| 2023-10-17 19:00:55,795 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,796 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 19:00:55,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,796 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 19:00:55,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,796 Train: 5777 sentences | |
| 2023-10-17 19:00:55,796 (train_with_dev=False, train_with_test=False) | |
| 2023-10-17 19:00:55,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,796 Training Params: | |
| 2023-10-17 19:00:55,796 - learning_rate: "5e-05" | |
| 2023-10-17 19:00:55,796 - mini_batch_size: "8" | |
| 2023-10-17 19:00:55,796 - max_epochs: "10" | |
| 2023-10-17 19:00:55,796 - shuffle: "True" | |
| 2023-10-17 19:00:55,796 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,796 Plugins: | |
| 2023-10-17 19:00:55,796 - TensorboardLogger | |
| 2023-10-17 19:00:55,797 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-17 19:00:55,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,797 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-17 19:00:55,797 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-17 19:00:55,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,797 Computation: | |
| 2023-10-17 19:00:55,797 - compute on device: cuda:0 | |
| 2023-10-17 19:00:55,797 - embedding storage: none | |
| 2023-10-17 19:00:55,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,797 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-17 19:00:55,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,797 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:00:55,797 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-17 19:01:01,305 epoch 1 - iter 72/723 - loss 2.43346961 - time (sec): 5.51 - samples/sec: 3053.64 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:01:06,577 epoch 1 - iter 144/723 - loss 1.39735442 - time (sec): 10.78 - samples/sec: 3151.18 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:01:11,902 epoch 1 - iter 216/723 - loss 0.98647245 - time (sec): 16.10 - samples/sec: 3181.79 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:01:17,195 epoch 1 - iter 288/723 - loss 0.77444671 - time (sec): 21.40 - samples/sec: 3222.92 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:01:22,154 epoch 1 - iter 360/723 - loss 0.64792967 - time (sec): 26.36 - samples/sec: 3272.45 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 19:01:27,784 epoch 1 - iter 432/723 - loss 0.55703287 - time (sec): 31.99 - samples/sec: 3262.43 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 19:01:33,257 epoch 1 - iter 504/723 - loss 0.49720863 - time (sec): 37.46 - samples/sec: 3257.16 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 19:01:38,961 epoch 1 - iter 576/723 - loss 0.44895161 - time (sec): 43.16 - samples/sec: 3238.06 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:01:44,455 epoch 1 - iter 648/723 - loss 0.41042010 - time (sec): 48.66 - samples/sec: 3237.70 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 19:01:49,975 epoch 1 - iter 720/723 - loss 0.38196732 - time (sec): 54.18 - samples/sec: 3239.23 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-17 19:01:50,192 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:01:50,192 EPOCH 1 done: loss 0.3808 - lr: 0.000050 | |
| 2023-10-17 19:01:53,250 DEV : loss 0.07317255437374115 - f1-score (micro avg) 0.8295 | |
| 2023-10-17 19:01:53,272 saving best model | |
| 2023-10-17 19:01:53,806 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:01:58,797 epoch 2 - iter 72/723 - loss 0.09594623 - time (sec): 4.99 - samples/sec: 3324.68 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 19:02:04,165 epoch 2 - iter 144/723 - loss 0.09490250 - time (sec): 10.36 - samples/sec: 3306.29 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-17 19:02:09,207 epoch 2 - iter 216/723 - loss 0.09141357 - time (sec): 15.40 - samples/sec: 3358.20 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 19:02:14,375 epoch 2 - iter 288/723 - loss 0.09618996 - time (sec): 20.57 - samples/sec: 3351.79 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-17 19:02:19,860 epoch 2 - iter 360/723 - loss 0.09056097 - time (sec): 26.05 - samples/sec: 3367.70 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 19:02:25,515 epoch 2 - iter 432/723 - loss 0.08791455 - time (sec): 31.71 - samples/sec: 3381.75 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-17 19:02:30,295 epoch 2 - iter 504/723 - loss 0.09029004 - time (sec): 36.49 - samples/sec: 3370.87 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:02:35,898 epoch 2 - iter 576/723 - loss 0.08956464 - time (sec): 42.09 - samples/sec: 3368.16 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-17 19:02:40,963 epoch 2 - iter 648/723 - loss 0.08990159 - time (sec): 47.16 - samples/sec: 3356.48 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-17 19:02:46,034 epoch 2 - iter 720/723 - loss 0.08747206 - time (sec): 52.23 - samples/sec: 3361.45 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:02:46,197 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:02:46,197 EPOCH 2 done: loss 0.0873 - lr: 0.000044 | |
| 2023-10-17 19:02:50,030 DEV : loss 0.06033102422952652 - f1-score (micro avg) 0.8512 | |
| 2023-10-17 19:02:50,046 saving best model | |
| 2023-10-17 19:02:50,562 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:02:55,561 epoch 3 - iter 72/723 - loss 0.05939468 - time (sec): 5.00 - samples/sec: 3464.35 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-17 19:03:00,234 epoch 3 - iter 144/723 - loss 0.06603411 - time (sec): 9.67 - samples/sec: 3510.27 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:03:05,632 epoch 3 - iter 216/723 - loss 0.06721595 - time (sec): 15.07 - samples/sec: 3457.17 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-17 19:03:10,987 epoch 3 - iter 288/723 - loss 0.06225454 - time (sec): 20.42 - samples/sec: 3431.78 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:03:16,247 epoch 3 - iter 360/723 - loss 0.06149114 - time (sec): 25.68 - samples/sec: 3439.35 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-17 19:03:21,493 epoch 3 - iter 432/723 - loss 0.06630663 - time (sec): 30.93 - samples/sec: 3417.42 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:03:26,570 epoch 3 - iter 504/723 - loss 0.06678596 - time (sec): 36.01 - samples/sec: 3413.39 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-17 19:03:32,030 epoch 3 - iter 576/723 - loss 0.06411011 - time (sec): 41.47 - samples/sec: 3413.58 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-17 19:03:37,092 epoch 3 - iter 648/723 - loss 0.06295898 - time (sec): 46.53 - samples/sec: 3408.05 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 19:03:42,333 epoch 3 - iter 720/723 - loss 0.06222050 - time (sec): 51.77 - samples/sec: 3391.79 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-17 19:03:42,513 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:42,513 EPOCH 3 done: loss 0.0621 - lr: 0.000039 | |
| 2023-10-17 19:03:45,685 DEV : loss 0.06847171485424042 - f1-score (micro avg) 0.865 | |
| 2023-10-17 19:03:45,702 saving best model | |
| 2023-10-17 19:03:46,180 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:03:51,616 epoch 4 - iter 72/723 - loss 0.04840124 - time (sec): 5.43 - samples/sec: 3391.17 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:03:57,075 epoch 4 - iter 144/723 - loss 0.04176500 - time (sec): 10.89 - samples/sec: 3354.24 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-17 19:04:01,951 epoch 4 - iter 216/723 - loss 0.04392943 - time (sec): 15.77 - samples/sec: 3360.14 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:04:07,383 epoch 4 - iter 288/723 - loss 0.04364348 - time (sec): 21.20 - samples/sec: 3342.12 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-17 19:04:12,696 epoch 4 - iter 360/723 - loss 0.04293801 - time (sec): 26.51 - samples/sec: 3294.13 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:04:17,989 epoch 4 - iter 432/723 - loss 0.04366335 - time (sec): 31.81 - samples/sec: 3293.19 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-17 19:04:23,052 epoch 4 - iter 504/723 - loss 0.04340638 - time (sec): 36.87 - samples/sec: 3327.19 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-17 19:04:28,459 epoch 4 - iter 576/723 - loss 0.04418918 - time (sec): 42.28 - samples/sec: 3317.02 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:04:33,632 epoch 4 - iter 648/723 - loss 0.04365686 - time (sec): 47.45 - samples/sec: 3318.67 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-17 19:04:38,779 epoch 4 - iter 720/723 - loss 0.04506250 - time (sec): 52.60 - samples/sec: 3341.13 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:04:38,929 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:04:38,929 EPOCH 4 done: loss 0.0450 - lr: 0.000033 | |
| 2023-10-17 19:04:42,195 DEV : loss 0.08221735805273056 - f1-score (micro avg) 0.8364 | |
| 2023-10-17 19:04:42,212 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:04:47,487 epoch 5 - iter 72/723 - loss 0.03743549 - time (sec): 5.27 - samples/sec: 3199.31 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-17 19:04:52,273 epoch 5 - iter 144/723 - loss 0.03409042 - time (sec): 10.06 - samples/sec: 3290.44 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:04:58,219 epoch 5 - iter 216/723 - loss 0.03376897 - time (sec): 16.01 - samples/sec: 3273.26 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-17 19:05:03,291 epoch 5 - iter 288/723 - loss 0.03120938 - time (sec): 21.08 - samples/sec: 3286.84 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:05:08,653 epoch 5 - iter 360/723 - loss 0.02837158 - time (sec): 26.44 - samples/sec: 3279.57 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-17 19:05:13,853 epoch 5 - iter 432/723 - loss 0.03029903 - time (sec): 31.64 - samples/sec: 3307.30 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-17 19:05:19,092 epoch 5 - iter 504/723 - loss 0.03306042 - time (sec): 36.88 - samples/sec: 3329.69 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:05:24,266 epoch 5 - iter 576/723 - loss 0.03308298 - time (sec): 42.05 - samples/sec: 3336.33 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-17 19:05:29,270 epoch 5 - iter 648/723 - loss 0.03349256 - time (sec): 47.06 - samples/sec: 3343.06 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:05:34,586 epoch 5 - iter 720/723 - loss 0.03379937 - time (sec): 52.37 - samples/sec: 3357.59 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-17 19:05:34,737 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:05:34,737 EPOCH 5 done: loss 0.0338 - lr: 0.000028 | |
| 2023-10-17 19:05:38,334 DEV : loss 0.10720644146203995 - f1-score (micro avg) 0.8427 | |
| 2023-10-17 19:05:38,350 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:05:43,670 epoch 6 - iter 72/723 - loss 0.01321373 - time (sec): 5.32 - samples/sec: 3423.73 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:05:48,889 epoch 6 - iter 144/723 - loss 0.01673976 - time (sec): 10.54 - samples/sec: 3405.46 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-17 19:05:53,981 epoch 6 - iter 216/723 - loss 0.02074721 - time (sec): 15.63 - samples/sec: 3431.04 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:05:59,313 epoch 6 - iter 288/723 - loss 0.02272213 - time (sec): 20.96 - samples/sec: 3397.60 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-17 19:06:04,725 epoch 6 - iter 360/723 - loss 0.02522995 - time (sec): 26.37 - samples/sec: 3400.38 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-17 19:06:09,964 epoch 6 - iter 432/723 - loss 0.02397191 - time (sec): 31.61 - samples/sec: 3400.05 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:06:15,057 epoch 6 - iter 504/723 - loss 0.02395899 - time (sec): 36.71 - samples/sec: 3398.23 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-17 19:06:19,981 epoch 6 - iter 576/723 - loss 0.02394027 - time (sec): 41.63 - samples/sec: 3393.65 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:06:25,252 epoch 6 - iter 648/723 - loss 0.02321616 - time (sec): 46.90 - samples/sec: 3383.09 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-17 19:06:30,319 epoch 6 - iter 720/723 - loss 0.02360596 - time (sec): 51.97 - samples/sec: 3381.82 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:06:30,493 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:06:30,493 EPOCH 6 done: loss 0.0236 - lr: 0.000022 | |
| 2023-10-17 19:06:33,631 DEV : loss 0.11060281097888947 - f1-score (micro avg) 0.8685 | |
| 2023-10-17 19:06:33,647 saving best model | |
| 2023-10-17 19:06:34,132 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:06:39,278 epoch 7 - iter 72/723 - loss 0.00876763 - time (sec): 5.14 - samples/sec: 3437.08 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-17 19:06:44,216 epoch 7 - iter 144/723 - loss 0.02003264 - time (sec): 10.08 - samples/sec: 3403.22 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:06:49,975 epoch 7 - iter 216/723 - loss 0.01713238 - time (sec): 15.84 - samples/sec: 3350.31 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-17 19:06:55,422 epoch 7 - iter 288/723 - loss 0.01901167 - time (sec): 21.29 - samples/sec: 3363.59 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-17 19:07:01,160 epoch 7 - iter 360/723 - loss 0.01889764 - time (sec): 27.03 - samples/sec: 3314.38 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:07:06,516 epoch 7 - iter 432/723 - loss 0.01931896 - time (sec): 32.38 - samples/sec: 3310.20 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-17 19:07:11,616 epoch 7 - iter 504/723 - loss 0.01874983 - time (sec): 37.48 - samples/sec: 3321.01 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:07:16,600 epoch 7 - iter 576/723 - loss 0.01774094 - time (sec): 42.46 - samples/sec: 3335.39 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-17 19:07:21,515 epoch 7 - iter 648/723 - loss 0.01802068 - time (sec): 47.38 - samples/sec: 3345.34 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:07:26,773 epoch 7 - iter 720/723 - loss 0.01760980 - time (sec): 52.64 - samples/sec: 3338.15 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-17 19:07:26,934 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:07:26,934 EPOCH 7 done: loss 0.0176 - lr: 0.000017 | |
| 2023-10-17 19:07:30,123 DEV : loss 0.12062493711709976 - f1-score (micro avg) 0.871 | |
| 2023-10-17 19:07:30,140 saving best model | |
| 2023-10-17 19:07:30,646 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:07:35,825 epoch 8 - iter 72/723 - loss 0.00784529 - time (sec): 5.18 - samples/sec: 3430.07 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:07:41,032 epoch 8 - iter 144/723 - loss 0.01225137 - time (sec): 10.38 - samples/sec: 3398.94 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-17 19:07:46,165 epoch 8 - iter 216/723 - loss 0.01162890 - time (sec): 15.52 - samples/sec: 3352.59 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-17 19:07:51,358 epoch 8 - iter 288/723 - loss 0.01081302 - time (sec): 20.71 - samples/sec: 3356.51 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:07:56,407 epoch 8 - iter 360/723 - loss 0.01066576 - time (sec): 25.76 - samples/sec: 3346.47 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-17 19:08:01,553 epoch 8 - iter 432/723 - loss 0.01039858 - time (sec): 30.91 - samples/sec: 3357.31 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:08:06,835 epoch 8 - iter 504/723 - loss 0.01051658 - time (sec): 36.19 - samples/sec: 3341.97 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-17 19:08:12,477 epoch 8 - iter 576/723 - loss 0.01174400 - time (sec): 41.83 - samples/sec: 3352.33 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:08:17,598 epoch 8 - iter 648/723 - loss 0.01179448 - time (sec): 46.95 - samples/sec: 3354.69 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-17 19:08:23,116 epoch 8 - iter 720/723 - loss 0.01201515 - time (sec): 52.47 - samples/sec: 3346.33 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:08:23,307 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:08:23,307 EPOCH 8 done: loss 0.0120 - lr: 0.000011 | |
| 2023-10-17 19:08:26,870 DEV : loss 0.12349953502416611 - f1-score (micro avg) 0.8772 | |
| 2023-10-17 19:08:26,886 saving best model | |
| 2023-10-17 19:08:27,376 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:08:32,712 epoch 9 - iter 72/723 - loss 0.00578653 - time (sec): 5.33 - samples/sec: 3302.60 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-17 19:08:38,063 epoch 9 - iter 144/723 - loss 0.00590740 - time (sec): 10.68 - samples/sec: 3389.04 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-17 19:08:42,976 epoch 9 - iter 216/723 - loss 0.00660418 - time (sec): 15.60 - samples/sec: 3394.47 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:08:48,105 epoch 9 - iter 288/723 - loss 0.00656305 - time (sec): 20.73 - samples/sec: 3401.06 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-17 19:08:53,371 epoch 9 - iter 360/723 - loss 0.00596195 - time (sec): 25.99 - samples/sec: 3407.27 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:08:58,592 epoch 9 - iter 432/723 - loss 0.00648461 - time (sec): 31.21 - samples/sec: 3392.16 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-17 19:09:04,561 epoch 9 - iter 504/723 - loss 0.00760297 - time (sec): 37.18 - samples/sec: 3353.67 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:09:09,754 epoch 9 - iter 576/723 - loss 0.00747124 - time (sec): 42.37 - samples/sec: 3344.01 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-17 19:09:15,067 epoch 9 - iter 648/723 - loss 0.00742990 - time (sec): 47.69 - samples/sec: 3352.27 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:09:19,783 epoch 9 - iter 720/723 - loss 0.00779320 - time (sec): 52.40 - samples/sec: 3354.70 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-17 19:09:19,935 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:09:19,936 EPOCH 9 done: loss 0.0078 - lr: 0.000006 | |
| 2023-10-17 19:09:23,169 DEV : loss 0.13878272473812103 - f1-score (micro avg) 0.8739 | |
| 2023-10-17 19:09:23,185 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:09:28,694 epoch 10 - iter 72/723 - loss 0.00379082 - time (sec): 5.51 - samples/sec: 3264.76 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-17 19:09:33,696 epoch 10 - iter 144/723 - loss 0.00277850 - time (sec): 10.51 - samples/sec: 3333.21 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:09:39,096 epoch 10 - iter 216/723 - loss 0.00300045 - time (sec): 15.91 - samples/sec: 3324.90 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-17 19:09:44,374 epoch 10 - iter 288/723 - loss 0.00434885 - time (sec): 21.19 - samples/sec: 3333.17 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:09:49,498 epoch 10 - iter 360/723 - loss 0.00447209 - time (sec): 26.31 - samples/sec: 3338.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-17 19:09:55,377 epoch 10 - iter 432/723 - loss 0.00446912 - time (sec): 32.19 - samples/sec: 3295.01 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:10:00,772 epoch 10 - iter 504/723 - loss 0.00425532 - time (sec): 37.59 - samples/sec: 3273.65 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-17 19:10:05,867 epoch 10 - iter 576/723 - loss 0.00443165 - time (sec): 42.68 - samples/sec: 3277.16 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:10:10,997 epoch 10 - iter 648/723 - loss 0.00471256 - time (sec): 47.81 - samples/sec: 3300.13 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-17 19:10:16,284 epoch 10 - iter 720/723 - loss 0.00513082 - time (sec): 53.10 - samples/sec: 3311.35 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-17 19:10:16,431 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:16,432 EPOCH 10 done: loss 0.0051 - lr: 0.000000 | |
| 2023-10-17 19:10:19,626 DEV : loss 0.1487891674041748 - f1-score (micro avg) 0.8743 | |
| 2023-10-17 19:10:20,036 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-17 19:10:20,037 Loading model from best epoch ... | |
| 2023-10-17 19:10:21,726 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 19:10:24,520 | |
| Results: | |
| - F-score (micro) 0.8384 | |
| - F-score (macro) 0.7459 | |
| - Accuracy 0.7301 | |
| By class: | |
| precision recall f1-score support | |
| PER 0.8697 0.8029 0.8350 482 | |
| LOC 0.9105 0.8886 0.8994 458 | |
| ORG 0.4535 0.5652 0.5032 69 | |
| micro avg 0.8517 0.8256 0.8384 1009 | |
| macro avg 0.7446 0.7523 0.7459 1009 | |
| weighted avg 0.8597 0.8256 0.8415 1009 | |
| 2023-10-17 19:10:24,520 ---------------------------------------------------------------------------------------------------- | |