pos-french-camembert-flair / training.log

Update model

75f7dd8 almost 3 years ago

96.5 kB

	2021-12-31 08:35:07,676 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,680 Model: "SequenceTagger(
	(embeddings): StackedEmbeddings(
	(list_embedding_0): FlairEmbeddings(
	(lm): LanguageModel(
	(drop): Dropout(p=0.5, inplace=False)
	(encoder): Embedding(275, 100)
	(rnn): LSTM(100, 1024)
	(decoder): Linear(in_features=1024, out_features=275, bias=True)
	)
	)
	(list_embedding_1): FlairEmbeddings(
	(lm): LanguageModel(
	(drop): Dropout(p=0.5, inplace=False)
	(encoder): Embedding(275, 100)
	(rnn): LSTM(100, 1024)
	(decoder): Linear(in_features=1024, out_features=275, bias=True)
	)
	)
	(list_embedding_2): TransformerWordEmbeddings(
	(model): CamembertModel(
	(embeddings): RobertaEmbeddings(
	(word_embeddings): Embedding(32005, 768, padding_idx=1)
	(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): RobertaEncoder(
	(layer): ModuleList(
	(0): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaLayer(
	(attention): RobertaAttention(
	(self): RobertaSelfAttention(
	(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): RobertaSelfOutput(
	(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): RobertaIntermediate(
	(dense): Linear(in_features=768, out_features=3072, bias=True)
	)
	(output): RobertaOutput(
	(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): RobertaPooler(
	(dense): Linear(in_features=768, out_features=768, bias=True)
	(activation): Tanh()
	)
	)
	)
	)
	(word_dropout): WordDropout(p=0.05)
	(locked_dropout): LockedDropout(p=0.5)
	(embedding2nn): Linear(in_features=2816, out_features=2816, bias=True)
	(rnn): LSTM(2816, 256, batch_first=True, bidirectional=True)
	(linear): Linear(in_features=512, out_features=68, bias=True)
	(beta): 1.0
	(weights): None
	(weight_tensor) None
	)"
	2021-12-31 08:35:07,680 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,681 Corpus: "Corpus: 14449 train + 1476 dev + 416 test sentences"
	2021-12-31 08:35:07,681 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,681 Parameters:
	2021-12-31 08:35:07,681 - learning_rate: "0.1"
	2021-12-31 08:35:07,681 - mini_batch_size: "8"
	2021-12-31 08:35:07,681 - patience: "3"
	2021-12-31 08:35:07,681 - anneal_factor: "0.5"
	2021-12-31 08:35:07,681 - max_epochs: "50"
	2021-12-31 08:35:07,681 - shuffle: "True"
	2021-12-31 08:35:07,681 - train_with_dev: "False"
	2021-12-31 08:35:07,681 - batch_growth_annealing: "False"
	2021-12-31 08:35:07,681 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,681 Model training base path: "models/UPOS_UD_FRENCH_GSD_PLUS_Flair-Embeddings_50_2021-12-31-08:34:44"
	2021-12-31 08:35:07,681 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,682 Device: cuda:0
	2021-12-31 08:35:07,682 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:07,682 Embeddings storage mode: cpu
	2021-12-31 08:35:07,686 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:35:35,600 epoch 1 - iter 180/1807 - loss 1.43338722 - samples/sec: 51.63 - lr: 0.100000
	2021-12-31 08:36:03,642 epoch 1 - iter 360/1807 - loss 0.97278560 - samples/sec: 51.39 - lr: 0.100000
	2021-12-31 08:36:31,448 epoch 1 - iter 540/1807 - loss 0.77628898 - samples/sec: 51.83 - lr: 0.100000
	2021-12-31 08:37:00,007 epoch 1 - iter 720/1807 - loss 0.66122431 - samples/sec: 50.46 - lr: 0.100000
	2021-12-31 08:37:29,449 epoch 1 - iter 900/1807 - loss 0.58637716 - samples/sec: 48.94 - lr: 0.100000
	2021-12-31 08:37:57,842 epoch 1 - iter 1080/1807 - loss 0.53261867 - samples/sec: 50.75 - lr: 0.100000
	2021-12-31 08:38:27,836 epoch 1 - iter 1260/1807 - loss 0.49236809 - samples/sec: 48.04 - lr: 0.100000
	2021-12-31 08:38:56,177 epoch 1 - iter 1440/1807 - loss 0.46224064 - samples/sec: 50.84 - lr: 0.100000
	2021-12-31 08:39:25,301 epoch 1 - iter 1620/1807 - loss 0.43700232 - samples/sec: 49.48 - lr: 0.100000
	2021-12-31 08:39:53,843 epoch 1 - iter 1800/1807 - loss 0.41459922 - samples/sec: 50.49 - lr: 0.100000
	2021-12-31 08:39:54,850 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:39:54,851 EPOCH 1 done: loss 0.4139 - lr 0.1000000
	2021-12-31 08:40:38,186 DEV : loss 0.09867297857999802 - f1-score (micro avg) 0.9723
	2021-12-31 08:40:38,373 BAD EPOCHS (no improvement): 0
	2021-12-31 08:40:38,375 saving best model
	2021-12-31 08:40:43,945 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:40:59,809 epoch 2 - iter 180/1807 - loss 0.20282785 - samples/sec: 90.92 - lr: 0.100000
	2021-12-31 08:41:15,798 epoch 2 - iter 360/1807 - loss 0.20600484 - samples/sec: 90.20 - lr: 0.100000
	2021-12-31 08:41:31,824 epoch 2 - iter 540/1807 - loss 0.20352355 - samples/sec: 89.99 - lr: 0.100000
	2021-12-31 08:41:47,291 epoch 2 - iter 720/1807 - loss 0.19945298 - samples/sec: 93.24 - lr: 0.100000
	2021-12-31 08:42:03,389 epoch 2 - iter 900/1807 - loss 0.19672769 - samples/sec: 89.58 - lr: 0.100000
	2021-12-31 08:42:19,546 epoch 2 - iter 1080/1807 - loss 0.19404584 - samples/sec: 89.25 - lr: 0.100000
	2021-12-31 08:42:35,186 epoch 2 - iter 1260/1807 - loss 0.19211776 - samples/sec: 92.22 - lr: 0.100000
	2021-12-31 08:42:51,014 epoch 2 - iter 1440/1807 - loss 0.19040930 - samples/sec: 91.11 - lr: 0.100000
	2021-12-31 08:43:07,108 epoch 2 - iter 1620/1807 - loss 0.18835936 - samples/sec: 89.60 - lr: 0.100000
	2021-12-31 08:43:22,664 epoch 2 - iter 1800/1807 - loss 0.18684498 - samples/sec: 92.71 - lr: 0.100000
	2021-12-31 08:43:23,166 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:43:23,166 EPOCH 2 done: loss 0.1868 - lr 0.1000000
	2021-12-31 08:43:59,411 DEV : loss 0.08219591528177261 - f1-score (micro avg) 0.9761
	2021-12-31 08:43:59,601 BAD EPOCHS (no improvement): 0
	2021-12-31 08:43:59,602 saving best model
	2021-12-31 08:44:04,994 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:44:21,188 epoch 3 - iter 180/1807 - loss 0.16248988 - samples/sec: 89.06 - lr: 0.100000
	2021-12-31 08:44:37,143 epoch 3 - iter 360/1807 - loss 0.16012805 - samples/sec: 90.38 - lr: 0.100000
	2021-12-31 08:44:53,240 epoch 3 - iter 540/1807 - loss 0.15771573 - samples/sec: 89.59 - lr: 0.100000
	2021-12-31 08:45:08,820 epoch 3 - iter 720/1807 - loss 0.15678918 - samples/sec: 92.57 - lr: 0.100000
	2021-12-31 08:45:24,447 epoch 3 - iter 900/1807 - loss 0.15583330 - samples/sec: 92.28 - lr: 0.100000
	2021-12-31 08:45:40,453 epoch 3 - iter 1080/1807 - loss 0.15551694 - samples/sec: 90.10 - lr: 0.100000
	2021-12-31 08:45:56,421 epoch 3 - iter 1260/1807 - loss 0.15503272 - samples/sec: 90.32 - lr: 0.100000
	2021-12-31 08:46:12,207 epoch 3 - iter 1440/1807 - loss 0.15478837 - samples/sec: 91.35 - lr: 0.100000
	2021-12-31 08:46:28,067 epoch 3 - iter 1620/1807 - loss 0.15437671 - samples/sec: 90.93 - lr: 0.100000
	2021-12-31 08:46:44,096 epoch 3 - iter 1800/1807 - loss 0.15334210 - samples/sec: 89.96 - lr: 0.100000
	2021-12-31 08:46:44,638 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:46:44,638 EPOCH 3 done: loss 0.1533 - lr 0.1000000
	2021-12-31 08:47:19,364 DEV : loss 0.07821641117334366 - f1-score (micro avg) 0.9771
	2021-12-31 08:47:19,574 BAD EPOCHS (no improvement): 0
	2021-12-31 08:47:19,576 saving best model
	2021-12-31 08:47:25,807 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:47:42,295 epoch 4 - iter 180/1807 - loss 0.14078583 - samples/sec: 87.48 - lr: 0.100000
	2021-12-31 08:47:58,394 epoch 4 - iter 360/1807 - loss 0.14084079 - samples/sec: 89.58 - lr: 0.100000
	2021-12-31 08:48:14,377 epoch 4 - iter 540/1807 - loss 0.13969043 - samples/sec: 90.22 - lr: 0.100000
	2021-12-31 08:48:30,411 epoch 4 - iter 720/1807 - loss 0.13901425 - samples/sec: 89.95 - lr: 0.100000
	2021-12-31 08:48:45,985 epoch 4 - iter 900/1807 - loss 0.13965987 - samples/sec: 92.60 - lr: 0.100000
	2021-12-31 08:49:01,706 epoch 4 - iter 1080/1807 - loss 0.13942263 - samples/sec: 91.73 - lr: 0.100000
	2021-12-31 08:49:17,833 epoch 4 - iter 1260/1807 - loss 0.13931213 - samples/sec: 89.42 - lr: 0.100000
	2021-12-31 08:49:33,693 epoch 4 - iter 1440/1807 - loss 0.13835426 - samples/sec: 90.94 - lr: 0.100000
	2021-12-31 08:49:49,444 epoch 4 - iter 1620/1807 - loss 0.13722078 - samples/sec: 91.56 - lr: 0.100000
	2021-12-31 08:50:05,233 epoch 4 - iter 1800/1807 - loss 0.13680325 - samples/sec: 91.33 - lr: 0.100000
	2021-12-31 08:50:05,825 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:50:05,826 EPOCH 4 done: loss 0.1368 - lr 0.1000000
	2021-12-31 08:50:40,951 DEV : loss 0.07048774510622025 - f1-score (micro avg) 0.9784
	2021-12-31 08:50:41,121 BAD EPOCHS (no improvement): 0
	2021-12-31 08:50:41,123 saving best model
	2021-12-31 08:50:46,985 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:51:03,480 epoch 5 - iter 180/1807 - loss 0.12576483 - samples/sec: 87.44 - lr: 0.100000
	2021-12-31 08:51:19,312 epoch 5 - iter 360/1807 - loss 0.12838224 - samples/sec: 91.10 - lr: 0.100000
	2021-12-31 08:51:35,140 epoch 5 - iter 540/1807 - loss 0.13027925 - samples/sec: 91.11 - lr: 0.100000
	2021-12-31 08:51:51,382 epoch 5 - iter 720/1807 - loss 0.13001079 - samples/sec: 88.78 - lr: 0.100000
	2021-12-31 08:52:07,009 epoch 5 - iter 900/1807 - loss 0.12990639 - samples/sec: 92.28 - lr: 0.100000
	2021-12-31 08:52:22,749 epoch 5 - iter 1080/1807 - loss 0.12927608 - samples/sec: 91.63 - lr: 0.100000
	2021-12-31 08:52:38,459 epoch 5 - iter 1260/1807 - loss 0.12839810 - samples/sec: 91.79 - lr: 0.100000
	2021-12-31 08:52:54,183 epoch 5 - iter 1440/1807 - loss 0.12750076 - samples/sec: 91.71 - lr: 0.100000
	2021-12-31 08:53:09,782 epoch 5 - iter 1620/1807 - loss 0.12744081 - samples/sec: 92.45 - lr: 0.100000
	2021-12-31 08:53:26,181 epoch 5 - iter 1800/1807 - loss 0.12697954 - samples/sec: 87.94 - lr: 0.100000
	2021-12-31 08:53:26,718 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:53:26,718 EPOCH 5 done: loss 0.1270 - lr 0.1000000
	2021-12-31 08:54:05,303 DEV : loss 0.06857253611087799 - f1-score (micro avg) 0.9795
	2021-12-31 08:54:05,490 BAD EPOCHS (no improvement): 0
	2021-12-31 08:54:05,491 saving best model
	2021-12-31 08:54:11,317 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:54:27,729 epoch 6 - iter 180/1807 - loss 0.12012197 - samples/sec: 87.88 - lr: 0.100000
	2021-12-31 08:54:43,570 epoch 6 - iter 360/1807 - loss 0.12134345 - samples/sec: 91.04 - lr: 0.100000
	2021-12-31 08:54:59,298 epoch 6 - iter 540/1807 - loss 0.12010472 - samples/sec: 91.70 - lr: 0.100000
	2021-12-31 08:55:14,710 epoch 6 - iter 720/1807 - loss 0.11985671 - samples/sec: 93.58 - lr: 0.100000
	2021-12-31 08:55:30,873 epoch 6 - iter 900/1807 - loss 0.12032070 - samples/sec: 89.22 - lr: 0.100000
	2021-12-31 08:55:46,705 epoch 6 - iter 1080/1807 - loss 0.11976455 - samples/sec: 91.08 - lr: 0.100000
	2021-12-31 08:56:02,915 epoch 6 - iter 1260/1807 - loss 0.11964832 - samples/sec: 88.97 - lr: 0.100000
	2021-12-31 08:56:18,616 epoch 6 - iter 1440/1807 - loss 0.11958148 - samples/sec: 91.86 - lr: 0.100000
	2021-12-31 08:56:34,478 epoch 6 - iter 1620/1807 - loss 0.12003314 - samples/sec: 90.91 - lr: 0.100000
	2021-12-31 08:56:50,548 epoch 6 - iter 1800/1807 - loss 0.11950787 - samples/sec: 89.75 - lr: 0.100000
	2021-12-31 08:56:51,070 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:56:51,070 EPOCH 6 done: loss 0.1195 - lr 0.1000000
	2021-12-31 08:57:26,881 DEV : loss 0.06588418781757355 - f1-score (micro avg) 0.9805
	2021-12-31 08:57:27,077 BAD EPOCHS (no improvement): 0
	2021-12-31 08:57:27,079 saving best model
	2021-12-31 08:57:32,878 ----------------------------------------------------------------------------------------------------
	2021-12-31 08:57:49,222 epoch 7 - iter 180/1807 - loss 0.11622596 - samples/sec: 88.27 - lr: 0.100000
	2021-12-31 08:58:05,154 epoch 7 - iter 360/1807 - loss 0.11182908 - samples/sec: 90.52 - lr: 0.100000
	2021-12-31 08:58:21,316 epoch 7 - iter 540/1807 - loss 0.11325284 - samples/sec: 89.23 - lr: 0.100000
	2021-12-31 08:58:37,501 epoch 7 - iter 720/1807 - loss 0.11356510 - samples/sec: 89.11 - lr: 0.100000
	2021-12-31 08:58:53,437 epoch 7 - iter 900/1807 - loss 0.11375009 - samples/sec: 90.50 - lr: 0.100000
	2021-12-31 08:59:09,683 epoch 7 - iter 1080/1807 - loss 0.11424006 - samples/sec: 88.76 - lr: 0.100000
	2021-12-31 08:59:25,513 epoch 7 - iter 1260/1807 - loss 0.11502991 - samples/sec: 91.10 - lr: 0.100000
	2021-12-31 08:59:41,355 epoch 7 - iter 1440/1807 - loss 0.11465724 - samples/sec: 91.04 - lr: 0.100000
	2021-12-31 08:59:57,048 epoch 7 - iter 1620/1807 - loss 0.11489345 - samples/sec: 91.91 - lr: 0.100000
	2021-12-31 09:00:13,626 epoch 7 - iter 1800/1807 - loss 0.11495780 - samples/sec: 86.99 - lr: 0.100000
	2021-12-31 09:00:14,225 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:00:14,225 EPOCH 7 done: loss 0.1149 - lr 0.1000000
	2021-12-31 09:00:50,356 DEV : loss 0.06450950354337692 - f1-score (micro avg) 0.981
	2021-12-31 09:00:50,566 BAD EPOCHS (no improvement): 0
	2021-12-31 09:00:50,572 saving best model
	2021-12-31 09:00:56,353 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:01:12,703 epoch 8 - iter 180/1807 - loss 0.10372694 - samples/sec: 88.23 - lr: 0.100000
	2021-12-31 09:01:28,785 epoch 8 - iter 360/1807 - loss 0.10507104 - samples/sec: 89.68 - lr: 0.100000
	2021-12-31 09:01:45,134 epoch 8 - iter 540/1807 - loss 0.10666062 - samples/sec: 88.21 - lr: 0.100000
	2021-12-31 09:02:01,507 epoch 8 - iter 720/1807 - loss 0.10750728 - samples/sec: 88.08 - lr: 0.100000
	2021-12-31 09:02:17,626 epoch 8 - iter 900/1807 - loss 0.10760637 - samples/sec: 89.47 - lr: 0.100000
	2021-12-31 09:02:33,374 epoch 8 - iter 1080/1807 - loss 0.10788257 - samples/sec: 91.58 - lr: 0.100000
	2021-12-31 09:02:49,200 epoch 8 - iter 1260/1807 - loss 0.10808589 - samples/sec: 91.12 - lr: 0.100000
	2021-12-31 09:03:05,738 epoch 8 - iter 1440/1807 - loss 0.10815170 - samples/sec: 87.20 - lr: 0.100000
	2021-12-31 09:03:21,442 epoch 8 - iter 1620/1807 - loss 0.10840840 - samples/sec: 91.84 - lr: 0.100000
	2021-12-31 09:03:37,709 epoch 8 - iter 1800/1807 - loss 0.10855634 - samples/sec: 88.66 - lr: 0.100000
	2021-12-31 09:03:38,280 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:03:38,280 EPOCH 8 done: loss 0.1086 - lr 0.1000000
	2021-12-31 09:04:17,043 DEV : loss 0.06390747427940369 - f1-score (micro avg) 0.9805
	2021-12-31 09:04:17,194 BAD EPOCHS (no improvement): 1
	2021-12-31 09:04:17,196 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:04:33,331 epoch 9 - iter 180/1807 - loss 0.10260778 - samples/sec: 89.39 - lr: 0.100000
	2021-12-31 09:04:49,336 epoch 9 - iter 360/1807 - loss 0.10566575 - samples/sec: 90.11 - lr: 0.100000
	2021-12-31 09:05:05,083 epoch 9 - iter 540/1807 - loss 0.10556216 - samples/sec: 91.59 - lr: 0.100000
	2021-12-31 09:05:21,004 epoch 9 - iter 720/1807 - loss 0.10506801 - samples/sec: 90.58 - lr: 0.100000
	2021-12-31 09:05:37,109 epoch 9 - iter 900/1807 - loss 0.10596338 - samples/sec: 89.54 - lr: 0.100000
	2021-12-31 09:05:52,784 epoch 9 - iter 1080/1807 - loss 0.10577668 - samples/sec: 92.02 - lr: 0.100000
	2021-12-31 09:06:08,937 epoch 9 - iter 1260/1807 - loss 0.10613509 - samples/sec: 89.28 - lr: 0.100000
	2021-12-31 09:06:24,601 epoch 9 - iter 1440/1807 - loss 0.10637150 - samples/sec: 92.06 - lr: 0.100000
	2021-12-31 09:06:40,409 epoch 9 - iter 1620/1807 - loss 0.10629708 - samples/sec: 91.23 - lr: 0.100000
	2021-12-31 09:06:55,972 epoch 9 - iter 1800/1807 - loss 0.10610710 - samples/sec: 92.67 - lr: 0.100000
	2021-12-31 09:06:56,557 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:06:56,557 EPOCH 9 done: loss 0.1061 - lr 0.1000000
	2021-12-31 09:07:32,784 DEV : loss 0.06607701629400253 - f1-score (micro avg) 0.9814
	2021-12-31 09:07:32,970 BAD EPOCHS (no improvement): 0
	2021-12-31 09:07:32,972 saving best model
	2021-12-31 09:07:38,755 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:07:55,004 epoch 10 - iter 180/1807 - loss 0.10366226 - samples/sec: 88.76 - lr: 0.100000
	2021-12-31 09:08:11,104 epoch 10 - iter 360/1807 - loss 0.10828055 - samples/sec: 89.58 - lr: 0.100000
	2021-12-31 09:08:26,748 epoch 10 - iter 540/1807 - loss 0.10589800 - samples/sec: 92.20 - lr: 0.100000
	2021-12-31 09:08:42,772 epoch 10 - iter 720/1807 - loss 0.10467961 - samples/sec: 90.00 - lr: 0.100000
	2021-12-31 09:08:58,992 epoch 10 - iter 900/1807 - loss 0.10355149 - samples/sec: 88.91 - lr: 0.100000
	2021-12-31 09:09:14,753 epoch 10 - iter 1080/1807 - loss 0.10313717 - samples/sec: 91.50 - lr: 0.100000
	2021-12-31 09:09:30,631 epoch 10 - iter 1260/1807 - loss 0.10353533 - samples/sec: 90.84 - lr: 0.100000
	2021-12-31 09:09:46,654 epoch 10 - iter 1440/1807 - loss 0.10386166 - samples/sec: 90.02 - lr: 0.100000
	2021-12-31 09:10:02,791 epoch 10 - iter 1620/1807 - loss 0.10346798 - samples/sec: 89.36 - lr: 0.100000
	2021-12-31 09:10:18,970 epoch 10 - iter 1800/1807 - loss 0.10358051 - samples/sec: 89.14 - lr: 0.100000
	2021-12-31 09:10:19,492 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:10:19,492 EPOCH 10 done: loss 0.1036 - lr 0.1000000
	2021-12-31 09:10:55,557 DEV : loss 0.06536506861448288 - f1-score (micro avg) 0.9811
	2021-12-31 09:10:55,753 BAD EPOCHS (no improvement): 1
	2021-12-31 09:10:55,756 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:11:12,024 epoch 11 - iter 180/1807 - loss 0.10182872 - samples/sec: 88.66 - lr: 0.100000
	2021-12-31 09:11:28,246 epoch 11 - iter 360/1807 - loss 0.10175535 - samples/sec: 88.90 - lr: 0.100000
	2021-12-31 09:11:43,844 epoch 11 - iter 540/1807 - loss 0.10107946 - samples/sec: 92.46 - lr: 0.100000
	2021-12-31 09:11:59,559 epoch 11 - iter 720/1807 - loss 0.10053922 - samples/sec: 91.77 - lr: 0.100000
	2021-12-31 09:12:15,490 epoch 11 - iter 900/1807 - loss 0.10047028 - samples/sec: 90.54 - lr: 0.100000
	2021-12-31 09:12:31,195 epoch 11 - iter 1080/1807 - loss 0.09993958 - samples/sec: 91.82 - lr: 0.100000
	2021-12-31 09:12:47,013 epoch 11 - iter 1260/1807 - loss 0.09996914 - samples/sec: 91.17 - lr: 0.100000
	2021-12-31 09:13:03,156 epoch 11 - iter 1440/1807 - loss 0.09980985 - samples/sec: 89.35 - lr: 0.100000
	2021-12-31 09:13:18,852 epoch 11 - iter 1620/1807 - loss 0.09941318 - samples/sec: 91.88 - lr: 0.100000
	2021-12-31 09:13:35,014 epoch 11 - iter 1800/1807 - loss 0.09934768 - samples/sec: 89.23 - lr: 0.100000
	2021-12-31 09:13:35,650 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:13:35,650 EPOCH 11 done: loss 0.0993 - lr 0.1000000
	2021-12-31 09:14:14,419 DEV : loss 0.06659943610429764 - f1-score (micro avg) 0.9811
	2021-12-31 09:14:14,622 BAD EPOCHS (no improvement): 2
	2021-12-31 09:14:14,623 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:14:30,892 epoch 12 - iter 180/1807 - loss 0.09334718 - samples/sec: 88.66 - lr: 0.100000
	2021-12-31 09:14:46,737 epoch 12 - iter 360/1807 - loss 0.09477923 - samples/sec: 91.02 - lr: 0.100000
	2021-12-31 09:15:02,926 epoch 12 - iter 540/1807 - loss 0.09677398 - samples/sec: 89.09 - lr: 0.100000
	2021-12-31 09:15:19,177 epoch 12 - iter 720/1807 - loss 0.09825518 - samples/sec: 88.74 - lr: 0.100000
	2021-12-31 09:15:34,958 epoch 12 - iter 900/1807 - loss 0.09910665 - samples/sec: 91.38 - lr: 0.100000
	2021-12-31 09:15:51,056 epoch 12 - iter 1080/1807 - loss 0.09820501 - samples/sec: 89.59 - lr: 0.100000
	2021-12-31 09:16:07,231 epoch 12 - iter 1260/1807 - loss 0.09858638 - samples/sec: 89.16 - lr: 0.100000
	2021-12-31 09:16:22,988 epoch 12 - iter 1440/1807 - loss 0.09845736 - samples/sec: 91.52 - lr: 0.100000
	2021-12-31 09:16:38,631 epoch 12 - iter 1620/1807 - loss 0.09859390 - samples/sec: 92.21 - lr: 0.100000
	2021-12-31 09:16:54,209 epoch 12 - iter 1800/1807 - loss 0.09847298 - samples/sec: 92.58 - lr: 0.100000
	2021-12-31 09:16:54,729 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:16:54,730 EPOCH 12 done: loss 0.0984 - lr 0.1000000
	2021-12-31 09:17:31,308 DEV : loss 0.06410104781389236 - f1-score (micro avg) 0.9816
	2021-12-31 09:17:31,487 BAD EPOCHS (no improvement): 0
	2021-12-31 09:17:31,489 saving best model
	2021-12-31 09:17:37,260 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:17:54,060 epoch 13 - iter 180/1807 - loss 0.10013605 - samples/sec: 85.86 - lr: 0.100000
	2021-12-31 09:18:09,827 epoch 13 - iter 360/1807 - loss 0.09881566 - samples/sec: 91.47 - lr: 0.100000
	2021-12-31 09:18:25,218 epoch 13 - iter 540/1807 - loss 0.09860664 - samples/sec: 93.71 - lr: 0.100000
	2021-12-31 09:18:41,246 epoch 13 - iter 720/1807 - loss 0.09768065 - samples/sec: 89.97 - lr: 0.100000
	2021-12-31 09:18:57,306 epoch 13 - iter 900/1807 - loss 0.09766501 - samples/sec: 89.79 - lr: 0.100000
	2021-12-31 09:19:12,914 epoch 13 - iter 1080/1807 - loss 0.09767968 - samples/sec: 92.41 - lr: 0.100000
	2021-12-31 09:19:29,144 epoch 13 - iter 1260/1807 - loss 0.09667902 - samples/sec: 88.86 - lr: 0.100000
	2021-12-31 09:19:45,573 epoch 13 - iter 1440/1807 - loss 0.09670686 - samples/sec: 87.78 - lr: 0.100000
	2021-12-31 09:20:01,566 epoch 13 - iter 1620/1807 - loss 0.09672936 - samples/sec: 90.18 - lr: 0.100000
	2021-12-31 09:20:17,572 epoch 13 - iter 1800/1807 - loss 0.09666135 - samples/sec: 90.10 - lr: 0.100000
	2021-12-31 09:20:18,200 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:20:18,200 EPOCH 13 done: loss 0.0967 - lr 0.1000000
	2021-12-31 09:20:54,147 DEV : loss 0.06427688896656036 - f1-score (micro avg) 0.9816
	2021-12-31 09:20:54,334 BAD EPOCHS (no improvement): 1
	2021-12-31 09:20:54,335 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:21:10,174 epoch 14 - iter 180/1807 - loss 0.09391481 - samples/sec: 91.06 - lr: 0.100000
	2021-12-31 09:21:26,400 epoch 14 - iter 360/1807 - loss 0.09267418 - samples/sec: 88.88 - lr: 0.100000
	2021-12-31 09:21:42,313 epoch 14 - iter 540/1807 - loss 0.09273735 - samples/sec: 90.64 - lr: 0.100000
	2021-12-31 09:21:58,477 epoch 14 - iter 720/1807 - loss 0.09237732 - samples/sec: 89.22 - lr: 0.100000
	2021-12-31 09:22:14,088 epoch 14 - iter 900/1807 - loss 0.09290387 - samples/sec: 92.38 - lr: 0.100000
	2021-12-31 09:22:29,793 epoch 14 - iter 1080/1807 - loss 0.09305725 - samples/sec: 91.82 - lr: 0.100000
	2021-12-31 09:22:45,455 epoch 14 - iter 1260/1807 - loss 0.09321173 - samples/sec: 92.09 - lr: 0.100000
	2021-12-31 09:23:01,412 epoch 14 - iter 1440/1807 - loss 0.09321459 - samples/sec: 90.38 - lr: 0.100000
	2021-12-31 09:23:17,629 epoch 14 - iter 1620/1807 - loss 0.09332877 - samples/sec: 88.93 - lr: 0.100000
	2021-12-31 09:23:33,527 epoch 14 - iter 1800/1807 - loss 0.09313892 - samples/sec: 90.71 - lr: 0.100000
	2021-12-31 09:23:34,165 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:23:34,165 EPOCH 14 done: loss 0.0931 - lr 0.1000000
	2021-12-31 09:24:12,840 DEV : loss 0.06639766693115234 - f1-score (micro avg) 0.9817
	2021-12-31 09:24:13,034 BAD EPOCHS (no improvement): 0
	2021-12-31 09:24:13,036 saving best model
	2021-12-31 09:24:18,822 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:24:34,568 epoch 15 - iter 180/1807 - loss 0.09134784 - samples/sec: 91.60 - lr: 0.100000
	2021-12-31 09:24:50,712 epoch 15 - iter 360/1807 - loss 0.09119751 - samples/sec: 89.33 - lr: 0.100000
	2021-12-31 09:25:07,155 epoch 15 - iter 540/1807 - loss 0.08993505 - samples/sec: 87.70 - lr: 0.100000
	2021-12-31 09:25:23,092 epoch 15 - iter 720/1807 - loss 0.09062331 - samples/sec: 90.50 - lr: 0.100000
	2021-12-31 09:25:39,643 epoch 15 - iter 900/1807 - loss 0.09054947 - samples/sec: 87.13 - lr: 0.100000
	2021-12-31 09:25:56,080 epoch 15 - iter 1080/1807 - loss 0.09120586 - samples/sec: 87.73 - lr: 0.100000
	2021-12-31 09:26:12,023 epoch 15 - iter 1260/1807 - loss 0.09202164 - samples/sec: 90.49 - lr: 0.100000
	2021-12-31 09:26:27,452 epoch 15 - iter 1440/1807 - loss 0.09257595 - samples/sec: 93.48 - lr: 0.100000
	2021-12-31 09:26:43,293 epoch 15 - iter 1620/1807 - loss 0.09296868 - samples/sec: 91.04 - lr: 0.100000
	2021-12-31 09:26:59,412 epoch 15 - iter 1800/1807 - loss 0.09272942 - samples/sec: 89.47 - lr: 0.100000
	2021-12-31 09:26:59,991 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:26:59,991 EPOCH 15 done: loss 0.0927 - lr 0.1000000
	2021-12-31 09:27:36,227 DEV : loss 0.06283392012119293 - f1-score (micro avg) 0.982
	2021-12-31 09:27:36,433 BAD EPOCHS (no improvement): 0
	2021-12-31 09:27:36,435 saving best model
	2021-12-31 09:27:42,216 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:27:58,274 epoch 16 - iter 180/1807 - loss 0.08868552 - samples/sec: 89.83 - lr: 0.100000
	2021-12-31 09:28:14,083 epoch 16 - iter 360/1807 - loss 0.08898795 - samples/sec: 91.23 - lr: 0.100000
	2021-12-31 09:28:30,428 epoch 16 - iter 540/1807 - loss 0.08723848 - samples/sec: 88.23 - lr: 0.100000
	2021-12-31 09:28:46,065 epoch 16 - iter 720/1807 - loss 0.08840922 - samples/sec: 92.21 - lr: 0.100000
	2021-12-31 09:29:01,697 epoch 16 - iter 900/1807 - loss 0.08907246 - samples/sec: 92.26 - lr: 0.100000
	2021-12-31 09:29:17,387 epoch 16 - iter 1080/1807 - loss 0.09016391 - samples/sec: 91.91 - lr: 0.100000
	2021-12-31 09:29:33,637 epoch 16 - iter 1260/1807 - loss 0.09090909 - samples/sec: 88.74 - lr: 0.100000
	2021-12-31 09:29:49,596 epoch 16 - iter 1440/1807 - loss 0.09079363 - samples/sec: 90.36 - lr: 0.100000
	2021-12-31 09:30:05,085 epoch 16 - iter 1620/1807 - loss 0.09144623 - samples/sec: 93.12 - lr: 0.100000
	2021-12-31 09:30:21,000 epoch 16 - iter 1800/1807 - loss 0.09062250 - samples/sec: 90.62 - lr: 0.100000
	2021-12-31 09:30:21,608 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:30:21,608 EPOCH 16 done: loss 0.0906 - lr 0.1000000
	2021-12-31 09:30:58,333 DEV : loss 0.06354553997516632 - f1-score (micro avg) 0.982
	2021-12-31 09:30:58,512 BAD EPOCHS (no improvement): 1
	2021-12-31 09:30:58,514 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:31:14,847 epoch 17 - iter 180/1807 - loss 0.08390522 - samples/sec: 88.30 - lr: 0.100000
	2021-12-31 09:31:30,522 epoch 17 - iter 360/1807 - loss 0.08649584 - samples/sec: 92.01 - lr: 0.100000
	2021-12-31 09:31:46,288 epoch 17 - iter 540/1807 - loss 0.08940335 - samples/sec: 91.48 - lr: 0.100000
	2021-12-31 09:32:02,118 epoch 17 - iter 720/1807 - loss 0.09059873 - samples/sec: 91.09 - lr: 0.100000
	2021-12-31 09:32:17,806 epoch 17 - iter 900/1807 - loss 0.09026440 - samples/sec: 91.93 - lr: 0.100000
	2021-12-31 09:32:33,488 epoch 17 - iter 1080/1807 - loss 0.09038711 - samples/sec: 91.96 - lr: 0.100000
	2021-12-31 09:32:49,442 epoch 17 - iter 1260/1807 - loss 0.08978670 - samples/sec: 90.39 - lr: 0.100000
	2021-12-31 09:33:05,170 epoch 17 - iter 1440/1807 - loss 0.08929018 - samples/sec: 91.69 - lr: 0.100000
	2021-12-31 09:33:21,122 epoch 17 - iter 1620/1807 - loss 0.08920206 - samples/sec: 90.40 - lr: 0.100000
	2021-12-31 09:33:36,598 epoch 17 - iter 1800/1807 - loss 0.08958801 - samples/sec: 93.18 - lr: 0.100000
	2021-12-31 09:33:37,149 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:33:37,149 EPOCH 17 done: loss 0.0895 - lr 0.1000000
	2021-12-31 09:34:16,446 DEV : loss 0.06361010670661926 - f1-score (micro avg) 0.9823
	2021-12-31 09:34:16,599 BAD EPOCHS (no improvement): 0
	2021-12-31 09:34:16,600 saving best model
	2021-12-31 09:34:22,434 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:34:38,419 epoch 18 - iter 180/1807 - loss 0.08343062 - samples/sec: 90.22 - lr: 0.100000
	2021-12-31 09:34:54,655 epoch 18 - iter 360/1807 - loss 0.08575852 - samples/sec: 88.82 - lr: 0.100000
	2021-12-31 09:35:10,385 epoch 18 - iter 540/1807 - loss 0.08392644 - samples/sec: 91.68 - lr: 0.100000
	2021-12-31 09:35:26,310 epoch 18 - iter 720/1807 - loss 0.08351999 - samples/sec: 90.57 - lr: 0.100000
	2021-12-31 09:35:41,876 epoch 18 - iter 900/1807 - loss 0.08509375 - samples/sec: 92.64 - lr: 0.100000
	2021-12-31 09:35:57,882 epoch 18 - iter 1080/1807 - loss 0.08493115 - samples/sec: 90.10 - lr: 0.100000
	2021-12-31 09:36:13,926 epoch 18 - iter 1260/1807 - loss 0.08609299 - samples/sec: 89.88 - lr: 0.100000
	2021-12-31 09:36:30,070 epoch 18 - iter 1440/1807 - loss 0.08644835 - samples/sec: 89.34 - lr: 0.100000
	2021-12-31 09:36:45,689 epoch 18 - iter 1620/1807 - loss 0.08698449 - samples/sec: 92.33 - lr: 0.100000
	2021-12-31 09:37:01,595 epoch 18 - iter 1800/1807 - loss 0.08715385 - samples/sec: 90.66 - lr: 0.100000
	2021-12-31 09:37:02,116 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:37:02,116 EPOCH 18 done: loss 0.0872 - lr 0.1000000
	2021-12-31 09:37:38,287 DEV : loss 0.06376409530639648 - f1-score (micro avg) 0.982
	2021-12-31 09:37:38,491 BAD EPOCHS (no improvement): 1
	2021-12-31 09:37:38,492 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:37:54,464 epoch 19 - iter 180/1807 - loss 0.07802257 - samples/sec: 90.31 - lr: 0.100000
	2021-12-31 09:38:10,256 epoch 19 - iter 360/1807 - loss 0.07892620 - samples/sec: 91.32 - lr: 0.100000
	2021-12-31 09:38:26,632 epoch 19 - iter 540/1807 - loss 0.08133170 - samples/sec: 88.06 - lr: 0.100000
	2021-12-31 09:38:42,673 epoch 19 - iter 720/1807 - loss 0.08367885 - samples/sec: 89.91 - lr: 0.100000
	2021-12-31 09:38:58,503 epoch 19 - iter 900/1807 - loss 0.08447871 - samples/sec: 91.11 - lr: 0.100000
	2021-12-31 09:39:14,461 epoch 19 - iter 1080/1807 - loss 0.08413767 - samples/sec: 90.37 - lr: 0.100000
	2021-12-31 09:39:30,176 epoch 19 - iter 1260/1807 - loss 0.08455665 - samples/sec: 91.77 - lr: 0.100000
	2021-12-31 09:39:46,325 epoch 19 - iter 1440/1807 - loss 0.08578599 - samples/sec: 89.30 - lr: 0.100000
	2021-12-31 09:40:02,191 epoch 19 - iter 1620/1807 - loss 0.08628902 - samples/sec: 90.90 - lr: 0.100000
	2021-12-31 09:40:18,069 epoch 19 - iter 1800/1807 - loss 0.08634962 - samples/sec: 90.82 - lr: 0.100000
	2021-12-31 09:40:18,635 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:40:18,636 EPOCH 19 done: loss 0.0863 - lr 0.1000000
	2021-12-31 09:40:54,638 DEV : loss 0.06360483914613724 - f1-score (micro avg) 0.9824
	2021-12-31 09:40:54,809 BAD EPOCHS (no improvement): 0
	2021-12-31 09:40:54,812 saving best model
	2021-12-31 09:41:00,532 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:41:16,605 epoch 20 - iter 180/1807 - loss 0.08580796 - samples/sec: 89.75 - lr: 0.100000
	2021-12-31 09:41:32,626 epoch 20 - iter 360/1807 - loss 0.08441046 - samples/sec: 90.02 - lr: 0.100000
	2021-12-31 09:41:48,195 epoch 20 - iter 540/1807 - loss 0.08457436 - samples/sec: 92.63 - lr: 0.100000
	2021-12-31 09:42:03,884 epoch 20 - iter 720/1807 - loss 0.08433505 - samples/sec: 91.92 - lr: 0.100000
	2021-12-31 09:42:19,662 epoch 20 - iter 900/1807 - loss 0.08465375 - samples/sec: 91.40 - lr: 0.100000
	2021-12-31 09:42:35,290 epoch 20 - iter 1080/1807 - loss 0.08384813 - samples/sec: 92.28 - lr: 0.100000
	2021-12-31 09:42:50,667 epoch 20 - iter 1260/1807 - loss 0.08437448 - samples/sec: 93.79 - lr: 0.100000
	2021-12-31 09:43:06,838 epoch 20 - iter 1440/1807 - loss 0.08483000 - samples/sec: 89.18 - lr: 0.100000
	2021-12-31 09:43:23,128 epoch 20 - iter 1620/1807 - loss 0.08554680 - samples/sec: 88.52 - lr: 0.100000
	2021-12-31 09:43:38,996 epoch 20 - iter 1800/1807 - loss 0.08579345 - samples/sec: 90.89 - lr: 0.100000
	2021-12-31 09:43:39,520 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:43:39,520 EPOCH 20 done: loss 0.0858 - lr 0.1000000
	2021-12-31 09:44:18,433 DEV : loss 0.06494450569152832 - f1-score (micro avg) 0.982
	2021-12-31 09:44:18,588 BAD EPOCHS (no improvement): 1
	2021-12-31 09:44:18,590 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:44:34,495 epoch 21 - iter 180/1807 - loss 0.08058450 - samples/sec: 90.65 - lr: 0.100000
	2021-12-31 09:44:50,061 epoch 21 - iter 360/1807 - loss 0.08169987 - samples/sec: 92.62 - lr: 0.100000
	2021-12-31 09:45:05,780 epoch 21 - iter 540/1807 - loss 0.08147401 - samples/sec: 91.76 - lr: 0.100000
	2021-12-31 09:45:21,869 epoch 21 - iter 720/1807 - loss 0.08235327 - samples/sec: 89.64 - lr: 0.100000
	2021-12-31 09:45:38,316 epoch 21 - iter 900/1807 - loss 0.08324710 - samples/sec: 87.67 - lr: 0.100000
	2021-12-31 09:45:54,314 epoch 21 - iter 1080/1807 - loss 0.08294963 - samples/sec: 90.14 - lr: 0.100000
	2021-12-31 09:46:10,369 epoch 21 - iter 1260/1807 - loss 0.08355307 - samples/sec: 89.83 - lr: 0.100000
	2021-12-31 09:46:26,469 epoch 21 - iter 1440/1807 - loss 0.08343050 - samples/sec: 89.57 - lr: 0.100000
	2021-12-31 09:46:42,401 epoch 21 - iter 1620/1807 - loss 0.08414815 - samples/sec: 90.52 - lr: 0.100000
	2021-12-31 09:46:58,257 epoch 21 - iter 1800/1807 - loss 0.08376554 - samples/sec: 90.95 - lr: 0.100000
	2021-12-31 09:46:58,880 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:46:58,880 EPOCH 21 done: loss 0.0839 - lr 0.1000000
	2021-12-31 09:47:35,248 DEV : loss 0.06328344345092773 - f1-score (micro avg) 0.9827
	2021-12-31 09:47:35,446 BAD EPOCHS (no improvement): 0
	2021-12-31 09:47:35,448 saving best model
	2021-12-31 09:47:41,248 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:47:57,255 epoch 22 - iter 180/1807 - loss 0.08050373 - samples/sec: 90.12 - lr: 0.100000
	2021-12-31 09:48:13,186 epoch 22 - iter 360/1807 - loss 0.08239139 - samples/sec: 90.52 - lr: 0.100000
	2021-12-31 09:48:29,067 epoch 22 - iter 540/1807 - loss 0.08228212 - samples/sec: 90.81 - lr: 0.100000
	2021-12-31 09:48:45,039 epoch 22 - iter 720/1807 - loss 0.08279713 - samples/sec: 90.30 - lr: 0.100000
	2021-12-31 09:49:00,510 epoch 22 - iter 900/1807 - loss 0.08334789 - samples/sec: 93.22 - lr: 0.100000
	2021-12-31 09:49:16,362 epoch 22 - iter 1080/1807 - loss 0.08342389 - samples/sec: 90.97 - lr: 0.100000
	2021-12-31 09:49:32,567 epoch 22 - iter 1260/1807 - loss 0.08349166 - samples/sec: 88.99 - lr: 0.100000
	2021-12-31 09:49:48,320 epoch 22 - iter 1440/1807 - loss 0.08427908 - samples/sec: 91.55 - lr: 0.100000
	2021-12-31 09:50:04,570 epoch 22 - iter 1620/1807 - loss 0.08465300 - samples/sec: 88.75 - lr: 0.100000
	2021-12-31 09:50:20,943 epoch 22 - iter 1800/1807 - loss 0.08437528 - samples/sec: 88.07 - lr: 0.100000
	2021-12-31 09:50:21,480 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:50:21,480 EPOCH 22 done: loss 0.0844 - lr 0.1000000
	2021-12-31 09:50:58,771 DEV : loss 0.06346500664949417 - f1-score (micro avg) 0.9815
	2021-12-31 09:50:58,967 BAD EPOCHS (no improvement): 1
	2021-12-31 09:50:58,969 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:51:15,272 epoch 23 - iter 180/1807 - loss 0.07857499 - samples/sec: 88.47 - lr: 0.100000
	2021-12-31 09:51:31,123 epoch 23 - iter 360/1807 - loss 0.07736816 - samples/sec: 91.00 - lr: 0.100000
	2021-12-31 09:51:47,441 epoch 23 - iter 540/1807 - loss 0.07865886 - samples/sec: 88.38 - lr: 0.100000
	2021-12-31 09:52:03,508 epoch 23 - iter 720/1807 - loss 0.08053686 - samples/sec: 89.75 - lr: 0.100000
	2021-12-31 09:52:19,618 epoch 23 - iter 900/1807 - loss 0.08084826 - samples/sec: 89.52 - lr: 0.100000
	2021-12-31 09:52:35,467 epoch 23 - iter 1080/1807 - loss 0.08116025 - samples/sec: 91.00 - lr: 0.100000
	2021-12-31 09:52:51,307 epoch 23 - iter 1260/1807 - loss 0.08137722 - samples/sec: 91.04 - lr: 0.100000
	2021-12-31 09:53:07,605 epoch 23 - iter 1440/1807 - loss 0.08168418 - samples/sec: 88.48 - lr: 0.100000
	2021-12-31 09:53:23,242 epoch 23 - iter 1620/1807 - loss 0.08161521 - samples/sec: 92.22 - lr: 0.100000
	2021-12-31 09:53:38,917 epoch 23 - iter 1800/1807 - loss 0.08147531 - samples/sec: 92.01 - lr: 0.100000
	2021-12-31 09:53:39,396 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:53:39,396 EPOCH 23 done: loss 0.0814 - lr 0.1000000
	2021-12-31 09:54:15,841 DEV : loss 0.06540019810199738 - f1-score (micro avg) 0.9821
	2021-12-31 09:54:16,023 BAD EPOCHS (no improvement): 2
	2021-12-31 09:54:16,025 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:54:32,334 epoch 24 - iter 180/1807 - loss 0.07795468 - samples/sec: 88.43 - lr: 0.100000
	2021-12-31 09:54:48,084 epoch 24 - iter 360/1807 - loss 0.07908717 - samples/sec: 91.57 - lr: 0.100000
	2021-12-31 09:55:04,326 epoch 24 - iter 540/1807 - loss 0.08004992 - samples/sec: 88.79 - lr: 0.100000
	2021-12-31 09:55:20,651 epoch 24 - iter 720/1807 - loss 0.08100541 - samples/sec: 88.34 - lr: 0.100000
	2021-12-31 09:55:36,785 epoch 24 - iter 900/1807 - loss 0.08142507 - samples/sec: 89.38 - lr: 0.100000
	2021-12-31 09:55:52,742 epoch 24 - iter 1080/1807 - loss 0.08232817 - samples/sec: 90.38 - lr: 0.100000
	2021-12-31 09:56:08,164 epoch 24 - iter 1260/1807 - loss 0.08188184 - samples/sec: 93.53 - lr: 0.100000
	2021-12-31 09:56:24,063 epoch 24 - iter 1440/1807 - loss 0.08243719 - samples/sec: 90.71 - lr: 0.100000
	2021-12-31 09:56:40,384 epoch 24 - iter 1620/1807 - loss 0.08222346 - samples/sec: 88.35 - lr: 0.100000
	2021-12-31 09:56:56,011 epoch 24 - iter 1800/1807 - loss 0.08229498 - samples/sec: 92.29 - lr: 0.100000
	2021-12-31 09:56:56,616 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:56:56,616 EPOCH 24 done: loss 0.0822 - lr 0.1000000
	2021-12-31 09:57:35,721 DEV : loss 0.06453310698270798 - f1-score (micro avg) 0.9819
	2021-12-31 09:57:35,917 BAD EPOCHS (no improvement): 3
	2021-12-31 09:57:35,919 ----------------------------------------------------------------------------------------------------
	2021-12-31 09:57:52,048 epoch 25 - iter 180/1807 - loss 0.07765362 - samples/sec: 89.42 - lr: 0.100000
	2021-12-31 09:58:07,956 epoch 25 - iter 360/1807 - loss 0.07932940 - samples/sec: 90.65 - lr: 0.100000
	2021-12-31 09:58:23,863 epoch 25 - iter 540/1807 - loss 0.08046614 - samples/sec: 90.65 - lr: 0.100000
	2021-12-31 09:58:39,725 epoch 25 - iter 720/1807 - loss 0.07941669 - samples/sec: 90.92 - lr: 0.100000
	2021-12-31 09:58:55,303 epoch 25 - iter 900/1807 - loss 0.08092722 - samples/sec: 92.57 - lr: 0.100000
	2021-12-31 09:59:11,794 epoch 25 - iter 1080/1807 - loss 0.08150485 - samples/sec: 87.44 - lr: 0.100000
	2021-12-31 09:59:27,795 epoch 25 - iter 1260/1807 - loss 0.08118184 - samples/sec: 90.13 - lr: 0.100000
	2021-12-31 09:59:43,595 epoch 25 - iter 1440/1807 - loss 0.08068256 - samples/sec: 91.28 - lr: 0.100000
	2021-12-31 09:59:59,146 epoch 25 - iter 1620/1807 - loss 0.08113371 - samples/sec: 92.74 - lr: 0.100000
	2021-12-31 10:00:14,684 epoch 25 - iter 1800/1807 - loss 0.08112289 - samples/sec: 92.81 - lr: 0.100000
	2021-12-31 10:00:15,230 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:00:15,230 EPOCH 25 done: loss 0.0812 - lr 0.1000000
	2021-12-31 10:00:51,681 DEV : loss 0.06579063087701797 - f1-score (micro avg) 0.9817
	2021-12-31 10:00:51,872 BAD EPOCHS (no improvement): 4
	2021-12-31 10:00:51,874 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:01:08,252 epoch 26 - iter 180/1807 - loss 0.07473820 - samples/sec: 88.06 - lr: 0.050000
	2021-12-31 10:01:24,095 epoch 26 - iter 360/1807 - loss 0.07741051 - samples/sec: 91.03 - lr: 0.050000
	2021-12-31 10:01:40,042 epoch 26 - iter 540/1807 - loss 0.07612793 - samples/sec: 90.43 - lr: 0.050000
	2021-12-31 10:01:55,977 epoch 26 - iter 720/1807 - loss 0.07597233 - samples/sec: 90.49 - lr: 0.050000
	2021-12-31 10:02:12,264 epoch 26 - iter 900/1807 - loss 0.07560347 - samples/sec: 88.55 - lr: 0.050000
	2021-12-31 10:02:28,030 epoch 26 - iter 1080/1807 - loss 0.07626889 - samples/sec: 91.47 - lr: 0.050000
	2021-12-31 10:02:43,691 epoch 26 - iter 1260/1807 - loss 0.07613186 - samples/sec: 92.08 - lr: 0.050000
	2021-12-31 10:02:59,223 epoch 26 - iter 1440/1807 - loss 0.07558384 - samples/sec: 92.85 - lr: 0.050000
	2021-12-31 10:03:15,259 epoch 26 - iter 1620/1807 - loss 0.07503334 - samples/sec: 89.93 - lr: 0.050000
	2021-12-31 10:03:31,614 epoch 26 - iter 1800/1807 - loss 0.07448614 - samples/sec: 88.18 - lr: 0.050000
	2021-12-31 10:03:32,151 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:03:32,151 EPOCH 26 done: loss 0.0744 - lr 0.0500000
	2021-12-31 10:04:08,767 DEV : loss 0.06646668165922165 - f1-score (micro avg) 0.9822
	2021-12-31 10:04:08,949 BAD EPOCHS (no improvement): 1
	2021-12-31 10:04:08,950 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:04:25,529 epoch 27 - iter 180/1807 - loss 0.06581114 - samples/sec: 86.99 - lr: 0.050000
	2021-12-31 10:04:41,436 epoch 27 - iter 360/1807 - loss 0.06857834 - samples/sec: 90.66 - lr: 0.050000
	2021-12-31 10:04:57,191 epoch 27 - iter 540/1807 - loss 0.07081005 - samples/sec: 91.54 - lr: 0.050000
	2021-12-31 10:05:13,183 epoch 27 - iter 720/1807 - loss 0.07198836 - samples/sec: 90.18 - lr: 0.050000
	2021-12-31 10:05:29,131 epoch 27 - iter 900/1807 - loss 0.07153264 - samples/sec: 90.42 - lr: 0.050000
	2021-12-31 10:05:44,864 epoch 27 - iter 1080/1807 - loss 0.07164274 - samples/sec: 91.66 - lr: 0.050000
	2021-12-31 10:06:00,643 epoch 27 - iter 1260/1807 - loss 0.07167991 - samples/sec: 91.40 - lr: 0.050000
	2021-12-31 10:06:15,929 epoch 27 - iter 1440/1807 - loss 0.07130117 - samples/sec: 94.34 - lr: 0.050000
	2021-12-31 10:06:32,208 epoch 27 - iter 1620/1807 - loss 0.07137995 - samples/sec: 88.59 - lr: 0.050000
	2021-12-31 10:06:48,072 epoch 27 - iter 1800/1807 - loss 0.07123898 - samples/sec: 90.90 - lr: 0.050000
	2021-12-31 10:06:48,616 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:06:48,616 EPOCH 27 done: loss 0.0712 - lr 0.0500000
	2021-12-31 10:07:27,769 DEV : loss 0.06514652073383331 - f1-score (micro avg) 0.9823
	2021-12-31 10:07:27,967 BAD EPOCHS (no improvement): 2
	2021-12-31 10:07:27,968 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:07:43,921 epoch 28 - iter 180/1807 - loss 0.06865415 - samples/sec: 90.41 - lr: 0.050000
	2021-12-31 10:08:00,073 epoch 28 - iter 360/1807 - loss 0.06855531 - samples/sec: 89.28 - lr: 0.050000
	2021-12-31 10:08:16,259 epoch 28 - iter 540/1807 - loss 0.06891820 - samples/sec: 89.09 - lr: 0.050000
	2021-12-31 10:08:31,981 epoch 28 - iter 720/1807 - loss 0.06951336 - samples/sec: 91.73 - lr: 0.050000
	2021-12-31 10:08:47,429 epoch 28 - iter 900/1807 - loss 0.07014278 - samples/sec: 93.35 - lr: 0.050000
	2021-12-31 10:09:03,024 epoch 28 - iter 1080/1807 - loss 0.07071541 - samples/sec: 92.47 - lr: 0.050000
	2021-12-31 10:09:18,974 epoch 28 - iter 1260/1807 - loss 0.07012373 - samples/sec: 90.41 - lr: 0.050000
	2021-12-31 10:09:34,620 epoch 28 - iter 1440/1807 - loss 0.07028479 - samples/sec: 92.17 - lr: 0.050000
	2021-12-31 10:09:50,427 epoch 28 - iter 1620/1807 - loss 0.07017402 - samples/sec: 91.23 - lr: 0.050000
	2021-12-31 10:10:05,997 epoch 28 - iter 1800/1807 - loss 0.07002142 - samples/sec: 92.62 - lr: 0.050000
	2021-12-31 10:10:06,547 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:10:06,548 EPOCH 28 done: loss 0.0701 - lr 0.0500000
	2021-12-31 10:10:43,342 DEV : loss 0.06285692006349564 - f1-score (micro avg) 0.9828
	2021-12-31 10:10:43,549 BAD EPOCHS (no improvement): 0
	2021-12-31 10:10:43,550 saving best model
	2021-12-31 10:10:49,346 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:11:05,893 epoch 29 - iter 180/1807 - loss 0.06749112 - samples/sec: 87.17 - lr: 0.050000
	2021-12-31 10:11:21,660 epoch 29 - iter 360/1807 - loss 0.06704871 - samples/sec: 91.46 - lr: 0.050000
	2021-12-31 10:11:37,404 epoch 29 - iter 540/1807 - loss 0.06846136 - samples/sec: 91.60 - lr: 0.050000
	2021-12-31 10:11:53,397 epoch 29 - iter 720/1807 - loss 0.06901632 - samples/sec: 90.17 - lr: 0.050000
	2021-12-31 10:12:09,257 epoch 29 - iter 900/1807 - loss 0.06809349 - samples/sec: 90.93 - lr: 0.050000
	2021-12-31 10:12:24,599 epoch 29 - iter 1080/1807 - loss 0.06824897 - samples/sec: 94.00 - lr: 0.050000
	2021-12-31 10:12:40,447 epoch 29 - iter 1260/1807 - loss 0.06782382 - samples/sec: 91.00 - lr: 0.050000
	2021-12-31 10:12:56,595 epoch 29 - iter 1440/1807 - loss 0.06808796 - samples/sec: 89.30 - lr: 0.050000
	2021-12-31 10:13:12,755 epoch 29 - iter 1620/1807 - loss 0.06798634 - samples/sec: 89.24 - lr: 0.050000
	2021-12-31 10:13:28,701 epoch 29 - iter 1800/1807 - loss 0.06777472 - samples/sec: 90.44 - lr: 0.050000
	2021-12-31 10:13:29,227 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:13:29,228 EPOCH 29 done: loss 0.0678 - lr 0.0500000
	2021-12-31 10:14:05,041 DEV : loss 0.06288447976112366 - f1-score (micro avg) 0.9831
	2021-12-31 10:14:05,221 BAD EPOCHS (no improvement): 0
	2021-12-31 10:14:05,222 saving best model
	2021-12-31 10:14:10,675 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:14:26,845 epoch 30 - iter 180/1807 - loss 0.06615046 - samples/sec: 89.20 - lr: 0.050000
	2021-12-31 10:14:42,781 epoch 30 - iter 360/1807 - loss 0.06701908 - samples/sec: 90.50 - lr: 0.050000
	2021-12-31 10:14:58,746 epoch 30 - iter 540/1807 - loss 0.06748578 - samples/sec: 90.33 - lr: 0.050000
	2021-12-31 10:15:14,479 epoch 30 - iter 720/1807 - loss 0.06796474 - samples/sec: 91.66 - lr: 0.050000
	2021-12-31 10:15:30,280 epoch 30 - iter 900/1807 - loss 0.06739311 - samples/sec: 91.26 - lr: 0.050000
	2021-12-31 10:15:45,933 epoch 30 - iter 1080/1807 - loss 0.06699810 - samples/sec: 92.13 - lr: 0.050000
	2021-12-31 10:16:01,690 epoch 30 - iter 1260/1807 - loss 0.06745951 - samples/sec: 91.53 - lr: 0.050000
	2021-12-31 10:16:17,453 epoch 30 - iter 1440/1807 - loss 0.06704309 - samples/sec: 91.49 - lr: 0.050000
	2021-12-31 10:16:33,233 epoch 30 - iter 1620/1807 - loss 0.06649743 - samples/sec: 91.38 - lr: 0.050000
	2021-12-31 10:16:49,143 epoch 30 - iter 1800/1807 - loss 0.06655280 - samples/sec: 90.65 - lr: 0.050000
	2021-12-31 10:16:49,685 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:16:49,685 EPOCH 30 done: loss 0.0666 - lr 0.0500000
	2021-12-31 10:17:28,240 DEV : loss 0.06311798095703125 - f1-score (micro avg) 0.9824
	2021-12-31 10:17:28,433 BAD EPOCHS (no improvement): 1
	2021-12-31 10:17:28,434 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:17:44,966 epoch 31 - iter 180/1807 - loss 0.06627745 - samples/sec: 87.24 - lr: 0.050000
	2021-12-31 10:18:00,662 epoch 31 - iter 360/1807 - loss 0.06286711 - samples/sec: 91.88 - lr: 0.050000
	2021-12-31 10:18:16,307 epoch 31 - iter 540/1807 - loss 0.06454841 - samples/sec: 92.17 - lr: 0.050000
	2021-12-31 10:18:32,243 epoch 31 - iter 720/1807 - loss 0.06465161 - samples/sec: 90.50 - lr: 0.050000
	2021-12-31 10:18:47,799 epoch 31 - iter 900/1807 - loss 0.06488043 - samples/sec: 92.70 - lr: 0.050000
	2021-12-31 10:19:03,602 epoch 31 - iter 1080/1807 - loss 0.06501278 - samples/sec: 91.26 - lr: 0.050000
	2021-12-31 10:19:19,610 epoch 31 - iter 1260/1807 - loss 0.06524649 - samples/sec: 90.08 - lr: 0.050000
	2021-12-31 10:19:35,038 epoch 31 - iter 1440/1807 - loss 0.06554492 - samples/sec: 93.48 - lr: 0.050000
	2021-12-31 10:19:51,164 epoch 31 - iter 1620/1807 - loss 0.06599922 - samples/sec: 89.43 - lr: 0.050000
	2021-12-31 10:20:07,078 epoch 31 - iter 1800/1807 - loss 0.06644678 - samples/sec: 90.61 - lr: 0.050000
	2021-12-31 10:20:07,640 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:20:07,640 EPOCH 31 done: loss 0.0666 - lr 0.0500000
	2021-12-31 10:20:43,927 DEV : loss 0.06285466253757477 - f1-score (micro avg) 0.9829
	2021-12-31 10:20:44,123 BAD EPOCHS (no improvement): 2
	2021-12-31 10:20:44,125 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:21:00,298 epoch 32 - iter 180/1807 - loss 0.06077116 - samples/sec: 89.18 - lr: 0.050000
	2021-12-31 10:21:16,393 epoch 32 - iter 360/1807 - loss 0.06270324 - samples/sec: 89.60 - lr: 0.050000
	2021-12-31 10:21:32,158 epoch 32 - iter 540/1807 - loss 0.06340224 - samples/sec: 91.47 - lr: 0.050000
	2021-12-31 10:21:48,183 epoch 32 - iter 720/1807 - loss 0.06267842 - samples/sec: 89.99 - lr: 0.050000
	2021-12-31 10:22:03,949 epoch 32 - iter 900/1807 - loss 0.06345792 - samples/sec: 91.50 - lr: 0.050000
	2021-12-31 10:22:19,674 epoch 32 - iter 1080/1807 - loss 0.06439376 - samples/sec: 91.71 - lr: 0.050000
	2021-12-31 10:22:35,414 epoch 32 - iter 1260/1807 - loss 0.06437464 - samples/sec: 91.63 - lr: 0.050000
	2021-12-31 10:22:51,702 epoch 32 - iter 1440/1807 - loss 0.06435182 - samples/sec: 88.53 - lr: 0.050000
	2021-12-31 10:23:07,918 epoch 32 - iter 1620/1807 - loss 0.06467809 - samples/sec: 88.93 - lr: 0.050000
	2021-12-31 10:23:23,880 epoch 32 - iter 1800/1807 - loss 0.06484923 - samples/sec: 90.35 - lr: 0.050000
	2021-12-31 10:23:24,513 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:23:24,513 EPOCH 32 done: loss 0.0648 - lr 0.0500000
	2021-12-31 10:24:00,678 DEV : loss 0.062373436987400055 - f1-score (micro avg) 0.9827
	2021-12-31 10:24:00,863 BAD EPOCHS (no improvement): 3
	2021-12-31 10:24:00,865 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:24:17,368 epoch 33 - iter 180/1807 - loss 0.06511517 - samples/sec: 87.39 - lr: 0.050000
	2021-12-31 10:24:33,869 epoch 33 - iter 360/1807 - loss 0.06359714 - samples/sec: 87.39 - lr: 0.050000
	2021-12-31 10:24:49,974 epoch 33 - iter 540/1807 - loss 0.06324776 - samples/sec: 89.54 - lr: 0.050000
	2021-12-31 10:25:05,411 epoch 33 - iter 720/1807 - loss 0.06296883 - samples/sec: 93.42 - lr: 0.050000
	2021-12-31 10:25:21,477 epoch 33 - iter 900/1807 - loss 0.06304943 - samples/sec: 89.76 - lr: 0.050000
	2021-12-31 10:25:37,062 epoch 33 - iter 1080/1807 - loss 0.06266940 - samples/sec: 92.52 - lr: 0.050000
	2021-12-31 10:25:52,743 epoch 33 - iter 1260/1807 - loss 0.06359599 - samples/sec: 91.97 - lr: 0.050000
	2021-12-31 10:26:08,521 epoch 33 - iter 1440/1807 - loss 0.06353058 - samples/sec: 91.40 - lr: 0.050000
	2021-12-31 10:26:24,080 epoch 33 - iter 1620/1807 - loss 0.06366170 - samples/sec: 92.69 - lr: 0.050000
	2021-12-31 10:26:39,568 epoch 33 - iter 1800/1807 - loss 0.06405823 - samples/sec: 93.11 - lr: 0.050000
	2021-12-31 10:26:40,121 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:26:40,121 EPOCH 33 done: loss 0.0640 - lr 0.0500000
	2021-12-31 10:27:18,678 DEV : loss 0.06352584064006805 - f1-score (micro avg) 0.983
	2021-12-31 10:27:18,875 BAD EPOCHS (no improvement): 4
	2021-12-31 10:27:18,877 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:27:34,632 epoch 34 - iter 180/1807 - loss 0.05738992 - samples/sec: 91.55 - lr: 0.025000
	2021-12-31 10:27:50,783 epoch 34 - iter 360/1807 - loss 0.05964139 - samples/sec: 89.29 - lr: 0.025000
	2021-12-31 10:28:06,956 epoch 34 - iter 540/1807 - loss 0.05950577 - samples/sec: 89.16 - lr: 0.025000
	2021-12-31 10:28:23,264 epoch 34 - iter 720/1807 - loss 0.06033373 - samples/sec: 88.43 - lr: 0.025000
	2021-12-31 10:28:38,762 epoch 34 - iter 900/1807 - loss 0.06053852 - samples/sec: 93.06 - lr: 0.025000
	2021-12-31 10:28:54,790 epoch 34 - iter 1080/1807 - loss 0.06008683 - samples/sec: 89.97 - lr: 0.025000
	2021-12-31 10:29:10,752 epoch 34 - iter 1260/1807 - loss 0.06017032 - samples/sec: 90.34 - lr: 0.025000
	2021-12-31 10:29:26,533 epoch 34 - iter 1440/1807 - loss 0.06026720 - samples/sec: 91.39 - lr: 0.025000
	2021-12-31 10:29:41,962 epoch 34 - iter 1620/1807 - loss 0.06023939 - samples/sec: 93.47 - lr: 0.025000
	2021-12-31 10:29:57,974 epoch 34 - iter 1800/1807 - loss 0.06024915 - samples/sec: 90.06 - lr: 0.025000
	2021-12-31 10:29:58,641 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:29:58,642 EPOCH 34 done: loss 0.0602 - lr 0.0250000
	2021-12-31 10:30:34,901 DEV : loss 0.06348917633295059 - f1-score (micro avg) 0.9835
	2021-12-31 10:30:35,087 BAD EPOCHS (no improvement): 0
	2021-12-31 10:30:35,089 saving best model
	2021-12-31 10:30:40,883 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:30:57,202 epoch 35 - iter 180/1807 - loss 0.05878333 - samples/sec: 88.38 - lr: 0.025000
	2021-12-31 10:31:12,996 epoch 35 - iter 360/1807 - loss 0.05795906 - samples/sec: 91.32 - lr: 0.025000
	2021-12-31 10:31:29,079 epoch 35 - iter 540/1807 - loss 0.05935994 - samples/sec: 89.67 - lr: 0.025000
	2021-12-31 10:31:45,084 epoch 35 - iter 720/1807 - loss 0.05982168 - samples/sec: 90.10 - lr: 0.025000
	2021-12-31 10:32:00,692 epoch 35 - iter 900/1807 - loss 0.05928538 - samples/sec: 92.39 - lr: 0.025000
	2021-12-31 10:32:16,615 epoch 35 - iter 1080/1807 - loss 0.05961166 - samples/sec: 90.58 - lr: 0.025000
	2021-12-31 10:32:32,475 epoch 35 - iter 1260/1807 - loss 0.06019352 - samples/sec: 90.93 - lr: 0.025000
	2021-12-31 10:32:48,494 epoch 35 - iter 1440/1807 - loss 0.06020781 - samples/sec: 90.02 - lr: 0.025000
	2021-12-31 10:33:04,244 epoch 35 - iter 1620/1807 - loss 0.05999299 - samples/sec: 91.57 - lr: 0.025000
	2021-12-31 10:33:20,684 epoch 35 - iter 1800/1807 - loss 0.05998842 - samples/sec: 87.72 - lr: 0.025000
	2021-12-31 10:33:21,238 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:33:21,238 EPOCH 35 done: loss 0.0600 - lr 0.0250000
	2021-12-31 10:33:57,434 DEV : loss 0.06338120251893997 - f1-score (micro avg) 0.9829
	2021-12-31 10:33:57,624 BAD EPOCHS (no improvement): 1
	2021-12-31 10:33:57,626 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:34:13,768 epoch 36 - iter 180/1807 - loss 0.06028850 - samples/sec: 89.35 - lr: 0.025000
	2021-12-31 10:34:29,556 epoch 36 - iter 360/1807 - loss 0.05827195 - samples/sec: 91.34 - lr: 0.025000
	2021-12-31 10:34:46,060 epoch 36 - iter 540/1807 - loss 0.05947832 - samples/sec: 87.38 - lr: 0.025000
	2021-12-31 10:35:02,018 epoch 36 - iter 720/1807 - loss 0.05898679 - samples/sec: 90.38 - lr: 0.025000
	2021-12-31 10:35:18,203 epoch 36 - iter 900/1807 - loss 0.05910041 - samples/sec: 89.10 - lr: 0.025000
	2021-12-31 10:35:34,254 epoch 36 - iter 1080/1807 - loss 0.05973540 - samples/sec: 89.84 - lr: 0.025000
	2021-12-31 10:35:50,256 epoch 36 - iter 1260/1807 - loss 0.05924335 - samples/sec: 90.13 - lr: 0.025000
	2021-12-31 10:36:06,236 epoch 36 - iter 1440/1807 - loss 0.05881263 - samples/sec: 90.25 - lr: 0.025000
	2021-12-31 10:36:22,117 epoch 36 - iter 1620/1807 - loss 0.05885928 - samples/sec: 90.80 - lr: 0.025000
	2021-12-31 10:36:38,208 epoch 36 - iter 1800/1807 - loss 0.05867245 - samples/sec: 89.62 - lr: 0.025000
	2021-12-31 10:36:38,763 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:36:38,763 EPOCH 36 done: loss 0.0587 - lr 0.0250000
	2021-12-31 10:37:17,552 DEV : loss 0.06424003839492798 - f1-score (micro avg) 0.9835
	2021-12-31 10:37:17,751 BAD EPOCHS (no improvement): 2
	2021-12-31 10:37:17,752 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:37:33,804 epoch 37 - iter 180/1807 - loss 0.05692650 - samples/sec: 89.85 - lr: 0.025000
	2021-12-31 10:37:50,368 epoch 37 - iter 360/1807 - loss 0.05616469 - samples/sec: 87.06 - lr: 0.025000
	2021-12-31 10:38:06,389 epoch 37 - iter 540/1807 - loss 0.05662717 - samples/sec: 90.01 - lr: 0.025000
	2021-12-31 10:38:22,399 epoch 37 - iter 720/1807 - loss 0.05716632 - samples/sec: 90.08 - lr: 0.025000
	2021-12-31 10:38:37,783 epoch 37 - iter 900/1807 - loss 0.05713545 - samples/sec: 93.74 - lr: 0.025000
	2021-12-31 10:38:53,871 epoch 37 - iter 1080/1807 - loss 0.05764661 - samples/sec: 89.64 - lr: 0.025000
	2021-12-31 10:39:10,031 epoch 37 - iter 1260/1807 - loss 0.05713711 - samples/sec: 89.23 - lr: 0.025000
	2021-12-31 10:39:25,737 epoch 37 - iter 1440/1807 - loss 0.05769197 - samples/sec: 91.83 - lr: 0.025000
	2021-12-31 10:39:41,486 epoch 37 - iter 1620/1807 - loss 0.05788084 - samples/sec: 91.57 - lr: 0.025000
	2021-12-31 10:39:57,218 epoch 37 - iter 1800/1807 - loss 0.05864320 - samples/sec: 91.67 - lr: 0.025000
	2021-12-31 10:39:57,747 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:39:57,748 EPOCH 37 done: loss 0.0586 - lr 0.0250000
	2021-12-31 10:40:34,869 DEV : loss 0.06326954811811447 - f1-score (micro avg) 0.9831
	2021-12-31 10:40:35,052 BAD EPOCHS (no improvement): 3
	2021-12-31 10:40:35,054 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:40:51,312 epoch 38 - iter 180/1807 - loss 0.05496563 - samples/sec: 88.71 - lr: 0.025000
	2021-12-31 10:41:07,088 epoch 38 - iter 360/1807 - loss 0.05435886 - samples/sec: 91.42 - lr: 0.025000
	2021-12-31 10:41:22,841 epoch 38 - iter 540/1807 - loss 0.05464384 - samples/sec: 91.55 - lr: 0.025000
	2021-12-31 10:41:38,398 epoch 38 - iter 720/1807 - loss 0.05548335 - samples/sec: 92.69 - lr: 0.025000
	2021-12-31 10:41:54,754 epoch 38 - iter 900/1807 - loss 0.05628518 - samples/sec: 88.18 - lr: 0.025000
	2021-12-31 10:42:10,229 epoch 38 - iter 1080/1807 - loss 0.05604961 - samples/sec: 93.19 - lr: 0.025000
	2021-12-31 10:42:26,417 epoch 38 - iter 1260/1807 - loss 0.05594531 - samples/sec: 89.09 - lr: 0.025000
	2021-12-31 10:42:42,839 epoch 38 - iter 1440/1807 - loss 0.05651329 - samples/sec: 87.81 - lr: 0.025000
	2021-12-31 10:42:58,889 epoch 38 - iter 1620/1807 - loss 0.05695998 - samples/sec: 89.85 - lr: 0.025000
	2021-12-31 10:43:15,043 epoch 38 - iter 1800/1807 - loss 0.05706783 - samples/sec: 89.27 - lr: 0.025000
	2021-12-31 10:43:15,590 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:43:15,590 EPOCH 38 done: loss 0.0570 - lr 0.0250000
	2021-12-31 10:43:52,423 DEV : loss 0.06343492120504379 - f1-score (micro avg) 0.9831
	2021-12-31 10:43:52,610 BAD EPOCHS (no improvement): 4
	2021-12-31 10:43:52,612 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:44:08,739 epoch 39 - iter 180/1807 - loss 0.05834451 - samples/sec: 89.43 - lr: 0.012500
	2021-12-31 10:44:24,462 epoch 39 - iter 360/1807 - loss 0.05496382 - samples/sec: 91.72 - lr: 0.012500
	2021-12-31 10:44:40,570 epoch 39 - iter 540/1807 - loss 0.05537094 - samples/sec: 89.53 - lr: 0.012500
	2021-12-31 10:44:56,434 epoch 39 - iter 720/1807 - loss 0.05546561 - samples/sec: 90.90 - lr: 0.012500
	2021-12-31 10:45:12,338 epoch 39 - iter 900/1807 - loss 0.05527723 - samples/sec: 90.67 - lr: 0.012500
	2021-12-31 10:45:27,903 epoch 39 - iter 1080/1807 - loss 0.05518412 - samples/sec: 92.65 - lr: 0.012500
	2021-12-31 10:45:43,777 epoch 39 - iter 1260/1807 - loss 0.05540916 - samples/sec: 90.86 - lr: 0.012500
	2021-12-31 10:45:59,259 epoch 39 - iter 1440/1807 - loss 0.05568263 - samples/sec: 93.15 - lr: 0.012500
	2021-12-31 10:46:15,024 epoch 39 - iter 1620/1807 - loss 0.05532678 - samples/sec: 91.47 - lr: 0.012500
	2021-12-31 10:46:30,975 epoch 39 - iter 1800/1807 - loss 0.05524694 - samples/sec: 90.40 - lr: 0.012500
	2021-12-31 10:46:31,584 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:46:31,585 EPOCH 39 done: loss 0.0552 - lr 0.0125000
	2021-12-31 10:47:10,908 DEV : loss 0.06419230252504349 - f1-score (micro avg) 0.9829
	2021-12-31 10:47:11,105 BAD EPOCHS (no improvement): 1
	2021-12-31 10:47:11,106 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:47:26,949 epoch 40 - iter 180/1807 - loss 0.05824543 - samples/sec: 91.06 - lr: 0.012500
	2021-12-31 10:47:42,913 epoch 40 - iter 360/1807 - loss 0.05527233 - samples/sec: 90.33 - lr: 0.012500
	2021-12-31 10:47:59,224 epoch 40 - iter 540/1807 - loss 0.05570769 - samples/sec: 88.41 - lr: 0.012500
	2021-12-31 10:48:14,703 epoch 40 - iter 720/1807 - loss 0.05485811 - samples/sec: 93.17 - lr: 0.012500
	2021-12-31 10:48:30,458 epoch 40 - iter 900/1807 - loss 0.05502772 - samples/sec: 91.54 - lr: 0.012500
	2021-12-31 10:48:46,369 epoch 40 - iter 1080/1807 - loss 0.05487373 - samples/sec: 90.63 - lr: 0.012500
	2021-12-31 10:49:01,734 epoch 40 - iter 1260/1807 - loss 0.05438047 - samples/sec: 93.85 - lr: 0.012500
	2021-12-31 10:49:17,649 epoch 40 - iter 1440/1807 - loss 0.05459548 - samples/sec: 90.61 - lr: 0.012500
	2021-12-31 10:49:33,390 epoch 40 - iter 1620/1807 - loss 0.05450567 - samples/sec: 91.62 - lr: 0.012500
	2021-12-31 10:49:49,353 epoch 40 - iter 1800/1807 - loss 0.05462945 - samples/sec: 90.34 - lr: 0.012500
	2021-12-31 10:49:49,959 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:49:49,959 EPOCH 40 done: loss 0.0546 - lr 0.0125000
	2021-12-31 10:50:26,216 DEV : loss 0.06343018263578415 - f1-score (micro avg) 0.9829
	2021-12-31 10:50:26,401 BAD EPOCHS (no improvement): 2
	2021-12-31 10:50:26,402 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:50:42,801 epoch 41 - iter 180/1807 - loss 0.04923909 - samples/sec: 87.95 - lr: 0.012500
	2021-12-31 10:50:58,898 epoch 41 - iter 360/1807 - loss 0.05125288 - samples/sec: 89.59 - lr: 0.012500
	2021-12-31 10:51:14,501 epoch 41 - iter 540/1807 - loss 0.05242298 - samples/sec: 92.43 - lr: 0.012500
	2021-12-31 10:51:30,244 epoch 41 - iter 720/1807 - loss 0.05272643 - samples/sec: 91.60 - lr: 0.012500
	2021-12-31 10:51:46,266 epoch 41 - iter 900/1807 - loss 0.05277145 - samples/sec: 90.01 - lr: 0.012500
	2021-12-31 10:52:02,535 epoch 41 - iter 1080/1807 - loss 0.05329680 - samples/sec: 88.64 - lr: 0.012500
	2021-12-31 10:52:18,362 epoch 41 - iter 1260/1807 - loss 0.05349535 - samples/sec: 91.12 - lr: 0.012500
	2021-12-31 10:52:34,324 epoch 41 - iter 1440/1807 - loss 0.05371268 - samples/sec: 90.35 - lr: 0.012500
	2021-12-31 10:52:50,154 epoch 41 - iter 1620/1807 - loss 0.05362217 - samples/sec: 91.09 - lr: 0.012500
	2021-12-31 10:53:06,114 epoch 41 - iter 1800/1807 - loss 0.05361560 - samples/sec: 90.36 - lr: 0.012500
	2021-12-31 10:53:06,648 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:53:06,649 EPOCH 41 done: loss 0.0537 - lr 0.0125000
	2021-12-31 10:53:42,920 DEV : loss 0.06420625746250153 - f1-score (micro avg) 0.9831
	2021-12-31 10:53:43,107 BAD EPOCHS (no improvement): 3
	2021-12-31 10:53:43,108 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:53:59,320 epoch 42 - iter 180/1807 - loss 0.04886676 - samples/sec: 88.96 - lr: 0.012500
	2021-12-31 10:54:15,301 epoch 42 - iter 360/1807 - loss 0.05210812 - samples/sec: 90.24 - lr: 0.012500
	2021-12-31 10:54:31,014 epoch 42 - iter 540/1807 - loss 0.05220145 - samples/sec: 91.78 - lr: 0.012500
	2021-12-31 10:54:46,930 epoch 42 - iter 720/1807 - loss 0.05239133 - samples/sec: 90.61 - lr: 0.012500
	2021-12-31 10:55:02,977 epoch 42 - iter 900/1807 - loss 0.05260141 - samples/sec: 89.87 - lr: 0.012500
	2021-12-31 10:55:19,228 epoch 42 - iter 1080/1807 - loss 0.05260187 - samples/sec: 88.74 - lr: 0.012500
	2021-12-31 10:55:35,215 epoch 42 - iter 1260/1807 - loss 0.05242910 - samples/sec: 90.21 - lr: 0.012500
	2021-12-31 10:55:51,163 epoch 42 - iter 1440/1807 - loss 0.05265492 - samples/sec: 90.43 - lr: 0.012500
	2021-12-31 10:56:07,328 epoch 42 - iter 1620/1807 - loss 0.05317972 - samples/sec: 89.21 - lr: 0.012500
	2021-12-31 10:56:23,405 epoch 42 - iter 1800/1807 - loss 0.05319734 - samples/sec: 89.70 - lr: 0.012500
	2021-12-31 10:56:23,951 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:56:23,951 EPOCH 42 done: loss 0.0532 - lr 0.0125000
	2021-12-31 10:57:03,168 DEV : loss 0.06362675130367279 - f1-score (micro avg) 0.9831
	2021-12-31 10:57:03,368 BAD EPOCHS (no improvement): 4
	2021-12-31 10:57:03,370 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:57:19,009 epoch 43 - iter 180/1807 - loss 0.05496817 - samples/sec: 92.23 - lr: 0.006250
	2021-12-31 10:57:34,952 epoch 43 - iter 360/1807 - loss 0.05262157 - samples/sec: 90.45 - lr: 0.006250
	2021-12-31 10:57:51,104 epoch 43 - iter 540/1807 - loss 0.05252708 - samples/sec: 89.28 - lr: 0.006250
	2021-12-31 10:58:06,630 epoch 43 - iter 720/1807 - loss 0.05258453 - samples/sec: 92.89 - lr: 0.006250
	2021-12-31 10:58:22,297 epoch 43 - iter 900/1807 - loss 0.05170441 - samples/sec: 92.05 - lr: 0.006250
	2021-12-31 10:58:38,636 epoch 43 - iter 1080/1807 - loss 0.05199907 - samples/sec: 88.26 - lr: 0.006250
	2021-12-31 10:58:54,582 epoch 43 - iter 1260/1807 - loss 0.05289598 - samples/sec: 90.42 - lr: 0.006250
	2021-12-31 10:59:10,756 epoch 43 - iter 1440/1807 - loss 0.05239565 - samples/sec: 89.17 - lr: 0.006250
	2021-12-31 10:59:26,756 epoch 43 - iter 1620/1807 - loss 0.05245197 - samples/sec: 90.14 - lr: 0.006250
	2021-12-31 10:59:43,140 epoch 43 - iter 1800/1807 - loss 0.05236153 - samples/sec: 88.01 - lr: 0.006250
	2021-12-31 10:59:43,734 ----------------------------------------------------------------------------------------------------
	2021-12-31 10:59:43,734 EPOCH 43 done: loss 0.0523 - lr 0.0062500
	2021-12-31 11:00:19,875 DEV : loss 0.06449297815561295 - f1-score (micro avg) 0.983
	2021-12-31 11:00:20,058 BAD EPOCHS (no improvement): 1
	2021-12-31 11:00:20,060 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:00:36,054 epoch 44 - iter 180/1807 - loss 0.05668095 - samples/sec: 90.17 - lr: 0.006250
	2021-12-31 11:00:51,879 epoch 44 - iter 360/1807 - loss 0.05376107 - samples/sec: 91.13 - lr: 0.006250
	2021-12-31 11:01:07,774 epoch 44 - iter 540/1807 - loss 0.05410164 - samples/sec: 90.73 - lr: 0.006250
	2021-12-31 11:01:23,539 epoch 44 - iter 720/1807 - loss 0.05349578 - samples/sec: 91.47 - lr: 0.006250
	2021-12-31 11:01:39,511 epoch 44 - iter 900/1807 - loss 0.05316904 - samples/sec: 90.29 - lr: 0.006250
	2021-12-31 11:01:55,495 epoch 44 - iter 1080/1807 - loss 0.05360298 - samples/sec: 90.23 - lr: 0.006250
	2021-12-31 11:02:11,974 epoch 44 - iter 1260/1807 - loss 0.05360002 - samples/sec: 87.52 - lr: 0.006250
	2021-12-31 11:02:27,697 epoch 44 - iter 1440/1807 - loss 0.05333331 - samples/sec: 91.72 - lr: 0.006250
	2021-12-31 11:02:43,120 epoch 44 - iter 1620/1807 - loss 0.05286587 - samples/sec: 93.50 - lr: 0.006250
	2021-12-31 11:02:58,798 epoch 44 - iter 1800/1807 - loss 0.05270956 - samples/sec: 91.99 - lr: 0.006250
	2021-12-31 11:02:59,351 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:02:59,352 EPOCH 44 done: loss 0.0527 - lr 0.0062500
	2021-12-31 11:03:35,832 DEV : loss 0.06455685943365097 - f1-score (micro avg) 0.9831
	2021-12-31 11:03:36,019 BAD EPOCHS (no improvement): 2
	2021-12-31 11:03:36,021 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:03:52,202 epoch 45 - iter 180/1807 - loss 0.05063292 - samples/sec: 89.13 - lr: 0.006250
	2021-12-31 11:04:08,225 epoch 45 - iter 360/1807 - loss 0.05171673 - samples/sec: 90.00 - lr: 0.006250
	2021-12-31 11:04:24,263 epoch 45 - iter 540/1807 - loss 0.05167432 - samples/sec: 89.93 - lr: 0.006250
	2021-12-31 11:04:40,362 epoch 45 - iter 720/1807 - loss 0.05121190 - samples/sec: 89.58 - lr: 0.006250
	2021-12-31 11:04:56,274 epoch 45 - iter 900/1807 - loss 0.05221446 - samples/sec: 90.63 - lr: 0.006250
	2021-12-31 11:05:12,479 epoch 45 - iter 1080/1807 - loss 0.05188940 - samples/sec: 88.99 - lr: 0.006250
	2021-12-31 11:05:28,572 epoch 45 - iter 1260/1807 - loss 0.05237022 - samples/sec: 89.62 - lr: 0.006250
	2021-12-31 11:05:44,476 epoch 45 - iter 1440/1807 - loss 0.05180768 - samples/sec: 90.68 - lr: 0.006250
	2021-12-31 11:06:00,356 epoch 45 - iter 1620/1807 - loss 0.05176296 - samples/sec: 90.81 - lr: 0.006250
	2021-12-31 11:06:16,343 epoch 45 - iter 1800/1807 - loss 0.05236414 - samples/sec: 90.20 - lr: 0.006250
	2021-12-31 11:06:16,948 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:06:16,949 EPOCH 45 done: loss 0.0523 - lr 0.0062500
	2021-12-31 11:06:56,269 DEV : loss 0.06413871794939041 - f1-score (micro avg) 0.983
	2021-12-31 11:06:56,425 BAD EPOCHS (no improvement): 3
	2021-12-31 11:06:56,427 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:07:12,359 epoch 46 - iter 180/1807 - loss 0.04909660 - samples/sec: 90.52 - lr: 0.006250
	2021-12-31 11:07:27,933 epoch 46 - iter 360/1807 - loss 0.04990439 - samples/sec: 92.58 - lr: 0.006250
	2021-12-31 11:07:44,036 epoch 46 - iter 540/1807 - loss 0.05183261 - samples/sec: 89.55 - lr: 0.006250
	2021-12-31 11:07:59,808 epoch 46 - iter 720/1807 - loss 0.05108367 - samples/sec: 91.44 - lr: 0.006250
	2021-12-31 11:08:16,323 epoch 46 - iter 900/1807 - loss 0.05156129 - samples/sec: 87.33 - lr: 0.006250
	2021-12-31 11:08:32,181 epoch 46 - iter 1080/1807 - loss 0.05164911 - samples/sec: 90.93 - lr: 0.006250
	2021-12-31 11:08:48,124 epoch 46 - iter 1260/1807 - loss 0.05241189 - samples/sec: 90.45 - lr: 0.006250
	2021-12-31 11:09:04,600 epoch 46 - iter 1440/1807 - loss 0.05209220 - samples/sec: 87.53 - lr: 0.006250
	2021-12-31 11:09:20,227 epoch 46 - iter 1620/1807 - loss 0.05187081 - samples/sec: 92.29 - lr: 0.006250
	2021-12-31 11:09:36,191 epoch 46 - iter 1800/1807 - loss 0.05205935 - samples/sec: 90.34 - lr: 0.006250
	2021-12-31 11:09:36,782 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:09:36,782 EPOCH 46 done: loss 0.0521 - lr 0.0062500
	2021-12-31 11:10:13,201 DEV : loss 0.0644669309258461 - f1-score (micro avg) 0.983
	2021-12-31 11:10:13,398 BAD EPOCHS (no improvement): 4
	2021-12-31 11:10:13,399 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:10:29,417 epoch 47 - iter 180/1807 - loss 0.05250873 - samples/sec: 90.04 - lr: 0.003125
	2021-12-31 11:10:45,589 epoch 47 - iter 360/1807 - loss 0.05160928 - samples/sec: 89.18 - lr: 0.003125
	2021-12-31 11:11:01,280 epoch 47 - iter 540/1807 - loss 0.05161492 - samples/sec: 91.91 - lr: 0.003125
	2021-12-31 11:11:17,277 epoch 47 - iter 720/1807 - loss 0.05136337 - samples/sec: 90.15 - lr: 0.003125
	2021-12-31 11:11:33,230 epoch 47 - iter 900/1807 - loss 0.05023989 - samples/sec: 90.40 - lr: 0.003125
	2021-12-31 11:11:49,156 epoch 47 - iter 1080/1807 - loss 0.05064277 - samples/sec: 90.55 - lr: 0.003125
	2021-12-31 11:12:04,959 epoch 47 - iter 1260/1807 - loss 0.05089925 - samples/sec: 91.25 - lr: 0.003125
	2021-12-31 11:12:21,092 epoch 47 - iter 1440/1807 - loss 0.05071923 - samples/sec: 89.39 - lr: 0.003125
	2021-12-31 11:12:36,949 epoch 47 - iter 1620/1807 - loss 0.05083516 - samples/sec: 90.95 - lr: 0.003125
	2021-12-31 11:12:52,744 epoch 47 - iter 1800/1807 - loss 0.05106443 - samples/sec: 91.31 - lr: 0.003125
	2021-12-31 11:12:53,321 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:12:53,321 EPOCH 47 done: loss 0.0511 - lr 0.0031250
	2021-12-31 11:13:29,490 DEV : loss 0.06470787525177002 - f1-score (micro avg) 0.9829
	2021-12-31 11:13:29,672 BAD EPOCHS (no improvement): 1
	2021-12-31 11:13:29,674 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:13:45,987 epoch 48 - iter 180/1807 - loss 0.05119727 - samples/sec: 88.41 - lr: 0.003125
	2021-12-31 11:14:02,271 epoch 48 - iter 360/1807 - loss 0.05026057 - samples/sec: 88.57 - lr: 0.003125
	2021-12-31 11:14:18,202 epoch 48 - iter 540/1807 - loss 0.04968790 - samples/sec: 90.53 - lr: 0.003125
	2021-12-31 11:14:33,834 epoch 48 - iter 720/1807 - loss 0.05040465 - samples/sec: 92.25 - lr: 0.003125
	2021-12-31 11:14:49,709 epoch 48 - iter 900/1807 - loss 0.05065504 - samples/sec: 90.84 - lr: 0.003125
	2021-12-31 11:15:05,727 epoch 48 - iter 1080/1807 - loss 0.05037297 - samples/sec: 90.02 - lr: 0.003125
	2021-12-31 11:15:21,077 epoch 48 - iter 1260/1807 - loss 0.05063199 - samples/sec: 93.96 - lr: 0.003125
	2021-12-31 11:15:36,587 epoch 48 - iter 1440/1807 - loss 0.05076731 - samples/sec: 92.98 - lr: 0.003125
	2021-12-31 11:15:52,489 epoch 48 - iter 1620/1807 - loss 0.05082260 - samples/sec: 90.68 - lr: 0.003125
	2021-12-31 11:16:08,520 epoch 48 - iter 1800/1807 - loss 0.05101165 - samples/sec: 89.96 - lr: 0.003125
	2021-12-31 11:16:09,115 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:16:09,116 EPOCH 48 done: loss 0.0510 - lr 0.0031250
	2021-12-31 11:16:48,035 DEV : loss 0.06484530121088028 - f1-score (micro avg) 0.983
	2021-12-31 11:16:48,189 BAD EPOCHS (no improvement): 2
	2021-12-31 11:16:48,191 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:17:03,775 epoch 49 - iter 180/1807 - loss 0.04706234 - samples/sec: 92.51 - lr: 0.003125
	2021-12-31 11:17:19,604 epoch 49 - iter 360/1807 - loss 0.04796051 - samples/sec: 91.07 - lr: 0.003125
	2021-12-31 11:17:35,506 epoch 49 - iter 540/1807 - loss 0.04820802 - samples/sec: 90.67 - lr: 0.003125
	2021-12-31 11:17:51,301 epoch 49 - iter 720/1807 - loss 0.04872061 - samples/sec: 91.31 - lr: 0.003125
	2021-12-31 11:18:06,963 epoch 49 - iter 900/1807 - loss 0.04900955 - samples/sec: 92.08 - lr: 0.003125
	2021-12-31 11:18:22,961 epoch 49 - iter 1080/1807 - loss 0.04952427 - samples/sec: 90.14 - lr: 0.003125
	2021-12-31 11:18:39,172 epoch 49 - iter 1260/1807 - loss 0.04981242 - samples/sec: 88.96 - lr: 0.003125
	2021-12-31 11:18:55,485 epoch 49 - iter 1440/1807 - loss 0.05015633 - samples/sec: 88.41 - lr: 0.003125
	2021-12-31 11:19:11,166 epoch 49 - iter 1620/1807 - loss 0.05076498 - samples/sec: 91.97 - lr: 0.003125
	2021-12-31 11:19:27,065 epoch 49 - iter 1800/1807 - loss 0.05104387 - samples/sec: 90.71 - lr: 0.003125
	2021-12-31 11:19:27,675 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:19:27,675 EPOCH 49 done: loss 0.0510 - lr 0.0031250
	2021-12-31 11:20:04,021 DEV : loss 0.06486314535140991 - f1-score (micro avg) 0.983
	2021-12-31 11:20:04,217 BAD EPOCHS (no improvement): 3
	2021-12-31 11:20:04,218 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:20:20,650 epoch 50 - iter 180/1807 - loss 0.05726933 - samples/sec: 87.77 - lr: 0.003125
	2021-12-31 11:20:36,455 epoch 50 - iter 360/1807 - loss 0.05538766 - samples/sec: 91.25 - lr: 0.003125
	2021-12-31 11:20:52,012 epoch 50 - iter 540/1807 - loss 0.05444601 - samples/sec: 92.69 - lr: 0.003125
	2021-12-31 11:21:07,973 epoch 50 - iter 720/1807 - loss 0.05313637 - samples/sec: 90.35 - lr: 0.003125
	2021-12-31 11:21:23,983 epoch 50 - iter 900/1807 - loss 0.05290526 - samples/sec: 90.08 - lr: 0.003125
	2021-12-31 11:21:39,924 epoch 50 - iter 1080/1807 - loss 0.05235234 - samples/sec: 90.47 - lr: 0.003125
	2021-12-31 11:21:55,732 epoch 50 - iter 1260/1807 - loss 0.05207690 - samples/sec: 91.23 - lr: 0.003125
	2021-12-31 11:22:11,663 epoch 50 - iter 1440/1807 - loss 0.05205514 - samples/sec: 90.52 - lr: 0.003125
	2021-12-31 11:22:27,392 epoch 50 - iter 1620/1807 - loss 0.05173851 - samples/sec: 91.69 - lr: 0.003125
	2021-12-31 11:22:43,193 epoch 50 - iter 1800/1807 - loss 0.05189058 - samples/sec: 91.27 - lr: 0.003125
	2021-12-31 11:22:43,750 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:22:43,750 EPOCH 50 done: loss 0.0519 - lr 0.0031250
	2021-12-31 11:23:20,432 DEV : loss 0.06452730298042297 - f1-score (micro avg) 0.9831
	2021-12-31 11:23:20,619 BAD EPOCHS (no improvement): 4
	2021-12-31 11:23:25,890 ----------------------------------------------------------------------------------------------------
	2021-12-31 11:23:25,893 loading file models/UPOS_UD_FRENCH_GSD_PLUS_Flair-Embeddings_50_2021-12-31-08:34:44/best-model.pt
	2021-12-31 11:23:43,354 0.9797 0.9797 0.9797 0.9797
	2021-12-31 11:23:43,354
	Results:
	- F-score (micro) 0.9797
	- F-score (macro) 0.9178
	- Accuracy 0.9797

	By class:
	precision recall f1-score support

	PREP 0.9966 0.9987 0.9976 1483
	PUNCT 1.0000 1.0000 1.0000 833
	NMS 0.9634 0.9801 0.9717 753
	DET 0.9923 0.9984 0.9954 645
	VERB 0.9913 0.9811 0.9862 583
	NFS 0.9667 0.9839 0.9752 560
	ADV 0.9940 0.9821 0.9880 504
	PROPN 0.9541 0.8937 0.9229 395
	DETMS 1.0000 1.0000 1.0000 362
	AUX 0.9860 0.9915 0.9888 355
	YPFOR 1.0000 1.0000 1.0000 353
	NMP 0.9666 0.9475 0.9570 305
	COCO 0.9959 1.0000 0.9980 245
	ADJMS 0.9463 0.9385 0.9424 244
	DETFS 1.0000 1.0000 1.0000 240
	CHIF 0.9648 0.9865 0.9755 222
	NFP 0.9515 0.9849 0.9679 199
	ADJFS 0.9657 0.9286 0.9468 182
	VPPMS 0.9387 0.9745 0.9563 157
	COSUB 1.0000 0.9844 0.9921 128
	DINTMS 0.9918 0.9918 0.9918 122
	XFAMIL 0.9298 0.9217 0.9258 115
	PPER3MS 1.0000 1.0000 1.0000 87
	ADJMP 0.9294 0.9634 0.9461 82
	PDEMMS 1.0000 1.0000 1.0000 75
	ADJFP 0.9861 0.9342 0.9595 76
	PREL 0.9859 1.0000 0.9929 70
	DINTFS 0.9839 1.0000 0.9919 61
	PREF 1.0000 1.0000 1.0000 52
	PPOBJMS 0.9565 0.9362 0.9462 47
	PREFP 0.9778 1.0000 0.9888 44
	PINDMS 1.0000 0.9773 0.9885 44
	VPPFS 0.8298 0.9750 0.8966 40
	PPER1S 1.0000 1.0000 1.0000 42
	SYM 1.0000 0.9474 0.9730 38
	NOUN 0.8824 0.7692 0.8219 39
	PRON 1.0000 0.9677 0.9836 31
	PDEMFS 1.0000 1.0000 1.0000 29
	VPPMP 0.9286 1.0000 0.9630 26
	ADJ 0.9524 0.9091 0.9302 22
	PPER3MP 1.0000 1.0000 1.0000 20
	VPPFP 1.0000 1.0000 1.0000 19
	PPER3FS 1.0000 1.0000 1.0000 18
	MOTINC 0.3333 0.4000 0.3636 15
	PREFS 1.0000 1.0000 1.0000 10
	PPOBJMP 1.0000 0.8000 0.8889 10
	PPOBJFS 0.6250 0.8333 0.7143 6
	INTJ 0.5000 0.6667 0.5714 6
	PART 1.0000 1.0000 1.0000 4
	PDEMMP 1.0000 1.0000 1.0000 3
	PDEMFP 1.0000 1.0000 1.0000 3
	PPER3FP 1.0000 1.0000 1.0000 2
	NUM 1.0000 0.3333 0.5000 3
	PPER2S 1.0000 1.0000 1.0000 2
	PPOBJFP 0.5000 0.5000 0.5000 2
	PRELMS 1.0000 1.0000 1.0000 2
	PINDFS 0.5000 1.0000 0.6667 1
	PINDMP 1.0000 1.0000 1.0000 1
	X 0.0000 0.0000 0.0000 1
	PINDFP 1.0000 1.0000 1.0000 1

	micro avg 0.9797 0.9797 0.9797 10019
	macro avg 0.9228 0.9230 0.9178 10019
	weighted avg 0.9802 0.9797 0.9798 10019
	samples avg 0.9797 0.9797 0.9797 10019

	2021-12-31 11:23:43,354 ----------------------------------------------------------------------------------------------------