| 2023-10-19 20:32:00,351 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,351 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 20:32:00,351 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,351 MultiCorpus: 7142 train + 698 dev + 2570 test sentences | |
| - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator | |
| 2023-10-19 20:32:00,351 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,351 Train: 7142 sentences | |
| 2023-10-19 20:32:00,351 (train_with_dev=False, train_with_test=False) | |
| 2023-10-19 20:32:00,351 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,351 Training Params: | |
| 2023-10-19 20:32:00,351 - learning_rate: "3e-05" | |
| 2023-10-19 20:32:00,351 - mini_batch_size: "4" | |
| 2023-10-19 20:32:00,352 - max_epochs: "10" | |
| 2023-10-19 20:32:00,352 - shuffle: "True" | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 Plugins: | |
| 2023-10-19 20:32:00,352 - TensorboardLogger | |
| 2023-10-19 20:32:00,352 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-19 20:32:00,352 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 Computation: | |
| 2023-10-19 20:32:00,352 - compute on device: cuda:0 | |
| 2023-10-19 20:32:00,352 - embedding storage: none | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 Model training base path: "hmbench-newseye/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:00,352 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-19 20:32:03,297 epoch 1 - iter 178/1786 - loss 3.32754534 - time (sec): 2.94 - samples/sec: 8301.19 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:32:06,455 epoch 1 - iter 356/1786 - loss 2.99552020 - time (sec): 6.10 - samples/sec: 8180.03 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:32:09,601 epoch 1 - iter 534/1786 - loss 2.50760636 - time (sec): 9.25 - samples/sec: 8150.43 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:32:12,742 epoch 1 - iter 712/1786 - loss 2.07292944 - time (sec): 12.39 - samples/sec: 8259.58 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:32:15,794 epoch 1 - iter 890/1786 - loss 1.82574013 - time (sec): 15.44 - samples/sec: 8191.99 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:32:18,850 epoch 1 - iter 1068/1786 - loss 1.65402095 - time (sec): 18.50 - samples/sec: 8111.22 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:32:21,884 epoch 1 - iter 1246/1786 - loss 1.52017083 - time (sec): 21.53 - samples/sec: 8051.47 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:32:24,890 epoch 1 - iter 1424/1786 - loss 1.40266291 - time (sec): 24.54 - samples/sec: 8076.12 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:32:27,811 epoch 1 - iter 1602/1786 - loss 1.30836370 - time (sec): 27.46 - samples/sec: 8142.50 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:32:31,068 epoch 1 - iter 1780/1786 - loss 1.23181977 - time (sec): 30.72 - samples/sec: 8084.96 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 20:32:31,159 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:31,160 EPOCH 1 done: loss 1.2311 - lr: 0.000030 | |
| 2023-10-19 20:32:32,634 DEV : loss 0.332442045211792 - f1-score (micro avg) 0.086 | |
| 2023-10-19 20:32:32,648 saving best model | |
| 2023-10-19 20:32:32,680 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:32:35,792 epoch 2 - iter 178/1786 - loss 0.48971429 - time (sec): 3.11 - samples/sec: 8407.28 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-19 20:32:38,828 epoch 2 - iter 356/1786 - loss 0.48727058 - time (sec): 6.15 - samples/sec: 8212.21 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:32:41,833 epoch 2 - iter 534/1786 - loss 0.47308375 - time (sec): 9.15 - samples/sec: 8096.70 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:32:44,934 epoch 2 - iter 712/1786 - loss 0.47093786 - time (sec): 12.25 - samples/sec: 8191.56 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-19 20:32:47,998 epoch 2 - iter 890/1786 - loss 0.45727677 - time (sec): 15.32 - samples/sec: 8181.28 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:32:51,091 epoch 2 - iter 1068/1786 - loss 0.45758949 - time (sec): 18.41 - samples/sec: 8168.29 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:32:54,094 epoch 2 - iter 1246/1786 - loss 0.45211801 - time (sec): 21.41 - samples/sec: 8132.84 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-19 20:32:57,133 epoch 2 - iter 1424/1786 - loss 0.44511293 - time (sec): 24.45 - samples/sec: 8142.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:33:00,236 epoch 2 - iter 1602/1786 - loss 0.44288817 - time (sec): 27.56 - samples/sec: 8134.49 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:33:03,253 epoch 2 - iter 1780/1786 - loss 0.43672204 - time (sec): 30.57 - samples/sec: 8119.04 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-19 20:33:03,343 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:33:03,344 EPOCH 2 done: loss 0.4369 - lr: 0.000027 | |
| 2023-10-19 20:33:05,683 DEV : loss 0.2546565532684326 - f1-score (micro avg) 0.366 | |
| 2023-10-19 20:33:05,696 saving best model | |
| 2023-10-19 20:33:05,730 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:33:08,715 epoch 3 - iter 178/1786 - loss 0.37082634 - time (sec): 2.99 - samples/sec: 7746.66 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:33:11,668 epoch 3 - iter 356/1786 - loss 0.36635335 - time (sec): 5.94 - samples/sec: 8104.85 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:33:14,833 epoch 3 - iter 534/1786 - loss 0.36916731 - time (sec): 9.10 - samples/sec: 8042.33 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-19 20:33:17,972 epoch 3 - iter 712/1786 - loss 0.37973970 - time (sec): 12.24 - samples/sec: 8096.35 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:33:20,911 epoch 3 - iter 890/1786 - loss 0.38024056 - time (sec): 15.18 - samples/sec: 8137.05 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:33:23,735 epoch 3 - iter 1068/1786 - loss 0.37160042 - time (sec): 18.00 - samples/sec: 8260.60 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-19 20:33:26,857 epoch 3 - iter 1246/1786 - loss 0.36830405 - time (sec): 21.13 - samples/sec: 8222.40 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:33:30,028 epoch 3 - iter 1424/1786 - loss 0.36360124 - time (sec): 24.30 - samples/sec: 8191.11 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:33:33,157 epoch 3 - iter 1602/1786 - loss 0.35846373 - time (sec): 27.43 - samples/sec: 8164.32 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-19 20:33:36,217 epoch 3 - iter 1780/1786 - loss 0.35471508 - time (sec): 30.49 - samples/sec: 8118.57 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:33:36,332 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:33:36,332 EPOCH 3 done: loss 0.3546 - lr: 0.000023 | |
| 2023-10-19 20:33:39,156 DEV : loss 0.22689871490001678 - f1-score (micro avg) 0.4293 | |
| 2023-10-19 20:33:39,170 saving best model | |
| 2023-10-19 20:33:39,203 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:33:42,292 epoch 4 - iter 178/1786 - loss 0.33183201 - time (sec): 3.09 - samples/sec: 7976.40 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:33:45,317 epoch 4 - iter 356/1786 - loss 0.33466415 - time (sec): 6.11 - samples/sec: 8090.12 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-19 20:33:48,413 epoch 4 - iter 534/1786 - loss 0.31911501 - time (sec): 9.21 - samples/sec: 8052.80 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:33:51,452 epoch 4 - iter 712/1786 - loss 0.31645588 - time (sec): 12.25 - samples/sec: 8078.11 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:33:54,555 epoch 4 - iter 890/1786 - loss 0.31727146 - time (sec): 15.35 - samples/sec: 8064.96 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-19 20:33:57,632 epoch 4 - iter 1068/1786 - loss 0.31778035 - time (sec): 18.43 - samples/sec: 8114.20 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:34:00,664 epoch 4 - iter 1246/1786 - loss 0.32088801 - time (sec): 21.46 - samples/sec: 8061.89 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:34:03,815 epoch 4 - iter 1424/1786 - loss 0.32135691 - time (sec): 24.61 - samples/sec: 8065.68 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-19 20:34:06,801 epoch 4 - iter 1602/1786 - loss 0.32028615 - time (sec): 27.60 - samples/sec: 8032.40 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:34:09,981 epoch 4 - iter 1780/1786 - loss 0.31755337 - time (sec): 30.78 - samples/sec: 8054.80 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:34:10,091 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:34:10,091 EPOCH 4 done: loss 0.3173 - lr: 0.000020 | |
| 2023-10-19 20:34:12,477 DEV : loss 0.21633675694465637 - f1-score (micro avg) 0.4634 | |
| 2023-10-19 20:34:12,492 saving best model | |
| 2023-10-19 20:34:12,528 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:34:15,215 epoch 5 - iter 178/1786 - loss 0.27680115 - time (sec): 2.69 - samples/sec: 9072.91 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-19 20:34:17,836 epoch 5 - iter 356/1786 - loss 0.28824880 - time (sec): 5.31 - samples/sec: 9164.73 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:34:20,835 epoch 5 - iter 534/1786 - loss 0.29282530 - time (sec): 8.31 - samples/sec: 8785.11 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:34:23,952 epoch 5 - iter 712/1786 - loss 0.29251154 - time (sec): 11.42 - samples/sec: 8608.71 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-19 20:34:27,467 epoch 5 - iter 890/1786 - loss 0.29527347 - time (sec): 14.94 - samples/sec: 8294.34 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:34:30,608 epoch 5 - iter 1068/1786 - loss 0.29254338 - time (sec): 18.08 - samples/sec: 8231.58 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:34:33,649 epoch 5 - iter 1246/1786 - loss 0.29410203 - time (sec): 21.12 - samples/sec: 8210.30 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-19 20:34:36,935 epoch 5 - iter 1424/1786 - loss 0.29602451 - time (sec): 24.41 - samples/sec: 8141.60 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:34:40,074 epoch 5 - iter 1602/1786 - loss 0.29176349 - time (sec): 27.55 - samples/sec: 8101.73 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:34:43,157 epoch 5 - iter 1780/1786 - loss 0.29064522 - time (sec): 30.63 - samples/sec: 8094.19 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-19 20:34:43,261 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:34:43,261 EPOCH 5 done: loss 0.2905 - lr: 0.000017 | |
| 2023-10-19 20:34:46,153 DEV : loss 0.20622387528419495 - f1-score (micro avg) 0.4786 | |
| 2023-10-19 20:34:46,168 saving best model | |
| 2023-10-19 20:34:46,201 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:34:49,342 epoch 6 - iter 178/1786 - loss 0.27032943 - time (sec): 3.14 - samples/sec: 7933.80 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:34:52,435 epoch 6 - iter 356/1786 - loss 0.27170061 - time (sec): 6.23 - samples/sec: 7725.16 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:34:55,670 epoch 6 - iter 534/1786 - loss 0.26713977 - time (sec): 9.47 - samples/sec: 7598.11 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-19 20:34:58,761 epoch 6 - iter 712/1786 - loss 0.26494070 - time (sec): 12.56 - samples/sec: 7680.41 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:35:01,862 epoch 6 - iter 890/1786 - loss 0.26762243 - time (sec): 15.66 - samples/sec: 7704.47 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:35:04,978 epoch 6 - iter 1068/1786 - loss 0.27032426 - time (sec): 18.78 - samples/sec: 7748.42 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-19 20:35:08,054 epoch 6 - iter 1246/1786 - loss 0.27154388 - time (sec): 21.85 - samples/sec: 7823.54 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:35:11,117 epoch 6 - iter 1424/1786 - loss 0.27377412 - time (sec): 24.91 - samples/sec: 7910.87 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:35:14,161 epoch 6 - iter 1602/1786 - loss 0.27292448 - time (sec): 27.96 - samples/sec: 7962.08 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-19 20:35:17,363 epoch 6 - iter 1780/1786 - loss 0.27251347 - time (sec): 31.16 - samples/sec: 7950.61 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:35:17,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:35:17,477 EPOCH 6 done: loss 0.2720 - lr: 0.000013 | |
| 2023-10-19 20:35:19,851 DEV : loss 0.1968582421541214 - f1-score (micro avg) 0.4949 | |
| 2023-10-19 20:35:19,865 saving best model | |
| 2023-10-19 20:35:19,900 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:35:22,936 epoch 7 - iter 178/1786 - loss 0.24006764 - time (sec): 3.03 - samples/sec: 7523.24 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:35:25,964 epoch 7 - iter 356/1786 - loss 0.25690864 - time (sec): 6.06 - samples/sec: 7769.94 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-19 20:35:29,059 epoch 7 - iter 534/1786 - loss 0.25439491 - time (sec): 9.16 - samples/sec: 7909.75 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:35:32,058 epoch 7 - iter 712/1786 - loss 0.25285107 - time (sec): 12.16 - samples/sec: 7921.22 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:35:35,190 epoch 7 - iter 890/1786 - loss 0.25158788 - time (sec): 15.29 - samples/sec: 7977.69 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-19 20:35:38,159 epoch 7 - iter 1068/1786 - loss 0.25381241 - time (sec): 18.26 - samples/sec: 7966.12 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:35:41,156 epoch 7 - iter 1246/1786 - loss 0.25712643 - time (sec): 21.25 - samples/sec: 7918.27 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:35:44,414 epoch 7 - iter 1424/1786 - loss 0.25746357 - time (sec): 24.51 - samples/sec: 8037.79 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-19 20:35:47,477 epoch 7 - iter 1602/1786 - loss 0.25757421 - time (sec): 27.58 - samples/sec: 8119.90 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:35:50,558 epoch 7 - iter 1780/1786 - loss 0.25799854 - time (sec): 30.66 - samples/sec: 8090.47 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:35:50,663 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:35:50,664 EPOCH 7 done: loss 0.2576 - lr: 0.000010 | |
| 2023-10-19 20:35:53,513 DEV : loss 0.19658498466014862 - f1-score (micro avg) 0.4945 | |
| 2023-10-19 20:35:53,528 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:35:56,505 epoch 8 - iter 178/1786 - loss 0.22844374 - time (sec): 2.98 - samples/sec: 7926.19 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-19 20:35:59,573 epoch 8 - iter 356/1786 - loss 0.23968996 - time (sec): 6.04 - samples/sec: 8226.99 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:36:02,632 epoch 8 - iter 534/1786 - loss 0.24477437 - time (sec): 9.10 - samples/sec: 8151.27 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:36:05,766 epoch 8 - iter 712/1786 - loss 0.24078464 - time (sec): 12.24 - samples/sec: 8098.25 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-19 20:36:08,877 epoch 8 - iter 890/1786 - loss 0.25006937 - time (sec): 15.35 - samples/sec: 7993.62 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:36:11,957 epoch 8 - iter 1068/1786 - loss 0.25146410 - time (sec): 18.43 - samples/sec: 8001.77 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:36:15,041 epoch 8 - iter 1246/1786 - loss 0.24964134 - time (sec): 21.51 - samples/sec: 7964.04 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-19 20:36:18,053 epoch 8 - iter 1424/1786 - loss 0.24702717 - time (sec): 24.53 - samples/sec: 7974.14 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:36:21,146 epoch 8 - iter 1602/1786 - loss 0.24740242 - time (sec): 27.62 - samples/sec: 8066.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:36:24,282 epoch 8 - iter 1780/1786 - loss 0.24591802 - time (sec): 30.75 - samples/sec: 8065.89 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-19 20:36:24,388 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:36:24,388 EPOCH 8 done: loss 0.2465 - lr: 0.000007 | |
| 2023-10-19 20:36:26,749 DEV : loss 0.19389420747756958 - f1-score (micro avg) 0.5054 | |
| 2023-10-19 20:36:26,764 saving best model | |
| 2023-10-19 20:36:26,799 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:36:29,850 epoch 9 - iter 178/1786 - loss 0.25583969 - time (sec): 3.05 - samples/sec: 7983.20 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:36:32,832 epoch 9 - iter 356/1786 - loss 0.24145976 - time (sec): 6.03 - samples/sec: 8129.78 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:36:35,417 epoch 9 - iter 534/1786 - loss 0.24379068 - time (sec): 8.62 - samples/sec: 8495.79 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-19 20:36:38,167 epoch 9 - iter 712/1786 - loss 0.24757821 - time (sec): 11.37 - samples/sec: 8686.25 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:36:41,229 epoch 9 - iter 890/1786 - loss 0.24744320 - time (sec): 14.43 - samples/sec: 8711.33 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:36:44,224 epoch 9 - iter 1068/1786 - loss 0.24257814 - time (sec): 17.42 - samples/sec: 8575.61 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-19 20:36:47,249 epoch 9 - iter 1246/1786 - loss 0.24236958 - time (sec): 20.45 - samples/sec: 8537.05 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:36:50,305 epoch 9 - iter 1424/1786 - loss 0.24100770 - time (sec): 23.51 - samples/sec: 8446.55 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:36:53,554 epoch 9 - iter 1602/1786 - loss 0.23994016 - time (sec): 26.75 - samples/sec: 8359.62 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-19 20:36:56,756 epoch 9 - iter 1780/1786 - loss 0.23975442 - time (sec): 29.96 - samples/sec: 8274.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:36:56,862 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:36:56,862 EPOCH 9 done: loss 0.2396 - lr: 0.000003 | |
| 2023-10-19 20:36:59,733 DEV : loss 0.19508205354213715 - f1-score (micro avg) 0.5112 | |
| 2023-10-19 20:36:59,749 saving best model | |
| 2023-10-19 20:36:59,785 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:37:02,860 epoch 10 - iter 178/1786 - loss 0.22700481 - time (sec): 3.07 - samples/sec: 8525.85 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:37:05,989 epoch 10 - iter 356/1786 - loss 0.22976632 - time (sec): 6.20 - samples/sec: 8348.54 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-19 20:37:09,068 epoch 10 - iter 534/1786 - loss 0.23666307 - time (sec): 9.28 - samples/sec: 8401.78 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:37:12,053 epoch 10 - iter 712/1786 - loss 0.23862130 - time (sec): 12.27 - samples/sec: 8350.81 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:37:15,183 epoch 10 - iter 890/1786 - loss 0.23849067 - time (sec): 15.40 - samples/sec: 8264.52 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-19 20:37:18,236 epoch 10 - iter 1068/1786 - loss 0.23907350 - time (sec): 18.45 - samples/sec: 8214.37 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:37:21,420 epoch 10 - iter 1246/1786 - loss 0.23722320 - time (sec): 21.63 - samples/sec: 8133.94 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:37:24,454 epoch 10 - iter 1424/1786 - loss 0.23624508 - time (sec): 24.67 - samples/sec: 8100.71 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-19 20:37:27,377 epoch 10 - iter 1602/1786 - loss 0.23688162 - time (sec): 27.59 - samples/sec: 8104.12 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-19 20:37:30,390 epoch 10 - iter 1780/1786 - loss 0.23692269 - time (sec): 30.60 - samples/sec: 8091.67 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-19 20:37:30,493 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:37:30,494 EPOCH 10 done: loss 0.2370 - lr: 0.000000 | |
| 2023-10-19 20:37:32,851 DEV : loss 0.1948169320821762 - f1-score (micro avg) 0.5124 | |
| 2023-10-19 20:37:32,865 saving best model | |
| 2023-10-19 20:37:32,928 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-19 20:37:32,928 Loading model from best epoch ... | |
| 2023-10-19 20:37:33,001 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-19 20:37:37,533 | |
| Results: | |
| - F-score (micro) 0.4123 | |
| - F-score (macro) 0.241 | |
| - Accuracy 0.2682 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.4067 0.5233 0.4577 1095 | |
| PER 0.4154 0.5020 0.4546 1012 | |
| ORG 0.0765 0.0392 0.0519 357 | |
| HumanProd 0.0000 0.0000 0.0000 33 | |
| micro avg 0.3890 0.4385 0.4123 2497 | |
| macro avg 0.2246 0.2661 0.2410 2497 | |
| weighted avg 0.3576 0.4385 0.3924 2497 | |
| 2023-10-19 20:37:37,533 ---------------------------------------------------------------------------------------------------- | |