File size: 36,908 Bytes
2ccbe2e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 |
2023-10-25 00:11:18,614 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,615 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): 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)
)
)
(1): 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)
)
)
(2): 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)
)
)
(3): 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)
)
)
(4): 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)
)
)
(5): 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)
)
)
(6): 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)
)
)
(7): 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)
)
)
(8): 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)
)
)
(9): 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)
)
)
(10): 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)
)
)
(11): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=768, out_features=768, bias=True)
(key): Linear(in_features=768, out_features=768, bias=True)
(value): Linear(in_features=768, out_features=768, bias=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=768, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=768, out_features=3072, bias=True)
(intermediate_act_fn): GELUActivation()
)
(output): BertOutput(
(dense): Linear(in_features=3072, out_features=768, bias=True)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=768, out_features=768, bias=True)
(activation): Tanh()
)
)
)
(locked_dropout): LockedDropout(p=0.5)
(linear): Linear(in_features=768, out_features=13, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-25 00:11:18,615 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,615 MultiCorpus: 5777 train + 722 dev + 723 test sentences
- NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /home/ubuntu/.flair/datasets/ner_icdar_europeana/nl
2023-10-25 00:11:18,615 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Train: 5777 sentences
2023-10-25 00:11:18,616 (train_with_dev=False, train_with_test=False)
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Training Params:
2023-10-25 00:11:18,616 - learning_rate: "3e-05"
2023-10-25 00:11:18,616 - mini_batch_size: "4"
2023-10-25 00:11:18,616 - max_epochs: "10"
2023-10-25 00:11:18,616 - shuffle: "True"
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Plugins:
2023-10-25 00:11:18,616 - TensorboardLogger
2023-10-25 00:11:18,616 - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 00:11:18,616 - metric: "('micro avg', 'f1-score')"
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Computation:
2023-10-25 00:11:18,616 - compute on device: cuda:0
2023-10-25 00:11:18,616 - embedding storage: none
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 ----------------------------------------------------------------------------------------------------
2023-10-25 00:11:18,616 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 00:11:29,321 epoch 1 - iter 144/1445 - loss 1.38938163 - time (sec): 10.70 - samples/sec: 1720.98 - lr: 0.000003 - momentum: 0.000000
2023-10-25 00:11:39,360 epoch 1 - iter 288/1445 - loss 0.87654160 - time (sec): 20.74 - samples/sec: 1667.66 - lr: 0.000006 - momentum: 0.000000
2023-10-25 00:11:49,875 epoch 1 - iter 432/1445 - loss 0.65410083 - time (sec): 31.26 - samples/sec: 1658.76 - lr: 0.000009 - momentum: 0.000000
2023-10-25 00:12:00,072 epoch 1 - iter 576/1445 - loss 0.53644177 - time (sec): 41.45 - samples/sec: 1661.93 - lr: 0.000012 - momentum: 0.000000
2023-10-25 00:12:11,122 epoch 1 - iter 720/1445 - loss 0.45401570 - time (sec): 52.51 - samples/sec: 1670.87 - lr: 0.000015 - momentum: 0.000000
2023-10-25 00:12:21,401 epoch 1 - iter 864/1445 - loss 0.40781351 - time (sec): 62.78 - samples/sec: 1664.14 - lr: 0.000018 - momentum: 0.000000
2023-10-25 00:12:32,044 epoch 1 - iter 1008/1445 - loss 0.36577446 - time (sec): 73.43 - samples/sec: 1667.51 - lr: 0.000021 - momentum: 0.000000
2023-10-25 00:12:42,531 epoch 1 - iter 1152/1445 - loss 0.33817906 - time (sec): 83.91 - samples/sec: 1670.17 - lr: 0.000024 - momentum: 0.000000
2023-10-25 00:12:53,139 epoch 1 - iter 1296/1445 - loss 0.31541819 - time (sec): 94.52 - samples/sec: 1670.96 - lr: 0.000027 - momentum: 0.000000
2023-10-25 00:13:03,644 epoch 1 - iter 1440/1445 - loss 0.29840554 - time (sec): 105.03 - samples/sec: 1671.49 - lr: 0.000030 - momentum: 0.000000
2023-10-25 00:13:04,067 ----------------------------------------------------------------------------------------------------
2023-10-25 00:13:04,067 EPOCH 1 done: loss 0.2976 - lr: 0.000030
2023-10-25 00:13:07,349 DEV : loss 0.13481558859348297 - f1-score (micro avg) 0.5007
2023-10-25 00:13:07,360 saving best model
2023-10-25 00:13:07,833 ----------------------------------------------------------------------------------------------------
2023-10-25 00:13:18,284 epoch 2 - iter 144/1445 - loss 0.11213883 - time (sec): 10.45 - samples/sec: 1656.80 - lr: 0.000030 - momentum: 0.000000
2023-10-25 00:13:29,023 epoch 2 - iter 288/1445 - loss 0.12245620 - time (sec): 21.19 - samples/sec: 1687.57 - lr: 0.000029 - momentum: 0.000000
2023-10-25 00:13:39,836 epoch 2 - iter 432/1445 - loss 0.11723412 - time (sec): 32.00 - samples/sec: 1687.73 - lr: 0.000029 - momentum: 0.000000
2023-10-25 00:13:50,678 epoch 2 - iter 576/1445 - loss 0.11064019 - time (sec): 42.84 - samples/sec: 1685.23 - lr: 0.000029 - momentum: 0.000000
2023-10-25 00:14:01,208 epoch 2 - iter 720/1445 - loss 0.10928472 - time (sec): 53.37 - samples/sec: 1672.93 - lr: 0.000028 - momentum: 0.000000
2023-10-25 00:14:11,856 epoch 2 - iter 864/1445 - loss 0.10679391 - time (sec): 64.02 - samples/sec: 1678.60 - lr: 0.000028 - momentum: 0.000000
2023-10-25 00:14:22,186 epoch 2 - iter 1008/1445 - loss 0.10555065 - time (sec): 74.35 - samples/sec: 1666.89 - lr: 0.000028 - momentum: 0.000000
2023-10-25 00:14:32,456 epoch 2 - iter 1152/1445 - loss 0.10376908 - time (sec): 84.62 - samples/sec: 1666.77 - lr: 0.000027 - momentum: 0.000000
2023-10-25 00:14:42,859 epoch 2 - iter 1296/1445 - loss 0.10361640 - time (sec): 95.03 - samples/sec: 1664.12 - lr: 0.000027 - momentum: 0.000000
2023-10-25 00:14:53,345 epoch 2 - iter 1440/1445 - loss 0.10081503 - time (sec): 105.51 - samples/sec: 1664.11 - lr: 0.000027 - momentum: 0.000000
2023-10-25 00:14:53,797 ----------------------------------------------------------------------------------------------------
2023-10-25 00:14:53,798 EPOCH 2 done: loss 0.1006 - lr: 0.000027
2023-10-25 00:14:57,509 DEV : loss 0.09922739118337631 - f1-score (micro avg) 0.7789
2023-10-25 00:14:57,521 saving best model
2023-10-25 00:14:58,112 ----------------------------------------------------------------------------------------------------
2023-10-25 00:15:08,688 epoch 3 - iter 144/1445 - loss 0.07401386 - time (sec): 10.58 - samples/sec: 1626.38 - lr: 0.000026 - momentum: 0.000000
2023-10-25 00:15:19,237 epoch 3 - iter 288/1445 - loss 0.07036989 - time (sec): 21.12 - samples/sec: 1663.55 - lr: 0.000026 - momentum: 0.000000
2023-10-25 00:15:29,743 epoch 3 - iter 432/1445 - loss 0.07228507 - time (sec): 31.63 - samples/sec: 1660.81 - lr: 0.000026 - momentum: 0.000000
2023-10-25 00:15:40,193 epoch 3 - iter 576/1445 - loss 0.06975233 - time (sec): 42.08 - samples/sec: 1661.84 - lr: 0.000025 - momentum: 0.000000
2023-10-25 00:15:50,838 epoch 3 - iter 720/1445 - loss 0.07320523 - time (sec): 52.72 - samples/sec: 1659.56 - lr: 0.000025 - momentum: 0.000000
2023-10-25 00:16:01,293 epoch 3 - iter 864/1445 - loss 0.07136932 - time (sec): 63.18 - samples/sec: 1654.97 - lr: 0.000025 - momentum: 0.000000
2023-10-25 00:16:11,569 epoch 3 - iter 1008/1445 - loss 0.07073740 - time (sec): 73.46 - samples/sec: 1657.77 - lr: 0.000024 - momentum: 0.000000
2023-10-25 00:16:22,487 epoch 3 - iter 1152/1445 - loss 0.06940519 - time (sec): 84.37 - samples/sec: 1667.92 - lr: 0.000024 - momentum: 0.000000
2023-10-25 00:16:33,200 epoch 3 - iter 1296/1445 - loss 0.06930457 - time (sec): 95.09 - samples/sec: 1665.11 - lr: 0.000024 - momentum: 0.000000
2023-10-25 00:16:43,676 epoch 3 - iter 1440/1445 - loss 0.06923652 - time (sec): 105.56 - samples/sec: 1664.57 - lr: 0.000023 - momentum: 0.000000
2023-10-25 00:16:44,021 ----------------------------------------------------------------------------------------------------
2023-10-25 00:16:44,021 EPOCH 3 done: loss 0.0692 - lr: 0.000023
2023-10-25 00:16:47,446 DEV : loss 0.13537803292274475 - f1-score (micro avg) 0.7799
2023-10-25 00:16:47,458 saving best model
2023-10-25 00:16:48,053 ----------------------------------------------------------------------------------------------------
2023-10-25 00:16:58,764 epoch 4 - iter 144/1445 - loss 0.05989448 - time (sec): 10.71 - samples/sec: 1663.20 - lr: 0.000023 - momentum: 0.000000
2023-10-25 00:17:09,630 epoch 4 - iter 288/1445 - loss 0.05059786 - time (sec): 21.58 - samples/sec: 1620.12 - lr: 0.000023 - momentum: 0.000000
2023-10-25 00:17:20,376 epoch 4 - iter 432/1445 - loss 0.04777464 - time (sec): 32.32 - samples/sec: 1653.35 - lr: 0.000022 - momentum: 0.000000
2023-10-25 00:17:31,029 epoch 4 - iter 576/1445 - loss 0.04689286 - time (sec): 42.98 - samples/sec: 1668.10 - lr: 0.000022 - momentum: 0.000000
2023-10-25 00:17:41,011 epoch 4 - iter 720/1445 - loss 0.04834085 - time (sec): 52.96 - samples/sec: 1655.32 - lr: 0.000022 - momentum: 0.000000
2023-10-25 00:17:51,641 epoch 4 - iter 864/1445 - loss 0.04645510 - time (sec): 63.59 - samples/sec: 1654.41 - lr: 0.000021 - momentum: 0.000000
2023-10-25 00:18:02,147 epoch 4 - iter 1008/1445 - loss 0.04662996 - time (sec): 74.09 - samples/sec: 1654.67 - lr: 0.000021 - momentum: 0.000000
2023-10-25 00:18:12,811 epoch 4 - iter 1152/1445 - loss 0.04833320 - time (sec): 84.76 - samples/sec: 1657.00 - lr: 0.000021 - momentum: 0.000000
2023-10-25 00:18:23,313 epoch 4 - iter 1296/1445 - loss 0.04773193 - time (sec): 95.26 - samples/sec: 1661.15 - lr: 0.000020 - momentum: 0.000000
2023-10-25 00:18:33,848 epoch 4 - iter 1440/1445 - loss 0.04746787 - time (sec): 105.79 - samples/sec: 1661.63 - lr: 0.000020 - momentum: 0.000000
2023-10-25 00:18:34,192 ----------------------------------------------------------------------------------------------------
2023-10-25 00:18:34,192 EPOCH 4 done: loss 0.0475 - lr: 0.000020
2023-10-25 00:18:37,622 DEV : loss 0.12032151222229004 - f1-score (micro avg) 0.8011
2023-10-25 00:18:37,634 saving best model
2023-10-25 00:18:38,207 ----------------------------------------------------------------------------------------------------
2023-10-25 00:18:48,599 epoch 5 - iter 144/1445 - loss 0.02983013 - time (sec): 10.39 - samples/sec: 1631.93 - lr: 0.000020 - momentum: 0.000000
2023-10-25 00:18:58,968 epoch 5 - iter 288/1445 - loss 0.02899526 - time (sec): 20.76 - samples/sec: 1639.27 - lr: 0.000019 - momentum: 0.000000
2023-10-25 00:19:09,760 epoch 5 - iter 432/1445 - loss 0.03130541 - time (sec): 31.55 - samples/sec: 1659.53 - lr: 0.000019 - momentum: 0.000000
2023-10-25 00:19:20,186 epoch 5 - iter 576/1445 - loss 0.03109030 - time (sec): 41.98 - samples/sec: 1650.29 - lr: 0.000019 - momentum: 0.000000
2023-10-25 00:19:30,854 epoch 5 - iter 720/1445 - loss 0.03453446 - time (sec): 52.65 - samples/sec: 1651.54 - lr: 0.000018 - momentum: 0.000000
2023-10-25 00:19:41,861 epoch 5 - iter 864/1445 - loss 0.03446052 - time (sec): 63.65 - samples/sec: 1662.69 - lr: 0.000018 - momentum: 0.000000
2023-10-25 00:19:52,258 epoch 5 - iter 1008/1445 - loss 0.03609405 - time (sec): 74.05 - samples/sec: 1661.99 - lr: 0.000018 - momentum: 0.000000
2023-10-25 00:20:02,565 epoch 5 - iter 1152/1445 - loss 0.03627626 - time (sec): 84.36 - samples/sec: 1661.97 - lr: 0.000017 - momentum: 0.000000
2023-10-25 00:20:13,190 epoch 5 - iter 1296/1445 - loss 0.03556309 - time (sec): 94.98 - samples/sec: 1666.39 - lr: 0.000017 - momentum: 0.000000
2023-10-25 00:20:23,734 epoch 5 - iter 1440/1445 - loss 0.03679685 - time (sec): 105.53 - samples/sec: 1665.75 - lr: 0.000017 - momentum: 0.000000
2023-10-25 00:20:24,070 ----------------------------------------------------------------------------------------------------
2023-10-25 00:20:24,070 EPOCH 5 done: loss 0.0368 - lr: 0.000017
2023-10-25 00:20:27,795 DEV : loss 0.1298297941684723 - f1-score (micro avg) 0.8238
2023-10-25 00:20:27,807 saving best model
2023-10-25 00:20:28,405 ----------------------------------------------------------------------------------------------------
2023-10-25 00:20:39,126 epoch 6 - iter 144/1445 - loss 0.01601013 - time (sec): 10.72 - samples/sec: 1683.95 - lr: 0.000016 - momentum: 0.000000
2023-10-25 00:20:49,460 epoch 6 - iter 288/1445 - loss 0.02373592 - time (sec): 21.05 - samples/sec: 1666.69 - lr: 0.000016 - momentum: 0.000000
2023-10-25 00:20:59,889 epoch 6 - iter 432/1445 - loss 0.02608343 - time (sec): 31.48 - samples/sec: 1673.09 - lr: 0.000016 - momentum: 0.000000
2023-10-25 00:21:10,404 epoch 6 - iter 576/1445 - loss 0.02606470 - time (sec): 42.00 - samples/sec: 1670.48 - lr: 0.000015 - momentum: 0.000000
2023-10-25 00:21:21,085 epoch 6 - iter 720/1445 - loss 0.02539757 - time (sec): 52.68 - samples/sec: 1672.76 - lr: 0.000015 - momentum: 0.000000
2023-10-25 00:21:31,532 epoch 6 - iter 864/1445 - loss 0.02480823 - time (sec): 63.13 - samples/sec: 1668.80 - lr: 0.000015 - momentum: 0.000000
2023-10-25 00:21:41,901 epoch 6 - iter 1008/1445 - loss 0.02490080 - time (sec): 73.50 - samples/sec: 1665.35 - lr: 0.000014 - momentum: 0.000000
2023-10-25 00:21:52,431 epoch 6 - iter 1152/1445 - loss 0.02503213 - time (sec): 84.03 - samples/sec: 1667.30 - lr: 0.000014 - momentum: 0.000000
2023-10-25 00:22:03,316 epoch 6 - iter 1296/1445 - loss 0.02496600 - time (sec): 94.91 - samples/sec: 1676.20 - lr: 0.000014 - momentum: 0.000000
2023-10-25 00:22:13,716 epoch 6 - iter 1440/1445 - loss 0.02479026 - time (sec): 105.31 - samples/sec: 1669.96 - lr: 0.000013 - momentum: 0.000000
2023-10-25 00:22:14,016 ----------------------------------------------------------------------------------------------------
2023-10-25 00:22:14,017 EPOCH 6 done: loss 0.0249 - lr: 0.000013
2023-10-25 00:22:17,443 DEV : loss 0.20431096851825714 - f1-score (micro avg) 0.7895
2023-10-25 00:22:17,455 ----------------------------------------------------------------------------------------------------
2023-10-25 00:22:27,950 epoch 7 - iter 144/1445 - loss 0.01117684 - time (sec): 10.49 - samples/sec: 1663.75 - lr: 0.000013 - momentum: 0.000000
2023-10-25 00:22:38,150 epoch 7 - iter 288/1445 - loss 0.01571047 - time (sec): 20.69 - samples/sec: 1639.81 - lr: 0.000013 - momentum: 0.000000
2023-10-25 00:22:49,582 epoch 7 - iter 432/1445 - loss 0.01656906 - time (sec): 32.13 - samples/sec: 1676.46 - lr: 0.000012 - momentum: 0.000000
2023-10-25 00:23:00,018 epoch 7 - iter 576/1445 - loss 0.01503815 - time (sec): 42.56 - samples/sec: 1673.14 - lr: 0.000012 - momentum: 0.000000
2023-10-25 00:23:10,915 epoch 7 - iter 720/1445 - loss 0.01601736 - time (sec): 53.46 - samples/sec: 1671.50 - lr: 0.000012 - momentum: 0.000000
2023-10-25 00:23:21,092 epoch 7 - iter 864/1445 - loss 0.01576845 - time (sec): 63.64 - samples/sec: 1663.45 - lr: 0.000011 - momentum: 0.000000
2023-10-25 00:23:32,263 epoch 7 - iter 1008/1445 - loss 0.01739489 - time (sec): 74.81 - samples/sec: 1669.40 - lr: 0.000011 - momentum: 0.000000
2023-10-25 00:23:42,513 epoch 7 - iter 1152/1445 - loss 0.01767123 - time (sec): 85.06 - samples/sec: 1657.92 - lr: 0.000011 - momentum: 0.000000
2023-10-25 00:23:53,120 epoch 7 - iter 1296/1445 - loss 0.01754927 - time (sec): 95.66 - samples/sec: 1658.01 - lr: 0.000010 - momentum: 0.000000
2023-10-25 00:24:03,214 epoch 7 - iter 1440/1445 - loss 0.01693935 - time (sec): 105.76 - samples/sec: 1661.54 - lr: 0.000010 - momentum: 0.000000
2023-10-25 00:24:03,537 ----------------------------------------------------------------------------------------------------
2023-10-25 00:24:03,538 EPOCH 7 done: loss 0.0169 - lr: 0.000010
2023-10-25 00:24:06,979 DEV : loss 0.18424199521541595 - f1-score (micro avg) 0.8119
2023-10-25 00:24:06,991 ----------------------------------------------------------------------------------------------------
2023-10-25 00:24:17,311 epoch 8 - iter 144/1445 - loss 0.00930858 - time (sec): 10.32 - samples/sec: 1632.76 - lr: 0.000010 - momentum: 0.000000
2023-10-25 00:24:27,987 epoch 8 - iter 288/1445 - loss 0.01249980 - time (sec): 21.00 - samples/sec: 1632.85 - lr: 0.000009 - momentum: 0.000000
2023-10-25 00:24:38,238 epoch 8 - iter 432/1445 - loss 0.01219123 - time (sec): 31.25 - samples/sec: 1619.39 - lr: 0.000009 - momentum: 0.000000
2023-10-25 00:24:49,551 epoch 8 - iter 576/1445 - loss 0.01174793 - time (sec): 42.56 - samples/sec: 1649.32 - lr: 0.000009 - momentum: 0.000000
2023-10-25 00:24:59,973 epoch 8 - iter 720/1445 - loss 0.01162494 - time (sec): 52.98 - samples/sec: 1654.59 - lr: 0.000008 - momentum: 0.000000
2023-10-25 00:25:10,506 epoch 8 - iter 864/1445 - loss 0.01127335 - time (sec): 63.51 - samples/sec: 1656.66 - lr: 0.000008 - momentum: 0.000000
2023-10-25 00:25:21,054 epoch 8 - iter 1008/1445 - loss 0.01257425 - time (sec): 74.06 - samples/sec: 1661.14 - lr: 0.000008 - momentum: 0.000000
2023-10-25 00:25:31,601 epoch 8 - iter 1152/1445 - loss 0.01352298 - time (sec): 84.61 - samples/sec: 1660.77 - lr: 0.000007 - momentum: 0.000000
2023-10-25 00:25:41,995 epoch 8 - iter 1296/1445 - loss 0.01297552 - time (sec): 95.00 - samples/sec: 1660.40 - lr: 0.000007 - momentum: 0.000000
2023-10-25 00:25:52,563 epoch 8 - iter 1440/1445 - loss 0.01308558 - time (sec): 105.57 - samples/sec: 1664.94 - lr: 0.000007 - momentum: 0.000000
2023-10-25 00:25:52,893 ----------------------------------------------------------------------------------------------------
2023-10-25 00:25:52,894 EPOCH 8 done: loss 0.0132 - lr: 0.000007
2023-10-25 00:25:56,623 DEV : loss 0.18342554569244385 - f1-score (micro avg) 0.8154
2023-10-25 00:25:56,635 ----------------------------------------------------------------------------------------------------
2023-10-25 00:26:07,274 epoch 9 - iter 144/1445 - loss 0.00487700 - time (sec): 10.64 - samples/sec: 1686.80 - lr: 0.000006 - momentum: 0.000000
2023-10-25 00:26:17,719 epoch 9 - iter 288/1445 - loss 0.00618271 - time (sec): 21.08 - samples/sec: 1674.65 - lr: 0.000006 - momentum: 0.000000
2023-10-25 00:26:28,409 epoch 9 - iter 432/1445 - loss 0.00694467 - time (sec): 31.77 - samples/sec: 1668.72 - lr: 0.000006 - momentum: 0.000000
2023-10-25 00:26:39,233 epoch 9 - iter 576/1445 - loss 0.00703293 - time (sec): 42.60 - samples/sec: 1679.56 - lr: 0.000005 - momentum: 0.000000
2023-10-25 00:26:49,652 epoch 9 - iter 720/1445 - loss 0.00748005 - time (sec): 53.02 - samples/sec: 1667.43 - lr: 0.000005 - momentum: 0.000000
2023-10-25 00:27:00,096 epoch 9 - iter 864/1445 - loss 0.00812538 - time (sec): 63.46 - samples/sec: 1660.54 - lr: 0.000005 - momentum: 0.000000
2023-10-25 00:27:10,612 epoch 9 - iter 1008/1445 - loss 0.00850011 - time (sec): 73.98 - samples/sec: 1664.19 - lr: 0.000004 - momentum: 0.000000
2023-10-25 00:27:21,467 epoch 9 - iter 1152/1445 - loss 0.00876078 - time (sec): 84.83 - samples/sec: 1669.13 - lr: 0.000004 - momentum: 0.000000
2023-10-25 00:27:31,749 epoch 9 - iter 1296/1445 - loss 0.00983545 - time (sec): 95.11 - samples/sec: 1664.29 - lr: 0.000004 - momentum: 0.000000
2023-10-25 00:27:42,233 epoch 9 - iter 1440/1445 - loss 0.00953351 - time (sec): 105.60 - samples/sec: 1663.77 - lr: 0.000003 - momentum: 0.000000
2023-10-25 00:27:42,560 ----------------------------------------------------------------------------------------------------
2023-10-25 00:27:42,560 EPOCH 9 done: loss 0.0097 - lr: 0.000003
2023-10-25 00:27:45,993 DEV : loss 0.18781644105911255 - f1-score (micro avg) 0.823
2023-10-25 00:27:46,005 ----------------------------------------------------------------------------------------------------
2023-10-25 00:27:56,502 epoch 10 - iter 144/1445 - loss 0.00437476 - time (sec): 10.50 - samples/sec: 1646.85 - lr: 0.000003 - momentum: 0.000000
2023-10-25 00:28:07,554 epoch 10 - iter 288/1445 - loss 0.00845703 - time (sec): 21.55 - samples/sec: 1620.52 - lr: 0.000003 - momentum: 0.000000
2023-10-25 00:28:17,904 epoch 10 - iter 432/1445 - loss 0.00618837 - time (sec): 31.90 - samples/sec: 1633.18 - lr: 0.000002 - momentum: 0.000000
2023-10-25 00:28:28,473 epoch 10 - iter 576/1445 - loss 0.00597168 - time (sec): 42.47 - samples/sec: 1649.52 - lr: 0.000002 - momentum: 0.000000
2023-10-25 00:28:38,916 epoch 10 - iter 720/1445 - loss 0.00539134 - time (sec): 52.91 - samples/sec: 1651.52 - lr: 0.000002 - momentum: 0.000000
2023-10-25 00:28:50,172 epoch 10 - iter 864/1445 - loss 0.00625082 - time (sec): 64.17 - samples/sec: 1667.60 - lr: 0.000001 - momentum: 0.000000
2023-10-25 00:29:00,734 epoch 10 - iter 1008/1445 - loss 0.00634905 - time (sec): 74.73 - samples/sec: 1667.31 - lr: 0.000001 - momentum: 0.000000
2023-10-25 00:29:11,282 epoch 10 - iter 1152/1445 - loss 0.00643576 - time (sec): 85.28 - samples/sec: 1669.39 - lr: 0.000001 - momentum: 0.000000
2023-10-25 00:29:21,407 epoch 10 - iter 1296/1445 - loss 0.00623537 - time (sec): 95.40 - samples/sec: 1662.12 - lr: 0.000000 - momentum: 0.000000
2023-10-25 00:29:31,911 epoch 10 - iter 1440/1445 - loss 0.00626251 - time (sec): 105.90 - samples/sec: 1660.30 - lr: 0.000000 - momentum: 0.000000
2023-10-25 00:29:32,215 ----------------------------------------------------------------------------------------------------
2023-10-25 00:29:32,216 EPOCH 10 done: loss 0.0063 - lr: 0.000000
2023-10-25 00:29:35,646 DEV : loss 0.19258512556552887 - f1-score (micro avg) 0.8221
2023-10-25 00:29:36,125 ----------------------------------------------------------------------------------------------------
2023-10-25 00:29:36,126 Loading model from best epoch ...
2023-10-25 00:29:37,790 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
2023-10-25 00:29:41,330
Results:
- F-score (micro) 0.7947
- F-score (macro) 0.6981
- Accuracy 0.6764
By class:
precision recall f1-score support
PER 0.7939 0.8071 0.8004 482
LOC 0.8662 0.8057 0.8348 458
ORG 0.5283 0.4058 0.4590 69
micro avg 0.8111 0.7790 0.7947 1009
macro avg 0.7295 0.6728 0.6981 1009
weighted avg 0.8085 0.7790 0.7927 1009
2023-10-25 00:29:41,330 ----------------------------------------------------------------------------------------------------
|