| 2023-10-18 16:08:51,954 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,954 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=25, bias=True) |
| (loss_function): CrossEntropyLoss() |
| )" |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 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 |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Train: 1214 sentences |
| 2023-10-18 16:08:51,955 (train_with_dev=False, train_with_test=False) |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Training Params: |
| 2023-10-18 16:08:51,955 - learning_rate: "3e-05" |
| 2023-10-18 16:08:51,955 - mini_batch_size: "4" |
| 2023-10-18 16:08:51,955 - max_epochs: "10" |
| 2023-10-18 16:08:51,955 - shuffle: "True" |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Plugins: |
| 2023-10-18 16:08:51,955 - TensorboardLogger |
| 2023-10-18 16:08:51,955 - LinearScheduler | warmup_fraction: '0.1' |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Final evaluation on model from best epoch (best-model.pt) |
| 2023-10-18 16:08:51,955 - metric: "('micro avg', 'f1-score')" |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Computation: |
| 2023-10-18 16:08:51,955 - compute on device: cuda:0 |
| 2023-10-18 16:08:51,955 - embedding storage: none |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 Model training base path: "hmbench-ajmc/en-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4" |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,955 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:51,956 Logging anything other than scalars to TensorBoard is currently not supported. |
| 2023-10-18 16:08:52,485 epoch 1 - iter 30/304 - loss 4.01153679 - time (sec): 0.53 - samples/sec: 6294.54 - lr: 0.000003 - momentum: 0.000000 |
| 2023-10-18 16:08:52,956 epoch 1 - iter 60/304 - loss 3.98996454 - time (sec): 1.00 - samples/sec: 6549.21 - lr: 0.000006 - momentum: 0.000000 |
| 2023-10-18 16:08:53,410 epoch 1 - iter 90/304 - loss 3.87728027 - time (sec): 1.45 - samples/sec: 6834.08 - lr: 0.000009 - momentum: 0.000000 |
| 2023-10-18 16:08:53,861 epoch 1 - iter 120/304 - loss 3.75037405 - time (sec): 1.91 - samples/sec: 6763.39 - lr: 0.000012 - momentum: 0.000000 |
| 2023-10-18 16:08:54,323 epoch 1 - iter 150/304 - loss 3.55728522 - time (sec): 2.37 - samples/sec: 6763.47 - lr: 0.000015 - momentum: 0.000000 |
| 2023-10-18 16:08:54,774 epoch 1 - iter 180/304 - loss 3.33656985 - time (sec): 2.82 - samples/sec: 6767.60 - lr: 0.000018 - momentum: 0.000000 |
| 2023-10-18 16:08:55,211 epoch 1 - iter 210/304 - loss 3.13709034 - time (sec): 3.26 - samples/sec: 6778.45 - lr: 0.000021 - momentum: 0.000000 |
| 2023-10-18 16:08:55,662 epoch 1 - iter 240/304 - loss 2.92540655 - time (sec): 3.71 - samples/sec: 6702.39 - lr: 0.000024 - momentum: 0.000000 |
| 2023-10-18 16:08:56,132 epoch 1 - iter 270/304 - loss 2.70761557 - time (sec): 4.18 - samples/sec: 6709.90 - lr: 0.000027 - momentum: 0.000000 |
| 2023-10-18 16:08:56,577 epoch 1 - iter 300/304 - loss 2.55625887 - time (sec): 4.62 - samples/sec: 6645.97 - lr: 0.000030 - momentum: 0.000000 |
| 2023-10-18 16:08:56,633 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:56,633 EPOCH 1 done: loss 2.5423 - lr: 0.000030 |
| 2023-10-18 16:08:57,089 DEV : loss 0.7825055122375488 - f1-score (micro avg) 0.0 |
| 2023-10-18 16:08:57,095 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:08:57,571 epoch 2 - iter 30/304 - loss 0.78534276 - time (sec): 0.48 - samples/sec: 6519.05 - lr: 0.000030 - momentum: 0.000000 |
| 2023-10-18 16:08:58,068 epoch 2 - iter 60/304 - loss 0.71401044 - time (sec): 0.97 - samples/sec: 6571.87 - lr: 0.000029 - momentum: 0.000000 |
| 2023-10-18 16:08:58,558 epoch 2 - iter 90/304 - loss 0.74732198 - time (sec): 1.46 - samples/sec: 6371.00 - lr: 0.000029 - momentum: 0.000000 |
| 2023-10-18 16:08:59,011 epoch 2 - iter 120/304 - loss 0.75838159 - time (sec): 1.92 - samples/sec: 6481.39 - lr: 0.000029 - momentum: 0.000000 |
| 2023-10-18 16:08:59,455 epoch 2 - iter 150/304 - loss 0.72013262 - time (sec): 2.36 - samples/sec: 6487.21 - lr: 0.000028 - momentum: 0.000000 |
| 2023-10-18 16:08:59,910 epoch 2 - iter 180/304 - loss 0.72897860 - time (sec): 2.82 - samples/sec: 6501.00 - lr: 0.000028 - momentum: 0.000000 |
| 2023-10-18 16:09:00,371 epoch 2 - iter 210/304 - loss 0.72831220 - time (sec): 3.28 - samples/sec: 6595.42 - lr: 0.000028 - momentum: 0.000000 |
| 2023-10-18 16:09:00,828 epoch 2 - iter 240/304 - loss 0.72645015 - time (sec): 3.73 - samples/sec: 6627.43 - lr: 0.000027 - momentum: 0.000000 |
| 2023-10-18 16:09:01,277 epoch 2 - iter 270/304 - loss 0.71491415 - time (sec): 4.18 - samples/sec: 6607.90 - lr: 0.000027 - momentum: 0.000000 |
| 2023-10-18 16:09:01,724 epoch 2 - iter 300/304 - loss 0.71709671 - time (sec): 4.63 - samples/sec: 6632.50 - lr: 0.000027 - momentum: 0.000000 |
| 2023-10-18 16:09:01,782 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:01,782 EPOCH 2 done: loss 0.7157 - lr: 0.000027 |
| 2023-10-18 16:09:02,280 DEV : loss 0.5436066389083862 - f1-score (micro avg) 0.0187 |
| 2023-10-18 16:09:02,286 saving best model |
| 2023-10-18 16:09:02,319 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:02,758 epoch 3 - iter 30/304 - loss 0.57899992 - time (sec): 0.44 - samples/sec: 6672.32 - lr: 0.000026 - momentum: 0.000000 |
| 2023-10-18 16:09:03,211 epoch 3 - iter 60/304 - loss 0.60466115 - time (sec): 0.89 - samples/sec: 6855.50 - lr: 0.000026 - momentum: 0.000000 |
| 2023-10-18 16:09:03,657 epoch 3 - iter 90/304 - loss 0.60185213 - time (sec): 1.34 - samples/sec: 6851.15 - lr: 0.000026 - momentum: 0.000000 |
| 2023-10-18 16:09:04,110 epoch 3 - iter 120/304 - loss 0.58787198 - time (sec): 1.79 - samples/sec: 7029.09 - lr: 0.000025 - momentum: 0.000000 |
| 2023-10-18 16:09:04,557 epoch 3 - iter 150/304 - loss 0.55695365 - time (sec): 2.24 - samples/sec: 6902.93 - lr: 0.000025 - momentum: 0.000000 |
| 2023-10-18 16:09:04,999 epoch 3 - iter 180/304 - loss 0.54596510 - time (sec): 2.68 - samples/sec: 6782.83 - lr: 0.000025 - momentum: 0.000000 |
| 2023-10-18 16:09:05,447 epoch 3 - iter 210/304 - loss 0.53557908 - time (sec): 3.13 - samples/sec: 6736.88 - lr: 0.000024 - momentum: 0.000000 |
| 2023-10-18 16:09:05,911 epoch 3 - iter 240/304 - loss 0.53512397 - time (sec): 3.59 - samples/sec: 6750.04 - lr: 0.000024 - momentum: 0.000000 |
| 2023-10-18 16:09:06,366 epoch 3 - iter 270/304 - loss 0.53704901 - time (sec): 4.05 - samples/sec: 6797.90 - lr: 0.000024 - momentum: 0.000000 |
| 2023-10-18 16:09:06,833 epoch 3 - iter 300/304 - loss 0.52828713 - time (sec): 4.51 - samples/sec: 6786.40 - lr: 0.000023 - momentum: 0.000000 |
| 2023-10-18 16:09:06,889 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:06,889 EPOCH 3 done: loss 0.5261 - lr: 0.000023 |
| 2023-10-18 16:09:07,386 DEV : loss 0.40468713641166687 - f1-score (micro avg) 0.2832 |
| 2023-10-18 16:09:07,391 saving best model |
| 2023-10-18 16:09:07,423 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:07,871 epoch 4 - iter 30/304 - loss 0.50840551 - time (sec): 0.45 - samples/sec: 6343.82 - lr: 0.000023 - momentum: 0.000000 |
| 2023-10-18 16:09:08,320 epoch 4 - iter 60/304 - loss 0.52475072 - time (sec): 0.90 - samples/sec: 6775.18 - lr: 0.000023 - momentum: 0.000000 |
| 2023-10-18 16:09:08,770 epoch 4 - iter 90/304 - loss 0.50741565 - time (sec): 1.35 - samples/sec: 6806.24 - lr: 0.000022 - momentum: 0.000000 |
| 2023-10-18 16:09:09,231 epoch 4 - iter 120/304 - loss 0.48651339 - time (sec): 1.81 - samples/sec: 6785.06 - lr: 0.000022 - momentum: 0.000000 |
| 2023-10-18 16:09:09,700 epoch 4 - iter 150/304 - loss 0.48036194 - time (sec): 2.28 - samples/sec: 6718.10 - lr: 0.000022 - momentum: 0.000000 |
| 2023-10-18 16:09:10,147 epoch 4 - iter 180/304 - loss 0.46923649 - time (sec): 2.72 - samples/sec: 6725.24 - lr: 0.000021 - momentum: 0.000000 |
| 2023-10-18 16:09:10,604 epoch 4 - iter 210/304 - loss 0.45712690 - time (sec): 3.18 - samples/sec: 6760.63 - lr: 0.000021 - momentum: 0.000000 |
| 2023-10-18 16:09:11,069 epoch 4 - iter 240/304 - loss 0.44283720 - time (sec): 3.65 - samples/sec: 6784.42 - lr: 0.000021 - momentum: 0.000000 |
| 2023-10-18 16:09:11,565 epoch 4 - iter 270/304 - loss 0.43551713 - time (sec): 4.14 - samples/sec: 6685.10 - lr: 0.000020 - momentum: 0.000000 |
| 2023-10-18 16:09:12,041 epoch 4 - iter 300/304 - loss 0.43265860 - time (sec): 4.62 - samples/sec: 6631.80 - lr: 0.000020 - momentum: 0.000000 |
| 2023-10-18 16:09:12,105 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:12,105 EPOCH 4 done: loss 0.4307 - lr: 0.000020 |
| 2023-10-18 16:09:12,609 DEV : loss 0.3631349503993988 - f1-score (micro avg) 0.3265 |
| 2023-10-18 16:09:12,614 saving best model |
| 2023-10-18 16:09:12,647 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:13,106 epoch 5 - iter 30/304 - loss 0.34025576 - time (sec): 0.46 - samples/sec: 6983.59 - lr: 0.000020 - momentum: 0.000000 |
| 2023-10-18 16:09:13,557 epoch 5 - iter 60/304 - loss 0.36196872 - time (sec): 0.91 - samples/sec: 6820.93 - lr: 0.000019 - momentum: 0.000000 |
| 2023-10-18 16:09:13,997 epoch 5 - iter 90/304 - loss 0.35683083 - time (sec): 1.35 - samples/sec: 6634.21 - lr: 0.000019 - momentum: 0.000000 |
| 2023-10-18 16:09:14,466 epoch 5 - iter 120/304 - loss 0.40639760 - time (sec): 1.82 - samples/sec: 6544.84 - lr: 0.000019 - momentum: 0.000000 |
| 2023-10-18 16:09:14,946 epoch 5 - iter 150/304 - loss 0.40249742 - time (sec): 2.30 - samples/sec: 6546.89 - lr: 0.000018 - momentum: 0.000000 |
| 2023-10-18 16:09:15,420 epoch 5 - iter 180/304 - loss 0.39759932 - time (sec): 2.77 - samples/sec: 6643.26 - lr: 0.000018 - momentum: 0.000000 |
| 2023-10-18 16:09:15,906 epoch 5 - iter 210/304 - loss 0.39767302 - time (sec): 3.26 - samples/sec: 6611.63 - lr: 0.000018 - momentum: 0.000000 |
| 2023-10-18 16:09:16,356 epoch 5 - iter 240/304 - loss 0.38927505 - time (sec): 3.71 - samples/sec: 6599.33 - lr: 0.000017 - momentum: 0.000000 |
| 2023-10-18 16:09:16,798 epoch 5 - iter 270/304 - loss 0.38503699 - time (sec): 4.15 - samples/sec: 6657.04 - lr: 0.000017 - momentum: 0.000000 |
| 2023-10-18 16:09:17,245 epoch 5 - iter 300/304 - loss 0.37423160 - time (sec): 4.60 - samples/sec: 6664.77 - lr: 0.000017 - momentum: 0.000000 |
| 2023-10-18 16:09:17,305 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:17,305 EPOCH 5 done: loss 0.3752 - lr: 0.000017 |
| 2023-10-18 16:09:17,818 DEV : loss 0.33564966917037964 - f1-score (micro avg) 0.3549 |
| 2023-10-18 16:09:17,823 saving best model |
| 2023-10-18 16:09:17,857 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:18,298 epoch 6 - iter 30/304 - loss 0.31383168 - time (sec): 0.44 - samples/sec: 6530.98 - lr: 0.000016 - momentum: 0.000000 |
| 2023-10-18 16:09:18,754 epoch 6 - iter 60/304 - loss 0.36402365 - time (sec): 0.90 - samples/sec: 6790.46 - lr: 0.000016 - momentum: 0.000000 |
| 2023-10-18 16:09:19,203 epoch 6 - iter 90/304 - loss 0.34412109 - time (sec): 1.35 - samples/sec: 6673.20 - lr: 0.000016 - momentum: 0.000000 |
| 2023-10-18 16:09:19,659 epoch 6 - iter 120/304 - loss 0.35244301 - time (sec): 1.80 - samples/sec: 6592.56 - lr: 0.000015 - momentum: 0.000000 |
| 2023-10-18 16:09:20,110 epoch 6 - iter 150/304 - loss 0.35525525 - time (sec): 2.25 - samples/sec: 6543.44 - lr: 0.000015 - momentum: 0.000000 |
| 2023-10-18 16:09:20,563 epoch 6 - iter 180/304 - loss 0.35450906 - time (sec): 2.71 - samples/sec: 6623.51 - lr: 0.000015 - momentum: 0.000000 |
| 2023-10-18 16:09:21,005 epoch 6 - iter 210/304 - loss 0.35652642 - time (sec): 3.15 - samples/sec: 6675.12 - lr: 0.000014 - momentum: 0.000000 |
| 2023-10-18 16:09:21,459 epoch 6 - iter 240/304 - loss 0.34611008 - time (sec): 3.60 - samples/sec: 6736.50 - lr: 0.000014 - momentum: 0.000000 |
| 2023-10-18 16:09:21,919 epoch 6 - iter 270/304 - loss 0.34946532 - time (sec): 4.06 - samples/sec: 6737.04 - lr: 0.000014 - momentum: 0.000000 |
| 2023-10-18 16:09:22,378 epoch 6 - iter 300/304 - loss 0.35022338 - time (sec): 4.52 - samples/sec: 6768.37 - lr: 0.000013 - momentum: 0.000000 |
| 2023-10-18 16:09:22,434 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:22,434 EPOCH 6 done: loss 0.3500 - lr: 0.000013 |
| 2023-10-18 16:09:22,944 DEV : loss 0.3146110773086548 - f1-score (micro avg) 0.3941 |
| 2023-10-18 16:09:22,949 saving best model |
| 2023-10-18 16:09:22,982 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:23,439 epoch 7 - iter 30/304 - loss 0.34579912 - time (sec): 0.46 - samples/sec: 7197.20 - lr: 0.000013 - momentum: 0.000000 |
| 2023-10-18 16:09:23,879 epoch 7 - iter 60/304 - loss 0.35223700 - time (sec): 0.90 - samples/sec: 7077.64 - lr: 0.000013 - momentum: 0.000000 |
| 2023-10-18 16:09:24,347 epoch 7 - iter 90/304 - loss 0.35405953 - time (sec): 1.36 - samples/sec: 6890.01 - lr: 0.000012 - momentum: 0.000000 |
| 2023-10-18 16:09:24,799 epoch 7 - iter 120/304 - loss 0.35665519 - time (sec): 1.82 - samples/sec: 6851.86 - lr: 0.000012 - momentum: 0.000000 |
| 2023-10-18 16:09:25,247 epoch 7 - iter 150/304 - loss 0.35744709 - time (sec): 2.26 - samples/sec: 6844.70 - lr: 0.000012 - momentum: 0.000000 |
| 2023-10-18 16:09:25,696 epoch 7 - iter 180/304 - loss 0.35241960 - time (sec): 2.71 - samples/sec: 6728.76 - lr: 0.000011 - momentum: 0.000000 |
| 2023-10-18 16:09:26,151 epoch 7 - iter 210/304 - loss 0.34968566 - time (sec): 3.17 - samples/sec: 6765.80 - lr: 0.000011 - momentum: 0.000000 |
| 2023-10-18 16:09:26,618 epoch 7 - iter 240/304 - loss 0.34106153 - time (sec): 3.64 - samples/sec: 6701.38 - lr: 0.000011 - momentum: 0.000000 |
| 2023-10-18 16:09:27,042 epoch 7 - iter 270/304 - loss 0.33440491 - time (sec): 4.06 - samples/sec: 6782.04 - lr: 0.000010 - momentum: 0.000000 |
| 2023-10-18 16:09:27,453 epoch 7 - iter 300/304 - loss 0.33224705 - time (sec): 4.47 - samples/sec: 6847.16 - lr: 0.000010 - momentum: 0.000000 |
| 2023-10-18 16:09:27,510 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:27,510 EPOCH 7 done: loss 0.3296 - lr: 0.000010 |
| 2023-10-18 16:09:28,025 DEV : loss 0.3068331182003021 - f1-score (micro avg) 0.415 |
| 2023-10-18 16:09:28,031 saving best model |
| 2023-10-18 16:09:28,064 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:28,478 epoch 8 - iter 30/304 - loss 0.32214846 - time (sec): 0.41 - samples/sec: 7581.45 - lr: 0.000010 - momentum: 0.000000 |
| 2023-10-18 16:09:28,894 epoch 8 - iter 60/304 - loss 0.31625296 - time (sec): 0.83 - samples/sec: 7351.48 - lr: 0.000009 - momentum: 0.000000 |
| 2023-10-18 16:09:29,309 epoch 8 - iter 90/304 - loss 0.32570838 - time (sec): 1.24 - samples/sec: 7281.07 - lr: 0.000009 - momentum: 0.000000 |
| 2023-10-18 16:09:29,720 epoch 8 - iter 120/304 - loss 0.32093278 - time (sec): 1.66 - samples/sec: 7336.63 - lr: 0.000009 - momentum: 0.000000 |
| 2023-10-18 16:09:30,135 epoch 8 - iter 150/304 - loss 0.32687162 - time (sec): 2.07 - samples/sec: 7331.03 - lr: 0.000008 - momentum: 0.000000 |
| 2023-10-18 16:09:30,553 epoch 8 - iter 180/304 - loss 0.32787873 - time (sec): 2.49 - samples/sec: 7329.18 - lr: 0.000008 - momentum: 0.000000 |
| 2023-10-18 16:09:30,960 epoch 8 - iter 210/304 - loss 0.32674467 - time (sec): 2.90 - samples/sec: 7387.71 - lr: 0.000008 - momentum: 0.000000 |
| 2023-10-18 16:09:31,373 epoch 8 - iter 240/304 - loss 0.32799821 - time (sec): 3.31 - samples/sec: 7456.67 - lr: 0.000007 - momentum: 0.000000 |
| 2023-10-18 16:09:31,787 epoch 8 - iter 270/304 - loss 0.33179337 - time (sec): 3.72 - samples/sec: 7464.60 - lr: 0.000007 - momentum: 0.000000 |
| 2023-10-18 16:09:32,193 epoch 8 - iter 300/304 - loss 0.32052399 - time (sec): 4.13 - samples/sec: 7437.71 - lr: 0.000007 - momentum: 0.000000 |
| 2023-10-18 16:09:32,245 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:32,246 EPOCH 8 done: loss 0.3206 - lr: 0.000007 |
| 2023-10-18 16:09:32,757 DEV : loss 0.3029431998729706 - f1-score (micro avg) 0.4329 |
| 2023-10-18 16:09:32,763 saving best model |
| 2023-10-18 16:09:32,797 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:33,214 epoch 9 - iter 30/304 - loss 0.33032810 - time (sec): 0.42 - samples/sec: 8011.67 - lr: 0.000006 - momentum: 0.000000 |
| 2023-10-18 16:09:33,669 epoch 9 - iter 60/304 - loss 0.29904318 - time (sec): 0.87 - samples/sec: 7401.84 - lr: 0.000006 - momentum: 0.000000 |
| 2023-10-18 16:09:34,142 epoch 9 - iter 90/304 - loss 0.31053130 - time (sec): 1.34 - samples/sec: 7202.35 - lr: 0.000006 - momentum: 0.000000 |
| 2023-10-18 16:09:34,595 epoch 9 - iter 120/304 - loss 0.29487625 - time (sec): 1.80 - samples/sec: 7107.20 - lr: 0.000005 - momentum: 0.000000 |
| 2023-10-18 16:09:35,070 epoch 9 - iter 150/304 - loss 0.31264043 - time (sec): 2.27 - samples/sec: 6987.64 - lr: 0.000005 - momentum: 0.000000 |
| 2023-10-18 16:09:35,531 epoch 9 - iter 180/304 - loss 0.32296408 - time (sec): 2.73 - samples/sec: 6976.30 - lr: 0.000005 - momentum: 0.000000 |
| 2023-10-18 16:09:35,970 epoch 9 - iter 210/304 - loss 0.31918692 - time (sec): 3.17 - samples/sec: 6887.06 - lr: 0.000004 - momentum: 0.000000 |
| 2023-10-18 16:09:36,431 epoch 9 - iter 240/304 - loss 0.31887737 - time (sec): 3.63 - samples/sec: 6810.69 - lr: 0.000004 - momentum: 0.000000 |
| 2023-10-18 16:09:36,901 epoch 9 - iter 270/304 - loss 0.32134098 - time (sec): 4.10 - samples/sec: 6717.90 - lr: 0.000004 - momentum: 0.000000 |
| 2023-10-18 16:09:37,352 epoch 9 - iter 300/304 - loss 0.31556798 - time (sec): 4.55 - samples/sec: 6734.15 - lr: 0.000003 - momentum: 0.000000 |
| 2023-10-18 16:09:37,416 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:37,416 EPOCH 9 done: loss 0.3131 - lr: 0.000003 |
| 2023-10-18 16:09:37,928 DEV : loss 0.30005350708961487 - f1-score (micro avg) 0.4364 |
| 2023-10-18 16:09:37,933 saving best model |
| 2023-10-18 16:09:37,970 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:38,424 epoch 10 - iter 30/304 - loss 0.24235338 - time (sec): 0.45 - samples/sec: 6499.25 - lr: 0.000003 - momentum: 0.000000 |
| 2023-10-18 16:09:38,892 epoch 10 - iter 60/304 - loss 0.28433270 - time (sec): 0.92 - samples/sec: 6604.41 - lr: 0.000003 - momentum: 0.000000 |
| 2023-10-18 16:09:39,351 epoch 10 - iter 90/304 - loss 0.27118477 - time (sec): 1.38 - samples/sec: 6675.67 - lr: 0.000002 - momentum: 0.000000 |
| 2023-10-18 16:09:39,803 epoch 10 - iter 120/304 - loss 0.27659234 - time (sec): 1.83 - samples/sec: 6674.83 - lr: 0.000002 - momentum: 0.000000 |
| 2023-10-18 16:09:40,256 epoch 10 - iter 150/304 - loss 0.28318744 - time (sec): 2.28 - samples/sec: 6625.65 - lr: 0.000002 - momentum: 0.000000 |
| 2023-10-18 16:09:40,710 epoch 10 - iter 180/304 - loss 0.28760891 - time (sec): 2.74 - samples/sec: 6697.04 - lr: 0.000001 - momentum: 0.000000 |
| 2023-10-18 16:09:41,173 epoch 10 - iter 210/304 - loss 0.29813461 - time (sec): 3.20 - samples/sec: 6678.49 - lr: 0.000001 - momentum: 0.000000 |
| 2023-10-18 16:09:41,652 epoch 10 - iter 240/304 - loss 0.30000148 - time (sec): 3.68 - samples/sec: 6671.22 - lr: 0.000001 - momentum: 0.000000 |
| 2023-10-18 16:09:42,123 epoch 10 - iter 270/304 - loss 0.29854400 - time (sec): 4.15 - samples/sec: 6657.62 - lr: 0.000000 - momentum: 0.000000 |
| 2023-10-18 16:09:42,583 epoch 10 - iter 300/304 - loss 0.30223981 - time (sec): 4.61 - samples/sec: 6645.43 - lr: 0.000000 - momentum: 0.000000 |
| 2023-10-18 16:09:42,643 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:42,643 EPOCH 10 done: loss 0.3021 - lr: 0.000000 |
| 2023-10-18 16:09:43,151 DEV : loss 0.3000636398792267 - f1-score (micro avg) 0.4394 |
| 2023-10-18 16:09:43,157 saving best model |
| 2023-10-18 16:09:43,217 ---------------------------------------------------------------------------------------------------- |
| 2023-10-18 16:09:43,217 Loading model from best epoch ... |
| 2023-10-18 16:09:43,297 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 |
| 2023-10-18 16:09:43,769 |
| Results: |
| - F-score (micro) 0.4498 |
| - F-score (macro) 0.2815 |
| - Accuracy 0.302 |
|
|
| By class: |
| precision recall f1-score support |
|
|
| scope 0.4233 0.5298 0.4706 151 |
| work 0.2601 0.4737 0.3358 95 |
| pers 0.6753 0.5417 0.6012 96 |
| loc 0.0000 0.0000 0.0000 3 |
| date 0.0000 0.0000 0.0000 3 |
|
|
| micro avg 0.4032 0.5086 0.4498 348 |
| macro avg 0.2717 0.3090 0.2815 348 |
| weighted avg 0.4410 0.5086 0.4617 348 |
|
|
| 2023-10-18 16:09:43,770 ---------------------------------------------------------------------------------------------------- |
|
|
