| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,207 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(32001, 128) | |
| (position_embeddings): Embedding(512, 128) | |
| (token_type_embeddings): Embedding(2, 128) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (encoder): BertEncoder( | |
| (layer): ModuleList( | |
| (0-1): 2 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (query): Linear(in_features=128, out_features=128, bias=True) | |
| (key): Linear(in_features=128, out_features=128, bias=True) | |
| (value): Linear(in_features=128, out_features=128, bias=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| (output): BertSelfOutput( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| (intermediate): BertIntermediate( | |
| (dense): Linear(in_features=128, out_features=512, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (dense): Linear(in_features=512, out_features=128, bias=True) | |
| (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True) | |
| (dropout): Dropout(p=0.1, inplace=False) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=128, out_features=128, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=128, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,207 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences | |
| - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator | |
| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,207 Train: 20847 sentences | |
| 2023-10-19 12:38:44,207 (train_with_dev=False, train_with_test=False) | |
| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,207 Training Params: | |
| 2023-10-19 12:38:44,207 - learning_rate: "5e-05" | |
| 2023-10-19 12:38:44,207 - mini_batch_size: "4" | |
| 2023-10-19 12:38:44,207 - max_epochs: "10" | |
| 2023-10-19 12:38:44,207 - shuffle: "True" | |
| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,207 Plugins: | |
| 2023-10-19 12:38:44,207 - TensorboardLogger | |
| 2023-10-19 12:38:44,207 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-19 12:38:44,207 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,208 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-19 12:38:44,208 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-19 12:38:44,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,208 Computation: | |
| 2023-10-19 12:38:44,208 - compute on device: cuda:0 | |
| 2023-10-19 12:38:44,208 - embedding storage: none | |
| 2023-10-19 12:38:44,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,208 Model training base path: "hmbench-newseye/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-19 12:38:44,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,208 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:38:44,208 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-19 12:38:52,418 epoch 1 - iter 521/5212 - loss 3.42604136 - time (sec): 8.21 - samples/sec: 4698.46 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 12:39:00,610 epoch 1 - iter 1042/5212 - loss 2.44104122 - time (sec): 16.40 - samples/sec: 4513.24 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 12:39:08,630 epoch 1 - iter 1563/5212 - loss 1.85175851 - time (sec): 24.42 - samples/sec: 4442.18 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 12:39:17,015 epoch 1 - iter 2084/5212 - loss 1.52346946 - time (sec): 32.81 - samples/sec: 4460.50 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 12:39:25,253 epoch 1 - iter 2605/5212 - loss 1.33374847 - time (sec): 41.05 - samples/sec: 4415.37 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 12:39:33,797 epoch 1 - iter 3126/5212 - loss 1.18123210 - time (sec): 49.59 - samples/sec: 4431.28 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 12:39:42,091 epoch 1 - iter 3647/5212 - loss 1.06507178 - time (sec): 57.88 - samples/sec: 4460.86 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-19 12:39:50,274 epoch 1 - iter 4168/5212 - loss 0.98648191 - time (sec): 66.07 - samples/sec: 4435.47 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-19 12:39:58,678 epoch 1 - iter 4689/5212 - loss 0.91790985 - time (sec): 74.47 - samples/sec: 4441.81 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-19 12:40:07,124 epoch 1 - iter 5210/5212 - loss 0.86893234 - time (sec): 82.92 - samples/sec: 4427.56 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-19 12:40:07,164 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:40:07,164 EPOCH 1 done: loss 0.8683 - lr: 0.000050 | |
| 2023-10-19 12:40:10,143 DEV : loss 0.14668601751327515 - f1-score (micro avg) 0.2553 | |
| 2023-10-19 12:40:10,167 saving best model | |
| 2023-10-19 12:40:10,195 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:40:18,443 epoch 2 - iter 521/5212 - loss 0.36989339 - time (sec): 8.25 - samples/sec: 4548.82 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-19 12:40:26,940 epoch 2 - iter 1042/5212 - loss 0.36460474 - time (sec): 16.74 - samples/sec: 4638.12 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-19 12:40:34,539 epoch 2 - iter 1563/5212 - loss 0.35676632 - time (sec): 24.34 - samples/sec: 4753.46 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-19 12:40:42,578 epoch 2 - iter 2084/5212 - loss 0.35219138 - time (sec): 32.38 - samples/sec: 4628.18 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-19 12:40:50,828 epoch 2 - iter 2605/5212 - loss 0.35698932 - time (sec): 40.63 - samples/sec: 4589.75 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-19 12:40:59,176 epoch 2 - iter 3126/5212 - loss 0.35632972 - time (sec): 48.98 - samples/sec: 4562.33 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-19 12:41:07,474 epoch 2 - iter 3647/5212 - loss 0.35437571 - time (sec): 57.28 - samples/sec: 4520.49 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-19 12:41:15,443 epoch 2 - iter 4168/5212 - loss 0.35077830 - time (sec): 65.25 - samples/sec: 4511.87 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-19 12:41:23,605 epoch 2 - iter 4689/5212 - loss 0.34724407 - time (sec): 73.41 - samples/sec: 4480.54 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-19 12:41:31,941 epoch 2 - iter 5210/5212 - loss 0.34213703 - time (sec): 81.75 - samples/sec: 4493.35 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-19 12:41:31,969 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:41:31,969 EPOCH 2 done: loss 0.3421 - lr: 0.000044 | |
| 2023-10-19 12:41:37,054 DEV : loss 0.1477486938238144 - f1-score (micro avg) 0.268 | |
| 2023-10-19 12:41:37,079 saving best model | |
| 2023-10-19 12:41:37,111 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:41:45,513 epoch 3 - iter 521/5212 - loss 0.30625132 - time (sec): 8.40 - samples/sec: 4389.44 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-19 12:41:53,837 epoch 3 - iter 1042/5212 - loss 0.28511737 - time (sec): 16.73 - samples/sec: 4611.01 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-19 12:42:02,178 epoch 3 - iter 1563/5212 - loss 0.29631007 - time (sec): 25.07 - samples/sec: 4461.36 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-19 12:42:10,497 epoch 3 - iter 2084/5212 - loss 0.29906238 - time (sec): 33.39 - samples/sec: 4388.92 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-19 12:42:18,831 epoch 3 - iter 2605/5212 - loss 0.29236860 - time (sec): 41.72 - samples/sec: 4411.83 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-19 12:42:27,376 epoch 3 - iter 3126/5212 - loss 0.29086057 - time (sec): 50.26 - samples/sec: 4484.68 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-19 12:42:35,391 epoch 3 - iter 3647/5212 - loss 0.28709763 - time (sec): 58.28 - samples/sec: 4418.75 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-19 12:42:43,630 epoch 3 - iter 4168/5212 - loss 0.28615399 - time (sec): 66.52 - samples/sec: 4392.11 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-19 12:42:52,134 epoch 3 - iter 4689/5212 - loss 0.28645582 - time (sec): 75.02 - samples/sec: 4417.42 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-19 12:43:00,575 epoch 3 - iter 5210/5212 - loss 0.28485558 - time (sec): 83.46 - samples/sec: 4401.47 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-19 12:43:00,608 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:43:00,609 EPOCH 3 done: loss 0.2848 - lr: 0.000039 | |
| 2023-10-19 12:43:05,127 DEV : loss 0.15424801409244537 - f1-score (micro avg) 0.2655 | |
| 2023-10-19 12:43:05,150 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:43:13,654 epoch 4 - iter 521/5212 - loss 0.23083735 - time (sec): 8.50 - samples/sec: 4449.71 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-19 12:43:21,963 epoch 4 - iter 1042/5212 - loss 0.24038158 - time (sec): 16.81 - samples/sec: 4370.66 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-19 12:43:30,476 epoch 4 - iter 1563/5212 - loss 0.24387218 - time (sec): 25.33 - samples/sec: 4396.26 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-19 12:43:38,752 epoch 4 - iter 2084/5212 - loss 0.25131770 - time (sec): 33.60 - samples/sec: 4347.25 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-19 12:43:46,995 epoch 4 - iter 2605/5212 - loss 0.25240929 - time (sec): 41.84 - samples/sec: 4359.80 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-19 12:43:55,908 epoch 4 - iter 3126/5212 - loss 0.24536869 - time (sec): 50.76 - samples/sec: 4309.73 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-19 12:44:04,103 epoch 4 - iter 3647/5212 - loss 0.24569598 - time (sec): 58.95 - samples/sec: 4322.62 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-19 12:44:12,545 epoch 4 - iter 4168/5212 - loss 0.24208870 - time (sec): 67.39 - samples/sec: 4334.05 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-19 12:44:20,894 epoch 4 - iter 4689/5212 - loss 0.24553610 - time (sec): 75.74 - samples/sec: 4371.14 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-19 12:44:29,241 epoch 4 - iter 5210/5212 - loss 0.24595979 - time (sec): 84.09 - samples/sec: 4367.98 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-19 12:44:29,274 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:44:29,274 EPOCH 4 done: loss 0.2459 - lr: 0.000033 | |
| 2023-10-19 12:44:33,816 DEV : loss 0.16588500142097473 - f1-score (micro avg) 0.2542 | |
| 2023-10-19 12:44:33,839 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:44:41,920 epoch 5 - iter 521/5212 - loss 0.23619366 - time (sec): 8.08 - samples/sec: 4011.71 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-19 12:44:50,407 epoch 5 - iter 1042/5212 - loss 0.22990360 - time (sec): 16.57 - samples/sec: 4419.65 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-19 12:44:58,588 epoch 5 - iter 1563/5212 - loss 0.23443858 - time (sec): 24.75 - samples/sec: 4332.12 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-19 12:45:06,990 epoch 5 - iter 2084/5212 - loss 0.23265323 - time (sec): 33.15 - samples/sec: 4402.86 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-19 12:45:15,383 epoch 5 - iter 2605/5212 - loss 0.22890484 - time (sec): 41.54 - samples/sec: 4363.15 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-19 12:45:23,928 epoch 5 - iter 3126/5212 - loss 0.22567797 - time (sec): 50.09 - samples/sec: 4377.36 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 12:45:32,221 epoch 5 - iter 3647/5212 - loss 0.22504579 - time (sec): 58.38 - samples/sec: 4384.04 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 12:45:40,448 epoch 5 - iter 4168/5212 - loss 0.22175996 - time (sec): 66.61 - samples/sec: 4373.65 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 12:45:48,958 epoch 5 - iter 4689/5212 - loss 0.22060023 - time (sec): 75.12 - samples/sec: 4394.33 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 12:45:57,313 epoch 5 - iter 5210/5212 - loss 0.21920627 - time (sec): 83.47 - samples/sec: 4400.79 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 12:45:57,347 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:45:57,348 EPOCH 5 done: loss 0.2193 - lr: 0.000028 | |
| 2023-10-19 12:46:02,433 DEV : loss 0.1704423874616623 - f1-score (micro avg) 0.2369 | |
| 2023-10-19 12:46:02,455 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:46:10,589 epoch 6 - iter 521/5212 - loss 0.20066139 - time (sec): 8.13 - samples/sec: 4352.84 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 12:46:18,871 epoch 6 - iter 1042/5212 - loss 0.20163315 - time (sec): 16.42 - samples/sec: 4372.98 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 12:46:26,922 epoch 6 - iter 1563/5212 - loss 0.20471101 - time (sec): 24.47 - samples/sec: 4398.00 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 12:46:34,965 epoch 6 - iter 2084/5212 - loss 0.20285373 - time (sec): 32.51 - samples/sec: 4460.23 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 12:46:43,049 epoch 6 - iter 2605/5212 - loss 0.20365457 - time (sec): 40.59 - samples/sec: 4462.42 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 12:46:51,455 epoch 6 - iter 3126/5212 - loss 0.20122669 - time (sec): 49.00 - samples/sec: 4485.43 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 12:46:59,804 epoch 6 - iter 3647/5212 - loss 0.20056229 - time (sec): 57.35 - samples/sec: 4484.76 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 12:47:08,064 epoch 6 - iter 4168/5212 - loss 0.20088302 - time (sec): 65.61 - samples/sec: 4461.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 12:47:16,409 epoch 6 - iter 4689/5212 - loss 0.20360026 - time (sec): 73.95 - samples/sec: 4446.39 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 12:47:24,692 epoch 6 - iter 5210/5212 - loss 0.20135037 - time (sec): 82.24 - samples/sec: 4465.47 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 12:47:24,730 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:47:24,730 EPOCH 6 done: loss 0.2015 - lr: 0.000022 | |
| 2023-10-19 12:47:29,838 DEV : loss 0.18821725249290466 - f1-score (micro avg) 0.2472 | |
| 2023-10-19 12:47:29,861 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:47:38,045 epoch 7 - iter 521/5212 - loss 0.18170328 - time (sec): 8.18 - samples/sec: 4512.41 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 12:47:45,967 epoch 7 - iter 1042/5212 - loss 0.18669584 - time (sec): 16.11 - samples/sec: 4459.69 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 12:47:54,222 epoch 7 - iter 1563/5212 - loss 0.19044056 - time (sec): 24.36 - samples/sec: 4417.82 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 12:48:02,478 epoch 7 - iter 2084/5212 - loss 0.18825042 - time (sec): 32.62 - samples/sec: 4460.22 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 12:48:10,835 epoch 7 - iter 2605/5212 - loss 0.18756143 - time (sec): 40.97 - samples/sec: 4474.00 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 12:48:19,272 epoch 7 - iter 3126/5212 - loss 0.18748580 - time (sec): 49.41 - samples/sec: 4448.10 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 12:48:27,883 epoch 7 - iter 3647/5212 - loss 0.19022095 - time (sec): 58.02 - samples/sec: 4465.43 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 12:48:36,192 epoch 7 - iter 4168/5212 - loss 0.18650095 - time (sec): 66.33 - samples/sec: 4433.66 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 12:48:44,645 epoch 7 - iter 4689/5212 - loss 0.18516860 - time (sec): 74.78 - samples/sec: 4424.80 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 12:48:52,930 epoch 7 - iter 5210/5212 - loss 0.18473747 - time (sec): 83.07 - samples/sec: 4420.26 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 12:48:52,972 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:48:52,972 EPOCH 7 done: loss 0.1847 - lr: 0.000017 | |
| 2023-10-19 12:48:58,094 DEV : loss 0.21395063400268555 - f1-score (micro avg) 0.2538 | |
| 2023-10-19 12:48:58,117 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:49:06,575 epoch 8 - iter 521/5212 - loss 0.15862877 - time (sec): 8.46 - samples/sec: 4334.42 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 12:49:14,911 epoch 8 - iter 1042/5212 - loss 0.18100841 - time (sec): 16.79 - samples/sec: 4502.79 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 12:49:23,046 epoch 8 - iter 1563/5212 - loss 0.18687514 - time (sec): 24.93 - samples/sec: 4498.75 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 12:49:31,042 epoch 8 - iter 2084/5212 - loss 0.18206795 - time (sec): 32.92 - samples/sec: 4519.24 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 12:49:39,110 epoch 8 - iter 2605/5212 - loss 0.17991319 - time (sec): 40.99 - samples/sec: 4479.84 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 12:49:47,355 epoch 8 - iter 3126/5212 - loss 0.17865515 - time (sec): 49.24 - samples/sec: 4467.04 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 12:49:55,723 epoch 8 - iter 3647/5212 - loss 0.17797690 - time (sec): 57.61 - samples/sec: 4466.78 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 12:50:03,712 epoch 8 - iter 4168/5212 - loss 0.17640421 - time (sec): 65.59 - samples/sec: 4452.77 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 12:50:12,162 epoch 8 - iter 4689/5212 - loss 0.17412305 - time (sec): 74.05 - samples/sec: 4450.19 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 12:50:20,336 epoch 8 - iter 5210/5212 - loss 0.17327899 - time (sec): 82.22 - samples/sec: 4466.46 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 12:50:20,368 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:50:20,369 EPOCH 8 done: loss 0.1732 - lr: 0.000011 | |
| 2023-10-19 12:50:25,581 DEV : loss 0.2319490760564804 - f1-score (micro avg) 0.2526 | |
| 2023-10-19 12:50:25,603 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:50:33,726 epoch 9 - iter 521/5212 - loss 0.18312888 - time (sec): 8.12 - samples/sec: 4590.45 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 12:50:41,977 epoch 9 - iter 1042/5212 - loss 0.17592071 - time (sec): 16.37 - samples/sec: 4421.50 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 12:50:50,476 epoch 9 - iter 1563/5212 - loss 0.16919437 - time (sec): 24.87 - samples/sec: 4446.16 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 12:50:58,858 epoch 9 - iter 2084/5212 - loss 0.16984065 - time (sec): 33.25 - samples/sec: 4421.93 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 12:51:07,083 epoch 9 - iter 2605/5212 - loss 0.16510263 - time (sec): 41.48 - samples/sec: 4411.94 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 12:51:15,417 epoch 9 - iter 3126/5212 - loss 0.16523013 - time (sec): 49.81 - samples/sec: 4377.83 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 12:51:23,816 epoch 9 - iter 3647/5212 - loss 0.16658392 - time (sec): 58.21 - samples/sec: 4403.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 12:51:32,026 epoch 9 - iter 4168/5212 - loss 0.16708629 - time (sec): 66.42 - samples/sec: 4393.88 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 12:51:40,671 epoch 9 - iter 4689/5212 - loss 0.16558440 - time (sec): 75.07 - samples/sec: 4369.94 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 12:51:49,043 epoch 9 - iter 5210/5212 - loss 0.16580617 - time (sec): 83.44 - samples/sec: 4403.02 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 12:51:49,078 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:51:49,078 EPOCH 9 done: loss 0.1658 - lr: 0.000006 | |
| 2023-10-19 12:51:54,229 DEV : loss 0.2346869856119156 - f1-score (micro avg) 0.2311 | |
| 2023-10-19 12:51:54,254 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:52:02,385 epoch 10 - iter 521/5212 - loss 0.12981061 - time (sec): 8.13 - samples/sec: 4684.15 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 12:52:10,554 epoch 10 - iter 1042/5212 - loss 0.14790609 - time (sec): 16.30 - samples/sec: 4512.11 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 12:52:18,659 epoch 10 - iter 1563/5212 - loss 0.15676457 - time (sec): 24.40 - samples/sec: 4452.83 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 12:52:26,867 epoch 10 - iter 2084/5212 - loss 0.15662785 - time (sec): 32.61 - samples/sec: 4479.24 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 12:52:35,401 epoch 10 - iter 2605/5212 - loss 0.15975847 - time (sec): 41.15 - samples/sec: 4497.68 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 12:52:43,847 epoch 10 - iter 3126/5212 - loss 0.15964390 - time (sec): 49.59 - samples/sec: 4397.75 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 12:52:52,232 epoch 10 - iter 3647/5212 - loss 0.15852081 - time (sec): 57.98 - samples/sec: 4435.35 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 12:53:00,489 epoch 10 - iter 4168/5212 - loss 0.16049237 - time (sec): 66.23 - samples/sec: 4398.62 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 12:53:08,832 epoch 10 - iter 4689/5212 - loss 0.15889932 - time (sec): 74.58 - samples/sec: 4416.14 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 12:53:17,265 epoch 10 - iter 5210/5212 - loss 0.15970840 - time (sec): 83.01 - samples/sec: 4424.80 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-19 12:53:17,299 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:53:17,299 EPOCH 10 done: loss 0.1597 - lr: 0.000000 | |
| 2023-10-19 12:53:22,483 DEV : loss 0.23591217398643494 - f1-score (micro avg) 0.2428 | |
| 2023-10-19 12:53:22,536 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 12:53:22,536 Loading model from best epoch ... | |
| 2023-10-19 12:53:22,620 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-19 12:53:28,802 | |
| Results: | |
| - F-score (micro) 0.2064 | |
| - F-score (macro) 0.1091 | |
| - Accuracy 0.1156 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.4440 0.2611 0.3288 1214 | |
| PER 0.1258 0.0755 0.0944 808 | |
| ORG 0.0294 0.0085 0.0132 353 | |
| HumanProd 0.0000 0.0000 0.0000 15 | |
| micro avg 0.2929 0.1594 0.2064 2390 | |
| macro avg 0.1498 0.0863 0.1091 2390 | |
| weighted avg 0.2724 0.1594 0.2009 2390 | |
| 2023-10-19 12:53:28,802 ---------------------------------------------------------------------------------------------------- | |