| 2023-10-17 18:14:36,572 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,573 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=13, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-17 18:14:36,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,573 MultiCorpus: 5777 train + 722 dev + 723 test sentences | |
| - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl | |
| 2023-10-17 18:14:36,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,573 Train: 5777 sentences | |
| 2023-10-17 18:14:36,573 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 18:14:36,573 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,573 Training Params: | |
| 2023-10-17 18:14:36,573 - learning_rate: "5e-05" | |
| 2023-10-17 18:14:36,573 - mini_batch_size: "8" | |
| 2023-10-17 18:14:36,573 - max_epochs: "10" | |
| 2023-10-17 18:14:36,574 - shuffle: "True" | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 Plugins: | |
| 2023-10-17 18:14:36,574 - TensorboardLogger | |
| 2023-10-17 18:14:36,574 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 18:14:36,574 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 Computation: | |
| 2023-10-17 18:14:36,574 - compute on device: cuda:0 | |
| 2023-10-17 18:14:36,574 - embedding storage: none | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4" | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:14:36,574 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 18:14:41,661 epoch 1 - iter 72/723 - loss 2.82846299 - time (sec): 5.09 - samples/sec: 3184.96 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:14:47,525 epoch 1 - iter 144/723 - loss 1.53756178 - time (sec): 10.95 - samples/sec: 3122.44 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:14:52,788 epoch 1 - iter 216/723 - loss 1.08563753 - time (sec): 16.21 - samples/sec: 3188.21 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:14:58,171 epoch 1 - iter 288/723 - loss 0.85363225 - time (sec): 21.60 - samples/sec: 3202.36 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:15:03,632 epoch 1 - iter 360/723 - loss 0.70678074 - time (sec): 27.06 - samples/sec: 3220.89 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:15:09,301 epoch 1 - iter 432/723 - loss 0.60781553 - time (sec): 32.73 - samples/sec: 3226.45 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:15:14,759 epoch 1 - iter 504/723 - loss 0.53815724 - time (sec): 38.18 - samples/sec: 3229.85 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:15:20,287 epoch 1 - iter 576/723 - loss 0.48624214 - time (sec): 43.71 - samples/sec: 3230.61 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:15:26,129 epoch 1 - iter 648/723 - loss 0.44583351 - time (sec): 49.55 - samples/sec: 3209.61 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:15:30,721 epoch 1 - iter 720/723 - loss 0.41328459 - time (sec): 54.15 - samples/sec: 3244.08 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 18:15:30,886 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:15:30,886 EPOCH 1 done: loss 0.4122 - lr: 0.000050 | |
| 2023-10-17 18:15:33,753 DEV : loss 0.12260212749242783 - f1-score (micro avg) 0.5904 | |
| 2023-10-17 18:15:33,773 saving best model | |
| 2023-10-17 18:15:34,229 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:15:39,667 epoch 2 - iter 72/723 - loss 0.08593148 - time (sec): 5.44 - samples/sec: 3423.88 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:15:44,495 epoch 2 - iter 144/723 - loss 0.08917940 - time (sec): 10.26 - samples/sec: 3457.27 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 18:15:50,485 epoch 2 - iter 216/723 - loss 0.09223283 - time (sec): 16.25 - samples/sec: 3293.87 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:15:55,565 epoch 2 - iter 288/723 - loss 0.08777997 - time (sec): 21.33 - samples/sec: 3334.97 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 18:16:00,549 epoch 2 - iter 360/723 - loss 0.09090521 - time (sec): 26.32 - samples/sec: 3337.51 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:16:05,459 epoch 2 - iter 432/723 - loss 0.09183452 - time (sec): 31.23 - samples/sec: 3344.78 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 18:16:11,257 epoch 2 - iter 504/723 - loss 0.08898983 - time (sec): 37.03 - samples/sec: 3329.60 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:16:16,170 epoch 2 - iter 576/723 - loss 0.08716904 - time (sec): 41.94 - samples/sec: 3327.72 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 18:16:21,460 epoch 2 - iter 648/723 - loss 0.08641612 - time (sec): 47.23 - samples/sec: 3325.11 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 18:16:26,879 epoch 2 - iter 720/723 - loss 0.08419639 - time (sec): 52.65 - samples/sec: 3339.21 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 18:16:27,044 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:16:27,045 EPOCH 2 done: loss 0.0842 - lr: 0.000044 | |
| 2023-10-17 18:16:30,379 DEV : loss 0.07783125340938568 - f1-score (micro avg) 0.8082 | |
| 2023-10-17 18:16:30,401 saving best model | |
| 2023-10-17 18:16:30,846 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:16:36,693 epoch 3 - iter 72/723 - loss 0.05301331 - time (sec): 5.84 - samples/sec: 2992.47 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 18:16:41,929 epoch 3 - iter 144/723 - loss 0.05340362 - time (sec): 11.08 - samples/sec: 3145.26 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:16:46,948 epoch 3 - iter 216/723 - loss 0.05843774 - time (sec): 16.10 - samples/sec: 3203.11 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 18:16:52,164 epoch 3 - iter 288/723 - loss 0.05891078 - time (sec): 21.31 - samples/sec: 3207.70 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:16:57,780 epoch 3 - iter 360/723 - loss 0.05823104 - time (sec): 26.93 - samples/sec: 3203.75 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 18:17:03,835 epoch 3 - iter 432/723 - loss 0.06089242 - time (sec): 32.99 - samples/sec: 3215.06 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:17:09,285 epoch 3 - iter 504/723 - loss 0.06007862 - time (sec): 38.44 - samples/sec: 3237.98 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 18:17:14,379 epoch 3 - iter 576/723 - loss 0.05958555 - time (sec): 43.53 - samples/sec: 3254.82 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 18:17:19,692 epoch 3 - iter 648/723 - loss 0.05839709 - time (sec): 48.84 - samples/sec: 3251.06 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 18:17:24,980 epoch 3 - iter 720/723 - loss 0.05846821 - time (sec): 54.13 - samples/sec: 3241.95 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 18:17:25,236 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:17:25,236 EPOCH 3 done: loss 0.0585 - lr: 0.000039 | |
| 2023-10-17 18:17:28,635 DEV : loss 0.06642612814903259 - f1-score (micro avg) 0.8681 | |
| 2023-10-17 18:17:28,656 saving best model | |
| 2023-10-17 18:17:29,133 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:17:34,244 epoch 4 - iter 72/723 - loss 0.03361156 - time (sec): 5.11 - samples/sec: 3379.83 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:17:39,440 epoch 4 - iter 144/723 - loss 0.03971135 - time (sec): 10.30 - samples/sec: 3358.00 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 18:17:44,886 epoch 4 - iter 216/723 - loss 0.03902710 - time (sec): 15.75 - samples/sec: 3322.89 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:17:50,204 epoch 4 - iter 288/723 - loss 0.03924984 - time (sec): 21.07 - samples/sec: 3303.57 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 18:17:55,096 epoch 4 - iter 360/723 - loss 0.03839109 - time (sec): 25.96 - samples/sec: 3310.04 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:18:00,634 epoch 4 - iter 432/723 - loss 0.03903095 - time (sec): 31.50 - samples/sec: 3308.90 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 18:18:06,123 epoch 4 - iter 504/723 - loss 0.04064308 - time (sec): 36.99 - samples/sec: 3313.10 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 18:18:11,189 epoch 4 - iter 576/723 - loss 0.04149638 - time (sec): 42.05 - samples/sec: 3315.45 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 18:18:16,556 epoch 4 - iter 648/723 - loss 0.04083870 - time (sec): 47.42 - samples/sec: 3315.10 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 18:18:21,965 epoch 4 - iter 720/723 - loss 0.04158702 - time (sec): 52.83 - samples/sec: 3323.32 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:18:22,157 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:18:22,158 EPOCH 4 done: loss 0.0416 - lr: 0.000033 | |
| 2023-10-17 18:18:26,317 DEV : loss 0.08198380470275879 - f1-score (micro avg) 0.8284 | |
| 2023-10-17 18:18:26,337 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:18:31,722 epoch 5 - iter 72/723 - loss 0.02307719 - time (sec): 5.38 - samples/sec: 3302.59 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 18:18:36,964 epoch 5 - iter 144/723 - loss 0.02546761 - time (sec): 10.62 - samples/sec: 3328.56 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:18:41,939 epoch 5 - iter 216/723 - loss 0.02670835 - time (sec): 15.60 - samples/sec: 3328.47 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 18:18:47,488 epoch 5 - iter 288/723 - loss 0.02866238 - time (sec): 21.15 - samples/sec: 3329.01 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:18:52,380 epoch 5 - iter 360/723 - loss 0.02813552 - time (sec): 26.04 - samples/sec: 3347.59 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 18:18:57,646 epoch 5 - iter 432/723 - loss 0.02897696 - time (sec): 31.31 - samples/sec: 3336.12 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 18:19:03,014 epoch 5 - iter 504/723 - loss 0.03086408 - time (sec): 36.68 - samples/sec: 3303.79 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:19:08,556 epoch 5 - iter 576/723 - loss 0.03134206 - time (sec): 42.22 - samples/sec: 3291.15 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 18:19:14,073 epoch 5 - iter 648/723 - loss 0.03166141 - time (sec): 47.73 - samples/sec: 3282.55 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:19:19,823 epoch 5 - iter 720/723 - loss 0.03223354 - time (sec): 53.48 - samples/sec: 3284.17 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 18:19:20,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:19:20,031 EPOCH 5 done: loss 0.0322 - lr: 0.000028 | |
| 2023-10-17 18:19:23,459 DEV : loss 0.09982232004404068 - f1-score (micro avg) 0.8539 | |
| 2023-10-17 18:19:23,478 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:19:28,683 epoch 6 - iter 72/723 - loss 0.01778433 - time (sec): 5.20 - samples/sec: 3306.78 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:19:33,594 epoch 6 - iter 144/723 - loss 0.02139824 - time (sec): 10.11 - samples/sec: 3389.91 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 18:19:39,086 epoch 6 - iter 216/723 - loss 0.02084459 - time (sec): 15.61 - samples/sec: 3359.56 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:19:43,976 epoch 6 - iter 288/723 - loss 0.01975764 - time (sec): 20.50 - samples/sec: 3322.86 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 18:19:50,263 epoch 6 - iter 360/723 - loss 0.02010295 - time (sec): 26.78 - samples/sec: 3268.81 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 18:19:55,145 epoch 6 - iter 432/723 - loss 0.02157312 - time (sec): 31.67 - samples/sec: 3326.35 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:20:00,278 epoch 6 - iter 504/723 - loss 0.02145423 - time (sec): 36.80 - samples/sec: 3327.88 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 18:20:05,845 epoch 6 - iter 576/723 - loss 0.02219732 - time (sec): 42.37 - samples/sec: 3342.04 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:20:10,852 epoch 6 - iter 648/723 - loss 0.02281230 - time (sec): 47.37 - samples/sec: 3341.14 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 18:20:16,104 epoch 6 - iter 720/723 - loss 0.02320535 - time (sec): 52.62 - samples/sec: 3340.45 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:20:16,251 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:20:16,251 EPOCH 6 done: loss 0.0233 - lr: 0.000022 | |
| 2023-10-17 18:20:19,622 DEV : loss 0.10310214757919312 - f1-score (micro avg) 0.8637 | |
| 2023-10-17 18:20:19,639 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:20:24,696 epoch 7 - iter 72/723 - loss 0.01137758 - time (sec): 5.06 - samples/sec: 3312.99 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 18:20:29,955 epoch 7 - iter 144/723 - loss 0.01035726 - time (sec): 10.31 - samples/sec: 3328.52 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:20:35,456 epoch 7 - iter 216/723 - loss 0.01222737 - time (sec): 15.82 - samples/sec: 3347.94 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 18:20:40,772 epoch 7 - iter 288/723 - loss 0.01398472 - time (sec): 21.13 - samples/sec: 3325.67 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 18:20:46,399 epoch 7 - iter 360/723 - loss 0.01391412 - time (sec): 26.76 - samples/sec: 3309.49 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:20:51,771 epoch 7 - iter 432/723 - loss 0.01726287 - time (sec): 32.13 - samples/sec: 3299.59 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 18:20:57,440 epoch 7 - iter 504/723 - loss 0.01722411 - time (sec): 37.80 - samples/sec: 3304.69 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:21:02,335 epoch 7 - iter 576/723 - loss 0.01664986 - time (sec): 42.69 - samples/sec: 3312.40 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 18:21:07,462 epoch 7 - iter 648/723 - loss 0.01678267 - time (sec): 47.82 - samples/sec: 3321.58 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:21:12,580 epoch 7 - iter 720/723 - loss 0.01673920 - time (sec): 52.94 - samples/sec: 3318.91 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 18:21:12,758 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:21:12,758 EPOCH 7 done: loss 0.0168 - lr: 0.000017 | |
| 2023-10-17 18:21:16,524 DEV : loss 0.12066669762134552 - f1-score (micro avg) 0.8634 | |
| 2023-10-17 18:21:16,541 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:21:21,843 epoch 8 - iter 72/723 - loss 0.00672480 - time (sec): 5.30 - samples/sec: 3449.42 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:21:27,188 epoch 8 - iter 144/723 - loss 0.00814462 - time (sec): 10.65 - samples/sec: 3398.01 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 18:21:32,219 epoch 8 - iter 216/723 - loss 0.00959825 - time (sec): 15.68 - samples/sec: 3412.55 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 18:21:37,317 epoch 8 - iter 288/723 - loss 0.00947515 - time (sec): 20.77 - samples/sec: 3372.69 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:21:42,967 epoch 8 - iter 360/723 - loss 0.01067416 - time (sec): 26.42 - samples/sec: 3350.48 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 18:21:47,982 epoch 8 - iter 432/723 - loss 0.01055203 - time (sec): 31.44 - samples/sec: 3372.63 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:21:52,946 epoch 8 - iter 504/723 - loss 0.01033183 - time (sec): 36.40 - samples/sec: 3359.17 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 18:21:58,319 epoch 8 - iter 576/723 - loss 0.01006916 - time (sec): 41.78 - samples/sec: 3347.55 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:22:03,879 epoch 8 - iter 648/723 - loss 0.01046073 - time (sec): 47.34 - samples/sec: 3343.65 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 18:22:09,026 epoch 8 - iter 720/723 - loss 0.01086649 - time (sec): 52.48 - samples/sec: 3350.17 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:22:09,176 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:09,176 EPOCH 8 done: loss 0.0108 - lr: 0.000011 | |
| 2023-10-17 18:22:12,573 DEV : loss 0.12902837991714478 - f1-score (micro avg) 0.8617 | |
| 2023-10-17 18:22:12,591 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:22:18,040 epoch 9 - iter 72/723 - loss 0.00542030 - time (sec): 5.45 - samples/sec: 3217.95 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 18:22:23,260 epoch 9 - iter 144/723 - loss 0.00471316 - time (sec): 10.67 - samples/sec: 3292.45 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 18:22:28,631 epoch 9 - iter 216/723 - loss 0.00496387 - time (sec): 16.04 - samples/sec: 3327.91 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:22:34,047 epoch 9 - iter 288/723 - loss 0.00662306 - time (sec): 21.45 - samples/sec: 3324.31 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 18:22:39,129 epoch 9 - iter 360/723 - loss 0.00710139 - time (sec): 26.54 - samples/sec: 3306.26 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:22:44,235 epoch 9 - iter 432/723 - loss 0.00756603 - time (sec): 31.64 - samples/sec: 3336.32 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 18:22:50,214 epoch 9 - iter 504/723 - loss 0.00737050 - time (sec): 37.62 - samples/sec: 3275.66 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:22:55,692 epoch 9 - iter 576/723 - loss 0.00778212 - time (sec): 43.10 - samples/sec: 3280.49 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 18:23:00,511 epoch 9 - iter 648/723 - loss 0.00759945 - time (sec): 47.92 - samples/sec: 3296.91 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:23:06,028 epoch 9 - iter 720/723 - loss 0.00777119 - time (sec): 53.44 - samples/sec: 3286.78 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 18:23:06,230 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:06,230 EPOCH 9 done: loss 0.0077 - lr: 0.000006 | |
| 2023-10-17 18:23:09,690 DEV : loss 0.14203666150569916 - f1-score (micro avg) 0.8652 | |
| 2023-10-17 18:23:09,725 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:23:15,274 epoch 10 - iter 72/723 - loss 0.00541186 - time (sec): 5.55 - samples/sec: 3342.77 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 18:23:20,833 epoch 10 - iter 144/723 - loss 0.00416299 - time (sec): 11.11 - samples/sec: 3195.94 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:23:26,151 epoch 10 - iter 216/723 - loss 0.00402157 - time (sec): 16.42 - samples/sec: 3212.81 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 18:23:31,122 epoch 10 - iter 288/723 - loss 0.00415435 - time (sec): 21.39 - samples/sec: 3264.59 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:23:36,696 epoch 10 - iter 360/723 - loss 0.00474951 - time (sec): 26.97 - samples/sec: 3276.79 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 18:23:42,377 epoch 10 - iter 432/723 - loss 0.00538210 - time (sec): 32.65 - samples/sec: 3274.77 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:23:47,603 epoch 10 - iter 504/723 - loss 0.00603509 - time (sec): 37.88 - samples/sec: 3278.50 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 18:23:52,459 epoch 10 - iter 576/723 - loss 0.00551894 - time (sec): 42.73 - samples/sec: 3305.81 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:23:57,911 epoch 10 - iter 648/723 - loss 0.00616743 - time (sec): 48.18 - samples/sec: 3310.83 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 18:24:03,071 epoch 10 - iter 720/723 - loss 0.00577409 - time (sec): 53.34 - samples/sec: 3289.75 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 18:24:03,303 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:03,304 EPOCH 10 done: loss 0.0058 - lr: 0.000000 | |
| 2023-10-17 18:24:07,157 DEV : loss 0.14152230322360992 - f1-score (micro avg) 0.8652 | |
| 2023-10-17 18:24:07,568 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 18:24:07,569 Loading model from best epoch ... | |
| 2023-10-17 18:24:09,014 SequenceTagger predicts: Dictionary with 13 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 | |
| 2023-10-17 18:24:11,493 | |
| Results: | |
| - F-score (micro) 0.845 | |
| - F-score (macro) 0.726 | |
| - Accuracy 0.7393 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8364 0.8485 0.8424 482 | |
| LOC 0.9297 0.8952 0.9121 458 | |
| ORG 0.4265 0.4203 0.4234 69 | |
| micro avg 0.8497 0.8404 0.8450 1009 | |
| macro avg 0.7309 0.7213 0.7260 1009 | |
| weighted avg 0.8507 0.8404 0.8454 1009 | |
| 2023-10-17 18:24:11,494 ---------------------------------------------------------------------------------------------------- | |