| 2023-10-25 18:53:21,074 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Model: "SequenceTagger( | |
| (embeddings): TransformerWordEmbeddings( | |
| (model): BertModel( | |
| (embeddings): BertEmbeddings( | |
| (word_embeddings): Embedding(64001, 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): BertEncoder( | |
| (layer): ModuleList( | |
| (0-11): 12 x BertLayer( | |
| (attention): BertAttention( | |
| (self): BertSelfAttention( | |
| (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): BertSelfOutput( | |
| (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): BertIntermediate( | |
| (dense): Linear(in_features=768, out_features=3072, bias=True) | |
| (intermediate_act_fn): GELUActivation() | |
| ) | |
| (output): BertOutput( | |
| (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) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (pooler): BertPooler( | |
| (dense): Linear(in_features=768, out_features=768, bias=True) | |
| (activation): Tanh() | |
| ) | |
| ) | |
| ) | |
| (locked_dropout): LockedDropout(p=0.5) | |
| (linear): Linear(in_features=768, out_features=17, bias=True) | |
| (loss_function): CrossEntropyLoss() | |
| )" | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences | |
| - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Train: 20847 sentences | |
| 2023-10-25 18:53:21,075 (train_with_dev=False, train_with_test=False) | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Training Params: | |
| 2023-10-25 18:53:21,075 - learning_rate: "5e-05" | |
| 2023-10-25 18:53:21,075 - mini_batch_size: "8" | |
| 2023-10-25 18:53:21,075 - max_epochs: "10" | |
| 2023-10-25 18:53:21,075 - shuffle: "True" | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Plugins: | |
| 2023-10-25 18:53:21,075 - TensorboardLogger | |
| 2023-10-25 18:53:21,075 - LinearScheduler | warmup_fraction: '0.1' | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Final evaluation on model from best epoch (best-model.pt) | |
| 2023-10-25 18:53:21,075 - metric: "('micro avg', 'f1-score')" | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Computation: | |
| 2023-10-25 18:53:21,075 - compute on device: cuda:0 | |
| 2023-10-25 18:53:21,075 - embedding storage: none | |
| 2023-10-25 18:53:21,075 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,075 Model training base path: "hmbench-newseye/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5" | |
| 2023-10-25 18:53:21,076 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,076 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:53:21,076 Logging anything other than scalars to TensorBoard is currently not supported. | |
| 2023-10-25 18:53:35,071 epoch 1 - iter 260/2606 - loss 1.22654989 - time (sec): 13.99 - samples/sec: 2582.53 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 18:53:48,825 epoch 1 - iter 520/2606 - loss 0.79397378 - time (sec): 27.75 - samples/sec: 2647.86 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 18:54:03,050 epoch 1 - iter 780/2606 - loss 0.60720555 - time (sec): 41.97 - samples/sec: 2660.39 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 18:54:17,076 epoch 1 - iter 1040/2606 - loss 0.51582665 - time (sec): 56.00 - samples/sec: 2652.91 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 18:54:30,805 epoch 1 - iter 1300/2606 - loss 0.46165890 - time (sec): 69.73 - samples/sec: 2629.90 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 18:54:44,643 epoch 1 - iter 1560/2606 - loss 0.42197187 - time (sec): 83.57 - samples/sec: 2612.42 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 18:54:59,068 epoch 1 - iter 1820/2606 - loss 0.38914452 - time (sec): 97.99 - samples/sec: 2631.50 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 18:55:14,246 epoch 1 - iter 2080/2606 - loss 0.36051912 - time (sec): 113.17 - samples/sec: 2613.37 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 18:55:28,081 epoch 1 - iter 2340/2606 - loss 0.34210880 - time (sec): 127.00 - samples/sec: 2610.36 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 18:55:41,859 epoch 1 - iter 2600/2606 - loss 0.32875774 - time (sec): 140.78 - samples/sec: 2601.68 - lr: 0.000050 - momentum: 0.000000 | |
| 2023-10-25 18:55:42,255 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:55:42,256 EPOCH 1 done: loss 0.3282 - lr: 0.000050 | |
| 2023-10-25 18:55:46,806 DEV : loss 0.10818666964769363 - f1-score (micro avg) 0.3028 | |
| 2023-10-25 18:55:46,831 saving best model | |
| 2023-10-25 18:55:47,171 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:56:00,856 epoch 2 - iter 260/2606 - loss 0.16703388 - time (sec): 13.68 - samples/sec: 2673.86 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 18:56:14,745 epoch 2 - iter 520/2606 - loss 0.16020151 - time (sec): 27.57 - samples/sec: 2639.84 - lr: 0.000049 - momentum: 0.000000 | |
| 2023-10-25 18:56:28,759 epoch 2 - iter 780/2606 - loss 0.16073044 - time (sec): 41.59 - samples/sec: 2650.19 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 18:56:42,925 epoch 2 - iter 1040/2606 - loss 0.17210066 - time (sec): 55.75 - samples/sec: 2643.62 - lr: 0.000048 - momentum: 0.000000 | |
| 2023-10-25 18:56:56,952 epoch 2 - iter 1300/2606 - loss 0.18255173 - time (sec): 69.78 - samples/sec: 2621.28 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 18:57:11,062 epoch 2 - iter 1560/2606 - loss 0.18257560 - time (sec): 83.89 - samples/sec: 2640.91 - lr: 0.000047 - momentum: 0.000000 | |
| 2023-10-25 18:57:24,788 epoch 2 - iter 1820/2606 - loss 0.18125754 - time (sec): 97.62 - samples/sec: 2639.70 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 18:57:38,312 epoch 2 - iter 2080/2606 - loss 0.18852407 - time (sec): 111.14 - samples/sec: 2624.26 - lr: 0.000046 - momentum: 0.000000 | |
| 2023-10-25 18:57:52,289 epoch 2 - iter 2340/2606 - loss 0.20269247 - time (sec): 125.12 - samples/sec: 2626.55 - lr: 0.000045 - momentum: 0.000000 | |
| 2023-10-25 18:58:05,728 epoch 2 - iter 2600/2606 - loss 0.21971447 - time (sec): 138.56 - samples/sec: 2644.17 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 18:58:06,094 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:58:06,094 EPOCH 2 done: loss 0.2193 - lr: 0.000044 | |
| 2023-10-25 18:58:12,220 DEV : loss 0.15937478840351105 - f1-score (micro avg) 0.146 | |
| 2023-10-25 18:58:12,245 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 18:58:26,118 epoch 3 - iter 260/2606 - loss 0.35785536 - time (sec): 13.87 - samples/sec: 2625.46 - lr: 0.000044 - momentum: 0.000000 | |
| 2023-10-25 18:58:40,275 epoch 3 - iter 520/2606 - loss 0.33128432 - time (sec): 28.03 - samples/sec: 2711.15 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 18:58:54,085 epoch 3 - iter 780/2606 - loss 0.32057211 - time (sec): 41.84 - samples/sec: 2695.43 - lr: 0.000043 - momentum: 0.000000 | |
| 2023-10-25 18:59:07,877 epoch 3 - iter 1040/2606 - loss 0.31732087 - time (sec): 55.63 - samples/sec: 2662.56 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 18:59:21,706 epoch 3 - iter 1300/2606 - loss 0.31159665 - time (sec): 69.46 - samples/sec: 2666.29 - lr: 0.000042 - momentum: 0.000000 | |
| 2023-10-25 18:59:35,403 epoch 3 - iter 1560/2606 - loss 0.29696758 - time (sec): 83.16 - samples/sec: 2639.12 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 18:59:48,699 epoch 3 - iter 1820/2606 - loss 0.27941389 - time (sec): 96.45 - samples/sec: 2649.65 - lr: 0.000041 - momentum: 0.000000 | |
| 2023-10-25 19:00:03,073 epoch 3 - iter 2080/2606 - loss 0.26628342 - time (sec): 110.83 - samples/sec: 2661.43 - lr: 0.000040 - momentum: 0.000000 | |
| 2023-10-25 19:00:16,640 epoch 3 - iter 2340/2606 - loss 0.25955628 - time (sec): 124.39 - samples/sec: 2642.95 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 19:00:30,814 epoch 3 - iter 2600/2606 - loss 0.25232625 - time (sec): 138.57 - samples/sec: 2646.42 - lr: 0.000039 - momentum: 0.000000 | |
| 2023-10-25 19:00:31,097 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:00:31,098 EPOCH 3 done: loss 0.2522 - lr: 0.000039 | |
| 2023-10-25 19:00:37,278 DEV : loss 0.1657640039920807 - f1-score (micro avg) 0.1864 | |
| 2023-10-25 19:00:37,304 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:00:51,401 epoch 4 - iter 260/2606 - loss 0.15124015 - time (sec): 14.10 - samples/sec: 2591.51 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 19:01:06,091 epoch 4 - iter 520/2606 - loss 0.16792346 - time (sec): 28.79 - samples/sec: 2664.43 - lr: 0.000038 - momentum: 0.000000 | |
| 2023-10-25 19:01:19,837 epoch 4 - iter 780/2606 - loss 0.16285129 - time (sec): 42.53 - samples/sec: 2663.29 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 19:01:34,811 epoch 4 - iter 1040/2606 - loss 0.15299021 - time (sec): 57.51 - samples/sec: 2637.57 - lr: 0.000037 - momentum: 0.000000 | |
| 2023-10-25 19:01:49,026 epoch 4 - iter 1300/2606 - loss 0.14524141 - time (sec): 71.72 - samples/sec: 2644.43 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 19:02:02,607 epoch 4 - iter 1560/2606 - loss 0.14577143 - time (sec): 85.30 - samples/sec: 2630.63 - lr: 0.000036 - momentum: 0.000000 | |
| 2023-10-25 19:02:16,480 epoch 4 - iter 1820/2606 - loss 0.14482886 - time (sec): 99.18 - samples/sec: 2640.54 - lr: 0.000035 - momentum: 0.000000 | |
| 2023-10-25 19:02:30,428 epoch 4 - iter 2080/2606 - loss 0.14186931 - time (sec): 113.12 - samples/sec: 2636.86 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 19:02:43,625 epoch 4 - iter 2340/2606 - loss 0.13854088 - time (sec): 126.32 - samples/sec: 2637.26 - lr: 0.000034 - momentum: 0.000000 | |
| 2023-10-25 19:02:56,979 epoch 4 - iter 2600/2606 - loss 0.13696604 - time (sec): 139.67 - samples/sec: 2626.30 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 19:02:57,258 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:02:57,259 EPOCH 4 done: loss 0.1369 - lr: 0.000033 | |
| 2023-10-25 19:03:03,450 DEV : loss 0.1679009050130844 - f1-score (micro avg) 0.2583 | |
| 2023-10-25 19:03:03,476 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:03:17,388 epoch 5 - iter 260/2606 - loss 0.12128412 - time (sec): 13.91 - samples/sec: 2601.28 - lr: 0.000033 - momentum: 0.000000 | |
| 2023-10-25 19:03:31,093 epoch 5 - iter 520/2606 - loss 0.10950431 - time (sec): 27.62 - samples/sec: 2579.15 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 19:03:45,240 epoch 5 - iter 780/2606 - loss 0.11025977 - time (sec): 41.76 - samples/sec: 2612.93 - lr: 0.000032 - momentum: 0.000000 | |
| 2023-10-25 19:03:59,070 epoch 5 - iter 1040/2606 - loss 0.12022034 - time (sec): 55.59 - samples/sec: 2650.10 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 19:04:13,019 epoch 5 - iter 1300/2606 - loss 0.11986942 - time (sec): 69.54 - samples/sec: 2649.73 - lr: 0.000031 - momentum: 0.000000 | |
| 2023-10-25 19:04:26,967 epoch 5 - iter 1560/2606 - loss 0.12190371 - time (sec): 83.49 - samples/sec: 2649.25 - lr: 0.000030 - momentum: 0.000000 | |
| 2023-10-25 19:04:41,286 epoch 5 - iter 1820/2606 - loss 0.12535053 - time (sec): 97.81 - samples/sec: 2604.46 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 19:04:54,862 epoch 5 - iter 2080/2606 - loss 0.12512345 - time (sec): 111.38 - samples/sec: 2622.64 - lr: 0.000029 - momentum: 0.000000 | |
| 2023-10-25 19:05:08,753 epoch 5 - iter 2340/2606 - loss 0.12311329 - time (sec): 125.28 - samples/sec: 2623.06 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 19:05:23,105 epoch 5 - iter 2600/2606 - loss 0.11877944 - time (sec): 139.63 - samples/sec: 2625.34 - lr: 0.000028 - momentum: 0.000000 | |
| 2023-10-25 19:05:23,396 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:05:23,397 EPOCH 5 done: loss 0.1186 - lr: 0.000028 | |
| 2023-10-25 19:05:29,639 DEV : loss 0.24302677810192108 - f1-score (micro avg) 0.3593 | |
| 2023-10-25 19:05:29,664 saving best model | |
| 2023-10-25 19:05:30,133 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:05:44,343 epoch 6 - iter 260/2606 - loss 0.06961303 - time (sec): 14.20 - samples/sec: 2677.08 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 19:05:58,247 epoch 6 - iter 520/2606 - loss 0.06637601 - time (sec): 28.11 - samples/sec: 2600.18 - lr: 0.000027 - momentum: 0.000000 | |
| 2023-10-25 19:06:11,653 epoch 6 - iter 780/2606 - loss 0.07414255 - time (sec): 41.51 - samples/sec: 2613.60 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 19:06:25,533 epoch 6 - iter 1040/2606 - loss 0.10031781 - time (sec): 55.39 - samples/sec: 2648.30 - lr: 0.000026 - momentum: 0.000000 | |
| 2023-10-25 19:06:39,167 epoch 6 - iter 1300/2606 - loss 0.13040414 - time (sec): 69.03 - samples/sec: 2637.32 - lr: 0.000025 - momentum: 0.000000 | |
| 2023-10-25 19:06:53,355 epoch 6 - iter 1560/2606 - loss 0.13377462 - time (sec): 83.22 - samples/sec: 2645.86 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 19:07:06,957 epoch 6 - iter 1820/2606 - loss 0.13543341 - time (sec): 96.82 - samples/sec: 2631.12 - lr: 0.000024 - momentum: 0.000000 | |
| 2023-10-25 19:07:20,744 epoch 6 - iter 2080/2606 - loss 0.13407847 - time (sec): 110.61 - samples/sec: 2636.25 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 19:07:35,017 epoch 6 - iter 2340/2606 - loss 0.13093426 - time (sec): 124.88 - samples/sec: 2635.80 - lr: 0.000023 - momentum: 0.000000 | |
| 2023-10-25 19:07:50,193 epoch 6 - iter 2600/2606 - loss 0.12726324 - time (sec): 140.05 - samples/sec: 2616.54 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 19:07:50,554 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:07:50,555 EPOCH 6 done: loss 0.1275 - lr: 0.000022 | |
| 2023-10-25 19:07:56,751 DEV : loss 0.21893833577632904 - f1-score (micro avg) 0.2173 | |
| 2023-10-25 19:07:56,777 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:08:10,969 epoch 7 - iter 260/2606 - loss 0.11553804 - time (sec): 14.19 - samples/sec: 2546.35 - lr: 0.000022 - momentum: 0.000000 | |
| 2023-10-25 19:08:25,327 epoch 7 - iter 520/2606 - loss 0.11916207 - time (sec): 28.55 - samples/sec: 2588.66 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 19:08:39,233 epoch 7 - iter 780/2606 - loss 0.12128387 - time (sec): 42.46 - samples/sec: 2613.09 - lr: 0.000021 - momentum: 0.000000 | |
| 2023-10-25 19:08:53,554 epoch 7 - iter 1040/2606 - loss 0.12599467 - time (sec): 56.78 - samples/sec: 2633.23 - lr: 0.000020 - momentum: 0.000000 | |
| 2023-10-25 19:09:07,296 epoch 7 - iter 1300/2606 - loss 0.12603993 - time (sec): 70.52 - samples/sec: 2630.77 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 19:09:21,108 epoch 7 - iter 1560/2606 - loss 0.13415502 - time (sec): 84.33 - samples/sec: 2656.62 - lr: 0.000019 - momentum: 0.000000 | |
| 2023-10-25 19:09:35,497 epoch 7 - iter 1820/2606 - loss 0.13605167 - time (sec): 98.72 - samples/sec: 2651.85 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 19:09:49,453 epoch 7 - iter 2080/2606 - loss 0.13494947 - time (sec): 112.68 - samples/sec: 2647.74 - lr: 0.000018 - momentum: 0.000000 | |
| 2023-10-25 19:10:03,525 epoch 7 - iter 2340/2606 - loss 0.13572897 - time (sec): 126.75 - samples/sec: 2621.39 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 19:10:17,206 epoch 7 - iter 2600/2606 - loss 0.13869799 - time (sec): 140.43 - samples/sec: 2611.15 - lr: 0.000017 - momentum: 0.000000 | |
| 2023-10-25 19:10:17,500 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:10:17,501 EPOCH 7 done: loss 0.1388 - lr: 0.000017 | |
| 2023-10-25 19:10:24,378 DEV : loss 0.22277408838272095 - f1-score (micro avg) 0.1056 | |
| 2023-10-25 19:10:24,404 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:10:38,339 epoch 8 - iter 260/2606 - loss 0.13444344 - time (sec): 13.93 - samples/sec: 2599.23 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 19:10:52,192 epoch 8 - iter 520/2606 - loss 0.12655038 - time (sec): 27.79 - samples/sec: 2594.77 - lr: 0.000016 - momentum: 0.000000 | |
| 2023-10-25 19:11:06,051 epoch 8 - iter 780/2606 - loss 0.13953058 - time (sec): 41.65 - samples/sec: 2615.05 - lr: 0.000015 - momentum: 0.000000 | |
| 2023-10-25 19:11:19,501 epoch 8 - iter 1040/2606 - loss 0.15672566 - time (sec): 55.10 - samples/sec: 2596.78 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 19:11:33,165 epoch 8 - iter 1300/2606 - loss 0.16238670 - time (sec): 68.76 - samples/sec: 2630.61 - lr: 0.000014 - momentum: 0.000000 | |
| 2023-10-25 19:11:46,784 epoch 8 - iter 1560/2606 - loss 0.16000621 - time (sec): 82.38 - samples/sec: 2609.36 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 19:12:01,346 epoch 8 - iter 1820/2606 - loss 0.16256852 - time (sec): 96.94 - samples/sec: 2607.62 - lr: 0.000013 - momentum: 0.000000 | |
| 2023-10-25 19:12:15,435 epoch 8 - iter 2080/2606 - loss 0.16386440 - time (sec): 111.03 - samples/sec: 2610.02 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 19:12:29,146 epoch 8 - iter 2340/2606 - loss 0.16468898 - time (sec): 124.74 - samples/sec: 2638.59 - lr: 0.000012 - momentum: 0.000000 | |
| 2023-10-25 19:12:42,925 epoch 8 - iter 2600/2606 - loss 0.16416334 - time (sec): 138.52 - samples/sec: 2645.99 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 19:12:43,215 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:12:43,215 EPOCH 8 done: loss 0.1644 - lr: 0.000011 | |
| 2023-10-25 19:12:50,042 DEV : loss 0.25141724944114685 - f1-score (micro avg) 0.0708 | |
| 2023-10-25 19:12:50,069 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:13:04,144 epoch 9 - iter 260/2606 - loss 0.16456916 - time (sec): 14.07 - samples/sec: 2636.38 - lr: 0.000011 - momentum: 0.000000 | |
| 2023-10-25 19:13:18,077 epoch 9 - iter 520/2606 - loss 0.17390022 - time (sec): 28.01 - samples/sec: 2556.96 - lr: 0.000010 - momentum: 0.000000 | |
| 2023-10-25 19:13:32,123 epoch 9 - iter 780/2606 - loss 0.16945904 - time (sec): 42.05 - samples/sec: 2607.81 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 19:13:45,929 epoch 9 - iter 1040/2606 - loss 0.17187574 - time (sec): 55.86 - samples/sec: 2605.36 - lr: 0.000009 - momentum: 0.000000 | |
| 2023-10-25 19:13:59,718 epoch 9 - iter 1300/2606 - loss 0.17064245 - time (sec): 69.65 - samples/sec: 2590.76 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 19:14:13,646 epoch 9 - iter 1560/2606 - loss 0.16565863 - time (sec): 83.58 - samples/sec: 2599.36 - lr: 0.000008 - momentum: 0.000000 | |
| 2023-10-25 19:14:27,426 epoch 9 - iter 1820/2606 - loss 0.16328328 - time (sec): 97.36 - samples/sec: 2588.64 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 19:14:41,710 epoch 9 - iter 2080/2606 - loss 0.15985803 - time (sec): 111.64 - samples/sec: 2608.36 - lr: 0.000007 - momentum: 0.000000 | |
| 2023-10-25 19:14:55,830 epoch 9 - iter 2340/2606 - loss 0.15644552 - time (sec): 125.76 - samples/sec: 2630.74 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 19:15:09,880 epoch 9 - iter 2600/2606 - loss 0.15293464 - time (sec): 139.81 - samples/sec: 2618.85 - lr: 0.000006 - momentum: 0.000000 | |
| 2023-10-25 19:15:10,303 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:15:10,304 EPOCH 9 done: loss 0.1527 - lr: 0.000006 | |
| 2023-10-25 19:15:17,210 DEV : loss 0.23577940464019775 - f1-score (micro avg) 0.1376 | |
| 2023-10-25 19:15:17,236 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:15:31,281 epoch 10 - iter 260/2606 - loss 0.11824962 - time (sec): 14.04 - samples/sec: 2639.64 - lr: 0.000005 - momentum: 0.000000 | |
| 2023-10-25 19:15:45,059 epoch 10 - iter 520/2606 - loss 0.13577297 - time (sec): 27.82 - samples/sec: 2632.39 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 19:15:58,722 epoch 10 - iter 780/2606 - loss 0.14718022 - time (sec): 41.48 - samples/sec: 2638.99 - lr: 0.000004 - momentum: 0.000000 | |
| 2023-10-25 19:16:12,501 epoch 10 - iter 1040/2606 - loss 0.15180573 - time (sec): 55.26 - samples/sec: 2626.46 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 19:16:26,627 epoch 10 - iter 1300/2606 - loss 0.15379125 - time (sec): 69.39 - samples/sec: 2612.90 - lr: 0.000003 - momentum: 0.000000 | |
| 2023-10-25 19:16:40,065 epoch 10 - iter 1560/2606 - loss 0.15876599 - time (sec): 82.83 - samples/sec: 2594.32 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 19:16:54,014 epoch 10 - iter 1820/2606 - loss 0.15804883 - time (sec): 96.78 - samples/sec: 2597.72 - lr: 0.000002 - momentum: 0.000000 | |
| 2023-10-25 19:17:07,637 epoch 10 - iter 2080/2606 - loss 0.15931423 - time (sec): 110.40 - samples/sec: 2606.04 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 19:17:22,183 epoch 10 - iter 2340/2606 - loss 0.15752814 - time (sec): 124.95 - samples/sec: 2623.44 - lr: 0.000001 - momentum: 0.000000 | |
| 2023-10-25 19:17:36,063 epoch 10 - iter 2600/2606 - loss 0.15722249 - time (sec): 138.83 - samples/sec: 2636.58 - lr: 0.000000 - momentum: 0.000000 | |
| 2023-10-25 19:17:36,487 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:17:36,487 EPOCH 10 done: loss 0.1571 - lr: 0.000000 | |
| 2023-10-25 19:17:43,301 DEV : loss 0.22768089175224304 - f1-score (micro avg) 0.0925 | |
| 2023-10-25 19:17:43,799 ---------------------------------------------------------------------------------------------------- | |
| 2023-10-25 19:17:43,800 Loading model from best epoch ... | |
| 2023-10-25 19:17:45,401 SequenceTagger predicts: Dictionary with 17 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, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd | |
| 2023-10-25 19:17:55,259 | |
| Results: | |
| - F-score (micro) 0.4822 | |
| - F-score (macro) 0.3067 | |
| - Accuracy 0.3221 | |
| By class: | |
| precision recall f1-score support | |
| LOC 0.5077 0.6820 0.5821 1214 | |
| PER 0.4086 0.4703 0.4373 808 | |
| ORG 0.2050 0.2096 0.2073 353 | |
| HumanProd 0.0000 0.0000 0.0000 15 | |
| micro avg 0.4380 0.5364 0.4822 2390 | |
| macro avg 0.2803 0.3405 0.3067 2390 | |
| weighted avg 0.4263 0.5364 0.4741 2390 | |
| 2023-10-25 19:17:55,259 ---------------------------------------------------------------------------------------------------- | |