File size: 25,393 Bytes
400e985 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 |
2023-10-12 22:42:25,718 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,721 Model: "SequenceTagger(
(embeddings): ByT5Embeddings(
(model): T5EncoderModel(
(shared): Embedding(384, 1472)
(encoder): T5Stack(
(embed_tokens): Embedding(384, 1472)
(block): ModuleList(
(0): T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
(relative_attention_bias): Embedding(32, 6)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(1-11): 11 x T5Block(
(layer): ModuleList(
(0): T5LayerSelfAttention(
(SelfAttention): T5Attention(
(q): Linear(in_features=1472, out_features=384, bias=False)
(k): Linear(in_features=1472, out_features=384, bias=False)
(v): Linear(in_features=1472, out_features=384, bias=False)
(o): Linear(in_features=384, out_features=1472, bias=False)
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(1): T5LayerFF(
(DenseReluDense): T5DenseGatedActDense(
(wi_0): Linear(in_features=1472, out_features=3584, bias=False)
(wi_1): Linear(in_features=1472, out_features=3584, bias=False)
(wo): Linear(in_features=3584, out_features=1472, bias=False)
(dropout): Dropout(p=0.1, inplace=False)
(act): NewGELUActivation()
)
(layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=1472, out_features=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-12 22:42:25,721 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,721 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
2023-10-12 22:42:25,721 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,721 Train: 14465 sentences
2023-10-12 22:42:25,721 (train_with_dev=False, train_with_test=False)
2023-10-12 22:42:25,722 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,722 Training Params:
2023-10-12 22:42:25,722 - learning_rate: "0.00015"
2023-10-12 22:42:25,722 - mini_batch_size: "8"
2023-10-12 22:42:25,722 - max_epochs: "10"
2023-10-12 22:42:25,722 - shuffle: "True"
2023-10-12 22:42:25,722 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,722 Plugins:
2023-10-12 22:42:25,722 - TensorboardLogger
2023-10-12 22:42:25,722 - LinearScheduler | warmup_fraction: '0.1'
2023-10-12 22:42:25,722 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,722 Final evaluation on model from best epoch (best-model.pt)
2023-10-12 22:42:25,722 - metric: "('micro avg', 'f1-score')"
2023-10-12 22:42:25,722 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,722 Computation:
2023-10-12 22:42:25,723 - compute on device: cuda:0
2023-10-12 22:42:25,723 - embedding storage: none
2023-10-12 22:42:25,723 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,723 Model training base path: "hmbench-letemps/fr-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-1"
2023-10-12 22:42:25,723 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,723 ----------------------------------------------------------------------------------------------------
2023-10-12 22:42:25,723 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-12 22:44:07,805 epoch 1 - iter 180/1809 - loss 2.57222062 - time (sec): 102.08 - samples/sec: 376.55 - lr: 0.000015 - momentum: 0.000000
2023-10-12 22:45:47,049 epoch 1 - iter 360/1809 - loss 2.35786106 - time (sec): 201.32 - samples/sec: 377.04 - lr: 0.000030 - momentum: 0.000000
2023-10-12 22:47:19,208 epoch 1 - iter 540/1809 - loss 2.01770182 - time (sec): 293.48 - samples/sec: 384.68 - lr: 0.000045 - momentum: 0.000000
2023-10-12 22:48:49,641 epoch 1 - iter 720/1809 - loss 1.66056163 - time (sec): 383.92 - samples/sec: 395.07 - lr: 0.000060 - momentum: 0.000000
2023-10-12 22:50:18,165 epoch 1 - iter 900/1809 - loss 1.38841808 - time (sec): 472.44 - samples/sec: 400.83 - lr: 0.000075 - momentum: 0.000000
2023-10-12 22:51:47,112 epoch 1 - iter 1080/1809 - loss 1.19834151 - time (sec): 561.39 - samples/sec: 402.83 - lr: 0.000089 - momentum: 0.000000
2023-10-12 22:53:15,665 epoch 1 - iter 1260/1809 - loss 1.05788394 - time (sec): 649.94 - samples/sec: 404.31 - lr: 0.000104 - momentum: 0.000000
2023-10-12 22:54:46,068 epoch 1 - iter 1440/1809 - loss 0.94563350 - time (sec): 740.34 - samples/sec: 406.31 - lr: 0.000119 - momentum: 0.000000
2023-10-12 22:56:17,923 epoch 1 - iter 1620/1809 - loss 0.85880262 - time (sec): 832.20 - samples/sec: 407.21 - lr: 0.000134 - momentum: 0.000000
2023-10-12 22:57:51,086 epoch 1 - iter 1800/1809 - loss 0.78348215 - time (sec): 925.36 - samples/sec: 408.35 - lr: 0.000149 - momentum: 0.000000
2023-10-12 22:57:55,498 ----------------------------------------------------------------------------------------------------
2023-10-12 22:57:55,498 EPOCH 1 done: loss 0.7800 - lr: 0.000149
2023-10-12 22:58:31,841 DEV : loss 0.1441633254289627 - f1-score (micro avg) 0.3673
2023-10-12 22:58:31,902 saving best model
2023-10-12 22:58:32,765 ----------------------------------------------------------------------------------------------------
2023-10-12 23:00:09,462 epoch 2 - iter 180/1809 - loss 0.11170747 - time (sec): 96.69 - samples/sec: 400.61 - lr: 0.000148 - momentum: 0.000000
2023-10-12 23:01:44,813 epoch 2 - iter 360/1809 - loss 0.11397447 - time (sec): 192.05 - samples/sec: 403.34 - lr: 0.000147 - momentum: 0.000000
2023-10-12 23:03:16,132 epoch 2 - iter 540/1809 - loss 0.11058507 - time (sec): 283.36 - samples/sec: 406.96 - lr: 0.000145 - momentum: 0.000000
2023-10-12 23:04:47,107 epoch 2 - iter 720/1809 - loss 0.10972006 - time (sec): 374.34 - samples/sec: 406.43 - lr: 0.000143 - momentum: 0.000000
2023-10-12 23:06:17,438 epoch 2 - iter 900/1809 - loss 0.10675904 - time (sec): 464.67 - samples/sec: 405.71 - lr: 0.000142 - momentum: 0.000000
2023-10-12 23:07:48,550 epoch 2 - iter 1080/1809 - loss 0.10643316 - time (sec): 555.78 - samples/sec: 408.15 - lr: 0.000140 - momentum: 0.000000
2023-10-12 23:09:19,398 epoch 2 - iter 1260/1809 - loss 0.10422146 - time (sec): 646.63 - samples/sec: 409.03 - lr: 0.000138 - momentum: 0.000000
2023-10-12 23:10:52,238 epoch 2 - iter 1440/1809 - loss 0.10187179 - time (sec): 739.47 - samples/sec: 409.41 - lr: 0.000137 - momentum: 0.000000
2023-10-12 23:12:23,351 epoch 2 - iter 1620/1809 - loss 0.09902556 - time (sec): 830.58 - samples/sec: 410.91 - lr: 0.000135 - momentum: 0.000000
2023-10-12 23:13:54,328 epoch 2 - iter 1800/1809 - loss 0.09837045 - time (sec): 921.56 - samples/sec: 410.24 - lr: 0.000133 - momentum: 0.000000
2023-10-12 23:13:58,390 ----------------------------------------------------------------------------------------------------
2023-10-12 23:13:58,390 EPOCH 2 done: loss 0.0981 - lr: 0.000133
2023-10-12 23:14:36,178 DEV : loss 0.0997246503829956 - f1-score (micro avg) 0.6206
2023-10-12 23:14:36,235 saving best model
2023-10-12 23:14:38,819 ----------------------------------------------------------------------------------------------------
2023-10-12 23:16:13,637 epoch 3 - iter 180/1809 - loss 0.06267834 - time (sec): 94.81 - samples/sec: 402.42 - lr: 0.000132 - momentum: 0.000000
2023-10-12 23:17:46,059 epoch 3 - iter 360/1809 - loss 0.06023491 - time (sec): 187.24 - samples/sec: 408.98 - lr: 0.000130 - momentum: 0.000000
2023-10-12 23:19:16,706 epoch 3 - iter 540/1809 - loss 0.06190782 - time (sec): 277.88 - samples/sec: 407.79 - lr: 0.000128 - momentum: 0.000000
2023-10-12 23:20:52,077 epoch 3 - iter 720/1809 - loss 0.06109607 - time (sec): 373.25 - samples/sec: 403.10 - lr: 0.000127 - momentum: 0.000000
2023-10-12 23:22:25,696 epoch 3 - iter 900/1809 - loss 0.06165193 - time (sec): 466.87 - samples/sec: 403.46 - lr: 0.000125 - momentum: 0.000000
2023-10-12 23:23:59,309 epoch 3 - iter 1080/1809 - loss 0.06206747 - time (sec): 560.49 - samples/sec: 403.93 - lr: 0.000123 - momentum: 0.000000
2023-10-12 23:25:33,753 epoch 3 - iter 1260/1809 - loss 0.06194083 - time (sec): 654.93 - samples/sec: 404.63 - lr: 0.000122 - momentum: 0.000000
2023-10-12 23:27:05,673 epoch 3 - iter 1440/1809 - loss 0.06118851 - time (sec): 746.85 - samples/sec: 404.71 - lr: 0.000120 - momentum: 0.000000
2023-10-12 23:28:38,308 epoch 3 - iter 1620/1809 - loss 0.06177140 - time (sec): 839.48 - samples/sec: 405.10 - lr: 0.000118 - momentum: 0.000000
2023-10-12 23:30:11,083 epoch 3 - iter 1800/1809 - loss 0.06083773 - time (sec): 932.26 - samples/sec: 405.59 - lr: 0.000117 - momentum: 0.000000
2023-10-12 23:30:15,308 ----------------------------------------------------------------------------------------------------
2023-10-12 23:30:15,309 EPOCH 3 done: loss 0.0608 - lr: 0.000117
2023-10-12 23:30:54,908 DEV : loss 0.14741627871990204 - f1-score (micro avg) 0.6255
2023-10-12 23:30:54,971 saving best model
2023-10-12 23:30:57,602 ----------------------------------------------------------------------------------------------------
2023-10-12 23:32:29,140 epoch 4 - iter 180/1809 - loss 0.04432308 - time (sec): 91.53 - samples/sec: 402.88 - lr: 0.000115 - momentum: 0.000000
2023-10-12 23:34:01,093 epoch 4 - iter 360/1809 - loss 0.04554957 - time (sec): 183.49 - samples/sec: 415.77 - lr: 0.000113 - momentum: 0.000000
2023-10-12 23:35:32,639 epoch 4 - iter 540/1809 - loss 0.04344483 - time (sec): 275.03 - samples/sec: 412.63 - lr: 0.000112 - momentum: 0.000000
2023-10-12 23:37:05,804 epoch 4 - iter 720/1809 - loss 0.04221052 - time (sec): 368.20 - samples/sec: 408.78 - lr: 0.000110 - momentum: 0.000000
2023-10-12 23:38:39,875 epoch 4 - iter 900/1809 - loss 0.04316114 - time (sec): 462.27 - samples/sec: 405.17 - lr: 0.000108 - momentum: 0.000000
2023-10-12 23:40:13,662 epoch 4 - iter 1080/1809 - loss 0.04415013 - time (sec): 556.05 - samples/sec: 405.42 - lr: 0.000107 - momentum: 0.000000
2023-10-12 23:41:44,160 epoch 4 - iter 1260/1809 - loss 0.04402235 - time (sec): 646.55 - samples/sec: 406.88 - lr: 0.000105 - momentum: 0.000000
2023-10-12 23:43:15,665 epoch 4 - iter 1440/1809 - loss 0.04423013 - time (sec): 738.06 - samples/sec: 407.84 - lr: 0.000103 - momentum: 0.000000
2023-10-12 23:44:47,822 epoch 4 - iter 1620/1809 - loss 0.04340254 - time (sec): 830.22 - samples/sec: 409.92 - lr: 0.000102 - momentum: 0.000000
2023-10-12 23:46:22,508 epoch 4 - iter 1800/1809 - loss 0.04342319 - time (sec): 924.90 - samples/sec: 408.87 - lr: 0.000100 - momentum: 0.000000
2023-10-12 23:46:26,848 ----------------------------------------------------------------------------------------------------
2023-10-12 23:46:26,848 EPOCH 4 done: loss 0.0437 - lr: 0.000100
2023-10-12 23:47:04,639 DEV : loss 0.1756805181503296 - f1-score (micro avg) 0.6169
2023-10-12 23:47:04,696 ----------------------------------------------------------------------------------------------------
2023-10-12 23:48:38,776 epoch 5 - iter 180/1809 - loss 0.03157894 - time (sec): 94.08 - samples/sec: 407.31 - lr: 0.000098 - momentum: 0.000000
2023-10-12 23:50:11,001 epoch 5 - iter 360/1809 - loss 0.02830269 - time (sec): 186.30 - samples/sec: 411.52 - lr: 0.000097 - momentum: 0.000000
2023-10-12 23:51:41,162 epoch 5 - iter 540/1809 - loss 0.02843117 - time (sec): 276.46 - samples/sec: 409.58 - lr: 0.000095 - momentum: 0.000000
2023-10-12 23:53:15,346 epoch 5 - iter 720/1809 - loss 0.03067151 - time (sec): 370.65 - samples/sec: 403.73 - lr: 0.000093 - momentum: 0.000000
2023-10-12 23:54:49,546 epoch 5 - iter 900/1809 - loss 0.03160142 - time (sec): 464.85 - samples/sec: 402.68 - lr: 0.000092 - momentum: 0.000000
2023-10-12 23:56:20,496 epoch 5 - iter 1080/1809 - loss 0.03108926 - time (sec): 555.80 - samples/sec: 405.37 - lr: 0.000090 - momentum: 0.000000
2023-10-12 23:57:47,978 epoch 5 - iter 1260/1809 - loss 0.03185705 - time (sec): 643.28 - samples/sec: 408.31 - lr: 0.000088 - momentum: 0.000000
2023-10-12 23:59:20,267 epoch 5 - iter 1440/1809 - loss 0.03333433 - time (sec): 735.57 - samples/sec: 407.23 - lr: 0.000087 - momentum: 0.000000
2023-10-13 00:00:56,869 epoch 5 - iter 1620/1809 - loss 0.03273045 - time (sec): 832.17 - samples/sec: 408.49 - lr: 0.000085 - momentum: 0.000000
2023-10-13 00:02:34,892 epoch 5 - iter 1800/1809 - loss 0.03316525 - time (sec): 930.19 - samples/sec: 406.50 - lr: 0.000083 - momentum: 0.000000
2023-10-13 00:02:39,155 ----------------------------------------------------------------------------------------------------
2023-10-13 00:02:39,155 EPOCH 5 done: loss 0.0331 - lr: 0.000083
2023-10-13 00:03:20,597 DEV : loss 0.23575519025325775 - f1-score (micro avg) 0.617
2023-10-13 00:03:20,661 ----------------------------------------------------------------------------------------------------
2023-10-13 00:04:52,695 epoch 6 - iter 180/1809 - loss 0.02388711 - time (sec): 92.03 - samples/sec: 408.81 - lr: 0.000082 - momentum: 0.000000
2023-10-13 00:06:24,791 epoch 6 - iter 360/1809 - loss 0.02401339 - time (sec): 184.13 - samples/sec: 411.47 - lr: 0.000080 - momentum: 0.000000
2023-10-13 00:07:59,259 epoch 6 - iter 540/1809 - loss 0.02310670 - time (sec): 278.60 - samples/sec: 406.14 - lr: 0.000078 - momentum: 0.000000
2023-10-13 00:09:31,467 epoch 6 - iter 720/1809 - loss 0.02334831 - time (sec): 370.80 - samples/sec: 408.26 - lr: 0.000077 - momentum: 0.000000
2023-10-13 00:11:06,383 epoch 6 - iter 900/1809 - loss 0.02452192 - time (sec): 465.72 - samples/sec: 407.11 - lr: 0.000075 - momentum: 0.000000
2023-10-13 00:12:41,135 epoch 6 - iter 1080/1809 - loss 0.02459648 - time (sec): 560.47 - samples/sec: 405.40 - lr: 0.000073 - momentum: 0.000000
2023-10-13 00:14:17,989 epoch 6 - iter 1260/1809 - loss 0.02521649 - time (sec): 657.33 - samples/sec: 403.03 - lr: 0.000072 - momentum: 0.000000
2023-10-13 00:15:54,582 epoch 6 - iter 1440/1809 - loss 0.02521885 - time (sec): 753.92 - samples/sec: 399.88 - lr: 0.000070 - momentum: 0.000000
2023-10-13 00:17:34,466 epoch 6 - iter 1620/1809 - loss 0.02506005 - time (sec): 853.80 - samples/sec: 397.24 - lr: 0.000068 - momentum: 0.000000
2023-10-13 00:19:10,740 epoch 6 - iter 1800/1809 - loss 0.02442039 - time (sec): 950.08 - samples/sec: 397.99 - lr: 0.000067 - momentum: 0.000000
2023-10-13 00:19:15,046 ----------------------------------------------------------------------------------------------------
2023-10-13 00:19:15,047 EPOCH 6 done: loss 0.0243 - lr: 0.000067
2023-10-13 00:19:55,967 DEV : loss 0.2817913591861725 - f1-score (micro avg) 0.6398
2023-10-13 00:19:56,045 saving best model
2023-10-13 00:19:57,138 ----------------------------------------------------------------------------------------------------
2023-10-13 00:21:32,179 epoch 7 - iter 180/1809 - loss 0.01493884 - time (sec): 95.04 - samples/sec: 388.91 - lr: 0.000065 - momentum: 0.000000
2023-10-13 00:23:05,610 epoch 7 - iter 360/1809 - loss 0.01507536 - time (sec): 188.47 - samples/sec: 401.81 - lr: 0.000063 - momentum: 0.000000
2023-10-13 00:24:41,229 epoch 7 - iter 540/1809 - loss 0.01649935 - time (sec): 284.09 - samples/sec: 399.44 - lr: 0.000062 - momentum: 0.000000
2023-10-13 00:26:17,385 epoch 7 - iter 720/1809 - loss 0.01746454 - time (sec): 380.24 - samples/sec: 397.51 - lr: 0.000060 - momentum: 0.000000
2023-10-13 00:27:48,257 epoch 7 - iter 900/1809 - loss 0.01772093 - time (sec): 471.12 - samples/sec: 400.88 - lr: 0.000058 - momentum: 0.000000
2023-10-13 00:29:15,753 epoch 7 - iter 1080/1809 - loss 0.01691637 - time (sec): 558.61 - samples/sec: 404.51 - lr: 0.000057 - momentum: 0.000000
2023-10-13 00:30:47,556 epoch 7 - iter 1260/1809 - loss 0.01716291 - time (sec): 650.42 - samples/sec: 405.67 - lr: 0.000055 - momentum: 0.000000
2023-10-13 00:32:24,463 epoch 7 - iter 1440/1809 - loss 0.01829192 - time (sec): 747.32 - samples/sec: 403.28 - lr: 0.000053 - momentum: 0.000000
2023-10-13 00:34:06,279 epoch 7 - iter 1620/1809 - loss 0.01866002 - time (sec): 849.14 - samples/sec: 400.09 - lr: 0.000052 - momentum: 0.000000
2023-10-13 00:35:43,193 epoch 7 - iter 1800/1809 - loss 0.01826084 - time (sec): 946.05 - samples/sec: 399.82 - lr: 0.000050 - momentum: 0.000000
2023-10-13 00:35:47,355 ----------------------------------------------------------------------------------------------------
2023-10-13 00:35:47,356 EPOCH 7 done: loss 0.0182 - lr: 0.000050
2023-10-13 00:36:26,299 DEV : loss 0.3023461401462555 - f1-score (micro avg) 0.6502
2023-10-13 00:36:26,356 saving best model
2023-10-13 00:36:28,945 ----------------------------------------------------------------------------------------------------
2023-10-13 00:37:59,940 epoch 8 - iter 180/1809 - loss 0.01451939 - time (sec): 90.99 - samples/sec: 412.53 - lr: 0.000048 - momentum: 0.000000
2023-10-13 00:39:33,475 epoch 8 - iter 360/1809 - loss 0.01255235 - time (sec): 184.52 - samples/sec: 411.41 - lr: 0.000047 - momentum: 0.000000
2023-10-13 00:41:07,633 epoch 8 - iter 540/1809 - loss 0.01182338 - time (sec): 278.68 - samples/sec: 408.87 - lr: 0.000045 - momentum: 0.000000
2023-10-13 00:42:39,556 epoch 8 - iter 720/1809 - loss 0.01274256 - time (sec): 370.61 - samples/sec: 412.85 - lr: 0.000043 - momentum: 0.000000
2023-10-13 00:44:10,716 epoch 8 - iter 900/1809 - loss 0.01253653 - time (sec): 461.77 - samples/sec: 414.98 - lr: 0.000042 - momentum: 0.000000
2023-10-13 00:45:38,696 epoch 8 - iter 1080/1809 - loss 0.01269966 - time (sec): 549.75 - samples/sec: 414.13 - lr: 0.000040 - momentum: 0.000000
2023-10-13 00:47:06,823 epoch 8 - iter 1260/1809 - loss 0.01283451 - time (sec): 637.87 - samples/sec: 415.05 - lr: 0.000038 - momentum: 0.000000
2023-10-13 00:48:38,750 epoch 8 - iter 1440/1809 - loss 0.01300464 - time (sec): 729.80 - samples/sec: 415.22 - lr: 0.000037 - momentum: 0.000000
2023-10-13 00:50:07,404 epoch 8 - iter 1620/1809 - loss 0.01320616 - time (sec): 818.45 - samples/sec: 416.97 - lr: 0.000035 - momentum: 0.000000
2023-10-13 00:51:35,459 epoch 8 - iter 1800/1809 - loss 0.01348805 - time (sec): 906.51 - samples/sec: 417.43 - lr: 0.000033 - momentum: 0.000000
2023-10-13 00:51:39,256 ----------------------------------------------------------------------------------------------------
2023-10-13 00:51:39,256 EPOCH 8 done: loss 0.0134 - lr: 0.000033
2023-10-13 00:52:16,475 DEV : loss 0.3305288553237915 - f1-score (micro avg) 0.6487
2023-10-13 00:52:16,533 ----------------------------------------------------------------------------------------------------
2023-10-13 00:53:46,221 epoch 9 - iter 180/1809 - loss 0.00593172 - time (sec): 89.69 - samples/sec: 414.24 - lr: 0.000032 - momentum: 0.000000
2023-10-13 00:55:18,160 epoch 9 - iter 360/1809 - loss 0.00911510 - time (sec): 181.63 - samples/sec: 411.53 - lr: 0.000030 - momentum: 0.000000
2023-10-13 00:56:48,486 epoch 9 - iter 540/1809 - loss 0.00925733 - time (sec): 271.95 - samples/sec: 412.89 - lr: 0.000028 - momentum: 0.000000
2023-10-13 00:58:22,172 epoch 9 - iter 720/1809 - loss 0.00972486 - time (sec): 365.64 - samples/sec: 416.61 - lr: 0.000027 - momentum: 0.000000
2023-10-13 00:59:59,270 epoch 9 - iter 900/1809 - loss 0.00982915 - time (sec): 462.74 - samples/sec: 410.07 - lr: 0.000025 - momentum: 0.000000
2023-10-13 01:01:31,167 epoch 9 - iter 1080/1809 - loss 0.00992239 - time (sec): 554.63 - samples/sec: 410.23 - lr: 0.000023 - momentum: 0.000000
2023-10-13 01:03:03,196 epoch 9 - iter 1260/1809 - loss 0.00987652 - time (sec): 646.66 - samples/sec: 408.94 - lr: 0.000022 - momentum: 0.000000
2023-10-13 01:04:36,184 epoch 9 - iter 1440/1809 - loss 0.00999639 - time (sec): 739.65 - samples/sec: 409.36 - lr: 0.000020 - momentum: 0.000000
2023-10-13 01:06:10,125 epoch 9 - iter 1620/1809 - loss 0.00981387 - time (sec): 833.59 - samples/sec: 409.53 - lr: 0.000018 - momentum: 0.000000
2023-10-13 01:07:42,547 epoch 9 - iter 1800/1809 - loss 0.00963508 - time (sec): 926.01 - samples/sec: 408.65 - lr: 0.000017 - momentum: 0.000000
2023-10-13 01:07:46,624 ----------------------------------------------------------------------------------------------------
2023-10-13 01:07:46,624 EPOCH 9 done: loss 0.0096 - lr: 0.000017
2023-10-13 01:08:26,098 DEV : loss 0.36490538716316223 - f1-score (micro avg) 0.6474
2023-10-13 01:08:26,158 ----------------------------------------------------------------------------------------------------
2023-10-13 01:09:58,926 epoch 10 - iter 180/1809 - loss 0.01093935 - time (sec): 92.77 - samples/sec: 407.46 - lr: 0.000015 - momentum: 0.000000
2023-10-13 01:11:31,538 epoch 10 - iter 360/1809 - loss 0.00895096 - time (sec): 185.38 - samples/sec: 404.83 - lr: 0.000013 - momentum: 0.000000
2023-10-13 01:13:04,293 epoch 10 - iter 540/1809 - loss 0.00986715 - time (sec): 278.13 - samples/sec: 405.74 - lr: 0.000012 - momentum: 0.000000
2023-10-13 01:14:35,898 epoch 10 - iter 720/1809 - loss 0.00934801 - time (sec): 369.74 - samples/sec: 405.71 - lr: 0.000010 - momentum: 0.000000
2023-10-13 01:16:09,995 epoch 10 - iter 900/1809 - loss 0.00920377 - time (sec): 463.84 - samples/sec: 405.65 - lr: 0.000008 - momentum: 0.000000
2023-10-13 01:17:41,994 epoch 10 - iter 1080/1809 - loss 0.00843499 - time (sec): 555.83 - samples/sec: 406.93 - lr: 0.000007 - momentum: 0.000000
2023-10-13 01:19:11,885 epoch 10 - iter 1260/1809 - loss 0.00837965 - time (sec): 645.72 - samples/sec: 409.24 - lr: 0.000005 - momentum: 0.000000
2023-10-13 01:20:42,654 epoch 10 - iter 1440/1809 - loss 0.00861846 - time (sec): 736.49 - samples/sec: 410.76 - lr: 0.000003 - momentum: 0.000000
2023-10-13 01:22:12,500 epoch 10 - iter 1620/1809 - loss 0.00843137 - time (sec): 826.34 - samples/sec: 412.02 - lr: 0.000002 - momentum: 0.000000
2023-10-13 01:23:41,817 epoch 10 - iter 1800/1809 - loss 0.00810910 - time (sec): 915.66 - samples/sec: 413.30 - lr: 0.000000 - momentum: 0.000000
2023-10-13 01:23:45,653 ----------------------------------------------------------------------------------------------------
2023-10-13 01:23:45,653 EPOCH 10 done: loss 0.0081 - lr: 0.000000
2023-10-13 01:24:25,128 DEV : loss 0.3651101589202881 - f1-score (micro avg) 0.6381
2023-10-13 01:24:26,124 ----------------------------------------------------------------------------------------------------
2023-10-13 01:24:26,126 Loading model from best epoch ...
2023-10-13 01:24:31,655 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
2023-10-13 01:25:29,437
Results:
- F-score (micro) 0.6478
- F-score (macro) 0.5104
- Accuracy 0.4908
By class:
precision recall f1-score support
loc 0.6357 0.7766 0.6992 591
pers 0.5565 0.7591 0.6422 357
org 0.2241 0.1646 0.1898 79
micro avg 0.5864 0.7235 0.6478 1027
macro avg 0.4721 0.5668 0.5104 1027
weighted avg 0.5765 0.7235 0.6402 1027
2023-10-13 01:25:29,437 ----------------------------------------------------------------------------------------------------
|