| 2023-10-25 10:42:24,196 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 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 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 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 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Train: 14465 sentences | |
| 2023-10-25 10:42:24,197 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Training Params: | |
| 2023-10-25 10:42:24,197 - learning_rate: "5e-05" | |
| 2023-10-25 10:42:24,197 - mini_batch_size: "8" | |
| 2023-10-25 10:42:24,197 - max_epochs: "10" | |
| 2023-10-25 10:42:24,197 - shuffle: "True" | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Plugins: | |
| 2023-10-25 10:42:24,197 - TensorboardLogger | |
| 2023-10-25 10:42:24,197 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 10:42:24,197 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Computation: | |
| 2023-10-25 10:42:24,197 - compute on device: cuda:0 | |
| 2023-10-25 10:42:24,197 - embedding storage: none | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:42:24,198 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 10:42:39,798 epoch 1 - iter 180/1809 - loss 1.08864236 - time (sec): 15.60 - samples/sec: 2462.39 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 10:42:55,362 epoch 1 - iter 360/1809 - loss 0.63737072 - time (sec): 31.16 - samples/sec: 2435.51 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 10:43:11,204 epoch 1 - iter 540/1809 - loss 0.47500323 - time (sec): 47.01 - samples/sec: 2422.29 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 10:43:26,982 epoch 1 - iter 720/1809 - loss 0.38842572 - time (sec): 62.78 - samples/sec: 2405.92 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 10:43:42,388 epoch 1 - iter 900/1809 - loss 0.33612833 - time (sec): 78.19 - samples/sec: 2392.53 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 10:43:58,152 epoch 1 - iter 1080/1809 - loss 0.29705344 - time (sec): 93.95 - samples/sec: 2390.75 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 10:44:14,538 epoch 1 - iter 1260/1809 - loss 0.26939451 - time (sec): 110.34 - samples/sec: 2392.79 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 10:44:30,974 epoch 1 - iter 1440/1809 - loss 0.24905179 - time (sec): 126.78 - samples/sec: 2389.57 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 10:44:46,901 epoch 1 - iter 1620/1809 - loss 0.23268593 - time (sec): 142.70 - samples/sec: 2385.14 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 10:45:02,841 epoch 1 - iter 1800/1809 - loss 0.21934057 - time (sec): 158.64 - samples/sec: 2384.02 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 10:45:03,516 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:45:03,517 EPOCH 1 done: loss 0.2188 - lr: 0.000050 | |
| 2023-10-25 10:45:08,070 DEV : loss 0.12551043927669525 - f1-score (micro avg) 0.595 | |
| 2023-10-25 10:45:08,092 saving best model | |
| 2023-10-25 10:45:08,652 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:45:24,334 epoch 2 - iter 180/1809 - loss 0.09357098 - time (sec): 15.68 - samples/sec: 2407.94 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 10:45:40,596 epoch 2 - iter 360/1809 - loss 0.09016993 - time (sec): 31.94 - samples/sec: 2403.78 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 10:45:56,781 epoch 2 - iter 540/1809 - loss 0.09172432 - time (sec): 48.13 - samples/sec: 2396.27 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 10:46:12,794 epoch 2 - iter 720/1809 - loss 0.09158145 - time (sec): 64.14 - samples/sec: 2398.33 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 10:46:28,593 epoch 2 - iter 900/1809 - loss 0.09251771 - time (sec): 79.94 - samples/sec: 2389.54 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 10:46:44,259 epoch 2 - iter 1080/1809 - loss 0.09131020 - time (sec): 95.61 - samples/sec: 2395.09 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 10:46:59,923 epoch 2 - iter 1260/1809 - loss 0.09065843 - time (sec): 111.27 - samples/sec: 2387.06 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 10:47:15,682 epoch 2 - iter 1440/1809 - loss 0.09009273 - time (sec): 127.03 - samples/sec: 2386.49 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 10:47:31,440 epoch 2 - iter 1620/1809 - loss 0.08870597 - time (sec): 142.79 - samples/sec: 2389.70 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 10:47:47,438 epoch 2 - iter 1800/1809 - loss 0.08734034 - time (sec): 158.79 - samples/sec: 2380.41 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 10:47:48,319 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:47:48,320 EPOCH 2 done: loss 0.0871 - lr: 0.000044 | |
| 2023-10-25 10:47:53,589 DEV : loss 0.12736038863658905 - f1-score (micro avg) 0.6164 | |
| 2023-10-25 10:47:53,611 saving best model | |
| 2023-10-25 10:47:54,320 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:48:10,502 epoch 3 - iter 180/1809 - loss 0.07791949 - time (sec): 16.18 - samples/sec: 2440.64 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 10:48:26,551 epoch 3 - iter 360/1809 - loss 0.07255591 - time (sec): 32.23 - samples/sec: 2434.36 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 10:48:42,860 epoch 3 - iter 540/1809 - loss 0.07280647 - time (sec): 48.54 - samples/sec: 2416.45 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 10:48:58,313 epoch 3 - iter 720/1809 - loss 0.06999820 - time (sec): 63.99 - samples/sec: 2405.21 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 10:49:14,210 epoch 3 - iter 900/1809 - loss 0.06882067 - time (sec): 79.89 - samples/sec: 2398.64 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 10:49:29,782 epoch 3 - iter 1080/1809 - loss 0.06780427 - time (sec): 95.46 - samples/sec: 2391.39 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 10:49:45,430 epoch 3 - iter 1260/1809 - loss 0.06627869 - time (sec): 111.11 - samples/sec: 2384.04 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 10:50:01,822 epoch 3 - iter 1440/1809 - loss 0.06607504 - time (sec): 127.50 - samples/sec: 2375.41 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 10:50:17,479 epoch 3 - iter 1620/1809 - loss 0.06532994 - time (sec): 143.16 - samples/sec: 2381.32 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 10:50:33,050 epoch 3 - iter 1800/1809 - loss 0.06483682 - time (sec): 158.73 - samples/sec: 2383.21 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 10:50:33,799 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:50:33,799 EPOCH 3 done: loss 0.0649 - lr: 0.000039 | |
| 2023-10-25 10:50:38,557 DEV : loss 0.13015878200531006 - f1-score (micro avg) 0.6083 | |
| 2023-10-25 10:50:38,579 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:50:54,622 epoch 4 - iter 180/1809 - loss 0.04109198 - time (sec): 16.04 - samples/sec: 2401.20 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 10:51:10,400 epoch 4 - iter 360/1809 - loss 0.04019791 - time (sec): 31.82 - samples/sec: 2393.98 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 10:51:26,181 epoch 4 - iter 540/1809 - loss 0.04111006 - time (sec): 47.60 - samples/sec: 2401.38 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 10:51:41,964 epoch 4 - iter 720/1809 - loss 0.04191859 - time (sec): 63.38 - samples/sec: 2379.87 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 10:51:57,954 epoch 4 - iter 900/1809 - loss 0.04474768 - time (sec): 79.37 - samples/sec: 2381.93 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 10:52:13,744 epoch 4 - iter 1080/1809 - loss 0.04597864 - time (sec): 95.16 - samples/sec: 2371.18 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 10:52:29,289 epoch 4 - iter 1260/1809 - loss 0.04532760 - time (sec): 110.71 - samples/sec: 2374.95 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 10:52:45,599 epoch 4 - iter 1440/1809 - loss 0.04474968 - time (sec): 127.02 - samples/sec: 2360.69 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 10:53:01,795 epoch 4 - iter 1620/1809 - loss 0.04456366 - time (sec): 143.21 - samples/sec: 2366.29 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 10:53:17,695 epoch 4 - iter 1800/1809 - loss 0.04497375 - time (sec): 159.11 - samples/sec: 2376.49 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 10:53:18,468 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:53:18,469 EPOCH 4 done: loss 0.0450 - lr: 0.000033 | |
| 2023-10-25 10:53:23,224 DEV : loss 0.23449285328388214 - f1-score (micro avg) 0.5643 | |
| 2023-10-25 10:53:23,246 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:53:39,283 epoch 5 - iter 180/1809 - loss 0.11798032 - time (sec): 16.04 - samples/sec: 2458.47 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 10:53:55,130 epoch 5 - iter 360/1809 - loss 0.09384126 - time (sec): 31.88 - samples/sec: 2408.73 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 10:54:10,990 epoch 5 - iter 540/1809 - loss 0.07744584 - time (sec): 47.74 - samples/sec: 2388.60 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 10:54:26,505 epoch 5 - iter 720/1809 - loss 0.08471679 - time (sec): 63.26 - samples/sec: 2396.43 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 10:54:42,213 epoch 5 - iter 900/1809 - loss 0.09678449 - time (sec): 78.97 - samples/sec: 2398.43 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 10:54:58,597 epoch 5 - iter 1080/1809 - loss 0.09685579 - time (sec): 95.35 - samples/sec: 2396.32 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 10:55:14,316 epoch 5 - iter 1260/1809 - loss 0.09900587 - time (sec): 111.07 - samples/sec: 2388.46 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 10:55:30,081 epoch 5 - iter 1440/1809 - loss 0.10576125 - time (sec): 126.83 - samples/sec: 2388.49 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 10:55:45,766 epoch 5 - iter 1620/1809 - loss 0.11334555 - time (sec): 142.52 - samples/sec: 2382.86 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 10:56:01,695 epoch 5 - iter 1800/1809 - loss 0.11935313 - time (sec): 158.45 - samples/sec: 2386.46 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 10:56:02,462 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:56:02,462 EPOCH 5 done: loss 0.1197 - lr: 0.000028 | |
| 2023-10-25 10:56:07,710 DEV : loss 0.22438712418079376 - f1-score (micro avg) 0.3385 | |
| 2023-10-25 10:56:07,732 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:56:23,701 epoch 6 - iter 180/1809 - loss 0.13593977 - time (sec): 15.97 - samples/sec: 2374.30 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 10:56:39,782 epoch 6 - iter 360/1809 - loss 0.11374633 - time (sec): 32.05 - samples/sec: 2397.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 10:56:55,834 epoch 6 - iter 540/1809 - loss 0.10944967 - time (sec): 48.10 - samples/sec: 2399.11 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 10:57:11,763 epoch 6 - iter 720/1809 - loss 0.13307279 - time (sec): 64.03 - samples/sec: 2395.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 10:57:27,269 epoch 6 - iter 900/1809 - loss 0.14472156 - time (sec): 79.54 - samples/sec: 2392.63 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 10:57:43,006 epoch 6 - iter 1080/1809 - loss 0.14546492 - time (sec): 95.27 - samples/sec: 2388.10 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 10:57:58,783 epoch 6 - iter 1260/1809 - loss 0.14276182 - time (sec): 111.05 - samples/sec: 2382.48 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 10:58:14,861 epoch 6 - iter 1440/1809 - loss 0.13027593 - time (sec): 127.13 - samples/sec: 2387.70 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 10:58:30,584 epoch 6 - iter 1620/1809 - loss 0.12180313 - time (sec): 142.85 - samples/sec: 2386.56 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 10:58:46,528 epoch 6 - iter 1800/1809 - loss 0.11629211 - time (sec): 158.80 - samples/sec: 2381.42 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 10:58:47,311 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:58:47,312 EPOCH 6 done: loss 0.1159 - lr: 0.000022 | |
| 2023-10-25 10:58:52,577 DEV : loss 0.23836202919483185 - f1-score (micro avg) 0.5285 | |
| 2023-10-25 10:58:52,599 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 10:59:08,273 epoch 7 - iter 180/1809 - loss 0.05953192 - time (sec): 15.67 - samples/sec: 2390.84 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 10:59:24,137 epoch 7 - iter 360/1809 - loss 0.06041906 - time (sec): 31.54 - samples/sec: 2347.48 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 10:59:40,181 epoch 7 - iter 540/1809 - loss 0.06633058 - time (sec): 47.58 - samples/sec: 2329.88 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 10:59:55,826 epoch 7 - iter 720/1809 - loss 0.06758924 - time (sec): 63.23 - samples/sec: 2345.81 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 11:00:12,024 epoch 7 - iter 900/1809 - loss 0.06923090 - time (sec): 79.42 - samples/sec: 2348.03 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 11:00:27,650 epoch 7 - iter 1080/1809 - loss 0.06847767 - time (sec): 95.05 - samples/sec: 2350.34 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 11:00:43,756 epoch 7 - iter 1260/1809 - loss 0.06519470 - time (sec): 111.16 - samples/sec: 2354.86 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 11:01:00,077 epoch 7 - iter 1440/1809 - loss 0.06291968 - time (sec): 127.48 - samples/sec: 2362.89 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 11:01:15,563 epoch 7 - iter 1620/1809 - loss 0.06280369 - time (sec): 142.96 - samples/sec: 2372.87 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 11:01:31,725 epoch 7 - iter 1800/1809 - loss 0.06011227 - time (sec): 159.12 - samples/sec: 2377.28 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 11:01:32,510 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:01:32,510 EPOCH 7 done: loss 0.0601 - lr: 0.000017 | |
| 2023-10-25 11:01:37,792 DEV : loss 0.25131794810295105 - f1-score (micro avg) 0.5408 | |
| 2023-10-25 11:01:37,814 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:01:53,779 epoch 8 - iter 180/1809 - loss 0.01859667 - time (sec): 15.96 - samples/sec: 2421.30 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 11:02:09,497 epoch 8 - iter 360/1809 - loss 0.02439411 - time (sec): 31.68 - samples/sec: 2406.52 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 11:02:25,696 epoch 8 - iter 540/1809 - loss 0.02666204 - time (sec): 47.88 - samples/sec: 2383.15 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 11:02:41,394 epoch 8 - iter 720/1809 - loss 0.03108643 - time (sec): 63.58 - samples/sec: 2379.68 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 11:02:57,230 epoch 8 - iter 900/1809 - loss 0.03146788 - time (sec): 79.42 - samples/sec: 2379.80 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 11:03:13,381 epoch 8 - iter 1080/1809 - loss 0.03266776 - time (sec): 95.57 - samples/sec: 2388.45 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 11:03:29,042 epoch 8 - iter 1260/1809 - loss 0.03363994 - time (sec): 111.23 - samples/sec: 2391.56 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 11:03:44,858 epoch 8 - iter 1440/1809 - loss 0.03353747 - time (sec): 127.04 - samples/sec: 2394.81 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 11:04:00,459 epoch 8 - iter 1620/1809 - loss 0.03451516 - time (sec): 142.64 - samples/sec: 2393.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 11:04:16,154 epoch 8 - iter 1800/1809 - loss 0.03533870 - time (sec): 158.34 - samples/sec: 2387.59 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 11:04:16,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:04:16,986 EPOCH 8 done: loss 0.0353 - lr: 0.000011 | |
| 2023-10-25 11:04:22,282 DEV : loss 0.2803691029548645 - f1-score (micro avg) 0.5162 | |
| 2023-10-25 11:04:22,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:04:38,035 epoch 9 - iter 180/1809 - loss 0.04227779 - time (sec): 15.73 - samples/sec: 2359.95 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 11:04:53,886 epoch 9 - iter 360/1809 - loss 0.03812442 - time (sec): 31.58 - samples/sec: 2363.59 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 11:05:09,537 epoch 9 - iter 540/1809 - loss 0.03623853 - time (sec): 47.23 - samples/sec: 2371.61 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 11:05:25,709 epoch 9 - iter 720/1809 - loss 0.03584853 - time (sec): 63.40 - samples/sec: 2381.00 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 11:05:41,500 epoch 9 - iter 900/1809 - loss 0.03443228 - time (sec): 79.20 - samples/sec: 2386.06 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 11:05:57,949 epoch 9 - iter 1080/1809 - loss 0.03283348 - time (sec): 95.64 - samples/sec: 2383.97 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 11:06:14,072 epoch 9 - iter 1260/1809 - loss 0.03344930 - time (sec): 111.77 - samples/sec: 2378.11 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 11:06:30,047 epoch 9 - iter 1440/1809 - loss 0.03338922 - time (sec): 127.74 - samples/sec: 2380.90 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 11:06:45,210 epoch 9 - iter 1620/1809 - loss 0.03462184 - time (sec): 142.91 - samples/sec: 2379.23 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 11:07:00,995 epoch 9 - iter 1800/1809 - loss 0.03463472 - time (sec): 158.69 - samples/sec: 2383.29 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 11:07:01,773 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:07:01,773 EPOCH 9 done: loss 0.0347 - lr: 0.000006 | |
| 2023-10-25 11:07:06,528 DEV : loss 0.2776682376861572 - f1-score (micro avg) 0.5031 | |
| 2023-10-25 11:07:06,550 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:07:22,652 epoch 10 - iter 180/1809 - loss 0.02754181 - time (sec): 16.10 - samples/sec: 2301.55 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 11:07:38,870 epoch 10 - iter 360/1809 - loss 0.03479173 - time (sec): 32.32 - samples/sec: 2325.30 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 11:07:55,201 epoch 10 - iter 540/1809 - loss 0.03464083 - time (sec): 48.65 - samples/sec: 2351.22 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 11:08:11,048 epoch 10 - iter 720/1809 - loss 0.03422069 - time (sec): 64.50 - samples/sec: 2358.86 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 11:08:26,946 epoch 10 - iter 900/1809 - loss 0.03352713 - time (sec): 80.40 - samples/sec: 2373.35 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 11:08:42,565 epoch 10 - iter 1080/1809 - loss 0.03377603 - time (sec): 96.01 - samples/sec: 2365.83 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 11:08:58,382 epoch 10 - iter 1260/1809 - loss 0.03388777 - time (sec): 111.83 - samples/sec: 2369.29 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 11:09:14,125 epoch 10 - iter 1440/1809 - loss 0.03414918 - time (sec): 127.57 - samples/sec: 2372.33 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 11:09:30,395 epoch 10 - iter 1620/1809 - loss 0.03466586 - time (sec): 143.84 - samples/sec: 2374.22 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 11:09:46,068 epoch 10 - iter 1800/1809 - loss 0.03590016 - time (sec): 159.52 - samples/sec: 2372.05 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 11:09:46,864 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:46,864 EPOCH 10 done: loss 0.0359 - lr: 0.000000 | |
| 2023-10-25 11:09:51,615 DEV : loss 0.2868908643722534 - f1-score (micro avg) 0.4824 | |
| 2023-10-25 11:09:52,189 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 11:09:52,190 Loading model from best epoch ... | |
| 2023-10-25 11:09:53,952 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 11:10:00,212 | |
| Results: | |
| - F-score (micro) 0.6416 | |
| - F-score (macro) 0.4392 | |
| - Accuracy 0.4784 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.6730 0.7208 0.6961 591 | |
| pers 0.5624 0.6947 0.6216 357 | |
| org 0.0000 0.0000 0.0000 79 | |
| micro avg 0.6276 0.6563 0.6416 1027 | |
| macro avg 0.4118 0.4718 0.4392 1027 | |
| weighted avg 0.5828 0.6563 0.6166 1027 | |
| 2023-10-25 11:10:00,213 ---------------------------------------------------------------------------------------------------- | |