| 2023-10-17 09:43:43,013 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,014 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): ElectraModel( | |
| (embeddings): ElectraEmbeddings( | |
| (word_embeddings): Embedding(32001, 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): ElectraEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x ElectraLayer( | |
| (attention): ElectraAttention( | |
| (self): ElectraSelfAttention( | |
| (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): ElectraSelfOutput( | |
| (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): ElectraIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): ElectraOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=25, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 09:43:43,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,014 MultiCorpus: 1214 train + 266 dev + 251 test sentences | |
| - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator | |
| 2023-10-17 09:43:43,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,014 Train: 1214 sentences | |
| 2023-10-17 09:43:43,014 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 09:43:43,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,014 Training Params: | |
| 2023-10-17 09:43:43,014 - learning_rate: "5e-05" | |
| 2023-10-17 09:43:43,014 - mini_batch_size: "4" | |
| 2023-10-17 09:43:43,014 - max_epochs: "10" | |
| 2023-10-17 09:43:43,014 - shuffle: "True" | |
| 2023-10-17 09:43:43,014 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,014 Plugins: | |
| 2023-10-17 09:43:43,014 - TensorboardLogger | |
| 2023-10-17 09:43:43,015 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 09:43:43,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,015 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 09:43:43,015 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 09:43:43,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,015 Computation: | |
| 2023-10-17 09:43:43,015 - compute on device: cuda:0 | |
| 2023-10-17 09:43:43,015 - embedding storage: none | |
| 2023-10-17 09:43:43,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,015 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2" | |
| 2023-10-17 09:43:43,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,015 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:43,015 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 09:43:44,472 epoch 1 - iter 30/304 - loss 3.85303893 - time (sec): 1.46 - samples/sec: 2032.49 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:43:45,859 epoch 1 - iter 60/304 - loss 2.70859312 - time (sec): 2.84 - samples/sec: 2160.04 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:43:47,232 epoch 1 - iter 90/304 - loss 2.05939999 - time (sec): 4.22 - samples/sec: 2212.41 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:43:48,626 epoch 1 - iter 120/304 - loss 1.68331626 - time (sec): 5.61 - samples/sec: 2179.76 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:43:49,966 epoch 1 - iter 150/304 - loss 1.41963423 - time (sec): 6.95 - samples/sec: 2235.40 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:43:51,355 epoch 1 - iter 180/304 - loss 1.25060057 - time (sec): 8.34 - samples/sec: 2193.16 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:43:52,796 epoch 1 - iter 210/304 - loss 1.11912342 - time (sec): 9.78 - samples/sec: 2177.63 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 09:43:54,207 epoch 1 - iter 240/304 - loss 1.01434373 - time (sec): 11.19 - samples/sec: 2175.58 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 09:43:55,616 epoch 1 - iter 270/304 - loss 0.92573670 - time (sec): 12.60 - samples/sec: 2183.17 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 09:43:57,063 epoch 1 - iter 300/304 - loss 0.85261400 - time (sec): 14.05 - samples/sec: 2186.16 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:43:57,242 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:43:57,242 EPOCH 1 done: loss 0.8464 - lr: 0.000049 | |
| 2023-10-17 09:43:58,560 DEV : loss 0.20075689256191254 - f1-score (micro avg) 0.6292 | |
| 2023-10-17 09:43:58,570 saving best model | |
| 2023-10-17 09:43:58,912 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:00,332 epoch 2 - iter 30/304 - loss 0.20653213 - time (sec): 1.42 - samples/sec: 2158.64 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:44:01,764 epoch 2 - iter 60/304 - loss 0.16108696 - time (sec): 2.85 - samples/sec: 2191.43 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 09:44:03,179 epoch 2 - iter 90/304 - loss 0.16203340 - time (sec): 4.27 - samples/sec: 2139.09 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 09:44:04,543 epoch 2 - iter 120/304 - loss 0.15811444 - time (sec): 5.63 - samples/sec: 2156.62 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 09:44:05,890 epoch 2 - iter 150/304 - loss 0.14928484 - time (sec): 6.98 - samples/sec: 2192.71 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 09:44:07,238 epoch 2 - iter 180/304 - loss 0.14562242 - time (sec): 8.32 - samples/sec: 2194.83 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 09:44:08,530 epoch 2 - iter 210/304 - loss 0.14077729 - time (sec): 9.62 - samples/sec: 2212.31 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 09:44:09,896 epoch 2 - iter 240/304 - loss 0.14061539 - time (sec): 10.98 - samples/sec: 2221.21 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 09:44:11,256 epoch 2 - iter 270/304 - loss 0.14244412 - time (sec): 12.34 - samples/sec: 2238.55 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 09:44:12,597 epoch 2 - iter 300/304 - loss 0.14143420 - time (sec): 13.68 - samples/sec: 2243.43 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 09:44:12,770 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:12,771 EPOCH 2 done: loss 0.1404 - lr: 0.000045 | |
| 2023-10-17 09:44:13,731 DEV : loss 0.151620551943779 - f1-score (micro avg) 0.7813 | |
| 2023-10-17 09:44:13,738 saving best model | |
| 2023-10-17 09:44:14,201 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:15,522 epoch 3 - iter 30/304 - loss 0.10391077 - time (sec): 1.32 - samples/sec: 2395.65 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 09:44:16,840 epoch 3 - iter 60/304 - loss 0.09772973 - time (sec): 2.64 - samples/sec: 2277.13 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 09:44:18,177 epoch 3 - iter 90/304 - loss 0.09243704 - time (sec): 3.98 - samples/sec: 2256.10 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 09:44:19,510 epoch 3 - iter 120/304 - loss 0.09744463 - time (sec): 5.31 - samples/sec: 2248.13 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 09:44:20,866 epoch 3 - iter 150/304 - loss 0.10036627 - time (sec): 6.66 - samples/sec: 2244.51 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 09:44:22,310 epoch 3 - iter 180/304 - loss 0.09933123 - time (sec): 8.11 - samples/sec: 2225.18 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 09:44:23,735 epoch 3 - iter 210/304 - loss 0.09472151 - time (sec): 9.53 - samples/sec: 2223.11 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 09:44:25,099 epoch 3 - iter 240/304 - loss 0.09113119 - time (sec): 10.90 - samples/sec: 2259.48 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 09:44:26,456 epoch 3 - iter 270/304 - loss 0.08756966 - time (sec): 12.25 - samples/sec: 2264.82 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 09:44:27,809 epoch 3 - iter 300/304 - loss 0.08830567 - time (sec): 13.61 - samples/sec: 2256.25 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 09:44:27,976 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:27,977 EPOCH 3 done: loss 0.0895 - lr: 0.000039 | |
| 2023-10-17 09:44:28,943 DEV : loss 0.17477081716060638 - f1-score (micro avg) 0.8047 | |
| 2023-10-17 09:44:28,950 saving best model | |
| 2023-10-17 09:44:29,418 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:30,807 epoch 4 - iter 30/304 - loss 0.04755733 - time (sec): 1.38 - samples/sec: 2018.58 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 09:44:32,126 epoch 4 - iter 60/304 - loss 0.06338761 - time (sec): 2.70 - samples/sec: 2052.32 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 09:44:33,617 epoch 4 - iter 90/304 - loss 0.06724667 - time (sec): 4.19 - samples/sec: 2009.06 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 09:44:35,081 epoch 4 - iter 120/304 - loss 0.06089099 - time (sec): 5.66 - samples/sec: 2006.35 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 09:44:36,433 epoch 4 - iter 150/304 - loss 0.06159323 - time (sec): 7.01 - samples/sec: 2069.74 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 09:44:37,836 epoch 4 - iter 180/304 - loss 0.06403016 - time (sec): 8.41 - samples/sec: 2114.49 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 09:44:39,202 epoch 4 - iter 210/304 - loss 0.06555839 - time (sec): 9.78 - samples/sec: 2136.62 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 09:44:40,545 epoch 4 - iter 240/304 - loss 0.06644536 - time (sec): 11.12 - samples/sec: 2162.32 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 09:44:41,885 epoch 4 - iter 270/304 - loss 0.06816296 - time (sec): 12.46 - samples/sec: 2190.31 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 09:44:43,304 epoch 4 - iter 300/304 - loss 0.06500450 - time (sec): 13.88 - samples/sec: 2204.31 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 09:44:43,471 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:43,471 EPOCH 4 done: loss 0.0655 - lr: 0.000033 | |
| 2023-10-17 09:44:44,449 DEV : loss 0.18980929255485535 - f1-score (micro avg) 0.8365 | |
| 2023-10-17 09:44:44,456 saving best model | |
| 2023-10-17 09:44:44,925 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:46,326 epoch 5 - iter 30/304 - loss 0.02401111 - time (sec): 1.40 - samples/sec: 2267.34 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 09:44:47,656 epoch 5 - iter 60/304 - loss 0.05342675 - time (sec): 2.73 - samples/sec: 2173.77 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 09:44:49,056 epoch 5 - iter 90/304 - loss 0.05631191 - time (sec): 4.13 - samples/sec: 2176.16 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 09:44:50,505 epoch 5 - iter 120/304 - loss 0.06003646 - time (sec): 5.58 - samples/sec: 2126.49 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 09:44:51,955 epoch 5 - iter 150/304 - loss 0.05754935 - time (sec): 7.03 - samples/sec: 2092.70 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 09:44:53,374 epoch 5 - iter 180/304 - loss 0.05497355 - time (sec): 8.45 - samples/sec: 2155.79 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:44:54,709 epoch 5 - iter 210/304 - loss 0.04948656 - time (sec): 9.78 - samples/sec: 2201.45 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 09:44:56,049 epoch 5 - iter 240/304 - loss 0.04587377 - time (sec): 11.12 - samples/sec: 2205.68 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 09:44:57,396 epoch 5 - iter 270/304 - loss 0.04919135 - time (sec): 12.47 - samples/sec: 2202.09 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:44:58,771 epoch 5 - iter 300/304 - loss 0.05122097 - time (sec): 13.84 - samples/sec: 2211.11 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 09:44:58,949 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:44:58,949 EPOCH 5 done: loss 0.0513 - lr: 0.000028 | |
| 2023-10-17 09:44:59,930 DEV : loss 0.19925805926322937 - f1-score (micro avg) 0.8353 | |
| 2023-10-17 09:44:59,939 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:01,299 epoch 6 - iter 30/304 - loss 0.01433141 - time (sec): 1.36 - samples/sec: 2429.62 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:45:02,704 epoch 6 - iter 60/304 - loss 0.03628474 - time (sec): 2.76 - samples/sec: 2405.36 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 09:45:04,042 epoch 6 - iter 90/304 - loss 0.03234465 - time (sec): 4.10 - samples/sec: 2371.94 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:45:05,475 epoch 6 - iter 120/304 - loss 0.02501041 - time (sec): 5.53 - samples/sec: 2312.29 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 09:45:06,839 epoch 6 - iter 150/304 - loss 0.02649602 - time (sec): 6.90 - samples/sec: 2294.45 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:45:08,222 epoch 6 - iter 180/304 - loss 0.03984986 - time (sec): 8.28 - samples/sec: 2239.41 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 09:45:09,615 epoch 6 - iter 210/304 - loss 0.04051217 - time (sec): 9.67 - samples/sec: 2208.55 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 09:45:10,995 epoch 6 - iter 240/304 - loss 0.04107986 - time (sec): 11.05 - samples/sec: 2205.29 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:45:12,405 epoch 6 - iter 270/304 - loss 0.03983681 - time (sec): 12.46 - samples/sec: 2199.95 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 09:45:13,775 epoch 6 - iter 300/304 - loss 0.03899728 - time (sec): 13.83 - samples/sec: 2215.05 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:45:13,955 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:13,955 EPOCH 6 done: loss 0.0386 - lr: 0.000022 | |
| 2023-10-17 09:45:14,940 DEV : loss 0.21286360919475555 - f1-score (micro avg) 0.819 | |
| 2023-10-17 09:45:14,946 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:16,343 epoch 7 - iter 30/304 - loss 0.03207576 - time (sec): 1.40 - samples/sec: 2050.31 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 09:45:17,670 epoch 7 - iter 60/304 - loss 0.03650962 - time (sec): 2.72 - samples/sec: 2137.02 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:45:19,016 epoch 7 - iter 90/304 - loss 0.03639294 - time (sec): 4.07 - samples/sec: 2224.59 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 09:45:20,337 epoch 7 - iter 120/304 - loss 0.02934814 - time (sec): 5.39 - samples/sec: 2228.78 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:45:21,631 epoch 7 - iter 150/304 - loss 0.02501591 - time (sec): 6.68 - samples/sec: 2255.28 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 09:45:23,006 epoch 7 - iter 180/304 - loss 0.02484613 - time (sec): 8.06 - samples/sec: 2215.80 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 09:45:24,339 epoch 7 - iter 210/304 - loss 0.02512442 - time (sec): 9.39 - samples/sec: 2227.51 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:45:25,698 epoch 7 - iter 240/304 - loss 0.02405767 - time (sec): 10.75 - samples/sec: 2239.72 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 09:45:27,092 epoch 7 - iter 270/304 - loss 0.02534607 - time (sec): 12.14 - samples/sec: 2249.47 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:45:28,418 epoch 7 - iter 300/304 - loss 0.02497540 - time (sec): 13.47 - samples/sec: 2275.48 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 09:45:28,595 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:28,596 EPOCH 7 done: loss 0.0247 - lr: 0.000017 | |
| 2023-10-17 09:45:29,537 DEV : loss 0.2345665693283081 - f1-score (micro avg) 0.8333 | |
| 2023-10-17 09:45:29,544 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:30,934 epoch 8 - iter 30/304 - loss 0.04718473 - time (sec): 1.39 - samples/sec: 2124.09 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:45:32,289 epoch 8 - iter 60/304 - loss 0.02677817 - time (sec): 2.74 - samples/sec: 2170.57 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 09:45:33,600 epoch 8 - iter 90/304 - loss 0.02084026 - time (sec): 4.06 - samples/sec: 2273.67 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:45:34,882 epoch 8 - iter 120/304 - loss 0.01771749 - time (sec): 5.34 - samples/sec: 2272.30 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 09:45:36,172 epoch 8 - iter 150/304 - loss 0.02343652 - time (sec): 6.63 - samples/sec: 2279.67 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 09:45:37,535 epoch 8 - iter 180/304 - loss 0.02058013 - time (sec): 7.99 - samples/sec: 2296.71 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:45:38,910 epoch 8 - iter 210/304 - loss 0.01947847 - time (sec): 9.36 - samples/sec: 2269.12 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 09:45:40,272 epoch 8 - iter 240/304 - loss 0.02129666 - time (sec): 10.73 - samples/sec: 2294.70 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:45:41,629 epoch 8 - iter 270/304 - loss 0.02070254 - time (sec): 12.08 - samples/sec: 2286.10 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 09:45:43,011 epoch 8 - iter 300/304 - loss 0.02150750 - time (sec): 13.47 - samples/sec: 2275.45 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:45:43,181 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:43,181 EPOCH 8 done: loss 0.0219 - lr: 0.000011 | |
| 2023-10-17 09:45:44,193 DEV : loss 0.25073373317718506 - f1-score (micro avg) 0.8432 | |
| 2023-10-17 09:45:44,205 saving best model | |
| 2023-10-17 09:45:44,681 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:46,277 epoch 9 - iter 30/304 - loss 0.00629017 - time (sec): 1.59 - samples/sec: 1784.73 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 09:45:47,888 epoch 9 - iter 60/304 - loss 0.01431142 - time (sec): 3.21 - samples/sec: 1853.34 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:45:49,474 epoch 9 - iter 90/304 - loss 0.01967760 - time (sec): 4.79 - samples/sec: 1873.97 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 09:45:51,034 epoch 9 - iter 120/304 - loss 0.01851460 - time (sec): 6.35 - samples/sec: 1928.59 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 09:45:52,428 epoch 9 - iter 150/304 - loss 0.01578032 - time (sec): 7.74 - samples/sec: 1971.08 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:45:53,769 epoch 9 - iter 180/304 - loss 0.01692281 - time (sec): 9.09 - samples/sec: 2005.54 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 09:45:55,104 epoch 9 - iter 210/304 - loss 0.01528711 - time (sec): 10.42 - samples/sec: 2020.52 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:45:56,458 epoch 9 - iter 240/304 - loss 0.01382498 - time (sec): 11.77 - samples/sec: 2035.96 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 09:45:57,812 epoch 9 - iter 270/304 - loss 0.01825035 - time (sec): 13.13 - samples/sec: 2089.48 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:45:59,169 epoch 9 - iter 300/304 - loss 0.01919734 - time (sec): 14.49 - samples/sec: 2105.89 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 09:45:59,347 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:45:59,347 EPOCH 9 done: loss 0.0190 - lr: 0.000006 | |
| 2023-10-17 09:46:00,301 DEV : loss 0.2418389618396759 - f1-score (micro avg) 0.8205 | |
| 2023-10-17 09:46:00,309 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:46:01,658 epoch 10 - iter 30/304 - loss 0.01494221 - time (sec): 1.35 - samples/sec: 2236.95 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:46:03,109 epoch 10 - iter 60/304 - loss 0.00743611 - time (sec): 2.80 - samples/sec: 2200.83 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 09:46:04,464 epoch 10 - iter 90/304 - loss 0.01218086 - time (sec): 4.15 - samples/sec: 2253.55 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 09:46:05,856 epoch 10 - iter 120/304 - loss 0.01366126 - time (sec): 5.55 - samples/sec: 2200.93 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:46:07,216 epoch 10 - iter 150/304 - loss 0.01371746 - time (sec): 6.91 - samples/sec: 2224.27 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 09:46:08,671 epoch 10 - iter 180/304 - loss 0.01566323 - time (sec): 8.36 - samples/sec: 2180.75 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:46:10,035 epoch 10 - iter 210/304 - loss 0.01547879 - time (sec): 9.72 - samples/sec: 2192.13 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 09:46:11,389 epoch 10 - iter 240/304 - loss 0.01473170 - time (sec): 11.08 - samples/sec: 2213.78 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:46:12,752 epoch 10 - iter 270/304 - loss 0.01388526 - time (sec): 12.44 - samples/sec: 2196.48 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 09:46:14,148 epoch 10 - iter 300/304 - loss 0.01305331 - time (sec): 13.84 - samples/sec: 2210.22 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 09:46:14,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:46:14,338 EPOCH 10 done: loss 0.0129 - lr: 0.000000 | |
| 2023-10-17 09:46:15,308 DEV : loss 0.2391704022884369 - f1-score (micro avg) 0.8314 | |
| 2023-10-17 09:46:15,682 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 09:46:15,684 Loading model from best epoch ... | |
| 2023-10-17 09:46:17,079 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object | |
| 2023-10-17 09:46:17,998 | |
| Results: | |
| - F-score (micro) 0.8182 | |
| - F-score (macro) 0.5979 | |
| - Accuracy 0.6972 | |
| By class: | |
| precision recall f1-score support | |
| scope 0.7834 0.8146 0.7987 151 | |
| pers 0.7982 0.9479 0.8667 96 | |
| work 0.7885 0.8632 0.8241 95 | |
| date 0.0000 0.0000 0.0000 3 | |
| loc 1.0000 0.3333 0.5000 3 | |
| micro avg 0.7857 0.8534 0.8182 348 | |
| macro avg 0.6740 0.5918 0.5979 348 | |
| weighted avg 0.7840 0.8534 0.8149 348 | |
| 2023-10-17 09:46:17,998 ---------------------------------------------------------------------------------------------------- | |