File size: 23,906 Bytes
b743d26 |
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 |
2023-10-18 16:37:46,705 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 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 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 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 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 Train: 966 sentences
2023-10-18 16:37:46,706 (train_with_dev=False, train_with_test=False)
2023-10-18 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 Training Params:
2023-10-18 16:37:46,706 - learning_rate: "5e-05"
2023-10-18 16:37:46,706 - mini_batch_size: "8"
2023-10-18 16:37:46,706 - max_epochs: "10"
2023-10-18 16:37:46,706 - shuffle: "True"
2023-10-18 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 Plugins:
2023-10-18 16:37:46,706 - TensorboardLogger
2023-10-18 16:37:46,706 - LinearScheduler | warmup_fraction: '0.1'
2023-10-18 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 Final evaluation on model from best epoch (best-model.pt)
2023-10-18 16:37:46,706 - metric: "('micro avg', 'f1-score')"
2023-10-18 16:37:46,706 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,706 Computation:
2023-10-18 16:37:46,707 - compute on device: cuda:0
2023-10-18 16:37:46,707 - embedding storage: none
2023-10-18 16:37:46,707 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,707 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-18 16:37:46,707 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,707 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:46,707 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-18 16:37:46,983 epoch 1 - iter 12/121 - loss 4.06423244 - time (sec): 0.28 - samples/sec: 9156.40 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:37:47,262 epoch 1 - iter 24/121 - loss 3.89967677 - time (sec): 0.55 - samples/sec: 8881.22 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:37:47,552 epoch 1 - iter 36/121 - loss 3.84560872 - time (sec): 0.84 - samples/sec: 8947.53 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:37:47,838 epoch 1 - iter 48/121 - loss 3.71254191 - time (sec): 1.13 - samples/sec: 9182.28 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:37:48,099 epoch 1 - iter 60/121 - loss 3.57296790 - time (sec): 1.39 - samples/sec: 8964.72 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:37:48,369 epoch 1 - iter 72/121 - loss 3.42366005 - time (sec): 1.66 - samples/sec: 8935.77 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:37:48,633 epoch 1 - iter 84/121 - loss 3.24611854 - time (sec): 1.93 - samples/sec: 8911.86 - lr: 0.000034 - momentum: 0.000000
2023-10-18 16:37:48,899 epoch 1 - iter 96/121 - loss 3.03337096 - time (sec): 2.19 - samples/sec: 8930.89 - lr: 0.000039 - momentum: 0.000000
2023-10-18 16:37:49,163 epoch 1 - iter 108/121 - loss 2.81189925 - time (sec): 2.46 - samples/sec: 9074.53 - lr: 0.000044 - momentum: 0.000000
2023-10-18 16:37:49,435 epoch 1 - iter 120/121 - loss 2.63276419 - time (sec): 2.73 - samples/sec: 8999.91 - lr: 0.000049 - momentum: 0.000000
2023-10-18 16:37:49,455 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:49,455 EPOCH 1 done: loss 2.6200 - lr: 0.000049
2023-10-18 16:37:49,966 DEV : loss 0.6585149765014648 - f1-score (micro avg) 0.0
2023-10-18 16:37:49,970 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:50,235 epoch 2 - iter 12/121 - loss 0.79443559 - time (sec): 0.26 - samples/sec: 9359.92 - lr: 0.000049 - momentum: 0.000000
2023-10-18 16:37:50,516 epoch 2 - iter 24/121 - loss 0.81201782 - time (sec): 0.54 - samples/sec: 9591.10 - lr: 0.000049 - momentum: 0.000000
2023-10-18 16:37:50,789 epoch 2 - iter 36/121 - loss 0.76364936 - time (sec): 0.82 - samples/sec: 9742.55 - lr: 0.000048 - momentum: 0.000000
2023-10-18 16:37:51,053 epoch 2 - iter 48/121 - loss 0.73351545 - time (sec): 1.08 - samples/sec: 9830.85 - lr: 0.000048 - momentum: 0.000000
2023-10-18 16:37:51,306 epoch 2 - iter 60/121 - loss 0.72650713 - time (sec): 1.33 - samples/sec: 9403.27 - lr: 0.000047 - momentum: 0.000000
2023-10-18 16:37:51,569 epoch 2 - iter 72/121 - loss 0.71917414 - time (sec): 1.60 - samples/sec: 9209.16 - lr: 0.000047 - momentum: 0.000000
2023-10-18 16:37:51,857 epoch 2 - iter 84/121 - loss 0.71563670 - time (sec): 1.89 - samples/sec: 9047.31 - lr: 0.000046 - momentum: 0.000000
2023-10-18 16:37:52,141 epoch 2 - iter 96/121 - loss 0.71831549 - time (sec): 2.17 - samples/sec: 9064.31 - lr: 0.000046 - momentum: 0.000000
2023-10-18 16:37:52,417 epoch 2 - iter 108/121 - loss 0.70583269 - time (sec): 2.45 - samples/sec: 9050.50 - lr: 0.000045 - momentum: 0.000000
2023-10-18 16:37:52,694 epoch 2 - iter 120/121 - loss 0.68450949 - time (sec): 2.72 - samples/sec: 9031.31 - lr: 0.000045 - momentum: 0.000000
2023-10-18 16:37:52,716 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:52,716 EPOCH 2 done: loss 0.6847 - lr: 0.000045
2023-10-18 16:37:53,147 DEV : loss 0.5573856234550476 - f1-score (micro avg) 0.0
2023-10-18 16:37:53,152 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:53,431 epoch 3 - iter 12/121 - loss 0.57685052 - time (sec): 0.28 - samples/sec: 8896.62 - lr: 0.000044 - momentum: 0.000000
2023-10-18 16:37:53,691 epoch 3 - iter 24/121 - loss 0.59677529 - time (sec): 0.54 - samples/sec: 8619.78 - lr: 0.000043 - momentum: 0.000000
2023-10-18 16:37:53,962 epoch 3 - iter 36/121 - loss 0.62216977 - time (sec): 0.81 - samples/sec: 8603.50 - lr: 0.000043 - momentum: 0.000000
2023-10-18 16:37:54,232 epoch 3 - iter 48/121 - loss 0.61021734 - time (sec): 1.08 - samples/sec: 8793.59 - lr: 0.000042 - momentum: 0.000000
2023-10-18 16:37:54,507 epoch 3 - iter 60/121 - loss 0.60690012 - time (sec): 1.36 - samples/sec: 8787.69 - lr: 0.000042 - momentum: 0.000000
2023-10-18 16:37:54,781 epoch 3 - iter 72/121 - loss 0.57933023 - time (sec): 1.63 - samples/sec: 8993.46 - lr: 0.000041 - momentum: 0.000000
2023-10-18 16:37:55,051 epoch 3 - iter 84/121 - loss 0.57146458 - time (sec): 1.90 - samples/sec: 9003.22 - lr: 0.000041 - momentum: 0.000000
2023-10-18 16:37:55,325 epoch 3 - iter 96/121 - loss 0.56608970 - time (sec): 2.17 - samples/sec: 8961.15 - lr: 0.000040 - momentum: 0.000000
2023-10-18 16:37:55,601 epoch 3 - iter 108/121 - loss 0.55476563 - time (sec): 2.45 - samples/sec: 9013.13 - lr: 0.000040 - momentum: 0.000000
2023-10-18 16:37:55,881 epoch 3 - iter 120/121 - loss 0.55137957 - time (sec): 2.73 - samples/sec: 8992.62 - lr: 0.000039 - momentum: 0.000000
2023-10-18 16:37:55,904 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:55,904 EPOCH 3 done: loss 0.5512 - lr: 0.000039
2023-10-18 16:37:56,333 DEV : loss 0.42163369059562683 - f1-score (micro avg) 0.2788
2023-10-18 16:37:56,337 saving best model
2023-10-18 16:37:56,366 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:56,647 epoch 4 - iter 12/121 - loss 0.54623942 - time (sec): 0.28 - samples/sec: 9667.83 - lr: 0.000038 - momentum: 0.000000
2023-10-18 16:37:56,927 epoch 4 - iter 24/121 - loss 0.50675691 - time (sec): 0.56 - samples/sec: 8891.17 - lr: 0.000038 - momentum: 0.000000
2023-10-18 16:37:57,194 epoch 4 - iter 36/121 - loss 0.49893346 - time (sec): 0.83 - samples/sec: 8816.67 - lr: 0.000037 - momentum: 0.000000
2023-10-18 16:37:57,468 epoch 4 - iter 48/121 - loss 0.48315990 - time (sec): 1.10 - samples/sec: 8837.45 - lr: 0.000037 - momentum: 0.000000
2023-10-18 16:37:57,752 epoch 4 - iter 60/121 - loss 0.47606222 - time (sec): 1.39 - samples/sec: 9010.30 - lr: 0.000036 - momentum: 0.000000
2023-10-18 16:37:58,025 epoch 4 - iter 72/121 - loss 0.46853704 - time (sec): 1.66 - samples/sec: 8954.16 - lr: 0.000036 - momentum: 0.000000
2023-10-18 16:37:58,294 epoch 4 - iter 84/121 - loss 0.45908363 - time (sec): 1.93 - samples/sec: 8907.61 - lr: 0.000035 - momentum: 0.000000
2023-10-18 16:37:58,567 epoch 4 - iter 96/121 - loss 0.45593541 - time (sec): 2.20 - samples/sec: 9001.07 - lr: 0.000035 - momentum: 0.000000
2023-10-18 16:37:58,829 epoch 4 - iter 108/121 - loss 0.46075997 - time (sec): 2.46 - samples/sec: 9004.61 - lr: 0.000034 - momentum: 0.000000
2023-10-18 16:37:59,109 epoch 4 - iter 120/121 - loss 0.45718074 - time (sec): 2.74 - samples/sec: 8973.14 - lr: 0.000034 - momentum: 0.000000
2023-10-18 16:37:59,127 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:59,128 EPOCH 4 done: loss 0.4567 - lr: 0.000034
2023-10-18 16:37:59,559 DEV : loss 0.3446199297904968 - f1-score (micro avg) 0.4725
2023-10-18 16:37:59,563 saving best model
2023-10-18 16:37:59,597 ----------------------------------------------------------------------------------------------------
2023-10-18 16:37:59,856 epoch 5 - iter 12/121 - loss 0.41508969 - time (sec): 0.26 - samples/sec: 9044.81 - lr: 0.000033 - momentum: 0.000000
2023-10-18 16:38:00,125 epoch 5 - iter 24/121 - loss 0.42994677 - time (sec): 0.53 - samples/sec: 9060.25 - lr: 0.000032 - momentum: 0.000000
2023-10-18 16:38:00,394 epoch 5 - iter 36/121 - loss 0.41473805 - time (sec): 0.80 - samples/sec: 8980.16 - lr: 0.000032 - momentum: 0.000000
2023-10-18 16:38:00,679 epoch 5 - iter 48/121 - loss 0.40379782 - time (sec): 1.08 - samples/sec: 9215.40 - lr: 0.000031 - momentum: 0.000000
2023-10-18 16:38:00,951 epoch 5 - iter 60/121 - loss 0.40918990 - time (sec): 1.35 - samples/sec: 9280.53 - lr: 0.000031 - momentum: 0.000000
2023-10-18 16:38:01,228 epoch 5 - iter 72/121 - loss 0.40526997 - time (sec): 1.63 - samples/sec: 9214.71 - lr: 0.000030 - momentum: 0.000000
2023-10-18 16:38:01,493 epoch 5 - iter 84/121 - loss 0.40300316 - time (sec): 1.90 - samples/sec: 9127.93 - lr: 0.000030 - momentum: 0.000000
2023-10-18 16:38:01,763 epoch 5 - iter 96/121 - loss 0.39720734 - time (sec): 2.17 - samples/sec: 9178.51 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:38:02,034 epoch 5 - iter 108/121 - loss 0.40050812 - time (sec): 2.44 - samples/sec: 9133.80 - lr: 0.000029 - momentum: 0.000000
2023-10-18 16:38:02,305 epoch 5 - iter 120/121 - loss 0.39605476 - time (sec): 2.71 - samples/sec: 9086.62 - lr: 0.000028 - momentum: 0.000000
2023-10-18 16:38:02,322 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:02,322 EPOCH 5 done: loss 0.3973 - lr: 0.000028
2023-10-18 16:38:02,752 DEV : loss 0.3135037422180176 - f1-score (micro avg) 0.4919
2023-10-18 16:38:02,756 saving best model
2023-10-18 16:38:02,789 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:03,066 epoch 6 - iter 12/121 - loss 0.35254438 - time (sec): 0.28 - samples/sec: 9292.40 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:38:03,341 epoch 6 - iter 24/121 - loss 0.36693620 - time (sec): 0.55 - samples/sec: 9320.89 - lr: 0.000027 - momentum: 0.000000
2023-10-18 16:38:03,609 epoch 6 - iter 36/121 - loss 0.36194737 - time (sec): 0.82 - samples/sec: 9335.62 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:38:03,900 epoch 6 - iter 48/121 - loss 0.37128051 - time (sec): 1.11 - samples/sec: 9156.22 - lr: 0.000026 - momentum: 0.000000
2023-10-18 16:38:04,178 epoch 6 - iter 60/121 - loss 0.36331801 - time (sec): 1.39 - samples/sec: 9133.13 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:38:04,448 epoch 6 - iter 72/121 - loss 0.35824236 - time (sec): 1.66 - samples/sec: 9138.92 - lr: 0.000025 - momentum: 0.000000
2023-10-18 16:38:04,717 epoch 6 - iter 84/121 - loss 0.35498454 - time (sec): 1.93 - samples/sec: 9010.20 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:38:04,989 epoch 6 - iter 96/121 - loss 0.36536908 - time (sec): 2.20 - samples/sec: 9007.78 - lr: 0.000024 - momentum: 0.000000
2023-10-18 16:38:05,265 epoch 6 - iter 108/121 - loss 0.37179129 - time (sec): 2.47 - samples/sec: 9011.06 - lr: 0.000023 - momentum: 0.000000
2023-10-18 16:38:05,560 epoch 6 - iter 120/121 - loss 0.36874895 - time (sec): 2.77 - samples/sec: 8883.11 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:38:05,578 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:05,578 EPOCH 6 done: loss 0.3670 - lr: 0.000022
2023-10-18 16:38:06,011 DEV : loss 0.29502981901168823 - f1-score (micro avg) 0.4904
2023-10-18 16:38:06,015 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:06,311 epoch 7 - iter 12/121 - loss 0.33538454 - time (sec): 0.30 - samples/sec: 9443.11 - lr: 0.000022 - momentum: 0.000000
2023-10-18 16:38:06,601 epoch 7 - iter 24/121 - loss 0.33269331 - time (sec): 0.59 - samples/sec: 9015.43 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:38:06,886 epoch 7 - iter 36/121 - loss 0.34057186 - time (sec): 0.87 - samples/sec: 8808.40 - lr: 0.000021 - momentum: 0.000000
2023-10-18 16:38:07,164 epoch 7 - iter 48/121 - loss 0.35006255 - time (sec): 1.15 - samples/sec: 8665.54 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:38:07,447 epoch 7 - iter 60/121 - loss 0.35051450 - time (sec): 1.43 - samples/sec: 8554.00 - lr: 0.000020 - momentum: 0.000000
2023-10-18 16:38:07,731 epoch 7 - iter 72/121 - loss 0.34679089 - time (sec): 1.72 - samples/sec: 8497.45 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:38:08,016 epoch 7 - iter 84/121 - loss 0.34961647 - time (sec): 2.00 - samples/sec: 8541.49 - lr: 0.000019 - momentum: 0.000000
2023-10-18 16:38:08,294 epoch 7 - iter 96/121 - loss 0.35121463 - time (sec): 2.28 - samples/sec: 8601.73 - lr: 0.000018 - momentum: 0.000000
2023-10-18 16:38:08,581 epoch 7 - iter 108/121 - loss 0.35352437 - time (sec): 2.57 - samples/sec: 8606.00 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:38:08,861 epoch 7 - iter 120/121 - loss 0.35152520 - time (sec): 2.84 - samples/sec: 8645.20 - lr: 0.000017 - momentum: 0.000000
2023-10-18 16:38:08,881 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:08,881 EPOCH 7 done: loss 0.3518 - lr: 0.000017
2023-10-18 16:38:09,312 DEV : loss 0.28431111574172974 - f1-score (micro avg) 0.4868
2023-10-18 16:38:09,316 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:09,610 epoch 8 - iter 12/121 - loss 0.47161874 - time (sec): 0.29 - samples/sec: 9319.18 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:38:09,888 epoch 8 - iter 24/121 - loss 0.39663415 - time (sec): 0.57 - samples/sec: 8686.15 - lr: 0.000016 - momentum: 0.000000
2023-10-18 16:38:10,184 epoch 8 - iter 36/121 - loss 0.37145716 - time (sec): 0.87 - samples/sec: 8550.75 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:38:10,456 epoch 8 - iter 48/121 - loss 0.35177998 - time (sec): 1.14 - samples/sec: 8736.95 - lr: 0.000015 - momentum: 0.000000
2023-10-18 16:38:10,738 epoch 8 - iter 60/121 - loss 0.34654712 - time (sec): 1.42 - samples/sec: 8830.25 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:38:11,013 epoch 8 - iter 72/121 - loss 0.34061403 - time (sec): 1.70 - samples/sec: 8720.62 - lr: 0.000014 - momentum: 0.000000
2023-10-18 16:38:11,301 epoch 8 - iter 84/121 - loss 0.33533672 - time (sec): 1.98 - samples/sec: 8702.28 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:38:11,582 epoch 8 - iter 96/121 - loss 0.33895771 - time (sec): 2.27 - samples/sec: 8751.23 - lr: 0.000013 - momentum: 0.000000
2023-10-18 16:38:11,865 epoch 8 - iter 108/121 - loss 0.34448416 - time (sec): 2.55 - samples/sec: 8773.46 - lr: 0.000012 - momentum: 0.000000
2023-10-18 16:38:12,143 epoch 8 - iter 120/121 - loss 0.34155459 - time (sec): 2.83 - samples/sec: 8715.12 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:38:12,162 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:12,162 EPOCH 8 done: loss 0.3409 - lr: 0.000011
2023-10-18 16:38:12,600 DEV : loss 0.277322381734848 - f1-score (micro avg) 0.4874
2023-10-18 16:38:12,604 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:12,826 epoch 9 - iter 12/121 - loss 0.36612372 - time (sec): 0.22 - samples/sec: 10690.18 - lr: 0.000011 - momentum: 0.000000
2023-10-18 16:38:13,049 epoch 9 - iter 24/121 - loss 0.35162201 - time (sec): 0.44 - samples/sec: 10550.48 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:38:13,291 epoch 9 - iter 36/121 - loss 0.34091714 - time (sec): 0.69 - samples/sec: 10582.62 - lr: 0.000010 - momentum: 0.000000
2023-10-18 16:38:13,549 epoch 9 - iter 48/121 - loss 0.32767882 - time (sec): 0.94 - samples/sec: 10136.48 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:38:13,819 epoch 9 - iter 60/121 - loss 0.33057948 - time (sec): 1.21 - samples/sec: 9924.73 - lr: 0.000009 - momentum: 0.000000
2023-10-18 16:38:14,083 epoch 9 - iter 72/121 - loss 0.32622971 - time (sec): 1.48 - samples/sec: 9892.74 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:38:14,356 epoch 9 - iter 84/121 - loss 0.33658856 - time (sec): 1.75 - samples/sec: 9768.35 - lr: 0.000008 - momentum: 0.000000
2023-10-18 16:38:14,633 epoch 9 - iter 96/121 - loss 0.33404051 - time (sec): 2.03 - samples/sec: 9642.83 - lr: 0.000007 - momentum: 0.000000
2023-10-18 16:38:14,922 epoch 9 - iter 108/121 - loss 0.32949463 - time (sec): 2.32 - samples/sec: 9555.83 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:38:15,203 epoch 9 - iter 120/121 - loss 0.32480974 - time (sec): 2.60 - samples/sec: 9472.42 - lr: 0.000006 - momentum: 0.000000
2023-10-18 16:38:15,221 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:15,221 EPOCH 9 done: loss 0.3259 - lr: 0.000006
2023-10-18 16:38:15,664 DEV : loss 0.2769020199775696 - f1-score (micro avg) 0.485
2023-10-18 16:38:15,669 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:15,941 epoch 10 - iter 12/121 - loss 0.31703877 - time (sec): 0.27 - samples/sec: 7708.05 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:38:16,205 epoch 10 - iter 24/121 - loss 0.32343603 - time (sec): 0.54 - samples/sec: 8437.40 - lr: 0.000005 - momentum: 0.000000
2023-10-18 16:38:16,478 epoch 10 - iter 36/121 - loss 0.32421369 - time (sec): 0.81 - samples/sec: 8652.52 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:38:16,753 epoch 10 - iter 48/121 - loss 0.33412753 - time (sec): 1.08 - samples/sec: 8854.06 - lr: 0.000004 - momentum: 0.000000
2023-10-18 16:38:17,025 epoch 10 - iter 60/121 - loss 0.32558920 - time (sec): 1.36 - samples/sec: 8915.05 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:38:17,304 epoch 10 - iter 72/121 - loss 0.31995198 - time (sec): 1.63 - samples/sec: 8966.51 - lr: 0.000003 - momentum: 0.000000
2023-10-18 16:38:17,583 epoch 10 - iter 84/121 - loss 0.33265760 - time (sec): 1.91 - samples/sec: 8922.66 - lr: 0.000002 - momentum: 0.000000
2023-10-18 16:38:17,849 epoch 10 - iter 96/121 - loss 0.33878559 - time (sec): 2.18 - samples/sec: 8962.03 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:38:18,113 epoch 10 - iter 108/121 - loss 0.33332984 - time (sec): 2.44 - samples/sec: 8989.20 - lr: 0.000001 - momentum: 0.000000
2023-10-18 16:38:18,396 epoch 10 - iter 120/121 - loss 0.32884184 - time (sec): 2.73 - samples/sec: 9047.08 - lr: 0.000000 - momentum: 0.000000
2023-10-18 16:38:18,413 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:18,413 EPOCH 10 done: loss 0.3288 - lr: 0.000000
2023-10-18 16:38:18,841 DEV : loss 0.2749263644218445 - f1-score (micro avg) 0.4808
2023-10-18 16:38:18,876 ----------------------------------------------------------------------------------------------------
2023-10-18 16:38:18,876 Loading model from best epoch ...
2023-10-18 16:38:18,958 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 16:38:19,355
Results:
- F-score (micro) 0.4391
- F-score (macro) 0.2022
- Accuracy 0.2964
By class:
precision recall f1-score support
scope 0.3500 0.4884 0.4078 129
pers 0.5542 0.6619 0.6033 139
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 0.4480 0.4306 0.4391 360
macro avg 0.1808 0.2300 0.2022 360
weighted avg 0.3394 0.4306 0.3790 360
2023-10-18 16:38:19,355 ----------------------------------------------------------------------------------------------------
|