2023-10-19 20:58:16,394 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,394 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=17, bias=True) (loss_function): CrossEntropyLoss() )" 2023-10-19 20:58:16,394 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,394 MultiCorpus: 7142 train + 698 dev + 2570 test sentences - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator 2023-10-19 20:58:16,394 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,394 Train: 7142 sentences 2023-10-19 20:58:16,394 (train_with_dev=False, train_with_test=False) 2023-10-19 20:58:16,394 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Training Params: 2023-10-19 20:58:16,395 - learning_rate: "5e-05" 2023-10-19 20:58:16,395 - mini_batch_size: "4" 2023-10-19 20:58:16,395 - max_epochs: "10" 2023-10-19 20:58:16,395 - shuffle: "True" 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Plugins: 2023-10-19 20:58:16,395 - TensorboardLogger 2023-10-19 20:58:16,395 - LinearScheduler | warmup_fraction: '0.1' 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Final evaluation on model from best epoch (best-model.pt) 2023-10-19 20:58:16,395 - metric: "('micro avg', 'f1-score')" 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Computation: 2023-10-19 20:58:16,395 - compute on device: cuda:0 2023-10-19 20:58:16,395 - embedding storage: none 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Model training base path: "hmbench-newseye/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:16,395 Logging anything other than scalars to TensorBoard is currently not supported. 2023-10-19 20:58:19,025 epoch 1 - iter 178/1786 - loss 3.39433925 - time (sec): 2.63 - samples/sec: 9379.21 - lr: 0.000005 - momentum: 0.000000 2023-10-19 20:58:21,707 epoch 1 - iter 356/1786 - loss 2.91442988 - time (sec): 5.31 - samples/sec: 9619.01 - lr: 0.000010 - momentum: 0.000000 2023-10-19 20:58:24,768 epoch 1 - iter 534/1786 - loss 2.29912039 - time (sec): 8.37 - samples/sec: 9185.83 - lr: 0.000015 - momentum: 0.000000 2023-10-19 20:58:27,960 epoch 1 - iter 712/1786 - loss 1.91163547 - time (sec): 11.56 - samples/sec: 8856.81 - lr: 0.000020 - momentum: 0.000000 2023-10-19 20:58:31,072 epoch 1 - iter 890/1786 - loss 1.69293519 - time (sec): 14.68 - samples/sec: 8590.79 - lr: 0.000025 - momentum: 0.000000 2023-10-19 20:58:34,159 epoch 1 - iter 1068/1786 - loss 1.52968510 - time (sec): 17.76 - samples/sec: 8452.84 - lr: 0.000030 - momentum: 0.000000 2023-10-19 20:58:37,316 epoch 1 - iter 1246/1786 - loss 1.39348187 - time (sec): 20.92 - samples/sec: 8397.32 - lr: 0.000035 - momentum: 0.000000 2023-10-19 20:58:40,371 epoch 1 - iter 1424/1786 - loss 1.28507688 - time (sec): 23.98 - samples/sec: 8375.29 - lr: 0.000040 - momentum: 0.000000 2023-10-19 20:58:43,370 epoch 1 - iter 1602/1786 - loss 1.19861795 - time (sec): 26.97 - samples/sec: 8325.77 - lr: 0.000045 - momentum: 0.000000 2023-10-19 20:58:46,435 epoch 1 - iter 1780/1786 - loss 1.13141747 - time (sec): 30.04 - samples/sec: 8257.10 - lr: 0.000050 - momentum: 0.000000 2023-10-19 20:58:46,527 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:46,527 EPOCH 1 done: loss 1.1299 - lr: 0.000050 2023-10-19 20:58:47,918 DEV : loss 0.3072870969772339 - f1-score (micro avg) 0.2262 2023-10-19 20:58:47,932 saving best model 2023-10-19 20:58:47,966 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:58:51,058 epoch 2 - iter 178/1786 - loss 0.46644868 - time (sec): 3.09 - samples/sec: 7639.57 - lr: 0.000049 - momentum: 0.000000 2023-10-19 20:58:54,074 epoch 2 - iter 356/1786 - loss 0.46322785 - time (sec): 6.11 - samples/sec: 7992.93 - lr: 0.000049 - momentum: 0.000000 2023-10-19 20:58:57,117 epoch 2 - iter 534/1786 - loss 0.45211784 - time (sec): 9.15 - samples/sec: 8006.32 - lr: 0.000048 - momentum: 0.000000 2023-10-19 20:59:00,061 epoch 2 - iter 712/1786 - loss 0.44022463 - time (sec): 12.09 - samples/sec: 8050.83 - lr: 0.000048 - momentum: 0.000000 2023-10-19 20:59:03,120 epoch 2 - iter 890/1786 - loss 0.42492323 - time (sec): 15.15 - samples/sec: 8078.68 - lr: 0.000047 - momentum: 0.000000 2023-10-19 20:59:06,209 epoch 2 - iter 1068/1786 - loss 0.41906923 - time (sec): 18.24 - samples/sec: 8122.04 - lr: 0.000047 - momentum: 0.000000 2023-10-19 20:59:09,470 epoch 2 - iter 1246/1786 - loss 0.41285425 - time (sec): 21.50 - samples/sec: 8094.77 - lr: 0.000046 - momentum: 0.000000 2023-10-19 20:59:12,467 epoch 2 - iter 1424/1786 - loss 0.41328103 - time (sec): 24.50 - samples/sec: 8047.76 - lr: 0.000046 - momentum: 0.000000 2023-10-19 20:59:15,495 epoch 2 - iter 1602/1786 - loss 0.40602105 - time (sec): 27.53 - samples/sec: 8059.81 - lr: 0.000045 - momentum: 0.000000 2023-10-19 20:59:18,579 epoch 2 - iter 1780/1786 - loss 0.40352887 - time (sec): 30.61 - samples/sec: 8101.49 - lr: 0.000044 - momentum: 0.000000 2023-10-19 20:59:18,683 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:59:18,683 EPOCH 2 done: loss 0.4037 - lr: 0.000044 2023-10-19 20:59:21,544 DEV : loss 0.23947705328464508 - f1-score (micro avg) 0.3628 2023-10-19 20:59:21,558 saving best model 2023-10-19 20:59:21,594 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:59:24,722 epoch 3 - iter 178/1786 - loss 0.30638540 - time (sec): 3.13 - samples/sec: 8248.30 - lr: 0.000044 - momentum: 0.000000 2023-10-19 20:59:27,738 epoch 3 - iter 356/1786 - loss 0.32648450 - time (sec): 6.14 - samples/sec: 8067.28 - lr: 0.000043 - momentum: 0.000000 2023-10-19 20:59:30,745 epoch 3 - iter 534/1786 - loss 0.33121133 - time (sec): 9.15 - samples/sec: 8004.37 - lr: 0.000043 - momentum: 0.000000 2023-10-19 20:59:33,798 epoch 3 - iter 712/1786 - loss 0.32647076 - time (sec): 12.20 - samples/sec: 8063.71 - lr: 0.000042 - momentum: 0.000000 2023-10-19 20:59:36,949 epoch 3 - iter 890/1786 - loss 0.32878218 - time (sec): 15.35 - samples/sec: 8065.26 - lr: 0.000042 - momentum: 0.000000 2023-10-19 20:59:40,305 epoch 3 - iter 1068/1786 - loss 0.33069697 - time (sec): 18.71 - samples/sec: 7989.44 - lr: 0.000041 - momentum: 0.000000 2023-10-19 20:59:43,433 epoch 3 - iter 1246/1786 - loss 0.32906811 - time (sec): 21.84 - samples/sec: 7995.43 - lr: 0.000041 - momentum: 0.000000 2023-10-19 20:59:46,484 epoch 3 - iter 1424/1786 - loss 0.32966262 - time (sec): 24.89 - samples/sec: 7989.64 - lr: 0.000040 - momentum: 0.000000 2023-10-19 20:59:49,454 epoch 3 - iter 1602/1786 - loss 0.32998018 - time (sec): 27.86 - samples/sec: 7989.40 - lr: 0.000039 - momentum: 0.000000 2023-10-19 20:59:52,398 epoch 3 - iter 1780/1786 - loss 0.32830930 - time (sec): 30.80 - samples/sec: 8052.42 - lr: 0.000039 - momentum: 0.000000 2023-10-19 20:59:52,479 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:59:52,479 EPOCH 3 done: loss 0.3291 - lr: 0.000039 2023-10-19 20:59:54,832 DEV : loss 0.21711337566375732 - f1-score (micro avg) 0.4412 2023-10-19 20:59:54,845 saving best model 2023-10-19 20:59:54,880 ---------------------------------------------------------------------------------------------------- 2023-10-19 20:59:58,253 epoch 4 - iter 178/1786 - loss 0.28910294 - time (sec): 3.37 - samples/sec: 7599.18 - lr: 0.000038 - momentum: 0.000000 2023-10-19 21:00:01,330 epoch 4 - iter 356/1786 - loss 0.28554259 - time (sec): 6.45 - samples/sec: 7654.04 - lr: 0.000038 - momentum: 0.000000 2023-10-19 21:00:04,474 epoch 4 - iter 534/1786 - loss 0.28752177 - time (sec): 9.59 - samples/sec: 7716.32 - lr: 0.000037 - momentum: 0.000000 2023-10-19 21:00:07,494 epoch 4 - iter 712/1786 - loss 0.29481804 - time (sec): 12.61 - samples/sec: 7746.74 - lr: 0.000037 - momentum: 0.000000 2023-10-19 21:00:10,542 epoch 4 - iter 890/1786 - loss 0.29209292 - time (sec): 15.66 - samples/sec: 7825.10 - lr: 0.000036 - momentum: 0.000000 2023-10-19 21:00:13,639 epoch 4 - iter 1068/1786 - loss 0.29321400 - time (sec): 18.76 - samples/sec: 7799.47 - lr: 0.000036 - momentum: 0.000000 2023-10-19 21:00:16,855 epoch 4 - iter 1246/1786 - loss 0.29088719 - time (sec): 21.97 - samples/sec: 7788.31 - lr: 0.000035 - momentum: 0.000000 2023-10-19 21:00:20,030 epoch 4 - iter 1424/1786 - loss 0.28877714 - time (sec): 25.15 - samples/sec: 7893.11 - lr: 0.000034 - momentum: 0.000000 2023-10-19 21:00:23,060 epoch 4 - iter 1602/1786 - loss 0.28795049 - time (sec): 28.18 - samples/sec: 7909.66 - lr: 0.000034 - momentum: 0.000000 2023-10-19 21:00:26,192 epoch 4 - iter 1780/1786 - loss 0.28608450 - time (sec): 31.31 - samples/sec: 7908.48 - lr: 0.000033 - momentum: 0.000000 2023-10-19 21:00:26,298 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:00:26,298 EPOCH 4 done: loss 0.2856 - lr: 0.000033 2023-10-19 21:00:29,109 DEV : loss 0.21065032482147217 - f1-score (micro avg) 0.4851 2023-10-19 21:00:29,122 saving best model 2023-10-19 21:00:29,158 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:00:32,181 epoch 5 - iter 178/1786 - loss 0.26936022 - time (sec): 3.02 - samples/sec: 7810.87 - lr: 0.000033 - momentum: 0.000000 2023-10-19 21:00:35,233 epoch 5 - iter 356/1786 - loss 0.25893596 - time (sec): 6.07 - samples/sec: 8113.38 - lr: 0.000032 - momentum: 0.000000 2023-10-19 21:00:38,268 epoch 5 - iter 534/1786 - loss 0.26522534 - time (sec): 9.11 - samples/sec: 8061.37 - lr: 0.000032 - momentum: 0.000000 2023-10-19 21:00:41,439 epoch 5 - iter 712/1786 - loss 0.26176498 - time (sec): 12.28 - samples/sec: 8024.11 - lr: 0.000031 - momentum: 0.000000 2023-10-19 21:00:44,487 epoch 5 - iter 890/1786 - loss 0.26297763 - time (sec): 15.33 - samples/sec: 8044.77 - lr: 0.000031 - momentum: 0.000000 2023-10-19 21:00:47,482 epoch 5 - iter 1068/1786 - loss 0.25919324 - time (sec): 18.32 - samples/sec: 8016.32 - lr: 0.000030 - momentum: 0.000000 2023-10-19 21:00:50,611 epoch 5 - iter 1246/1786 - loss 0.25806711 - time (sec): 21.45 - samples/sec: 8119.10 - lr: 0.000029 - momentum: 0.000000 2023-10-19 21:00:53,748 epoch 5 - iter 1424/1786 - loss 0.25466980 - time (sec): 24.59 - samples/sec: 8072.99 - lr: 0.000029 - momentum: 0.000000 2023-10-19 21:00:56,856 epoch 5 - iter 1602/1786 - loss 0.25598645 - time (sec): 27.70 - samples/sec: 8070.63 - lr: 0.000028 - momentum: 0.000000 2023-10-19 21:00:59,939 epoch 5 - iter 1780/1786 - loss 0.25465192 - time (sec): 30.78 - samples/sec: 8048.62 - lr: 0.000028 - momentum: 0.000000 2023-10-19 21:01:00,052 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:01:00,052 EPOCH 5 done: loss 0.2543 - lr: 0.000028 2023-10-19 21:01:02,433 DEV : loss 0.20281952619552612 - f1-score (micro avg) 0.4948 2023-10-19 21:01:02,448 saving best model 2023-10-19 21:01:02,483 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:01:05,510 epoch 6 - iter 178/1786 - loss 0.23393227 - time (sec): 3.03 - samples/sec: 7808.95 - lr: 0.000027 - momentum: 0.000000 2023-10-19 21:01:08,545 epoch 6 - iter 356/1786 - loss 0.23081599 - time (sec): 6.06 - samples/sec: 8163.67 - lr: 0.000027 - momentum: 0.000000 2023-10-19 21:01:11,648 epoch 6 - iter 534/1786 - loss 0.23479214 - time (sec): 9.16 - samples/sec: 8155.13 - lr: 0.000026 - momentum: 0.000000 2023-10-19 21:01:14,701 epoch 6 - iter 712/1786 - loss 0.23298850 - time (sec): 12.22 - samples/sec: 8207.54 - lr: 0.000026 - momentum: 0.000000 2023-10-19 21:01:17,670 epoch 6 - iter 890/1786 - loss 0.23743133 - time (sec): 15.19 - samples/sec: 8100.39 - lr: 0.000025 - momentum: 0.000000 2023-10-19 21:01:20,467 epoch 6 - iter 1068/1786 - loss 0.23775517 - time (sec): 17.98 - samples/sec: 8153.61 - lr: 0.000024 - momentum: 0.000000 2023-10-19 21:01:23,606 epoch 6 - iter 1246/1786 - loss 0.23641985 - time (sec): 21.12 - samples/sec: 8149.38 - lr: 0.000024 - momentum: 0.000000 2023-10-19 21:01:26,829 epoch 6 - iter 1424/1786 - loss 0.23416317 - time (sec): 24.35 - samples/sec: 8123.71 - lr: 0.000023 - momentum: 0.000000 2023-10-19 21:01:29,978 epoch 6 - iter 1602/1786 - loss 0.23280312 - time (sec): 27.49 - samples/sec: 8121.44 - lr: 0.000023 - momentum: 0.000000 2023-10-19 21:01:33,180 epoch 6 - iter 1780/1786 - loss 0.23351653 - time (sec): 30.70 - samples/sec: 8085.38 - lr: 0.000022 - momentum: 0.000000 2023-10-19 21:01:33,290 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:01:33,291 EPOCH 6 done: loss 0.2338 - lr: 0.000022 2023-10-19 21:01:36,137 DEV : loss 0.2004702240228653 - f1-score (micro avg) 0.5138 2023-10-19 21:01:36,151 saving best model 2023-10-19 21:01:36,187 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:01:39,079 epoch 7 - iter 178/1786 - loss 0.23612974 - time (sec): 2.89 - samples/sec: 8198.00 - lr: 0.000022 - momentum: 0.000000 2023-10-19 21:01:42,193 epoch 7 - iter 356/1786 - loss 0.21613429 - time (sec): 6.01 - samples/sec: 8097.03 - lr: 0.000021 - momentum: 0.000000 2023-10-19 21:01:45,222 epoch 7 - iter 534/1786 - loss 0.21090820 - time (sec): 9.03 - samples/sec: 8043.86 - lr: 0.000021 - momentum: 0.000000 2023-10-19 21:01:48,279 epoch 7 - iter 712/1786 - loss 0.21151190 - time (sec): 12.09 - samples/sec: 8048.66 - lr: 0.000020 - momentum: 0.000000 2023-10-19 21:01:51,326 epoch 7 - iter 890/1786 - loss 0.21415014 - time (sec): 15.14 - samples/sec: 8097.58 - lr: 0.000019 - momentum: 0.000000 2023-10-19 21:01:54,448 epoch 7 - iter 1068/1786 - loss 0.22230949 - time (sec): 18.26 - samples/sec: 8094.44 - lr: 0.000019 - momentum: 0.000000 2023-10-19 21:01:57,518 epoch 7 - iter 1246/1786 - loss 0.22203000 - time (sec): 21.33 - samples/sec: 8038.74 - lr: 0.000018 - momentum: 0.000000 2023-10-19 21:02:00,602 epoch 7 - iter 1424/1786 - loss 0.22048490 - time (sec): 24.41 - samples/sec: 8093.24 - lr: 0.000018 - momentum: 0.000000 2023-10-19 21:02:03,686 epoch 7 - iter 1602/1786 - loss 0.21897496 - time (sec): 27.50 - samples/sec: 8107.85 - lr: 0.000017 - momentum: 0.000000 2023-10-19 21:02:06,657 epoch 7 - iter 1780/1786 - loss 0.21764711 - time (sec): 30.47 - samples/sec: 8128.14 - lr: 0.000017 - momentum: 0.000000 2023-10-19 21:02:06,760 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:02:06,761 EPOCH 7 done: loss 0.2174 - lr: 0.000017 2023-10-19 21:02:09,120 DEV : loss 0.20184864103794098 - f1-score (micro avg) 0.5363 2023-10-19 21:02:09,133 saving best model 2023-10-19 21:02:09,167 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:02:12,237 epoch 8 - iter 178/1786 - loss 0.19631205 - time (sec): 3.07 - samples/sec: 8420.53 - lr: 0.000016 - momentum: 0.000000 2023-10-19 21:02:15,400 epoch 8 - iter 356/1786 - loss 0.20351488 - time (sec): 6.23 - samples/sec: 8448.43 - lr: 0.000016 - momentum: 0.000000 2023-10-19 21:02:18,524 epoch 8 - iter 534/1786 - loss 0.19623338 - time (sec): 9.36 - samples/sec: 8444.47 - lr: 0.000015 - momentum: 0.000000 2023-10-19 21:02:21,610 epoch 8 - iter 712/1786 - loss 0.20086781 - time (sec): 12.44 - samples/sec: 8326.28 - lr: 0.000014 - momentum: 0.000000 2023-10-19 21:02:24,651 epoch 8 - iter 890/1786 - loss 0.20639441 - time (sec): 15.48 - samples/sec: 8245.95 - lr: 0.000014 - momentum: 0.000000 2023-10-19 21:02:27,907 epoch 8 - iter 1068/1786 - loss 0.20336709 - time (sec): 18.74 - samples/sec: 8209.92 - lr: 0.000013 - momentum: 0.000000 2023-10-19 21:02:30,983 epoch 8 - iter 1246/1786 - loss 0.20354696 - time (sec): 21.81 - samples/sec: 8112.38 - lr: 0.000013 - momentum: 0.000000 2023-10-19 21:02:34,043 epoch 8 - iter 1424/1786 - loss 0.20314656 - time (sec): 24.88 - samples/sec: 8074.10 - lr: 0.000012 - momentum: 0.000000 2023-10-19 21:02:37,160 epoch 8 - iter 1602/1786 - loss 0.20316820 - time (sec): 27.99 - samples/sec: 8039.11 - lr: 0.000012 - momentum: 0.000000 2023-10-19 21:02:40,110 epoch 8 - iter 1780/1786 - loss 0.20620940 - time (sec): 30.94 - samples/sec: 8015.46 - lr: 0.000011 - momentum: 0.000000 2023-10-19 21:02:40,204 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:02:40,205 EPOCH 8 done: loss 0.2060 - lr: 0.000011 2023-10-19 21:02:43,005 DEV : loss 0.19445763528347015 - f1-score (micro avg) 0.5412 2023-10-19 21:02:43,020 saving best model 2023-10-19 21:02:43,054 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:02:46,193 epoch 9 - iter 178/1786 - loss 0.20595102 - time (sec): 3.14 - samples/sec: 8098.61 - lr: 0.000011 - momentum: 0.000000 2023-10-19 21:02:49,523 epoch 9 - iter 356/1786 - loss 0.20915004 - time (sec): 6.47 - samples/sec: 7781.12 - lr: 0.000010 - momentum: 0.000000 2023-10-19 21:02:52,616 epoch 9 - iter 534/1786 - loss 0.21073170 - time (sec): 9.56 - samples/sec: 7757.88 - lr: 0.000009 - momentum: 0.000000 2023-10-19 21:02:55,656 epoch 9 - iter 712/1786 - loss 0.21153248 - time (sec): 12.60 - samples/sec: 7796.02 - lr: 0.000009 - momentum: 0.000000 2023-10-19 21:02:58,639 epoch 9 - iter 890/1786 - loss 0.20761614 - time (sec): 15.58 - samples/sec: 7833.49 - lr: 0.000008 - momentum: 0.000000 2023-10-19 21:03:01,755 epoch 9 - iter 1068/1786 - loss 0.20308539 - time (sec): 18.70 - samples/sec: 7955.21 - lr: 0.000008 - momentum: 0.000000 2023-10-19 21:03:04,756 epoch 9 - iter 1246/1786 - loss 0.20231833 - time (sec): 21.70 - samples/sec: 7957.84 - lr: 0.000007 - momentum: 0.000000 2023-10-19 21:03:08,025 epoch 9 - iter 1424/1786 - loss 0.20265135 - time (sec): 24.97 - samples/sec: 7928.87 - lr: 0.000007 - momentum: 0.000000 2023-10-19 21:03:11,119 epoch 9 - iter 1602/1786 - loss 0.20136577 - time (sec): 28.06 - samples/sec: 7934.50 - lr: 0.000006 - momentum: 0.000000 2023-10-19 21:03:14,180 epoch 9 - iter 1780/1786 - loss 0.19963572 - time (sec): 31.12 - samples/sec: 7968.46 - lr: 0.000006 - momentum: 0.000000 2023-10-19 21:03:14,278 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:03:14,279 EPOCH 9 done: loss 0.1998 - lr: 0.000006 2023-10-19 21:03:16,670 DEV : loss 0.19829225540161133 - f1-score (micro avg) 0.5422 2023-10-19 21:03:16,685 saving best model 2023-10-19 21:03:16,720 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:03:19,410 epoch 10 - iter 178/1786 - loss 0.18647044 - time (sec): 2.69 - samples/sec: 8782.65 - lr: 0.000005 - momentum: 0.000000 2023-10-19 21:03:22,378 epoch 10 - iter 356/1786 - loss 0.18609814 - time (sec): 5.66 - samples/sec: 8421.25 - lr: 0.000004 - momentum: 0.000000 2023-10-19 21:03:25,553 epoch 10 - iter 534/1786 - loss 0.18905060 - time (sec): 8.83 - samples/sec: 8418.27 - lr: 0.000004 - momentum: 0.000000 2023-10-19 21:03:28,473 epoch 10 - iter 712/1786 - loss 0.18325220 - time (sec): 11.75 - samples/sec: 8332.62 - lr: 0.000003 - momentum: 0.000000 2023-10-19 21:03:31,603 epoch 10 - iter 890/1786 - loss 0.18627484 - time (sec): 14.88 - samples/sec: 8203.30 - lr: 0.000003 - momentum: 0.000000 2023-10-19 21:03:34,723 epoch 10 - iter 1068/1786 - loss 0.18580625 - time (sec): 18.00 - samples/sec: 8209.34 - lr: 0.000002 - momentum: 0.000000 2023-10-19 21:03:37,964 epoch 10 - iter 1246/1786 - loss 0.18908200 - time (sec): 21.24 - samples/sec: 8087.53 - lr: 0.000002 - momentum: 0.000000 2023-10-19 21:03:41,184 epoch 10 - iter 1424/1786 - loss 0.19346145 - time (sec): 24.46 - samples/sec: 8079.92 - lr: 0.000001 - momentum: 0.000000 2023-10-19 21:03:44,560 epoch 10 - iter 1602/1786 - loss 0.19442863 - time (sec): 27.84 - samples/sec: 8041.93 - lr: 0.000001 - momentum: 0.000000 2023-10-19 21:03:47,563 epoch 10 - iter 1780/1786 - loss 0.19490021 - time (sec): 30.84 - samples/sec: 8043.92 - lr: 0.000000 - momentum: 0.000000 2023-10-19 21:03:47,661 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:03:47,661 EPOCH 10 done: loss 0.1948 - lr: 0.000000 2023-10-19 21:03:50,516 DEV : loss 0.19669239223003387 - f1-score (micro avg) 0.539 2023-10-19 21:03:50,560 ---------------------------------------------------------------------------------------------------- 2023-10-19 21:03:50,560 Loading model from best epoch ... 2023-10-19 21:03:50,642 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd 2023-10-19 21:03:55,238 Results: - F-score (micro) 0.4292 - F-score (macro) 0.2773 - Accuracy 0.2824 By class: precision recall f1-score support LOC 0.4196 0.5361 0.4707 1095 PER 0.4366 0.4931 0.4631 1012 ORG 0.1986 0.1569 0.1753 357 HumanProd 0.0000 0.0000 0.0000 33 micro avg 0.4044 0.4573 0.4292 2497 macro avg 0.2637 0.2965 0.2773 2497 weighted avg 0.3893 0.4573 0.4192 2497 2023-10-19 21:03:55,238 ----------------------------------------------------------------------------------------------------