File size: 36,853 Bytes
a867fa0 |
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 |
2023-10-25 10:42:24,196 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 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 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
- NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /home/ubuntu/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Train: 14465 sentences
2023-10-25 10:42:24,197 (train_with_dev=False, train_with_test=False)
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Training Params:
2023-10-25 10:42:24,197 - learning_rate: "5e-05"
2023-10-25 10:42:24,197 - mini_batch_size: "8"
2023-10-25 10:42:24,197 - max_epochs: "10"
2023-10-25 10:42:24,197 - shuffle: "True"
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Plugins:
2023-10-25 10:42:24,197 - TensorboardLogger
2023-10-25 10:42:24,197 - LinearScheduler | warmup_fraction: '0.1'
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Final evaluation on model from best epoch (best-model.pt)
2023-10-25 10:42:24,197 - metric: "('micro avg', 'f1-score')"
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Computation:
2023-10-25 10:42:24,197 - compute on device: cuda:0
2023-10-25 10:42:24,197 - embedding storage: none
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,197 ----------------------------------------------------------------------------------------------------
2023-10-25 10:42:24,198 Logging anything other than scalars to TensorBoard is currently not supported.
2023-10-25 10:42:39,798 epoch 1 - iter 180/1809 - loss 1.08864236 - time (sec): 15.60 - samples/sec: 2462.39 - lr: 0.000005 - momentum: 0.000000
2023-10-25 10:42:55,362 epoch 1 - iter 360/1809 - loss 0.63737072 - time (sec): 31.16 - samples/sec: 2435.51 - lr: 0.000010 - momentum: 0.000000
2023-10-25 10:43:11,204 epoch 1 - iter 540/1809 - loss 0.47500323 - time (sec): 47.01 - samples/sec: 2422.29 - lr: 0.000015 - momentum: 0.000000
2023-10-25 10:43:26,982 epoch 1 - iter 720/1809 - loss 0.38842572 - time (sec): 62.78 - samples/sec: 2405.92 - lr: 0.000020 - momentum: 0.000000
2023-10-25 10:43:42,388 epoch 1 - iter 900/1809 - loss 0.33612833 - time (sec): 78.19 - samples/sec: 2392.53 - lr: 0.000025 - momentum: 0.000000
2023-10-25 10:43:58,152 epoch 1 - iter 1080/1809 - loss 0.29705344 - time (sec): 93.95 - samples/sec: 2390.75 - lr: 0.000030 - momentum: 0.000000
2023-10-25 10:44:14,538 epoch 1 - iter 1260/1809 - loss 0.26939451 - time (sec): 110.34 - samples/sec: 2392.79 - lr: 0.000035 - momentum: 0.000000
2023-10-25 10:44:30,974 epoch 1 - iter 1440/1809 - loss 0.24905179 - time (sec): 126.78 - samples/sec: 2389.57 - lr: 0.000040 - momentum: 0.000000
2023-10-25 10:44:46,901 epoch 1 - iter 1620/1809 - loss 0.23268593 - time (sec): 142.70 - samples/sec: 2385.14 - lr: 0.000045 - momentum: 0.000000
2023-10-25 10:45:02,841 epoch 1 - iter 1800/1809 - loss 0.21934057 - time (sec): 158.64 - samples/sec: 2384.02 - lr: 0.000050 - momentum: 0.000000
2023-10-25 10:45:03,516 ----------------------------------------------------------------------------------------------------
2023-10-25 10:45:03,517 EPOCH 1 done: loss 0.2188 - lr: 0.000050
2023-10-25 10:45:08,070 DEV : loss 0.12551043927669525 - f1-score (micro avg) 0.595
2023-10-25 10:45:08,092 saving best model
2023-10-25 10:45:08,652 ----------------------------------------------------------------------------------------------------
2023-10-25 10:45:24,334 epoch 2 - iter 180/1809 - loss 0.09357098 - time (sec): 15.68 - samples/sec: 2407.94 - lr: 0.000049 - momentum: 0.000000
2023-10-25 10:45:40,596 epoch 2 - iter 360/1809 - loss 0.09016993 - time (sec): 31.94 - samples/sec: 2403.78 - lr: 0.000049 - momentum: 0.000000
2023-10-25 10:45:56,781 epoch 2 - iter 540/1809 - loss 0.09172432 - time (sec): 48.13 - samples/sec: 2396.27 - lr: 0.000048 - momentum: 0.000000
2023-10-25 10:46:12,794 epoch 2 - iter 720/1809 - loss 0.09158145 - time (sec): 64.14 - samples/sec: 2398.33 - lr: 0.000048 - momentum: 0.000000
2023-10-25 10:46:28,593 epoch 2 - iter 900/1809 - loss 0.09251771 - time (sec): 79.94 - samples/sec: 2389.54 - lr: 0.000047 - momentum: 0.000000
2023-10-25 10:46:44,259 epoch 2 - iter 1080/1809 - loss 0.09131020 - time (sec): 95.61 - samples/sec: 2395.09 - lr: 0.000047 - momentum: 0.000000
2023-10-25 10:46:59,923 epoch 2 - iter 1260/1809 - loss 0.09065843 - time (sec): 111.27 - samples/sec: 2387.06 - lr: 0.000046 - momentum: 0.000000
2023-10-25 10:47:15,682 epoch 2 - iter 1440/1809 - loss 0.09009273 - time (sec): 127.03 - samples/sec: 2386.49 - lr: 0.000046 - momentum: 0.000000
2023-10-25 10:47:31,440 epoch 2 - iter 1620/1809 - loss 0.08870597 - time (sec): 142.79 - samples/sec: 2389.70 - lr: 0.000045 - momentum: 0.000000
2023-10-25 10:47:47,438 epoch 2 - iter 1800/1809 - loss 0.08734034 - time (sec): 158.79 - samples/sec: 2380.41 - lr: 0.000044 - momentum: 0.000000
2023-10-25 10:47:48,319 ----------------------------------------------------------------------------------------------------
2023-10-25 10:47:48,320 EPOCH 2 done: loss 0.0871 - lr: 0.000044
2023-10-25 10:47:53,589 DEV : loss 0.12736038863658905 - f1-score (micro avg) 0.6164
2023-10-25 10:47:53,611 saving best model
2023-10-25 10:47:54,320 ----------------------------------------------------------------------------------------------------
2023-10-25 10:48:10,502 epoch 3 - iter 180/1809 - loss 0.07791949 - time (sec): 16.18 - samples/sec: 2440.64 - lr: 0.000044 - momentum: 0.000000
2023-10-25 10:48:26,551 epoch 3 - iter 360/1809 - loss 0.07255591 - time (sec): 32.23 - samples/sec: 2434.36 - lr: 0.000043 - momentum: 0.000000
2023-10-25 10:48:42,860 epoch 3 - iter 540/1809 - loss 0.07280647 - time (sec): 48.54 - samples/sec: 2416.45 - lr: 0.000043 - momentum: 0.000000
2023-10-25 10:48:58,313 epoch 3 - iter 720/1809 - loss 0.06999820 - time (sec): 63.99 - samples/sec: 2405.21 - lr: 0.000042 - momentum: 0.000000
2023-10-25 10:49:14,210 epoch 3 - iter 900/1809 - loss 0.06882067 - time (sec): 79.89 - samples/sec: 2398.64 - lr: 0.000042 - momentum: 0.000000
2023-10-25 10:49:29,782 epoch 3 - iter 1080/1809 - loss 0.06780427 - time (sec): 95.46 - samples/sec: 2391.39 - lr: 0.000041 - momentum: 0.000000
2023-10-25 10:49:45,430 epoch 3 - iter 1260/1809 - loss 0.06627869 - time (sec): 111.11 - samples/sec: 2384.04 - lr: 0.000041 - momentum: 0.000000
2023-10-25 10:50:01,822 epoch 3 - iter 1440/1809 - loss 0.06607504 - time (sec): 127.50 - samples/sec: 2375.41 - lr: 0.000040 - momentum: 0.000000
2023-10-25 10:50:17,479 epoch 3 - iter 1620/1809 - loss 0.06532994 - time (sec): 143.16 - samples/sec: 2381.32 - lr: 0.000039 - momentum: 0.000000
2023-10-25 10:50:33,050 epoch 3 - iter 1800/1809 - loss 0.06483682 - time (sec): 158.73 - samples/sec: 2383.21 - lr: 0.000039 - momentum: 0.000000
2023-10-25 10:50:33,799 ----------------------------------------------------------------------------------------------------
2023-10-25 10:50:33,799 EPOCH 3 done: loss 0.0649 - lr: 0.000039
2023-10-25 10:50:38,557 DEV : loss 0.13015878200531006 - f1-score (micro avg) 0.6083
2023-10-25 10:50:38,579 ----------------------------------------------------------------------------------------------------
2023-10-25 10:50:54,622 epoch 4 - iter 180/1809 - loss 0.04109198 - time (sec): 16.04 - samples/sec: 2401.20 - lr: 0.000038 - momentum: 0.000000
2023-10-25 10:51:10,400 epoch 4 - iter 360/1809 - loss 0.04019791 - time (sec): 31.82 - samples/sec: 2393.98 - lr: 0.000038 - momentum: 0.000000
2023-10-25 10:51:26,181 epoch 4 - iter 540/1809 - loss 0.04111006 - time (sec): 47.60 - samples/sec: 2401.38 - lr: 0.000037 - momentum: 0.000000
2023-10-25 10:51:41,964 epoch 4 - iter 720/1809 - loss 0.04191859 - time (sec): 63.38 - samples/sec: 2379.87 - lr: 0.000037 - momentum: 0.000000
2023-10-25 10:51:57,954 epoch 4 - iter 900/1809 - loss 0.04474768 - time (sec): 79.37 - samples/sec: 2381.93 - lr: 0.000036 - momentum: 0.000000
2023-10-25 10:52:13,744 epoch 4 - iter 1080/1809 - loss 0.04597864 - time (sec): 95.16 - samples/sec: 2371.18 - lr: 0.000036 - momentum: 0.000000
2023-10-25 10:52:29,289 epoch 4 - iter 1260/1809 - loss 0.04532760 - time (sec): 110.71 - samples/sec: 2374.95 - lr: 0.000035 - momentum: 0.000000
2023-10-25 10:52:45,599 epoch 4 - iter 1440/1809 - loss 0.04474968 - time (sec): 127.02 - samples/sec: 2360.69 - lr: 0.000034 - momentum: 0.000000
2023-10-25 10:53:01,795 epoch 4 - iter 1620/1809 - loss 0.04456366 - time (sec): 143.21 - samples/sec: 2366.29 - lr: 0.000034 - momentum: 0.000000
2023-10-25 10:53:17,695 epoch 4 - iter 1800/1809 - loss 0.04497375 - time (sec): 159.11 - samples/sec: 2376.49 - lr: 0.000033 - momentum: 0.000000
2023-10-25 10:53:18,468 ----------------------------------------------------------------------------------------------------
2023-10-25 10:53:18,469 EPOCH 4 done: loss 0.0450 - lr: 0.000033
2023-10-25 10:53:23,224 DEV : loss 0.23449285328388214 - f1-score (micro avg) 0.5643
2023-10-25 10:53:23,246 ----------------------------------------------------------------------------------------------------
2023-10-25 10:53:39,283 epoch 5 - iter 180/1809 - loss 0.11798032 - time (sec): 16.04 - samples/sec: 2458.47 - lr: 0.000033 - momentum: 0.000000
2023-10-25 10:53:55,130 epoch 5 - iter 360/1809 - loss 0.09384126 - time (sec): 31.88 - samples/sec: 2408.73 - lr: 0.000032 - momentum: 0.000000
2023-10-25 10:54:10,990 epoch 5 - iter 540/1809 - loss 0.07744584 - time (sec): 47.74 - samples/sec: 2388.60 - lr: 0.000032 - momentum: 0.000000
2023-10-25 10:54:26,505 epoch 5 - iter 720/1809 - loss 0.08471679 - time (sec): 63.26 - samples/sec: 2396.43 - lr: 0.000031 - momentum: 0.000000
2023-10-25 10:54:42,213 epoch 5 - iter 900/1809 - loss 0.09678449 - time (sec): 78.97 - samples/sec: 2398.43 - lr: 0.000031 - momentum: 0.000000
2023-10-25 10:54:58,597 epoch 5 - iter 1080/1809 - loss 0.09685579 - time (sec): 95.35 - samples/sec: 2396.32 - lr: 0.000030 - momentum: 0.000000
2023-10-25 10:55:14,316 epoch 5 - iter 1260/1809 - loss 0.09900587 - time (sec): 111.07 - samples/sec: 2388.46 - lr: 0.000029 - momentum: 0.000000
2023-10-25 10:55:30,081 epoch 5 - iter 1440/1809 - loss 0.10576125 - time (sec): 126.83 - samples/sec: 2388.49 - lr: 0.000029 - momentum: 0.000000
2023-10-25 10:55:45,766 epoch 5 - iter 1620/1809 - loss 0.11334555 - time (sec): 142.52 - samples/sec: 2382.86 - lr: 0.000028 - momentum: 0.000000
2023-10-25 10:56:01,695 epoch 5 - iter 1800/1809 - loss 0.11935313 - time (sec): 158.45 - samples/sec: 2386.46 - lr: 0.000028 - momentum: 0.000000
2023-10-25 10:56:02,462 ----------------------------------------------------------------------------------------------------
2023-10-25 10:56:02,462 EPOCH 5 done: loss 0.1197 - lr: 0.000028
2023-10-25 10:56:07,710 DEV : loss 0.22438712418079376 - f1-score (micro avg) 0.3385
2023-10-25 10:56:07,732 ----------------------------------------------------------------------------------------------------
2023-10-25 10:56:23,701 epoch 6 - iter 180/1809 - loss 0.13593977 - time (sec): 15.97 - samples/sec: 2374.30 - lr: 0.000027 - momentum: 0.000000
2023-10-25 10:56:39,782 epoch 6 - iter 360/1809 - loss 0.11374633 - time (sec): 32.05 - samples/sec: 2397.55 - lr: 0.000027 - momentum: 0.000000
2023-10-25 10:56:55,834 epoch 6 - iter 540/1809 - loss 0.10944967 - time (sec): 48.10 - samples/sec: 2399.11 - lr: 0.000026 - momentum: 0.000000
2023-10-25 10:57:11,763 epoch 6 - iter 720/1809 - loss 0.13307279 - time (sec): 64.03 - samples/sec: 2395.36 - lr: 0.000026 - momentum: 0.000000
2023-10-25 10:57:27,269 epoch 6 - iter 900/1809 - loss 0.14472156 - time (sec): 79.54 - samples/sec: 2392.63 - lr: 0.000025 - momentum: 0.000000
2023-10-25 10:57:43,006 epoch 6 - iter 1080/1809 - loss 0.14546492 - time (sec): 95.27 - samples/sec: 2388.10 - lr: 0.000024 - momentum: 0.000000
2023-10-25 10:57:58,783 epoch 6 - iter 1260/1809 - loss 0.14276182 - time (sec): 111.05 - samples/sec: 2382.48 - lr: 0.000024 - momentum: 0.000000
2023-10-25 10:58:14,861 epoch 6 - iter 1440/1809 - loss 0.13027593 - time (sec): 127.13 - samples/sec: 2387.70 - lr: 0.000023 - momentum: 0.000000
2023-10-25 10:58:30,584 epoch 6 - iter 1620/1809 - loss 0.12180313 - time (sec): 142.85 - samples/sec: 2386.56 - lr: 0.000023 - momentum: 0.000000
2023-10-25 10:58:46,528 epoch 6 - iter 1800/1809 - loss 0.11629211 - time (sec): 158.80 - samples/sec: 2381.42 - lr: 0.000022 - momentum: 0.000000
2023-10-25 10:58:47,311 ----------------------------------------------------------------------------------------------------
2023-10-25 10:58:47,312 EPOCH 6 done: loss 0.1159 - lr: 0.000022
2023-10-25 10:58:52,577 DEV : loss 0.23836202919483185 - f1-score (micro avg) 0.5285
2023-10-25 10:58:52,599 ----------------------------------------------------------------------------------------------------
2023-10-25 10:59:08,273 epoch 7 - iter 180/1809 - loss 0.05953192 - time (sec): 15.67 - samples/sec: 2390.84 - lr: 0.000022 - momentum: 0.000000
2023-10-25 10:59:24,137 epoch 7 - iter 360/1809 - loss 0.06041906 - time (sec): 31.54 - samples/sec: 2347.48 - lr: 0.000021 - momentum: 0.000000
2023-10-25 10:59:40,181 epoch 7 - iter 540/1809 - loss 0.06633058 - time (sec): 47.58 - samples/sec: 2329.88 - lr: 0.000021 - momentum: 0.000000
2023-10-25 10:59:55,826 epoch 7 - iter 720/1809 - loss 0.06758924 - time (sec): 63.23 - samples/sec: 2345.81 - lr: 0.000020 - momentum: 0.000000
2023-10-25 11:00:12,024 epoch 7 - iter 900/1809 - loss 0.06923090 - time (sec): 79.42 - samples/sec: 2348.03 - lr: 0.000019 - momentum: 0.000000
2023-10-25 11:00:27,650 epoch 7 - iter 1080/1809 - loss 0.06847767 - time (sec): 95.05 - samples/sec: 2350.34 - lr: 0.000019 - momentum: 0.000000
2023-10-25 11:00:43,756 epoch 7 - iter 1260/1809 - loss 0.06519470 - time (sec): 111.16 - samples/sec: 2354.86 - lr: 0.000018 - momentum: 0.000000
2023-10-25 11:01:00,077 epoch 7 - iter 1440/1809 - loss 0.06291968 - time (sec): 127.48 - samples/sec: 2362.89 - lr: 0.000018 - momentum: 0.000000
2023-10-25 11:01:15,563 epoch 7 - iter 1620/1809 - loss 0.06280369 - time (sec): 142.96 - samples/sec: 2372.87 - lr: 0.000017 - momentum: 0.000000
2023-10-25 11:01:31,725 epoch 7 - iter 1800/1809 - loss 0.06011227 - time (sec): 159.12 - samples/sec: 2377.28 - lr: 0.000017 - momentum: 0.000000
2023-10-25 11:01:32,510 ----------------------------------------------------------------------------------------------------
2023-10-25 11:01:32,510 EPOCH 7 done: loss 0.0601 - lr: 0.000017
2023-10-25 11:01:37,792 DEV : loss 0.25131794810295105 - f1-score (micro avg) 0.5408
2023-10-25 11:01:37,814 ----------------------------------------------------------------------------------------------------
2023-10-25 11:01:53,779 epoch 8 - iter 180/1809 - loss 0.01859667 - time (sec): 15.96 - samples/sec: 2421.30 - lr: 0.000016 - momentum: 0.000000
2023-10-25 11:02:09,497 epoch 8 - iter 360/1809 - loss 0.02439411 - time (sec): 31.68 - samples/sec: 2406.52 - lr: 0.000016 - momentum: 0.000000
2023-10-25 11:02:25,696 epoch 8 - iter 540/1809 - loss 0.02666204 - time (sec): 47.88 - samples/sec: 2383.15 - lr: 0.000015 - momentum: 0.000000
2023-10-25 11:02:41,394 epoch 8 - iter 720/1809 - loss 0.03108643 - time (sec): 63.58 - samples/sec: 2379.68 - lr: 0.000014 - momentum: 0.000000
2023-10-25 11:02:57,230 epoch 8 - iter 900/1809 - loss 0.03146788 - time (sec): 79.42 - samples/sec: 2379.80 - lr: 0.000014 - momentum: 0.000000
2023-10-25 11:03:13,381 epoch 8 - iter 1080/1809 - loss 0.03266776 - time (sec): 95.57 - samples/sec: 2388.45 - lr: 0.000013 - momentum: 0.000000
2023-10-25 11:03:29,042 epoch 8 - iter 1260/1809 - loss 0.03363994 - time (sec): 111.23 - samples/sec: 2391.56 - lr: 0.000013 - momentum: 0.000000
2023-10-25 11:03:44,858 epoch 8 - iter 1440/1809 - loss 0.03353747 - time (sec): 127.04 - samples/sec: 2394.81 - lr: 0.000012 - momentum: 0.000000
2023-10-25 11:04:00,459 epoch 8 - iter 1620/1809 - loss 0.03451516 - time (sec): 142.64 - samples/sec: 2393.65 - lr: 0.000012 - momentum: 0.000000
2023-10-25 11:04:16,154 epoch 8 - iter 1800/1809 - loss 0.03533870 - time (sec): 158.34 - samples/sec: 2387.59 - lr: 0.000011 - momentum: 0.000000
2023-10-25 11:04:16,985 ----------------------------------------------------------------------------------------------------
2023-10-25 11:04:16,986 EPOCH 8 done: loss 0.0353 - lr: 0.000011
2023-10-25 11:04:22,282 DEV : loss 0.2803691029548645 - f1-score (micro avg) 0.5162
2023-10-25 11:04:22,304 ----------------------------------------------------------------------------------------------------
2023-10-25 11:04:38,035 epoch 9 - iter 180/1809 - loss 0.04227779 - time (sec): 15.73 - samples/sec: 2359.95 - lr: 0.000011 - momentum: 0.000000
2023-10-25 11:04:53,886 epoch 9 - iter 360/1809 - loss 0.03812442 - time (sec): 31.58 - samples/sec: 2363.59 - lr: 0.000010 - momentum: 0.000000
2023-10-25 11:05:09,537 epoch 9 - iter 540/1809 - loss 0.03623853 - time (sec): 47.23 - samples/sec: 2371.61 - lr: 0.000009 - momentum: 0.000000
2023-10-25 11:05:25,709 epoch 9 - iter 720/1809 - loss 0.03584853 - time (sec): 63.40 - samples/sec: 2381.00 - lr: 0.000009 - momentum: 0.000000
2023-10-25 11:05:41,500 epoch 9 - iter 900/1809 - loss 0.03443228 - time (sec): 79.20 - samples/sec: 2386.06 - lr: 0.000008 - momentum: 0.000000
2023-10-25 11:05:57,949 epoch 9 - iter 1080/1809 - loss 0.03283348 - time (sec): 95.64 - samples/sec: 2383.97 - lr: 0.000008 - momentum: 0.000000
2023-10-25 11:06:14,072 epoch 9 - iter 1260/1809 - loss 0.03344930 - time (sec): 111.77 - samples/sec: 2378.11 - lr: 0.000007 - momentum: 0.000000
2023-10-25 11:06:30,047 epoch 9 - iter 1440/1809 - loss 0.03338922 - time (sec): 127.74 - samples/sec: 2380.90 - lr: 0.000007 - momentum: 0.000000
2023-10-25 11:06:45,210 epoch 9 - iter 1620/1809 - loss 0.03462184 - time (sec): 142.91 - samples/sec: 2379.23 - lr: 0.000006 - momentum: 0.000000
2023-10-25 11:07:00,995 epoch 9 - iter 1800/1809 - loss 0.03463472 - time (sec): 158.69 - samples/sec: 2383.29 - lr: 0.000006 - momentum: 0.000000
2023-10-25 11:07:01,773 ----------------------------------------------------------------------------------------------------
2023-10-25 11:07:01,773 EPOCH 9 done: loss 0.0347 - lr: 0.000006
2023-10-25 11:07:06,528 DEV : loss 0.2776682376861572 - f1-score (micro avg) 0.5031
2023-10-25 11:07:06,550 ----------------------------------------------------------------------------------------------------
2023-10-25 11:07:22,652 epoch 10 - iter 180/1809 - loss 0.02754181 - time (sec): 16.10 - samples/sec: 2301.55 - lr: 0.000005 - momentum: 0.000000
2023-10-25 11:07:38,870 epoch 10 - iter 360/1809 - loss 0.03479173 - time (sec): 32.32 - samples/sec: 2325.30 - lr: 0.000004 - momentum: 0.000000
2023-10-25 11:07:55,201 epoch 10 - iter 540/1809 - loss 0.03464083 - time (sec): 48.65 - samples/sec: 2351.22 - lr: 0.000004 - momentum: 0.000000
2023-10-25 11:08:11,048 epoch 10 - iter 720/1809 - loss 0.03422069 - time (sec): 64.50 - samples/sec: 2358.86 - lr: 0.000003 - momentum: 0.000000
2023-10-25 11:08:26,946 epoch 10 - iter 900/1809 - loss 0.03352713 - time (sec): 80.40 - samples/sec: 2373.35 - lr: 0.000003 - momentum: 0.000000
2023-10-25 11:08:42,565 epoch 10 - iter 1080/1809 - loss 0.03377603 - time (sec): 96.01 - samples/sec: 2365.83 - lr: 0.000002 - momentum: 0.000000
2023-10-25 11:08:58,382 epoch 10 - iter 1260/1809 - loss 0.03388777 - time (sec): 111.83 - samples/sec: 2369.29 - lr: 0.000002 - momentum: 0.000000
2023-10-25 11:09:14,125 epoch 10 - iter 1440/1809 - loss 0.03414918 - time (sec): 127.57 - samples/sec: 2372.33 - lr: 0.000001 - momentum: 0.000000
2023-10-25 11:09:30,395 epoch 10 - iter 1620/1809 - loss 0.03466586 - time (sec): 143.84 - samples/sec: 2374.22 - lr: 0.000001 - momentum: 0.000000
2023-10-25 11:09:46,068 epoch 10 - iter 1800/1809 - loss 0.03590016 - time (sec): 159.52 - samples/sec: 2372.05 - lr: 0.000000 - momentum: 0.000000
2023-10-25 11:09:46,864 ----------------------------------------------------------------------------------------------------
2023-10-25 11:09:46,864 EPOCH 10 done: loss 0.0359 - lr: 0.000000
2023-10-25 11:09:51,615 DEV : loss 0.2868908643722534 - f1-score (micro avg) 0.4824
2023-10-25 11:09:52,189 ----------------------------------------------------------------------------------------------------
2023-10-25 11:09:52,190 Loading model from best epoch ...
2023-10-25 11:09:53,952 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
2023-10-25 11:10:00,212
Results:
- F-score (micro) 0.6416
- F-score (macro) 0.4392
- Accuracy 0.4784
By class:
precision recall f1-score support
loc 0.6730 0.7208 0.6961 591
pers 0.5624 0.6947 0.6216 357
org 0.0000 0.0000 0.0000 79
micro avg 0.6276 0.6563 0.6416 1027
macro avg 0.4118 0.4718 0.4392 1027
weighted avg 0.5828 0.6563 0.6166 1027
2023-10-25 11:10:00,213 ----------------------------------------------------------------------------------------------------
|