File size: 25,196 Bytes
9df1844 |
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 |
2023-10-11 19:13:59,349 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,352 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()
)"
2023-10-11 19:13:59,352 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,352 MultiCorpus: 5777 train + 722 dev + 723 test sentences
- NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
2023-10-11 19:13:59,352 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,352 Train: 5777 sentences
2023-10-11 19:13:59,352 (train_with_dev=False, train_with_test=False)
2023-10-11 19:13:59,352 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,352 Training Params:
2023-10-11 19:13:59,352 - learning_rate: "0.00015"
2023-10-11 19:13:59,352 - mini_batch_size: "8"
2023-10-11 19:13:59,353 - max_epochs: "10"
2023-10-11 19:13:59,353 - shuffle: "True"
2023-10-11 19:13:59,353 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,353 Plugins:
2023-10-11 19:13:59,353 - TensorboardLogger
2023-10-11 19:13:59,353 - LinearScheduler | warmup_fraction: '0.1'
2023-10-11 19:13:59,353 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,353 Final evaluation on model from best epoch (best-model.pt)
2023-10-11 19:13:59,353 - metric: "('micro avg', 'f1-score')"
2023-10-11 19:13:59,353 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,353 Computation:
2023-10-11 19:13:59,353 - compute on device: cuda:0
2023-10-11 19:13:59,353 - embedding storage: none
2023-10-11 19:13:59,353 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,353 Model training base path: "hmbench-icdar/nl-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-2"
2023-10-11 19:13:59,354 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,354 ----------------------------------------------------------------------------------------------------
2023-10-11 19:13:59,354 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-11 19:14:44,985 epoch 1 - iter 72/723 - loss 2.57086872 - time (sec): 45.63 - samples/sec: 407.45 - lr: 0.000015 - momentum: 0.000000
2023-10-11 19:15:23,902 epoch 1 - iter 144/723 - loss 2.53330840 - time (sec): 84.55 - samples/sec: 421.96 - lr: 0.000030 - momentum: 0.000000
2023-10-11 19:16:07,025 epoch 1 - iter 216/723 - loss 2.37416485 - time (sec): 127.67 - samples/sec: 422.29 - lr: 0.000045 - momentum: 0.000000
2023-10-11 19:16:48,488 epoch 1 - iter 288/723 - loss 2.16789438 - time (sec): 169.13 - samples/sec: 421.74 - lr: 0.000060 - momentum: 0.000000
2023-10-11 19:17:29,619 epoch 1 - iter 360/723 - loss 1.94703601 - time (sec): 210.26 - samples/sec: 423.82 - lr: 0.000074 - momentum: 0.000000
2023-10-11 19:18:12,121 epoch 1 - iter 432/723 - loss 1.72485908 - time (sec): 252.77 - samples/sec: 422.53 - lr: 0.000089 - momentum: 0.000000
2023-10-11 19:18:54,982 epoch 1 - iter 504/723 - loss 1.52985339 - time (sec): 295.63 - samples/sec: 421.70 - lr: 0.000104 - momentum: 0.000000
2023-10-11 19:19:35,885 epoch 1 - iter 576/723 - loss 1.37738975 - time (sec): 336.53 - samples/sec: 421.04 - lr: 0.000119 - momentum: 0.000000
2023-10-11 19:20:16,171 epoch 1 - iter 648/723 - loss 1.25078985 - time (sec): 376.81 - samples/sec: 422.83 - lr: 0.000134 - momentum: 0.000000
2023-10-11 19:20:56,215 epoch 1 - iter 720/723 - loss 1.15095694 - time (sec): 416.86 - samples/sec: 421.68 - lr: 0.000149 - momentum: 0.000000
2023-10-11 19:20:57,395 ----------------------------------------------------------------------------------------------------
2023-10-11 19:20:57,396 EPOCH 1 done: loss 1.1488 - lr: 0.000149
2023-10-11 19:21:17,705 DEV : loss 0.21648679673671722 - f1-score (micro avg) 0.0123
2023-10-11 19:21:17,740 saving best model
2023-10-11 19:21:18,688 ----------------------------------------------------------------------------------------------------
2023-10-11 19:22:01,303 epoch 2 - iter 72/723 - loss 0.16183662 - time (sec): 42.61 - samples/sec: 399.65 - lr: 0.000148 - momentum: 0.000000
2023-10-11 19:22:42,923 epoch 2 - iter 144/723 - loss 0.16103628 - time (sec): 84.23 - samples/sec: 411.91 - lr: 0.000147 - momentum: 0.000000
2023-10-11 19:23:25,027 epoch 2 - iter 216/723 - loss 0.15369470 - time (sec): 126.34 - samples/sec: 419.60 - lr: 0.000145 - momentum: 0.000000
2023-10-11 19:24:10,544 epoch 2 - iter 288/723 - loss 0.14990715 - time (sec): 171.85 - samples/sec: 413.84 - lr: 0.000143 - momentum: 0.000000
2023-10-11 19:24:54,049 epoch 2 - iter 360/723 - loss 0.14344494 - time (sec): 215.36 - samples/sec: 411.96 - lr: 0.000142 - momentum: 0.000000
2023-10-11 19:25:35,378 epoch 2 - iter 432/723 - loss 0.14132544 - time (sec): 256.69 - samples/sec: 412.37 - lr: 0.000140 - momentum: 0.000000
2023-10-11 19:26:17,204 epoch 2 - iter 504/723 - loss 0.13701095 - time (sec): 298.51 - samples/sec: 412.84 - lr: 0.000138 - momentum: 0.000000
2023-10-11 19:26:59,167 epoch 2 - iter 576/723 - loss 0.13330675 - time (sec): 340.48 - samples/sec: 413.59 - lr: 0.000137 - momentum: 0.000000
2023-10-11 19:27:42,057 epoch 2 - iter 648/723 - loss 0.13052442 - time (sec): 383.37 - samples/sec: 410.86 - lr: 0.000135 - momentum: 0.000000
2023-10-11 19:28:23,642 epoch 2 - iter 720/723 - loss 0.12780591 - time (sec): 424.95 - samples/sec: 413.52 - lr: 0.000133 - momentum: 0.000000
2023-10-11 19:28:24,842 ----------------------------------------------------------------------------------------------------
2023-10-11 19:28:24,843 EPOCH 2 done: loss 0.1278 - lr: 0.000133
2023-10-11 19:28:45,421 DEV : loss 0.1180637776851654 - f1-score (micro avg) 0.6647
2023-10-11 19:28:45,451 saving best model
2023-10-11 19:28:52,913 ----------------------------------------------------------------------------------------------------
2023-10-11 19:29:33,850 epoch 3 - iter 72/723 - loss 0.10015265 - time (sec): 40.91 - samples/sec: 444.71 - lr: 0.000132 - momentum: 0.000000
2023-10-11 19:30:13,514 epoch 3 - iter 144/723 - loss 0.08972155 - time (sec): 80.57 - samples/sec: 438.21 - lr: 0.000130 - momentum: 0.000000
2023-10-11 19:30:52,539 epoch 3 - iter 216/723 - loss 0.08709046 - time (sec): 119.59 - samples/sec: 438.87 - lr: 0.000128 - momentum: 0.000000
2023-10-11 19:31:33,908 epoch 3 - iter 288/723 - loss 0.08496174 - time (sec): 160.96 - samples/sec: 430.63 - lr: 0.000127 - momentum: 0.000000
2023-10-11 19:32:13,347 epoch 3 - iter 360/723 - loss 0.08081415 - time (sec): 200.40 - samples/sec: 432.84 - lr: 0.000125 - momentum: 0.000000
2023-10-11 19:32:54,772 epoch 3 - iter 432/723 - loss 0.08200482 - time (sec): 241.83 - samples/sec: 437.58 - lr: 0.000123 - momentum: 0.000000
2023-10-11 19:33:38,370 epoch 3 - iter 504/723 - loss 0.08119768 - time (sec): 285.42 - samples/sec: 430.71 - lr: 0.000122 - momentum: 0.000000
2023-10-11 19:34:22,240 epoch 3 - iter 576/723 - loss 0.07951784 - time (sec): 329.29 - samples/sec: 425.75 - lr: 0.000120 - momentum: 0.000000
2023-10-11 19:35:04,706 epoch 3 - iter 648/723 - loss 0.07780987 - time (sec): 371.76 - samples/sec: 422.78 - lr: 0.000118 - momentum: 0.000000
2023-10-11 19:35:48,845 epoch 3 - iter 720/723 - loss 0.07699412 - time (sec): 415.90 - samples/sec: 422.44 - lr: 0.000117 - momentum: 0.000000
2023-10-11 19:35:50,187 ----------------------------------------------------------------------------------------------------
2023-10-11 19:35:50,188 EPOCH 3 done: loss 0.0769 - lr: 0.000117
2023-10-11 19:36:12,306 DEV : loss 0.08086864650249481 - f1-score (micro avg) 0.8377
2023-10-11 19:36:12,336 saving best model
2023-10-11 19:36:23,238 ----------------------------------------------------------------------------------------------------
2023-10-11 19:37:04,812 epoch 4 - iter 72/723 - loss 0.06706830 - time (sec): 41.57 - samples/sec: 421.51 - lr: 0.000115 - momentum: 0.000000
2023-10-11 19:37:47,107 epoch 4 - iter 144/723 - loss 0.05669850 - time (sec): 83.86 - samples/sec: 423.73 - lr: 0.000113 - momentum: 0.000000
2023-10-11 19:38:29,958 epoch 4 - iter 216/723 - loss 0.05685534 - time (sec): 126.72 - samples/sec: 416.60 - lr: 0.000112 - momentum: 0.000000
2023-10-11 19:39:11,998 epoch 4 - iter 288/723 - loss 0.05541904 - time (sec): 168.76 - samples/sec: 416.31 - lr: 0.000110 - momentum: 0.000000
2023-10-11 19:39:54,241 epoch 4 - iter 360/723 - loss 0.05734549 - time (sec): 211.00 - samples/sec: 410.12 - lr: 0.000108 - momentum: 0.000000
2023-10-11 19:40:37,348 epoch 4 - iter 432/723 - loss 0.05576876 - time (sec): 254.10 - samples/sec: 412.05 - lr: 0.000107 - momentum: 0.000000
2023-10-11 19:41:20,058 epoch 4 - iter 504/723 - loss 0.05631673 - time (sec): 296.82 - samples/sec: 414.70 - lr: 0.000105 - momentum: 0.000000
2023-10-11 19:42:01,084 epoch 4 - iter 576/723 - loss 0.05413009 - time (sec): 337.84 - samples/sec: 416.26 - lr: 0.000103 - momentum: 0.000000
2023-10-11 19:42:44,112 epoch 4 - iter 648/723 - loss 0.05175789 - time (sec): 380.87 - samples/sec: 419.25 - lr: 0.000102 - momentum: 0.000000
2023-10-11 19:43:24,791 epoch 4 - iter 720/723 - loss 0.05190640 - time (sec): 421.55 - samples/sec: 417.18 - lr: 0.000100 - momentum: 0.000000
2023-10-11 19:43:26,016 ----------------------------------------------------------------------------------------------------
2023-10-11 19:43:26,016 EPOCH 4 done: loss 0.0519 - lr: 0.000100
2023-10-11 19:43:48,629 DEV : loss 0.07001111656427383 - f1-score (micro avg) 0.8727
2023-10-11 19:43:48,665 saving best model
2023-10-11 19:43:52,185 ----------------------------------------------------------------------------------------------------
2023-10-11 19:44:35,248 epoch 5 - iter 72/723 - loss 0.03577280 - time (sec): 43.06 - samples/sec: 410.16 - lr: 0.000098 - momentum: 0.000000
2023-10-11 19:45:15,914 epoch 5 - iter 144/723 - loss 0.03264401 - time (sec): 83.72 - samples/sec: 421.27 - lr: 0.000097 - momentum: 0.000000
2023-10-11 19:45:57,621 epoch 5 - iter 216/723 - loss 0.03662028 - time (sec): 125.43 - samples/sec: 426.47 - lr: 0.000095 - momentum: 0.000000
2023-10-11 19:46:40,431 epoch 5 - iter 288/723 - loss 0.03545328 - time (sec): 168.24 - samples/sec: 420.72 - lr: 0.000093 - momentum: 0.000000
2023-10-11 19:47:22,294 epoch 5 - iter 360/723 - loss 0.03467577 - time (sec): 210.10 - samples/sec: 425.95 - lr: 0.000092 - momentum: 0.000000
2023-10-11 19:48:03,651 epoch 5 - iter 432/723 - loss 0.03412429 - time (sec): 251.46 - samples/sec: 420.87 - lr: 0.000090 - momentum: 0.000000
2023-10-11 19:48:47,048 epoch 5 - iter 504/723 - loss 0.03625783 - time (sec): 294.86 - samples/sec: 419.45 - lr: 0.000088 - momentum: 0.000000
2023-10-11 19:49:28,818 epoch 5 - iter 576/723 - loss 0.03576595 - time (sec): 336.63 - samples/sec: 419.01 - lr: 0.000087 - momentum: 0.000000
2023-10-11 19:50:09,866 epoch 5 - iter 648/723 - loss 0.03742931 - time (sec): 377.68 - samples/sec: 419.77 - lr: 0.000085 - momentum: 0.000000
2023-10-11 19:50:50,937 epoch 5 - iter 720/723 - loss 0.03701053 - time (sec): 418.75 - samples/sec: 419.33 - lr: 0.000083 - momentum: 0.000000
2023-10-11 19:50:52,310 ----------------------------------------------------------------------------------------------------
2023-10-11 19:50:52,311 EPOCH 5 done: loss 0.0369 - lr: 0.000083
2023-10-11 19:51:16,106 DEV : loss 0.07903970032930374 - f1-score (micro avg) 0.8603
2023-10-11 19:51:16,143 ----------------------------------------------------------------------------------------------------
2023-10-11 19:52:00,787 epoch 6 - iter 72/723 - loss 0.02447853 - time (sec): 44.64 - samples/sec: 416.76 - lr: 0.000082 - momentum: 0.000000
2023-10-11 19:52:44,152 epoch 6 - iter 144/723 - loss 0.02205426 - time (sec): 88.01 - samples/sec: 418.68 - lr: 0.000080 - momentum: 0.000000
2023-10-11 19:53:25,211 epoch 6 - iter 216/723 - loss 0.02750277 - time (sec): 129.07 - samples/sec: 410.91 - lr: 0.000078 - momentum: 0.000000
2023-10-11 19:54:08,739 epoch 6 - iter 288/723 - loss 0.02591301 - time (sec): 172.59 - samples/sec: 408.80 - lr: 0.000077 - momentum: 0.000000
2023-10-11 19:54:51,542 epoch 6 - iter 360/723 - loss 0.02561029 - time (sec): 215.40 - samples/sec: 403.07 - lr: 0.000075 - momentum: 0.000000
2023-10-11 19:55:37,784 epoch 6 - iter 432/723 - loss 0.02497769 - time (sec): 261.64 - samples/sec: 400.75 - lr: 0.000073 - momentum: 0.000000
2023-10-11 19:56:24,102 epoch 6 - iter 504/723 - loss 0.02676010 - time (sec): 307.96 - samples/sec: 401.09 - lr: 0.000072 - momentum: 0.000000
2023-10-11 19:57:11,010 epoch 6 - iter 576/723 - loss 0.02633032 - time (sec): 354.86 - samples/sec: 398.37 - lr: 0.000070 - momentum: 0.000000
2023-10-11 19:57:54,453 epoch 6 - iter 648/723 - loss 0.02681762 - time (sec): 398.31 - samples/sec: 396.04 - lr: 0.000068 - momentum: 0.000000
2023-10-11 19:58:40,721 epoch 6 - iter 720/723 - loss 0.02707283 - time (sec): 444.58 - samples/sec: 394.53 - lr: 0.000067 - momentum: 0.000000
2023-10-11 19:58:42,172 ----------------------------------------------------------------------------------------------------
2023-10-11 19:58:42,172 EPOCH 6 done: loss 0.0270 - lr: 0.000067
2023-10-11 19:59:07,335 DEV : loss 0.09442799538373947 - f1-score (micro avg) 0.8571
2023-10-11 19:59:07,373 ----------------------------------------------------------------------------------------------------
2023-10-11 19:59:52,725 epoch 7 - iter 72/723 - loss 0.02094561 - time (sec): 45.35 - samples/sec: 391.65 - lr: 0.000065 - momentum: 0.000000
2023-10-11 20:00:33,300 epoch 7 - iter 144/723 - loss 0.01875934 - time (sec): 85.92 - samples/sec: 398.24 - lr: 0.000063 - momentum: 0.000000
2023-10-11 20:01:14,107 epoch 7 - iter 216/723 - loss 0.01681267 - time (sec): 126.73 - samples/sec: 398.42 - lr: 0.000062 - momentum: 0.000000
2023-10-11 20:01:57,563 epoch 7 - iter 288/723 - loss 0.01766153 - time (sec): 170.19 - samples/sec: 410.15 - lr: 0.000060 - momentum: 0.000000
2023-10-11 20:02:43,950 epoch 7 - iter 360/723 - loss 0.02292811 - time (sec): 216.58 - samples/sec: 405.16 - lr: 0.000058 - momentum: 0.000000
2023-10-11 20:03:27,340 epoch 7 - iter 432/723 - loss 0.02258017 - time (sec): 259.97 - samples/sec: 407.35 - lr: 0.000057 - momentum: 0.000000
2023-10-11 20:04:08,335 epoch 7 - iter 504/723 - loss 0.02155383 - time (sec): 300.96 - samples/sec: 407.69 - lr: 0.000055 - momentum: 0.000000
2023-10-11 20:04:50,397 epoch 7 - iter 576/723 - loss 0.02107573 - time (sec): 343.02 - samples/sec: 409.98 - lr: 0.000053 - momentum: 0.000000
2023-10-11 20:05:32,273 epoch 7 - iter 648/723 - loss 0.02110528 - time (sec): 384.90 - samples/sec: 411.17 - lr: 0.000052 - momentum: 0.000000
2023-10-11 20:06:15,185 epoch 7 - iter 720/723 - loss 0.02085093 - time (sec): 427.81 - samples/sec: 410.19 - lr: 0.000050 - momentum: 0.000000
2023-10-11 20:06:16,648 ----------------------------------------------------------------------------------------------------
2023-10-11 20:06:16,649 EPOCH 7 done: loss 0.0208 - lr: 0.000050
2023-10-11 20:06:40,108 DEV : loss 0.09876430779695511 - f1-score (micro avg) 0.8703
2023-10-11 20:06:40,152 ----------------------------------------------------------------------------------------------------
2023-10-11 20:07:22,836 epoch 8 - iter 72/723 - loss 0.00933933 - time (sec): 42.68 - samples/sec: 420.64 - lr: 0.000048 - momentum: 0.000000
2023-10-11 20:08:03,853 epoch 8 - iter 144/723 - loss 0.01292328 - time (sec): 83.70 - samples/sec: 408.45 - lr: 0.000047 - momentum: 0.000000
2023-10-11 20:08:43,013 epoch 8 - iter 216/723 - loss 0.01314725 - time (sec): 122.86 - samples/sec: 413.22 - lr: 0.000045 - momentum: 0.000000
2023-10-11 20:09:23,514 epoch 8 - iter 288/723 - loss 0.01277868 - time (sec): 163.36 - samples/sec: 415.17 - lr: 0.000043 - momentum: 0.000000
2023-10-11 20:10:04,265 epoch 8 - iter 360/723 - loss 0.01439634 - time (sec): 204.11 - samples/sec: 418.58 - lr: 0.000042 - momentum: 0.000000
2023-10-11 20:10:45,239 epoch 8 - iter 432/723 - loss 0.01543636 - time (sec): 245.09 - samples/sec: 423.69 - lr: 0.000040 - momentum: 0.000000
2023-10-11 20:11:26,857 epoch 8 - iter 504/723 - loss 0.01613212 - time (sec): 286.70 - samples/sec: 427.85 - lr: 0.000038 - momentum: 0.000000
2023-10-11 20:12:06,133 epoch 8 - iter 576/723 - loss 0.01588643 - time (sec): 325.98 - samples/sec: 429.05 - lr: 0.000037 - momentum: 0.000000
2023-10-11 20:12:48,288 epoch 8 - iter 648/723 - loss 0.01595246 - time (sec): 368.13 - samples/sec: 429.70 - lr: 0.000035 - momentum: 0.000000
2023-10-11 20:13:31,496 epoch 8 - iter 720/723 - loss 0.01649749 - time (sec): 411.34 - samples/sec: 427.11 - lr: 0.000033 - momentum: 0.000000
2023-10-11 20:13:32,739 ----------------------------------------------------------------------------------------------------
2023-10-11 20:13:32,740 EPOCH 8 done: loss 0.0165 - lr: 0.000033
2023-10-11 20:13:55,278 DEV : loss 0.10501116514205933 - f1-score (micro avg) 0.8751
2023-10-11 20:13:55,327 saving best model
2023-10-11 20:13:56,488 ----------------------------------------------------------------------------------------------------
2023-10-11 20:14:41,953 epoch 9 - iter 72/723 - loss 0.00692157 - time (sec): 45.46 - samples/sec: 377.43 - lr: 0.000032 - momentum: 0.000000
2023-10-11 20:15:23,711 epoch 9 - iter 144/723 - loss 0.00987217 - time (sec): 87.22 - samples/sec: 390.20 - lr: 0.000030 - momentum: 0.000000
2023-10-11 20:16:06,341 epoch 9 - iter 216/723 - loss 0.01091573 - time (sec): 129.85 - samples/sec: 394.00 - lr: 0.000028 - momentum: 0.000000
2023-10-11 20:16:50,893 epoch 9 - iter 288/723 - loss 0.01283372 - time (sec): 174.40 - samples/sec: 400.17 - lr: 0.000027 - momentum: 0.000000
2023-10-11 20:17:36,364 epoch 9 - iter 360/723 - loss 0.01390500 - time (sec): 219.87 - samples/sec: 402.90 - lr: 0.000025 - momentum: 0.000000
2023-10-11 20:18:19,862 epoch 9 - iter 432/723 - loss 0.01345060 - time (sec): 263.37 - samples/sec: 403.65 - lr: 0.000023 - momentum: 0.000000
2023-10-11 20:19:02,380 epoch 9 - iter 504/723 - loss 0.01441546 - time (sec): 305.89 - samples/sec: 405.73 - lr: 0.000022 - momentum: 0.000000
2023-10-11 20:19:45,060 epoch 9 - iter 576/723 - loss 0.01394066 - time (sec): 348.57 - samples/sec: 406.20 - lr: 0.000020 - momentum: 0.000000
2023-10-11 20:20:25,766 epoch 9 - iter 648/723 - loss 0.01417785 - time (sec): 389.28 - samples/sec: 407.17 - lr: 0.000018 - momentum: 0.000000
2023-10-11 20:21:06,100 epoch 9 - iter 720/723 - loss 0.01360125 - time (sec): 429.61 - samples/sec: 408.77 - lr: 0.000017 - momentum: 0.000000
2023-10-11 20:21:07,399 ----------------------------------------------------------------------------------------------------
2023-10-11 20:21:07,399 EPOCH 9 done: loss 0.0136 - lr: 0.000017
2023-10-11 20:21:30,023 DEV : loss 0.11595697700977325 - f1-score (micro avg) 0.8585
2023-10-11 20:21:30,064 ----------------------------------------------------------------------------------------------------
2023-10-11 20:22:12,604 epoch 10 - iter 72/723 - loss 0.01406246 - time (sec): 42.54 - samples/sec: 423.37 - lr: 0.000015 - momentum: 0.000000
2023-10-11 20:22:55,515 epoch 10 - iter 144/723 - loss 0.01245519 - time (sec): 85.45 - samples/sec: 424.31 - lr: 0.000013 - momentum: 0.000000
2023-10-11 20:23:38,829 epoch 10 - iter 216/723 - loss 0.01322961 - time (sec): 128.76 - samples/sec: 430.22 - lr: 0.000012 - momentum: 0.000000
2023-10-11 20:24:20,473 epoch 10 - iter 288/723 - loss 0.01274717 - time (sec): 170.41 - samples/sec: 428.27 - lr: 0.000010 - momentum: 0.000000
2023-10-11 20:25:01,572 epoch 10 - iter 360/723 - loss 0.01269929 - time (sec): 211.51 - samples/sec: 430.74 - lr: 0.000008 - momentum: 0.000000
2023-10-11 20:25:43,691 epoch 10 - iter 432/723 - loss 0.01264156 - time (sec): 253.62 - samples/sec: 423.44 - lr: 0.000007 - momentum: 0.000000
2023-10-11 20:26:25,384 epoch 10 - iter 504/723 - loss 0.01254290 - time (sec): 295.32 - samples/sec: 421.37 - lr: 0.000005 - momentum: 0.000000
2023-10-11 20:27:06,979 epoch 10 - iter 576/723 - loss 0.01252330 - time (sec): 336.91 - samples/sec: 420.64 - lr: 0.000003 - momentum: 0.000000
2023-10-11 20:27:46,703 epoch 10 - iter 648/723 - loss 0.01221020 - time (sec): 376.64 - samples/sec: 421.88 - lr: 0.000002 - momentum: 0.000000
2023-10-11 20:28:26,795 epoch 10 - iter 720/723 - loss 0.01195603 - time (sec): 416.73 - samples/sec: 421.67 - lr: 0.000000 - momentum: 0.000000
2023-10-11 20:28:27,946 ----------------------------------------------------------------------------------------------------
2023-10-11 20:28:27,946 EPOCH 10 done: loss 0.0119 - lr: 0.000000
2023-10-11 20:28:49,635 DEV : loss 0.11474814265966415 - f1-score (micro avg) 0.8625
2023-10-11 20:28:50,709 ----------------------------------------------------------------------------------------------------
2023-10-11 20:28:50,711 Loading model from best epoch ...
2023-10-11 20:28:55,094 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
2023-10-11 20:29:19,250
Results:
- F-score (micro) 0.8422
- F-score (macro) 0.7359
- Accuracy 0.7429
By class:
precision recall f1-score support
PER 0.8480 0.8797 0.8635 482
LOC 0.9159 0.8319 0.8719 458
ORG 0.5172 0.4348 0.4724 69
micro avg 0.8573 0.8276 0.8422 1009
macro avg 0.7604 0.7154 0.7359 1009
weighted avg 0.8562 0.8276 0.8406 1009
2023-10-11 20:29:19,250 ----------------------------------------------------------------------------------------------------
|