| 2023-10-18 16:49:10,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,985 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 16:49:10,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,985 MultiCorpus: 966 train + 219 dev + 204 test sentences | |
| - NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator | |
| 2023-10-18 16:49:10,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,985 Train: 966 sentences | |
| 2023-10-18 16:49:10,985 (train_with_dev=False, train_with_test=False) | |
| 2023-10-18 16:49:10,985 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,985 Training Params: | |
| 2023-10-18 16:49:10,985 - learning_rate: "5e-05" | |
| 2023-10-18 16:49:10,986 - mini_batch_size: "8" | |
| 2023-10-18 16:49:10,986 - max_epochs: "10" | |
| 2023-10-18 16:49:10,986 - shuffle: "True" | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 Plugins: | |
| 2023-10-18 16:49:10,986 - TensorboardLogger | |
| 2023-10-18 16:49:10,986 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-18 16:49:10,986 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 Computation: | |
| 2023-10-18 16:49:10,986 - compute on device: cuda:0 | |
| 2023-10-18 16:49:10,986 - embedding storage: none | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:10,986 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-18 16:49:11,253 epoch 1 - iter 12/121 - loss 3.72713736 - time (sec): 0.27 - samples/sec: 8719.95 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:49:11,515 epoch 1 - iter 24/121 - loss 3.68254028 - time (sec): 0.53 - samples/sec: 8136.54 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:49:11,791 epoch 1 - iter 36/121 - loss 3.59134609 - time (sec): 0.81 - samples/sec: 8880.54 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:49:12,037 epoch 1 - iter 48/121 - loss 3.55633584 - time (sec): 1.05 - samples/sec: 9032.24 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:49:12,316 epoch 1 - iter 60/121 - loss 3.46291980 - time (sec): 1.33 - samples/sec: 8972.06 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:49:12,594 epoch 1 - iter 72/121 - loss 3.33050515 - time (sec): 1.61 - samples/sec: 8738.79 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:49:12,888 epoch 1 - iter 84/121 - loss 3.12714917 - time (sec): 1.90 - samples/sec: 8831.68 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 16:49:13,178 epoch 1 - iter 96/121 - loss 2.91734135 - time (sec): 2.19 - samples/sec: 8992.53 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 16:49:13,472 epoch 1 - iter 108/121 - loss 2.71807092 - time (sec): 2.49 - samples/sec: 8972.59 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 16:49:13,744 epoch 1 - iter 120/121 - loss 2.56157405 - time (sec): 2.76 - samples/sec: 8940.35 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 16:49:13,761 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:13,761 EPOCH 1 done: loss 2.5586 - lr: 0.000049 | |
| 2023-10-18 16:49:14,263 DEV : loss 0.6689526438713074 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:49:14,267 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:14,537 epoch 2 - iter 12/121 - loss 0.85949641 - time (sec): 0.27 - samples/sec: 8527.91 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 16:49:14,808 epoch 2 - iter 24/121 - loss 0.80203153 - time (sec): 0.54 - samples/sec: 8843.97 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-18 16:49:15,082 epoch 2 - iter 36/121 - loss 0.74766992 - time (sec): 0.81 - samples/sec: 8853.54 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 16:49:15,361 epoch 2 - iter 48/121 - loss 0.74653215 - time (sec): 1.09 - samples/sec: 9031.51 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-18 16:49:15,629 epoch 2 - iter 60/121 - loss 0.74136252 - time (sec): 1.36 - samples/sec: 8881.34 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 16:49:15,909 epoch 2 - iter 72/121 - loss 0.73051734 - time (sec): 1.64 - samples/sec: 8964.48 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-18 16:49:16,194 epoch 2 - iter 84/121 - loss 0.69974561 - time (sec): 1.93 - samples/sec: 8987.28 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 16:49:16,454 epoch 2 - iter 96/121 - loss 0.68148518 - time (sec): 2.19 - samples/sec: 9057.63 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-18 16:49:16,733 epoch 2 - iter 108/121 - loss 0.68752824 - time (sec): 2.46 - samples/sec: 8966.01 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 16:49:17,009 epoch 2 - iter 120/121 - loss 0.67810410 - time (sec): 2.74 - samples/sec: 8941.80 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-18 16:49:17,031 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:17,031 EPOCH 2 done: loss 0.6798 - lr: 0.000045 | |
| 2023-10-18 16:49:17,445 DEV : loss 0.5302271246910095 - f1-score (micro avg) 0.0 | |
| 2023-10-18 16:49:17,449 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:17,733 epoch 3 - iter 12/121 - loss 0.63136350 - time (sec): 0.28 - samples/sec: 8812.39 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-18 16:49:18,013 epoch 3 - iter 24/121 - loss 0.63881305 - time (sec): 0.56 - samples/sec: 8522.42 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 16:49:18,285 epoch 3 - iter 36/121 - loss 0.61984806 - time (sec): 0.84 - samples/sec: 8446.79 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-18 16:49:18,564 epoch 3 - iter 48/121 - loss 0.60854023 - time (sec): 1.11 - samples/sec: 8569.04 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 16:49:18,847 epoch 3 - iter 60/121 - loss 0.59345209 - time (sec): 1.40 - samples/sec: 8608.60 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-18 16:49:19,125 epoch 3 - iter 72/121 - loss 0.58075144 - time (sec): 1.68 - samples/sec: 8525.12 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 16:49:19,417 epoch 3 - iter 84/121 - loss 0.56521053 - time (sec): 1.97 - samples/sec: 8572.83 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-18 16:49:19,700 epoch 3 - iter 96/121 - loss 0.55199458 - time (sec): 2.25 - samples/sec: 8755.00 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 16:49:19,962 epoch 3 - iter 108/121 - loss 0.54104939 - time (sec): 2.51 - samples/sec: 8836.74 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-18 16:49:20,242 epoch 3 - iter 120/121 - loss 0.54037189 - time (sec): 2.79 - samples/sec: 8801.33 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-18 16:49:20,262 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:20,262 EPOCH 3 done: loss 0.5410 - lr: 0.000039 | |
| 2023-10-18 16:49:20,695 DEV : loss 0.381939560174942 - f1-score (micro avg) 0.3002 | |
| 2023-10-18 16:49:20,700 saving best model | |
| 2023-10-18 16:49:20,731 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:20,989 epoch 4 - iter 12/121 - loss 0.50702022 - time (sec): 0.26 - samples/sec: 8128.22 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 16:49:21,277 epoch 4 - iter 24/121 - loss 0.49506642 - time (sec): 0.54 - samples/sec: 8209.41 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-18 16:49:21,569 epoch 4 - iter 36/121 - loss 0.47500254 - time (sec): 0.84 - samples/sec: 8682.50 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 16:49:21,853 epoch 4 - iter 48/121 - loss 0.47354154 - time (sec): 1.12 - samples/sec: 8583.02 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-18 16:49:22,134 epoch 4 - iter 60/121 - loss 0.47124215 - time (sec): 1.40 - samples/sec: 8610.82 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 16:49:22,388 epoch 4 - iter 72/121 - loss 0.46122791 - time (sec): 1.66 - samples/sec: 8812.55 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-18 16:49:22,627 epoch 4 - iter 84/121 - loss 0.45653064 - time (sec): 1.90 - samples/sec: 9128.40 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 16:49:22,859 epoch 4 - iter 96/121 - loss 0.44905118 - time (sec): 2.13 - samples/sec: 9298.71 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-18 16:49:23,097 epoch 4 - iter 108/121 - loss 0.45279950 - time (sec): 2.37 - samples/sec: 9400.33 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 16:49:23,338 epoch 4 - iter 120/121 - loss 0.44523965 - time (sec): 2.61 - samples/sec: 9462.90 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-18 16:49:23,353 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:23,353 EPOCH 4 done: loss 0.4454 - lr: 0.000034 | |
| 2023-10-18 16:49:23,789 DEV : loss 0.3381112813949585 - f1-score (micro avg) 0.4947 | |
| 2023-10-18 16:49:23,794 saving best model | |
| 2023-10-18 16:49:23,830 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:24,117 epoch 5 - iter 12/121 - loss 0.41972847 - time (sec): 0.29 - samples/sec: 8612.77 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-18 16:49:24,403 epoch 5 - iter 24/121 - loss 0.41330755 - time (sec): 0.57 - samples/sec: 8795.86 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 16:49:24,691 epoch 5 - iter 36/121 - loss 0.40168231 - time (sec): 0.86 - samples/sec: 8748.80 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-18 16:49:24,985 epoch 5 - iter 48/121 - loss 0.41316545 - time (sec): 1.15 - samples/sec: 8822.37 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 16:49:25,270 epoch 5 - iter 60/121 - loss 0.41557311 - time (sec): 1.44 - samples/sec: 8746.90 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-18 16:49:25,561 epoch 5 - iter 72/121 - loss 0.41191855 - time (sec): 1.73 - samples/sec: 8674.73 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:49:25,840 epoch 5 - iter 84/121 - loss 0.40660510 - time (sec): 2.01 - samples/sec: 8677.35 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-18 16:49:26,130 epoch 5 - iter 96/121 - loss 0.40532680 - time (sec): 2.30 - samples/sec: 8674.10 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:49:26,407 epoch 5 - iter 108/121 - loss 0.39336067 - time (sec): 2.58 - samples/sec: 8661.97 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-18 16:49:26,677 epoch 5 - iter 120/121 - loss 0.39049497 - time (sec): 2.85 - samples/sec: 8653.68 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-18 16:49:26,701 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:26,701 EPOCH 5 done: loss 0.3905 - lr: 0.000028 | |
| 2023-10-18 16:49:27,124 DEV : loss 0.3011309802532196 - f1-score (micro avg) 0.5082 | |
| 2023-10-18 16:49:27,128 saving best model | |
| 2023-10-18 16:49:27,162 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:27,442 epoch 6 - iter 12/121 - loss 0.37794026 - time (sec): 0.28 - samples/sec: 9209.89 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:49:27,731 epoch 6 - iter 24/121 - loss 0.37454241 - time (sec): 0.57 - samples/sec: 8822.22 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-18 16:49:28,007 epoch 6 - iter 36/121 - loss 0.38763418 - time (sec): 0.84 - samples/sec: 8933.48 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:49:28,275 epoch 6 - iter 48/121 - loss 0.35457046 - time (sec): 1.11 - samples/sec: 8773.55 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-18 16:49:28,544 epoch 6 - iter 60/121 - loss 0.35728616 - time (sec): 1.38 - samples/sec: 8902.85 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:49:28,806 epoch 6 - iter 72/121 - loss 0.36295866 - time (sec): 1.64 - samples/sec: 8996.27 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-18 16:49:29,073 epoch 6 - iter 84/121 - loss 0.36487335 - time (sec): 1.91 - samples/sec: 8970.49 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:49:29,360 epoch 6 - iter 96/121 - loss 0.36377538 - time (sec): 2.20 - samples/sec: 8954.12 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-18 16:49:29,633 epoch 6 - iter 108/121 - loss 0.36537129 - time (sec): 2.47 - samples/sec: 8881.51 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-18 16:49:29,904 epoch 6 - iter 120/121 - loss 0.36732004 - time (sec): 2.74 - samples/sec: 8960.94 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:49:29,925 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:29,925 EPOCH 6 done: loss 0.3688 - lr: 0.000022 | |
| 2023-10-18 16:49:30,359 DEV : loss 0.2984113097190857 - f1-score (micro avg) 0.502 | |
| 2023-10-18 16:49:30,364 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:30,651 epoch 7 - iter 12/121 - loss 0.40613445 - time (sec): 0.29 - samples/sec: 8976.21 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-18 16:49:30,909 epoch 7 - iter 24/121 - loss 0.41370276 - time (sec): 0.54 - samples/sec: 8608.82 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:49:31,179 epoch 7 - iter 36/121 - loss 0.37536403 - time (sec): 0.82 - samples/sec: 8675.70 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-18 16:49:31,469 epoch 7 - iter 48/121 - loss 0.36222419 - time (sec): 1.10 - samples/sec: 8516.41 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:49:31,757 epoch 7 - iter 60/121 - loss 0.35411100 - time (sec): 1.39 - samples/sec: 8553.45 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-18 16:49:32,054 epoch 7 - iter 72/121 - loss 0.34332631 - time (sec): 1.69 - samples/sec: 8575.99 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:49:32,340 epoch 7 - iter 84/121 - loss 0.33865656 - time (sec): 1.98 - samples/sec: 8573.15 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-18 16:49:32,641 epoch 7 - iter 96/121 - loss 0.33749701 - time (sec): 2.28 - samples/sec: 8731.67 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-18 16:49:32,922 epoch 7 - iter 108/121 - loss 0.33356220 - time (sec): 2.56 - samples/sec: 8671.42 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:49:33,214 epoch 7 - iter 120/121 - loss 0.33868936 - time (sec): 2.85 - samples/sec: 8611.06 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-18 16:49:33,237 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:33,237 EPOCH 7 done: loss 0.3400 - lr: 0.000017 | |
| 2023-10-18 16:49:33,666 DEV : loss 0.27059388160705566 - f1-score (micro avg) 0.5045 | |
| 2023-10-18 16:49:33,670 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:33,968 epoch 8 - iter 12/121 - loss 0.30290414 - time (sec): 0.30 - samples/sec: 8972.35 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:49:34,233 epoch 8 - iter 24/121 - loss 0.31569742 - time (sec): 0.56 - samples/sec: 9301.98 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-18 16:49:34,501 epoch 8 - iter 36/121 - loss 0.33749440 - time (sec): 0.83 - samples/sec: 9037.76 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:49:34,765 epoch 8 - iter 48/121 - loss 0.32913262 - time (sec): 1.09 - samples/sec: 9003.84 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-18 16:49:35,035 epoch 8 - iter 60/121 - loss 0.32611495 - time (sec): 1.36 - samples/sec: 9087.31 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:49:35,305 epoch 8 - iter 72/121 - loss 0.33844770 - time (sec): 1.63 - samples/sec: 9239.39 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-18 16:49:35,573 epoch 8 - iter 84/121 - loss 0.33910562 - time (sec): 1.90 - samples/sec: 9126.54 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:49:35,865 epoch 8 - iter 96/121 - loss 0.33140197 - time (sec): 2.19 - samples/sec: 8997.65 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-18 16:49:36,149 epoch 8 - iter 108/121 - loss 0.32859024 - time (sec): 2.48 - samples/sec: 8976.42 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-18 16:49:36,440 epoch 8 - iter 120/121 - loss 0.32937493 - time (sec): 2.77 - samples/sec: 8880.63 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:49:36,461 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:36,461 EPOCH 8 done: loss 0.3309 - lr: 0.000011 | |
| 2023-10-18 16:49:36,887 DEV : loss 0.2683504819869995 - f1-score (micro avg) 0.5013 | |
| 2023-10-18 16:49:36,892 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:37,144 epoch 9 - iter 12/121 - loss 0.29611456 - time (sec): 0.25 - samples/sec: 8083.33 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-18 16:49:37,413 epoch 9 - iter 24/121 - loss 0.30471163 - time (sec): 0.52 - samples/sec: 8653.57 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:49:37,681 epoch 9 - iter 36/121 - loss 0.32069614 - time (sec): 0.79 - samples/sec: 9053.93 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-18 16:49:37,949 epoch 9 - iter 48/121 - loss 0.33713582 - time (sec): 1.06 - samples/sec: 9070.10 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:49:38,213 epoch 9 - iter 60/121 - loss 0.33878681 - time (sec): 1.32 - samples/sec: 9123.25 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-18 16:49:38,486 epoch 9 - iter 72/121 - loss 0.32211477 - time (sec): 1.59 - samples/sec: 8964.35 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:49:38,760 epoch 9 - iter 84/121 - loss 0.32473282 - time (sec): 1.87 - samples/sec: 8827.54 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-18 16:49:39,054 epoch 9 - iter 96/121 - loss 0.32602555 - time (sec): 2.16 - samples/sec: 8896.30 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-18 16:49:39,339 epoch 9 - iter 108/121 - loss 0.32172863 - time (sec): 2.45 - samples/sec: 8988.93 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:49:39,627 epoch 9 - iter 120/121 - loss 0.31854401 - time (sec): 2.73 - samples/sec: 9031.83 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-18 16:49:39,643 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:39,643 EPOCH 9 done: loss 0.3188 - lr: 0.000006 | |
| 2023-10-18 16:49:40,074 DEV : loss 0.26560044288635254 - f1-score (micro avg) 0.5057 | |
| 2023-10-18 16:49:40,079 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:40,361 epoch 10 - iter 12/121 - loss 0.27727518 - time (sec): 0.28 - samples/sec: 7967.73 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:49:40,652 epoch 10 - iter 24/121 - loss 0.27962103 - time (sec): 0.57 - samples/sec: 8188.65 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-18 16:49:40,942 epoch 10 - iter 36/121 - loss 0.29244867 - time (sec): 0.86 - samples/sec: 8244.33 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:49:41,215 epoch 10 - iter 48/121 - loss 0.29015356 - time (sec): 1.14 - samples/sec: 8530.01 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-18 16:49:41,508 epoch 10 - iter 60/121 - loss 0.30367640 - time (sec): 1.43 - samples/sec: 8411.83 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:49:41,802 epoch 10 - iter 72/121 - loss 0.31348682 - time (sec): 1.72 - samples/sec: 8568.36 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-18 16:49:42,083 epoch 10 - iter 84/121 - loss 0.30219811 - time (sec): 2.00 - samples/sec: 8609.62 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-18 16:49:42,352 epoch 10 - iter 96/121 - loss 0.30601340 - time (sec): 2.27 - samples/sec: 8641.36 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:49:42,640 epoch 10 - iter 108/121 - loss 0.30556624 - time (sec): 2.56 - samples/sec: 8644.25 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-18 16:49:42,917 epoch 10 - iter 120/121 - loss 0.31380038 - time (sec): 2.84 - samples/sec: 8652.47 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-18 16:49:42,941 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:42,941 EPOCH 10 done: loss 0.3123 - lr: 0.000000 | |
| 2023-10-18 16:49:43,379 DEV : loss 0.2643878161907196 - f1-score (micro avg) 0.5032 | |
| 2023-10-18 16:49:43,411 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-18 16:49:43,411 Loading model from best epoch ... | |
| 2023-10-18 16:49:43,479 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date | |
| 2023-10-18 16:49:43,894 | |
| Results: | |
| - F-score (micro) 0.4511 | |
| - F-score (macro) 0.2083 | |
| - Accuracy 0.3072 | |
| By class: | |
| precision recall f1-score support | |
| pers 0.5419 0.6978 0.6101 139 | |
| scope 0.4027 0.4651 0.4317 129 | |
| work 0.0000 0.0000 0.0000 80 | |
| loc 0.0000 0.0000 0.0000 9 | |
| date 0.0000 0.0000 0.0000 3 | |
| micro avg 0.4673 0.4361 0.4511 360 | |
| macro avg 0.1889 0.2326 0.2083 360 | |
| weighted avg 0.3535 0.4361 0.3902 360 | |
| 2023-10-18 16:49:43,894 ---------------------------------------------------------------------------------------------------- | |