File size: 24,009 Bytes
de43a91 |
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 |
2023-10-17 09:38:34,141 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,142 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): ElectraModel(
(embeddings): ElectraEmbeddings(
(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): ElectraEncoder(
(layer): ModuleList(
(0-11): 12 x ElectraLayer(
(attention): ElectraAttention(
(self): ElectraSelfAttention(
(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): ElectraSelfOutput(
(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): ElectraIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): ElectraOutput(
(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)
)
)
)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-17 09:38:34,142 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 MultiCorpus: 1214 train + 266 dev + 251 test sentences
- NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Train: 1214 sentences
2023-10-17 09:38:34,143 (train_with_dev=False, train_with_test=False)
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Training Params:
2023-10-17 09:38:34,143 - learning_rate: "5e-05"
2023-10-17 09:38:34,143 - mini_batch_size: "8"
2023-10-17 09:38:34,143 - max_epochs: "10"
2023-10-17 09:38:34,143 - shuffle: "True"
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Plugins:
2023-10-17 09:38:34,143 - TensorboardLogger
2023-10-17 09:38:34,143 - LinearScheduler | warmup_fraction: '0.1'
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Final evaluation on model from best epoch (best-model.pt)
2023-10-17 09:38:34,143 - metric: "('micro avg', 'f1-score')"
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Computation:
2023-10-17 09:38:34,143 - compute on device: cuda:0
2023-10-17 09:38:34,143 - embedding storage: none
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Model training base path: "hmbench-ajmc/en-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:34,143 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-17 09:38:34,950 epoch 1 - iter 15/152 - loss 3.27859425 - time (sec): 0.81 - samples/sec: 3732.51 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:38:35,826 epoch 1 - iter 30/152 - loss 2.72599269 - time (sec): 1.68 - samples/sec: 3539.20 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:38:36,686 epoch 1 - iter 45/152 - loss 2.08274849 - time (sec): 2.54 - samples/sec: 3696.16 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:38:37,548 epoch 1 - iter 60/152 - loss 1.69026109 - time (sec): 3.40 - samples/sec: 3728.36 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:38:38,379 epoch 1 - iter 75/152 - loss 1.46877182 - time (sec): 4.24 - samples/sec: 3650.48 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:38:39,218 epoch 1 - iter 90/152 - loss 1.28998562 - time (sec): 5.07 - samples/sec: 3599.89 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:38:40,116 epoch 1 - iter 105/152 - loss 1.15167153 - time (sec): 5.97 - samples/sec: 3585.63 - lr: 0.000034 - momentum: 0.000000
2023-10-17 09:38:40,972 epoch 1 - iter 120/152 - loss 1.05035412 - time (sec): 6.83 - samples/sec: 3580.80 - lr: 0.000039 - momentum: 0.000000
2023-10-17 09:38:41,843 epoch 1 - iter 135/152 - loss 0.96613510 - time (sec): 7.70 - samples/sec: 3566.35 - lr: 0.000044 - momentum: 0.000000
2023-10-17 09:38:42,715 epoch 1 - iter 150/152 - loss 0.89078976 - time (sec): 8.57 - samples/sec: 3576.29 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:38:42,823 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:42,823 EPOCH 1 done: loss 0.8833 - lr: 0.000049
2023-10-17 09:38:43,599 DEV : loss 0.1987733244895935 - f1-score (micro avg) 0.6076
2023-10-17 09:38:43,606 saving best model
2023-10-17 09:38:43,940 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:44,818 epoch 2 - iter 15/152 - loss 0.20082465 - time (sec): 0.88 - samples/sec: 3433.40 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:38:45,655 epoch 2 - iter 30/152 - loss 0.19478102 - time (sec): 1.71 - samples/sec: 3565.02 - lr: 0.000049 - momentum: 0.000000
2023-10-17 09:38:46,493 epoch 2 - iter 45/152 - loss 0.17303971 - time (sec): 2.55 - samples/sec: 3611.14 - lr: 0.000048 - momentum: 0.000000
2023-10-17 09:38:47,364 epoch 2 - iter 60/152 - loss 0.16161793 - time (sec): 3.42 - samples/sec: 3578.45 - lr: 0.000048 - momentum: 0.000000
2023-10-17 09:38:48,245 epoch 2 - iter 75/152 - loss 0.15733415 - time (sec): 4.30 - samples/sec: 3583.42 - lr: 0.000047 - momentum: 0.000000
2023-10-17 09:38:49,039 epoch 2 - iter 90/152 - loss 0.14995035 - time (sec): 5.10 - samples/sec: 3592.35 - lr: 0.000047 - momentum: 0.000000
2023-10-17 09:38:49,872 epoch 2 - iter 105/152 - loss 0.14810154 - time (sec): 5.93 - samples/sec: 3569.23 - lr: 0.000046 - momentum: 0.000000
2023-10-17 09:38:50,735 epoch 2 - iter 120/152 - loss 0.14985129 - time (sec): 6.79 - samples/sec: 3609.32 - lr: 0.000046 - momentum: 0.000000
2023-10-17 09:38:51,593 epoch 2 - iter 135/152 - loss 0.14474154 - time (sec): 7.65 - samples/sec: 3625.84 - lr: 0.000045 - momentum: 0.000000
2023-10-17 09:38:52,480 epoch 2 - iter 150/152 - loss 0.14450170 - time (sec): 8.54 - samples/sec: 3594.70 - lr: 0.000045 - momentum: 0.000000
2023-10-17 09:38:52,583 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:52,583 EPOCH 2 done: loss 0.1435 - lr: 0.000045
2023-10-17 09:38:53,538 DEV : loss 0.13812772929668427 - f1-score (micro avg) 0.8167
2023-10-17 09:38:53,544 saving best model
2023-10-17 09:38:54,193 ----------------------------------------------------------------------------------------------------
2023-10-17 09:38:55,055 epoch 3 - iter 15/152 - loss 0.08406498 - time (sec): 0.86 - samples/sec: 3394.23 - lr: 0.000044 - momentum: 0.000000
2023-10-17 09:38:55,855 epoch 3 - iter 30/152 - loss 0.08216989 - time (sec): 1.66 - samples/sec: 3549.93 - lr: 0.000043 - momentum: 0.000000
2023-10-17 09:38:56,689 epoch 3 - iter 45/152 - loss 0.08400782 - time (sec): 2.49 - samples/sec: 3517.04 - lr: 0.000043 - momentum: 0.000000
2023-10-17 09:38:57,506 epoch 3 - iter 60/152 - loss 0.07951715 - time (sec): 3.31 - samples/sec: 3543.39 - lr: 0.000042 - momentum: 0.000000
2023-10-17 09:38:58,410 epoch 3 - iter 75/152 - loss 0.07134940 - time (sec): 4.21 - samples/sec: 3594.73 - lr: 0.000042 - momentum: 0.000000
2023-10-17 09:38:59,296 epoch 3 - iter 90/152 - loss 0.08497999 - time (sec): 5.10 - samples/sec: 3594.94 - lr: 0.000041 - momentum: 0.000000
2023-10-17 09:39:00,149 epoch 3 - iter 105/152 - loss 0.08940396 - time (sec): 5.95 - samples/sec: 3603.39 - lr: 0.000041 - momentum: 0.000000
2023-10-17 09:39:01,011 epoch 3 - iter 120/152 - loss 0.08746023 - time (sec): 6.81 - samples/sec: 3592.93 - lr: 0.000040 - momentum: 0.000000
2023-10-17 09:39:01,849 epoch 3 - iter 135/152 - loss 0.08383760 - time (sec): 7.65 - samples/sec: 3575.69 - lr: 0.000040 - momentum: 0.000000
2023-10-17 09:39:02,739 epoch 3 - iter 150/152 - loss 0.08213378 - time (sec): 8.54 - samples/sec: 3589.37 - lr: 0.000039 - momentum: 0.000000
2023-10-17 09:39:02,841 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:02,842 EPOCH 3 done: loss 0.0825 - lr: 0.000039
2023-10-17 09:39:03,799 DEV : loss 0.1335965245962143 - f1-score (micro avg) 0.8278
2023-10-17 09:39:03,805 saving best model
2023-10-17 09:39:04,237 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:05,055 epoch 4 - iter 15/152 - loss 0.03908169 - time (sec): 0.81 - samples/sec: 3830.29 - lr: 0.000038 - momentum: 0.000000
2023-10-17 09:39:05,898 epoch 4 - iter 30/152 - loss 0.04629587 - time (sec): 1.65 - samples/sec: 3707.14 - lr: 0.000038 - momentum: 0.000000
2023-10-17 09:39:06,753 epoch 4 - iter 45/152 - loss 0.05984097 - time (sec): 2.51 - samples/sec: 3578.75 - lr: 0.000037 - momentum: 0.000000
2023-10-17 09:39:07,691 epoch 4 - iter 60/152 - loss 0.05594081 - time (sec): 3.45 - samples/sec: 3589.48 - lr: 0.000037 - momentum: 0.000000
2023-10-17 09:39:08,547 epoch 4 - iter 75/152 - loss 0.05336373 - time (sec): 4.30 - samples/sec: 3554.56 - lr: 0.000036 - momentum: 0.000000
2023-10-17 09:39:09,403 epoch 4 - iter 90/152 - loss 0.05316291 - time (sec): 5.16 - samples/sec: 3529.17 - lr: 0.000036 - momentum: 0.000000
2023-10-17 09:39:10,283 epoch 4 - iter 105/152 - loss 0.05437028 - time (sec): 6.04 - samples/sec: 3544.89 - lr: 0.000035 - momentum: 0.000000
2023-10-17 09:39:11,123 epoch 4 - iter 120/152 - loss 0.05389946 - time (sec): 6.88 - samples/sec: 3571.08 - lr: 0.000035 - momentum: 0.000000
2023-10-17 09:39:12,003 epoch 4 - iter 135/152 - loss 0.05636939 - time (sec): 7.76 - samples/sec: 3563.84 - lr: 0.000034 - momentum: 0.000000
2023-10-17 09:39:12,831 epoch 4 - iter 150/152 - loss 0.05731052 - time (sec): 8.59 - samples/sec: 3575.72 - lr: 0.000034 - momentum: 0.000000
2023-10-17 09:39:12,936 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:12,936 EPOCH 4 done: loss 0.0574 - lr: 0.000034
2023-10-17 09:39:13,907 DEV : loss 0.14786171913146973 - f1-score (micro avg) 0.83
2023-10-17 09:39:13,915 saving best model
2023-10-17 09:39:14,340 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:15,265 epoch 5 - iter 15/152 - loss 0.05904708 - time (sec): 0.92 - samples/sec: 3658.66 - lr: 0.000033 - momentum: 0.000000
2023-10-17 09:39:16,172 epoch 5 - iter 30/152 - loss 0.04451243 - time (sec): 1.83 - samples/sec: 3466.96 - lr: 0.000032 - momentum: 0.000000
2023-10-17 09:39:17,059 epoch 5 - iter 45/152 - loss 0.04383666 - time (sec): 2.72 - samples/sec: 3563.23 - lr: 0.000032 - momentum: 0.000000
2023-10-17 09:39:17,903 epoch 5 - iter 60/152 - loss 0.03689764 - time (sec): 3.56 - samples/sec: 3569.59 - lr: 0.000031 - momentum: 0.000000
2023-10-17 09:39:18,733 epoch 5 - iter 75/152 - loss 0.03291934 - time (sec): 4.39 - samples/sec: 3594.00 - lr: 0.000031 - momentum: 0.000000
2023-10-17 09:39:19,588 epoch 5 - iter 90/152 - loss 0.03570598 - time (sec): 5.25 - samples/sec: 3561.01 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:39:20,460 epoch 5 - iter 105/152 - loss 0.03541183 - time (sec): 6.12 - samples/sec: 3544.28 - lr: 0.000030 - momentum: 0.000000
2023-10-17 09:39:21,266 epoch 5 - iter 120/152 - loss 0.04052611 - time (sec): 6.92 - samples/sec: 3528.99 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:39:22,140 epoch 5 - iter 135/152 - loss 0.03986727 - time (sec): 7.80 - samples/sec: 3536.23 - lr: 0.000029 - momentum: 0.000000
2023-10-17 09:39:22,995 epoch 5 - iter 150/152 - loss 0.04344923 - time (sec): 8.65 - samples/sec: 3548.42 - lr: 0.000028 - momentum: 0.000000
2023-10-17 09:39:23,099 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:23,099 EPOCH 5 done: loss 0.0432 - lr: 0.000028
2023-10-17 09:39:24,037 DEV : loss 0.18125084042549133 - f1-score (micro avg) 0.8386
2023-10-17 09:39:24,044 saving best model
2023-10-17 09:39:24,518 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:25,402 epoch 6 - iter 15/152 - loss 0.03603697 - time (sec): 0.88 - samples/sec: 3513.16 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:39:26,246 epoch 6 - iter 30/152 - loss 0.02829961 - time (sec): 1.73 - samples/sec: 3425.55 - lr: 0.000027 - momentum: 0.000000
2023-10-17 09:39:27,132 epoch 6 - iter 45/152 - loss 0.02713591 - time (sec): 2.61 - samples/sec: 3404.97 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:39:28,057 epoch 6 - iter 60/152 - loss 0.02652119 - time (sec): 3.54 - samples/sec: 3373.27 - lr: 0.000026 - momentum: 0.000000
2023-10-17 09:39:28,955 epoch 6 - iter 75/152 - loss 0.02681934 - time (sec): 4.44 - samples/sec: 3411.40 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:39:29,812 epoch 6 - iter 90/152 - loss 0.02547718 - time (sec): 5.29 - samples/sec: 3423.75 - lr: 0.000025 - momentum: 0.000000
2023-10-17 09:39:30,715 epoch 6 - iter 105/152 - loss 0.02868459 - time (sec): 6.20 - samples/sec: 3439.26 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:39:31,560 epoch 6 - iter 120/152 - loss 0.02636207 - time (sec): 7.04 - samples/sec: 3447.80 - lr: 0.000024 - momentum: 0.000000
2023-10-17 09:39:32,381 epoch 6 - iter 135/152 - loss 0.02747651 - time (sec): 7.86 - samples/sec: 3483.43 - lr: 0.000023 - momentum: 0.000000
2023-10-17 09:39:33,286 epoch 6 - iter 150/152 - loss 0.02916397 - time (sec): 8.77 - samples/sec: 3497.20 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:39:33,389 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:33,389 EPOCH 6 done: loss 0.0290 - lr: 0.000022
2023-10-17 09:39:34,346 DEV : loss 0.17775358259677887 - f1-score (micro avg) 0.8392
2023-10-17 09:39:34,354 saving best model
2023-10-17 09:39:34,847 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:35,727 epoch 7 - iter 15/152 - loss 0.01054120 - time (sec): 0.88 - samples/sec: 3191.99 - lr: 0.000022 - momentum: 0.000000
2023-10-17 09:39:36,613 epoch 7 - iter 30/152 - loss 0.00586221 - time (sec): 1.76 - samples/sec: 3306.50 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:39:37,476 epoch 7 - iter 45/152 - loss 0.01323046 - time (sec): 2.63 - samples/sec: 3394.61 - lr: 0.000021 - momentum: 0.000000
2023-10-17 09:39:38,352 epoch 7 - iter 60/152 - loss 0.01434518 - time (sec): 3.50 - samples/sec: 3381.57 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:39:39,198 epoch 7 - iter 75/152 - loss 0.01412553 - time (sec): 4.35 - samples/sec: 3445.80 - lr: 0.000020 - momentum: 0.000000
2023-10-17 09:39:40,033 epoch 7 - iter 90/152 - loss 0.01286259 - time (sec): 5.18 - samples/sec: 3473.05 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:39:40,921 epoch 7 - iter 105/152 - loss 0.01426731 - time (sec): 6.07 - samples/sec: 3466.78 - lr: 0.000019 - momentum: 0.000000
2023-10-17 09:39:41,876 epoch 7 - iter 120/152 - loss 0.01566369 - time (sec): 7.03 - samples/sec: 3476.59 - lr: 0.000018 - momentum: 0.000000
2023-10-17 09:39:42,805 epoch 7 - iter 135/152 - loss 0.01808615 - time (sec): 7.96 - samples/sec: 3486.38 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:39:43,656 epoch 7 - iter 150/152 - loss 0.02135121 - time (sec): 8.81 - samples/sec: 3478.81 - lr: 0.000017 - momentum: 0.000000
2023-10-17 09:39:43,764 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:43,764 EPOCH 7 done: loss 0.0214 - lr: 0.000017
2023-10-17 09:39:44,763 DEV : loss 0.18729975819587708 - f1-score (micro avg) 0.8547
2023-10-17 09:39:44,771 saving best model
2023-10-17 09:39:45,212 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:46,080 epoch 8 - iter 15/152 - loss 0.00906167 - time (sec): 0.87 - samples/sec: 3887.75 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:39:46,926 epoch 8 - iter 30/152 - loss 0.00839837 - time (sec): 1.71 - samples/sec: 3729.41 - lr: 0.000016 - momentum: 0.000000
2023-10-17 09:39:47,820 epoch 8 - iter 45/152 - loss 0.01422912 - time (sec): 2.60 - samples/sec: 3645.42 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:39:48,644 epoch 8 - iter 60/152 - loss 0.01285881 - time (sec): 3.43 - samples/sec: 3550.60 - lr: 0.000015 - momentum: 0.000000
2023-10-17 09:39:49,523 epoch 8 - iter 75/152 - loss 0.01186707 - time (sec): 4.31 - samples/sec: 3603.65 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:39:50,290 epoch 8 - iter 90/152 - loss 0.01303695 - time (sec): 5.08 - samples/sec: 3630.21 - lr: 0.000014 - momentum: 0.000000
2023-10-17 09:39:51,145 epoch 8 - iter 105/152 - loss 0.01545938 - time (sec): 5.93 - samples/sec: 3607.92 - lr: 0.000013 - momentum: 0.000000
2023-10-17 09:39:51,988 epoch 8 - iter 120/152 - loss 0.01686442 - time (sec): 6.77 - samples/sec: 3619.78 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:39:52,840 epoch 8 - iter 135/152 - loss 0.01607652 - time (sec): 7.63 - samples/sec: 3621.61 - lr: 0.000012 - momentum: 0.000000
2023-10-17 09:39:53,684 epoch 8 - iter 150/152 - loss 0.01592888 - time (sec): 8.47 - samples/sec: 3615.38 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:39:53,792 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:53,792 EPOCH 8 done: loss 0.0157 - lr: 0.000011
2023-10-17 09:39:54,730 DEV : loss 0.19675733149051666 - f1-score (micro avg) 0.8516
2023-10-17 09:39:54,737 ----------------------------------------------------------------------------------------------------
2023-10-17 09:39:55,580 epoch 9 - iter 15/152 - loss 0.01308460 - time (sec): 0.84 - samples/sec: 3652.30 - lr: 0.000011 - momentum: 0.000000
2023-10-17 09:39:56,439 epoch 9 - iter 30/152 - loss 0.00896246 - time (sec): 1.70 - samples/sec: 3516.26 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:39:57,331 epoch 9 - iter 45/152 - loss 0.01312645 - time (sec): 2.59 - samples/sec: 3534.32 - lr: 0.000010 - momentum: 0.000000
2023-10-17 09:39:58,174 epoch 9 - iter 60/152 - loss 0.01130915 - time (sec): 3.44 - samples/sec: 3505.52 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:39:59,043 epoch 9 - iter 75/152 - loss 0.01077197 - time (sec): 4.30 - samples/sec: 3539.88 - lr: 0.000009 - momentum: 0.000000
2023-10-17 09:39:59,895 epoch 9 - iter 90/152 - loss 0.01047289 - time (sec): 5.16 - samples/sec: 3559.78 - lr: 0.000008 - momentum: 0.000000
2023-10-17 09:40:00,767 epoch 9 - iter 105/152 - loss 0.00916831 - time (sec): 6.03 - samples/sec: 3536.58 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:40:01,576 epoch 9 - iter 120/152 - loss 0.01012104 - time (sec): 6.84 - samples/sec: 3548.84 - lr: 0.000007 - momentum: 0.000000
2023-10-17 09:40:02,455 epoch 9 - iter 135/152 - loss 0.01105105 - time (sec): 7.72 - samples/sec: 3555.43 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:40:03,345 epoch 9 - iter 150/152 - loss 0.01143143 - time (sec): 8.61 - samples/sec: 3561.34 - lr: 0.000006 - momentum: 0.000000
2023-10-17 09:40:03,449 ----------------------------------------------------------------------------------------------------
2023-10-17 09:40:03,449 EPOCH 9 done: loss 0.0113 - lr: 0.000006
2023-10-17 09:40:04,397 DEV : loss 0.200613334774971 - f1-score (micro avg) 0.8503
2023-10-17 09:40:04,405 ----------------------------------------------------------------------------------------------------
2023-10-17 09:40:05,304 epoch 10 - iter 15/152 - loss 0.00389795 - time (sec): 0.90 - samples/sec: 3276.13 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:40:06,241 epoch 10 - iter 30/152 - loss 0.00586938 - time (sec): 1.83 - samples/sec: 3256.88 - lr: 0.000005 - momentum: 0.000000
2023-10-17 09:40:07,204 epoch 10 - iter 45/152 - loss 0.00698098 - time (sec): 2.80 - samples/sec: 3313.32 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:40:08,154 epoch 10 - iter 60/152 - loss 0.01104798 - time (sec): 3.75 - samples/sec: 3254.03 - lr: 0.000004 - momentum: 0.000000
2023-10-17 09:40:09,020 epoch 10 - iter 75/152 - loss 0.00971413 - time (sec): 4.61 - samples/sec: 3281.76 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:40:09,935 epoch 10 - iter 90/152 - loss 0.00975448 - time (sec): 5.53 - samples/sec: 3280.82 - lr: 0.000003 - momentum: 0.000000
2023-10-17 09:40:10,824 epoch 10 - iter 105/152 - loss 0.00833967 - time (sec): 6.42 - samples/sec: 3327.69 - lr: 0.000002 - momentum: 0.000000
2023-10-17 09:40:11,689 epoch 10 - iter 120/152 - loss 0.00759956 - time (sec): 7.28 - samples/sec: 3341.10 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:40:12,574 epoch 10 - iter 135/152 - loss 0.00829980 - time (sec): 8.17 - samples/sec: 3354.76 - lr: 0.000001 - momentum: 0.000000
2023-10-17 09:40:13,508 epoch 10 - iter 150/152 - loss 0.00935136 - time (sec): 9.10 - samples/sec: 3363.67 - lr: 0.000000 - momentum: 0.000000
2023-10-17 09:40:13,628 ----------------------------------------------------------------------------------------------------
2023-10-17 09:40:13,628 EPOCH 10 done: loss 0.0092 - lr: 0.000000
2023-10-17 09:40:14,600 DEV : loss 0.19964995980262756 - f1-score (micro avg) 0.8544
2023-10-17 09:40:14,972 ----------------------------------------------------------------------------------------------------
2023-10-17 09:40:14,974 Loading model from best epoch ...
2023-10-17 09:40:16,456 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
2023-10-17 09:40:17,392
Results:
- F-score (micro) 0.8113
- F-score (macro) 0.6298
- Accuracy 0.6923
By class:
precision recall f1-score support
scope 0.7677 0.7881 0.7778 151
work 0.7843 0.8421 0.8122 95
pers 0.8788 0.9062 0.8923 96
loc 0.6667 0.6667 0.6667 3
date 0.0000 0.0000 0.0000 3
micro avg 0.7956 0.8276 0.8113 348
macro avg 0.6195 0.6406 0.6298 348
weighted avg 0.7954 0.8276 0.8111 348
2023-10-17 09:40:17,392 ----------------------------------------------------------------------------------------------------
|