training.log
| 1 | 2021-01-15 16:27:19,924 ---------------------------------------------------------------------------------------------------- |
| 2 | 2021-01-15 16:27:19,927 Model: "SequenceTagger( |
| 3 | (embeddings): TransformerWordEmbeddings( |
| 4 | (model): XLMRobertaModel( |
| 5 | (embeddings): RobertaEmbeddings( |
| 6 | (word_embeddings): Embedding(250002, 1024, padding_idx=1) |
| 7 | (position_embeddings): Embedding(514, 1024, padding_idx=1) |
| 8 | (token_type_embeddings): Embedding(1, 1024) |
| 9 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 10 | (dropout): Dropout(p=0.1, inplace=False) |
| 11 | ) |
| 12 | (encoder): RobertaEncoder( |
| 13 | (layer): ModuleList( |
| 14 | (0): RobertaLayer( |
| 15 | (attention): RobertaAttention( |
| 16 | (self): RobertaSelfAttention( |
| 17 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 18 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 19 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 20 | (dropout): Dropout(p=0.1, inplace=False) |
| 21 | ) |
| 22 | (output): RobertaSelfOutput( |
| 23 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 24 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 25 | (dropout): Dropout(p=0.1, inplace=False) |
| 26 | ) |
| 27 | ) |
| 28 | (intermediate): RobertaIntermediate( |
| 29 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 30 | ) |
| 31 | (output): RobertaOutput( |
| 32 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 33 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 34 | (dropout): Dropout(p=0.1, inplace=False) |
| 35 | ) |
| 36 | ) |
| 37 | (1): RobertaLayer( |
| 38 | (attention): RobertaAttention( |
| 39 | (self): RobertaSelfAttention( |
| 40 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 41 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 42 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 43 | (dropout): Dropout(p=0.1, inplace=False) |
| 44 | ) |
| 45 | (output): RobertaSelfOutput( |
| 46 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 47 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 48 | (dropout): Dropout(p=0.1, inplace=False) |
| 49 | ) |
| 50 | ) |
| 51 | (intermediate): RobertaIntermediate( |
| 52 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 53 | ) |
| 54 | (output): RobertaOutput( |
| 55 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 56 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 57 | (dropout): Dropout(p=0.1, inplace=False) |
| 58 | ) |
| 59 | ) |
| 60 | (2): RobertaLayer( |
| 61 | (attention): RobertaAttention( |
| 62 | (self): RobertaSelfAttention( |
| 63 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 64 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 65 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 66 | (dropout): Dropout(p=0.1, inplace=False) |
| 67 | ) |
| 68 | (output): RobertaSelfOutput( |
| 69 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 70 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 71 | (dropout): Dropout(p=0.1, inplace=False) |
| 72 | ) |
| 73 | ) |
| 74 | (intermediate): RobertaIntermediate( |
| 75 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 76 | ) |
| 77 | (output): RobertaOutput( |
| 78 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 79 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 80 | (dropout): Dropout(p=0.1, inplace=False) |
| 81 | ) |
| 82 | ) |
| 83 | (3): RobertaLayer( |
| 84 | (attention): RobertaAttention( |
| 85 | (self): RobertaSelfAttention( |
| 86 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 87 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 88 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 89 | (dropout): Dropout(p=0.1, inplace=False) |
| 90 | ) |
| 91 | (output): RobertaSelfOutput( |
| 92 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 93 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 94 | (dropout): Dropout(p=0.1, inplace=False) |
| 95 | ) |
| 96 | ) |
| 97 | (intermediate): RobertaIntermediate( |
| 98 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 99 | ) |
| 100 | (output): RobertaOutput( |
| 101 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 102 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 103 | (dropout): Dropout(p=0.1, inplace=False) |
| 104 | ) |
| 105 | ) |
| 106 | (4): RobertaLayer( |
| 107 | (attention): RobertaAttention( |
| 108 | (self): RobertaSelfAttention( |
| 109 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 110 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 111 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 112 | (dropout): Dropout(p=0.1, inplace=False) |
| 113 | ) |
| 114 | (output): RobertaSelfOutput( |
| 115 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 116 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 117 | (dropout): Dropout(p=0.1, inplace=False) |
| 118 | ) |
| 119 | ) |
| 120 | (intermediate): RobertaIntermediate( |
| 121 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 122 | ) |
| 123 | (output): RobertaOutput( |
| 124 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 125 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 126 | (dropout): Dropout(p=0.1, inplace=False) |
| 127 | ) |
| 128 | ) |
| 129 | (5): RobertaLayer( |
| 130 | (attention): RobertaAttention( |
| 131 | (self): RobertaSelfAttention( |
| 132 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 133 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 134 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 135 | (dropout): Dropout(p=0.1, inplace=False) |
| 136 | ) |
| 137 | (output): RobertaSelfOutput( |
| 138 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 139 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 140 | (dropout): Dropout(p=0.1, inplace=False) |
| 141 | ) |
| 142 | ) |
| 143 | (intermediate): RobertaIntermediate( |
| 144 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 145 | ) |
| 146 | (output): RobertaOutput( |
| 147 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 148 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 149 | (dropout): Dropout(p=0.1, inplace=False) |
| 150 | ) |
| 151 | ) |
| 152 | (6): RobertaLayer( |
| 153 | (attention): RobertaAttention( |
| 154 | (self): RobertaSelfAttention( |
| 155 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 156 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 157 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 158 | (dropout): Dropout(p=0.1, inplace=False) |
| 159 | ) |
| 160 | (output): RobertaSelfOutput( |
| 161 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 162 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 163 | (dropout): Dropout(p=0.1, inplace=False) |
| 164 | ) |
| 165 | ) |
| 166 | (intermediate): RobertaIntermediate( |
| 167 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 168 | ) |
| 169 | (output): RobertaOutput( |
| 170 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 171 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 172 | (dropout): Dropout(p=0.1, inplace=False) |
| 173 | ) |
| 174 | ) |
| 175 | (7): RobertaLayer( |
| 176 | (attention): RobertaAttention( |
| 177 | (self): RobertaSelfAttention( |
| 178 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 179 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 180 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 181 | (dropout): Dropout(p=0.1, inplace=False) |
| 182 | ) |
| 183 | (output): RobertaSelfOutput( |
| 184 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 185 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 186 | (dropout): Dropout(p=0.1, inplace=False) |
| 187 | ) |
| 188 | ) |
| 189 | (intermediate): RobertaIntermediate( |
| 190 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 191 | ) |
| 192 | (output): RobertaOutput( |
| 193 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 194 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 195 | (dropout): Dropout(p=0.1, inplace=False) |
| 196 | ) |
| 197 | ) |
| 198 | (8): RobertaLayer( |
| 199 | (attention): RobertaAttention( |
| 200 | (self): RobertaSelfAttention( |
| 201 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 202 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 203 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 204 | (dropout): Dropout(p=0.1, inplace=False) |
| 205 | ) |
| 206 | (output): RobertaSelfOutput( |
| 207 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 208 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 209 | (dropout): Dropout(p=0.1, inplace=False) |
| 210 | ) |
| 211 | ) |
| 212 | (intermediate): RobertaIntermediate( |
| 213 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 214 | ) |
| 215 | (output): RobertaOutput( |
| 216 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 217 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 218 | (dropout): Dropout(p=0.1, inplace=False) |
| 219 | ) |
| 220 | ) |
| 221 | (9): RobertaLayer( |
| 222 | (attention): RobertaAttention( |
| 223 | (self): RobertaSelfAttention( |
| 224 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 225 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 226 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 227 | (dropout): Dropout(p=0.1, inplace=False) |
| 228 | ) |
| 229 | (output): RobertaSelfOutput( |
| 230 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 231 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 232 | (dropout): Dropout(p=0.1, inplace=False) |
| 233 | ) |
| 234 | ) |
| 235 | (intermediate): RobertaIntermediate( |
| 236 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 237 | ) |
| 238 | (output): RobertaOutput( |
| 239 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 240 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 241 | (dropout): Dropout(p=0.1, inplace=False) |
| 242 | ) |
| 243 | ) |
| 244 | (10): RobertaLayer( |
| 245 | (attention): RobertaAttention( |
| 246 | (self): RobertaSelfAttention( |
| 247 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 248 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 249 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 250 | (dropout): Dropout(p=0.1, inplace=False) |
| 251 | ) |
| 252 | (output): RobertaSelfOutput( |
| 253 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 254 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 255 | (dropout): Dropout(p=0.1, inplace=False) |
| 256 | ) |
| 257 | ) |
| 258 | (intermediate): RobertaIntermediate( |
| 259 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 260 | ) |
| 261 | (output): RobertaOutput( |
| 262 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 263 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 264 | (dropout): Dropout(p=0.1, inplace=False) |
| 265 | ) |
| 266 | ) |
| 267 | (11): RobertaLayer( |
| 268 | (attention): RobertaAttention( |
| 269 | (self): RobertaSelfAttention( |
| 270 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 271 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 272 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 273 | (dropout): Dropout(p=0.1, inplace=False) |
| 274 | ) |
| 275 | (output): RobertaSelfOutput( |
| 276 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 277 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 278 | (dropout): Dropout(p=0.1, inplace=False) |
| 279 | ) |
| 280 | ) |
| 281 | (intermediate): RobertaIntermediate( |
| 282 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 283 | ) |
| 284 | (output): RobertaOutput( |
| 285 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 286 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 287 | (dropout): Dropout(p=0.1, inplace=False) |
| 288 | ) |
| 289 | ) |
| 290 | (12): RobertaLayer( |
| 291 | (attention): RobertaAttention( |
| 292 | (self): RobertaSelfAttention( |
| 293 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 294 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 295 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 296 | (dropout): Dropout(p=0.1, inplace=False) |
| 297 | ) |
| 298 | (output): RobertaSelfOutput( |
| 299 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 300 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 301 | (dropout): Dropout(p=0.1, inplace=False) |
| 302 | ) |
| 303 | ) |
| 304 | (intermediate): RobertaIntermediate( |
| 305 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 306 | ) |
| 307 | (output): RobertaOutput( |
| 308 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 309 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 310 | (dropout): Dropout(p=0.1, inplace=False) |
| 311 | ) |
| 312 | ) |
| 313 | (13): RobertaLayer( |
| 314 | (attention): RobertaAttention( |
| 315 | (self): RobertaSelfAttention( |
| 316 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 317 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 318 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 319 | (dropout): Dropout(p=0.1, inplace=False) |
| 320 | ) |
| 321 | (output): RobertaSelfOutput( |
| 322 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 323 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 324 | (dropout): Dropout(p=0.1, inplace=False) |
| 325 | ) |
| 326 | ) |
| 327 | (intermediate): RobertaIntermediate( |
| 328 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 329 | ) |
| 330 | (output): RobertaOutput( |
| 331 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 332 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 333 | (dropout): Dropout(p=0.1, inplace=False) |
| 334 | ) |
| 335 | ) |
| 336 | (14): RobertaLayer( |
| 337 | (attention): RobertaAttention( |
| 338 | (self): RobertaSelfAttention( |
| 339 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 340 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 341 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 342 | (dropout): Dropout(p=0.1, inplace=False) |
| 343 | ) |
| 344 | (output): RobertaSelfOutput( |
| 345 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 346 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 347 | (dropout): Dropout(p=0.1, inplace=False) |
| 348 | ) |
| 349 | ) |
| 350 | (intermediate): RobertaIntermediate( |
| 351 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 352 | ) |
| 353 | (output): RobertaOutput( |
| 354 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 355 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 356 | (dropout): Dropout(p=0.1, inplace=False) |
| 357 | ) |
| 358 | ) |
| 359 | (15): RobertaLayer( |
| 360 | (attention): RobertaAttention( |
| 361 | (self): RobertaSelfAttention( |
| 362 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 363 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 364 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 365 | (dropout): Dropout(p=0.1, inplace=False) |
| 366 | ) |
| 367 | (output): RobertaSelfOutput( |
| 368 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 369 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 370 | (dropout): Dropout(p=0.1, inplace=False) |
| 371 | ) |
| 372 | ) |
| 373 | (intermediate): RobertaIntermediate( |
| 374 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 375 | ) |
| 376 | (output): RobertaOutput( |
| 377 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 378 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 379 | (dropout): Dropout(p=0.1, inplace=False) |
| 380 | ) |
| 381 | ) |
| 382 | (16): RobertaLayer( |
| 383 | (attention): RobertaAttention( |
| 384 | (self): RobertaSelfAttention( |
| 385 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 386 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 387 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 388 | (dropout): Dropout(p=0.1, inplace=False) |
| 389 | ) |
| 390 | (output): RobertaSelfOutput( |
| 391 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 392 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 393 | (dropout): Dropout(p=0.1, inplace=False) |
| 394 | ) |
| 395 | ) |
| 396 | (intermediate): RobertaIntermediate( |
| 397 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 398 | ) |
| 399 | (output): RobertaOutput( |
| 400 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 401 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 402 | (dropout): Dropout(p=0.1, inplace=False) |
| 403 | ) |
| 404 | ) |
| 405 | (17): RobertaLayer( |
| 406 | (attention): RobertaAttention( |
| 407 | (self): RobertaSelfAttention( |
| 408 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 409 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 410 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 411 | (dropout): Dropout(p=0.1, inplace=False) |
| 412 | ) |
| 413 | (output): RobertaSelfOutput( |
| 414 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 415 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 416 | (dropout): Dropout(p=0.1, inplace=False) |
| 417 | ) |
| 418 | ) |
| 419 | (intermediate): RobertaIntermediate( |
| 420 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 421 | ) |
| 422 | (output): RobertaOutput( |
| 423 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 424 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 425 | (dropout): Dropout(p=0.1, inplace=False) |
| 426 | ) |
| 427 | ) |
| 428 | (18): RobertaLayer( |
| 429 | (attention): RobertaAttention( |
| 430 | (self): RobertaSelfAttention( |
| 431 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 432 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 433 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 434 | (dropout): Dropout(p=0.1, inplace=False) |
| 435 | ) |
| 436 | (output): RobertaSelfOutput( |
| 437 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 438 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 439 | (dropout): Dropout(p=0.1, inplace=False) |
| 440 | ) |
| 441 | ) |
| 442 | (intermediate): RobertaIntermediate( |
| 443 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 444 | ) |
| 445 | (output): RobertaOutput( |
| 446 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 447 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 448 | (dropout): Dropout(p=0.1, inplace=False) |
| 449 | ) |
| 450 | ) |
| 451 | (19): RobertaLayer( |
| 452 | (attention): RobertaAttention( |
| 453 | (self): RobertaSelfAttention( |
| 454 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 455 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 456 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 457 | (dropout): Dropout(p=0.1, inplace=False) |
| 458 | ) |
| 459 | (output): RobertaSelfOutput( |
| 460 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 461 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 462 | (dropout): Dropout(p=0.1, inplace=False) |
| 463 | ) |
| 464 | ) |
| 465 | (intermediate): RobertaIntermediate( |
| 466 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 467 | ) |
| 468 | (output): RobertaOutput( |
| 469 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 470 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 471 | (dropout): Dropout(p=0.1, inplace=False) |
| 472 | ) |
| 473 | ) |
| 474 | (20): RobertaLayer( |
| 475 | (attention): RobertaAttention( |
| 476 | (self): RobertaSelfAttention( |
| 477 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 478 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 479 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 480 | (dropout): Dropout(p=0.1, inplace=False) |
| 481 | ) |
| 482 | (output): RobertaSelfOutput( |
| 483 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 484 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 485 | (dropout): Dropout(p=0.1, inplace=False) |
| 486 | ) |
| 487 | ) |
| 488 | (intermediate): RobertaIntermediate( |
| 489 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 490 | ) |
| 491 | (output): RobertaOutput( |
| 492 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 493 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 494 | (dropout): Dropout(p=0.1, inplace=False) |
| 495 | ) |
| 496 | ) |
| 497 | (21): RobertaLayer( |
| 498 | (attention): RobertaAttention( |
| 499 | (self): RobertaSelfAttention( |
| 500 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 501 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 502 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 503 | (dropout): Dropout(p=0.1, inplace=False) |
| 504 | ) |
| 505 | (output): RobertaSelfOutput( |
| 506 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 507 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 508 | (dropout): Dropout(p=0.1, inplace=False) |
| 509 | ) |
| 510 | ) |
| 511 | (intermediate): RobertaIntermediate( |
| 512 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 513 | ) |
| 514 | (output): RobertaOutput( |
| 515 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 516 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 517 | (dropout): Dropout(p=0.1, inplace=False) |
| 518 | ) |
| 519 | ) |
| 520 | (22): RobertaLayer( |
| 521 | (attention): RobertaAttention( |
| 522 | (self): RobertaSelfAttention( |
| 523 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 524 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 525 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 526 | (dropout): Dropout(p=0.1, inplace=False) |
| 527 | ) |
| 528 | (output): RobertaSelfOutput( |
| 529 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 530 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 531 | (dropout): Dropout(p=0.1, inplace=False) |
| 532 | ) |
| 533 | ) |
| 534 | (intermediate): RobertaIntermediate( |
| 535 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 536 | ) |
| 537 | (output): RobertaOutput( |
| 538 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 539 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 540 | (dropout): Dropout(p=0.1, inplace=False) |
| 541 | ) |
| 542 | ) |
| 543 | (23): RobertaLayer( |
| 544 | (attention): RobertaAttention( |
| 545 | (self): RobertaSelfAttention( |
| 546 | (query): Linear(in_features=1024, out_features=1024, bias=True) |
| 547 | (key): Linear(in_features=1024, out_features=1024, bias=True) |
| 548 | (value): Linear(in_features=1024, out_features=1024, bias=True) |
| 549 | (dropout): Dropout(p=0.1, inplace=False) |
| 550 | ) |
| 551 | (output): RobertaSelfOutput( |
| 552 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 553 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 554 | (dropout): Dropout(p=0.1, inplace=False) |
| 555 | ) |
| 556 | ) |
| 557 | (intermediate): RobertaIntermediate( |
| 558 | (dense): Linear(in_features=1024, out_features=4096, bias=True) |
| 559 | ) |
| 560 | (output): RobertaOutput( |
| 561 | (dense): Linear(in_features=4096, out_features=1024, bias=True) |
| 562 | (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True) |
| 563 | (dropout): Dropout(p=0.1, inplace=False) |
| 564 | ) |
| 565 | ) |
| 566 | ) |
| 567 | ) |
| 568 | (pooler): RobertaPooler( |
| 569 | (dense): Linear(in_features=1024, out_features=1024, bias=True) |
| 570 | (activation): Tanh() |
| 571 | ) |
| 572 | ) |
| 573 | ) |
| 574 | (word_dropout): WordDropout(p=0.05) |
| 575 | (locked_dropout): LockedDropout(p=0.5) |
| 576 | (linear): Linear(in_features=1024, out_features=20, bias=True) |
| 577 | (beta): 1.0 |
| 578 | (weights): None |
| 579 | (weight_tensor) None |
| 580 | )" |
| 581 | 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- |
| 582 | 2021-01-15 16:27:19,928 Corpus: "Corpus: 12705 train + 3068 dev + 3160 test sentences" |
| 583 | 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- |
| 584 | 2021-01-15 16:27:19,928 Parameters: |
| 585 | 2021-01-15 16:27:19,928 - learning_rate: "5e-06" |
| 586 | 2021-01-15 16:27:19,928 - mini_batch_size: "4" |
| 587 | 2021-01-15 16:27:19,928 - patience: "3" |
| 588 | 2021-01-15 16:27:19,928 - anneal_factor: "0.5" |
| 589 | 2021-01-15 16:27:19,928 - max_epochs: "20" |
| 590 | 2021-01-15 16:27:19,928 - shuffle: "True" |
| 591 | 2021-01-15 16:27:19,928 - train_with_dev: "True" |
| 592 | 2021-01-15 16:27:19,928 - batch_growth_annealing: "False" |
| 593 | 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- |
| 594 | 2021-01-15 16:27:19,928 Model training base path: "resources/contextdrop/flert-de-ft+dev-xlm-roberta-large-context+drop-64-True-42" |
| 595 | 2021-01-15 16:27:19,928 ---------------------------------------------------------------------------------------------------- |
| 596 | 2021-01-15 16:27:19,929 Device: cuda:2 |
| 597 | 2021-01-15 16:27:19,929 ---------------------------------------------------------------------------------------------------- |
| 598 | 2021-01-15 16:27:19,929 Embeddings storage mode: none |
| 599 | 2021-01-15 16:27:19,939 ---------------------------------------------------------------------------------------------------- |
| 600 | 2021-01-15 16:29:48,177 epoch 1 - iter 394/3944 - loss 0.58149384 - samples/sec: 10.63 - lr: 0.000005 |
| 601 | 2021-01-15 16:32:16,470 epoch 1 - iter 788/3944 - loss 0.43146001 - samples/sec: 10.63 - lr: 0.000005 |
| 602 | 2021-01-15 16:34:43,836 epoch 1 - iter 1182/3944 - loss 0.38010955 - samples/sec: 10.70 - lr: 0.000005 |
| 603 | 2021-01-15 16:37:11,698 epoch 1 - iter 1576/3944 - loss 0.34431028 - samples/sec: 10.66 - lr: 0.000005 |
| 604 | 2021-01-15 16:39:39,747 epoch 1 - iter 1970/3944 - loss 0.32744939 - samples/sec: 10.65 - lr: 0.000005 |
| 605 | 2021-01-15 16:42:07,631 epoch 1 - iter 2364/3944 - loss 0.31857823 - samples/sec: 10.66 - lr: 0.000005 |
| 606 | 2021-01-15 16:44:34,485 epoch 1 - iter 2758/3944 - loss 0.30456838 - samples/sec: 10.73 - lr: 0.000005 |
| 607 | 2021-01-15 16:47:02,394 epoch 1 - iter 3152/3944 - loss 0.29905511 - samples/sec: 10.66 - lr: 0.000005 |
| 608 | 2021-01-15 16:49:29,868 epoch 1 - iter 3546/3944 - loss 0.29295683 - samples/sec: 10.69 - lr: 0.000005 |
| 609 | 2021-01-15 16:51:58,152 epoch 1 - iter 3940/3944 - loss 0.28678117 - samples/sec: 10.63 - lr: 0.000005 |
| 610 | 2021-01-15 16:51:59,459 ---------------------------------------------------------------------------------------------------- |
| 611 | 2021-01-15 16:51:59,459 EPOCH 1 done: loss 0.2866 - lr 0.0000050 |
| 612 | 2021-01-15 16:51:59,459 BAD EPOCHS (no improvement): 4 |
| 613 | 2021-01-15 16:51:59,462 ---------------------------------------------------------------------------------------------------- |
| 614 | 2021-01-15 16:54:27,337 epoch 2 - iter 394/3944 - loss 0.23763366 - samples/sec: 10.66 - lr: 0.000005 |
| 615 | 2021-01-15 16:56:55,082 epoch 2 - iter 788/3944 - loss 0.20691177 - samples/sec: 10.67 - lr: 0.000005 |
| 616 | 2021-01-15 16:59:22,869 epoch 2 - iter 1182/3944 - loss 0.21072023 - samples/sec: 10.66 - lr: 0.000005 |
| 617 | 2021-01-15 17:01:50,770 epoch 2 - iter 1576/3944 - loss 0.20705774 - samples/sec: 10.66 - lr: 0.000005 |
| 618 | 2021-01-15 17:04:18,029 epoch 2 - iter 1970/3944 - loss 0.20345128 - samples/sec: 10.70 - lr: 0.000005 |
| 619 | 2021-01-15 17:06:45,050 epoch 2 - iter 2364/3944 - loss 0.19762390 - samples/sec: 10.72 - lr: 0.000005 |
| 620 | 2021-01-15 17:09:11,995 epoch 2 - iter 2758/3944 - loss 0.20206661 - samples/sec: 10.73 - lr: 0.000005 |
| 621 | 2021-01-15 17:11:39,892 epoch 2 - iter 3152/3944 - loss 0.19768991 - samples/sec: 10.66 - lr: 0.000005 |
| 622 | 2021-01-15 17:14:07,315 epoch 2 - iter 3546/3944 - loss 0.20115805 - samples/sec: 10.69 - lr: 0.000005 |
| 623 | 2021-01-15 17:16:34,784 epoch 2 - iter 3940/3944 - loss 0.19983876 - samples/sec: 10.69 - lr: 0.000005 |
| 624 | 2021-01-15 17:16:36,073 ---------------------------------------------------------------------------------------------------- |
| 625 | 2021-01-15 17:16:36,074 EPOCH 2 done: loss 0.1996 - lr 0.0000049 |
| 626 | 2021-01-15 17:16:36,074 BAD EPOCHS (no improvement): 4 |
| 627 | 2021-01-15 17:16:36,077 ---------------------------------------------------------------------------------------------------- |
| 628 | 2021-01-15 17:19:03,268 epoch 3 - iter 394/3944 - loss 0.16475767 - samples/sec: 10.71 - lr: 0.000005 |
| 629 | 2021-01-15 17:21:30,430 epoch 3 - iter 788/3944 - loss 0.16467943 - samples/sec: 10.71 - lr: 0.000005 |
| 630 | 2021-01-15 17:23:57,785 epoch 3 - iter 1182/3944 - loss 0.16820842 - samples/sec: 10.70 - lr: 0.000005 |
| 631 | 2021-01-15 17:26:25,077 epoch 3 - iter 1576/3944 - loss 0.17111347 - samples/sec: 10.70 - lr: 0.000005 |
| 632 | 2021-01-15 17:28:51,818 epoch 3 - iter 1970/3944 - loss 0.17649180 - samples/sec: 10.74 - lr: 0.000005 |
| 633 | 2021-01-15 17:31:18,679 epoch 3 - iter 2364/3944 - loss 0.18734800 - samples/sec: 10.73 - lr: 0.000005 |
| 634 | 2021-01-15 17:33:45,680 epoch 3 - iter 2758/3944 - loss 0.18971106 - samples/sec: 10.72 - lr: 0.000005 |
| 635 | 2021-01-15 17:36:13,246 epoch 3 - iter 3152/3944 - loss 0.18746164 - samples/sec: 10.68 - lr: 0.000005 |
| 636 | 2021-01-15 17:38:40,672 epoch 3 - iter 3546/3944 - loss 0.19218287 - samples/sec: 10.69 - lr: 0.000005 |
| 637 | 2021-01-15 17:41:07,957 epoch 3 - iter 3940/3944 - loss 0.19381799 - samples/sec: 10.70 - lr: 0.000005 |
| 638 | 2021-01-15 17:41:09,257 ---------------------------------------------------------------------------------------------------- |
| 639 | 2021-01-15 17:41:09,257 EPOCH 3 done: loss 0.1938 - lr 0.0000047 |
| 640 | 2021-01-15 17:41:09,257 BAD EPOCHS (no improvement): 4 |
| 641 | 2021-01-15 17:41:09,260 ---------------------------------------------------------------------------------------------------- |
| 642 | 2021-01-15 17:43:36,593 epoch 4 - iter 394/3944 - loss 0.16488209 - samples/sec: 10.70 - lr: 0.000005 |
| 643 | 2021-01-15 17:46:04,133 epoch 4 - iter 788/3944 - loss 0.17473605 - samples/sec: 10.68 - lr: 0.000005 |
| 644 | 2021-01-15 17:48:31,440 epoch 4 - iter 1182/3944 - loss 0.16738039 - samples/sec: 10.70 - lr: 0.000005 |
| 645 | 2021-01-15 17:50:58,858 epoch 4 - iter 1576/3944 - loss 0.16596805 - samples/sec: 10.69 - lr: 0.000005 |
| 646 | 2021-01-15 17:53:26,260 epoch 4 - iter 1970/3944 - loss 0.16483490 - samples/sec: 10.69 - lr: 0.000005 |
| 647 | 2021-01-15 17:55:53,072 epoch 4 - iter 2364/3944 - loss 0.16752558 - samples/sec: 10.74 - lr: 0.000005 |
| 648 | 2021-01-15 17:58:19,944 epoch 4 - iter 2758/3944 - loss 0.16537132 - samples/sec: 10.73 - lr: 0.000005 |
| 649 | 2021-01-15 18:00:47,459 epoch 4 - iter 3152/3944 - loss 0.16501133 - samples/sec: 10.68 - lr: 0.000005 |
| 650 | 2021-01-15 18:03:15,474 epoch 4 - iter 3546/3944 - loss 0.16726116 - samples/sec: 10.65 - lr: 0.000005 |
| 651 | 2021-01-15 18:05:43,265 epoch 4 - iter 3940/3944 - loss 0.16914137 - samples/sec: 10.66 - lr: 0.000005 |
| 652 | 2021-01-15 18:05:44,543 ---------------------------------------------------------------------------------------------------- |
| 653 | 2021-01-15 18:05:44,543 EPOCH 4 done: loss 0.1690 - lr 0.0000045 |
| 654 | 2021-01-15 18:05:44,543 BAD EPOCHS (no improvement): 4 |
| 655 | 2021-01-15 18:05:44,547 ---------------------------------------------------------------------------------------------------- |
| 656 | 2021-01-15 18:08:12,011 epoch 5 - iter 394/3944 - loss 0.15833616 - samples/sec: 10.69 - lr: 0.000004 |
| 657 | 2021-01-15 18:10:38,832 epoch 5 - iter 788/3944 - loss 0.16551527 - samples/sec: 10.74 - lr: 0.000004 |
| 658 | 2021-01-15 18:13:06,451 epoch 5 - iter 1182/3944 - loss 0.17177677 - samples/sec: 10.68 - lr: 0.000004 |
| 659 | 2021-01-15 18:15:34,493 epoch 5 - iter 1576/3944 - loss 0.17301128 - samples/sec: 10.65 - lr: 0.000004 |
| 660 | 2021-01-15 18:18:03,239 epoch 5 - iter 1970/3944 - loss 0.17650116 - samples/sec: 10.60 - lr: 0.000004 |
| 661 | 2021-01-15 18:20:32,247 epoch 5 - iter 2364/3944 - loss 0.17631064 - samples/sec: 10.58 - lr: 0.000004 |
| 662 | 2021-01-15 18:22:59,227 epoch 5 - iter 2758/3944 - loss 0.17537379 - samples/sec: 10.72 - lr: 0.000004 |
| 663 | 2021-01-15 18:25:24,556 epoch 5 - iter 3152/3944 - loss 0.17617518 - samples/sec: 10.85 - lr: 0.000004 |
| 664 | 2021-01-15 18:27:50,096 epoch 5 - iter 3546/3944 - loss 0.17367857 - samples/sec: 10.83 - lr: 0.000004 |
| 665 | 2021-01-15 18:30:16,704 epoch 5 - iter 3940/3944 - loss 0.17093901 - samples/sec: 10.75 - lr: 0.000004 |
| 666 | 2021-01-15 18:30:18,004 ---------------------------------------------------------------------------------------------------- |
| 667 | 2021-01-15 18:30:18,004 EPOCH 5 done: loss 0.1708 - lr 0.0000043 |
| 668 | 2021-01-15 18:30:18,004 BAD EPOCHS (no improvement): 4 |
| 669 | 2021-01-15 18:30:18,007 ---------------------------------------------------------------------------------------------------- |
| 670 | 2021-01-15 18:32:42,968 epoch 6 - iter 394/3944 - loss 0.17698825 - samples/sec: 10.87 - lr: 0.000004 |
| 671 | 2021-01-15 18:35:08,371 epoch 6 - iter 788/3944 - loss 0.16713416 - samples/sec: 10.84 - lr: 0.000004 |
| 672 | 2021-01-15 18:37:34,014 epoch 6 - iter 1182/3944 - loss 0.16902562 - samples/sec: 10.82 - lr: 0.000004 |
| 673 | 2021-01-15 18:40:00,144 epoch 6 - iter 1576/3944 - loss 0.16574844 - samples/sec: 10.79 - lr: 0.000004 |
| 674 | 2021-01-15 18:42:26,534 epoch 6 - iter 1970/3944 - loss 0.16657012 - samples/sec: 10.77 - lr: 0.000004 |
| 675 | 2021-01-15 18:44:52,613 epoch 6 - iter 2364/3944 - loss 0.16641916 - samples/sec: 10.79 - lr: 0.000004 |
| 676 | 2021-01-15 18:47:17,983 epoch 6 - iter 2758/3944 - loss 0.16274268 - samples/sec: 10.84 - lr: 0.000004 |
| 677 | 2021-01-15 18:49:43,878 epoch 6 - iter 3152/3944 - loss 0.16172776 - samples/sec: 10.80 - lr: 0.000004 |
| 678 | 2021-01-15 18:52:09,331 epoch 6 - iter 3546/3944 - loss 0.16291188 - samples/sec: 10.84 - lr: 0.000004 |
| 679 | 2021-01-15 18:54:34,272 epoch 6 - iter 3940/3944 - loss 0.16208591 - samples/sec: 10.87 - lr: 0.000004 |
| 680 | 2021-01-15 18:54:35,553 ---------------------------------------------------------------------------------------------------- |
| 681 | 2021-01-15 18:54:35,553 EPOCH 6 done: loss 0.1621 - lr 0.0000040 |
| 682 | 2021-01-15 18:54:35,553 BAD EPOCHS (no improvement): 4 |
| 683 | 2021-01-15 18:54:35,556 ---------------------------------------------------------------------------------------------------- |
| 684 | 2021-01-15 18:57:00,031 epoch 7 - iter 394/3944 - loss 0.15674837 - samples/sec: 10.91 - lr: 0.000004 |
| 685 | 2021-01-15 18:59:25,217 epoch 7 - iter 788/3944 - loss 0.16222971 - samples/sec: 10.86 - lr: 0.000004 |
| 686 | 2021-01-15 19:01:50,483 epoch 7 - iter 1182/3944 - loss 0.17608659 - samples/sec: 10.85 - lr: 0.000004 |
| 687 | 2021-01-15 19:04:15,644 epoch 7 - iter 1576/3944 - loss 0.17042676 - samples/sec: 10.86 - lr: 0.000004 |
| 688 | 2021-01-15 19:06:40,626 epoch 7 - iter 1970/3944 - loss 0.16835536 - samples/sec: 10.87 - lr: 0.000004 |
| 689 | 2021-01-15 19:09:06,269 epoch 7 - iter 2364/3944 - loss 0.17005717 - samples/sec: 10.82 - lr: 0.000004 |
| 690 | 2021-01-15 19:11:30,455 epoch 7 - iter 2758/3944 - loss 0.16986731 - samples/sec: 10.93 - lr: 0.000004 |
| 691 | 2021-01-15 19:13:55,363 epoch 7 - iter 3152/3944 - loss 0.16607768 - samples/sec: 10.88 - lr: 0.000004 |
| 692 | 2021-01-15 19:16:20,669 epoch 7 - iter 3546/3944 - loss 0.16408475 - samples/sec: 10.85 - lr: 0.000004 |
| 693 | 2021-01-15 19:18:46,350 epoch 7 - iter 3940/3944 - loss 0.16187247 - samples/sec: 10.82 - lr: 0.000004 |
| 694 | 2021-01-15 19:18:47,632 ---------------------------------------------------------------------------------------------------- |
| 695 | 2021-01-15 19:18:47,632 EPOCH 7 done: loss 0.1619 - lr 0.0000036 |
| 696 | 2021-01-15 19:18:47,632 BAD EPOCHS (no improvement): 4 |
| 697 | 2021-01-15 19:18:47,635 ---------------------------------------------------------------------------------------------------- |
| 698 | 2021-01-15 19:21:13,232 epoch 8 - iter 394/3944 - loss 0.15860862 - samples/sec: 10.83 - lr: 0.000004 |
| 699 | 2021-01-15 19:23:37,769 epoch 8 - iter 788/3944 - loss 0.16488914 - samples/sec: 10.90 - lr: 0.000004 |
| 700 | 2021-01-15 19:26:03,243 epoch 8 - iter 1182/3944 - loss 0.16503533 - samples/sec: 10.83 - lr: 0.000004 |
| 701 | 2021-01-15 19:28:28,171 epoch 8 - iter 1576/3944 - loss 0.16139434 - samples/sec: 10.88 - lr: 0.000003 |
| 702 | 2021-01-15 19:30:53,669 epoch 8 - iter 1970/3944 - loss 0.15723985 - samples/sec: 10.83 - lr: 0.000003 |
| 703 | 2021-01-15 19:33:18,230 epoch 8 - iter 2364/3944 - loss 0.15695920 - samples/sec: 10.90 - lr: 0.000003 |
| 704 | 2021-01-15 19:35:43,271 epoch 8 - iter 2758/3944 - loss 0.15942351 - samples/sec: 10.87 - lr: 0.000003 |
| 705 | 2021-01-15 19:38:07,861 epoch 8 - iter 3152/3944 - loss 0.16047035 - samples/sec: 10.90 - lr: 0.000003 |
| 706 | 2021-01-15 19:40:31,578 epoch 8 - iter 3546/3944 - loss 0.15915561 - samples/sec: 10.97 - lr: 0.000003 |
| 707 | 2021-01-15 19:42:56,291 epoch 8 - iter 3940/3944 - loss 0.15889894 - samples/sec: 10.89 - lr: 0.000003 |
| 708 | 2021-01-15 19:42:57,531 ---------------------------------------------------------------------------------------------------- |
| 709 | 2021-01-15 19:42:57,531 EPOCH 8 done: loss 0.1591 - lr 0.0000033 |
| 710 | 2021-01-15 19:42:57,531 BAD EPOCHS (no improvement): 4 |
| 711 | 2021-01-15 19:42:57,534 ---------------------------------------------------------------------------------------------------- |
| 712 | 2021-01-15 19:45:22,077 epoch 9 - iter 394/3944 - loss 0.15628960 - samples/sec: 10.90 - lr: 0.000003 |
| 713 | 2021-01-15 19:47:46,787 epoch 9 - iter 788/3944 - loss 0.15383703 - samples/sec: 10.89 - lr: 0.000003 |
| 714 | 2021-01-15 19:50:11,703 epoch 9 - iter 1182/3944 - loss 0.14587839 - samples/sec: 10.88 - lr: 0.000003 |
| 715 | 2021-01-15 19:52:36,604 epoch 9 - iter 1576/3944 - loss 0.14536078 - samples/sec: 10.88 - lr: 0.000003 |
| 716 | 2021-01-15 19:55:01,857 epoch 9 - iter 1970/3944 - loss 0.14842223 - samples/sec: 10.85 - lr: 0.000003 |
| 717 | 2021-01-15 19:57:26,976 epoch 9 - iter 2364/3944 - loss 0.14781136 - samples/sec: 10.86 - lr: 0.000003 |
| 718 | 2021-01-15 19:59:52,570 epoch 9 - iter 2758/3944 - loss 0.14980740 - samples/sec: 10.83 - lr: 0.000003 |
| 719 | 2021-01-15 20:02:16,766 epoch 9 - iter 3152/3944 - loss 0.15147019 - samples/sec: 10.93 - lr: 0.000003 |
| 720 | 2021-01-15 20:04:41,587 epoch 9 - iter 3546/3944 - loss 0.14992780 - samples/sec: 10.88 - lr: 0.000003 |
| 721 | 2021-01-15 20:07:07,065 epoch 9 - iter 3940/3944 - loss 0.14688711 - samples/sec: 10.83 - lr: 0.000003 |
| 722 | 2021-01-15 20:07:08,315 ---------------------------------------------------------------------------------------------------- |
| 723 | 2021-01-15 20:07:08,315 EPOCH 9 done: loss 0.1469 - lr 0.0000029 |
| 724 | 2021-01-15 20:07:08,315 BAD EPOCHS (no improvement): 4 |
| 725 | 2021-01-15 20:07:08,318 ---------------------------------------------------------------------------------------------------- |
| 726 | 2021-01-15 20:09:33,307 epoch 10 - iter 394/3944 - loss 0.15646665 - samples/sec: 10.87 - lr: 0.000003 |
| 727 | 2021-01-15 20:11:57,958 epoch 10 - iter 788/3944 - loss 0.15117971 - samples/sec: 10.90 - lr: 0.000003 |
| 728 | 2021-01-15 20:14:23,257 epoch 10 - iter 1182/3944 - loss 0.15319049 - samples/sec: 10.85 - lr: 0.000003 |
| 729 | 2021-01-15 20:16:47,405 epoch 10 - iter 1576/3944 - loss 0.14632406 - samples/sec: 10.93 - lr: 0.000003 |
| 730 | 2021-01-15 20:19:13,077 epoch 10 - iter 1970/3944 - loss 0.14880268 - samples/sec: 10.82 - lr: 0.000003 |
| 731 | 2021-01-15 20:21:37,974 epoch 10 - iter 2364/3944 - loss 0.14738769 - samples/sec: 10.88 - lr: 0.000003 |
| 732 | 2021-01-15 20:24:02,312 epoch 10 - iter 2758/3944 - loss 0.14992138 - samples/sec: 10.92 - lr: 0.000003 |
| 733 | 2021-01-15 20:26:26,416 epoch 10 - iter 3152/3944 - loss 0.14923992 - samples/sec: 10.94 - lr: 0.000003 |
| 734 | 2021-01-15 20:28:50,624 epoch 10 - iter 3546/3944 - loss 0.14988541 - samples/sec: 10.93 - lr: 0.000003 |
| 735 | 2021-01-15 20:31:15,232 epoch 10 - iter 3940/3944 - loss 0.14923823 - samples/sec: 10.90 - lr: 0.000003 |
| 736 | 2021-01-15 20:31:16,444 ---------------------------------------------------------------------------------------------------- |
| 737 | 2021-01-15 20:31:16,445 EPOCH 10 done: loss 0.1492 - lr 0.0000025 |
| 738 | 2021-01-15 20:31:16,445 BAD EPOCHS (no improvement): 4 |
| 739 | 2021-01-15 20:31:16,447 ---------------------------------------------------------------------------------------------------- |
| 740 | 2021-01-15 20:33:41,402 epoch 11 - iter 394/3944 - loss 0.16146740 - samples/sec: 10.87 - lr: 0.000002 |
| 741 | 2021-01-15 20:36:05,837 epoch 11 - iter 788/3944 - loss 0.16349808 - samples/sec: 10.91 - lr: 0.000002 |
| 742 | 2021-01-15 20:38:30,901 epoch 11 - iter 1182/3944 - loss 0.15115769 - samples/sec: 10.87 - lr: 0.000002 |
| 743 | 2021-01-15 20:40:55,438 epoch 11 - iter 1576/3944 - loss 0.14705117 - samples/sec: 10.90 - lr: 0.000002 |
| 744 | 2021-01-15 20:43:20,378 epoch 11 - iter 1970/3944 - loss 0.14991591 - samples/sec: 10.87 - lr: 0.000002 |
| 745 | 2021-01-15 20:45:45,151 epoch 11 - iter 2364/3944 - loss 0.15439655 - samples/sec: 10.89 - lr: 0.000002 |
| 746 | 2021-01-15 20:48:09,941 epoch 11 - iter 2758/3944 - loss 0.15580945 - samples/sec: 10.89 - lr: 0.000002 |
| 747 | 2021-01-15 20:50:34,492 epoch 11 - iter 3152/3944 - loss 0.15253824 - samples/sec: 10.90 - lr: 0.000002 |
| 748 | 2021-01-15 20:52:58,700 epoch 11 - iter 3546/3944 - loss 0.15092320 - samples/sec: 10.93 - lr: 0.000002 |
| 749 | 2021-01-15 20:55:23,174 epoch 11 - iter 3940/3944 - loss 0.15157769 - samples/sec: 10.91 - lr: 0.000002 |
| 750 | 2021-01-15 20:55:24,418 ---------------------------------------------------------------------------------------------------- |
| 751 | 2021-01-15 20:55:24,418 EPOCH 11 done: loss 0.1515 - lr 0.0000021 |
| 752 | 2021-01-15 20:55:24,418 BAD EPOCHS (no improvement): 4 |
| 753 | 2021-01-15 20:55:24,421 ---------------------------------------------------------------------------------------------------- |
| 754 | 2021-01-15 20:57:49,024 epoch 12 - iter 394/3944 - loss 0.13353775 - samples/sec: 10.90 - lr: 0.000002 |
| 755 | 2021-01-15 21:00:13,363 epoch 12 - iter 788/3944 - loss 0.12481125 - samples/sec: 10.92 - lr: 0.000002 |
| 756 | 2021-01-15 21:02:37,921 epoch 12 - iter 1182/3944 - loss 0.13012621 - samples/sec: 10.90 - lr: 0.000002 |
| 757 | 2021-01-15 21:05:02,587 epoch 12 - iter 1576/3944 - loss 0.13179293 - samples/sec: 10.90 - lr: 0.000002 |
| 758 | 2021-01-15 21:07:27,496 epoch 12 - iter 1970/3944 - loss 0.13504151 - samples/sec: 10.88 - lr: 0.000002 |
| 759 | 2021-01-15 21:09:52,384 epoch 12 - iter 2364/3944 - loss 0.13639646 - samples/sec: 10.88 - lr: 0.000002 |
| 760 | 2021-01-15 21:12:16,819 epoch 12 - iter 2758/3944 - loss 0.13538659 - samples/sec: 10.91 - lr: 0.000002 |
| 761 | 2021-01-15 21:14:41,429 epoch 12 - iter 3152/3944 - loss 0.13401163 - samples/sec: 10.90 - lr: 0.000002 |
| 762 | 2021-01-15 21:17:06,129 epoch 12 - iter 3546/3944 - loss 0.13558124 - samples/sec: 10.89 - lr: 0.000002 |
| 763 | 2021-01-15 21:19:30,783 epoch 12 - iter 3940/3944 - loss 0.13632296 - samples/sec: 10.90 - lr: 0.000002 |
| 764 | 2021-01-15 21:19:32,074 ---------------------------------------------------------------------------------------------------- |
| 765 | 2021-01-15 21:19:32,075 EPOCH 12 done: loss 0.1365 - lr 0.0000017 |
| 766 | 2021-01-15 21:19:32,075 BAD EPOCHS (no improvement): 4 |
| 767 | 2021-01-15 21:19:32,086 ---------------------------------------------------------------------------------------------------- |
| 768 | 2021-01-15 21:21:56,456 epoch 13 - iter 394/3944 - loss 0.13665988 - samples/sec: 10.92 - lr: 0.000002 |
| 769 | 2021-01-15 21:24:21,213 epoch 13 - iter 788/3944 - loss 0.13434678 - samples/sec: 10.89 - lr: 0.000002 |
| 770 | 2021-01-15 21:26:45,716 epoch 13 - iter 1182/3944 - loss 0.14362465 - samples/sec: 10.91 - lr: 0.000002 |
| 771 | 2021-01-15 21:29:10,027 epoch 13 - iter 1576/3944 - loss 0.14463862 - samples/sec: 10.92 - lr: 0.000002 |
| 772 | 2021-01-15 21:31:35,804 epoch 13 - iter 1970/3944 - loss 0.14445941 - samples/sec: 10.81 - lr: 0.000002 |
| 773 | 2021-01-15 21:34:02,830 epoch 13 - iter 2364/3944 - loss 0.14383136 - samples/sec: 10.72 - lr: 0.000002 |
| 774 | 2021-01-15 21:36:29,998 epoch 13 - iter 2758/3944 - loss 0.14458719 - samples/sec: 10.71 - lr: 0.000001 |
| 775 | 2021-01-15 21:38:58,765 epoch 13 - iter 3152/3944 - loss 0.14583862 - samples/sec: 10.59 - lr: 0.000001 |
| 776 | 2021-01-15 21:41:27,066 epoch 13 - iter 3546/3944 - loss 0.14570568 - samples/sec: 10.63 - lr: 0.000001 |
| 777 | 2021-01-15 21:43:53,640 epoch 13 - iter 3940/3944 - loss 0.14616666 - samples/sec: 10.75 - lr: 0.000001 |
| 778 | 2021-01-15 21:43:54,933 ---------------------------------------------------------------------------------------------------- |
| 779 | 2021-01-15 21:43:54,933 EPOCH 13 done: loss 0.1461 - lr 0.0000014 |
| 780 | 2021-01-15 21:43:54,933 BAD EPOCHS (no improvement): 4 |
| 781 | 2021-01-15 21:43:54,953 ---------------------------------------------------------------------------------------------------- |
| 782 | 2021-01-15 21:46:22,842 epoch 14 - iter 394/3944 - loss 0.12543846 - samples/sec: 10.66 - lr: 0.000001 |
| 783 | 2021-01-15 21:48:49,756 epoch 14 - iter 788/3944 - loss 0.12854973 - samples/sec: 10.73 - lr: 0.000001 |
| 784 | 2021-01-15 21:51:16,782 epoch 14 - iter 1182/3944 - loss 0.12800828 - samples/sec: 10.72 - lr: 0.000001 |
| 785 | 2021-01-15 21:53:43,875 epoch 14 - iter 1576/3944 - loss 0.13018865 - samples/sec: 10.72 - lr: 0.000001 |
| 786 | 2021-01-15 21:56:11,947 epoch 14 - iter 1970/3944 - loss 0.13230140 - samples/sec: 10.64 - lr: 0.000001 |
| 787 | 2021-01-15 21:58:40,070 epoch 14 - iter 2364/3944 - loss 0.13276864 - samples/sec: 10.64 - lr: 0.000001 |
| 788 | 2021-01-15 22:01:07,197 epoch 14 - iter 2758/3944 - loss 0.13188423 - samples/sec: 10.71 - lr: 0.000001 |
| 789 | 2021-01-15 22:03:33,892 epoch 14 - iter 3152/3944 - loss 0.13622326 - samples/sec: 10.74 - lr: 0.000001 |
| 790 | 2021-01-15 22:06:01,226 epoch 14 - iter 3546/3944 - loss 0.13623591 - samples/sec: 10.70 - lr: 0.000001 |
| 791 | 2021-01-15 22:08:29,247 epoch 14 - iter 3940/3944 - loss 0.13681664 - samples/sec: 10.65 - lr: 0.000001 |
| 792 | 2021-01-15 22:08:30,571 ---------------------------------------------------------------------------------------------------- |
| 793 | 2021-01-15 22:08:30,571 EPOCH 14 done: loss 0.1367 - lr 0.0000010 |
| 794 | 2021-01-15 22:08:30,571 BAD EPOCHS (no improvement): 4 |
| 795 | 2021-01-15 22:08:30,619 ---------------------------------------------------------------------------------------------------- |
| 796 | 2021-01-15 22:10:58,784 epoch 15 - iter 394/3944 - loss 0.14687040 - samples/sec: 10.64 - lr: 0.000001 |
| 797 | 2021-01-15 22:13:25,824 epoch 15 - iter 788/3944 - loss 0.13773561 - samples/sec: 10.72 - lr: 0.000001 |
| 798 | 2021-01-15 22:15:52,774 epoch 15 - iter 1182/3944 - loss 0.13724811 - samples/sec: 10.73 - lr: 0.000001 |
| 799 | 2021-01-15 22:18:19,309 epoch 15 - iter 1576/3944 - loss 0.14105250 - samples/sec: 10.76 - lr: 0.000001 |
| 800 | 2021-01-15 22:20:46,418 epoch 15 - iter 1970/3944 - loss 0.13929364 - samples/sec: 10.71 - lr: 0.000001 |
| 801 | 2021-01-15 22:23:12,930 epoch 15 - iter 2364/3944 - loss 0.13891907 - samples/sec: 10.76 - lr: 0.000001 |
| 802 | 2021-01-15 22:25:40,051 epoch 15 - iter 2758/3944 - loss 0.13941754 - samples/sec: 10.71 - lr: 0.000001 |
| 803 | 2021-01-15 22:28:06,583 epoch 15 - iter 3152/3944 - loss 0.14071295 - samples/sec: 10.76 - lr: 0.000001 |
| 804 | 2021-01-15 22:30:32,954 epoch 15 - iter 3546/3944 - loss 0.13981342 - samples/sec: 10.77 - lr: 0.000001 |
| 805 | 2021-01-15 22:33:00,397 epoch 15 - iter 3940/3944 - loss 0.13880390 - samples/sec: 10.69 - lr: 0.000001 |
| 806 | 2021-01-15 22:33:01,714 ---------------------------------------------------------------------------------------------------- |
| 807 | 2021-01-15 22:33:01,715 EPOCH 15 done: loss 0.1387 - lr 0.0000007 |
| 808 | 2021-01-15 22:33:01,715 BAD EPOCHS (no improvement): 4 |
| 809 | 2021-01-15 22:33:01,718 ---------------------------------------------------------------------------------------------------- |
| 810 | 2021-01-15 22:35:29,035 epoch 16 - iter 394/3944 - loss 0.14291727 - samples/sec: 10.70 - lr: 0.000001 |
| 811 | 2021-01-15 22:37:56,417 epoch 16 - iter 788/3944 - loss 0.13149588 - samples/sec: 10.69 - lr: 0.000001 |
| 812 | 2021-01-15 22:40:23,990 epoch 16 - iter 1182/3944 - loss 0.13203036 - samples/sec: 10.68 - lr: 0.000001 |
| 813 | 2021-01-15 22:42:51,538 epoch 16 - iter 1576/3944 - loss 0.13134927 - samples/sec: 10.68 - lr: 0.000001 |
| 814 | 2021-01-15 22:45:19,113 epoch 16 - iter 1970/3944 - loss 0.13179903 - samples/sec: 10.68 - lr: 0.000001 |
| 815 | 2021-01-15 22:47:46,156 epoch 16 - iter 2364/3944 - loss 0.13354076 - samples/sec: 10.72 - lr: 0.000001 |
| 816 | 2021-01-15 22:50:13,300 epoch 16 - iter 2758/3944 - loss 0.13476940 - samples/sec: 10.71 - lr: 0.000001 |
| 817 | 2021-01-15 22:52:38,377 epoch 16 - iter 3152/3944 - loss 0.13497255 - samples/sec: 10.86 - lr: 0.000001 |
| 818 | 2021-01-15 22:55:03,400 epoch 16 - iter 3546/3944 - loss 0.13634147 - samples/sec: 10.87 - lr: 0.000001 |
| 819 | 2021-01-15 22:57:27,892 epoch 16 - iter 3940/3944 - loss 0.13727031 - samples/sec: 10.91 - lr: 0.000000 |
| 820 | 2021-01-15 22:57:29,178 ---------------------------------------------------------------------------------------------------- |
| 821 | 2021-01-15 22:57:29,178 EPOCH 16 done: loss 0.1376 - lr 0.0000005 |
| 822 | 2021-01-15 22:57:29,178 BAD EPOCHS (no improvement): 4 |
| 823 | 2021-01-15 22:57:29,181 ---------------------------------------------------------------------------------------------------- |
| 824 | 2021-01-15 22:59:53,548 epoch 17 - iter 394/3944 - loss 0.14524632 - samples/sec: 10.92 - lr: 0.000000 |
| 825 | 2021-01-15 23:02:18,357 epoch 17 - iter 788/3944 - loss 0.14652155 - samples/sec: 10.88 - lr: 0.000000 |
| 826 | 2021-01-15 23:04:43,610 epoch 17 - iter 1182/3944 - loss 0.13884438 - samples/sec: 10.85 - lr: 0.000000 |
| 827 | 2021-01-15 23:07:08,806 epoch 17 - iter 1576/3944 - loss 0.13549453 - samples/sec: 10.86 - lr: 0.000000 |
| 828 | 2021-01-15 23:09:34,317 epoch 17 - iter 1970/3944 - loss 0.13560330 - samples/sec: 10.83 - lr: 0.000000 |
| 829 | 2021-01-15 23:11:59,595 epoch 17 - iter 2364/3944 - loss 0.13972037 - samples/sec: 10.85 - lr: 0.000000 |
| 830 | 2021-01-15 23:14:24,656 epoch 17 - iter 2758/3944 - loss 0.14040167 - samples/sec: 10.87 - lr: 0.000000 |
| 831 | 2021-01-15 23:16:49,375 epoch 17 - iter 3152/3944 - loss 0.13946642 - samples/sec: 10.89 - lr: 0.000000 |
| 832 | 2021-01-15 23:19:15,069 epoch 17 - iter 3546/3944 - loss 0.13849877 - samples/sec: 10.82 - lr: 0.000000 |
| 833 | 2021-01-15 23:21:40,239 epoch 17 - iter 3940/3944 - loss 0.13743522 - samples/sec: 10.86 - lr: 0.000000 |
| 834 | 2021-01-15 23:21:41,530 ---------------------------------------------------------------------------------------------------- |
| 835 | 2021-01-15 23:21:41,530 EPOCH 17 done: loss 0.1373 - lr 0.0000003 |
| 836 | 2021-01-15 23:21:41,530 BAD EPOCHS (no improvement): 4 |
| 837 | 2021-01-15 23:21:41,533 ---------------------------------------------------------------------------------------------------- |
| 838 | 2021-01-15 23:24:07,941 epoch 18 - iter 394/3944 - loss 0.13214318 - samples/sec: 10.77 - lr: 0.000000 |
| 839 | 2021-01-15 23:26:34,009 epoch 18 - iter 788/3944 - loss 0.14259440 - samples/sec: 10.79 - lr: 0.000000 |
| 840 | 2021-01-15 23:29:00,116 epoch 18 - iter 1182/3944 - loss 0.13753739 - samples/sec: 10.79 - lr: 0.000000 |
| 841 | 2021-01-15 23:31:25,087 epoch 18 - iter 1576/3944 - loss 0.13957844 - samples/sec: 10.87 - lr: 0.000000 |
| 842 | 2021-01-15 23:33:50,076 epoch 18 - iter 1970/3944 - loss 0.13743370 - samples/sec: 10.87 - lr: 0.000000 |
| 843 | 2021-01-15 23:36:14,776 epoch 18 - iter 2364/3944 - loss 0.13970779 - samples/sec: 10.89 - lr: 0.000000 |
| 844 | 2021-01-15 23:38:38,473 epoch 18 - iter 2758/3944 - loss 0.13932537 - samples/sec: 10.97 - lr: 0.000000 |
| 845 | 2021-01-15 23:41:03,249 epoch 18 - iter 3152/3944 - loss 0.13745278 - samples/sec: 10.89 - lr: 0.000000 |
| 846 | 2021-01-15 23:43:28,499 epoch 18 - iter 3546/3944 - loss 0.13924606 - samples/sec: 10.85 - lr: 0.000000 |
| 847 | 2021-01-15 23:45:53,779 epoch 18 - iter 3940/3944 - loss 0.13920658 - samples/sec: 10.85 - lr: 0.000000 |
| 848 | 2021-01-15 23:45:55,039 ---------------------------------------------------------------------------------------------------- |
| 849 | 2021-01-15 23:45:55,040 EPOCH 18 done: loss 0.1400 - lr 0.0000001 |
| 850 | 2021-01-15 23:45:55,040 BAD EPOCHS (no improvement): 4 |
| 851 | 2021-01-15 23:45:55,060 ---------------------------------------------------------------------------------------------------- |
| 852 | 2021-01-15 23:48:19,848 epoch 19 - iter 394/3944 - loss 0.12011491 - samples/sec: 10.89 - lr: 0.000000 |
| 853 | 2021-01-15 23:50:45,410 epoch 19 - iter 788/3944 - loss 0.12712191 - samples/sec: 10.83 - lr: 0.000000 |
| 854 | 2021-01-15 23:53:10,309 epoch 19 - iter 1182/3944 - loss 0.12601271 - samples/sec: 10.88 - lr: 0.000000 |
| 855 | 2021-01-15 23:55:35,025 epoch 19 - iter 1576/3944 - loss 0.12838937 - samples/sec: 10.89 - lr: 0.000000 |
| 856 | 2021-01-15 23:57:59,862 epoch 19 - iter 1970/3944 - loss 0.13018004 - samples/sec: 10.88 - lr: 0.000000 |
| 857 | 2021-01-16 00:00:24,890 epoch 19 - iter 2364/3944 - loss 0.12867846 - samples/sec: 10.87 - lr: 0.000000 |
| 858 | 2021-01-16 00:02:49,627 epoch 19 - iter 2758/3944 - loss 0.12932283 - samples/sec: 10.89 - lr: 0.000000 |
| 859 | 2021-01-16 00:05:14,400 epoch 19 - iter 3152/3944 - loss 0.12859496 - samples/sec: 10.89 - lr: 0.000000 |
| 860 | 2021-01-16 00:07:39,476 epoch 19 - iter 3546/3944 - loss 0.12980219 - samples/sec: 10.86 - lr: 0.000000 |
| 861 | 2021-01-16 00:10:04,796 epoch 19 - iter 3940/3944 - loss 0.13157911 - samples/sec: 10.85 - lr: 0.000000 |
| 862 | 2021-01-16 00:10:06,033 ---------------------------------------------------------------------------------------------------- |
| 863 | 2021-01-16 00:10:06,033 EPOCH 19 done: loss 0.1316 - lr 0.0000000 |
| 864 | 2021-01-16 00:10:06,033 BAD EPOCHS (no improvement): 4 |
| 865 | 2021-01-16 00:10:06,036 ---------------------------------------------------------------------------------------------------- |
| 866 | 2021-01-16 00:12:31,453 epoch 20 - iter 394/3944 - loss 0.12043092 - samples/sec: 10.84 - lr: 0.000000 |
| 867 | 2021-01-16 00:14:56,680 epoch 20 - iter 788/3944 - loss 0.13192874 - samples/sec: 10.85 - lr: 0.000000 |
| 868 | 2021-01-16 00:17:21,816 epoch 20 - iter 1182/3944 - loss 0.13095020 - samples/sec: 10.86 - lr: 0.000000 |
| 869 | 2021-01-16 00:19:46,815 epoch 20 - iter 1576/3944 - loss 0.13423819 - samples/sec: 10.87 - lr: 0.000000 |
| 870 | 2021-01-16 00:22:12,079 epoch 20 - iter 1970/3944 - loss 0.13458985 - samples/sec: 10.85 - lr: 0.000000 |
| 871 | 2021-01-16 00:24:37,900 epoch 20 - iter 2364/3944 - loss 0.13241959 - samples/sec: 10.81 - lr: 0.000000 |
| 872 | 2021-01-16 00:27:03,059 epoch 20 - iter 2758/3944 - loss 0.13235752 - samples/sec: 10.86 - lr: 0.000000 |
| 873 | 2021-01-16 00:29:28,845 epoch 20 - iter 3152/3944 - loss 0.13390899 - samples/sec: 10.81 - lr: 0.000000 |
| 874 | 2021-01-16 00:31:54,866 epoch 20 - iter 3546/3944 - loss 0.13467390 - samples/sec: 10.79 - lr: 0.000000 |
| 875 | 2021-01-16 00:34:19,750 epoch 20 - iter 3940/3944 - loss 0.13514658 - samples/sec: 10.88 - lr: 0.000000 |
| 876 | 2021-01-16 00:34:21,013 ---------------------------------------------------------------------------------------------------- |
| 877 | 2021-01-16 00:34:21,013 EPOCH 20 done: loss 0.1353 - lr 0.0000000 |
| 878 | 2021-01-16 00:34:21,013 BAD EPOCHS (no improvement): 4 |
| 879 | 2021-01-16 00:34:59,015 ---------------------------------------------------------------------------------------------------- |
| 880 | 2021-01-16 00:34:59,015 Testing using best model ... |
| 881 | 2021-01-16 00:36:54,780 0.9319 0.9145 0.9231 |
| 882 | 2021-01-16 00:36:54,780 |
| 883 | Results: |
| 884 | - F1-score (micro) 0.9231 |
| 885 | - F1-score (macro) 0.8691 |
| 886 | |
| 887 | By class: |
| 888 | LOC tp: 981 - fp: 62 - fn: 70 - precision: 0.9406 - recall: 0.9334 - f1-score: 0.9370 |
| 889 | MISC tp: 128 - fp: 26 - fn: 78 - precision: 0.8312 - recall: 0.6214 - f1-score: 0.7111 |
| 890 | ORG tp: 497 - fp: 87 - fn: 87 - precision: 0.8510 - recall: 0.8510 - f1-score: 0.8510 |
| 891 | PER tp: 1184 - fp: 29 - fn: 26 - precision: 0.9761 - recall: 0.9785 - f1-score: 0.9773 |
| 892 | 2021-01-16 00:36:54,780 ---------------------------------------------------------------------------------------------------- |
| 893 | |