| 2023-10-23 19:16:53,810 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,811 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=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Train: 966 sentences | |
| 2023-10-23 19:16:53,812 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Training Params: | |
| 2023-10-23 19:16:53,812 - learning_rate: "5e-05" | |
| 2023-10-23 19:16:53,812 - mini_batch_size: "8" | |
| 2023-10-23 19:16:53,812 - max_epochs: "10" | |
| 2023-10-23 19:16:53,812 - shuffle: "True" | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Plugins: | |
| 2023-10-23 19:16:53,812 - TensorboardLogger | |
| 2023-10-23 19:16:53,812 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 19:16:53,812 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Computation: | |
| 2023-10-23 19:16:53,812 - compute on device: cuda:0 | |
| 2023-10-23 19:16:53,812 - embedding storage: none | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1" | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,812 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:16:53,813 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 19:16:54,860 epoch 1 - iter 12/121 - loss 3.70276262 - time (sec): 1.05 - samples/sec: 2270.31 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:16:55,939 epoch 1 - iter 24/121 - loss 2.94388750 - time (sec): 2.13 - samples/sec: 2170.37 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:16:56,993 epoch 1 - iter 36/121 - loss 2.14431472 - time (sec): 3.18 - samples/sec: 2245.23 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:16:58,101 epoch 1 - iter 48/121 - loss 1.72480650 - time (sec): 4.29 - samples/sec: 2348.26 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:16:59,086 epoch 1 - iter 60/121 - loss 1.52035465 - time (sec): 5.27 - samples/sec: 2303.07 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:17:00,187 epoch 1 - iter 72/121 - loss 1.33210475 - time (sec): 6.37 - samples/sec: 2294.42 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:17:01,246 epoch 1 - iter 84/121 - loss 1.20099635 - time (sec): 7.43 - samples/sec: 2280.42 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:17:02,345 epoch 1 - iter 96/121 - loss 1.07387613 - time (sec): 8.53 - samples/sec: 2299.86 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 19:17:03,427 epoch 1 - iter 108/121 - loss 0.98002301 - time (sec): 9.61 - samples/sec: 2296.51 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 19:17:04,469 epoch 1 - iter 120/121 - loss 0.90647831 - time (sec): 10.66 - samples/sec: 2302.02 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:17:04,543 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:04,544 EPOCH 1 done: loss 0.8991 - lr: 0.000049 | |
| 2023-10-23 19:17:05,376 DEV : loss 0.18442463874816895 - f1-score (micro avg) 0.6868 | |
| 2023-10-23 19:17:05,381 saving best model | |
| 2023-10-23 19:17:05,868 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:06,928 epoch 2 - iter 12/121 - loss 0.15705501 - time (sec): 1.06 - samples/sec: 2168.99 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:17:08,035 epoch 2 - iter 24/121 - loss 0.13657685 - time (sec): 2.17 - samples/sec: 2214.74 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 19:17:09,109 epoch 2 - iter 36/121 - loss 0.14488585 - time (sec): 3.24 - samples/sec: 2260.59 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 19:17:10,171 epoch 2 - iter 48/121 - loss 0.15283456 - time (sec): 4.30 - samples/sec: 2183.19 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 19:17:11,332 epoch 2 - iter 60/121 - loss 0.15273878 - time (sec): 5.46 - samples/sec: 2225.64 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 19:17:12,301 epoch 2 - iter 72/121 - loss 0.15603911 - time (sec): 6.43 - samples/sec: 2222.49 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 19:17:13,332 epoch 2 - iter 84/121 - loss 0.15252101 - time (sec): 7.46 - samples/sec: 2261.11 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 19:17:14,480 epoch 2 - iter 96/121 - loss 0.15153949 - time (sec): 8.61 - samples/sec: 2281.76 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 19:17:15,522 epoch 2 - iter 108/121 - loss 0.14821059 - time (sec): 9.65 - samples/sec: 2278.10 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 19:17:16,625 epoch 2 - iter 120/121 - loss 0.14288083 - time (sec): 10.76 - samples/sec: 2287.83 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 19:17:16,696 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:16,697 EPOCH 2 done: loss 0.1424 - lr: 0.000045 | |
| 2023-10-23 19:17:17,402 DEV : loss 0.11657055467367172 - f1-score (micro avg) 0.7735 | |
| 2023-10-23 19:17:17,406 saving best model | |
| 2023-10-23 19:17:18,089 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:19,070 epoch 3 - iter 12/121 - loss 0.08238361 - time (sec): 0.98 - samples/sec: 2252.66 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 19:17:20,133 epoch 3 - iter 24/121 - loss 0.08198313 - time (sec): 2.04 - samples/sec: 2274.97 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 19:17:21,336 epoch 3 - iter 36/121 - loss 0.09209441 - time (sec): 3.25 - samples/sec: 2217.70 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 19:17:22,436 epoch 3 - iter 48/121 - loss 0.09095958 - time (sec): 4.35 - samples/sec: 2210.50 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 19:17:23,484 epoch 3 - iter 60/121 - loss 0.09157820 - time (sec): 5.39 - samples/sec: 2235.27 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 19:17:24,578 epoch 3 - iter 72/121 - loss 0.08770180 - time (sec): 6.49 - samples/sec: 2251.10 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 19:17:25,710 epoch 3 - iter 84/121 - loss 0.08228471 - time (sec): 7.62 - samples/sec: 2227.99 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 19:17:26,830 epoch 3 - iter 96/121 - loss 0.08072554 - time (sec): 8.74 - samples/sec: 2258.26 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 19:17:27,828 epoch 3 - iter 108/121 - loss 0.08348649 - time (sec): 9.74 - samples/sec: 2269.70 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 19:17:28,958 epoch 3 - iter 120/121 - loss 0.08324832 - time (sec): 10.87 - samples/sec: 2262.21 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 19:17:29,035 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:29,036 EPOCH 3 done: loss 0.0828 - lr: 0.000039 | |
| 2023-10-23 19:17:29,746 DEV : loss 0.12160609662532806 - f1-score (micro avg) 0.8191 | |
| 2023-10-23 19:17:29,750 saving best model | |
| 2023-10-23 19:17:30,362 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:31,428 epoch 4 - iter 12/121 - loss 0.04546451 - time (sec): 1.06 - samples/sec: 2196.28 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 19:17:32,597 epoch 4 - iter 24/121 - loss 0.06098250 - time (sec): 2.23 - samples/sec: 2185.14 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 19:17:33,672 epoch 4 - iter 36/121 - loss 0.05602913 - time (sec): 3.31 - samples/sec: 2214.07 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 19:17:34,748 epoch 4 - iter 48/121 - loss 0.05772828 - time (sec): 4.39 - samples/sec: 2250.27 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 19:17:35,830 epoch 4 - iter 60/121 - loss 0.05350712 - time (sec): 5.47 - samples/sec: 2300.81 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 19:17:36,946 epoch 4 - iter 72/121 - loss 0.05555258 - time (sec): 6.58 - samples/sec: 2314.94 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 19:17:37,930 epoch 4 - iter 84/121 - loss 0.05687203 - time (sec): 7.57 - samples/sec: 2300.44 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 19:17:38,978 epoch 4 - iter 96/121 - loss 0.05775887 - time (sec): 8.61 - samples/sec: 2296.05 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 19:17:40,075 epoch 4 - iter 108/121 - loss 0.05928323 - time (sec): 9.71 - samples/sec: 2297.60 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:17:41,104 epoch 4 - iter 120/121 - loss 0.05753039 - time (sec): 10.74 - samples/sec: 2297.05 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 19:17:41,170 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:41,170 EPOCH 4 done: loss 0.0574 - lr: 0.000034 | |
| 2023-10-23 19:17:41,877 DEV : loss 0.13370861113071442 - f1-score (micro avg) 0.846 | |
| 2023-10-23 19:17:41,881 saving best model | |
| 2023-10-23 19:17:42,498 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:43,607 epoch 5 - iter 12/121 - loss 0.03795536 - time (sec): 1.11 - samples/sec: 2037.39 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 19:17:44,666 epoch 5 - iter 24/121 - loss 0.04199710 - time (sec): 2.17 - samples/sec: 2151.57 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 19:17:45,727 epoch 5 - iter 36/121 - loss 0.04063135 - time (sec): 3.23 - samples/sec: 2183.68 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 19:17:46,828 epoch 5 - iter 48/121 - loss 0.04131379 - time (sec): 4.33 - samples/sec: 2223.47 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 19:17:48,013 epoch 5 - iter 60/121 - loss 0.04224433 - time (sec): 5.51 - samples/sec: 2249.93 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 19:17:49,089 epoch 5 - iter 72/121 - loss 0.04511043 - time (sec): 6.59 - samples/sec: 2245.11 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:17:50,147 epoch 5 - iter 84/121 - loss 0.04148152 - time (sec): 7.65 - samples/sec: 2261.72 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 19:17:51,189 epoch 5 - iter 96/121 - loss 0.04159397 - time (sec): 8.69 - samples/sec: 2256.58 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:17:52,225 epoch 5 - iter 108/121 - loss 0.04023066 - time (sec): 9.73 - samples/sec: 2262.81 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 19:17:53,290 epoch 5 - iter 120/121 - loss 0.03970280 - time (sec): 10.79 - samples/sec: 2270.68 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 19:17:53,378 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:53,378 EPOCH 5 done: loss 0.0399 - lr: 0.000028 | |
| 2023-10-23 19:17:54,086 DEV : loss 0.15133920311927795 - f1-score (micro avg) 0.8446 | |
| 2023-10-23 19:17:54,091 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:17:55,186 epoch 6 - iter 12/121 - loss 0.02447443 - time (sec): 1.09 - samples/sec: 2281.68 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:17:56,257 epoch 6 - iter 24/121 - loss 0.02866063 - time (sec): 2.16 - samples/sec: 2292.94 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 19:17:57,361 epoch 6 - iter 36/121 - loss 0.02466423 - time (sec): 3.27 - samples/sec: 2227.08 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:17:58,323 epoch 6 - iter 48/121 - loss 0.02453619 - time (sec): 4.23 - samples/sec: 2253.25 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 19:17:59,502 epoch 6 - iter 60/121 - loss 0.02414396 - time (sec): 5.41 - samples/sec: 2276.41 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:18:00,637 epoch 6 - iter 72/121 - loss 0.02532751 - time (sec): 6.55 - samples/sec: 2254.28 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 19:18:01,786 epoch 6 - iter 84/121 - loss 0.02501141 - time (sec): 7.69 - samples/sec: 2216.56 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:18:02,857 epoch 6 - iter 96/121 - loss 0.02620381 - time (sec): 8.77 - samples/sec: 2237.47 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 19:18:03,974 epoch 6 - iter 108/121 - loss 0.02653234 - time (sec): 9.88 - samples/sec: 2223.71 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 19:18:05,062 epoch 6 - iter 120/121 - loss 0.02794705 - time (sec): 10.97 - samples/sec: 2239.31 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:18:05,131 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:05,132 EPOCH 6 done: loss 0.0279 - lr: 0.000022 | |
| 2023-10-23 19:18:05,992 DEV : loss 0.14656664431095123 - f1-score (micro avg) 0.8522 | |
| 2023-10-23 19:18:05,996 saving best model | |
| 2023-10-23 19:18:06,638 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:07,720 epoch 7 - iter 12/121 - loss 0.01613967 - time (sec): 1.08 - samples/sec: 2476.21 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 19:18:08,819 epoch 7 - iter 24/121 - loss 0.01984545 - time (sec): 2.18 - samples/sec: 2331.63 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:18:09,900 epoch 7 - iter 36/121 - loss 0.01834316 - time (sec): 3.26 - samples/sec: 2305.23 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 19:18:10,999 epoch 7 - iter 48/121 - loss 0.01661789 - time (sec): 4.36 - samples/sec: 2300.87 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:18:12,044 epoch 7 - iter 60/121 - loss 0.01760996 - time (sec): 5.40 - samples/sec: 2298.50 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 19:18:13,220 epoch 7 - iter 72/121 - loss 0.01879381 - time (sec): 6.58 - samples/sec: 2251.54 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:18:14,262 epoch 7 - iter 84/121 - loss 0.01780585 - time (sec): 7.62 - samples/sec: 2270.88 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 19:18:15,353 epoch 7 - iter 96/121 - loss 0.01714403 - time (sec): 8.71 - samples/sec: 2268.93 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 19:18:16,368 epoch 7 - iter 108/121 - loss 0.01812978 - time (sec): 9.73 - samples/sec: 2274.32 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:18:17,435 epoch 7 - iter 120/121 - loss 0.01793965 - time (sec): 10.80 - samples/sec: 2274.95 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 19:18:17,503 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:17,504 EPOCH 7 done: loss 0.0193 - lr: 0.000017 | |
| 2023-10-23 19:18:18,201 DEV : loss 0.18479269742965698 - f1-score (micro avg) 0.8539 | |
| 2023-10-23 19:18:18,205 saving best model | |
| 2023-10-23 19:18:18,809 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:19,886 epoch 8 - iter 12/121 - loss 0.01658824 - time (sec): 1.08 - samples/sec: 2310.61 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:18:20,994 epoch 8 - iter 24/121 - loss 0.01445413 - time (sec): 2.18 - samples/sec: 2277.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 19:18:22,068 epoch 8 - iter 36/121 - loss 0.01111450 - time (sec): 3.26 - samples/sec: 2253.49 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:18:23,079 epoch 8 - iter 48/121 - loss 0.01111916 - time (sec): 4.27 - samples/sec: 2282.85 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 19:18:24,085 epoch 8 - iter 60/121 - loss 0.01083118 - time (sec): 5.27 - samples/sec: 2267.00 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:18:25,103 epoch 8 - iter 72/121 - loss 0.01159512 - time (sec): 6.29 - samples/sec: 2296.82 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 19:18:26,208 epoch 8 - iter 84/121 - loss 0.01313584 - time (sec): 7.40 - samples/sec: 2297.06 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:18:27,351 epoch 8 - iter 96/121 - loss 0.01196163 - time (sec): 8.54 - samples/sec: 2317.34 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 19:18:28,377 epoch 8 - iter 108/121 - loss 0.01122020 - time (sec): 9.57 - samples/sec: 2325.53 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 19:18:29,426 epoch 8 - iter 120/121 - loss 0.01269033 - time (sec): 10.62 - samples/sec: 2306.08 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:18:29,541 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:29,541 EPOCH 8 done: loss 0.0126 - lr: 0.000011 | |
| 2023-10-23 19:18:30,241 DEV : loss 0.19710467755794525 - f1-score (micro avg) 0.8424 | |
| 2023-10-23 19:18:30,245 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:31,235 epoch 9 - iter 12/121 - loss 0.01794818 - time (sec): 0.99 - samples/sec: 2435.01 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 19:18:32,276 epoch 9 - iter 24/121 - loss 0.01251622 - time (sec): 2.03 - samples/sec: 2419.60 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:18:33,383 epoch 9 - iter 36/121 - loss 0.00847168 - time (sec): 3.14 - samples/sec: 2357.98 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 19:18:34,465 epoch 9 - iter 48/121 - loss 0.00852648 - time (sec): 4.22 - samples/sec: 2390.40 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:18:35,515 epoch 9 - iter 60/121 - loss 0.01017054 - time (sec): 5.27 - samples/sec: 2364.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 19:18:36,635 epoch 9 - iter 72/121 - loss 0.00894353 - time (sec): 6.39 - samples/sec: 2360.02 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:18:37,664 epoch 9 - iter 84/121 - loss 0.00789992 - time (sec): 7.42 - samples/sec: 2350.40 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 19:18:38,698 epoch 9 - iter 96/121 - loss 0.00788349 - time (sec): 8.45 - samples/sec: 2357.86 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 19:18:39,793 epoch 9 - iter 108/121 - loss 0.00834119 - time (sec): 9.55 - samples/sec: 2314.69 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:18:40,873 epoch 9 - iter 120/121 - loss 0.00822010 - time (sec): 10.63 - samples/sec: 2318.95 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 19:18:40,946 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:40,947 EPOCH 9 done: loss 0.0082 - lr: 0.000006 | |
| 2023-10-23 19:18:41,647 DEV : loss 0.2059398740530014 - f1-score (micro avg) 0.8354 | |
| 2023-10-23 19:18:41,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:42,828 epoch 10 - iter 12/121 - loss 0.00397773 - time (sec): 1.18 - samples/sec: 2221.89 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:18:43,931 epoch 10 - iter 24/121 - loss 0.00493849 - time (sec): 2.28 - samples/sec: 2261.14 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 19:18:44,978 epoch 10 - iter 36/121 - loss 0.00334518 - time (sec): 3.33 - samples/sec: 2351.77 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:18:46,067 epoch 10 - iter 48/121 - loss 0.00273462 - time (sec): 4.42 - samples/sec: 2344.85 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 19:18:47,158 epoch 10 - iter 60/121 - loss 0.00482458 - time (sec): 5.51 - samples/sec: 2334.56 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:18:48,231 epoch 10 - iter 72/121 - loss 0.00411537 - time (sec): 6.58 - samples/sec: 2316.05 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 19:18:49,216 epoch 10 - iter 84/121 - loss 0.00517085 - time (sec): 7.56 - samples/sec: 2302.06 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 19:18:50,215 epoch 10 - iter 96/121 - loss 0.00461560 - time (sec): 8.56 - samples/sec: 2316.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:18:51,284 epoch 10 - iter 108/121 - loss 0.00542344 - time (sec): 9.63 - samples/sec: 2319.31 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 19:18:52,308 epoch 10 - iter 120/121 - loss 0.00506168 - time (sec): 10.66 - samples/sec: 2310.54 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 19:18:52,370 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:52,371 EPOCH 10 done: loss 0.0050 - lr: 0.000000 | |
| 2023-10-23 19:18:53,071 DEV : loss 0.2112000286579132 - f1-score (micro avg) 0.8385 | |
| 2023-10-23 19:18:53,545 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 19:18:53,546 Loading model from best epoch ... | |
| 2023-10-23 19:18:55,021 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-23 19:18:55,887 | |
| Results: | |
| - F-score (micro) 0.8146 | |
| - F-score (macro) 0.5846 | |
| - Accuracy 0.7066 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.8378 0.8921 0.8641 139 | |
| scope 0.8321 0.8837 0.8571 129 | |
| work 0.6593 0.7500 0.7018 80 | |
| loc 1.0000 0.3333 0.5000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.7942 0.8361 0.8146 360 | |
| macro avg 0.6659 0.5718 0.5846 360 | |
| weighted avg 0.7932 0.8361 0.8092 360 | |
| 2023-10-23 19:18:55,887 ---------------------------------------------------------------------------------------------------- | |