File size: 24,035 Bytes
d712a65 |
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 |
2023-10-14 19:54:42,062 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,063 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=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-14 19:54:42,063 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
- NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Train: 14465 sentences
2023-10-14 19:54:42,064 (train_with_dev=False, train_with_test=False)
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Training Params:
2023-10-14 19:54:42,064 - learning_rate: "5e-05"
2023-10-14 19:54:42,064 - mini_batch_size: "8"
2023-10-14 19:54:42,064 - max_epochs: "10"
2023-10-14 19:54:42,064 - shuffle: "True"
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Plugins:
2023-10-14 19:54:42,064 - LinearScheduler | warmup_fraction: '0.1'
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Final evaluation on model from best epoch (best-model.pt)
2023-10-14 19:54:42,064 - metric: "('micro avg', 'f1-score')"
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Computation:
2023-10-14 19:54:42,064 - compute on device: cuda:0
2023-10-14 19:54:42,064 - embedding storage: none
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:42,064 ----------------------------------------------------------------------------------------------------
2023-10-14 19:54:53,413 epoch 1 - iter 180/1809 - loss 1.52200951 - time (sec): 11.35 - samples/sec: 3372.05 - lr: 0.000005 - momentum: 0.000000
2023-10-14 19:55:04,616 epoch 1 - iter 360/1809 - loss 0.86831072 - time (sec): 22.55 - samples/sec: 3369.01 - lr: 0.000010 - momentum: 0.000000
2023-10-14 19:55:16,043 epoch 1 - iter 540/1809 - loss 0.63472441 - time (sec): 33.98 - samples/sec: 3341.10 - lr: 0.000015 - momentum: 0.000000
2023-10-14 19:55:27,315 epoch 1 - iter 720/1809 - loss 0.50459405 - time (sec): 45.25 - samples/sec: 3369.27 - lr: 0.000020 - momentum: 0.000000
2023-10-14 19:55:38,557 epoch 1 - iter 900/1809 - loss 0.42878307 - time (sec): 56.49 - samples/sec: 3361.57 - lr: 0.000025 - momentum: 0.000000
2023-10-14 19:55:49,637 epoch 1 - iter 1080/1809 - loss 0.37737077 - time (sec): 67.57 - samples/sec: 3365.97 - lr: 0.000030 - momentum: 0.000000
2023-10-14 19:56:00,758 epoch 1 - iter 1260/1809 - loss 0.33903493 - time (sec): 78.69 - samples/sec: 3358.41 - lr: 0.000035 - momentum: 0.000000
2023-10-14 19:56:11,947 epoch 1 - iter 1440/1809 - loss 0.30859986 - time (sec): 89.88 - samples/sec: 3380.66 - lr: 0.000040 - momentum: 0.000000
2023-10-14 19:56:23,049 epoch 1 - iter 1620/1809 - loss 0.28703340 - time (sec): 100.98 - samples/sec: 3376.84 - lr: 0.000045 - momentum: 0.000000
2023-10-14 19:56:34,342 epoch 1 - iter 1800/1809 - loss 0.26826484 - time (sec): 112.28 - samples/sec: 3369.33 - lr: 0.000050 - momentum: 0.000000
2023-10-14 19:56:34,848 ----------------------------------------------------------------------------------------------------
2023-10-14 19:56:34,848 EPOCH 1 done: loss 0.2674 - lr: 0.000050
2023-10-14 19:56:40,094 DEV : loss 0.11045825481414795 - f1-score (micro avg) 0.5787
2023-10-14 19:56:40,133 saving best model
2023-10-14 19:56:40,519 ----------------------------------------------------------------------------------------------------
2023-10-14 19:56:52,597 epoch 2 - iter 180/1809 - loss 0.08253900 - time (sec): 12.08 - samples/sec: 3148.77 - lr: 0.000049 - momentum: 0.000000
2023-10-14 19:57:03,849 epoch 2 - iter 360/1809 - loss 0.08121285 - time (sec): 23.33 - samples/sec: 3260.77 - lr: 0.000049 - momentum: 0.000000
2023-10-14 19:57:15,405 epoch 2 - iter 540/1809 - loss 0.08522193 - time (sec): 34.88 - samples/sec: 3285.78 - lr: 0.000048 - momentum: 0.000000
2023-10-14 19:57:26,475 epoch 2 - iter 720/1809 - loss 0.08730972 - time (sec): 45.95 - samples/sec: 3299.17 - lr: 0.000048 - momentum: 0.000000
2023-10-14 19:57:37,666 epoch 2 - iter 900/1809 - loss 0.08799984 - time (sec): 57.15 - samples/sec: 3299.11 - lr: 0.000047 - momentum: 0.000000
2023-10-14 19:57:49,179 epoch 2 - iter 1080/1809 - loss 0.08647646 - time (sec): 68.66 - samples/sec: 3309.86 - lr: 0.000047 - momentum: 0.000000
2023-10-14 19:58:00,879 epoch 2 - iter 1260/1809 - loss 0.08797357 - time (sec): 80.36 - samples/sec: 3303.56 - lr: 0.000046 - momentum: 0.000000
2023-10-14 19:58:12,292 epoch 2 - iter 1440/1809 - loss 0.08580293 - time (sec): 91.77 - samples/sec: 3298.04 - lr: 0.000046 - momentum: 0.000000
2023-10-14 19:58:23,555 epoch 2 - iter 1620/1809 - loss 0.08520800 - time (sec): 103.03 - samples/sec: 3307.44 - lr: 0.000045 - momentum: 0.000000
2023-10-14 19:58:34,969 epoch 2 - iter 1800/1809 - loss 0.08503746 - time (sec): 114.45 - samples/sec: 3303.56 - lr: 0.000044 - momentum: 0.000000
2023-10-14 19:58:35,478 ----------------------------------------------------------------------------------------------------
2023-10-14 19:58:35,478 EPOCH 2 done: loss 0.0850 - lr: 0.000044
2023-10-14 19:58:41,049 DEV : loss 0.1115032285451889 - f1-score (micro avg) 0.6266
2023-10-14 19:58:41,090 saving best model
2023-10-14 19:58:41,553 ----------------------------------------------------------------------------------------------------
2023-10-14 19:58:52,347 epoch 3 - iter 180/1809 - loss 0.06275948 - time (sec): 10.79 - samples/sec: 3279.08 - lr: 0.000044 - momentum: 0.000000
2023-10-14 19:59:03,595 epoch 3 - iter 360/1809 - loss 0.05970878 - time (sec): 22.04 - samples/sec: 3333.30 - lr: 0.000043 - momentum: 0.000000
2023-10-14 19:59:14,873 epoch 3 - iter 540/1809 - loss 0.05985749 - time (sec): 33.31 - samples/sec: 3337.20 - lr: 0.000043 - momentum: 0.000000
2023-10-14 19:59:26,115 epoch 3 - iter 720/1809 - loss 0.05962676 - time (sec): 44.55 - samples/sec: 3373.45 - lr: 0.000042 - momentum: 0.000000
2023-10-14 19:59:38,946 epoch 3 - iter 900/1809 - loss 0.05858862 - time (sec): 57.39 - samples/sec: 3272.64 - lr: 0.000042 - momentum: 0.000000
2023-10-14 19:59:51,020 epoch 3 - iter 1080/1809 - loss 0.06104670 - time (sec): 69.46 - samples/sec: 3263.46 - lr: 0.000041 - momentum: 0.000000
2023-10-14 20:00:02,728 epoch 3 - iter 1260/1809 - loss 0.06035191 - time (sec): 81.17 - samples/sec: 3266.60 - lr: 0.000041 - momentum: 0.000000
2023-10-14 20:00:14,305 epoch 3 - iter 1440/1809 - loss 0.06077928 - time (sec): 92.75 - samples/sec: 3263.60 - lr: 0.000040 - momentum: 0.000000
2023-10-14 20:00:25,873 epoch 3 - iter 1620/1809 - loss 0.06099591 - time (sec): 104.31 - samples/sec: 3258.39 - lr: 0.000039 - momentum: 0.000000
2023-10-14 20:00:38,096 epoch 3 - iter 1800/1809 - loss 0.06131526 - time (sec): 116.54 - samples/sec: 3247.12 - lr: 0.000039 - momentum: 0.000000
2023-10-14 20:00:38,612 ----------------------------------------------------------------------------------------------------
2023-10-14 20:00:38,613 EPOCH 3 done: loss 0.0612 - lr: 0.000039
2023-10-14 20:00:44,254 DEV : loss 0.16415372490882874 - f1-score (micro avg) 0.6345
2023-10-14 20:00:44,285 saving best model
2023-10-14 20:00:44,797 ----------------------------------------------------------------------------------------------------
2023-10-14 20:00:56,704 epoch 4 - iter 180/1809 - loss 0.04050032 - time (sec): 11.90 - samples/sec: 3289.62 - lr: 0.000038 - momentum: 0.000000
2023-10-14 20:01:08,146 epoch 4 - iter 360/1809 - loss 0.04638374 - time (sec): 23.35 - samples/sec: 3270.50 - lr: 0.000038 - momentum: 0.000000
2023-10-14 20:01:19,817 epoch 4 - iter 540/1809 - loss 0.04256396 - time (sec): 35.02 - samples/sec: 3250.14 - lr: 0.000037 - momentum: 0.000000
2023-10-14 20:01:30,997 epoch 4 - iter 720/1809 - loss 0.04168535 - time (sec): 46.20 - samples/sec: 3253.48 - lr: 0.000037 - momentum: 0.000000
2023-10-14 20:01:42,070 epoch 4 - iter 900/1809 - loss 0.04138962 - time (sec): 57.27 - samples/sec: 3294.92 - lr: 0.000036 - momentum: 0.000000
2023-10-14 20:01:53,028 epoch 4 - iter 1080/1809 - loss 0.04200716 - time (sec): 68.23 - samples/sec: 3313.41 - lr: 0.000036 - momentum: 0.000000
2023-10-14 20:02:04,495 epoch 4 - iter 1260/1809 - loss 0.04192659 - time (sec): 79.69 - samples/sec: 3316.82 - lr: 0.000035 - momentum: 0.000000
2023-10-14 20:02:15,701 epoch 4 - iter 1440/1809 - loss 0.04206329 - time (sec): 90.90 - samples/sec: 3329.95 - lr: 0.000034 - momentum: 0.000000
2023-10-14 20:02:26,693 epoch 4 - iter 1620/1809 - loss 0.04322145 - time (sec): 101.89 - samples/sec: 3341.18 - lr: 0.000034 - momentum: 0.000000
2023-10-14 20:02:37,872 epoch 4 - iter 1800/1809 - loss 0.04389061 - time (sec): 113.07 - samples/sec: 3343.24 - lr: 0.000033 - momentum: 0.000000
2023-10-14 20:02:38,448 ----------------------------------------------------------------------------------------------------
2023-10-14 20:02:38,448 EPOCH 4 done: loss 0.0439 - lr: 0.000033
2023-10-14 20:02:45,397 DEV : loss 0.2739905118942261 - f1-score (micro avg) 0.6395
2023-10-14 20:02:45,428 saving best model
2023-10-14 20:02:45,967 ----------------------------------------------------------------------------------------------------
2023-10-14 20:02:57,970 epoch 5 - iter 180/1809 - loss 0.03274883 - time (sec): 12.00 - samples/sec: 3275.44 - lr: 0.000033 - momentum: 0.000000
2023-10-14 20:03:09,178 epoch 5 - iter 360/1809 - loss 0.03376456 - time (sec): 23.21 - samples/sec: 3310.77 - lr: 0.000032 - momentum: 0.000000
2023-10-14 20:03:20,340 epoch 5 - iter 540/1809 - loss 0.03372631 - time (sec): 34.37 - samples/sec: 3343.03 - lr: 0.000032 - momentum: 0.000000
2023-10-14 20:03:31,437 epoch 5 - iter 720/1809 - loss 0.03416861 - time (sec): 45.47 - samples/sec: 3332.71 - lr: 0.000031 - momentum: 0.000000
2023-10-14 20:03:42,821 epoch 5 - iter 900/1809 - loss 0.03305077 - time (sec): 56.85 - samples/sec: 3350.33 - lr: 0.000031 - momentum: 0.000000
2023-10-14 20:03:54,085 epoch 5 - iter 1080/1809 - loss 0.03328099 - time (sec): 68.11 - samples/sec: 3360.47 - lr: 0.000030 - momentum: 0.000000
2023-10-14 20:04:05,270 epoch 5 - iter 1260/1809 - loss 0.03312214 - time (sec): 79.30 - samples/sec: 3368.80 - lr: 0.000029 - momentum: 0.000000
2023-10-14 20:04:16,232 epoch 5 - iter 1440/1809 - loss 0.03276691 - time (sec): 90.26 - samples/sec: 3368.73 - lr: 0.000029 - momentum: 0.000000
2023-10-14 20:04:26,972 epoch 5 - iter 1620/1809 - loss 0.03238180 - time (sec): 101.00 - samples/sec: 3385.30 - lr: 0.000028 - momentum: 0.000000
2023-10-14 20:04:37,686 epoch 5 - iter 1800/1809 - loss 0.03256257 - time (sec): 111.71 - samples/sec: 3385.96 - lr: 0.000028 - momentum: 0.000000
2023-10-14 20:04:38,165 ----------------------------------------------------------------------------------------------------
2023-10-14 20:04:38,165 EPOCH 5 done: loss 0.0326 - lr: 0.000028
2023-10-14 20:04:44,446 DEV : loss 0.30132314562797546 - f1-score (micro avg) 0.6194
2023-10-14 20:04:44,476 ----------------------------------------------------------------------------------------------------
2023-10-14 20:04:55,618 epoch 6 - iter 180/1809 - loss 0.02000950 - time (sec): 11.14 - samples/sec: 3392.54 - lr: 0.000027 - momentum: 0.000000
2023-10-14 20:05:06,487 epoch 6 - iter 360/1809 - loss 0.02102558 - time (sec): 22.01 - samples/sec: 3410.42 - lr: 0.000027 - momentum: 0.000000
2023-10-14 20:05:17,381 epoch 6 - iter 540/1809 - loss 0.02110462 - time (sec): 32.90 - samples/sec: 3392.68 - lr: 0.000026 - momentum: 0.000000
2023-10-14 20:05:28,393 epoch 6 - iter 720/1809 - loss 0.02298616 - time (sec): 43.92 - samples/sec: 3398.32 - lr: 0.000026 - momentum: 0.000000
2023-10-14 20:05:39,567 epoch 6 - iter 900/1809 - loss 0.02202486 - time (sec): 55.09 - samples/sec: 3409.55 - lr: 0.000025 - momentum: 0.000000
2023-10-14 20:05:50,592 epoch 6 - iter 1080/1809 - loss 0.02290144 - time (sec): 66.11 - samples/sec: 3416.70 - lr: 0.000024 - momentum: 0.000000
2023-10-14 20:06:01,594 epoch 6 - iter 1260/1809 - loss 0.02273488 - time (sec): 77.12 - samples/sec: 3416.38 - lr: 0.000024 - momentum: 0.000000
2023-10-14 20:06:12,951 epoch 6 - iter 1440/1809 - loss 0.02310618 - time (sec): 88.47 - samples/sec: 3424.89 - lr: 0.000023 - momentum: 0.000000
2023-10-14 20:06:24,004 epoch 6 - iter 1620/1809 - loss 0.02272973 - time (sec): 99.53 - samples/sec: 3414.79 - lr: 0.000023 - momentum: 0.000000
2023-10-14 20:06:34,954 epoch 6 - iter 1800/1809 - loss 0.02299704 - time (sec): 110.48 - samples/sec: 3422.82 - lr: 0.000022 - momentum: 0.000000
2023-10-14 20:06:35,473 ----------------------------------------------------------------------------------------------------
2023-10-14 20:06:35,473 EPOCH 6 done: loss 0.0229 - lr: 0.000022
2023-10-14 20:06:41,937 DEV : loss 0.30204930901527405 - f1-score (micro avg) 0.637
2023-10-14 20:06:41,970 ----------------------------------------------------------------------------------------------------
2023-10-14 20:06:53,076 epoch 7 - iter 180/1809 - loss 0.01920066 - time (sec): 11.10 - samples/sec: 3480.61 - lr: 0.000022 - momentum: 0.000000
2023-10-14 20:07:04,403 epoch 7 - iter 360/1809 - loss 0.01732531 - time (sec): 22.43 - samples/sec: 3423.94 - lr: 0.000021 - momentum: 0.000000
2023-10-14 20:07:15,376 epoch 7 - iter 540/1809 - loss 0.01693909 - time (sec): 33.40 - samples/sec: 3427.04 - lr: 0.000021 - momentum: 0.000000
2023-10-14 20:07:26,346 epoch 7 - iter 720/1809 - loss 0.01681882 - time (sec): 44.37 - samples/sec: 3438.61 - lr: 0.000020 - momentum: 0.000000
2023-10-14 20:07:37,415 epoch 7 - iter 900/1809 - loss 0.01628210 - time (sec): 55.44 - samples/sec: 3429.77 - lr: 0.000019 - momentum: 0.000000
2023-10-14 20:07:48,365 epoch 7 - iter 1080/1809 - loss 0.01625405 - time (sec): 66.39 - samples/sec: 3429.63 - lr: 0.000019 - momentum: 0.000000
2023-10-14 20:07:59,296 epoch 7 - iter 1260/1809 - loss 0.01605560 - time (sec): 77.33 - samples/sec: 3432.14 - lr: 0.000018 - momentum: 0.000000
2023-10-14 20:08:10,313 epoch 7 - iter 1440/1809 - loss 0.01618800 - time (sec): 88.34 - samples/sec: 3433.08 - lr: 0.000018 - momentum: 0.000000
2023-10-14 20:08:21,163 epoch 7 - iter 1620/1809 - loss 0.01610626 - time (sec): 99.19 - samples/sec: 3433.41 - lr: 0.000017 - momentum: 0.000000
2023-10-14 20:08:31,856 epoch 7 - iter 1800/1809 - loss 0.01585667 - time (sec): 109.88 - samples/sec: 3441.41 - lr: 0.000017 - momentum: 0.000000
2023-10-14 20:08:32,342 ----------------------------------------------------------------------------------------------------
2023-10-14 20:08:32,342 EPOCH 7 done: loss 0.0159 - lr: 0.000017
2023-10-14 20:08:38,752 DEV : loss 0.37900328636169434 - f1-score (micro avg) 0.6506
2023-10-14 20:08:38,787 saving best model
2023-10-14 20:08:39,292 ----------------------------------------------------------------------------------------------------
2023-10-14 20:08:50,043 epoch 8 - iter 180/1809 - loss 0.01074333 - time (sec): 10.75 - samples/sec: 3429.58 - lr: 0.000016 - momentum: 0.000000
2023-10-14 20:09:01,139 epoch 8 - iter 360/1809 - loss 0.01024638 - time (sec): 21.85 - samples/sec: 3426.84 - lr: 0.000016 - momentum: 0.000000
2023-10-14 20:09:12,250 epoch 8 - iter 540/1809 - loss 0.00991737 - time (sec): 32.96 - samples/sec: 3443.87 - lr: 0.000015 - momentum: 0.000000
2023-10-14 20:09:23,339 epoch 8 - iter 720/1809 - loss 0.01001735 - time (sec): 44.05 - samples/sec: 3434.64 - lr: 0.000014 - momentum: 0.000000
2023-10-14 20:09:34,066 epoch 8 - iter 900/1809 - loss 0.01029062 - time (sec): 54.77 - samples/sec: 3440.98 - lr: 0.000014 - momentum: 0.000000
2023-10-14 20:09:44,738 epoch 8 - iter 1080/1809 - loss 0.01096769 - time (sec): 65.44 - samples/sec: 3422.83 - lr: 0.000013 - momentum: 0.000000
2023-10-14 20:09:56,318 epoch 8 - iter 1260/1809 - loss 0.01096529 - time (sec): 77.02 - samples/sec: 3418.87 - lr: 0.000013 - momentum: 0.000000
2023-10-14 20:10:07,341 epoch 8 - iter 1440/1809 - loss 0.01043110 - time (sec): 88.05 - samples/sec: 3414.98 - lr: 0.000012 - momentum: 0.000000
2023-10-14 20:10:18,516 epoch 8 - iter 1620/1809 - loss 0.01040260 - time (sec): 99.22 - samples/sec: 3419.48 - lr: 0.000012 - momentum: 0.000000
2023-10-14 20:10:29,408 epoch 8 - iter 1800/1809 - loss 0.01021177 - time (sec): 110.11 - samples/sec: 3430.44 - lr: 0.000011 - momentum: 0.000000
2023-10-14 20:10:30,023 ----------------------------------------------------------------------------------------------------
2023-10-14 20:10:30,023 EPOCH 8 done: loss 0.0102 - lr: 0.000011
2023-10-14 20:10:35,669 DEV : loss 0.386315256357193 - f1-score (micro avg) 0.6525
2023-10-14 20:10:35,702 saving best model
2023-10-14 20:10:36,220 ----------------------------------------------------------------------------------------------------
2023-10-14 20:10:48,463 epoch 9 - iter 180/1809 - loss 0.00502273 - time (sec): 12.24 - samples/sec: 3086.65 - lr: 0.000011 - momentum: 0.000000
2023-10-14 20:10:59,887 epoch 9 - iter 360/1809 - loss 0.00783396 - time (sec): 23.66 - samples/sec: 3250.37 - lr: 0.000010 - momentum: 0.000000
2023-10-14 20:11:11,027 epoch 9 - iter 540/1809 - loss 0.00740246 - time (sec): 34.80 - samples/sec: 3308.71 - lr: 0.000009 - momentum: 0.000000
2023-10-14 20:11:21,961 epoch 9 - iter 720/1809 - loss 0.00813486 - time (sec): 45.74 - samples/sec: 3318.19 - lr: 0.000009 - momentum: 0.000000
2023-10-14 20:11:32,832 epoch 9 - iter 900/1809 - loss 0.00721541 - time (sec): 56.61 - samples/sec: 3340.81 - lr: 0.000008 - momentum: 0.000000
2023-10-14 20:11:43,695 epoch 9 - iter 1080/1809 - loss 0.00729423 - time (sec): 67.47 - samples/sec: 3357.17 - lr: 0.000008 - momentum: 0.000000
2023-10-14 20:11:54,696 epoch 9 - iter 1260/1809 - loss 0.00715794 - time (sec): 78.47 - samples/sec: 3355.65 - lr: 0.000007 - momentum: 0.000000
2023-10-14 20:12:05,736 epoch 9 - iter 1440/1809 - loss 0.00685492 - time (sec): 89.51 - samples/sec: 3361.23 - lr: 0.000007 - momentum: 0.000000
2023-10-14 20:12:16,672 epoch 9 - iter 1620/1809 - loss 0.00683880 - time (sec): 100.45 - samples/sec: 3379.37 - lr: 0.000006 - momentum: 0.000000
2023-10-14 20:12:27,522 epoch 9 - iter 1800/1809 - loss 0.00673882 - time (sec): 111.30 - samples/sec: 3400.19 - lr: 0.000006 - momentum: 0.000000
2023-10-14 20:12:28,049 ----------------------------------------------------------------------------------------------------
2023-10-14 20:12:28,050 EPOCH 9 done: loss 0.0067 - lr: 0.000006
2023-10-14 20:12:33,774 DEV : loss 0.40529340505599976 - f1-score (micro avg) 0.6425
2023-10-14 20:12:33,810 ----------------------------------------------------------------------------------------------------
2023-10-14 20:12:44,875 epoch 10 - iter 180/1809 - loss 0.00252138 - time (sec): 11.06 - samples/sec: 3459.07 - lr: 0.000005 - momentum: 0.000000
2023-10-14 20:12:56,013 epoch 10 - iter 360/1809 - loss 0.00344089 - time (sec): 22.20 - samples/sec: 3465.51 - lr: 0.000004 - momentum: 0.000000
2023-10-14 20:13:07,057 epoch 10 - iter 540/1809 - loss 0.00356348 - time (sec): 33.25 - samples/sec: 3425.09 - lr: 0.000004 - momentum: 0.000000
2023-10-14 20:13:17,866 epoch 10 - iter 720/1809 - loss 0.00377280 - time (sec): 44.05 - samples/sec: 3445.07 - lr: 0.000003 - momentum: 0.000000
2023-10-14 20:13:29,123 epoch 10 - iter 900/1809 - loss 0.00362108 - time (sec): 55.31 - samples/sec: 3436.69 - lr: 0.000003 - momentum: 0.000000
2023-10-14 20:13:40,147 epoch 10 - iter 1080/1809 - loss 0.00375605 - time (sec): 66.34 - samples/sec: 3438.83 - lr: 0.000002 - momentum: 0.000000
2023-10-14 20:13:50,911 epoch 10 - iter 1260/1809 - loss 0.00378037 - time (sec): 77.10 - samples/sec: 3430.31 - lr: 0.000002 - momentum: 0.000000
2023-10-14 20:14:02,469 epoch 10 - iter 1440/1809 - loss 0.00397690 - time (sec): 88.66 - samples/sec: 3384.85 - lr: 0.000001 - momentum: 0.000000
2023-10-14 20:14:13,575 epoch 10 - iter 1620/1809 - loss 0.00377560 - time (sec): 99.76 - samples/sec: 3395.83 - lr: 0.000001 - momentum: 0.000000
2023-10-14 20:14:25,207 epoch 10 - iter 1800/1809 - loss 0.00397882 - time (sec): 111.40 - samples/sec: 3395.03 - lr: 0.000000 - momentum: 0.000000
2023-10-14 20:14:25,715 ----------------------------------------------------------------------------------------------------
2023-10-14 20:14:25,716 EPOCH 10 done: loss 0.0040 - lr: 0.000000
2023-10-14 20:14:31,605 DEV : loss 0.41697490215301514 - f1-score (micro avg) 0.642
2023-10-14 20:14:32,074 ----------------------------------------------------------------------------------------------------
2023-10-14 20:14:32,076 Loading model from best epoch ...
2023-10-14 20:14:33,753 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
2023-10-14 20:14:42,798
Results:
- F-score (micro) 0.6298
- F-score (macro) 0.4749
- Accuracy 0.4735
By class:
precision recall f1-score support
loc 0.6396 0.7327 0.6830 591
pers 0.5278 0.7451 0.6179 357
org 0.2059 0.0886 0.1239 79
micro avg 0.5811 0.6874 0.6298 1027
macro avg 0.4577 0.5221 0.4749 1027
weighted avg 0.5674 0.6874 0.6173 1027
2023-10-14 20:14:42,799 ----------------------------------------------------------------------------------------------------
|