File size: 23,999 Bytes
dbbe809 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 |
2023-10-25 21:33:51,878 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,879 Model: "SequenceTagger(
(embeddings): TransformerWordEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(64001, 768)
(position_embeddings): Embedding(512, 768)
(token_type_embeddings): Embedding(2, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0-11): 12 x BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=17, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-25 21:33:51,879 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 MultiCorpus: 1085 train + 148 dev + 364 test sentences
- NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 Train: 1085 sentences
2023-10-25 21:33:51,880 (train_with_dev=False, train_with_test=False)
2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 Training Params:
2023-10-25 21:33:51,880 - learning_rate: "5e-05"
2023-10-25 21:33:51,880 - mini_batch_size: "8"
2023-10-25 21:33:51,880 - max_epochs: "10"
2023-10-25 21:33:51,880 - shuffle: "True"
2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 Plugins:
2023-10-25 21:33:51,880 - TensorboardLogger
2023-10-25 21:33:51,880 - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 21:33:51,880 - metric: "('micro avg', 'f1-score')"
2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,880 Computation:
2023-10-25 21:33:51,880 - compute on device: cuda:0
2023-10-25 21:33:51,880 - embedding storage: none
2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,881 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
2023-10-25 21:33:51,881 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 21:33:52,790 epoch 1 - iter 13/136 - loss 2.59051122 - time (sec): 0.91 - samples/sec: 5504.78 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:33:53,806 epoch 1 - iter 26/136 - loss 2.00418505 - time (sec): 1.92 - samples/sec: 5261.02 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:33:54,806 epoch 1 - iter 39/136 - loss 1.53400120 - time (sec): 2.92 - samples/sec: 5235.21 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:33:55,907 epoch 1 - iter 52/136 - loss 1.25236188 - time (sec): 4.03 - samples/sec: 5213.17 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:33:56,961 epoch 1 - iter 65/136 - loss 1.09370900 - time (sec): 5.08 - samples/sec: 5086.47 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:33:58,003 epoch 1 - iter 78/136 - loss 0.96770702 - time (sec): 6.12 - samples/sec: 5037.96 - lr: 0.000028 - momentum: 0.000000
2023-10-25 21:33:59,051 epoch 1 - iter 91/136 - loss 0.86306761 - time (sec): 7.17 - samples/sec: 5068.05 - lr: 0.000033 - momentum: 0.000000
2023-10-25 21:34:00,036 epoch 1 - iter 104/136 - loss 0.78919472 - time (sec): 8.15 - samples/sec: 5034.91 - lr: 0.000038 - momentum: 0.000000
2023-10-25 21:34:01,075 epoch 1 - iter 117/136 - loss 0.72503737 - time (sec): 9.19 - samples/sec: 5003.90 - lr: 0.000043 - momentum: 0.000000
2023-10-25 21:34:01,983 epoch 1 - iter 130/136 - loss 0.68591323 - time (sec): 10.10 - samples/sec: 4944.79 - lr: 0.000047 - momentum: 0.000000
2023-10-25 21:34:02,385 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:02,385 EPOCH 1 done: loss 0.6651 - lr: 0.000047
2023-10-25 21:34:03,425 DEV : loss 0.12261621654033661 - f1-score (micro avg) 0.7132
2023-10-25 21:34:03,431 saving best model
2023-10-25 21:34:03,923 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:04,893 epoch 2 - iter 13/136 - loss 0.12096013 - time (sec): 0.97 - samples/sec: 5279.05 - lr: 0.000050 - momentum: 0.000000
2023-10-25 21:34:05,859 epoch 2 - iter 26/136 - loss 0.13795080 - time (sec): 1.93 - samples/sec: 5464.64 - lr: 0.000049 - momentum: 0.000000
2023-10-25 21:34:06,909 epoch 2 - iter 39/136 - loss 0.13603380 - time (sec): 2.98 - samples/sec: 4998.10 - lr: 0.000048 - momentum: 0.000000
2023-10-25 21:34:07,877 epoch 2 - iter 52/136 - loss 0.13411210 - time (sec): 3.95 - samples/sec: 4984.89 - lr: 0.000048 - momentum: 0.000000
2023-10-25 21:34:08,809 epoch 2 - iter 65/136 - loss 0.12883628 - time (sec): 4.88 - samples/sec: 5023.44 - lr: 0.000047 - momentum: 0.000000
2023-10-25 21:34:09,762 epoch 2 - iter 78/136 - loss 0.13332562 - time (sec): 5.84 - samples/sec: 5105.30 - lr: 0.000047 - momentum: 0.000000
2023-10-25 21:34:10,762 epoch 2 - iter 91/136 - loss 0.13183996 - time (sec): 6.84 - samples/sec: 5115.96 - lr: 0.000046 - momentum: 0.000000
2023-10-25 21:34:11,773 epoch 2 - iter 104/136 - loss 0.13051739 - time (sec): 7.85 - samples/sec: 5030.07 - lr: 0.000046 - momentum: 0.000000
2023-10-25 21:34:12,740 epoch 2 - iter 117/136 - loss 0.12896418 - time (sec): 8.82 - samples/sec: 5111.03 - lr: 0.000045 - momentum: 0.000000
2023-10-25 21:34:13,702 epoch 2 - iter 130/136 - loss 0.12638642 - time (sec): 9.78 - samples/sec: 5071.78 - lr: 0.000045 - momentum: 0.000000
2023-10-25 21:34:14,159 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:14,159 EPOCH 2 done: loss 0.1251 - lr: 0.000045
2023-10-25 21:34:15,382 DEV : loss 0.10230904072523117 - f1-score (micro avg) 0.769
2023-10-25 21:34:15,388 saving best model
2023-10-25 21:34:16,085 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:17,037 epoch 3 - iter 13/136 - loss 0.06535754 - time (sec): 0.95 - samples/sec: 4487.39 - lr: 0.000044 - momentum: 0.000000
2023-10-25 21:34:17,959 epoch 3 - iter 26/136 - loss 0.07728296 - time (sec): 1.87 - samples/sec: 4793.63 - lr: 0.000043 - momentum: 0.000000
2023-10-25 21:34:19,031 epoch 3 - iter 39/136 - loss 0.06353931 - time (sec): 2.94 - samples/sec: 4846.67 - lr: 0.000043 - momentum: 0.000000
2023-10-25 21:34:19,925 epoch 3 - iter 52/136 - loss 0.06837432 - time (sec): 3.84 - samples/sec: 4968.20 - lr: 0.000042 - momentum: 0.000000
2023-10-25 21:34:20,989 epoch 3 - iter 65/136 - loss 0.06431996 - time (sec): 4.90 - samples/sec: 4916.87 - lr: 0.000042 - momentum: 0.000000
2023-10-25 21:34:22,022 epoch 3 - iter 78/136 - loss 0.06167304 - time (sec): 5.93 - samples/sec: 5110.38 - lr: 0.000041 - momentum: 0.000000
2023-10-25 21:34:23,093 epoch 3 - iter 91/136 - loss 0.06277312 - time (sec): 7.01 - samples/sec: 5092.42 - lr: 0.000041 - momentum: 0.000000
2023-10-25 21:34:23,978 epoch 3 - iter 104/136 - loss 0.06304171 - time (sec): 7.89 - samples/sec: 5074.43 - lr: 0.000040 - momentum: 0.000000
2023-10-25 21:34:24,902 epoch 3 - iter 117/136 - loss 0.06234476 - time (sec): 8.81 - samples/sec: 5029.02 - lr: 0.000040 - momentum: 0.000000
2023-10-25 21:34:25,862 epoch 3 - iter 130/136 - loss 0.06152829 - time (sec): 9.77 - samples/sec: 5041.98 - lr: 0.000039 - momentum: 0.000000
2023-10-25 21:34:26,356 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:26,357 EPOCH 3 done: loss 0.0619 - lr: 0.000039
2023-10-25 21:34:27,513 DEV : loss 0.11677566170692444 - f1-score (micro avg) 0.7711
2023-10-25 21:34:27,519 saving best model
2023-10-25 21:34:28,211 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:29,551 epoch 4 - iter 13/136 - loss 0.03055324 - time (sec): 1.34 - samples/sec: 4020.86 - lr: 0.000038 - momentum: 0.000000
2023-10-25 21:34:30,638 epoch 4 - iter 26/136 - loss 0.03116300 - time (sec): 2.42 - samples/sec: 4639.52 - lr: 0.000038 - momentum: 0.000000
2023-10-25 21:34:31,721 epoch 4 - iter 39/136 - loss 0.03021750 - time (sec): 3.51 - samples/sec: 4715.23 - lr: 0.000037 - momentum: 0.000000
2023-10-25 21:34:32,625 epoch 4 - iter 52/136 - loss 0.02989708 - time (sec): 4.41 - samples/sec: 4771.58 - lr: 0.000037 - momentum: 0.000000
2023-10-25 21:34:33,518 epoch 4 - iter 65/136 - loss 0.03206761 - time (sec): 5.30 - samples/sec: 4780.00 - lr: 0.000036 - momentum: 0.000000
2023-10-25 21:34:34,528 epoch 4 - iter 78/136 - loss 0.03406822 - time (sec): 6.31 - samples/sec: 4756.18 - lr: 0.000036 - momentum: 0.000000
2023-10-25 21:34:35,598 epoch 4 - iter 91/136 - loss 0.03482818 - time (sec): 7.38 - samples/sec: 4768.44 - lr: 0.000035 - momentum: 0.000000
2023-10-25 21:34:36,625 epoch 4 - iter 104/136 - loss 0.03447137 - time (sec): 8.41 - samples/sec: 4839.62 - lr: 0.000035 - momentum: 0.000000
2023-10-25 21:34:37,523 epoch 4 - iter 117/136 - loss 0.03504448 - time (sec): 9.31 - samples/sec: 4838.91 - lr: 0.000034 - momentum: 0.000000
2023-10-25 21:34:38,577 epoch 4 - iter 130/136 - loss 0.03602045 - time (sec): 10.36 - samples/sec: 4814.68 - lr: 0.000034 - momentum: 0.000000
2023-10-25 21:34:38,986 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:38,987 EPOCH 4 done: loss 0.0358 - lr: 0.000034
2023-10-25 21:34:40,156 DEV : loss 0.11416536569595337 - f1-score (micro avg) 0.8133
2023-10-25 21:34:40,164 saving best model
2023-10-25 21:34:40,872 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:41,893 epoch 5 - iter 13/136 - loss 0.01946253 - time (sec): 1.02 - samples/sec: 4960.50 - lr: 0.000033 - momentum: 0.000000
2023-10-25 21:34:42,855 epoch 5 - iter 26/136 - loss 0.01547288 - time (sec): 1.98 - samples/sec: 4757.71 - lr: 0.000032 - momentum: 0.000000
2023-10-25 21:34:43,781 epoch 5 - iter 39/136 - loss 0.01856037 - time (sec): 2.91 - samples/sec: 4834.98 - lr: 0.000032 - momentum: 0.000000
2023-10-25 21:34:44,751 epoch 5 - iter 52/136 - loss 0.02123076 - time (sec): 3.88 - samples/sec: 4870.86 - lr: 0.000031 - momentum: 0.000000
2023-10-25 21:34:45,642 epoch 5 - iter 65/136 - loss 0.02421228 - time (sec): 4.77 - samples/sec: 4872.99 - lr: 0.000031 - momentum: 0.000000
2023-10-25 21:34:46,757 epoch 5 - iter 78/136 - loss 0.02165472 - time (sec): 5.88 - samples/sec: 4950.75 - lr: 0.000030 - momentum: 0.000000
2023-10-25 21:34:47,991 epoch 5 - iter 91/136 - loss 0.02043650 - time (sec): 7.12 - samples/sec: 4934.45 - lr: 0.000030 - momentum: 0.000000
2023-10-25 21:34:48,983 epoch 5 - iter 104/136 - loss 0.02120918 - time (sec): 8.11 - samples/sec: 4956.52 - lr: 0.000029 - momentum: 0.000000
2023-10-25 21:34:49,861 epoch 5 - iter 117/136 - loss 0.02482853 - time (sec): 8.99 - samples/sec: 4962.83 - lr: 0.000029 - momentum: 0.000000
2023-10-25 21:34:50,832 epoch 5 - iter 130/136 - loss 0.02472568 - time (sec): 9.96 - samples/sec: 4991.68 - lr: 0.000028 - momentum: 0.000000
2023-10-25 21:34:51,249 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:51,249 EPOCH 5 done: loss 0.0240 - lr: 0.000028
2023-10-25 21:34:52,460 DEV : loss 0.12781116366386414 - f1-score (micro avg) 0.8117
2023-10-25 21:34:52,467 ----------------------------------------------------------------------------------------------------
2023-10-25 21:34:53,956 epoch 6 - iter 13/136 - loss 0.00771416 - time (sec): 1.49 - samples/sec: 3794.62 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:34:55,019 epoch 6 - iter 26/136 - loss 0.01804796 - time (sec): 2.55 - samples/sec: 4164.42 - lr: 0.000027 - momentum: 0.000000
2023-10-25 21:34:55,948 epoch 6 - iter 39/136 - loss 0.01483424 - time (sec): 3.48 - samples/sec: 4473.84 - lr: 0.000026 - momentum: 0.000000
2023-10-25 21:34:56,965 epoch 6 - iter 52/136 - loss 0.01612002 - time (sec): 4.50 - samples/sec: 4502.50 - lr: 0.000026 - momentum: 0.000000
2023-10-25 21:34:57,931 epoch 6 - iter 65/136 - loss 0.01886579 - time (sec): 5.46 - samples/sec: 4495.53 - lr: 0.000025 - momentum: 0.000000
2023-10-25 21:34:58,949 epoch 6 - iter 78/136 - loss 0.01674238 - time (sec): 6.48 - samples/sec: 4628.11 - lr: 0.000025 - momentum: 0.000000
2023-10-25 21:34:59,937 epoch 6 - iter 91/136 - loss 0.01760742 - time (sec): 7.47 - samples/sec: 4692.38 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:35:00,995 epoch 6 - iter 104/136 - loss 0.01821699 - time (sec): 8.53 - samples/sec: 4795.24 - lr: 0.000024 - momentum: 0.000000
2023-10-25 21:35:02,018 epoch 6 - iter 117/136 - loss 0.02000563 - time (sec): 9.55 - samples/sec: 4754.41 - lr: 0.000023 - momentum: 0.000000
2023-10-25 21:35:02,921 epoch 6 - iter 130/136 - loss 0.01883848 - time (sec): 10.45 - samples/sec: 4821.33 - lr: 0.000023 - momentum: 0.000000
2023-10-25 21:35:03,286 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:03,286 EPOCH 6 done: loss 0.0184 - lr: 0.000023
2023-10-25 21:35:04,573 DEV : loss 0.14983585476875305 - f1-score (micro avg) 0.8152
2023-10-25 21:35:04,580 saving best model
2023-10-25 21:35:05,282 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:06,301 epoch 7 - iter 13/136 - loss 0.01240694 - time (sec): 1.02 - samples/sec: 4330.78 - lr: 0.000022 - momentum: 0.000000
2023-10-25 21:35:07,183 epoch 7 - iter 26/136 - loss 0.01223001 - time (sec): 1.90 - samples/sec: 4670.10 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:35:08,168 epoch 7 - iter 39/136 - loss 0.01307552 - time (sec): 2.88 - samples/sec: 4570.45 - lr: 0.000021 - momentum: 0.000000
2023-10-25 21:35:09,250 epoch 7 - iter 52/136 - loss 0.01143417 - time (sec): 3.97 - samples/sec: 4751.28 - lr: 0.000020 - momentum: 0.000000
2023-10-25 21:35:10,157 epoch 7 - iter 65/136 - loss 0.01047760 - time (sec): 4.87 - samples/sec: 4788.91 - lr: 0.000020 - momentum: 0.000000
2023-10-25 21:35:11,094 epoch 7 - iter 78/136 - loss 0.01355259 - time (sec): 5.81 - samples/sec: 4932.77 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:35:12,100 epoch 7 - iter 91/136 - loss 0.01486358 - time (sec): 6.82 - samples/sec: 4996.59 - lr: 0.000019 - momentum: 0.000000
2023-10-25 21:35:13,026 epoch 7 - iter 104/136 - loss 0.01535576 - time (sec): 7.74 - samples/sec: 5024.62 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:35:14,023 epoch 7 - iter 117/136 - loss 0.01407148 - time (sec): 8.74 - samples/sec: 5059.63 - lr: 0.000018 - momentum: 0.000000
2023-10-25 21:35:14,953 epoch 7 - iter 130/136 - loss 0.01377123 - time (sec): 9.67 - samples/sec: 5086.11 - lr: 0.000017 - momentum: 0.000000
2023-10-25 21:35:15,457 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:15,457 EPOCH 7 done: loss 0.0141 - lr: 0.000017
2023-10-25 21:35:16,727 DEV : loss 0.1700810343027115 - f1-score (micro avg) 0.8125
2023-10-25 21:35:16,733 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:17,638 epoch 8 - iter 13/136 - loss 0.00268544 - time (sec): 0.90 - samples/sec: 4952.01 - lr: 0.000016 - momentum: 0.000000
2023-10-25 21:35:19,021 epoch 8 - iter 26/136 - loss 0.00772798 - time (sec): 2.29 - samples/sec: 4415.85 - lr: 0.000016 - momentum: 0.000000
2023-10-25 21:35:20,065 epoch 8 - iter 39/136 - loss 0.00859103 - time (sec): 3.33 - samples/sec: 4731.91 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:35:21,066 epoch 8 - iter 52/136 - loss 0.01223108 - time (sec): 4.33 - samples/sec: 4749.17 - lr: 0.000015 - momentum: 0.000000
2023-10-25 21:35:22,005 epoch 8 - iter 65/136 - loss 0.01102516 - time (sec): 5.27 - samples/sec: 4730.92 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:35:22,995 epoch 8 - iter 78/136 - loss 0.01255129 - time (sec): 6.26 - samples/sec: 4887.61 - lr: 0.000014 - momentum: 0.000000
2023-10-25 21:35:23,945 epoch 8 - iter 91/136 - loss 0.01134563 - time (sec): 7.21 - samples/sec: 4920.30 - lr: 0.000013 - momentum: 0.000000
2023-10-25 21:35:24,996 epoch 8 - iter 104/136 - loss 0.01063784 - time (sec): 8.26 - samples/sec: 4886.69 - lr: 0.000013 - momentum: 0.000000
2023-10-25 21:35:25,876 epoch 8 - iter 117/136 - loss 0.01079658 - time (sec): 9.14 - samples/sec: 4920.33 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:35:26,908 epoch 8 - iter 130/136 - loss 0.00982405 - time (sec): 10.17 - samples/sec: 4907.66 - lr: 0.000012 - momentum: 0.000000
2023-10-25 21:35:27,362 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:27,362 EPOCH 8 done: loss 0.0104 - lr: 0.000012
2023-10-25 21:35:28,655 DEV : loss 0.17804576456546783 - f1-score (micro avg) 0.8116
2023-10-25 21:35:28,661 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:29,627 epoch 9 - iter 13/136 - loss 0.00055046 - time (sec): 0.96 - samples/sec: 4989.89 - lr: 0.000011 - momentum: 0.000000
2023-10-25 21:35:30,468 epoch 9 - iter 26/136 - loss 0.00298412 - time (sec): 1.81 - samples/sec: 4763.26 - lr: 0.000010 - momentum: 0.000000
2023-10-25 21:35:31,439 epoch 9 - iter 39/136 - loss 0.00647008 - time (sec): 2.78 - samples/sec: 4928.77 - lr: 0.000010 - momentum: 0.000000
2023-10-25 21:35:32,428 epoch 9 - iter 52/136 - loss 0.00565494 - time (sec): 3.77 - samples/sec: 4839.08 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:35:33,500 epoch 9 - iter 65/136 - loss 0.00505945 - time (sec): 4.84 - samples/sec: 4901.28 - lr: 0.000009 - momentum: 0.000000
2023-10-25 21:35:34,602 epoch 9 - iter 78/136 - loss 0.00449225 - time (sec): 5.94 - samples/sec: 4962.79 - lr: 0.000008 - momentum: 0.000000
2023-10-25 21:35:35,623 epoch 9 - iter 91/136 - loss 0.00512371 - time (sec): 6.96 - samples/sec: 5020.44 - lr: 0.000008 - momentum: 0.000000
2023-10-25 21:35:36,716 epoch 9 - iter 104/136 - loss 0.00515854 - time (sec): 8.05 - samples/sec: 5076.11 - lr: 0.000007 - momentum: 0.000000
2023-10-25 21:35:37,644 epoch 9 - iter 117/136 - loss 0.00609712 - time (sec): 8.98 - samples/sec: 5112.01 - lr: 0.000007 - momentum: 0.000000
2023-10-25 21:35:38,560 epoch 9 - iter 130/136 - loss 0.00628290 - time (sec): 9.90 - samples/sec: 5080.59 - lr: 0.000006 - momentum: 0.000000
2023-10-25 21:35:38,954 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:38,954 EPOCH 9 done: loss 0.0064 - lr: 0.000006
2023-10-25 21:35:40,225 DEV : loss 0.18354582786560059 - f1-score (micro avg) 0.8175
2023-10-25 21:35:40,231 saving best model
2023-10-25 21:35:40,903 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:41,884 epoch 10 - iter 13/136 - loss 0.00268180 - time (sec): 0.98 - samples/sec: 4610.51 - lr: 0.000005 - momentum: 0.000000
2023-10-25 21:35:43,155 epoch 10 - iter 26/136 - loss 0.00574221 - time (sec): 2.25 - samples/sec: 4107.44 - lr: 0.000005 - momentum: 0.000000
2023-10-25 21:35:44,144 epoch 10 - iter 39/136 - loss 0.00437948 - time (sec): 3.24 - samples/sec: 4659.58 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:35:45,004 epoch 10 - iter 52/136 - loss 0.00591017 - time (sec): 4.10 - samples/sec: 4701.14 - lr: 0.000004 - momentum: 0.000000
2023-10-25 21:35:45,924 epoch 10 - iter 65/136 - loss 0.00477376 - time (sec): 5.02 - samples/sec: 4776.88 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:35:47,009 epoch 10 - iter 78/136 - loss 0.00422044 - time (sec): 6.10 - samples/sec: 4768.42 - lr: 0.000003 - momentum: 0.000000
2023-10-25 21:35:48,051 epoch 10 - iter 91/136 - loss 0.00414085 - time (sec): 7.15 - samples/sec: 4778.06 - lr: 0.000002 - momentum: 0.000000
2023-10-25 21:35:48,971 epoch 10 - iter 104/136 - loss 0.00387906 - time (sec): 8.07 - samples/sec: 4878.30 - lr: 0.000002 - momentum: 0.000000
2023-10-25 21:35:49,893 epoch 10 - iter 117/136 - loss 0.00431272 - time (sec): 8.99 - samples/sec: 4954.92 - lr: 0.000001 - momentum: 0.000000
2023-10-25 21:35:50,958 epoch 10 - iter 130/136 - loss 0.00472815 - time (sec): 10.05 - samples/sec: 4952.02 - lr: 0.000000 - momentum: 0.000000
2023-10-25 21:35:51,450 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:51,451 EPOCH 10 done: loss 0.0052 - lr: 0.000000
2023-10-25 21:35:52,725 DEV : loss 0.18221181631088257 - f1-score (micro avg) 0.825
2023-10-25 21:35:52,731 saving best model
2023-10-25 21:35:53,934 ----------------------------------------------------------------------------------------------------
2023-10-25 21:35:53,935 Loading model from best epoch ...
2023-10-25 21:35:55,878 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-25 21:35:57,804
Results:
- F-score (micro) 0.7849
- F-score (macro) 0.7239
- Accuracy 0.6605
By class:
precision recall f1-score support
LOC 0.8349 0.8750 0.8545 312
PER 0.6842 0.8750 0.7679 208
ORG 0.4259 0.4182 0.4220 55
HumanProd 0.8000 0.9091 0.8511 22
micro avg 0.7411 0.8342 0.7849 597
macro avg 0.6862 0.7693 0.7239 597
weighted avg 0.7434 0.8342 0.7843 597
2023-10-25 21:35:57,804 ----------------------------------------------------------------------------------------------------
|