| 2023-10-25 08:00:15,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,629 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 768) | |
| (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() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences | |
| - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Train: 14465 sentences | |
| 2023-10-25 08:00:15,630 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Training Params: | |
| 2023-10-25 08:00:15,630 - learning_rate: "3e-05" | |
| 2023-10-25 08:00:15,630 - mini_batch_size: "8" | |
| 2023-10-25 08:00:15,630 - max_epochs: "10" | |
| 2023-10-25 08:00:15,630 - shuffle: "True" | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Plugins: | |
| 2023-10-25 08:00:15,630 - TensorboardLogger | |
| 2023-10-25 08:00:15,630 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 08:00:15,630 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Computation: | |
| 2023-10-25 08:00:15,630 - compute on device: cuda:0 | |
| 2023-10-25 08:00:15,630 - embedding storage: none | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:00:15,630 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 08:00:31,579 epoch 1 - iter 180/1809 - loss 1.59994791 - time (sec): 15.95 - samples/sec: 2365.16 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 08:00:46,626 epoch 1 - iter 360/1809 - loss 0.90942152 - time (sec): 31.00 - samples/sec: 2420.21 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 08:01:02,121 epoch 1 - iter 540/1809 - loss 0.65057194 - time (sec): 46.49 - samples/sec: 2437.06 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 08:01:17,548 epoch 1 - iter 720/1809 - loss 0.52234297 - time (sec): 61.92 - samples/sec: 2445.01 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 08:01:32,921 epoch 1 - iter 900/1809 - loss 0.44356097 - time (sec): 77.29 - samples/sec: 2440.72 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 08:01:48,608 epoch 1 - iter 1080/1809 - loss 0.38806485 - time (sec): 92.98 - samples/sec: 2438.35 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 08:02:04,004 epoch 1 - iter 1260/1809 - loss 0.34665146 - time (sec): 108.37 - samples/sec: 2444.01 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 08:02:19,487 epoch 1 - iter 1440/1809 - loss 0.31692748 - time (sec): 123.86 - samples/sec: 2440.98 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 08:02:35,196 epoch 1 - iter 1620/1809 - loss 0.29267973 - time (sec): 139.57 - samples/sec: 2437.07 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 08:02:50,837 epoch 1 - iter 1800/1809 - loss 0.27406237 - time (sec): 155.21 - samples/sec: 2436.52 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 08:02:51,583 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:02:51,583 EPOCH 1 done: loss 0.2733 - lr: 0.000030 | |
| 2023-10-25 08:02:56,022 DEV : loss 0.11878068745136261 - f1-score (micro avg) 0.6243 | |
| 2023-10-25 08:02:56,043 saving best model | |
| 2023-10-25 08:02:56,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:03:12,137 epoch 2 - iter 180/1809 - loss 0.08520146 - time (sec): 15.54 - samples/sec: 2457.95 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 08:03:28,446 epoch 2 - iter 360/1809 - loss 0.09154462 - time (sec): 31.84 - samples/sec: 2418.86 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 08:03:44,444 epoch 2 - iter 540/1809 - loss 0.09248862 - time (sec): 47.84 - samples/sec: 2412.53 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 08:04:00,307 epoch 2 - iter 720/1809 - loss 0.08973269 - time (sec): 63.71 - samples/sec: 2404.62 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 08:04:16,033 epoch 2 - iter 900/1809 - loss 0.08876132 - time (sec): 79.43 - samples/sec: 2403.58 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 08:04:31,870 epoch 2 - iter 1080/1809 - loss 0.08756439 - time (sec): 95.27 - samples/sec: 2394.03 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 08:04:47,396 epoch 2 - iter 1260/1809 - loss 0.08711257 - time (sec): 110.79 - samples/sec: 2393.13 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 08:05:03,398 epoch 2 - iter 1440/1809 - loss 0.08478479 - time (sec): 126.80 - samples/sec: 2393.23 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 08:05:19,435 epoch 2 - iter 1620/1809 - loss 0.08360993 - time (sec): 142.83 - samples/sec: 2388.17 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 08:05:34,900 epoch 2 - iter 1800/1809 - loss 0.08306504 - time (sec): 158.30 - samples/sec: 2388.83 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 08:05:35,628 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:05:35,629 EPOCH 2 done: loss 0.0831 - lr: 0.000027 | |
| 2023-10-25 08:05:40,837 DEV : loss 0.13267631828784943 - f1-score (micro avg) 0.6358 | |
| 2023-10-25 08:05:40,859 saving best model | |
| 2023-10-25 08:05:41,675 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:05:57,585 epoch 3 - iter 180/1809 - loss 0.06089348 - time (sec): 15.91 - samples/sec: 2355.16 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 08:06:13,768 epoch 3 - iter 360/1809 - loss 0.06038894 - time (sec): 32.09 - samples/sec: 2360.88 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 08:06:29,084 epoch 3 - iter 540/1809 - loss 0.05526036 - time (sec): 47.41 - samples/sec: 2389.71 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 08:06:44,661 epoch 3 - iter 720/1809 - loss 0.05749612 - time (sec): 62.98 - samples/sec: 2390.73 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 08:07:00,404 epoch 3 - iter 900/1809 - loss 0.05617974 - time (sec): 78.73 - samples/sec: 2403.04 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 08:07:16,708 epoch 3 - iter 1080/1809 - loss 0.05706057 - time (sec): 95.03 - samples/sec: 2404.56 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 08:07:32,106 epoch 3 - iter 1260/1809 - loss 0.05724190 - time (sec): 110.43 - samples/sec: 2401.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 08:07:48,254 epoch 3 - iter 1440/1809 - loss 0.05718478 - time (sec): 126.58 - samples/sec: 2408.93 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 08:08:04,408 epoch 3 - iter 1620/1809 - loss 0.05826610 - time (sec): 142.73 - samples/sec: 2395.50 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 08:08:19,957 epoch 3 - iter 1800/1809 - loss 0.05919743 - time (sec): 158.28 - samples/sec: 2391.38 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 08:08:20,676 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:08:20,676 EPOCH 3 done: loss 0.0592 - lr: 0.000023 | |
| 2023-10-25 08:08:25,440 DEV : loss 0.1354532539844513 - f1-score (micro avg) 0.6314 | |
| 2023-10-25 08:08:25,462 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:08:41,845 epoch 4 - iter 180/1809 - loss 0.03568652 - time (sec): 16.38 - samples/sec: 2312.63 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 08:08:58,273 epoch 4 - iter 360/1809 - loss 0.03716226 - time (sec): 32.81 - samples/sec: 2346.64 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 08:09:13,745 epoch 4 - iter 540/1809 - loss 0.03968774 - time (sec): 48.28 - samples/sec: 2347.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 08:09:29,537 epoch 4 - iter 720/1809 - loss 0.04000489 - time (sec): 64.07 - samples/sec: 2355.52 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 08:09:45,388 epoch 4 - iter 900/1809 - loss 0.03962584 - time (sec): 79.93 - samples/sec: 2362.15 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 08:10:01,321 epoch 4 - iter 1080/1809 - loss 0.03940596 - time (sec): 95.86 - samples/sec: 2371.85 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 08:10:17,098 epoch 4 - iter 1260/1809 - loss 0.04055800 - time (sec): 111.64 - samples/sec: 2371.02 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 08:10:32,621 epoch 4 - iter 1440/1809 - loss 0.04022573 - time (sec): 127.16 - samples/sec: 2373.19 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 08:10:48,660 epoch 4 - iter 1620/1809 - loss 0.04065113 - time (sec): 143.20 - samples/sec: 2370.71 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 08:11:04,972 epoch 4 - iter 1800/1809 - loss 0.04133841 - time (sec): 159.51 - samples/sec: 2370.42 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 08:11:05,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:11:05,824 EPOCH 4 done: loss 0.0414 - lr: 0.000020 | |
| 2023-10-25 08:11:10,594 DEV : loss 0.2289542257785797 - f1-score (micro avg) 0.6386 | |
| 2023-10-25 08:11:10,616 saving best model | |
| 2023-10-25 08:11:11,305 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:11:26,893 epoch 5 - iter 180/1809 - loss 0.02492765 - time (sec): 15.59 - samples/sec: 2342.07 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 08:11:42,990 epoch 5 - iter 360/1809 - loss 0.02595936 - time (sec): 31.68 - samples/sec: 2334.66 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 08:11:58,875 epoch 5 - iter 540/1809 - loss 0.02591071 - time (sec): 47.57 - samples/sec: 2350.63 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 08:12:14,762 epoch 5 - iter 720/1809 - loss 0.02549117 - time (sec): 63.46 - samples/sec: 2358.16 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 08:12:30,706 epoch 5 - iter 900/1809 - loss 0.02448476 - time (sec): 79.40 - samples/sec: 2376.53 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 08:12:46,502 epoch 5 - iter 1080/1809 - loss 0.02533076 - time (sec): 95.20 - samples/sec: 2368.81 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 08:13:02,210 epoch 5 - iter 1260/1809 - loss 0.02562868 - time (sec): 110.90 - samples/sec: 2367.94 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 08:13:18,742 epoch 5 - iter 1440/1809 - loss 0.02590139 - time (sec): 127.44 - samples/sec: 2370.63 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 08:13:34,484 epoch 5 - iter 1620/1809 - loss 0.02625493 - time (sec): 143.18 - samples/sec: 2370.26 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 08:13:50,871 epoch 5 - iter 1800/1809 - loss 0.02688381 - time (sec): 159.57 - samples/sec: 2371.05 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 08:13:51,555 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:13:51,555 EPOCH 5 done: loss 0.0269 - lr: 0.000017 | |
| 2023-10-25 08:13:56,313 DEV : loss 0.26100045442581177 - f1-score (micro avg) 0.6625 | |
| 2023-10-25 08:13:56,335 saving best model | |
| 2023-10-25 08:13:57,053 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:14:12,919 epoch 6 - iter 180/1809 - loss 0.01378039 - time (sec): 15.86 - samples/sec: 2282.43 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 08:14:28,961 epoch 6 - iter 360/1809 - loss 0.01816354 - time (sec): 31.91 - samples/sec: 2360.47 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 08:14:45,179 epoch 6 - iter 540/1809 - loss 0.01885418 - time (sec): 48.12 - samples/sec: 2356.04 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 08:15:00,786 epoch 6 - iter 720/1809 - loss 0.01972614 - time (sec): 63.73 - samples/sec: 2349.29 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 08:15:16,751 epoch 6 - iter 900/1809 - loss 0.01899198 - time (sec): 79.70 - samples/sec: 2361.69 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 08:15:32,360 epoch 6 - iter 1080/1809 - loss 0.01852834 - time (sec): 95.31 - samples/sec: 2362.64 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 08:15:48,278 epoch 6 - iter 1260/1809 - loss 0.01797562 - time (sec): 111.22 - samples/sec: 2363.36 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 08:16:04,333 epoch 6 - iter 1440/1809 - loss 0.01764648 - time (sec): 127.28 - samples/sec: 2373.74 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 08:16:20,288 epoch 6 - iter 1620/1809 - loss 0.01787887 - time (sec): 143.23 - samples/sec: 2372.76 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 08:16:36,075 epoch 6 - iter 1800/1809 - loss 0.01811722 - time (sec): 159.02 - samples/sec: 2376.53 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 08:16:36,858 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:16:36,858 EPOCH 6 done: loss 0.0182 - lr: 0.000013 | |
| 2023-10-25 08:16:42,101 DEV : loss 0.3313358724117279 - f1-score (micro avg) 0.6553 | |
| 2023-10-25 08:16:42,123 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:16:57,953 epoch 7 - iter 180/1809 - loss 0.00872843 - time (sec): 15.83 - samples/sec: 2415.85 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 08:17:13,241 epoch 7 - iter 360/1809 - loss 0.00854091 - time (sec): 31.12 - samples/sec: 2417.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 08:17:29,025 epoch 7 - iter 540/1809 - loss 0.01084116 - time (sec): 46.90 - samples/sec: 2397.20 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 08:17:44,926 epoch 7 - iter 720/1809 - loss 0.01304482 - time (sec): 62.80 - samples/sec: 2399.67 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 08:18:01,388 epoch 7 - iter 900/1809 - loss 0.01267124 - time (sec): 79.26 - samples/sec: 2410.58 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 08:18:16,849 epoch 7 - iter 1080/1809 - loss 0.01242008 - time (sec): 94.73 - samples/sec: 2406.32 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 08:18:33,141 epoch 7 - iter 1260/1809 - loss 0.01230193 - time (sec): 111.02 - samples/sec: 2391.84 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 08:18:48,939 epoch 7 - iter 1440/1809 - loss 0.01248631 - time (sec): 126.82 - samples/sec: 2391.04 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 08:19:04,921 epoch 7 - iter 1620/1809 - loss 0.01261317 - time (sec): 142.80 - samples/sec: 2390.66 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 08:19:20,957 epoch 7 - iter 1800/1809 - loss 0.01276577 - time (sec): 158.83 - samples/sec: 2380.11 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 08:19:21,677 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:19:21,677 EPOCH 7 done: loss 0.0127 - lr: 0.000010 | |
| 2023-10-25 08:19:26,940 DEV : loss 0.36011332273483276 - f1-score (micro avg) 0.6616 | |
| 2023-10-25 08:19:26,962 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:19:43,149 epoch 8 - iter 180/1809 - loss 0.00761376 - time (sec): 16.19 - samples/sec: 2367.10 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 08:19:59,316 epoch 8 - iter 360/1809 - loss 0.00758239 - time (sec): 32.35 - samples/sec: 2344.06 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 08:20:15,488 epoch 8 - iter 540/1809 - loss 0.00857590 - time (sec): 48.52 - samples/sec: 2374.72 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 08:20:30,539 epoch 8 - iter 720/1809 - loss 0.00895513 - time (sec): 63.58 - samples/sec: 2393.92 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 08:20:46,448 epoch 8 - iter 900/1809 - loss 0.00825738 - time (sec): 79.49 - samples/sec: 2390.01 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 08:21:02,541 epoch 8 - iter 1080/1809 - loss 0.00881305 - time (sec): 95.58 - samples/sec: 2386.85 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 08:21:18,012 epoch 8 - iter 1260/1809 - loss 0.00882209 - time (sec): 111.05 - samples/sec: 2382.50 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 08:21:34,428 epoch 8 - iter 1440/1809 - loss 0.00827827 - time (sec): 127.47 - samples/sec: 2379.38 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 08:21:50,011 epoch 8 - iter 1620/1809 - loss 0.00824322 - time (sec): 143.05 - samples/sec: 2380.33 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 08:22:05,668 epoch 8 - iter 1800/1809 - loss 0.00850028 - time (sec): 158.70 - samples/sec: 2383.21 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 08:22:06,376 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:22:06,376 EPOCH 8 done: loss 0.0086 - lr: 0.000007 | |
| 2023-10-25 08:22:11,644 DEV : loss 0.39194777607917786 - f1-score (micro avg) 0.6577 | |
| 2023-10-25 08:22:11,666 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:22:28,097 epoch 9 - iter 180/1809 - loss 0.00369902 - time (sec): 16.43 - samples/sec: 2368.97 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 08:22:44,007 epoch 9 - iter 360/1809 - loss 0.00469730 - time (sec): 32.34 - samples/sec: 2414.47 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 08:22:59,689 epoch 9 - iter 540/1809 - loss 0.00431458 - time (sec): 48.02 - samples/sec: 2412.11 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 08:23:15,295 epoch 9 - iter 720/1809 - loss 0.00481666 - time (sec): 63.63 - samples/sec: 2391.66 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 08:23:31,490 epoch 9 - iter 900/1809 - loss 0.00493696 - time (sec): 79.82 - samples/sec: 2402.05 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 08:23:47,176 epoch 9 - iter 1080/1809 - loss 0.00523981 - time (sec): 95.51 - samples/sec: 2394.12 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 08:24:02,926 epoch 9 - iter 1260/1809 - loss 0.00497472 - time (sec): 111.26 - samples/sec: 2386.83 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 08:24:18,624 epoch 9 - iter 1440/1809 - loss 0.00565406 - time (sec): 126.96 - samples/sec: 2386.65 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 08:24:34,491 epoch 9 - iter 1620/1809 - loss 0.00563871 - time (sec): 142.82 - samples/sec: 2386.99 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 08:24:50,211 epoch 9 - iter 1800/1809 - loss 0.00567494 - time (sec): 158.54 - samples/sec: 2383.99 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 08:24:51,042 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:24:51,043 EPOCH 9 done: loss 0.0057 - lr: 0.000003 | |
| 2023-10-25 08:24:55,799 DEV : loss 0.393858402967453 - f1-score (micro avg) 0.6654 | |
| 2023-10-25 08:24:55,821 saving best model | |
| 2023-10-25 08:24:56,521 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:25:12,728 epoch 10 - iter 180/1809 - loss 0.00196544 - time (sec): 16.21 - samples/sec: 2353.56 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 08:25:28,376 epoch 10 - iter 360/1809 - loss 0.00228683 - time (sec): 31.85 - samples/sec: 2391.48 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 08:25:44,475 epoch 10 - iter 540/1809 - loss 0.00299234 - time (sec): 47.95 - samples/sec: 2361.65 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 08:26:00,434 epoch 10 - iter 720/1809 - loss 0.00293109 - time (sec): 63.91 - samples/sec: 2370.47 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 08:26:16,100 epoch 10 - iter 900/1809 - loss 0.00302326 - time (sec): 79.58 - samples/sec: 2361.79 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 08:26:31,796 epoch 10 - iter 1080/1809 - loss 0.00327400 - time (sec): 95.27 - samples/sec: 2365.70 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 08:26:47,735 epoch 10 - iter 1260/1809 - loss 0.00338707 - time (sec): 111.21 - samples/sec: 2357.01 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 08:27:03,951 epoch 10 - iter 1440/1809 - loss 0.00361125 - time (sec): 127.43 - samples/sec: 2361.94 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 08:27:20,042 epoch 10 - iter 1620/1809 - loss 0.00365904 - time (sec): 143.52 - samples/sec: 2367.04 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 08:27:36,103 epoch 10 - iter 1800/1809 - loss 0.00356670 - time (sec): 159.58 - samples/sec: 2371.48 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 08:27:36,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:27:36,804 EPOCH 10 done: loss 0.0036 - lr: 0.000000 | |
| 2023-10-25 08:27:41,566 DEV : loss 0.40507274866104126 - f1-score (micro avg) 0.6612 | |
| 2023-10-25 08:27:42,142 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 08:27:42,143 Loading model from best epoch ... | |
| 2023-10-25 08:27:44,091 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org | |
| 2023-10-25 08:27:50,312 | |
| Results: | |
| - F-score (micro) 0.6545 | |
| - F-score (macro) 0.5095 | |
| - Accuracy 0.4987 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.6376 0.7919 0.7064 591 | |
| pers 0.5787 0.7619 0.6578 357 | |
| org 0.1791 0.1519 0.1644 79 | |
| micro avg 0.5917 0.7322 0.6545 1027 | |
| macro avg 0.4651 0.5686 0.5095 1027 | |
| weighted avg 0.5819 0.7322 0.6478 1027 | |
| 2023-10-25 08:27:50,312 ---------------------------------------------------------------------------------------------------- | |