| 2023-10-23 23:00:28,649 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,650 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 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 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 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Train: 3575 sentences | |
| 2023-10-23 23:00:28,651 (train_with_dev=False, train_with_test=False) | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Training Params: | |
| 2023-10-23 23:00:28,651 - learning_rate: "3e-05" | |
| 2023-10-23 23:00:28,651 - mini_batch_size: "8" | |
| 2023-10-23 23:00:28,651 - max_epochs: "10" | |
| 2023-10-23 23:00:28,651 - shuffle: "True" | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Plugins: | |
| 2023-10-23 23:00:28,651 - TensorboardLogger | |
| 2023-10-23 23:00:28,651 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-23 23:00:28,651 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Computation: | |
| 2023-10-23 23:00:28,651 - compute on device: cuda:0 | |
| 2023-10-23 23:00:28,651 - embedding storage: none | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:00:28,651 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-23 23:00:32,746 epoch 1 - iter 44/447 - loss 2.52602023 - time (sec): 4.09 - samples/sec: 2195.25 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:00:36,618 epoch 1 - iter 88/447 - loss 1.70182761 - time (sec): 7.97 - samples/sec: 2171.87 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:00:40,574 epoch 1 - iter 132/447 - loss 1.31473468 - time (sec): 11.92 - samples/sec: 2185.11 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 23:00:44,249 epoch 1 - iter 176/447 - loss 1.09744513 - time (sec): 15.60 - samples/sec: 2207.06 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:00:48,800 epoch 1 - iter 220/447 - loss 0.92998358 - time (sec): 20.15 - samples/sec: 2172.71 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:00:52,526 epoch 1 - iter 264/447 - loss 0.83386539 - time (sec): 23.87 - samples/sec: 2166.96 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:00:56,473 epoch 1 - iter 308/447 - loss 0.75611333 - time (sec): 27.82 - samples/sec: 2152.51 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:01:00,214 epoch 1 - iter 352/447 - loss 0.69739560 - time (sec): 31.56 - samples/sec: 2134.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:01:04,333 epoch 1 - iter 396/447 - loss 0.64562676 - time (sec): 35.68 - samples/sec: 2144.31 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:01:08,462 epoch 1 - iter 440/447 - loss 0.59937392 - time (sec): 39.81 - samples/sec: 2143.25 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:01:09,047 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:01:09,048 EPOCH 1 done: loss 0.5937 - lr: 0.000029 | |
| 2023-10-23 23:01:13,861 DEV : loss 0.19523081183433533 - f1-score (micro avg) 0.602 | |
| 2023-10-23 23:01:13,882 saving best model | |
| 2023-10-23 23:01:14,355 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:01:18,559 epoch 2 - iter 44/447 - loss 0.17169884 - time (sec): 4.20 - samples/sec: 2020.76 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-23 23:01:22,581 epoch 2 - iter 88/447 - loss 0.17647433 - time (sec): 8.22 - samples/sec: 2101.90 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:01:26,617 epoch 2 - iter 132/447 - loss 0.16565784 - time (sec): 12.26 - samples/sec: 2086.54 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:01:30,763 epoch 2 - iter 176/447 - loss 0.16430118 - time (sec): 16.41 - samples/sec: 2107.26 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-23 23:01:34,549 epoch 2 - iter 220/447 - loss 0.15912237 - time (sec): 20.19 - samples/sec: 2116.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 23:01:38,548 epoch 2 - iter 264/447 - loss 0.15555409 - time (sec): 24.19 - samples/sec: 2112.73 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 23:01:42,387 epoch 2 - iter 308/447 - loss 0.15167650 - time (sec): 28.03 - samples/sec: 2126.29 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-23 23:01:46,396 epoch 2 - iter 352/447 - loss 0.14567258 - time (sec): 32.04 - samples/sec: 2135.14 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:01:50,342 epoch 2 - iter 396/447 - loss 0.14264947 - time (sec): 35.99 - samples/sec: 2127.62 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:01:54,245 epoch 2 - iter 440/447 - loss 0.13821798 - time (sec): 39.89 - samples/sec: 2136.97 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-23 23:01:54,864 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:01:54,864 EPOCH 2 done: loss 0.1395 - lr: 0.000027 | |
| 2023-10-23 23:02:01,346 DEV : loss 0.12295468896627426 - f1-score (micro avg) 0.7103 | |
| 2023-10-23 23:02:01,366 saving best model | |
| 2023-10-23 23:02:01,953 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:02:06,309 epoch 3 - iter 44/447 - loss 0.09549111 - time (sec): 4.35 - samples/sec: 2195.36 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 23:02:10,254 epoch 3 - iter 88/447 - loss 0.07868123 - time (sec): 8.30 - samples/sec: 2242.07 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 23:02:14,277 epoch 3 - iter 132/447 - loss 0.08318832 - time (sec): 12.32 - samples/sec: 2209.09 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-23 23:02:17,984 epoch 3 - iter 176/447 - loss 0.07733080 - time (sec): 16.03 - samples/sec: 2198.38 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 23:02:22,352 epoch 3 - iter 220/447 - loss 0.07500939 - time (sec): 20.40 - samples/sec: 2181.80 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 23:02:26,654 epoch 3 - iter 264/447 - loss 0.07437472 - time (sec): 24.70 - samples/sec: 2171.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-23 23:02:30,577 epoch 3 - iter 308/447 - loss 0.07459318 - time (sec): 28.62 - samples/sec: 2157.01 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:02:34,258 epoch 3 - iter 352/447 - loss 0.07470733 - time (sec): 32.30 - samples/sec: 2137.56 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:02:38,173 epoch 3 - iter 396/447 - loss 0.07388045 - time (sec): 36.22 - samples/sec: 2148.46 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-23 23:02:41,938 epoch 3 - iter 440/447 - loss 0.07304330 - time (sec): 39.98 - samples/sec: 2136.97 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 23:02:42,478 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:02:42,479 EPOCH 3 done: loss 0.0728 - lr: 0.000023 | |
| 2023-10-23 23:02:48,963 DEV : loss 0.15343354642391205 - f1-score (micro avg) 0.7489 | |
| 2023-10-23 23:02:48,983 saving best model | |
| 2023-10-23 23:02:49,570 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:02:53,380 epoch 4 - iter 44/447 - loss 0.03471509 - time (sec): 3.81 - samples/sec: 2180.41 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 23:02:57,700 epoch 4 - iter 88/447 - loss 0.04095950 - time (sec): 8.13 - samples/sec: 2166.29 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-23 23:03:01,896 epoch 4 - iter 132/447 - loss 0.04313707 - time (sec): 12.33 - samples/sec: 2145.87 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 23:03:05,622 epoch 4 - iter 176/447 - loss 0.04217202 - time (sec): 16.05 - samples/sec: 2123.73 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 23:03:10,203 epoch 4 - iter 220/447 - loss 0.04425905 - time (sec): 20.63 - samples/sec: 2113.31 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-23 23:03:14,002 epoch 4 - iter 264/447 - loss 0.04327538 - time (sec): 24.43 - samples/sec: 2107.43 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:03:18,050 epoch 4 - iter 308/447 - loss 0.04558314 - time (sec): 28.48 - samples/sec: 2129.10 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:03:22,001 epoch 4 - iter 352/447 - loss 0.04373608 - time (sec): 32.43 - samples/sec: 2127.73 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-23 23:03:25,841 epoch 4 - iter 396/447 - loss 0.04253316 - time (sec): 36.27 - samples/sec: 2127.56 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:03:29,679 epoch 4 - iter 440/447 - loss 0.04399254 - time (sec): 40.11 - samples/sec: 2125.07 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:03:30,294 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:03:30,294 EPOCH 4 done: loss 0.0437 - lr: 0.000020 | |
| 2023-10-23 23:03:36,776 DEV : loss 0.16440840065479279 - f1-score (micro avg) 0.7465 | |
| 2023-10-23 23:03:36,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:03:40,718 epoch 5 - iter 44/447 - loss 0.03153993 - time (sec): 3.92 - samples/sec: 2183.07 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-23 23:03:45,031 epoch 5 - iter 88/447 - loss 0.03158561 - time (sec): 8.23 - samples/sec: 2117.98 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 23:03:48,851 epoch 5 - iter 132/447 - loss 0.03154475 - time (sec): 12.05 - samples/sec: 2134.16 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 23:03:52,601 epoch 5 - iter 176/447 - loss 0.02896412 - time (sec): 15.80 - samples/sec: 2134.56 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-23 23:03:56,655 epoch 5 - iter 220/447 - loss 0.02964248 - time (sec): 19.86 - samples/sec: 2123.94 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:04:00,713 epoch 5 - iter 264/447 - loss 0.02934625 - time (sec): 23.92 - samples/sec: 2115.14 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:04:04,358 epoch 5 - iter 308/447 - loss 0.02819574 - time (sec): 27.56 - samples/sec: 2124.76 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-23 23:04:08,764 epoch 5 - iter 352/447 - loss 0.03063596 - time (sec): 31.97 - samples/sec: 2126.05 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 23:04:12,599 epoch 5 - iter 396/447 - loss 0.02978320 - time (sec): 35.80 - samples/sec: 2137.51 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 23:04:16,554 epoch 5 - iter 440/447 - loss 0.02930160 - time (sec): 39.76 - samples/sec: 2141.01 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-23 23:04:17,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:04:17,157 EPOCH 5 done: loss 0.0292 - lr: 0.000017 | |
| 2023-10-23 23:04:23,636 DEV : loss 0.18590261042118073 - f1-score (micro avg) 0.771 | |
| 2023-10-23 23:04:23,656 saving best model | |
| 2023-10-23 23:04:24,245 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:04:28,359 epoch 6 - iter 44/447 - loss 0.02168377 - time (sec): 4.11 - samples/sec: 2005.67 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 23:04:32,535 epoch 6 - iter 88/447 - loss 0.02664472 - time (sec): 8.29 - samples/sec: 2046.54 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 23:04:37,101 epoch 6 - iter 132/447 - loss 0.02379201 - time (sec): 12.85 - samples/sec: 2069.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-23 23:04:40,881 epoch 6 - iter 176/447 - loss 0.02219099 - time (sec): 16.64 - samples/sec: 2088.60 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:04:44,787 epoch 6 - iter 220/447 - loss 0.02183849 - time (sec): 20.54 - samples/sec: 2102.02 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:04:48,657 epoch 6 - iter 264/447 - loss 0.02049396 - time (sec): 24.41 - samples/sec: 2109.29 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-23 23:04:52,413 epoch 6 - iter 308/447 - loss 0.02101667 - time (sec): 28.17 - samples/sec: 2106.25 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 23:04:56,108 epoch 6 - iter 352/447 - loss 0.01998352 - time (sec): 31.86 - samples/sec: 2107.46 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 23:05:00,274 epoch 6 - iter 396/447 - loss 0.02022647 - time (sec): 36.03 - samples/sec: 2113.02 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-23 23:05:04,211 epoch 6 - iter 440/447 - loss 0.02038921 - time (sec): 39.96 - samples/sec: 2131.51 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 23:05:04,873 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:05:04,874 EPOCH 6 done: loss 0.0206 - lr: 0.000013 | |
| 2023-10-23 23:05:11,385 DEV : loss 0.2045108526945114 - f1-score (micro avg) 0.7576 | |
| 2023-10-23 23:05:11,406 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:05:15,710 epoch 7 - iter 44/447 - loss 0.02004284 - time (sec): 4.30 - samples/sec: 2123.05 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 23:05:19,740 epoch 7 - iter 88/447 - loss 0.01541434 - time (sec): 8.33 - samples/sec: 2121.61 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-23 23:05:23,460 epoch 7 - iter 132/447 - loss 0.01587152 - time (sec): 12.05 - samples/sec: 2141.90 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:05:27,657 epoch 7 - iter 176/447 - loss 0.01550813 - time (sec): 16.25 - samples/sec: 2171.27 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:05:31,665 epoch 7 - iter 220/447 - loss 0.01526874 - time (sec): 20.26 - samples/sec: 2146.13 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-23 23:05:35,806 epoch 7 - iter 264/447 - loss 0.01545565 - time (sec): 24.40 - samples/sec: 2129.96 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 23:05:39,700 epoch 7 - iter 308/447 - loss 0.01438074 - time (sec): 28.29 - samples/sec: 2135.49 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 23:05:43,906 epoch 7 - iter 352/447 - loss 0.01391057 - time (sec): 32.50 - samples/sec: 2137.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-23 23:05:47,968 epoch 7 - iter 396/447 - loss 0.01352129 - time (sec): 36.56 - samples/sec: 2134.04 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:05:51,529 epoch 7 - iter 440/447 - loss 0.01375727 - time (sec): 40.12 - samples/sec: 2126.85 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:05:52,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:05:52,095 EPOCH 7 done: loss 0.0138 - lr: 0.000010 | |
| 2023-10-23 23:05:58,309 DEV : loss 0.22162960469722748 - f1-score (micro avg) 0.7836 | |
| 2023-10-23 23:05:58,329 saving best model | |
| 2023-10-23 23:05:59,227 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:06:03,130 epoch 8 - iter 44/447 - loss 0.00338610 - time (sec): 3.90 - samples/sec: 2177.22 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-23 23:06:07,503 epoch 8 - iter 88/447 - loss 0.00649872 - time (sec): 8.28 - samples/sec: 2124.18 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 23:06:11,262 epoch 8 - iter 132/447 - loss 0.00844255 - time (sec): 12.03 - samples/sec: 2139.75 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 23:06:15,220 epoch 8 - iter 176/447 - loss 0.00810306 - time (sec): 15.99 - samples/sec: 2115.00 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-23 23:06:19,137 epoch 8 - iter 220/447 - loss 0.00775609 - time (sec): 19.91 - samples/sec: 2119.19 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 23:06:22,765 epoch 8 - iter 264/447 - loss 0.00753910 - time (sec): 23.54 - samples/sec: 2132.64 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 23:06:26,708 epoch 8 - iter 308/447 - loss 0.00742374 - time (sec): 27.48 - samples/sec: 2137.96 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-23 23:06:31,358 epoch 8 - iter 352/447 - loss 0.00757262 - time (sec): 32.13 - samples/sec: 2125.85 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 23:06:35,232 epoch 8 - iter 396/447 - loss 0.00893999 - time (sec): 36.00 - samples/sec: 2144.09 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 23:06:39,044 epoch 8 - iter 440/447 - loss 0.00911259 - time (sec): 39.82 - samples/sec: 2143.63 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-23 23:06:39,653 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:06:39,653 EPOCH 8 done: loss 0.0094 - lr: 0.000007 | |
| 2023-10-23 23:06:45,867 DEV : loss 0.2305288016796112 - f1-score (micro avg) 0.7771 | |
| 2023-10-23 23:06:45,887 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:06:49,797 epoch 9 - iter 44/447 - loss 0.00749318 - time (sec): 3.91 - samples/sec: 2132.77 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:06:54,055 epoch 9 - iter 88/447 - loss 0.00578018 - time (sec): 8.17 - samples/sec: 2106.92 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:06:58,041 epoch 9 - iter 132/447 - loss 0.00513309 - time (sec): 12.15 - samples/sec: 2160.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-23 23:07:02,056 epoch 9 - iter 176/447 - loss 0.00514188 - time (sec): 16.17 - samples/sec: 2121.05 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:07:05,872 epoch 9 - iter 220/447 - loss 0.00441923 - time (sec): 19.98 - samples/sec: 2141.34 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:07:09,433 epoch 9 - iter 264/447 - loss 0.00540403 - time (sec): 23.54 - samples/sec: 2134.74 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-23 23:07:13,624 epoch 9 - iter 308/447 - loss 0.00549172 - time (sec): 27.74 - samples/sec: 2130.38 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 23:07:17,938 epoch 9 - iter 352/447 - loss 0.00557974 - time (sec): 32.05 - samples/sec: 2144.11 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 23:07:21,891 epoch 9 - iter 396/447 - loss 0.00615603 - time (sec): 36.00 - samples/sec: 2130.07 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-23 23:07:25,987 epoch 9 - iter 440/447 - loss 0.00622433 - time (sec): 40.10 - samples/sec: 2123.91 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:07:26,557 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:07:26,557 EPOCH 9 done: loss 0.0061 - lr: 0.000003 | |
| 2023-10-23 23:07:32,804 DEV : loss 0.24391140043735504 - f1-score (micro avg) 0.7819 | |
| 2023-10-23 23:07:32,824 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:07:36,558 epoch 10 - iter 44/447 - loss 0.00893320 - time (sec): 3.73 - samples/sec: 2136.89 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:07:40,288 epoch 10 - iter 88/447 - loss 0.00533915 - time (sec): 7.46 - samples/sec: 2130.68 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-23 23:07:44,363 epoch 10 - iter 132/447 - loss 0.00466202 - time (sec): 11.54 - samples/sec: 2152.54 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 23:07:48,688 epoch 10 - iter 176/447 - loss 0.00398884 - time (sec): 15.86 - samples/sec: 2135.03 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 23:07:52,909 epoch 10 - iter 220/447 - loss 0.00318742 - time (sec): 20.08 - samples/sec: 2136.60 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-23 23:07:57,023 epoch 10 - iter 264/447 - loss 0.00288008 - time (sec): 24.20 - samples/sec: 2115.28 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:08:00,749 epoch 10 - iter 308/447 - loss 0.00336446 - time (sec): 27.92 - samples/sec: 2121.73 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:08:04,576 epoch 10 - iter 352/447 - loss 0.00326997 - time (sec): 31.75 - samples/sec: 2122.19 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-23 23:08:08,617 epoch 10 - iter 396/447 - loss 0.00380379 - time (sec): 35.79 - samples/sec: 2130.28 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 23:08:12,964 epoch 10 - iter 440/447 - loss 0.00399744 - time (sec): 40.14 - samples/sec: 2118.14 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-23 23:08:13,600 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:13,601 EPOCH 10 done: loss 0.0039 - lr: 0.000000 | |
| 2023-10-23 23:08:19,844 DEV : loss 0.24326062202453613 - f1-score (micro avg) 0.7825 | |
| 2023-10-23 23:08:20,336 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-23 23:08:20,337 Loading model from best epoch ... | |
| 2023-10-23 23:08:22,007 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 23:08:26,848 | |
| Results: | |
| - F-score (micro) 0.7342 | |
| - F-score (macro) 0.6411 | |
| - Accuracy 0.5989 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.7823 0.8624 0.8204 596 | |
| pers 0.6778 0.7327 0.7042 333 | |
| org 0.5625 0.4773 0.5164 132 | |
| prod 0.5510 0.4091 0.4696 66 | |
| time 0.7174 0.6735 0.6947 49 | |
| micro avg 0.7198 0.7491 0.7342 1176 | |
| macro avg 0.6582 0.6310 0.6411 1176 | |
| weighted avg 0.7124 0.7491 0.7285 1176 | |
| 2023-10-23 23:08:26,848 ---------------------------------------------------------------------------------------------------- | |