| 2023-10-23 21:04:58,060 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 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 21:04:58,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 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 21:04:58,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 Train: 3575 sentences | |
| 2023-10-23 21:04:58,061 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 21:04:58,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 Training Params: | |
| 2023-10-23 21:04:58,061 - learning_rate: "3e-05" | |
| 2023-10-23 21:04:58,061 - mini_batch_size: "8" | |
| 2023-10-23 21:04:58,061 - max_epochs: "10" | |
| 2023-10-23 21:04:58,061 - shuffle: "True" | |
| 2023-10-23 21:04:58,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 Plugins: | |
| 2023-10-23 21:04:58,061 - TensorboardLogger | |
| 2023-10-23 21:04:58,061 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 21:04:58,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,061 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 21:04:58,061 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 21:04:58,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,062 Computation: | |
| 2023-10-23 21:04:58,062 - compute on device: cuda:0 | |
| 2023-10-23 21:04:58,062 - embedding storage: none | |
| 2023-10-23 21:04:58,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,062 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-23 21:04:58,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,062 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:04:58,062 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 21:05:01,858 epoch 1 - iter 44/447 - loss 2.77674307 - time (sec): 3.80 - samples/sec: 2068.88 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:05:05,973 epoch 1 - iter 88/447 - loss 1.75956664 - time (sec): 7.91 - samples/sec: 2088.59 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:05:10,065 epoch 1 - iter 132/447 - loss 1.30302502 - time (sec): 12.00 - samples/sec: 2082.97 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:05:14,086 epoch 1 - iter 176/447 - loss 1.08268102 - time (sec): 16.02 - samples/sec: 2078.90 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:05:17,972 epoch 1 - iter 220/447 - loss 0.93560897 - time (sec): 19.91 - samples/sec: 2103.90 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:05:21,763 epoch 1 - iter 264/447 - loss 0.83394592 - time (sec): 23.70 - samples/sec: 2104.11 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:05:25,684 epoch 1 - iter 308/447 - loss 0.75226450 - time (sec): 27.62 - samples/sec: 2106.94 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:05:29,651 epoch 1 - iter 352/447 - loss 0.68133343 - time (sec): 31.59 - samples/sec: 2108.95 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:05:34,085 epoch 1 - iter 396/447 - loss 0.62684172 - time (sec): 36.02 - samples/sec: 2124.23 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:05:37,891 epoch 1 - iter 440/447 - loss 0.58441638 - time (sec): 39.83 - samples/sec: 2137.74 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:05:38,506 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:05:38,506 EPOCH 1 done: loss 0.5780 - lr: 0.000029 | |
| 2023-10-23 21:05:43,315 DEV : loss 0.15914756059646606 - f1-score (micro avg) 0.5805 | |
| 2023-10-23 21:05:43,335 saving best model | |
| 2023-10-23 21:05:43,804 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:05:47,532 epoch 2 - iter 44/447 - loss 0.17247700 - time (sec): 3.73 - samples/sec: 2206.20 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 21:05:51,556 epoch 2 - iter 88/447 - loss 0.15210658 - time (sec): 7.75 - samples/sec: 2170.56 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:05:55,638 epoch 2 - iter 132/447 - loss 0.14415904 - time (sec): 11.83 - samples/sec: 2166.91 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:05:59,766 epoch 2 - iter 176/447 - loss 0.14348377 - time (sec): 15.96 - samples/sec: 2153.80 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 21:06:03,542 epoch 2 - iter 220/447 - loss 0.13706169 - time (sec): 19.74 - samples/sec: 2132.36 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:06:07,684 epoch 2 - iter 264/447 - loss 0.13827372 - time (sec): 23.88 - samples/sec: 2135.49 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:06:11,700 epoch 2 - iter 308/447 - loss 0.13580790 - time (sec): 27.90 - samples/sec: 2140.60 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 21:06:15,332 epoch 2 - iter 352/447 - loss 0.13583544 - time (sec): 31.53 - samples/sec: 2145.24 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:06:19,814 epoch 2 - iter 396/447 - loss 0.13680668 - time (sec): 36.01 - samples/sec: 2139.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:06:23,630 epoch 2 - iter 440/447 - loss 0.13356993 - time (sec): 39.83 - samples/sec: 2137.55 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 21:06:24,229 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:06:24,230 EPOCH 2 done: loss 0.1328 - lr: 0.000027 | |
| 2023-10-23 21:06:30,708 DEV : loss 0.12941311299800873 - f1-score (micro avg) 0.7109 | |
| 2023-10-23 21:06:30,728 saving best model | |
| 2023-10-23 21:06:31,322 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:06:35,398 epoch 3 - iter 44/447 - loss 0.05897943 - time (sec): 4.07 - samples/sec: 2144.85 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:06:39,480 epoch 3 - iter 88/447 - loss 0.07267667 - time (sec): 8.16 - samples/sec: 2139.98 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:06:43,614 epoch 3 - iter 132/447 - loss 0.07124643 - time (sec): 12.29 - samples/sec: 2163.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 21:06:47,536 epoch 3 - iter 176/447 - loss 0.06874515 - time (sec): 16.21 - samples/sec: 2126.51 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:06:51,418 epoch 3 - iter 220/447 - loss 0.06845317 - time (sec): 20.10 - samples/sec: 2144.00 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:06:55,177 epoch 3 - iter 264/447 - loss 0.06741457 - time (sec): 23.85 - samples/sec: 2150.15 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 21:06:59,046 epoch 3 - iter 308/447 - loss 0.06763183 - time (sec): 27.72 - samples/sec: 2142.44 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:07:03,214 epoch 3 - iter 352/447 - loss 0.06611837 - time (sec): 31.89 - samples/sec: 2146.71 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:07:07,031 epoch 3 - iter 396/447 - loss 0.06604370 - time (sec): 35.71 - samples/sec: 2149.25 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 21:07:11,156 epoch 3 - iter 440/447 - loss 0.06746680 - time (sec): 39.83 - samples/sec: 2134.13 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:07:11,816 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:07:11,816 EPOCH 3 done: loss 0.0677 - lr: 0.000023 | |
| 2023-10-23 21:07:18,319 DEV : loss 0.13155309855937958 - f1-score (micro avg) 0.7518 | |
| 2023-10-23 21:07:18,339 saving best model | |
| 2023-10-23 21:07:18,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:07:22,645 epoch 4 - iter 44/447 - loss 0.04956695 - time (sec): 3.73 - samples/sec: 2133.43 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:07:26,708 epoch 4 - iter 88/447 - loss 0.04093136 - time (sec): 7.79 - samples/sec: 2113.74 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 21:07:30,759 epoch 4 - iter 132/447 - loss 0.03912973 - time (sec): 11.85 - samples/sec: 2133.26 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:07:34,940 epoch 4 - iter 176/447 - loss 0.03954112 - time (sec): 16.03 - samples/sec: 2116.49 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:07:39,131 epoch 4 - iter 220/447 - loss 0.03912372 - time (sec): 20.22 - samples/sec: 2109.00 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 21:07:43,162 epoch 4 - iter 264/447 - loss 0.04029854 - time (sec): 24.25 - samples/sec: 2116.55 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:07:47,407 epoch 4 - iter 308/447 - loss 0.04017848 - time (sec): 28.49 - samples/sec: 2117.43 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:07:51,304 epoch 4 - iter 352/447 - loss 0.03995350 - time (sec): 32.39 - samples/sec: 2121.72 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 21:07:55,232 epoch 4 - iter 396/447 - loss 0.04119580 - time (sec): 36.32 - samples/sec: 2122.18 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:07:59,018 epoch 4 - iter 440/447 - loss 0.04224669 - time (sec): 40.10 - samples/sec: 2126.79 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:07:59,609 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:07:59,609 EPOCH 4 done: loss 0.0431 - lr: 0.000020 | |
| 2023-10-23 21:08:06,099 DEV : loss 0.17578744888305664 - f1-score (micro avg) 0.764 | |
| 2023-10-23 21:08:06,120 saving best model | |
| 2023-10-23 21:08:06,714 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:08:10,724 epoch 5 - iter 44/447 - loss 0.03173418 - time (sec): 4.01 - samples/sec: 2167.42 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 21:08:14,826 epoch 5 - iter 88/447 - loss 0.03285878 - time (sec): 8.11 - samples/sec: 2075.18 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 21:08:18,587 epoch 5 - iter 132/447 - loss 0.03247897 - time (sec): 11.87 - samples/sec: 2091.33 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 21:08:22,960 epoch 5 - iter 176/447 - loss 0.03016416 - time (sec): 16.24 - samples/sec: 2100.92 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 21:08:26,816 epoch 5 - iter 220/447 - loss 0.02778420 - time (sec): 20.10 - samples/sec: 2102.65 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:08:30,624 epoch 5 - iter 264/447 - loss 0.02814833 - time (sec): 23.91 - samples/sec: 2103.17 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:08:35,077 epoch 5 - iter 308/447 - loss 0.02586079 - time (sec): 28.36 - samples/sec: 2110.52 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 21:08:39,022 epoch 5 - iter 352/447 - loss 0.02544490 - time (sec): 32.31 - samples/sec: 2113.41 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:08:42,951 epoch 5 - iter 396/447 - loss 0.02670970 - time (sec): 36.24 - samples/sec: 2126.29 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:08:46,739 epoch 5 - iter 440/447 - loss 0.02604997 - time (sec): 40.02 - samples/sec: 2134.99 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 21:08:47,301 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:08:47,301 EPOCH 5 done: loss 0.0260 - lr: 0.000017 | |
| 2023-10-23 21:08:53,795 DEV : loss 0.19835765659809113 - f1-score (micro avg) 0.7738 | |
| 2023-10-23 21:08:53,815 saving best model | |
| 2023-10-23 21:08:54,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:08:58,311 epoch 6 - iter 44/447 - loss 0.02184566 - time (sec): 3.89 - samples/sec: 2032.43 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:09:02,255 epoch 6 - iter 88/447 - loss 0.02189035 - time (sec): 7.84 - samples/sec: 2042.74 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:09:06,400 epoch 6 - iter 132/447 - loss 0.01858513 - time (sec): 11.98 - samples/sec: 2069.63 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 21:09:10,451 epoch 6 - iter 176/447 - loss 0.01839336 - time (sec): 16.03 - samples/sec: 2120.22 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:09:14,439 epoch 6 - iter 220/447 - loss 0.01779606 - time (sec): 20.02 - samples/sec: 2132.02 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:09:18,507 epoch 6 - iter 264/447 - loss 0.01809152 - time (sec): 24.09 - samples/sec: 2112.60 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 21:09:22,335 epoch 6 - iter 308/447 - loss 0.01799876 - time (sec): 27.92 - samples/sec: 2123.56 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 21:09:26,257 epoch 6 - iter 352/447 - loss 0.01963981 - time (sec): 31.84 - samples/sec: 2130.81 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 21:09:30,544 epoch 6 - iter 396/447 - loss 0.01948104 - time (sec): 36.13 - samples/sec: 2122.38 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 21:09:34,423 epoch 6 - iter 440/447 - loss 0.01934598 - time (sec): 40.00 - samples/sec: 2135.33 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:09:34,989 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:09:34,990 EPOCH 6 done: loss 0.0195 - lr: 0.000013 | |
| 2023-10-23 21:09:41,480 DEV : loss 0.2243068516254425 - f1-score (micro avg) 0.7653 | |
| 2023-10-23 21:09:41,500 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:09:45,224 epoch 7 - iter 44/447 - loss 0.00920856 - time (sec): 3.72 - samples/sec: 2231.28 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:09:49,298 epoch 7 - iter 88/447 - loss 0.00662161 - time (sec): 7.80 - samples/sec: 2168.79 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 21:09:53,791 epoch 7 - iter 132/447 - loss 0.00770613 - time (sec): 12.29 - samples/sec: 2141.83 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:09:57,731 epoch 7 - iter 176/447 - loss 0.00876968 - time (sec): 16.23 - samples/sec: 2139.89 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:10:01,668 epoch 7 - iter 220/447 - loss 0.01105371 - time (sec): 20.17 - samples/sec: 2133.73 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 21:10:05,750 epoch 7 - iter 264/447 - loss 0.01232071 - time (sec): 24.25 - samples/sec: 2134.11 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:10:09,797 epoch 7 - iter 308/447 - loss 0.01229655 - time (sec): 28.30 - samples/sec: 2129.39 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:10:13,591 epoch 7 - iter 352/447 - loss 0.01195873 - time (sec): 32.09 - samples/sec: 2131.21 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 21:10:17,520 epoch 7 - iter 396/447 - loss 0.01218580 - time (sec): 36.02 - samples/sec: 2138.12 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:10:21,420 epoch 7 - iter 440/447 - loss 0.01243524 - time (sec): 39.92 - samples/sec: 2141.02 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:10:21,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:10:21,971 EPOCH 7 done: loss 0.0123 - lr: 0.000010 | |
| 2023-10-23 21:10:28,450 DEV : loss 0.23942111432552338 - f1-score (micro avg) 0.7782 | |
| 2023-10-23 21:10:28,471 saving best model | |
| 2023-10-23 21:10:29,061 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:10:32,915 epoch 8 - iter 44/447 - loss 0.01227698 - time (sec): 3.85 - samples/sec: 2174.91 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 21:10:36,826 epoch 8 - iter 88/447 - loss 0.01241903 - time (sec): 7.76 - samples/sec: 2170.56 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:10:40,673 epoch 8 - iter 132/447 - loss 0.01170822 - time (sec): 11.61 - samples/sec: 2125.15 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:10:45,301 epoch 8 - iter 176/447 - loss 0.00886420 - time (sec): 16.24 - samples/sec: 2140.47 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 21:10:49,255 epoch 8 - iter 220/447 - loss 0.00834151 - time (sec): 20.19 - samples/sec: 2146.67 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:10:52,900 epoch 8 - iter 264/447 - loss 0.00734419 - time (sec): 23.84 - samples/sec: 2125.14 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:10:57,066 epoch 8 - iter 308/447 - loss 0.00699004 - time (sec): 28.00 - samples/sec: 2125.54 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 21:11:01,039 epoch 8 - iter 352/447 - loss 0.00726347 - time (sec): 31.98 - samples/sec: 2127.42 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:11:05,458 epoch 8 - iter 396/447 - loss 0.00762904 - time (sec): 36.40 - samples/sec: 2122.16 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:11:09,201 epoch 8 - iter 440/447 - loss 0.00722230 - time (sec): 40.14 - samples/sec: 2121.45 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 21:11:09,820 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:11:09,820 EPOCH 8 done: loss 0.0072 - lr: 0.000007 | |
| 2023-10-23 21:11:16,024 DEV : loss 0.24051210284233093 - f1-score (micro avg) 0.7845 | |
| 2023-10-23 21:11:16,045 saving best model | |
| 2023-10-23 21:11:16,944 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:11:20,570 epoch 9 - iter 44/447 - loss 0.00666362 - time (sec): 3.62 - samples/sec: 2217.26 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:11:24,590 epoch 9 - iter 88/447 - loss 0.00577915 - time (sec): 7.65 - samples/sec: 2129.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:11:28,832 epoch 9 - iter 132/447 - loss 0.00485046 - time (sec): 11.89 - samples/sec: 2118.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 21:11:32,648 epoch 9 - iter 176/447 - loss 0.00491996 - time (sec): 15.70 - samples/sec: 2142.21 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:11:36,618 epoch 9 - iter 220/447 - loss 0.00513214 - time (sec): 19.67 - samples/sec: 2151.50 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:11:40,891 epoch 9 - iter 264/447 - loss 0.00479915 - time (sec): 23.95 - samples/sec: 2148.31 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 21:11:45,144 epoch 9 - iter 308/447 - loss 0.00461094 - time (sec): 28.20 - samples/sec: 2147.40 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 21:11:48,902 epoch 9 - iter 352/447 - loss 0.00508793 - time (sec): 31.96 - samples/sec: 2144.23 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 21:11:52,648 epoch 9 - iter 396/447 - loss 0.00553986 - time (sec): 35.70 - samples/sec: 2147.82 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 21:11:56,680 epoch 9 - iter 440/447 - loss 0.00517049 - time (sec): 39.74 - samples/sec: 2149.08 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:11:57,308 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:11:57,309 EPOCH 9 done: loss 0.0051 - lr: 0.000003 | |
| 2023-10-23 21:12:03,519 DEV : loss 0.2497478574514389 - f1-score (micro avg) 0.7909 | |
| 2023-10-23 21:12:03,540 saving best model | |
| 2023-10-23 21:12:04,111 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:12:08,002 epoch 10 - iter 44/447 - loss 0.00252055 - time (sec): 3.89 - samples/sec: 2207.00 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:12:12,159 epoch 10 - iter 88/447 - loss 0.00205105 - time (sec): 8.05 - samples/sec: 2163.44 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 21:12:16,370 epoch 10 - iter 132/447 - loss 0.00162416 - time (sec): 12.26 - samples/sec: 2100.99 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:12:20,040 epoch 10 - iter 176/447 - loss 0.00314123 - time (sec): 15.93 - samples/sec: 2135.69 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:12:24,341 epoch 10 - iter 220/447 - loss 0.00360926 - time (sec): 20.23 - samples/sec: 2144.50 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 21:12:28,106 epoch 10 - iter 264/447 - loss 0.00340675 - time (sec): 23.99 - samples/sec: 2135.76 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:12:31,919 epoch 10 - iter 308/447 - loss 0.00353423 - time (sec): 27.81 - samples/sec: 2147.17 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:12:36,013 epoch 10 - iter 352/447 - loss 0.00314415 - time (sec): 31.90 - samples/sec: 2139.65 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 21:12:40,324 epoch 10 - iter 396/447 - loss 0.00312445 - time (sec): 36.21 - samples/sec: 2122.16 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 21:12:44,382 epoch 10 - iter 440/447 - loss 0.00304078 - time (sec): 40.27 - samples/sec: 2116.62 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 21:12:45,004 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:12:45,004 EPOCH 10 done: loss 0.0030 - lr: 0.000000 | |
| 2023-10-23 21:12:51,224 DEV : loss 0.25497499108314514 - f1-score (micro avg) 0.7901 | |
| 2023-10-23 21:12:51,722 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 21:12:51,723 Loading model from best epoch ... | |
| 2023-10-23 21:12:53,466 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 21:12:58,280 | |
| Results: | |
| - F-score (micro) 0.7524 | |
| - F-score (macro) 0.665 | |
| - Accuracy 0.6214 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8280 0.8641 0.8456 596 | |
| pers 0.7064 0.7658 0.7349 333 | |
| org 0.4706 0.4848 0.4776 132 | |
| prod 0.6071 0.5152 0.5574 66 | |
| time 0.7500 0.6735 0.7097 49 | |
| micro avg 0.7391 0.7662 0.7524 1176 | |
| macro avg 0.6724 0.6607 0.6650 1176 | |
| weighted avg 0.7378 0.7662 0.7511 1176 | |
| 2023-10-23 21:12:58,280 ---------------------------------------------------------------------------------------------------- | |