File size: 36,866 Bytes
a2fc0a1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 |
2023-10-23 19:16:53,810 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,811 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=25, bias=True)
(loss_function): CrossEntropyLoss()
)"
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 MultiCorpus: 966 train + 219 dev + 204 test sentences
- NER_HIPE_2022 Corpus: 966 train + 219 dev + 204 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/ajmc/fr/with_doc_seperator
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Train: 966 sentences
2023-10-23 19:16:53,812 (train_with_dev=False, train_with_test=False)
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Training Params:
2023-10-23 19:16:53,812 - learning_rate: "5e-05"
2023-10-23 19:16:53,812 - mini_batch_size: "8"
2023-10-23 19:16:53,812 - max_epochs: "10"
2023-10-23 19:16:53,812 - shuffle: "True"
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Plugins:
2023-10-23 19:16:53,812 - TensorboardLogger
2023-10-23 19:16:53,812 - LinearScheduler | warmup_fraction: '0.1'
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Final evaluation on model from best epoch (best-model.pt)
2023-10-23 19:16:53,812 - metric: "('micro avg', 'f1-score')"
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Computation:
2023-10-23 19:16:53,812 - compute on device: cuda:0
2023-10-23 19:16:53,812 - embedding storage: none
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 Model training base path: "hmbench-ajmc/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,812 ----------------------------------------------------------------------------------------------------
2023-10-23 19:16:53,813 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-23 19:16:54,860 epoch 1 - iter 12/121 - loss 3.70276262 - time (sec): 1.05 - samples/sec: 2270.31 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:16:55,939 epoch 1 - iter 24/121 - loss 2.94388750 - time (sec): 2.13 - samples/sec: 2170.37 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:16:56,993 epoch 1 - iter 36/121 - loss 2.14431472 - time (sec): 3.18 - samples/sec: 2245.23 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:16:58,101 epoch 1 - iter 48/121 - loss 1.72480650 - time (sec): 4.29 - samples/sec: 2348.26 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:16:59,086 epoch 1 - iter 60/121 - loss 1.52035465 - time (sec): 5.27 - samples/sec: 2303.07 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:17:00,187 epoch 1 - iter 72/121 - loss 1.33210475 - time (sec): 6.37 - samples/sec: 2294.42 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:17:01,246 epoch 1 - iter 84/121 - loss 1.20099635 - time (sec): 7.43 - samples/sec: 2280.42 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:17:02,345 epoch 1 - iter 96/121 - loss 1.07387613 - time (sec): 8.53 - samples/sec: 2299.86 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:17:03,427 epoch 1 - iter 108/121 - loss 0.98002301 - time (sec): 9.61 - samples/sec: 2296.51 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:17:04,469 epoch 1 - iter 120/121 - loss 0.90647831 - time (sec): 10.66 - samples/sec: 2302.02 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:17:04,543 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:04,544 EPOCH 1 done: loss 0.8991 - lr: 0.000049
2023-10-23 19:17:05,376 DEV : loss 0.18442463874816895 - f1-score (micro avg) 0.6868
2023-10-23 19:17:05,381 saving best model
2023-10-23 19:17:05,868 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:06,928 epoch 2 - iter 12/121 - loss 0.15705501 - time (sec): 1.06 - samples/sec: 2168.99 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:17:08,035 epoch 2 - iter 24/121 - loss 0.13657685 - time (sec): 2.17 - samples/sec: 2214.74 - lr: 0.000049 - momentum: 0.000000
2023-10-23 19:17:09,109 epoch 2 - iter 36/121 - loss 0.14488585 - time (sec): 3.24 - samples/sec: 2260.59 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:17:10,171 epoch 2 - iter 48/121 - loss 0.15283456 - time (sec): 4.30 - samples/sec: 2183.19 - lr: 0.000048 - momentum: 0.000000
2023-10-23 19:17:11,332 epoch 2 - iter 60/121 - loss 0.15273878 - time (sec): 5.46 - samples/sec: 2225.64 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:17:12,301 epoch 2 - iter 72/121 - loss 0.15603911 - time (sec): 6.43 - samples/sec: 2222.49 - lr: 0.000047 - momentum: 0.000000
2023-10-23 19:17:13,332 epoch 2 - iter 84/121 - loss 0.15252101 - time (sec): 7.46 - samples/sec: 2261.11 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:17:14,480 epoch 2 - iter 96/121 - loss 0.15153949 - time (sec): 8.61 - samples/sec: 2281.76 - lr: 0.000046 - momentum: 0.000000
2023-10-23 19:17:15,522 epoch 2 - iter 108/121 - loss 0.14821059 - time (sec): 9.65 - samples/sec: 2278.10 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:17:16,625 epoch 2 - iter 120/121 - loss 0.14288083 - time (sec): 10.76 - samples/sec: 2287.83 - lr: 0.000045 - momentum: 0.000000
2023-10-23 19:17:16,696 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:16,697 EPOCH 2 done: loss 0.1424 - lr: 0.000045
2023-10-23 19:17:17,402 DEV : loss 0.11657055467367172 - f1-score (micro avg) 0.7735
2023-10-23 19:17:17,406 saving best model
2023-10-23 19:17:18,089 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:19,070 epoch 3 - iter 12/121 - loss 0.08238361 - time (sec): 0.98 - samples/sec: 2252.66 - lr: 0.000044 - momentum: 0.000000
2023-10-23 19:17:20,133 epoch 3 - iter 24/121 - loss 0.08198313 - time (sec): 2.04 - samples/sec: 2274.97 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:17:21,336 epoch 3 - iter 36/121 - loss 0.09209441 - time (sec): 3.25 - samples/sec: 2217.70 - lr: 0.000043 - momentum: 0.000000
2023-10-23 19:17:22,436 epoch 3 - iter 48/121 - loss 0.09095958 - time (sec): 4.35 - samples/sec: 2210.50 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:17:23,484 epoch 3 - iter 60/121 - loss 0.09157820 - time (sec): 5.39 - samples/sec: 2235.27 - lr: 0.000042 - momentum: 0.000000
2023-10-23 19:17:24,578 epoch 3 - iter 72/121 - loss 0.08770180 - time (sec): 6.49 - samples/sec: 2251.10 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:17:25,710 epoch 3 - iter 84/121 - loss 0.08228471 - time (sec): 7.62 - samples/sec: 2227.99 - lr: 0.000041 - momentum: 0.000000
2023-10-23 19:17:26,830 epoch 3 - iter 96/121 - loss 0.08072554 - time (sec): 8.74 - samples/sec: 2258.26 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:17:27,828 epoch 3 - iter 108/121 - loss 0.08348649 - time (sec): 9.74 - samples/sec: 2269.70 - lr: 0.000040 - momentum: 0.000000
2023-10-23 19:17:28,958 epoch 3 - iter 120/121 - loss 0.08324832 - time (sec): 10.87 - samples/sec: 2262.21 - lr: 0.000039 - momentum: 0.000000
2023-10-23 19:17:29,035 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:29,036 EPOCH 3 done: loss 0.0828 - lr: 0.000039
2023-10-23 19:17:29,746 DEV : loss 0.12160609662532806 - f1-score (micro avg) 0.8191
2023-10-23 19:17:29,750 saving best model
2023-10-23 19:17:30,362 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:31,428 epoch 4 - iter 12/121 - loss 0.04546451 - time (sec): 1.06 - samples/sec: 2196.28 - lr: 0.000038 - momentum: 0.000000
2023-10-23 19:17:32,597 epoch 4 - iter 24/121 - loss 0.06098250 - time (sec): 2.23 - samples/sec: 2185.14 - lr: 0.000038 - momentum: 0.000000
2023-10-23 19:17:33,672 epoch 4 - iter 36/121 - loss 0.05602913 - time (sec): 3.31 - samples/sec: 2214.07 - lr: 0.000037 - momentum: 0.000000
2023-10-23 19:17:34,748 epoch 4 - iter 48/121 - loss 0.05772828 - time (sec): 4.39 - samples/sec: 2250.27 - lr: 0.000037 - momentum: 0.000000
2023-10-23 19:17:35,830 epoch 4 - iter 60/121 - loss 0.05350712 - time (sec): 5.47 - samples/sec: 2300.81 - lr: 0.000036 - momentum: 0.000000
2023-10-23 19:17:36,946 epoch 4 - iter 72/121 - loss 0.05555258 - time (sec): 6.58 - samples/sec: 2314.94 - lr: 0.000036 - momentum: 0.000000
2023-10-23 19:17:37,930 epoch 4 - iter 84/121 - loss 0.05687203 - time (sec): 7.57 - samples/sec: 2300.44 - lr: 0.000035 - momentum: 0.000000
2023-10-23 19:17:38,978 epoch 4 - iter 96/121 - loss 0.05775887 - time (sec): 8.61 - samples/sec: 2296.05 - lr: 0.000035 - momentum: 0.000000
2023-10-23 19:17:40,075 epoch 4 - iter 108/121 - loss 0.05928323 - time (sec): 9.71 - samples/sec: 2297.60 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:17:41,104 epoch 4 - iter 120/121 - loss 0.05753039 - time (sec): 10.74 - samples/sec: 2297.05 - lr: 0.000034 - momentum: 0.000000
2023-10-23 19:17:41,170 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:41,170 EPOCH 4 done: loss 0.0574 - lr: 0.000034
2023-10-23 19:17:41,877 DEV : loss 0.13370861113071442 - f1-score (micro avg) 0.846
2023-10-23 19:17:41,881 saving best model
2023-10-23 19:17:42,498 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:43,607 epoch 5 - iter 12/121 - loss 0.03795536 - time (sec): 1.11 - samples/sec: 2037.39 - lr: 0.000033 - momentum: 0.000000
2023-10-23 19:17:44,666 epoch 5 - iter 24/121 - loss 0.04199710 - time (sec): 2.17 - samples/sec: 2151.57 - lr: 0.000032 - momentum: 0.000000
2023-10-23 19:17:45,727 epoch 5 - iter 36/121 - loss 0.04063135 - time (sec): 3.23 - samples/sec: 2183.68 - lr: 0.000032 - momentum: 0.000000
2023-10-23 19:17:46,828 epoch 5 - iter 48/121 - loss 0.04131379 - time (sec): 4.33 - samples/sec: 2223.47 - lr: 0.000031 - momentum: 0.000000
2023-10-23 19:17:48,013 epoch 5 - iter 60/121 - loss 0.04224433 - time (sec): 5.51 - samples/sec: 2249.93 - lr: 0.000031 - momentum: 0.000000
2023-10-23 19:17:49,089 epoch 5 - iter 72/121 - loss 0.04511043 - time (sec): 6.59 - samples/sec: 2245.11 - lr: 0.000030 - momentum: 0.000000
2023-10-23 19:17:50,147 epoch 5 - iter 84/121 - loss 0.04148152 - time (sec): 7.65 - samples/sec: 2261.72 - lr: 0.000030 - momentum: 0.000000
2023-10-23 19:17:51,189 epoch 5 - iter 96/121 - loss 0.04159397 - time (sec): 8.69 - samples/sec: 2256.58 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:17:52,225 epoch 5 - iter 108/121 - loss 0.04023066 - time (sec): 9.73 - samples/sec: 2262.81 - lr: 0.000029 - momentum: 0.000000
2023-10-23 19:17:53,290 epoch 5 - iter 120/121 - loss 0.03970280 - time (sec): 10.79 - samples/sec: 2270.68 - lr: 0.000028 - momentum: 0.000000
2023-10-23 19:17:53,378 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:53,378 EPOCH 5 done: loss 0.0399 - lr: 0.000028
2023-10-23 19:17:54,086 DEV : loss 0.15133920311927795 - f1-score (micro avg) 0.8446
2023-10-23 19:17:54,091 ----------------------------------------------------------------------------------------------------
2023-10-23 19:17:55,186 epoch 6 - iter 12/121 - loss 0.02447443 - time (sec): 1.09 - samples/sec: 2281.68 - lr: 0.000027 - momentum: 0.000000
2023-10-23 19:17:56,257 epoch 6 - iter 24/121 - loss 0.02866063 - time (sec): 2.16 - samples/sec: 2292.94 - lr: 0.000027 - momentum: 0.000000
2023-10-23 19:17:57,361 epoch 6 - iter 36/121 - loss 0.02466423 - time (sec): 3.27 - samples/sec: 2227.08 - lr: 0.000026 - momentum: 0.000000
2023-10-23 19:17:58,323 epoch 6 - iter 48/121 - loss 0.02453619 - time (sec): 4.23 - samples/sec: 2253.25 - lr: 0.000026 - momentum: 0.000000
2023-10-23 19:17:59,502 epoch 6 - iter 60/121 - loss 0.02414396 - time (sec): 5.41 - samples/sec: 2276.41 - lr: 0.000025 - momentum: 0.000000
2023-10-23 19:18:00,637 epoch 6 - iter 72/121 - loss 0.02532751 - time (sec): 6.55 - samples/sec: 2254.28 - lr: 0.000025 - momentum: 0.000000
2023-10-23 19:18:01,786 epoch 6 - iter 84/121 - loss 0.02501141 - time (sec): 7.69 - samples/sec: 2216.56 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:18:02,857 epoch 6 - iter 96/121 - loss 0.02620381 - time (sec): 8.77 - samples/sec: 2237.47 - lr: 0.000024 - momentum: 0.000000
2023-10-23 19:18:03,974 epoch 6 - iter 108/121 - loss 0.02653234 - time (sec): 9.88 - samples/sec: 2223.71 - lr: 0.000023 - momentum: 0.000000
2023-10-23 19:18:05,062 epoch 6 - iter 120/121 - loss 0.02794705 - time (sec): 10.97 - samples/sec: 2239.31 - lr: 0.000022 - momentum: 0.000000
2023-10-23 19:18:05,131 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:05,132 EPOCH 6 done: loss 0.0279 - lr: 0.000022
2023-10-23 19:18:05,992 DEV : loss 0.14656664431095123 - f1-score (micro avg) 0.8522
2023-10-23 19:18:05,996 saving best model
2023-10-23 19:18:06,638 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:07,720 epoch 7 - iter 12/121 - loss 0.01613967 - time (sec): 1.08 - samples/sec: 2476.21 - lr: 0.000022 - momentum: 0.000000
2023-10-23 19:18:08,819 epoch 7 - iter 24/121 - loss 0.01984545 - time (sec): 2.18 - samples/sec: 2331.63 - lr: 0.000021 - momentum: 0.000000
2023-10-23 19:18:09,900 epoch 7 - iter 36/121 - loss 0.01834316 - time (sec): 3.26 - samples/sec: 2305.23 - lr: 0.000021 - momentum: 0.000000
2023-10-23 19:18:10,999 epoch 7 - iter 48/121 - loss 0.01661789 - time (sec): 4.36 - samples/sec: 2300.87 - lr: 0.000020 - momentum: 0.000000
2023-10-23 19:18:12,044 epoch 7 - iter 60/121 - loss 0.01760996 - time (sec): 5.40 - samples/sec: 2298.50 - lr: 0.000020 - momentum: 0.000000
2023-10-23 19:18:13,220 epoch 7 - iter 72/121 - loss 0.01879381 - time (sec): 6.58 - samples/sec: 2251.54 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:18:14,262 epoch 7 - iter 84/121 - loss 0.01780585 - time (sec): 7.62 - samples/sec: 2270.88 - lr: 0.000019 - momentum: 0.000000
2023-10-23 19:18:15,353 epoch 7 - iter 96/121 - loss 0.01714403 - time (sec): 8.71 - samples/sec: 2268.93 - lr: 0.000018 - momentum: 0.000000
2023-10-23 19:18:16,368 epoch 7 - iter 108/121 - loss 0.01812978 - time (sec): 9.73 - samples/sec: 2274.32 - lr: 0.000017 - momentum: 0.000000
2023-10-23 19:18:17,435 epoch 7 - iter 120/121 - loss 0.01793965 - time (sec): 10.80 - samples/sec: 2274.95 - lr: 0.000017 - momentum: 0.000000
2023-10-23 19:18:17,503 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:17,504 EPOCH 7 done: loss 0.0193 - lr: 0.000017
2023-10-23 19:18:18,201 DEV : loss 0.18479269742965698 - f1-score (micro avg) 0.8539
2023-10-23 19:18:18,205 saving best model
2023-10-23 19:18:18,809 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:19,886 epoch 8 - iter 12/121 - loss 0.01658824 - time (sec): 1.08 - samples/sec: 2310.61 - lr: 0.000016 - momentum: 0.000000
2023-10-23 19:18:20,994 epoch 8 - iter 24/121 - loss 0.01445413 - time (sec): 2.18 - samples/sec: 2277.77 - lr: 0.000016 - momentum: 0.000000
2023-10-23 19:18:22,068 epoch 8 - iter 36/121 - loss 0.01111450 - time (sec): 3.26 - samples/sec: 2253.49 - lr: 0.000015 - momentum: 0.000000
2023-10-23 19:18:23,079 epoch 8 - iter 48/121 - loss 0.01111916 - time (sec): 4.27 - samples/sec: 2282.85 - lr: 0.000015 - momentum: 0.000000
2023-10-23 19:18:24,085 epoch 8 - iter 60/121 - loss 0.01083118 - time (sec): 5.27 - samples/sec: 2267.00 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:18:25,103 epoch 8 - iter 72/121 - loss 0.01159512 - time (sec): 6.29 - samples/sec: 2296.82 - lr: 0.000014 - momentum: 0.000000
2023-10-23 19:18:26,208 epoch 8 - iter 84/121 - loss 0.01313584 - time (sec): 7.40 - samples/sec: 2297.06 - lr: 0.000013 - momentum: 0.000000
2023-10-23 19:18:27,351 epoch 8 - iter 96/121 - loss 0.01196163 - time (sec): 8.54 - samples/sec: 2317.34 - lr: 0.000013 - momentum: 0.000000
2023-10-23 19:18:28,377 epoch 8 - iter 108/121 - loss 0.01122020 - time (sec): 9.57 - samples/sec: 2325.53 - lr: 0.000012 - momentum: 0.000000
2023-10-23 19:18:29,426 epoch 8 - iter 120/121 - loss 0.01269033 - time (sec): 10.62 - samples/sec: 2306.08 - lr: 0.000011 - momentum: 0.000000
2023-10-23 19:18:29,541 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:29,541 EPOCH 8 done: loss 0.0126 - lr: 0.000011
2023-10-23 19:18:30,241 DEV : loss 0.19710467755794525 - f1-score (micro avg) 0.8424
2023-10-23 19:18:30,245 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:31,235 epoch 9 - iter 12/121 - loss 0.01794818 - time (sec): 0.99 - samples/sec: 2435.01 - lr: 0.000011 - momentum: 0.000000
2023-10-23 19:18:32,276 epoch 9 - iter 24/121 - loss 0.01251622 - time (sec): 2.03 - samples/sec: 2419.60 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:18:33,383 epoch 9 - iter 36/121 - loss 0.00847168 - time (sec): 3.14 - samples/sec: 2357.98 - lr: 0.000010 - momentum: 0.000000
2023-10-23 19:18:34,465 epoch 9 - iter 48/121 - loss 0.00852648 - time (sec): 4.22 - samples/sec: 2390.40 - lr: 0.000009 - momentum: 0.000000
2023-10-23 19:18:35,515 epoch 9 - iter 60/121 - loss 0.01017054 - time (sec): 5.27 - samples/sec: 2364.10 - lr: 0.000009 - momentum: 0.000000
2023-10-23 19:18:36,635 epoch 9 - iter 72/121 - loss 0.00894353 - time (sec): 6.39 - samples/sec: 2360.02 - lr: 0.000008 - momentum: 0.000000
2023-10-23 19:18:37,664 epoch 9 - iter 84/121 - loss 0.00789992 - time (sec): 7.42 - samples/sec: 2350.40 - lr: 0.000008 - momentum: 0.000000
2023-10-23 19:18:38,698 epoch 9 - iter 96/121 - loss 0.00788349 - time (sec): 8.45 - samples/sec: 2357.86 - lr: 0.000007 - momentum: 0.000000
2023-10-23 19:18:39,793 epoch 9 - iter 108/121 - loss 0.00834119 - time (sec): 9.55 - samples/sec: 2314.69 - lr: 0.000006 - momentum: 0.000000
2023-10-23 19:18:40,873 epoch 9 - iter 120/121 - loss 0.00822010 - time (sec): 10.63 - samples/sec: 2318.95 - lr: 0.000006 - momentum: 0.000000
2023-10-23 19:18:40,946 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:40,947 EPOCH 9 done: loss 0.0082 - lr: 0.000006
2023-10-23 19:18:41,647 DEV : loss 0.2059398740530014 - f1-score (micro avg) 0.8354
2023-10-23 19:18:41,651 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:42,828 epoch 10 - iter 12/121 - loss 0.00397773 - time (sec): 1.18 - samples/sec: 2221.89 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:18:43,931 epoch 10 - iter 24/121 - loss 0.00493849 - time (sec): 2.28 - samples/sec: 2261.14 - lr: 0.000005 - momentum: 0.000000
2023-10-23 19:18:44,978 epoch 10 - iter 36/121 - loss 0.00334518 - time (sec): 3.33 - samples/sec: 2351.77 - lr: 0.000004 - momentum: 0.000000
2023-10-23 19:18:46,067 epoch 10 - iter 48/121 - loss 0.00273462 - time (sec): 4.42 - samples/sec: 2344.85 - lr: 0.000004 - momentum: 0.000000
2023-10-23 19:18:47,158 epoch 10 - iter 60/121 - loss 0.00482458 - time (sec): 5.51 - samples/sec: 2334.56 - lr: 0.000003 - momentum: 0.000000
2023-10-23 19:18:48,231 epoch 10 - iter 72/121 - loss 0.00411537 - time (sec): 6.58 - samples/sec: 2316.05 - lr: 0.000003 - momentum: 0.000000
2023-10-23 19:18:49,216 epoch 10 - iter 84/121 - loss 0.00517085 - time (sec): 7.56 - samples/sec: 2302.06 - lr: 0.000002 - momentum: 0.000000
2023-10-23 19:18:50,215 epoch 10 - iter 96/121 - loss 0.00461560 - time (sec): 8.56 - samples/sec: 2316.71 - lr: 0.000001 - momentum: 0.000000
2023-10-23 19:18:51,284 epoch 10 - iter 108/121 - loss 0.00542344 - time (sec): 9.63 - samples/sec: 2319.31 - lr: 0.000001 - momentum: 0.000000
2023-10-23 19:18:52,308 epoch 10 - iter 120/121 - loss 0.00506168 - time (sec): 10.66 - samples/sec: 2310.54 - lr: 0.000000 - momentum: 0.000000
2023-10-23 19:18:52,370 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:52,371 EPOCH 10 done: loss 0.0050 - lr: 0.000000
2023-10-23 19:18:53,071 DEV : loss 0.2112000286579132 - f1-score (micro avg) 0.8385
2023-10-23 19:18:53,545 ----------------------------------------------------------------------------------------------------
2023-10-23 19:18:53,546 Loading model from best epoch ...
2023-10-23 19:18:55,021 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
2023-10-23 19:18:55,887
Results:
- F-score (micro) 0.8146
- F-score (macro) 0.5846
- Accuracy 0.7066
By class:
precision recall f1-score support
pers 0.8378 0.8921 0.8641 139
scope 0.8321 0.8837 0.8571 129
work 0.6593 0.7500 0.7018 80
loc 1.0000 0.3333 0.5000 9
date 0.0000 0.0000 0.0000 3
micro avg 0.7942 0.8361 0.8146 360
macro avg 0.6659 0.5718 0.5846 360
weighted avg 0.7932 0.8361 0.8092 360
2023-10-23 19:18:55,887 ----------------------------------------------------------------------------------------------------
|