| 2023-10-23 21:51:48,190 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-23 21:51:48,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences | |
| - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator | |
| 2023-10-23 21:51:48,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 Train: 3575 sentences | |
| 2023-10-23 21:51:48,191 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 21:51:48,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 Training Params: | |
| 2023-10-23 21:51:48,191 - learning_rate: "5e-05" | |
| 2023-10-23 21:51:48,191 - mini_batch_size: "8" | |
| 2023-10-23 21:51:48,191 - max_epochs: "10" | |
| 2023-10-23 21:51:48,191 - shuffle: "True" | |
| 2023-10-23 21:51:48,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 Plugins: | |
| 2023-10-23 21:51:48,191 - TensorboardLogger | |
| 2023-10-23 21:51:48,191 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 21:51:48,191 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,191 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 21:51:48,192 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 21:51:48,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,192 Computation: | |
| 2023-10-23 21:51:48,192 - compute on device: cuda:0 | |
| 2023-10-23 21:51:48,192 - embedding storage: none | |
| 2023-10-23 21:51:48,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,192 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" | |
| 2023-10-23 21:51:48,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:51:48,192 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 21:51:51,912 epoch 1 - iter 44/447 - loss 2.29313211 - time (sec): 3.72 - samples/sec: 2237.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:51:56,026 epoch 1 - iter 88/447 - loss 1.38865220 - time (sec): 7.83 - samples/sec: 2193.17 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:51:59,986 epoch 1 - iter 132/447 - loss 1.05659540 - time (sec): 11.79 - samples/sec: 2206.41 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:52:03,902 epoch 1 - iter 176/447 - loss 0.87090716 - time (sec): 15.71 - samples/sec: 2211.45 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:52:08,079 epoch 1 - iter 220/447 - loss 0.75514341 - time (sec): 19.89 - samples/sec: 2202.39 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:52:11,971 epoch 1 - iter 264/447 - loss 0.68444882 - time (sec): 23.78 - samples/sec: 2187.95 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:52:16,054 epoch 1 - iter 308/447 - loss 0.62305335 - time (sec): 27.86 - samples/sec: 2175.18 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 21:52:19,742 epoch 1 - iter 352/447 - loss 0.57516175 - time (sec): 31.55 - samples/sec: 2176.87 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 21:52:23,652 epoch 1 - iter 396/447 - loss 0.53631211 - time (sec): 35.46 - samples/sec: 2171.06 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 21:52:27,765 epoch 1 - iter 440/447 - loss 0.50311971 - time (sec): 39.57 - samples/sec: 2153.98 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:52:28,386 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:52:28,386 EPOCH 1 done: loss 0.4989 - lr: 0.000049 | |
| 2023-10-23 21:52:33,199 DEV : loss 0.15912418067455292 - f1-score (micro avg) 0.6212 | |
| 2023-10-23 21:52:33,219 saving best model | |
| 2023-10-23 21:52:33,690 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:52:37,849 epoch 2 - iter 44/447 - loss 0.16382777 - time (sec): 4.16 - samples/sec: 2262.16 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:52:41,636 epoch 2 - iter 88/447 - loss 0.16917138 - time (sec): 7.95 - samples/sec: 2191.29 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-23 21:52:45,825 epoch 2 - iter 132/447 - loss 0.15404062 - time (sec): 12.13 - samples/sec: 2184.55 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 21:52:49,765 epoch 2 - iter 176/447 - loss 0.14805448 - time (sec): 16.07 - samples/sec: 2172.63 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-23 21:52:53,644 epoch 2 - iter 220/447 - loss 0.15365492 - time (sec): 19.95 - samples/sec: 2183.61 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 21:52:57,585 epoch 2 - iter 264/447 - loss 0.15189904 - time (sec): 23.89 - samples/sec: 2159.40 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-23 21:53:01,367 epoch 2 - iter 308/447 - loss 0.14490678 - time (sec): 27.68 - samples/sec: 2169.16 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 21:53:05,090 epoch 2 - iter 352/447 - loss 0.14359644 - time (sec): 31.40 - samples/sec: 2164.50 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-23 21:53:09,403 epoch 2 - iter 396/447 - loss 0.14016823 - time (sec): 35.71 - samples/sec: 2169.84 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 21:53:13,246 epoch 2 - iter 440/447 - loss 0.13820665 - time (sec): 39.56 - samples/sec: 2156.66 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-23 21:53:13,842 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:53:13,842 EPOCH 2 done: loss 0.1373 - lr: 0.000045 | |
| 2023-10-23 21:53:20,306 DEV : loss 0.14210455119609833 - f1-score (micro avg) 0.7045 | |
| 2023-10-23 21:53:20,326 saving best model | |
| 2023-10-23 21:53:20,913 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:53:25,525 epoch 3 - iter 44/447 - loss 0.06227375 - time (sec): 4.61 - samples/sec: 2261.38 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-23 21:53:29,525 epoch 3 - iter 88/447 - loss 0.07165190 - time (sec): 8.61 - samples/sec: 2207.97 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 21:53:33,454 epoch 3 - iter 132/447 - loss 0.08160062 - time (sec): 12.54 - samples/sec: 2176.12 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-23 21:53:37,270 epoch 3 - iter 176/447 - loss 0.07902211 - time (sec): 16.36 - samples/sec: 2161.58 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 21:53:41,358 epoch 3 - iter 220/447 - loss 0.08062267 - time (sec): 20.44 - samples/sec: 2137.04 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-23 21:53:45,283 epoch 3 - iter 264/447 - loss 0.07920300 - time (sec): 24.37 - samples/sec: 2141.99 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 21:53:49,123 epoch 3 - iter 308/447 - loss 0.07732504 - time (sec): 28.21 - samples/sec: 2170.23 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-23 21:53:52,752 epoch 3 - iter 352/447 - loss 0.07708732 - time (sec): 31.84 - samples/sec: 2155.62 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 21:53:56,778 epoch 3 - iter 396/447 - loss 0.07923155 - time (sec): 35.86 - samples/sec: 2139.98 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-23 21:54:00,715 epoch 3 - iter 440/447 - loss 0.07827057 - time (sec): 39.80 - samples/sec: 2145.05 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-23 21:54:01,263 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:54:01,264 EPOCH 3 done: loss 0.0777 - lr: 0.000039 | |
| 2023-10-23 21:54:07,723 DEV : loss 0.14090511202812195 - f1-score (micro avg) 0.734 | |
| 2023-10-23 21:54:07,743 saving best model | |
| 2023-10-23 21:54:08,333 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:54:12,185 epoch 4 - iter 44/447 - loss 0.03326246 - time (sec): 3.85 - samples/sec: 2188.51 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 21:54:16,012 epoch 4 - iter 88/447 - loss 0.05068608 - time (sec): 7.68 - samples/sec: 2182.23 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-23 21:54:20,213 epoch 4 - iter 132/447 - loss 0.04556488 - time (sec): 11.88 - samples/sec: 2185.55 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 21:54:24,231 epoch 4 - iter 176/447 - loss 0.04645699 - time (sec): 15.90 - samples/sec: 2148.79 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-23 21:54:28,566 epoch 4 - iter 220/447 - loss 0.04553391 - time (sec): 20.23 - samples/sec: 2164.44 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 21:54:32,420 epoch 4 - iter 264/447 - loss 0.04715501 - time (sec): 24.09 - samples/sec: 2150.66 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-23 21:54:36,267 epoch 4 - iter 308/447 - loss 0.04693343 - time (sec): 27.93 - samples/sec: 2140.13 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 21:54:39,947 epoch 4 - iter 352/447 - loss 0.04637201 - time (sec): 31.61 - samples/sec: 2136.49 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-23 21:54:44,126 epoch 4 - iter 396/447 - loss 0.04595036 - time (sec): 35.79 - samples/sec: 2128.05 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-23 21:54:48,078 epoch 4 - iter 440/447 - loss 0.04489916 - time (sec): 39.74 - samples/sec: 2135.48 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 21:54:48,940 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:54:48,941 EPOCH 4 done: loss 0.0446 - lr: 0.000033 | |
| 2023-10-23 21:54:55,383 DEV : loss 0.19732795655727386 - f1-score (micro avg) 0.7408 | |
| 2023-10-23 21:54:55,404 saving best model | |
| 2023-10-23 21:54:55,992 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:54:59,872 epoch 5 - iter 44/447 - loss 0.03250988 - time (sec): 3.88 - samples/sec: 2220.54 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-23 21:55:04,308 epoch 5 - iter 88/447 - loss 0.03182471 - time (sec): 8.32 - samples/sec: 2242.31 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 21:55:08,154 epoch 5 - iter 132/447 - loss 0.02881742 - time (sec): 12.16 - samples/sec: 2208.42 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-23 21:55:12,227 epoch 5 - iter 176/447 - loss 0.02933684 - time (sec): 16.23 - samples/sec: 2194.04 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 21:55:16,129 epoch 5 - iter 220/447 - loss 0.02984464 - time (sec): 20.14 - samples/sec: 2188.03 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-23 21:55:20,190 epoch 5 - iter 264/447 - loss 0.03171971 - time (sec): 24.20 - samples/sec: 2168.03 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 21:55:24,347 epoch 5 - iter 308/447 - loss 0.03032864 - time (sec): 28.35 - samples/sec: 2155.46 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 21:55:28,216 epoch 5 - iter 352/447 - loss 0.03110701 - time (sec): 32.22 - samples/sec: 2139.87 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:55:32,265 epoch 5 - iter 396/447 - loss 0.03273498 - time (sec): 36.27 - samples/sec: 2135.56 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:55:35,982 epoch 5 - iter 440/447 - loss 0.03230073 - time (sec): 39.99 - samples/sec: 2134.87 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:55:36,528 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:55:36,529 EPOCH 5 done: loss 0.0320 - lr: 0.000028 | |
| 2023-10-23 21:55:42,985 DEV : loss 0.20663930475711823 - f1-score (micro avg) 0.764 | |
| 2023-10-23 21:55:43,005 saving best model | |
| 2023-10-23 21:55:43,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:55:48,060 epoch 6 - iter 44/447 - loss 0.01932974 - time (sec): 4.46 - samples/sec: 2089.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:55:51,578 epoch 6 - iter 88/447 - loss 0.02196792 - time (sec): 7.98 - samples/sec: 2098.85 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:55:55,550 epoch 6 - iter 132/447 - loss 0.02780813 - time (sec): 11.95 - samples/sec: 2120.65 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:56:00,231 epoch 6 - iter 176/447 - loss 0.02510854 - time (sec): 16.63 - samples/sec: 2083.70 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:56:04,343 epoch 6 - iter 220/447 - loss 0.02380277 - time (sec): 20.75 - samples/sec: 2081.98 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:56:08,170 epoch 6 - iter 264/447 - loss 0.02441174 - time (sec): 24.57 - samples/sec: 2087.86 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:56:11,950 epoch 6 - iter 308/447 - loss 0.02554501 - time (sec): 28.35 - samples/sec: 2088.99 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:56:15,673 epoch 6 - iter 352/447 - loss 0.02528824 - time (sec): 32.08 - samples/sec: 2110.35 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:56:19,481 epoch 6 - iter 396/447 - loss 0.02554394 - time (sec): 35.88 - samples/sec: 2125.00 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:56:23,611 epoch 6 - iter 440/447 - loss 0.02544473 - time (sec): 40.01 - samples/sec: 2128.70 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:56:24,236 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:56:24,236 EPOCH 6 done: loss 0.0255 - lr: 0.000022 | |
| 2023-10-23 21:56:30,728 DEV : loss 0.22447437047958374 - f1-score (micro avg) 0.7667 | |
| 2023-10-23 21:56:30,748 saving best model | |
| 2023-10-23 21:56:31,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:56:35,589 epoch 7 - iter 44/447 - loss 0.01544098 - time (sec): 4.25 - samples/sec: 2160.52 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:56:40,182 epoch 7 - iter 88/447 - loss 0.01431395 - time (sec): 8.84 - samples/sec: 2132.61 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:56:43,965 epoch 7 - iter 132/447 - loss 0.01454596 - time (sec): 12.63 - samples/sec: 2163.80 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:56:47,703 epoch 7 - iter 176/447 - loss 0.01350481 - time (sec): 16.37 - samples/sec: 2140.77 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:56:51,756 epoch 7 - iter 220/447 - loss 0.01442563 - time (sec): 20.42 - samples/sec: 2112.10 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:56:55,642 epoch 7 - iter 264/447 - loss 0.01532664 - time (sec): 24.30 - samples/sec: 2115.03 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 21:56:59,603 epoch 7 - iter 308/447 - loss 0.01488010 - time (sec): 28.27 - samples/sec: 2132.00 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:57:03,516 epoch 7 - iter 352/447 - loss 0.01462539 - time (sec): 32.18 - samples/sec: 2127.87 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:57:07,421 epoch 7 - iter 396/447 - loss 0.01629265 - time (sec): 36.08 - samples/sec: 2136.74 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:57:11,303 epoch 7 - iter 440/447 - loss 0.01580825 - time (sec): 39.97 - samples/sec: 2132.81 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:57:11,917 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:57:11,917 EPOCH 7 done: loss 0.0157 - lr: 0.000017 | |
| 2023-10-23 21:57:18,395 DEV : loss 0.23538099229335785 - f1-score (micro avg) 0.7841 | |
| 2023-10-23 21:57:18,415 saving best model | |
| 2023-10-23 21:57:19,004 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:57:23,234 epoch 8 - iter 44/447 - loss 0.00792987 - time (sec): 4.23 - samples/sec: 2029.91 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:57:27,029 epoch 8 - iter 88/447 - loss 0.01703551 - time (sec): 8.02 - samples/sec: 2082.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:57:30,991 epoch 8 - iter 132/447 - loss 0.01456325 - time (sec): 11.99 - samples/sec: 2081.23 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:57:34,736 epoch 8 - iter 176/447 - loss 0.01409087 - time (sec): 15.73 - samples/sec: 2096.44 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:57:38,810 epoch 8 - iter 220/447 - loss 0.01363118 - time (sec): 19.81 - samples/sec: 2090.90 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 21:57:42,589 epoch 8 - iter 264/447 - loss 0.01253893 - time (sec): 23.58 - samples/sec: 2107.17 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:57:47,006 epoch 8 - iter 308/447 - loss 0.01335359 - time (sec): 28.00 - samples/sec: 2116.04 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:57:50,843 epoch 8 - iter 352/447 - loss 0.01275915 - time (sec): 31.84 - samples/sec: 2113.19 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:57:54,897 epoch 8 - iter 396/447 - loss 0.01177829 - time (sec): 35.89 - samples/sec: 2129.32 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:57:58,945 epoch 8 - iter 440/447 - loss 0.01177727 - time (sec): 39.94 - samples/sec: 2135.01 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:57:59,590 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:57:59,590 EPOCH 8 done: loss 0.0116 - lr: 0.000011 | |
| 2023-10-23 21:58:06,070 DEV : loss 0.26462581753730774 - f1-score (micro avg) 0.7742 | |
| 2023-10-23 21:58:06,090 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:58:09,847 epoch 9 - iter 44/447 - loss 0.00576407 - time (sec): 3.76 - samples/sec: 2085.12 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:58:14,233 epoch 9 - iter 88/447 - loss 0.00601925 - time (sec): 8.14 - samples/sec: 2162.51 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:58:18,304 epoch 9 - iter 132/447 - loss 0.00746578 - time (sec): 12.21 - samples/sec: 2172.28 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:58:22,338 epoch 9 - iter 176/447 - loss 0.00658948 - time (sec): 16.25 - samples/sec: 2153.41 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:58:26,476 epoch 9 - iter 220/447 - loss 0.00735456 - time (sec): 20.39 - samples/sec: 2139.00 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:58:30,916 epoch 9 - iter 264/447 - loss 0.00697126 - time (sec): 24.83 - samples/sec: 2129.10 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:58:34,709 epoch 9 - iter 308/447 - loss 0.00649014 - time (sec): 28.62 - samples/sec: 2132.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:58:38,420 epoch 9 - iter 352/447 - loss 0.00714014 - time (sec): 32.33 - samples/sec: 2132.07 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:58:42,066 epoch 9 - iter 396/447 - loss 0.00643507 - time (sec): 35.98 - samples/sec: 2129.34 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:58:45,856 epoch 9 - iter 440/447 - loss 0.00633788 - time (sec): 39.76 - samples/sec: 2136.00 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:58:46,577 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:58:46,577 EPOCH 9 done: loss 0.0062 - lr: 0.000006 | |
| 2023-10-23 21:58:53,066 DEV : loss 0.25273650884628296 - f1-score (micro avg) 0.7833 | |
| 2023-10-23 21:58:53,086 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:58:57,441 epoch 10 - iter 44/447 - loss 0.00306477 - time (sec): 4.35 - samples/sec: 2095.30 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:59:01,370 epoch 10 - iter 88/447 - loss 0.00266064 - time (sec): 8.28 - samples/sec: 2113.69 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:59:05,788 epoch 10 - iter 132/447 - loss 0.00212850 - time (sec): 12.70 - samples/sec: 2136.19 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 21:59:09,588 epoch 10 - iter 176/447 - loss 0.00183704 - time (sec): 16.50 - samples/sec: 2145.41 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:59:13,508 epoch 10 - iter 220/447 - loss 0.00284510 - time (sec): 20.42 - samples/sec: 2131.51 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:59:17,442 epoch 10 - iter 264/447 - loss 0.00406030 - time (sec): 24.36 - samples/sec: 2146.58 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:59:21,210 epoch 10 - iter 308/447 - loss 0.00388394 - time (sec): 28.12 - samples/sec: 2146.26 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:59:25,355 epoch 10 - iter 352/447 - loss 0.00402897 - time (sec): 32.27 - samples/sec: 2151.17 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:59:29,040 epoch 10 - iter 396/447 - loss 0.00401045 - time (sec): 35.95 - samples/sec: 2144.19 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:59:32,940 epoch 10 - iter 440/447 - loss 0.00388586 - time (sec): 39.85 - samples/sec: 2137.91 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 21:59:33,556 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:59:33,557 EPOCH 10 done: loss 0.0038 - lr: 0.000000 | |
| 2023-10-23 21:59:39,761 DEV : loss 0.261545330286026 - f1-score (micro avg) 0.791 | |
| 2023-10-23 21:59:39,782 saving best model | |
| 2023-10-23 21:59:40,837 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:59:40,838 Loading model from best epoch ... | |
| 2023-10-23 21:59:42,794 SequenceTagger predicts: Dictionary with 21 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, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time | |
| 2023-10-23 21:59:47,343 | |
| Results: | |
| - F-score (micro) 0.7492 | |
| - F-score (macro) 0.6673 | |
| - Accuracy 0.6174 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8385 0.8624 0.8503 596 | |
| pers 0.6556 0.7718 0.7090 333 | |
| org 0.4885 0.4848 0.4867 132 | |
| prod 0.6346 0.5000 0.5593 66 | |
| time 0.7727 0.6939 0.7312 49 | |
| micro avg 0.7321 0.7670 0.7492 1176 | |
| macro avg 0.6780 0.6626 0.6673 1176 | |
| weighted avg 0.7332 0.7670 0.7482 1176 | |
| 2023-10-23 21:59:47,343 ---------------------------------------------------------------------------------------------------- | |