| 2023-10-17 22:54:53,029 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,030 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=21, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 22:54:53,030 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences | |
| - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Train: 5901 sentences | |
| 2023-10-17 22:54:53,031 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Training Params: | |
| 2023-10-17 22:54:53,031 - learning_rate: "5e-05" | |
| 2023-10-17 22:54:53,031 - mini_batch_size: "4" | |
| 2023-10-17 22:54:53,031 - max_epochs: "10" | |
| 2023-10-17 22:54:53,031 - shuffle: "True" | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Plugins: | |
| 2023-10-17 22:54:53,031 - TensorboardLogger | |
| 2023-10-17 22:54:53,031 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 22:54:53,031 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Computation: | |
| 2023-10-17 22:54:53,031 - compute on device: cuda:0 | |
| 2023-10-17 22:54:53,031 - embedding storage: none | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:54:53,032 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 22:55:00,436 epoch 1 - iter 147/1476 - loss 2.61410065 - time (sec): 7.40 - samples/sec: 2290.24 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 22:55:07,619 epoch 1 - iter 294/1476 - loss 1.63401124 - time (sec): 14.59 - samples/sec: 2183.35 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 22:55:14,513 epoch 1 - iter 441/1476 - loss 1.23823546 - time (sec): 21.48 - samples/sec: 2196.79 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 22:55:21,963 epoch 1 - iter 588/1476 - loss 0.99381365 - time (sec): 28.93 - samples/sec: 2221.21 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 22:55:29,464 epoch 1 - iter 735/1476 - loss 0.82861680 - time (sec): 36.43 - samples/sec: 2270.11 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 22:55:36,924 epoch 1 - iter 882/1476 - loss 0.72615788 - time (sec): 43.89 - samples/sec: 2273.52 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 22:55:44,082 epoch 1 - iter 1029/1476 - loss 0.65613249 - time (sec): 51.05 - samples/sec: 2257.24 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 22:55:51,290 epoch 1 - iter 1176/1476 - loss 0.59494235 - time (sec): 58.26 - samples/sec: 2262.84 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 22:55:58,694 epoch 1 - iter 1323/1476 - loss 0.54631725 - time (sec): 65.66 - samples/sec: 2261.98 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 22:56:06,128 epoch 1 - iter 1470/1476 - loss 0.50564963 - time (sec): 73.10 - samples/sec: 2271.56 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 22:56:06,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:56:06,396 EPOCH 1 done: loss 0.5053 - lr: 0.000050 | |
| 2023-10-17 22:56:12,869 DEV : loss 0.16856464743614197 - f1-score (micro avg) 0.7249 | |
| 2023-10-17 22:56:12,904 saving best model | |
| 2023-10-17 22:56:13,312 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:56:20,687 epoch 2 - iter 147/1476 - loss 0.14697420 - time (sec): 7.37 - samples/sec: 2507.53 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 22:56:27,733 epoch 2 - iter 294/1476 - loss 0.14960317 - time (sec): 14.42 - samples/sec: 2392.91 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 22:56:35,139 epoch 2 - iter 441/1476 - loss 0.14816186 - time (sec): 21.83 - samples/sec: 2317.35 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 22:56:42,420 epoch 2 - iter 588/1476 - loss 0.14307432 - time (sec): 29.11 - samples/sec: 2304.79 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 22:56:49,369 epoch 2 - iter 735/1476 - loss 0.14205158 - time (sec): 36.06 - samples/sec: 2263.30 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 22:56:56,737 epoch 2 - iter 882/1476 - loss 0.13867117 - time (sec): 43.42 - samples/sec: 2252.93 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 22:57:03,747 epoch 2 - iter 1029/1476 - loss 0.13860745 - time (sec): 50.43 - samples/sec: 2246.86 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 22:57:10,914 epoch 2 - iter 1176/1476 - loss 0.13663928 - time (sec): 57.60 - samples/sec: 2245.71 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 22:57:18,134 epoch 2 - iter 1323/1476 - loss 0.13771676 - time (sec): 64.82 - samples/sec: 2253.18 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 22:57:25,405 epoch 2 - iter 1470/1476 - loss 0.13622049 - time (sec): 72.09 - samples/sec: 2277.56 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 22:57:25,970 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:57:25,970 EPOCH 2 done: loss 0.1350 - lr: 0.000044 | |
| 2023-10-17 22:57:37,562 DEV : loss 0.1357511579990387 - f1-score (micro avg) 0.806 | |
| 2023-10-17 22:57:37,592 saving best model | |
| 2023-10-17 22:57:38,178 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:57:45,993 epoch 3 - iter 147/1476 - loss 0.07789933 - time (sec): 7.81 - samples/sec: 2380.81 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 22:57:53,060 epoch 3 - iter 294/1476 - loss 0.08181281 - time (sec): 14.88 - samples/sec: 2342.38 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 22:57:59,874 epoch 3 - iter 441/1476 - loss 0.08737757 - time (sec): 21.69 - samples/sec: 2288.54 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 22:58:06,546 epoch 3 - iter 588/1476 - loss 0.09070383 - time (sec): 28.37 - samples/sec: 2322.34 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 22:58:13,353 epoch 3 - iter 735/1476 - loss 0.08945432 - time (sec): 35.17 - samples/sec: 2311.59 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 22:58:20,726 epoch 3 - iter 882/1476 - loss 0.08694692 - time (sec): 42.55 - samples/sec: 2319.25 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 22:58:28,090 epoch 3 - iter 1029/1476 - loss 0.09008265 - time (sec): 49.91 - samples/sec: 2332.14 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 22:58:34,993 epoch 3 - iter 1176/1476 - loss 0.08900752 - time (sec): 56.81 - samples/sec: 2316.86 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 22:58:42,197 epoch 3 - iter 1323/1476 - loss 0.08727828 - time (sec): 64.02 - samples/sec: 2310.81 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 22:58:49,967 epoch 3 - iter 1470/1476 - loss 0.08534777 - time (sec): 71.79 - samples/sec: 2309.57 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 22:58:50,257 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:58:50,257 EPOCH 3 done: loss 0.0851 - lr: 0.000039 | |
| 2023-10-17 22:59:01,890 DEV : loss 0.13451558351516724 - f1-score (micro avg) 0.8094 | |
| 2023-10-17 22:59:01,925 saving best model | |
| 2023-10-17 22:59:02,473 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 22:59:09,707 epoch 4 - iter 147/1476 - loss 0.05105380 - time (sec): 7.22 - samples/sec: 2150.03 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 22:59:16,983 epoch 4 - iter 294/1476 - loss 0.04798395 - time (sec): 14.49 - samples/sec: 2164.31 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 22:59:24,121 epoch 4 - iter 441/1476 - loss 0.04694055 - time (sec): 21.63 - samples/sec: 2191.91 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 22:59:31,928 epoch 4 - iter 588/1476 - loss 0.05761020 - time (sec): 29.44 - samples/sec: 2271.58 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 22:59:39,147 epoch 4 - iter 735/1476 - loss 0.06008736 - time (sec): 36.66 - samples/sec: 2287.63 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 22:59:46,000 epoch 4 - iter 882/1476 - loss 0.06216032 - time (sec): 43.51 - samples/sec: 2274.28 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 22:59:53,352 epoch 4 - iter 1029/1476 - loss 0.06083285 - time (sec): 50.86 - samples/sec: 2265.37 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 23:00:00,510 epoch 4 - iter 1176/1476 - loss 0.05979852 - time (sec): 58.02 - samples/sec: 2260.82 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 23:00:07,666 epoch 4 - iter 1323/1476 - loss 0.06094034 - time (sec): 65.17 - samples/sec: 2258.56 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 23:00:15,525 epoch 4 - iter 1470/1476 - loss 0.06439233 - time (sec): 73.03 - samples/sec: 2271.09 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 23:00:15,786 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:00:15,787 EPOCH 4 done: loss 0.0647 - lr: 0.000033 | |
| 2023-10-17 23:00:27,492 DEV : loss 0.17153489589691162 - f1-score (micro avg) 0.8151 | |
| 2023-10-17 23:00:27,527 saving best model | |
| 2023-10-17 23:00:28,067 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:00:35,275 epoch 5 - iter 147/1476 - loss 0.02693424 - time (sec): 7.21 - samples/sec: 2208.32 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 23:00:43,160 epoch 5 - iter 294/1476 - loss 0.04437274 - time (sec): 15.09 - samples/sec: 2088.84 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 23:00:51,347 epoch 5 - iter 441/1476 - loss 0.04231060 - time (sec): 23.28 - samples/sec: 2074.10 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 23:00:58,899 epoch 5 - iter 588/1476 - loss 0.03964767 - time (sec): 30.83 - samples/sec: 2130.13 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 23:01:06,222 epoch 5 - iter 735/1476 - loss 0.04489672 - time (sec): 38.15 - samples/sec: 2171.31 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 23:01:13,502 epoch 5 - iter 882/1476 - loss 0.04379355 - time (sec): 45.43 - samples/sec: 2190.95 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 23:01:20,560 epoch 5 - iter 1029/1476 - loss 0.04424447 - time (sec): 52.49 - samples/sec: 2199.56 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:01:28,426 epoch 5 - iter 1176/1476 - loss 0.04709511 - time (sec): 60.36 - samples/sec: 2242.67 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 23:01:35,493 epoch 5 - iter 1323/1476 - loss 0.04587284 - time (sec): 67.42 - samples/sec: 2233.46 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:01:42,740 epoch 5 - iter 1470/1476 - loss 0.04539351 - time (sec): 74.67 - samples/sec: 2221.97 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 23:01:43,007 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:01:43,007 EPOCH 5 done: loss 0.0453 - lr: 0.000028 | |
| 2023-10-17 23:01:55,382 DEV : loss 0.16670416295528412 - f1-score (micro avg) 0.8243 | |
| 2023-10-17 23:01:55,429 saving best model | |
| 2023-10-17 23:01:55,891 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:02:03,242 epoch 6 - iter 147/1476 - loss 0.04188951 - time (sec): 7.35 - samples/sec: 2208.61 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:02:10,517 epoch 6 - iter 294/1476 - loss 0.03674983 - time (sec): 14.62 - samples/sec: 2221.86 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 23:02:18,067 epoch 6 - iter 441/1476 - loss 0.03424510 - time (sec): 22.17 - samples/sec: 2259.51 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:02:25,103 epoch 6 - iter 588/1476 - loss 0.03260930 - time (sec): 29.21 - samples/sec: 2247.83 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 23:02:32,401 epoch 6 - iter 735/1476 - loss 0.03228254 - time (sec): 36.51 - samples/sec: 2229.88 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 23:02:40,187 epoch 6 - iter 882/1476 - loss 0.03612267 - time (sec): 44.29 - samples/sec: 2240.29 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:02:47,290 epoch 6 - iter 1029/1476 - loss 0.03358404 - time (sec): 51.40 - samples/sec: 2230.21 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 23:02:54,497 epoch 6 - iter 1176/1476 - loss 0.03290098 - time (sec): 58.60 - samples/sec: 2243.05 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:03:02,407 epoch 6 - iter 1323/1476 - loss 0.03435333 - time (sec): 66.51 - samples/sec: 2251.49 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 23:03:09,382 epoch 6 - iter 1470/1476 - loss 0.03301237 - time (sec): 73.49 - samples/sec: 2256.53 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:03:09,649 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:03:09,649 EPOCH 6 done: loss 0.0329 - lr: 0.000022 | |
| 2023-10-17 23:03:21,566 DEV : loss 0.19735385477542877 - f1-score (micro avg) 0.8315 | |
| 2023-10-17 23:03:21,602 saving best model | |
| 2023-10-17 23:03:22,194 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:03:30,571 epoch 7 - iter 147/1476 - loss 0.02345715 - time (sec): 8.37 - samples/sec: 2270.00 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 23:03:38,053 epoch 7 - iter 294/1476 - loss 0.02262037 - time (sec): 15.86 - samples/sec: 2241.11 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:03:45,134 epoch 7 - iter 441/1476 - loss 0.02093600 - time (sec): 22.94 - samples/sec: 2236.74 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 23:03:53,381 epoch 7 - iter 588/1476 - loss 0.01790932 - time (sec): 31.18 - samples/sec: 2197.93 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 23:04:01,112 epoch 7 - iter 735/1476 - loss 0.01989970 - time (sec): 38.92 - samples/sec: 2148.51 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:04:08,498 epoch 7 - iter 882/1476 - loss 0.02070017 - time (sec): 46.30 - samples/sec: 2160.07 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 23:04:16,020 epoch 7 - iter 1029/1476 - loss 0.02122502 - time (sec): 53.82 - samples/sec: 2166.98 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:04:23,338 epoch 7 - iter 1176/1476 - loss 0.02137335 - time (sec): 61.14 - samples/sec: 2174.04 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 23:04:30,882 epoch 7 - iter 1323/1476 - loss 0.02158579 - time (sec): 68.69 - samples/sec: 2174.28 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:04:38,059 epoch 7 - iter 1470/1476 - loss 0.02065480 - time (sec): 75.86 - samples/sec: 2184.32 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 23:04:38,347 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:04:38,347 EPOCH 7 done: loss 0.0206 - lr: 0.000017 | |
| 2023-10-17 23:04:50,314 DEV : loss 0.21340471506118774 - f1-score (micro avg) 0.839 | |
| 2023-10-17 23:04:50,348 saving best model | |
| 2023-10-17 23:04:50,888 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:04:58,545 epoch 8 - iter 147/1476 - loss 0.01817788 - time (sec): 7.64 - samples/sec: 2509.33 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:05:06,162 epoch 8 - iter 294/1476 - loss 0.01429890 - time (sec): 15.26 - samples/sec: 2279.74 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 23:05:13,685 epoch 8 - iter 441/1476 - loss 0.01404232 - time (sec): 22.78 - samples/sec: 2318.88 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 23:05:21,215 epoch 8 - iter 588/1476 - loss 0.01341993 - time (sec): 30.31 - samples/sec: 2310.71 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:05:28,651 epoch 8 - iter 735/1476 - loss 0.01234219 - time (sec): 37.75 - samples/sec: 2281.94 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 23:05:36,056 epoch 8 - iter 882/1476 - loss 0.01255617 - time (sec): 45.15 - samples/sec: 2248.13 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:05:43,528 epoch 8 - iter 1029/1476 - loss 0.01279467 - time (sec): 52.63 - samples/sec: 2236.05 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 23:05:50,830 epoch 8 - iter 1176/1476 - loss 0.01363296 - time (sec): 59.93 - samples/sec: 2241.20 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:05:58,137 epoch 8 - iter 1323/1476 - loss 0.01384585 - time (sec): 67.24 - samples/sec: 2236.28 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 23:06:05,073 epoch 8 - iter 1470/1476 - loss 0.01355309 - time (sec): 74.17 - samples/sec: 2235.95 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:06:05,338 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:06:05,338 EPOCH 8 done: loss 0.0135 - lr: 0.000011 | |
| 2023-10-17 23:06:16,942 DEV : loss 0.21790701150894165 - f1-score (micro avg) 0.8359 | |
| 2023-10-17 23:06:16,973 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:06:23,866 epoch 9 - iter 147/1476 - loss 0.00401227 - time (sec): 6.89 - samples/sec: 2184.20 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 23:06:31,070 epoch 9 - iter 294/1476 - loss 0.00427172 - time (sec): 14.10 - samples/sec: 2209.47 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 23:06:38,966 epoch 9 - iter 441/1476 - loss 0.00795735 - time (sec): 21.99 - samples/sec: 2360.74 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:06:45,704 epoch 9 - iter 588/1476 - loss 0.00775844 - time (sec): 28.73 - samples/sec: 2314.97 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 23:06:52,721 epoch 9 - iter 735/1476 - loss 0.00709240 - time (sec): 35.75 - samples/sec: 2300.82 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:07:00,353 epoch 9 - iter 882/1476 - loss 0.00746520 - time (sec): 43.38 - samples/sec: 2317.72 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 23:07:07,391 epoch 9 - iter 1029/1476 - loss 0.00734797 - time (sec): 50.42 - samples/sec: 2292.46 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:07:14,735 epoch 9 - iter 1176/1476 - loss 0.00905542 - time (sec): 57.76 - samples/sec: 2298.94 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 23:07:21,931 epoch 9 - iter 1323/1476 - loss 0.00876966 - time (sec): 64.96 - samples/sec: 2303.55 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:07:28,917 epoch 9 - iter 1470/1476 - loss 0.00840203 - time (sec): 71.94 - samples/sec: 2301.70 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 23:07:29,220 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:07:29,220 EPOCH 9 done: loss 0.0084 - lr: 0.000006 | |
| 2023-10-17 23:07:40,884 DEV : loss 0.22359006106853485 - f1-score (micro avg) 0.8372 | |
| 2023-10-17 23:07:40,923 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:07:47,911 epoch 10 - iter 147/1476 - loss 0.00147687 - time (sec): 6.99 - samples/sec: 2119.63 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 23:07:55,405 epoch 10 - iter 294/1476 - loss 0.00457169 - time (sec): 14.48 - samples/sec: 2132.53 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:08:02,488 epoch 10 - iter 441/1476 - loss 0.00420220 - time (sec): 21.56 - samples/sec: 2167.19 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 23:08:10,041 epoch 10 - iter 588/1476 - loss 0.00602254 - time (sec): 29.12 - samples/sec: 2263.71 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:08:17,049 epoch 10 - iter 735/1476 - loss 0.00562953 - time (sec): 36.12 - samples/sec: 2252.28 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 23:08:24,354 epoch 10 - iter 882/1476 - loss 0.00721583 - time (sec): 43.43 - samples/sec: 2268.84 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:08:31,340 epoch 10 - iter 1029/1476 - loss 0.00711626 - time (sec): 50.41 - samples/sec: 2272.54 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 23:08:38,403 epoch 10 - iter 1176/1476 - loss 0.00666628 - time (sec): 57.48 - samples/sec: 2277.09 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:08:45,938 epoch 10 - iter 1323/1476 - loss 0.00644189 - time (sec): 65.01 - samples/sec: 2299.98 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 23:08:53,126 epoch 10 - iter 1470/1476 - loss 0.00604544 - time (sec): 72.20 - samples/sec: 2291.20 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 23:08:53,437 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:08:53,437 EPOCH 10 done: loss 0.0060 - lr: 0.000000 | |
| 2023-10-17 23:09:05,404 DEV : loss 0.2264208048582077 - f1-score (micro avg) 0.838 | |
| 2023-10-17 23:09:05,856 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 23:09:05,857 Loading model from best epoch ... | |
| 2023-10-17 23:09:07,337 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-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod | |
| 2023-10-17 23:09:13,652 | |
| Results: | |
| - F-score (micro) 0.8038 | |
| - F-score (macro) 0.702 | |
| - Accuracy 0.6918 | |
| By class: | |
| precision recall f1-score support | |
| loc 0.8422 0.8834 0.8623 858 | |
| pers 0.7978 0.8007 0.7993 537 | |
| org 0.6016 0.5833 0.5923 132 | |
| prod 0.6508 0.6721 0.6613 61 | |
| time 0.5373 0.6667 0.5950 54 | |
| micro avg 0.7908 0.8173 0.8038 1642 | |
| macro avg 0.6859 0.7213 0.7020 1642 | |
| weighted avg 0.7912 0.8173 0.8037 1642 | |
| 2023-10-17 23:09:13,652 ---------------------------------------------------------------------------------------------------- | |