826 - samples/sec: 45.84 - lr: 0.100000
2022-08-06 15:46:59,791 epoch 4 - iter 2022/3375 - loss 0.10405522 - samples/sec: 45.28 - lr: 0.100000
2022-08-06 15:47:57,607 epoch 4 - iter 2359/3375 - loss 0.10411718 - samples/sec: 46.65 - lr: 0.100000
2022-08-06 15:48:55,410 epoch 4 - iter 2696/3375 - loss 0.10394934 - samples/sec: 46.66 - lr: 0.100000
2022-08-06 15:49:56,783 epoch 4 - iter 3033/3375 - loss 0.10374714 - samples/sec: 43.95 - lr: 0.100000
2022-08-06 15:50:54,113 epoch 4 - iter 3370/3375 - loss 0.10333066 - samples/sec: 47.05 - lr: 0.100000
2022-08-06 15:50:54,961 ----------------------------------------------------------------------------------------------------
2022-08-06 15:50:54,961 EPOCH 4 done: loss 0.1033 - lr 0.1000000
2022-08-06 15:50:54,961 BAD EPOCHS (no improvement): 0
2022-08-06 15:50:54,961 ----------------------------------------------------------------------------------------------------
2022-08-06 15:51:52,151 epoch 5 - iter 337/3375 - loss 0.08744228 - samples/sec: 47.17 - lr: 0.100000
2022-08-06 15:52:49,910 epoch 5 - iter 674/3375 - loss 0.08896766 - samples/sec: 46.70 - lr: 0.100000
2022-08-06 15:53:50,861 epoch 5 - iter 1011/3375 - loss 0.09000325 - samples/sec: 44.25 - lr: 0.100000
2022-08-06 15:54:48,357 epoch 5 - iter 1348/3375 - loss 0.09103779 - samples/sec: 46.91 - lr: 0.100000
2022-08-06 15:55:48,122 epoch 5 - iter 1685/3375 - loss 0.09107958 - samples/sec: 45.13 - lr: 0.100000
2022-08-06 15:56:49,324 epoch 5 - iter 2022/3375 - loss 0.09135469 - samples/sec: 44.07 - lr: 0.100000
2022-08-06 15:57:47,393 epoch 5 - iter 2359/3375 - loss 0.09172710 - samples/sec: 46.45 - lr: 0.100000
2022-08-06 15:58:45,694 epoch 5 - iter 2696/3375 - loss 0.09238154 - samples/sec: 46.27 - lr: 0.100000
2022-08-06 15:59:42,885 epoch 5 - iter 3033/3375 - loss 0.09253470 - samples/sec: 47.16 - lr: 0.100000
2022-08-06 16:00:44,492 epoch 5 - iter 3370/3375 - loss 0.09240350 - samples/sec: 43.78 - lr: 0.100000
2022-08-06 16:00:45,327 ----------------------------------------------------------------------------------------------------
2022-08-06 16:00:45,328 EPOCH 5 done: loss 0.0924 - lr 0.1000000
2022-08-06 16:00:45,328 BAD EPOCHS (no improvement): 0
2022-08-06 16:00:45,328 ----------------------------------------------------------------------------------------------------
2022-08-06 16:01:42,167 epoch 6 - iter 337/3375 - loss 0.08075428 - samples/sec: 47.46 - lr: 0.100000
2022-08-06 16:02:39,509 epoch 6 - iter 674/3375 - loss 0.08099115 - samples/sec: 47.04 - lr: 0.100000
2022-08-06 16:03:37,688 epoch 6 - iter 1011/3375 - loss 0.08140463 - samples/sec: 46.36 - lr: 0.100000
2022-08-06 16:04:38,640 epoch 6 - iter 1348/3375 - loss 0.08175190 - samples/sec: 44.25 - lr: 0.100000
2022-08-06 16:05:35,459 epoch 6 - iter 1685/3375 - loss 0.08233525 - samples/sec: 47.47 - lr: 0.100000
2022-08-06 16:06:33,941 epoch 6 - iter 2022/3375 - loss 0.08333964 - samples/sec: 46.12 - lr: 0.100000
2022-08-06 16:07:34,247 epoch 6 - iter 2359/3375 - loss 0.08370656 - samples/sec: 44.73 - lr: 0.100000
2022-08-06 16:08:32,546 epoch 6 - iter 2696/3375 - loss 0.08503503 - samples/sec: 46.27 - lr: 0.100000
2022-08-06 16:09:30,447 epoch 6 - iter 3033/3375 - loss 0.08526801 - samples/sec: 46.58 - lr: 0.100000
2022-08-06 16:10:29,216 epoch 6 - iter 3370/3375 - loss 0.08506276 - samples/sec: 45.90 - lr: 0.100000
2022-08-06 16:10:29,946 ----------------------------------------------------------------------------------------------------
2022-08-06 16:10:29,947 EPOCH 6 done: loss 0.0851 - lr 0.1000000
2022-08-06 16:10:29,947 BAD EPOCHS (no improvement): 0
2022-08-06 16:10:29,947 ----------------------------------------------------------------------------------------------------
2022-08-06 16:11:31,042 epoch 7 - iter 337/3375 - loss 0.07328964 - samples/sec: 44.15 - lr: 0.100000
2022-08-06 16:12:31,218 epoch 7 - iter 674/3375 - loss 0.07556648 - samples/sec: 44.82 - lr: 0.100000
2022-08-06 16:13:28,468 epoch 7 - iter 1011/3375 - loss 0.07578294 - samples/sec: 47.11 - lr: 0.100000
2022-08-06 16:14:28,318 epoch 7 - iter 1348/3375 - loss 0.07581855 - samples/sec: 45.07 - lr: 0.100000
2022-08-06 16:15:27,119 epoch 7 - iter 1685/3375 - loss 0.07674717 - samples/sec: 45.87 - lr: 0.100000
2022-08-06 16:16:25,205 epoch 7 - iter 2022/3375 - loss 0.07800463 - samples/sec: 46.44 - lr: 0.100000
2022-08-06 16:17:25,635 epoch 7 - iter 2359/3375 - loss 0.07788540 - samples/sec: 44.64 - lr: 0.100000
2022-08-06 16:18:25,934 epoch 7 - iter 2696/3375 - loss 0.07823310 - samples/sec: 44.73 - lr: 0.100000
2022-08-06 16:19:25,742 epoch 7 - iter 3033/3375 - loss 0.07862489 - samples/sec: 45.10 - lr: 0.100000
2022-08-06 16:20:24,514 epoch 7 - iter 3370/3375 - loss 0.07864779 - samples/sec: 45.89 - lr: 0.100000
2022-08-06 16:20:25,316 ----------------------------------------------------------------------------------------------------
2022-08-06 16:20:25,317 EPOCH 7 done: loss 0.0786 - lr 0.1000000
2022-08-06 16:20:25,317 BAD EPOCHS (no improvement): 0
2022-08-06 16:20:25,317 ----------------------------------------------------------------------------------------------------
2022-08-06 16:21:23,040 epoch 8 - iter 337/3375 - loss 0.06876001 - samples/sec: 46.73 - lr: 0.100000
2022-08-06 16:22:25,028 epoch 8 - iter 674/3375 - loss 0.06867038 - samples/sec: 43.51 - lr: 0.100000
2022-08-06 16:23:25,046 epoch 8 - iter 1011/3375 - loss 0.07011779 - samples/sec: 44.94 - lr: 0.100000
2022-08-06 16:24:23,287 epoch 8 - iter 1348/3375 - loss 0.07118411 - samples/sec: 46.31 - lr: 0.100000
2022-08-06 16:25:24,939 epoch 8 - iter 1685/3375 - loss 0.07159055 - samples/sec: 43.75 - lr: 0.100000
2022-08-06 16:26:23,316 epoch 8 - iter 2022/3375 - loss 0.07167687 - samples/sec: 46.21 - lr: 0.100000
2022-08-06 16:27:22,234 epoch 8 - iter 2359/3375 - loss 0.07190781 - samples/sec: 45.78 - lr: 0.100000
2022-08-06 16:28:20,921 epoch 8 - iter 2696/3375 - loss 0.07263123 - samples/sec: 45.96 - lr: 0.100000
2022-08-06 16:29:21,637 epoch 8 - iter 3033/3375 - loss 0.07345723 - samples/sec: 44.42 - lr: 0.100000
2022-08-06 16:30:20,403 epoch 8 - iter 3370/3375 - loss 0.07338627 - samples/sec: 45.90 - lr: 0.100000
2022-08-06 16:30:21,375 ----------------------------------------------------------------------------------------------------
2022-08-06 16:30:21,375 EPOCH 8 done: loss 0.0734 - lr 0.1000000
2022-08-06 16:30:21,375 BAD EPOCHS (no improvement): 0
2022-08-06 16:30:21,376 ----------------------------------------------------------------------------------------------------
2022-08-06 16:31:18,803 epoch 9 - iter 337/3375 - loss 0.06314787 - samples/sec: 46.97 - lr: 0.100000
2022-08-06 16:32:16,661 epoch 9 - iter 674/3375 - loss 0.06638022 - samples/sec: 46.62 - lr: 0.100000
2022-08-06 16:33:15,745 epoch 9 - iter 1011/3375 - loss 0.06547021 - samples/sec: 45.65 - lr: 0.100000
2022-08-06 16:34:14,632 epoch 9 - iter 1348/3375 - loss 0.06593581 - samples/sec: 45.81 - lr: 0.100000
2022-08-06 16:35:13,668 epoch 9 - iter 1685/3375 - loss 0.06772817 - samples/sec: 45.69 - lr: 0.100000
2022-08-06 16:36:15,567 epoch 9 - iter 2022/3375 - loss 0.06808051 - samples/sec: 43.58 - lr: 0.100000
2022-08-06 16:37:16,651 epoch 9 - iter 2359/3375 - loss 0.06796916 - samples/sec: 44.16 - lr: 0.100000
2022-08-06 16:38:14,513 epoch 9 - iter 2696/3375 - loss 0.06906572 - samples/sec: 46.62 - lr: 0.100000
2022-08-06 16:39:13,107 epoch 9 - iter 3033/3375 - loss 0.06917054 - samples/sec: 46.03 - lr: 0.100000
2022-08-06 16:40:12,475 epoch 9 - iter 3370/3375 - loss 0.06913866 - samples/sec: 45.43 - lr: 0.100000
2022-08-06 16:40:13,344 ----------------------------------------------------------------------------------------------------
2022-08-06 16:40:13,344 EPOCH 9 done: loss 0.0691 - lr 0.1000000
2022-08-06 16:40:13,344 BAD EPOCHS (no improvement): 0
2022-08-06 16:40:13,345 ----------------------------------------------------------------------------------------------------
2022-08-06 16:41:11,629 epoch 10 - iter 337/3375 - loss 0.05727560 - samples/sec: 46.28 - lr: 0.100000
2022-08-06 16:42:09,047 epoch 10 - iter 674/3375 - loss 0.06063155 - samples/sec: 46.98 - lr: 0.100000
2022-08-06 16:43:09,515 epoch 10 - iter 1011/3375 - loss 0.06369582 - samples/sec: 44.61 - lr: 0.100000
2022-08-06 16:44:07,978 epoch 10 - iter 1348/3375 - loss 0.06421773 - samples/sec: 46.14 - lr: 0.100000
2022-08-06 16:45:07,015 epoch 10 - iter 1685/3375 - loss 0.06397856 - samples/sec: 45.69 - lr: 0.100000
2022-08-06 16:46:05,736 epoch 10 - iter 2022/3375 - loss 0.06424947 - samples/sec: 45.93 - lr: 0.100000
2022-08-06 16:47:06,945 epoch 10 - iter 2359/3375 - loss 0.06511606 - samples/sec: 44.07 - lr: 0.100000
2022-08-06 16:48:05,819 epoch 10 - iter 2696/3375 - loss 0.06574495 - samples/sec: 45.82 - lr: 0.100000
2022-08-06 16:49:03,924 epoch 10 - iter 3033/3375 - loss 0.06552271 - samples/sec: 46.42 - lr: 0.100000
2022-08-06 16:50:00,641 epoch 10 - iter 3370/3375 - loss 0.06594147 - samples/sec: 47.56 - lr: 0.100000
2022-08-06 16:50:01,493 ----------------------------------------------------------------------------------------------------
2022-08-06 16:50:01,493 EPOCH 10 done: loss 0.0659 - lr 0.1000000
2022-08-06 16:50:01,493 BAD EPOCHS (no improvement): 0
2022-08-06 16:50:02,708 ----------------------------------------------------------------------------------------------------
2022-08-06 16:50:02,709 Testing using last state of model ...
2022-08-06 16:53:40,214 0.9632	0.9632	0.9632	0.9632
2022-08-06 16:53:40,215 
Results:
- F-score (micro) 0.9632
- F-score (macro) 0.9031
- Accuracy 0.9632

By class:
              precision    recall  f1-score   support

      N_SING     0.9691    0.9565    0.9627     30553
           P     0.9560    0.9937    0.9745      9951
        DELM     0.9936    0.9906    0.9921      8122
         ADJ     0.9205    0.9152    0.9179      7466
         CON     0.9892    0.9799    0.9845      6823
        N_PL     0.9476    0.9642    0.9558      5163
        V_PA     0.9729    0.9746    0.9737      2873
       V_PRS     0.9825    0.9898    0.9861      2841
         PRO     0.9656    0.9455    0.9555      2258
         NUM     0.9937    0.9933    0.9935      2232
         DET     0.9423    0.9698    0.9559      1853
      CLITIC     0.9992    1.0000    0.9996      1259
        V_PP     0.9699    0.9741    0.9720      1158
       V_SUB     0.9620    0.9573    0.9596      1031
         ADV     0.7784    0.8182    0.7978       880
    ADV_TIME     0.9126    0.9611    0.9363       489
       V_AUX     0.9869    0.9974    0.9921       379
     ADJ_SUP     0.9851    0.9815    0.9833       270
    ADJ_CMPR     0.9246    0.9534    0.9388       193
     ADJ_INO     0.7294    0.7381    0.7337       168
     ADV_NEG     0.9034    0.8792    0.8912       149
       ADV_I     0.8926    0.7714    0.8276       140
          FW     0.6893    0.5772    0.6283       123
    ADV_COMP     0.8267    0.8158    0.8212        76
     ADV_LOC     0.9722    0.9589    0.9655        73
       V_IMP     0.7292    0.6250    0.6731        56
        PREV     0.9286    0.8125    0.8667        32
         INT     0.9231    0.5000    0.6486        24

   micro avg     0.9632    0.9632    0.9632     86635
   macro avg     0.9195    0.8926    0.9031     86635
weighted avg     0.9633    0.9632    0.9631     86635
 samples avg     0.9632    0.9632    0.9632     86635

2022-08-06 16:53:40,215 ----------------------------------------------------------------------------------------------------