File size: 23,906 Bytes
3b5884f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
2023-10-13 08:18:44,052 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(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): 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 MultiCorpus: 1100 train + 206 dev + 240 test sentences
- NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Train: 1100 sentences
2023-10-13 08:18:44,053 (train_with_dev=False, train_with_test=False)
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Training Params:
2023-10-13 08:18:44,053 - learning_rate: "5e-05"
2023-10-13 08:18:44,053 - mini_batch_size: "8"
2023-10-13 08:18:44,053 - max_epochs: "10"
2023-10-13 08:18:44,053 - shuffle: "True"
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Plugins:
2023-10-13 08:18:44,053 - LinearScheduler | warmup_fraction: '0.1'
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Final evaluation on model from best epoch (best-model.pt)
2023-10-13 08:18:44,053 - metric: "('micro avg', 'f1-score')"
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Computation:
2023-10-13 08:18:44,053 - compute on device: cuda:0
2023-10-13 08:18:44,053 - embedding storage: none
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,053 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:44,769 epoch 1 - iter 13/138 - loss 3.36216384 - time (sec): 0.71 - samples/sec: 2638.24 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:18:45,511 epoch 1 - iter 26/138 - loss 3.05778578 - time (sec): 1.46 - samples/sec: 2880.89 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:18:46,213 epoch 1 - iter 39/138 - loss 2.50663084 - time (sec): 2.16 - samples/sec: 2928.60 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:18:46,974 epoch 1 - iter 52/138 - loss 2.12168365 - time (sec): 2.92 - samples/sec: 2885.36 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:18:47,664 epoch 1 - iter 65/138 - loss 1.85127161 - time (sec): 3.61 - samples/sec: 2900.21 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:18:48,458 epoch 1 - iter 78/138 - loss 1.62474225 - time (sec): 4.40 - samples/sec: 2900.66 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:18:49,213 epoch 1 - iter 91/138 - loss 1.46221903 - time (sec): 5.16 - samples/sec: 2915.04 - lr: 0.000033 - momentum: 0.000000
2023-10-13 08:18:49,925 epoch 1 - iter 104/138 - loss 1.35389479 - time (sec): 5.87 - samples/sec: 2891.43 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:18:50,720 epoch 1 - iter 117/138 - loss 1.24029074 - time (sec): 6.67 - samples/sec: 2888.87 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:18:51,440 epoch 1 - iter 130/138 - loss 1.16080197 - time (sec): 7.39 - samples/sec: 2894.16 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:18:51,871 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:51,872 EPOCH 1 done: loss 1.1099 - lr: 0.000047
2023-10-13 08:18:52,835 DEV : loss 0.2852579355239868 - f1-score (micro avg) 0.6815
2023-10-13 08:18:52,842 saving best model
2023-10-13 08:18:53,246 ----------------------------------------------------------------------------------------------------
2023-10-13 08:18:53,964 epoch 2 - iter 13/138 - loss 0.29008713 - time (sec): 0.72 - samples/sec: 2803.74 - lr: 0.000050 - momentum: 0.000000
2023-10-13 08:18:54,676 epoch 2 - iter 26/138 - loss 0.27894573 - time (sec): 1.43 - samples/sec: 2883.49 - lr: 0.000049 - momentum: 0.000000
2023-10-13 08:18:55,401 epoch 2 - iter 39/138 - loss 0.26387076 - time (sec): 2.15 - samples/sec: 2796.71 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:18:56,141 epoch 2 - iter 52/138 - loss 0.24752298 - time (sec): 2.89 - samples/sec: 2876.04 - lr: 0.000048 - momentum: 0.000000
2023-10-13 08:18:56,868 epoch 2 - iter 65/138 - loss 0.22805221 - time (sec): 3.62 - samples/sec: 2912.31 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:18:57,629 epoch 2 - iter 78/138 - loss 0.22365996 - time (sec): 4.38 - samples/sec: 2892.94 - lr: 0.000047 - momentum: 0.000000
2023-10-13 08:18:58,350 epoch 2 - iter 91/138 - loss 0.21579324 - time (sec): 5.10 - samples/sec: 2910.70 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:18:59,086 epoch 2 - iter 104/138 - loss 0.20462341 - time (sec): 5.84 - samples/sec: 2910.63 - lr: 0.000046 - momentum: 0.000000
2023-10-13 08:18:59,845 epoch 2 - iter 117/138 - loss 0.19740281 - time (sec): 6.60 - samples/sec: 2923.65 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:19:00,577 epoch 2 - iter 130/138 - loss 0.19452383 - time (sec): 7.33 - samples/sec: 2914.09 - lr: 0.000045 - momentum: 0.000000
2023-10-13 08:19:01,051 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:01,051 EPOCH 2 done: loss 0.1977 - lr: 0.000045
2023-10-13 08:19:01,753 DEV : loss 0.14731210470199585 - f1-score (micro avg) 0.8041
2023-10-13 08:19:01,758 saving best model
2023-10-13 08:19:02,198 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:02,903 epoch 3 - iter 13/138 - loss 0.12039031 - time (sec): 0.70 - samples/sec: 2866.43 - lr: 0.000044 - momentum: 0.000000
2023-10-13 08:19:03,675 epoch 3 - iter 26/138 - loss 0.09369394 - time (sec): 1.47 - samples/sec: 2908.65 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:19:04,473 epoch 3 - iter 39/138 - loss 0.10326361 - time (sec): 2.27 - samples/sec: 2888.04 - lr: 0.000043 - momentum: 0.000000
2023-10-13 08:19:05,196 epoch 3 - iter 52/138 - loss 0.10553197 - time (sec): 3.00 - samples/sec: 2938.08 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:19:05,892 epoch 3 - iter 65/138 - loss 0.11195550 - time (sec): 3.69 - samples/sec: 2951.29 - lr: 0.000042 - momentum: 0.000000
2023-10-13 08:19:06,665 epoch 3 - iter 78/138 - loss 0.10537692 - time (sec): 4.46 - samples/sec: 2904.53 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:19:07,387 epoch 3 - iter 91/138 - loss 0.10329309 - time (sec): 5.19 - samples/sec: 2935.01 - lr: 0.000041 - momentum: 0.000000
2023-10-13 08:19:08,155 epoch 3 - iter 104/138 - loss 0.10645368 - time (sec): 5.96 - samples/sec: 2935.54 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:19:08,832 epoch 3 - iter 117/138 - loss 0.10399949 - time (sec): 6.63 - samples/sec: 2922.79 - lr: 0.000040 - momentum: 0.000000
2023-10-13 08:19:09,542 epoch 3 - iter 130/138 - loss 0.10393272 - time (sec): 7.34 - samples/sec: 2914.56 - lr: 0.000039 - momentum: 0.000000
2023-10-13 08:19:09,974 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:09,975 EPOCH 3 done: loss 0.1024 - lr: 0.000039
2023-10-13 08:19:10,669 DEV : loss 0.13100138306617737 - f1-score (micro avg) 0.8446
2023-10-13 08:19:10,674 saving best model
2023-10-13 08:19:11,144 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:11,917 epoch 4 - iter 13/138 - loss 0.06021214 - time (sec): 0.77 - samples/sec: 2989.30 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:19:12,689 epoch 4 - iter 26/138 - loss 0.05825819 - time (sec): 1.54 - samples/sec: 2978.65 - lr: 0.000038 - momentum: 0.000000
2023-10-13 08:19:13,424 epoch 4 - iter 39/138 - loss 0.06845418 - time (sec): 2.27 - samples/sec: 2977.41 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:19:14,151 epoch 4 - iter 52/138 - loss 0.06522582 - time (sec): 3.00 - samples/sec: 2905.17 - lr: 0.000037 - momentum: 0.000000
2023-10-13 08:19:14,914 epoch 4 - iter 65/138 - loss 0.06752163 - time (sec): 3.76 - samples/sec: 2893.53 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:19:15,628 epoch 4 - iter 78/138 - loss 0.06464366 - time (sec): 4.48 - samples/sec: 2880.99 - lr: 0.000036 - momentum: 0.000000
2023-10-13 08:19:16,386 epoch 4 - iter 91/138 - loss 0.07140504 - time (sec): 5.24 - samples/sec: 2905.51 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:19:17,117 epoch 4 - iter 104/138 - loss 0.06658007 - time (sec): 5.97 - samples/sec: 2878.12 - lr: 0.000035 - momentum: 0.000000
2023-10-13 08:19:17,882 epoch 4 - iter 117/138 - loss 0.06558565 - time (sec): 6.73 - samples/sec: 2869.24 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:19:18,619 epoch 4 - iter 130/138 - loss 0.06645078 - time (sec): 7.47 - samples/sec: 2885.99 - lr: 0.000034 - momentum: 0.000000
2023-10-13 08:19:19,072 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:19,072 EPOCH 4 done: loss 0.0696 - lr: 0.000034
2023-10-13 08:19:19,781 DEV : loss 0.1526499092578888 - f1-score (micro avg) 0.8148
2023-10-13 08:19:19,786 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:20,455 epoch 5 - iter 13/138 - loss 0.03833787 - time (sec): 0.67 - samples/sec: 2816.94 - lr: 0.000033 - momentum: 0.000000
2023-10-13 08:19:21,163 epoch 5 - iter 26/138 - loss 0.03221155 - time (sec): 1.38 - samples/sec: 2885.15 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:19:21,922 epoch 5 - iter 39/138 - loss 0.03577119 - time (sec): 2.13 - samples/sec: 2999.40 - lr: 0.000032 - momentum: 0.000000
2023-10-13 08:19:22,647 epoch 5 - iter 52/138 - loss 0.04000067 - time (sec): 2.86 - samples/sec: 3018.36 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:19:23,435 epoch 5 - iter 65/138 - loss 0.04109399 - time (sec): 3.65 - samples/sec: 3003.21 - lr: 0.000031 - momentum: 0.000000
2023-10-13 08:19:24,174 epoch 5 - iter 78/138 - loss 0.04030136 - time (sec): 4.39 - samples/sec: 3024.11 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:19:24,887 epoch 5 - iter 91/138 - loss 0.04252457 - time (sec): 5.10 - samples/sec: 3003.16 - lr: 0.000030 - momentum: 0.000000
2023-10-13 08:19:25,575 epoch 5 - iter 104/138 - loss 0.04785958 - time (sec): 5.79 - samples/sec: 2990.90 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:19:26,315 epoch 5 - iter 117/138 - loss 0.05214743 - time (sec): 6.53 - samples/sec: 2985.14 - lr: 0.000029 - momentum: 0.000000
2023-10-13 08:19:27,024 epoch 5 - iter 130/138 - loss 0.05201815 - time (sec): 7.24 - samples/sec: 2968.00 - lr: 0.000028 - momentum: 0.000000
2023-10-13 08:19:27,473 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:27,474 EPOCH 5 done: loss 0.0509 - lr: 0.000028
2023-10-13 08:19:28,153 DEV : loss 0.12619180977344513 - f1-score (micro avg) 0.8616
2023-10-13 08:19:28,158 saving best model
2023-10-13 08:19:28,572 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:29,300 epoch 6 - iter 13/138 - loss 0.03249176 - time (sec): 0.72 - samples/sec: 2647.19 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:19:30,065 epoch 6 - iter 26/138 - loss 0.04087283 - time (sec): 1.49 - samples/sec: 2782.72 - lr: 0.000027 - momentum: 0.000000
2023-10-13 08:19:30,792 epoch 6 - iter 39/138 - loss 0.03129313 - time (sec): 2.22 - samples/sec: 2835.49 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:19:31,514 epoch 6 - iter 52/138 - loss 0.04084296 - time (sec): 2.94 - samples/sec: 2897.95 - lr: 0.000026 - momentum: 0.000000
2023-10-13 08:19:32,211 epoch 6 - iter 65/138 - loss 0.03888486 - time (sec): 3.64 - samples/sec: 2915.67 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:19:32,928 epoch 6 - iter 78/138 - loss 0.03995297 - time (sec): 4.35 - samples/sec: 2923.81 - lr: 0.000025 - momentum: 0.000000
2023-10-13 08:19:33,701 epoch 6 - iter 91/138 - loss 0.03603623 - time (sec): 5.13 - samples/sec: 2943.54 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:19:34,443 epoch 6 - iter 104/138 - loss 0.03370356 - time (sec): 5.87 - samples/sec: 2909.69 - lr: 0.000024 - momentum: 0.000000
2023-10-13 08:19:35,220 epoch 6 - iter 117/138 - loss 0.03376515 - time (sec): 6.65 - samples/sec: 2903.31 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:19:35,946 epoch 6 - iter 130/138 - loss 0.03817809 - time (sec): 7.37 - samples/sec: 2911.05 - lr: 0.000023 - momentum: 0.000000
2023-10-13 08:19:36,414 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:36,415 EPOCH 6 done: loss 0.0381 - lr: 0.000023
2023-10-13 08:19:37,126 DEV : loss 0.1473054736852646 - f1-score (micro avg) 0.8674
2023-10-13 08:19:37,132 saving best model
2023-10-13 08:19:37,583 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:38,371 epoch 7 - iter 13/138 - loss 0.01997817 - time (sec): 0.78 - samples/sec: 3006.86 - lr: 0.000022 - momentum: 0.000000
2023-10-13 08:19:39,068 epoch 7 - iter 26/138 - loss 0.02454367 - time (sec): 1.48 - samples/sec: 2879.53 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:19:39,717 epoch 7 - iter 39/138 - loss 0.01992186 - time (sec): 2.13 - samples/sec: 2893.57 - lr: 0.000021 - momentum: 0.000000
2023-10-13 08:19:40,457 epoch 7 - iter 52/138 - loss 0.02502743 - time (sec): 2.87 - samples/sec: 2922.55 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:19:41,140 epoch 7 - iter 65/138 - loss 0.03753523 - time (sec): 3.55 - samples/sec: 2902.17 - lr: 0.000020 - momentum: 0.000000
2023-10-13 08:19:41,896 epoch 7 - iter 78/138 - loss 0.03107997 - time (sec): 4.30 - samples/sec: 2926.49 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:19:42,589 epoch 7 - iter 91/138 - loss 0.02773132 - time (sec): 5.00 - samples/sec: 2925.34 - lr: 0.000019 - momentum: 0.000000
2023-10-13 08:19:43,372 epoch 7 - iter 104/138 - loss 0.02730363 - time (sec): 5.78 - samples/sec: 2945.17 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:19:44,061 epoch 7 - iter 117/138 - loss 0.02855620 - time (sec): 6.47 - samples/sec: 2944.97 - lr: 0.000018 - momentum: 0.000000
2023-10-13 08:19:44,758 epoch 7 - iter 130/138 - loss 0.02921022 - time (sec): 7.17 - samples/sec: 2966.83 - lr: 0.000017 - momentum: 0.000000
2023-10-13 08:19:45,225 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:45,225 EPOCH 7 done: loss 0.0291 - lr: 0.000017
2023-10-13 08:19:45,890 DEV : loss 0.15323472023010254 - f1-score (micro avg) 0.8816
2023-10-13 08:19:45,895 saving best model
2023-10-13 08:19:46,305 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:47,051 epoch 8 - iter 13/138 - loss 0.02038702 - time (sec): 0.74 - samples/sec: 3037.11 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:19:47,801 epoch 8 - iter 26/138 - loss 0.01412744 - time (sec): 1.49 - samples/sec: 2977.30 - lr: 0.000016 - momentum: 0.000000
2023-10-13 08:19:48,567 epoch 8 - iter 39/138 - loss 0.02947389 - time (sec): 2.26 - samples/sec: 2865.50 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:19:49,279 epoch 8 - iter 52/138 - loss 0.02461736 - time (sec): 2.97 - samples/sec: 2874.74 - lr: 0.000015 - momentum: 0.000000
2023-10-13 08:19:49,978 epoch 8 - iter 65/138 - loss 0.02189776 - time (sec): 3.67 - samples/sec: 2919.69 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:19:50,680 epoch 8 - iter 78/138 - loss 0.02300181 - time (sec): 4.37 - samples/sec: 2913.35 - lr: 0.000014 - momentum: 0.000000
2023-10-13 08:19:51,401 epoch 8 - iter 91/138 - loss 0.02120278 - time (sec): 5.09 - samples/sec: 2943.64 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:19:52,092 epoch 8 - iter 104/138 - loss 0.02079869 - time (sec): 5.78 - samples/sec: 2947.80 - lr: 0.000013 - momentum: 0.000000
2023-10-13 08:19:52,867 epoch 8 - iter 117/138 - loss 0.02160055 - time (sec): 6.56 - samples/sec: 2934.89 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:19:53,596 epoch 8 - iter 130/138 - loss 0.02068289 - time (sec): 7.29 - samples/sec: 2940.32 - lr: 0.000012 - momentum: 0.000000
2023-10-13 08:19:54,067 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:54,068 EPOCH 8 done: loss 0.0204 - lr: 0.000012
2023-10-13 08:19:54,835 DEV : loss 0.1583411544561386 - f1-score (micro avg) 0.869
2023-10-13 08:19:54,841 ----------------------------------------------------------------------------------------------------
2023-10-13 08:19:55,621 epoch 9 - iter 13/138 - loss 0.00691619 - time (sec): 0.78 - samples/sec: 2842.13 - lr: 0.000011 - momentum: 0.000000
2023-10-13 08:19:56,322 epoch 9 - iter 26/138 - loss 0.01096592 - time (sec): 1.48 - samples/sec: 2899.25 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:19:57,137 epoch 9 - iter 39/138 - loss 0.01429396 - time (sec): 2.29 - samples/sec: 2944.59 - lr: 0.000010 - momentum: 0.000000
2023-10-13 08:19:57,879 epoch 9 - iter 52/138 - loss 0.01763747 - time (sec): 3.04 - samples/sec: 2938.06 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:19:58,620 epoch 9 - iter 65/138 - loss 0.01457269 - time (sec): 3.78 - samples/sec: 2921.83 - lr: 0.000009 - momentum: 0.000000
2023-10-13 08:19:59,360 epoch 9 - iter 78/138 - loss 0.01700158 - time (sec): 4.52 - samples/sec: 2974.50 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:20:00,073 epoch 9 - iter 91/138 - loss 0.01610376 - time (sec): 5.23 - samples/sec: 2951.92 - lr: 0.000008 - momentum: 0.000000
2023-10-13 08:20:00,816 epoch 9 - iter 104/138 - loss 0.01519905 - time (sec): 5.97 - samples/sec: 2916.25 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:20:01,535 epoch 9 - iter 117/138 - loss 0.01372095 - time (sec): 6.69 - samples/sec: 2900.86 - lr: 0.000007 - momentum: 0.000000
2023-10-13 08:20:02,235 epoch 9 - iter 130/138 - loss 0.01660732 - time (sec): 7.39 - samples/sec: 2934.46 - lr: 0.000006 - momentum: 0.000000
2023-10-13 08:20:02,642 ----------------------------------------------------------------------------------------------------
2023-10-13 08:20:02,642 EPOCH 9 done: loss 0.0164 - lr: 0.000006
2023-10-13 08:20:03,404 DEV : loss 0.15242387354373932 - f1-score (micro avg) 0.8786
2023-10-13 08:20:03,409 ----------------------------------------------------------------------------------------------------
2023-10-13 08:20:04,151 epoch 10 - iter 13/138 - loss 0.00567269 - time (sec): 0.74 - samples/sec: 2961.98 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:20:04,915 epoch 10 - iter 26/138 - loss 0.00887180 - time (sec): 1.50 - samples/sec: 3105.29 - lr: 0.000005 - momentum: 0.000000
2023-10-13 08:20:05,704 epoch 10 - iter 39/138 - loss 0.00671609 - time (sec): 2.29 - samples/sec: 2986.45 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:20:06,488 epoch 10 - iter 52/138 - loss 0.00747113 - time (sec): 3.08 - samples/sec: 2893.02 - lr: 0.000004 - momentum: 0.000000
2023-10-13 08:20:07,205 epoch 10 - iter 65/138 - loss 0.00834283 - time (sec): 3.79 - samples/sec: 2944.79 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:20:07,910 epoch 10 - iter 78/138 - loss 0.00826691 - time (sec): 4.50 - samples/sec: 2948.72 - lr: 0.000003 - momentum: 0.000000
2023-10-13 08:20:08,616 epoch 10 - iter 91/138 - loss 0.00802626 - time (sec): 5.21 - samples/sec: 2922.30 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:20:09,384 epoch 10 - iter 104/138 - loss 0.00935538 - time (sec): 5.97 - samples/sec: 2900.14 - lr: 0.000002 - momentum: 0.000000
2023-10-13 08:20:10,136 epoch 10 - iter 117/138 - loss 0.01226645 - time (sec): 6.73 - samples/sec: 2892.25 - lr: 0.000001 - momentum: 0.000000
2023-10-13 08:20:10,897 epoch 10 - iter 130/138 - loss 0.01177825 - time (sec): 7.49 - samples/sec: 2888.89 - lr: 0.000000 - momentum: 0.000000
2023-10-13 08:20:11,295 ----------------------------------------------------------------------------------------------------
2023-10-13 08:20:11,295 EPOCH 10 done: loss 0.0113 - lr: 0.000000
2023-10-13 08:20:12,004 DEV : loss 0.15443024039268494 - f1-score (micro avg) 0.8786
2023-10-13 08:20:12,332 ----------------------------------------------------------------------------------------------------
2023-10-13 08:20:12,333 Loading model from best epoch ...
2023-10-13 08:20:13,698 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
2023-10-13 08:20:14,577
Results:
- F-score (micro) 0.9155
- F-score (macro) 0.806
- Accuracy 0.8564
By class:
precision recall f1-score support
scope 0.8962 0.9318 0.9136 176
pers 0.9609 0.9609 0.9609 128
work 0.8732 0.8378 0.8552 74
loc 0.6667 1.0000 0.8000 2
object 0.5000 0.5000 0.5000 2
micro avg 0.9096 0.9215 0.9155 382
macro avg 0.7794 0.8461 0.8060 382
weighted avg 0.9102 0.9215 0.9154 382
2023-10-13 08:20:14,577 ----------------------------------------------------------------------------------------------------
|