Spaces:
Running
Running
File size: 27,079 Bytes
fab07ce |
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 |
2023-06-02 14:25:08,771 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,775 Model: "TARSClassifier(
(tars_model): TextClassifier(
(decoder): Linear(in_features=768, out_features=2, bias=True)
(dropout): Dropout(p=0.0, inplace=False)
(locked_dropout): LockedDropout(p=0.0)
(word_dropout): WordDropout(p=0.0)
(loss_function): CrossEntropyLoss()
(document_embeddings): TransformerDocumentEmbeddings(
(model): BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(30522, 768, padding_idx=0)
(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()
)
)
)
)
)"
2023-06-02 14:25:08,776 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,777 Corpus: "Corpus: 320 train + 40 dev + 40 test sentences"
2023-06-02 14:25:08,778 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,779 Parameters:
2023-06-02 14:25:08,780 - learning_rate: "0.020000"
2023-06-02 14:25:08,780 - mini_batch_size: "16"
2023-06-02 14:25:08,781 - patience: "3"
2023-06-02 14:25:08,782 - anneal_factor: "0.5"
2023-06-02 14:25:08,782 - max_epochs: "6"
2023-06-02 14:25:08,783 - shuffle: "True"
2023-06-02 14:25:08,784 - train_with_dev: "False"
2023-06-02 14:25:08,784 - batch_growth_annealing: "False"
2023-06-02 14:25:08,785 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,785 Model training base path: "few-shot-model-avoid-multi"
2023-06-02 14:25:08,785 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,786 Device: cpu
2023-06-02 14:25:08,787 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:08,787 Embeddings storage mode: cpu
2023-06-02 14:25:08,788 ----------------------------------------------------------------------------------------------------
2023-06-02 14:25:22,986 epoch 1 - iter 2/20 - loss 0.08201581 - samples/sec: 2.28 - lr: 0.020000
2023-06-02 14:25:38,289 epoch 1 - iter 4/20 - loss 0.07553399 - samples/sec: 2.09 - lr: 0.020000
2023-06-02 14:25:55,912 epoch 1 - iter 6/20 - loss 0.07010122 - samples/sec: 1.82 - lr: 0.020000
2023-06-02 14:26:13,667 epoch 1 - iter 8/20 - loss 0.06748231 - samples/sec: 1.80 - lr: 0.020000
2023-06-02 14:26:32,776 epoch 1 - iter 10/20 - loss 0.06542407 - samples/sec: 1.68 - lr: 0.020000
2023-06-02 14:26:51,692 epoch 1 - iter 12/20 - loss 0.06340573 - samples/sec: 1.69 - lr: 0.020000
2023-06-02 14:27:08,675 epoch 1 - iter 14/20 - loss 0.06166933 - samples/sec: 1.89 - lr: 0.020000
2023-06-02 14:27:28,766 epoch 1 - iter 16/20 - loss 0.05963777 - samples/sec: 1.59 - lr: 0.020000
2023-06-02 14:27:48,103 epoch 1 - iter 18/20 - loss 0.05749305 - samples/sec: 1.66 - lr: 0.020000
2023-06-02 14:28:08,995 epoch 1 - iter 20/20 - loss 0.05420271 - samples/sec: 1.53 - lr: 0.020000
2023-06-02 14:28:09,002 ----------------------------------------------------------------------------------------------------
2023-06-02 14:28:09,006 EPOCH 1 done: loss 0.0542 - lr 0.020000
2023-06-02 14:28:27,486 Evaluating as a multi-label problem: False
2023-06-02 14:28:27,507 DEV : loss 0.13954095542430878 - f1-score (micro avg) 0.9474
2023-06-02 14:28:27,522 BAD EPOCHS (no improvement): 0
2023-06-02 14:28:27,524 saving best model
2023-06-02 14:28:28,463 ----------------------------------------------------------------------------------------------------
2023-06-02 14:28:49,872 epoch 2 - iter 2/20 - loss 0.03232752 - samples/sec: 1.51 - lr: 0.020000
2023-06-02 14:29:08,736 epoch 2 - iter 4/20 - loss 0.02754687 - samples/sec: 1.70 - lr: 0.020000
2023-06-02 14:29:28,976 epoch 2 - iter 6/20 - loss 0.02429472 - samples/sec: 1.58 - lr: 0.020000
2023-06-02 14:29:47,566 epoch 2 - iter 8/20 - loss 0.01991154 - samples/sec: 1.72 - lr: 0.020000
2023-06-02 14:30:06,087 epoch 2 - iter 10/20 - loss 0.02051827 - samples/sec: 1.73 - lr: 0.020000
2023-06-02 14:30:24,854 epoch 2 - iter 12/20 - loss 0.01816160 - samples/sec: 1.71 - lr: 0.020000
2023-06-02 14:30:44,124 epoch 2 - iter 14/20 - loss 0.01722967 - samples/sec: 1.66 - lr: 0.020000
2023-06-02 14:31:02,752 epoch 2 - iter 16/20 - loss 0.01540543 - samples/sec: 1.72 - lr: 0.020000
2023-06-02 14:31:21,526 epoch 2 - iter 18/20 - loss 0.01409036 - samples/sec: 1.71 - lr: 0.020000
2023-06-02 14:31:40,793 epoch 2 - iter 20/20 - loss 0.01284174 - samples/sec: 1.66 - lr: 0.020000
2023-06-02 14:31:40,799 ----------------------------------------------------------------------------------------------------
2023-06-02 14:31:40,801 EPOCH 2 done: loss 0.0128 - lr 0.020000
2023-06-02 14:31:59,920 Evaluating as a multi-label problem: True
2023-06-02 14:31:59,965 DEV : loss 0.02552533522248268 - f1-score (micro avg) 0.9877
2023-06-02 14:31:59,984 BAD EPOCHS (no improvement): 0
2023-06-02 14:31:59,987 saving best model
2023-06-02 14:32:00,905 ----------------------------------------------------------------------------------------------------
2023-06-02 14:32:21,756 epoch 3 - iter 2/20 - loss 0.00107591 - samples/sec: 1.54 - lr: 0.020000
2023-06-02 14:32:41,724 epoch 3 - iter 4/20 - loss 0.00104748 - samples/sec: 1.60 - lr: 0.020000
2023-06-02 14:33:00,542 epoch 3 - iter 6/20 - loss 0.00087392 - samples/sec: 1.70 - lr: 0.020000
2023-06-02 14:33:18,259 epoch 3 - iter 8/20 - loss 0.00069769 - samples/sec: 1.81 - lr: 0.020000
2023-06-02 14:33:35,557 epoch 3 - iter 10/20 - loss 0.00058949 - samples/sec: 1.85 - lr: 0.020000
2023-06-02 14:33:52,437 epoch 3 - iter 12/20 - loss 0.00065764 - samples/sec: 1.90 - lr: 0.020000
2023-06-02 14:34:09,061 epoch 3 - iter 14/20 - loss 0.00219498 - samples/sec: 1.93 - lr: 0.020000
2023-06-02 14:34:26,443 epoch 3 - iter 16/20 - loss 0.00285339 - samples/sec: 1.84 - lr: 0.020000
2023-06-02 14:34:44,161 epoch 3 - iter 18/20 - loss 0.00272177 - samples/sec: 1.81 - lr: 0.020000
2023-06-02 14:35:00,155 epoch 3 - iter 20/20 - loss 0.00257680 - samples/sec: 2.00 - lr: 0.020000
2023-06-02 14:35:00,161 ----------------------------------------------------------------------------------------------------
2023-06-02 14:35:00,163 EPOCH 3 done: loss 0.0026 - lr 0.020000
2023-06-02 14:35:14,530 Evaluating as a multi-label problem: False
2023-06-02 14:35:14,541 DEV : loss 0.0012317668879404664 - f1-score (micro avg) 1.0
2023-06-02 14:35:14,563 BAD EPOCHS (no improvement): 0
2023-06-02 14:35:14,567 saving best model
2023-06-02 14:35:15,339 ----------------------------------------------------------------------------------------------------
2023-06-02 14:35:33,110 epoch 4 - iter 2/20 - loss 0.00016652 - samples/sec: 1.81 - lr: 0.020000
2023-06-02 14:35:48,512 epoch 4 - iter 4/20 - loss 0.00014895 - samples/sec: 2.08 - lr: 0.020000
2023-06-02 14:36:07,826 epoch 4 - iter 6/20 - loss 0.00011768 - samples/sec: 1.66 - lr: 0.020000
2023-06-02 14:36:24,533 epoch 4 - iter 8/20 - loss 0.00009617 - samples/sec: 1.92 - lr: 0.020000
2023-06-02 14:36:41,069 epoch 4 - iter 10/20 - loss 0.00022733 - samples/sec: 1.94 - lr: 0.020000
2023-06-02 14:36:58,662 epoch 4 - iter 12/20 - loss 0.00162427 - samples/sec: 1.82 - lr: 0.020000
2023-06-02 14:37:15,836 epoch 4 - iter 14/20 - loss 0.00203344 - samples/sec: 1.87 - lr: 0.020000
2023-06-02 14:37:31,891 epoch 4 - iter 16/20 - loss 0.00202072 - samples/sec: 2.00 - lr: 0.020000
2023-06-02 14:37:52,319 epoch 4 - iter 18/20 - loss 0.00197607 - samples/sec: 1.57 - lr: 0.020000
2023-06-02 14:38:13,020 epoch 4 - iter 20/20 - loss 0.00178715 - samples/sec: 1.55 - lr: 0.020000
2023-06-02 14:38:13,025 ----------------------------------------------------------------------------------------------------
2023-06-02 14:38:13,026 EPOCH 4 done: loss 0.0018 - lr 0.020000
2023-06-02 14:38:28,160 Evaluating as a multi-label problem: False
2023-06-02 14:38:28,168 DEV : loss 0.00010660152474883944 - f1-score (micro avg) 1.0
2023-06-02 14:38:28,183 BAD EPOCHS (no improvement): 0
2023-06-02 14:38:28,185 ----------------------------------------------------------------------------------------------------
2023-06-02 14:38:44,255 epoch 5 - iter 2/20 - loss 0.00003677 - samples/sec: 2.00 - lr: 0.020000
2023-06-02 14:39:00,153 epoch 5 - iter 4/20 - loss 0.00006295 - samples/sec: 2.02 - lr: 0.020000
2023-06-02 14:39:20,191 epoch 5 - iter 6/20 - loss 0.00005841 - samples/sec: 1.60 - lr: 0.020000
2023-06-02 14:39:38,713 epoch 5 - iter 8/20 - loss 0.00005065 - samples/sec: 1.73 - lr: 0.020000
2023-06-02 14:40:00,109 epoch 5 - iter 10/20 - loss 0.00004766 - samples/sec: 1.50 - lr: 0.020000
2023-06-02 14:40:21,604 epoch 5 - iter 12/20 - loss 0.00004357 - samples/sec: 1.49 - lr: 0.020000
2023-06-02 14:40:39,866 epoch 5 - iter 14/20 - loss 0.00051349 - samples/sec: 1.75 - lr: 0.020000
2023-06-02 14:40:57,320 epoch 5 - iter 16/20 - loss 0.00045473 - samples/sec: 1.83 - lr: 0.020000
2023-06-02 14:41:17,345 epoch 5 - iter 18/20 - loss 0.00040704 - samples/sec: 1.60 - lr: 0.020000
2023-06-02 14:41:35,814 epoch 5 - iter 20/20 - loss 0.00036947 - samples/sec: 1.73 - lr: 0.020000
2023-06-02 14:41:35,822 ----------------------------------------------------------------------------------------------------
2023-06-02 14:41:35,824 EPOCH 5 done: loss 0.0004 - lr 0.020000
2023-06-02 14:41:53,128 Evaluating as a multi-label problem: False
2023-06-02 14:41:53,146 DEV : loss 5.184596011531539e-05 - f1-score (micro avg) 1.0
2023-06-02 14:41:53,172 BAD EPOCHS (no improvement): 0
2023-06-02 14:41:53,175 ----------------------------------------------------------------------------------------------------
2023-06-02 14:42:11,831 epoch 6 - iter 2/20 - loss 0.00021853 - samples/sec: 1.73 - lr: 0.020000
2023-06-02 14:42:29,786 epoch 6 - iter 4/20 - loss 0.00011888 - samples/sec: 1.78 - lr: 0.020000
2023-06-02 14:42:50,189 epoch 6 - iter 6/20 - loss 0.00008669 - samples/sec: 1.57 - lr: 0.020000
2023-06-02 14:43:07,162 epoch 6 - iter 8/20 - loss 0.00007672 - samples/sec: 1.89 - lr: 0.020000
2023-06-02 14:43:24,385 epoch 6 - iter 10/20 - loss 0.00006549 - samples/sec: 1.86 - lr: 0.020000
2023-06-02 14:43:40,104 epoch 6 - iter 12/20 - loss 0.00005759 - samples/sec: 2.04 - lr: 0.020000
2023-06-02 14:43:56,973 epoch 6 - iter 14/20 - loss 0.00005522 - samples/sec: 1.90 - lr: 0.020000
2023-06-02 14:44:13,936 epoch 6 - iter 16/20 - loss 0.00005217 - samples/sec: 1.89 - lr: 0.020000
2023-06-02 14:44:31,500 epoch 6 - iter 18/20 - loss 0.00004748 - samples/sec: 1.82 - lr: 0.020000
2023-06-02 14:44:49,136 epoch 6 - iter 20/20 - loss 0.00004882 - samples/sec: 1.82 - lr: 0.020000
2023-06-02 14:44:49,139 ----------------------------------------------------------------------------------------------------
2023-06-02 14:44:49,141 EPOCH 6 done: loss 0.0000 - lr 0.020000
2023-06-02 14:45:04,949 Evaluating as a multi-label problem: False
2023-06-02 14:45:04,963 DEV : loss 2.4813929485389963e-05 - f1-score (micro avg) 1.0
2023-06-02 14:45:04,990 BAD EPOCHS (no improvement): 0
2023-06-02 14:45:05,742 ----------------------------------------------------------------------------------------------------
2023-06-02 14:45:05,744 loading file few-shot-model-avoid-multi\best-model.pt
2023-06-02 14:45:24,058 Evaluating as a multi-label problem: False
2023-06-02 14:45:24,068 1.0 1.0 1.0 1.0
2023-06-02 14:45:24,070
Results:
- F-score (micro) 1.0
- F-score (macro) 1.0
- Accuracy 1.0
By class:
precision recall f1-score support
avoid_situations 1.0000 1.0000 1.0000 12
avoid_others 1.0000 1.0000 1.0000 12
avoid_stimuli 1.0000 1.0000 1.0000 10
avoid_activities 1.0000 1.0000 1.0000 6
accuracy 1.0000 40
macro avg 1.0000 1.0000 1.0000 40
weighted avg 1.0000 1.0000 1.0000 40
2023-06-02 14:45:24,071 ----------------------------------------------------------------------------------------------------
|