|
2023-10-16 18:30:41,019 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,020 Model: "SequenceTagger( |
|
(embeddings): TransformerWordEmbeddings( |
|
(model): BertModel( |
|
(embeddings): BertEmbeddings( |
|
(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): BertEncoder( |
|
(layer): ModuleList( |
|
(0-11): 12 x BertLayer( |
|
(attention): BertAttention( |
|
(self): BertSelfAttention( |
|
(query): Linear(in_features=768, out_features=768, bias=True) |
|
(key): Linear(in_features=768, out_features=768, bias=True) |
|
(value): Linear(in_features=768, out_features=768, bias=True) |
|
(dropout): Dropout(p=0.1, inplace=False) |
|
) |
|
(output): BertSelfOutput( |
|
(dense): Linear(in_features=768, out_features=768, bias=True) |
|
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) |
|
(dropout): Dropout(p=0.1, inplace=False) |
|
) |
|
) |
|
(intermediate): BertIntermediate( |
|
(dense): Linear(in_features=768, out_features=3072, bias=True) |
|
(intermediate_act_fn): GELUActivation() |
|
) |
|
(output): BertOutput( |
|
(dense): Linear(in_features=3072, out_features=768, bias=True) |
|
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True) |
|
(dropout): Dropout(p=0.1, inplace=False) |
|
) |
|
) |
|
) |
|
) |
|
(pooler): BertPooler( |
|
(dense): Linear(in_features=768, out_features=768, bias=True) |
|
(activation): Tanh() |
|
) |
|
) |
|
) |
|
(locked_dropout): LockedDropout(p=0.5) |
|
(linear): Linear(in_features=768, out_features=17, bias=True) |
|
(loss_function): CrossEntropyLoss() |
|
)" |
|
2023-10-16 18:30:41,020 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 MultiCorpus: 1166 train + 165 dev + 415 test sentences |
|
- NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Train: 1166 sentences |
|
2023-10-16 18:30:41,021 (train_with_dev=False, train_with_test=False) |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Training Params: |
|
2023-10-16 18:30:41,021 - learning_rate: "5e-05" |
|
2023-10-16 18:30:41,021 - mini_batch_size: "8" |
|
2023-10-16 18:30:41,021 - max_epochs: "10" |
|
2023-10-16 18:30:41,021 - shuffle: "True" |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Plugins: |
|
2023-10-16 18:30:41,021 - LinearScheduler | warmup_fraction: '0.1' |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Final evaluation on model from best epoch (best-model.pt) |
|
2023-10-16 18:30:41,021 - metric: "('micro avg', 'f1-score')" |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Computation: |
|
2023-10-16 18:30:41,021 - compute on device: cuda:0 |
|
2023-10-16 18:30:41,021 - embedding storage: none |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3" |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:41,021 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:42,212 epoch 1 - iter 14/146 - loss 2.90073598 - time (sec): 1.19 - samples/sec: 3343.07 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-16 18:30:43,382 epoch 1 - iter 28/146 - loss 2.61009746 - time (sec): 2.36 - samples/sec: 3081.79 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-16 18:30:44,973 epoch 1 - iter 42/146 - loss 1.82097782 - time (sec): 3.95 - samples/sec: 3099.36 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-16 18:30:46,384 epoch 1 - iter 56/146 - loss 1.53880713 - time (sec): 5.36 - samples/sec: 3070.13 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-16 18:30:47,588 epoch 1 - iter 70/146 - loss 1.36752879 - time (sec): 6.57 - samples/sec: 3031.29 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-16 18:30:48,854 epoch 1 - iter 84/146 - loss 1.29136891 - time (sec): 7.83 - samples/sec: 3019.42 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-16 18:30:50,774 epoch 1 - iter 98/146 - loss 1.13604122 - time (sec): 9.75 - samples/sec: 2962.85 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-16 18:30:52,273 epoch 1 - iter 112/146 - loss 1.03226442 - time (sec): 11.25 - samples/sec: 2963.99 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-16 18:30:53,897 epoch 1 - iter 126/146 - loss 0.93905554 - time (sec): 12.87 - samples/sec: 2956.53 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-16 18:30:55,301 epoch 1 - iter 140/146 - loss 0.86688508 - time (sec): 14.28 - samples/sec: 2969.28 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-16 18:30:55,965 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:55,965 EPOCH 1 done: loss 0.8394 - lr: 0.000048 |
|
2023-10-16 18:30:56,802 DEV : loss 0.21242927014827728 - f1-score (micro avg) 0.4782 |
|
2023-10-16 18:30:56,806 saving best model |
|
2023-10-16 18:30:57,201 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:30:58,684 epoch 2 - iter 14/146 - loss 0.24835850 - time (sec): 1.48 - samples/sec: 3237.36 - lr: 0.000050 - momentum: 0.000000 |
|
2023-10-16 18:31:00,328 epoch 2 - iter 28/146 - loss 0.24220847 - time (sec): 3.13 - samples/sec: 3043.72 - lr: 0.000049 - momentum: 0.000000 |
|
2023-10-16 18:31:01,559 epoch 2 - iter 42/146 - loss 0.23582406 - time (sec): 4.36 - samples/sec: 3034.13 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-16 18:31:02,973 epoch 2 - iter 56/146 - loss 0.22558961 - time (sec): 5.77 - samples/sec: 3001.51 - lr: 0.000048 - momentum: 0.000000 |
|
2023-10-16 18:31:04,305 epoch 2 - iter 70/146 - loss 0.21852986 - time (sec): 7.10 - samples/sec: 2954.56 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-16 18:31:05,999 epoch 2 - iter 84/146 - loss 0.23060054 - time (sec): 8.80 - samples/sec: 2949.37 - lr: 0.000047 - momentum: 0.000000 |
|
2023-10-16 18:31:07,551 epoch 2 - iter 98/146 - loss 0.21861190 - time (sec): 10.35 - samples/sec: 2956.61 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-16 18:31:08,738 epoch 2 - iter 112/146 - loss 0.21034426 - time (sec): 11.54 - samples/sec: 2964.15 - lr: 0.000046 - momentum: 0.000000 |
|
2023-10-16 18:31:10,020 epoch 2 - iter 126/146 - loss 0.20733549 - time (sec): 12.82 - samples/sec: 3002.18 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-16 18:31:11,627 epoch 2 - iter 140/146 - loss 0.20083590 - time (sec): 14.42 - samples/sec: 2992.18 - lr: 0.000045 - momentum: 0.000000 |
|
2023-10-16 18:31:12,084 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:12,084 EPOCH 2 done: loss 0.1995 - lr: 0.000045 |
|
2023-10-16 18:31:13,333 DEV : loss 0.14030463993549347 - f1-score (micro avg) 0.6021 |
|
2023-10-16 18:31:13,338 saving best model |
|
2023-10-16 18:31:13,834 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:16,105 epoch 3 - iter 14/146 - loss 0.17344869 - time (sec): 2.27 - samples/sec: 2286.20 - lr: 0.000044 - momentum: 0.000000 |
|
2023-10-16 18:31:17,368 epoch 3 - iter 28/146 - loss 0.17235774 - time (sec): 3.53 - samples/sec: 2646.16 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-16 18:31:18,893 epoch 3 - iter 42/146 - loss 0.15725543 - time (sec): 5.06 - samples/sec: 2792.00 - lr: 0.000043 - momentum: 0.000000 |
|
2023-10-16 18:31:20,349 epoch 3 - iter 56/146 - loss 0.14045524 - time (sec): 6.51 - samples/sec: 2875.19 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-16 18:31:21,940 epoch 3 - iter 70/146 - loss 0.12853378 - time (sec): 8.10 - samples/sec: 2875.20 - lr: 0.000042 - momentum: 0.000000 |
|
2023-10-16 18:31:23,206 epoch 3 - iter 84/146 - loss 0.12492428 - time (sec): 9.37 - samples/sec: 2887.87 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-16 18:31:24,635 epoch 3 - iter 98/146 - loss 0.12042291 - time (sec): 10.80 - samples/sec: 2886.03 - lr: 0.000041 - momentum: 0.000000 |
|
2023-10-16 18:31:25,852 epoch 3 - iter 112/146 - loss 0.11809638 - time (sec): 12.02 - samples/sec: 2910.19 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-16 18:31:27,358 epoch 3 - iter 126/146 - loss 0.11451646 - time (sec): 13.52 - samples/sec: 2905.95 - lr: 0.000040 - momentum: 0.000000 |
|
2023-10-16 18:31:28,584 epoch 3 - iter 140/146 - loss 0.11213648 - time (sec): 14.75 - samples/sec: 2916.08 - lr: 0.000039 - momentum: 0.000000 |
|
2023-10-16 18:31:29,040 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:29,040 EPOCH 3 done: loss 0.1114 - lr: 0.000039 |
|
2023-10-16 18:31:30,286 DEV : loss 0.1109694391489029 - f1-score (micro avg) 0.7066 |
|
2023-10-16 18:31:30,290 saving best model |
|
2023-10-16 18:31:30,792 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:32,089 epoch 4 - iter 14/146 - loss 0.06741993 - time (sec): 1.29 - samples/sec: 3016.26 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-16 18:31:33,391 epoch 4 - iter 28/146 - loss 0.07098649 - time (sec): 2.59 - samples/sec: 3070.96 - lr: 0.000038 - momentum: 0.000000 |
|
2023-10-16 18:31:34,729 epoch 4 - iter 42/146 - loss 0.08441382 - time (sec): 3.93 - samples/sec: 2968.10 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-16 18:31:36,286 epoch 4 - iter 56/146 - loss 0.07322493 - time (sec): 5.49 - samples/sec: 3004.06 - lr: 0.000037 - momentum: 0.000000 |
|
2023-10-16 18:31:37,528 epoch 4 - iter 70/146 - loss 0.07275131 - time (sec): 6.73 - samples/sec: 3010.99 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-16 18:31:38,881 epoch 4 - iter 84/146 - loss 0.07321996 - time (sec): 8.08 - samples/sec: 3010.69 - lr: 0.000036 - momentum: 0.000000 |
|
2023-10-16 18:31:40,259 epoch 4 - iter 98/146 - loss 0.07469954 - time (sec): 9.46 - samples/sec: 2992.62 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-16 18:31:41,811 epoch 4 - iter 112/146 - loss 0.07927519 - time (sec): 11.01 - samples/sec: 2989.44 - lr: 0.000035 - momentum: 0.000000 |
|
2023-10-16 18:31:43,127 epoch 4 - iter 126/146 - loss 0.07883891 - time (sec): 12.33 - samples/sec: 3010.88 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-16 18:31:44,886 epoch 4 - iter 140/146 - loss 0.07438665 - time (sec): 14.09 - samples/sec: 3030.54 - lr: 0.000034 - momentum: 0.000000 |
|
2023-10-16 18:31:45,421 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:45,421 EPOCH 4 done: loss 0.0733 - lr: 0.000034 |
|
2023-10-16 18:31:46,715 DEV : loss 0.10175595432519913 - f1-score (micro avg) 0.7583 |
|
2023-10-16 18:31:46,719 saving best model |
|
2023-10-16 18:31:47,234 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:31:48,760 epoch 5 - iter 14/146 - loss 0.07301139 - time (sec): 1.52 - samples/sec: 2767.38 - lr: 0.000033 - momentum: 0.000000 |
|
2023-10-16 18:31:50,262 epoch 5 - iter 28/146 - loss 0.05467576 - time (sec): 3.03 - samples/sec: 2770.85 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-16 18:31:51,886 epoch 5 - iter 42/146 - loss 0.04957886 - time (sec): 4.65 - samples/sec: 2753.58 - lr: 0.000032 - momentum: 0.000000 |
|
2023-10-16 18:31:53,160 epoch 5 - iter 56/146 - loss 0.04832781 - time (sec): 5.92 - samples/sec: 2788.29 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-16 18:31:54,659 epoch 5 - iter 70/146 - loss 0.05179242 - time (sec): 7.42 - samples/sec: 2802.73 - lr: 0.000031 - momentum: 0.000000 |
|
2023-10-16 18:31:56,055 epoch 5 - iter 84/146 - loss 0.05137597 - time (sec): 8.82 - samples/sec: 2825.33 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-16 18:31:57,544 epoch 5 - iter 98/146 - loss 0.05130334 - time (sec): 10.31 - samples/sec: 2829.89 - lr: 0.000030 - momentum: 0.000000 |
|
2023-10-16 18:31:58,970 epoch 5 - iter 112/146 - loss 0.05125951 - time (sec): 11.73 - samples/sec: 2890.23 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-16 18:32:00,395 epoch 5 - iter 126/146 - loss 0.05073713 - time (sec): 13.16 - samples/sec: 2904.17 - lr: 0.000029 - momentum: 0.000000 |
|
2023-10-16 18:32:01,716 epoch 5 - iter 140/146 - loss 0.04995567 - time (sec): 14.48 - samples/sec: 2913.06 - lr: 0.000028 - momentum: 0.000000 |
|
2023-10-16 18:32:02,426 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:02,426 EPOCH 5 done: loss 0.0486 - lr: 0.000028 |
|
2023-10-16 18:32:03,706 DEV : loss 0.11706184595823288 - f1-score (micro avg) 0.7046 |
|
2023-10-16 18:32:03,711 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:05,386 epoch 6 - iter 14/146 - loss 0.03465601 - time (sec): 1.67 - samples/sec: 2989.96 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-16 18:32:06,997 epoch 6 - iter 28/146 - loss 0.03333665 - time (sec): 3.28 - samples/sec: 2681.08 - lr: 0.000027 - momentum: 0.000000 |
|
2023-10-16 18:32:08,390 epoch 6 - iter 42/146 - loss 0.02993117 - time (sec): 4.68 - samples/sec: 2707.80 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-16 18:32:09,988 epoch 6 - iter 56/146 - loss 0.02776494 - time (sec): 6.28 - samples/sec: 2670.20 - lr: 0.000026 - momentum: 0.000000 |
|
2023-10-16 18:32:11,382 epoch 6 - iter 70/146 - loss 0.02718342 - time (sec): 7.67 - samples/sec: 2805.28 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-16 18:32:12,568 epoch 6 - iter 84/146 - loss 0.02843722 - time (sec): 8.86 - samples/sec: 2845.93 - lr: 0.000025 - momentum: 0.000000 |
|
2023-10-16 18:32:14,033 epoch 6 - iter 98/146 - loss 0.02633427 - time (sec): 10.32 - samples/sec: 2876.24 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-16 18:32:15,297 epoch 6 - iter 112/146 - loss 0.02898382 - time (sec): 11.58 - samples/sec: 2877.91 - lr: 0.000024 - momentum: 0.000000 |
|
2023-10-16 18:32:17,080 epoch 6 - iter 126/146 - loss 0.03285964 - time (sec): 13.37 - samples/sec: 2923.22 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-16 18:32:18,215 epoch 6 - iter 140/146 - loss 0.03401398 - time (sec): 14.50 - samples/sec: 2920.24 - lr: 0.000023 - momentum: 0.000000 |
|
2023-10-16 18:32:19,114 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:19,114 EPOCH 6 done: loss 0.0359 - lr: 0.000023 |
|
2023-10-16 18:32:20,340 DEV : loss 0.12150020152330399 - f1-score (micro avg) 0.7409 |
|
2023-10-16 18:32:20,344 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:21,970 epoch 7 - iter 14/146 - loss 0.03183064 - time (sec): 1.62 - samples/sec: 3256.19 - lr: 0.000022 - momentum: 0.000000 |
|
2023-10-16 18:32:23,197 epoch 7 - iter 28/146 - loss 0.02451667 - time (sec): 2.85 - samples/sec: 3220.52 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-16 18:32:24,790 epoch 7 - iter 42/146 - loss 0.02191339 - time (sec): 4.44 - samples/sec: 3101.58 - lr: 0.000021 - momentum: 0.000000 |
|
2023-10-16 18:32:26,257 epoch 7 - iter 56/146 - loss 0.02125095 - time (sec): 5.91 - samples/sec: 3003.69 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-16 18:32:27,775 epoch 7 - iter 70/146 - loss 0.02706119 - time (sec): 7.43 - samples/sec: 2964.28 - lr: 0.000020 - momentum: 0.000000 |
|
2023-10-16 18:32:29,322 epoch 7 - iter 84/146 - loss 0.02505213 - time (sec): 8.98 - samples/sec: 2957.87 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-16 18:32:30,488 epoch 7 - iter 98/146 - loss 0.02643594 - time (sec): 10.14 - samples/sec: 2975.44 - lr: 0.000019 - momentum: 0.000000 |
|
2023-10-16 18:32:31,886 epoch 7 - iter 112/146 - loss 0.02500584 - time (sec): 11.54 - samples/sec: 2962.65 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-16 18:32:33,268 epoch 7 - iter 126/146 - loss 0.02596879 - time (sec): 12.92 - samples/sec: 3004.97 - lr: 0.000018 - momentum: 0.000000 |
|
2023-10-16 18:32:34,527 epoch 7 - iter 140/146 - loss 0.02553034 - time (sec): 14.18 - samples/sec: 3010.56 - lr: 0.000017 - momentum: 0.000000 |
|
2023-10-16 18:32:35,244 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:35,244 EPOCH 7 done: loss 0.0251 - lr: 0.000017 |
|
2023-10-16 18:32:36,485 DEV : loss 0.11602330207824707 - f1-score (micro avg) 0.7699 |
|
2023-10-16 18:32:36,489 saving best model |
|
2023-10-16 18:32:37,056 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:38,367 epoch 8 - iter 14/146 - loss 0.03129626 - time (sec): 1.31 - samples/sec: 3195.87 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-16 18:32:39,770 epoch 8 - iter 28/146 - loss 0.02105207 - time (sec): 2.71 - samples/sec: 3170.88 - lr: 0.000016 - momentum: 0.000000 |
|
2023-10-16 18:32:41,336 epoch 8 - iter 42/146 - loss 0.02054404 - time (sec): 4.28 - samples/sec: 2981.94 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-16 18:32:42,828 epoch 8 - iter 56/146 - loss 0.01985796 - time (sec): 5.77 - samples/sec: 2902.09 - lr: 0.000015 - momentum: 0.000000 |
|
2023-10-16 18:32:44,319 epoch 8 - iter 70/146 - loss 0.02096278 - time (sec): 7.26 - samples/sec: 2925.26 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-16 18:32:45,534 epoch 8 - iter 84/146 - loss 0.02060282 - time (sec): 8.48 - samples/sec: 2958.97 - lr: 0.000014 - momentum: 0.000000 |
|
2023-10-16 18:32:47,293 epoch 8 - iter 98/146 - loss 0.02043961 - time (sec): 10.23 - samples/sec: 2920.58 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-16 18:32:48,752 epoch 8 - iter 112/146 - loss 0.01967954 - time (sec): 11.69 - samples/sec: 2945.27 - lr: 0.000013 - momentum: 0.000000 |
|
2023-10-16 18:32:49,995 epoch 8 - iter 126/146 - loss 0.01978582 - time (sec): 12.94 - samples/sec: 2944.65 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-16 18:32:51,387 epoch 8 - iter 140/146 - loss 0.02004748 - time (sec): 14.33 - samples/sec: 2972.78 - lr: 0.000012 - momentum: 0.000000 |
|
2023-10-16 18:32:52,022 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:52,022 EPOCH 8 done: loss 0.0199 - lr: 0.000012 |
|
2023-10-16 18:32:53,288 DEV : loss 0.13683120906352997 - f1-score (micro avg) 0.778 |
|
2023-10-16 18:32:53,292 saving best model |
|
2023-10-16 18:32:53,797 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:32:55,044 epoch 9 - iter 14/146 - loss 0.01036090 - time (sec): 1.24 - samples/sec: 3399.56 - lr: 0.000011 - momentum: 0.000000 |
|
2023-10-16 18:32:56,924 epoch 9 - iter 28/146 - loss 0.01412081 - time (sec): 3.12 - samples/sec: 2766.19 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-16 18:32:58,399 epoch 9 - iter 42/146 - loss 0.01439111 - time (sec): 4.59 - samples/sec: 2804.03 - lr: 0.000010 - momentum: 0.000000 |
|
2023-10-16 18:32:59,870 epoch 9 - iter 56/146 - loss 0.01249084 - time (sec): 6.06 - samples/sec: 2911.17 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-16 18:33:01,541 epoch 9 - iter 70/146 - loss 0.01166056 - time (sec): 7.74 - samples/sec: 2893.95 - lr: 0.000009 - momentum: 0.000000 |
|
2023-10-16 18:33:03,013 epoch 9 - iter 84/146 - loss 0.01200218 - time (sec): 9.21 - samples/sec: 2897.96 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-16 18:33:04,344 epoch 9 - iter 98/146 - loss 0.01474939 - time (sec): 10.54 - samples/sec: 2925.67 - lr: 0.000008 - momentum: 0.000000 |
|
2023-10-16 18:33:05,766 epoch 9 - iter 112/146 - loss 0.01486486 - time (sec): 11.96 - samples/sec: 2933.90 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-16 18:33:07,032 epoch 9 - iter 126/146 - loss 0.01464348 - time (sec): 13.23 - samples/sec: 2938.00 - lr: 0.000007 - momentum: 0.000000 |
|
2023-10-16 18:33:08,471 epoch 9 - iter 140/146 - loss 0.01441580 - time (sec): 14.67 - samples/sec: 2921.37 - lr: 0.000006 - momentum: 0.000000 |
|
2023-10-16 18:33:08,944 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:33:08,944 EPOCH 9 done: loss 0.0142 - lr: 0.000006 |
|
2023-10-16 18:33:10,208 DEV : loss 0.14194026589393616 - f1-score (micro avg) 0.7773 |
|
2023-10-16 18:33:10,212 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:33:11,637 epoch 10 - iter 14/146 - loss 0.01016943 - time (sec): 1.42 - samples/sec: 3092.25 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-16 18:33:13,234 epoch 10 - iter 28/146 - loss 0.01164300 - time (sec): 3.02 - samples/sec: 3152.92 - lr: 0.000005 - momentum: 0.000000 |
|
2023-10-16 18:33:14,590 epoch 10 - iter 42/146 - loss 0.01529058 - time (sec): 4.38 - samples/sec: 3063.14 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-16 18:33:15,902 epoch 10 - iter 56/146 - loss 0.01388744 - time (sec): 5.69 - samples/sec: 3098.56 - lr: 0.000004 - momentum: 0.000000 |
|
2023-10-16 18:33:17,357 epoch 10 - iter 70/146 - loss 0.01378762 - time (sec): 7.14 - samples/sec: 3016.66 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-16 18:33:19,018 epoch 10 - iter 84/146 - loss 0.01335628 - time (sec): 8.80 - samples/sec: 3048.03 - lr: 0.000003 - momentum: 0.000000 |
|
2023-10-16 18:33:20,320 epoch 10 - iter 98/146 - loss 0.01221901 - time (sec): 10.11 - samples/sec: 3063.87 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-16 18:33:21,629 epoch 10 - iter 112/146 - loss 0.01168636 - time (sec): 11.42 - samples/sec: 3029.87 - lr: 0.000002 - momentum: 0.000000 |
|
2023-10-16 18:33:23,148 epoch 10 - iter 126/146 - loss 0.01059421 - time (sec): 12.94 - samples/sec: 2999.30 - lr: 0.000001 - momentum: 0.000000 |
|
2023-10-16 18:33:24,515 epoch 10 - iter 140/146 - loss 0.01057943 - time (sec): 14.30 - samples/sec: 3013.35 - lr: 0.000000 - momentum: 0.000000 |
|
2023-10-16 18:33:24,998 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:33:24,998 EPOCH 10 done: loss 0.0108 - lr: 0.000000 |
|
2023-10-16 18:33:26,284 DEV : loss 0.14382334053516388 - f1-score (micro avg) 0.7676 |
|
2023-10-16 18:33:26,696 ---------------------------------------------------------------------------------------------------- |
|
2023-10-16 18:33:26,697 Loading model from best epoch ... |
|
2023-10-16 18:33:28,341 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 |
|
2023-10-16 18:33:30,789 |
|
Results: |
|
- F-score (micro) 0.743 |
|
- F-score (macro) 0.6497 |
|
- Accuracy 0.6158 |
|
|
|
By class: |
|
precision recall f1-score support |
|
|
|
PER 0.7849 0.8391 0.8111 348 |
|
LOC 0.6614 0.8084 0.7276 261 |
|
ORG 0.4194 0.5000 0.4561 52 |
|
HumanProd 0.5161 0.7273 0.6038 22 |
|
|
|
micro avg 0.6952 0.7980 0.7430 683 |
|
macro avg 0.5955 0.7187 0.6497 683 |
|
weighted avg 0.7013 0.7980 0.7455 683 |
|
|
|
2023-10-16 18:33:30,789 ---------------------------------------------------------------------------------------------------- |
|
|