End of training
Browse files- README.md +20 -20
- pytorch_model.bin +1 -1
- trainer_state.json +780 -780
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -49,26 +49,26 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:|
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.0004 | 10.0 |
|
| 62 |
-
| 0.0005 | 11.0 |
|
| 63 |
-
| 0.0004 | 12.0 |
|
| 64 |
-
| 0.0004 | 13.0 |
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.0004 | 15.0 |
|
| 67 |
-
| 0.0004 | 16.0 |
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.0004 | 20.0 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0016 | 1.0 | 3637 | 0.0000 | 0 | 0 |
|
| 53 |
+
| 0.0015 | 2.0 | 7274 | 0.0000 | 0 | 0 |
|
| 54 |
+
| 0.0011 | 3.0 | 10911 | 0.0000 | 0 | 0 |
|
| 55 |
+
| 0.001 | 4.0 | 14548 | 0.0000 | 0 | 0 |
|
| 56 |
+
| 0.0007 | 5.0 | 18185 | 0.0000 | 0 | 0 |
|
| 57 |
+
| 0.0008 | 6.0 | 21822 | 0.0000 | 0 | 0 |
|
| 58 |
+
| 0.0006 | 7.0 | 25459 | 0.0000 | 0 | 0 |
|
| 59 |
+
| 0.0007 | 8.0 | 29096 | 0.0000 | 0 | 0 |
|
| 60 |
+
| 0.0006 | 9.0 | 32733 | 0.0000 | 0 | 0 |
|
| 61 |
+
| 0.0004 | 10.0 | 36370 | 0.0000 | 0 | 0 |
|
| 62 |
+
| 0.0005 | 11.0 | 40007 | 0.0000 | 0 | 0 |
|
| 63 |
+
| 0.0004 | 12.0 | 43644 | 0.0000 | 0 | 0 |
|
| 64 |
+
| 0.0004 | 13.0 | 47281 | 0.0000 | 0 | 0 |
|
| 65 |
+
| 0.0005 | 14.0 | 50918 | 0.0000 | 0 | 0 |
|
| 66 |
+
| 0.0004 | 15.0 | 54555 | 0.0000 | 0 | 0 |
|
| 67 |
+
| 0.0004 | 16.0 | 58192 | 0.0000 | 0 | 0 |
|
| 68 |
+
| 0.0004 | 17.0 | 61829 | 0.0000 | 0 | 0 |
|
| 69 |
+
| 0.0004 | 18.0 | 65466 | 0.0000 | 0 | 0 |
|
| 70 |
+
| 0.0004 | 19.0 | 69103 | 0.0000 | 0 | 0 |
|
| 71 |
+
| 0.0004 | 20.0 | 72740 | 0.0000 | 0 | 0 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 258643461
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebdab04168d8d85d5700318b00b6602d10a2c48c00c8024df74c17d1bdd905cf
|
| 3 |
size 258643461
|
trainer_state.json
CHANGED
|
@@ -3,1426 +3,1426 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"learning_rate": 1.
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
-
"learning_rate": 5.
|
| 20 |
-
"loss": 0.
|
| 21 |
-
"step":
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss": 0.
|
| 27 |
-
"step":
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
-
"learning_rate": 2.
|
| 38 |
-
"loss": 0.
|
| 39 |
-
"step":
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
-
"learning_rate": 2.
|
| 44 |
-
"loss": 0.
|
| 45 |
-
"step":
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
-
"learning_rate": 3.
|
| 50 |
-
"loss": 0.
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
-
"learning_rate": 3.
|
| 56 |
-
"loss": 0.
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
-
"learning_rate": 4.
|
| 62 |
-
"loss": 0.
|
| 63 |
-
"step":
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
-
"learning_rate": 4.
|
| 68 |
-
"loss": 0.
|
| 69 |
-
"step":
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
-
"eval_loss":
|
| 74 |
"eval_max_distance": 0,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
-
"eval_runtime": 2.
|
| 77 |
-
"eval_samples_per_second":
|
| 78 |
-
"eval_steps_per_second": 0.
|
| 79 |
-
"step":
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
-
"learning_rate": 5.
|
| 84 |
-
"loss": 0.
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.1,
|
| 89 |
-
"learning_rate": 5.
|
| 90 |
-
"loss": 0.
|
| 91 |
-
"step":
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
-
"learning_rate": 6.
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.3,
|
| 101 |
-
"learning_rate": 6.
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"step":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.4,
|
| 107 |
-
"learning_rate": 7.
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.5,
|
| 113 |
-
"learning_rate": 7.
|
| 114 |
-
"loss": 0.
|
| 115 |
-
"step":
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.6,
|
| 119 |
-
"learning_rate": 8.
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.7,
|
| 125 |
-
"learning_rate": 8.
|
| 126 |
-
"loss": 0.
|
| 127 |
-
"step":
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.8,
|
| 131 |
-
"learning_rate": 9.
|
| 132 |
-
"loss": 0.
|
| 133 |
-
"step":
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.9,
|
| 137 |
-
"learning_rate": 9.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
-
"eval_loss":
|
| 144 |
"eval_max_distance": 0,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
-
"eval_runtime": 2.
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second": 0.
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 2.0,
|
| 153 |
-
"learning_rate": 9.
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 2.1,
|
| 159 |
-
"learning_rate": 9.
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.2,
|
| 165 |
-
"learning_rate": 9.
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.3,
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.4,
|
| 177 |
-
"learning_rate": 9.
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 2.5,
|
| 183 |
-
"learning_rate": 9.
|
| 184 |
-
"loss": 0.
|
| 185 |
-
"step":
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.6,
|
| 189 |
-
"learning_rate": 9.
|
| 190 |
-
"loss": 0.
|
| 191 |
-
"step":
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.7,
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.8,
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.9,
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
-
"eval_loss":
|
| 214 |
"eval_max_distance": 0,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
-
"eval_runtime": 2.
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second": 0.
|
| 219 |
-
"step":
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 3.
|
| 223 |
-
"learning_rate": 9.
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch": 3.
|
| 229 |
-
"learning_rate": 9.
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 3.
|
| 235 |
-
"learning_rate": 9.
|
| 236 |
-
"loss": 0.
|
| 237 |
-
"step":
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch": 3.
|
| 241 |
-
"learning_rate": 9.
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch": 3.
|
| 247 |
-
"learning_rate": 9.
|
| 248 |
"loss": 0.0006,
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 3.
|
| 253 |
-
"learning_rate": 9.
|
| 254 |
-
"loss": 0.
|
| 255 |
-
"step":
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch": 3.
|
| 259 |
-
"learning_rate": 9.
|
| 260 |
-
"loss": 0.
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 3.
|
| 265 |
-
"learning_rate": 9.
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 3.
|
| 271 |
-
"learning_rate": 8.
|
| 272 |
-
"loss": 0.
|
| 273 |
-
"step":
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch": 3.
|
| 277 |
-
"learning_rate": 8.
|
| 278 |
-
"loss": 0.
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
-
"eval_loss": 2.
|
| 284 |
"eval_max_distance": 0,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
-
"eval_runtime": 2.
|
| 287 |
-
"eval_samples_per_second":
|
| 288 |
-
"eval_steps_per_second": 0.
|
| 289 |
-
"step":
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 4.
|
| 293 |
-
"learning_rate": 8.
|
| 294 |
-
"loss": 0.
|
| 295 |
-
"step":
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 4.
|
| 299 |
-
"learning_rate": 8.
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"step":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
-
"epoch": 4.
|
| 305 |
-
"learning_rate": 8.
|
| 306 |
"loss": 0.0006,
|
| 307 |
-
"step":
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch": 4.
|
| 311 |
-
"learning_rate": 8.
|
| 312 |
-
"loss": 0.
|
| 313 |
-
"step":
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch": 4.
|
| 317 |
-
"learning_rate": 8.
|
| 318 |
"loss": 0.0007,
|
| 319 |
-
"step":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"epoch": 4.
|
| 323 |
-
"learning_rate": 8.
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch": 4.
|
| 329 |
-
"learning_rate": 8.
|
| 330 |
-
"loss": 0.
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 4.
|
| 335 |
-
"learning_rate": 8.
|
| 336 |
"loss": 0.0006,
|
| 337 |
-
"step":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch": 4.
|
| 341 |
-
"learning_rate": 8.
|
| 342 |
"loss": 0.0007,
|
| 343 |
-
"step":
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch": 4.
|
| 347 |
-
"learning_rate": 8.
|
| 348 |
-
"loss": 0.
|
| 349 |
-
"step":
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
-
"eval_loss":
|
| 354 |
"eval_max_distance": 0,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
-
"eval_runtime": 2.
|
| 357 |
-
"eval_samples_per_second":
|
| 358 |
-
"eval_steps_per_second": 0.
|
| 359 |
-
"step":
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 5.01,
|
| 363 |
-
"learning_rate": 8.328670024249207e-05,
|
| 364 |
-
"loss": 0.0006,
|
| 365 |
-
"step": 17900
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch": 5.
|
| 369 |
-
"learning_rate": 8.
|
| 370 |
"loss": 0.0007,
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch": 5.
|
| 375 |
-
"learning_rate": 8.
|
| 376 |
"loss": 0.0006,
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 5.
|
| 381 |
-
"learning_rate": 8.
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch": 5.
|
| 387 |
-
"learning_rate": 8.
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch": 5.
|
| 393 |
-
"learning_rate": 8.
|
| 394 |
-
"loss": 0.
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 5.
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"step":
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 5.
|
| 405 |
-
"learning_rate": 7.
|
| 406 |
-
"loss": 0.
|
| 407 |
-
"step":
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch": 5.
|
| 411 |
-
"learning_rate": 7.
|
| 412 |
-
"loss": 0.
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"epoch": 5.
|
| 417 |
-
"learning_rate": 7.
|
| 418 |
"loss": 0.0006,
|
| 419 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
-
"eval_loss":
|
| 424 |
"eval_max_distance": 0,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
-
"eval_runtime": 2.
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second": 0.
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 6.
|
| 433 |
-
"learning_rate": 7.
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.11,
|
| 439 |
-
"learning_rate": 7.
|
| 440 |
"loss": 0.0005,
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.21,
|
| 445 |
-
"learning_rate": 7.
|
| 446 |
"loss": 0.0006,
|
| 447 |
-
"step":
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.31,
|
| 451 |
-
"learning_rate": 7.
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 6.41,
|
| 457 |
-
"learning_rate": 7.
|
| 458 |
-
"loss": 0.
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 6.51,
|
| 463 |
-
"learning_rate": 7.
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 6.61,
|
| 469 |
-
"learning_rate": 7.
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 6.71,
|
| 475 |
-
"learning_rate": 7.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 6.81,
|
| 481 |
-
"learning_rate": 7.
|
| 482 |
"loss": 0.0005,
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.91,
|
| 487 |
-
"learning_rate": 7.
|
| 488 |
-
"loss": 0.
|
| 489 |
-
"step":
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
-
"eval_loss":
|
| 494 |
"eval_max_distance": 0,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
-
"eval_runtime": 2.
|
| 497 |
-
"eval_samples_per_second":
|
| 498 |
-
"eval_steps_per_second": 0.
|
| 499 |
-
"step":
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.01,
|
| 503 |
-
"learning_rate": 7.
|
| 504 |
-
"loss": 0.
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.11,
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.21,
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
"loss": 0.0005,
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.31,
|
| 521 |
-
"learning_rate": 7.
|
| 522 |
"loss": 0.0005,
|
| 523 |
-
"step":
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.41,
|
| 527 |
-
"learning_rate": 6.
|
| 528 |
-
"loss": 0.
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.51,
|
| 533 |
-
"learning_rate": 6.
|
| 534 |
"loss": 0.0004,
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 7.61,
|
| 539 |
-
"learning_rate": 6.
|
| 540 |
-
"loss": 0.
|
| 541 |
-
"step":
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.71,
|
| 545 |
-
"learning_rate": 6.
|
| 546 |
-
"loss": 0.
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 7.81,
|
| 551 |
-
"learning_rate": 6.
|
| 552 |
-
"loss": 0.
|
| 553 |
-
"step":
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 7.91,
|
| 557 |
-
"learning_rate": 6.
|
| 558 |
-
"loss": 0.
|
| 559 |
-
"step":
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
-
"eval_loss":
|
| 564 |
"eval_max_distance": 0,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
-
"eval_runtime": 2.
|
| 567 |
-
"eval_samples_per_second":
|
| 568 |
-
"eval_steps_per_second": 0.
|
| 569 |
-
"step":
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 8.01,
|
| 573 |
-
"learning_rate": 6.
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.11,
|
| 579 |
-
"learning_rate": 6.
|
| 580 |
-
"loss": 0.
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 8.21,
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 8.31,
|
| 591 |
-
"learning_rate": 6.
|
| 592 |
"loss": 0.0005,
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.41,
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.51,
|
| 603 |
-
"learning_rate": 6.
|
| 604 |
"loss": 0.0005,
|
| 605 |
-
"step":
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 8.61,
|
| 609 |
-
"learning_rate": 6.
|
| 610 |
-
"loss": 0.
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 8.71,
|
| 615 |
-
"learning_rate": 6.
|
| 616 |
"loss": 0.0005,
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 8.81,
|
| 621 |
-
"learning_rate": 6.
|
| 622 |
"loss": 0.0005,
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 8.91,
|
| 627 |
-
"learning_rate": 6.
|
| 628 |
-
"loss": 0.
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
-
"eval_loss":
|
| 634 |
"eval_max_distance": 0,
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
-
"eval_runtime": 2.
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second": 0.
|
| 639 |
-
"step":
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 9.02,
|
| 643 |
-
"learning_rate": 6.102717154759684e-05,
|
| 644 |
-
"loss": 0.0004,
|
| 645 |
-
"step": 32220
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch": 9.
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
"loss": 0.0005,
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch": 9.
|
| 655 |
-
"learning_rate":
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch": 9.
|
| 661 |
-
"learning_rate": 5.
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch": 9.
|
| 667 |
-
"learning_rate": 5.
|
| 668 |
"loss": 0.0005,
|
| 669 |
-
"step":
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch": 9.
|
| 673 |
-
"learning_rate": 5.
|
| 674 |
-
"loss": 0.
|
| 675 |
-
"step":
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch": 9.
|
| 679 |
-
"learning_rate": 5.
|
| 680 |
"loss": 0.0005,
|
| 681 |
-
"step":
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 9.
|
| 685 |
-
"learning_rate": 5.
|
| 686 |
-
"loss": 0.
|
| 687 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch": 9.
|
| 691 |
-
"learning_rate": 5.
|
| 692 |
"loss": 0.0005,
|
| 693 |
-
"step":
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch": 9.
|
| 697 |
-
"learning_rate": 5.
|
| 698 |
"loss": 0.0004,
|
| 699 |
-
"step":
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
-
"eval_loss":
|
| 704 |
"eval_max_distance": 0,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
-
"eval_runtime": 2.
|
| 707 |
-
"eval_samples_per_second":
|
| 708 |
-
"eval_steps_per_second": 0.
|
| 709 |
-
"step":
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 10.
|
| 713 |
-
"learning_rate": 5.
|
| 714 |
"loss": 0.0005,
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch": 10.
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch": 10.
|
| 725 |
-
"learning_rate": 5.
|
| 726 |
"loss": 0.0005,
|
| 727 |
-
"step":
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"epoch": 10.
|
| 731 |
-
"learning_rate": 5.
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"step":
|
| 734 |
},
|
| 735 |
{
|
| 736 |
-
"epoch": 10.
|
| 737 |
-
"learning_rate": 5.
|
| 738 |
"loss": 0.0005,
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch": 10.
|
| 743 |
-
"learning_rate": 5.
|
| 744 |
"loss": 0.0004,
|
| 745 |
-
"step":
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch": 10.
|
| 749 |
-
"learning_rate": 5.
|
| 750 |
"loss": 0.0005,
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 10.
|
| 755 |
-
"learning_rate": 5.
|
| 756 |
-
"loss": 0.
|
| 757 |
-
"step":
|
| 758 |
},
|
| 759 |
{
|
| 760 |
-
"epoch": 10.
|
| 761 |
-
"learning_rate": 5.
|
| 762 |
-
"loss": 0.
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
-
"epoch": 10.
|
| 767 |
-
"learning_rate": 5.
|
| 768 |
"loss": 0.0005,
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
-
"eval_loss":
|
| 774 |
"eval_max_distance": 0,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
-
"eval_runtime": 2.
|
| 777 |
-
"eval_samples_per_second":
|
| 778 |
-
"eval_steps_per_second": 0.
|
| 779 |
-
"step":
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch": 11.
|
| 783 |
-
"learning_rate": 4.
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch": 11.
|
| 789 |
-
"learning_rate": 4.
|
| 790 |
"loss": 0.0004,
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch": 11.
|
| 795 |
-
"learning_rate": 4.
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch": 11.
|
| 801 |
-
"learning_rate": 4.
|
| 802 |
"loss": 0.0004,
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch": 11.
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
"loss": 0.0005,
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch": 11.
|
| 813 |
-
"learning_rate": 4.
|
| 814 |
-
"loss": 0.
|
| 815 |
-
"step":
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch": 11.
|
| 819 |
-
"learning_rate": 4.
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 11.
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch": 11.
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
"loss": 0.0004,
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch": 11.
|
| 837 |
-
"learning_rate": 4.
|
| 838 |
"loss": 0.0004,
|
| 839 |
-
"step":
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
-
"eval_loss":
|
| 844 |
"eval_max_distance": 0,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
-
"eval_runtime": 2.
|
| 847 |
-
"eval_samples_per_second":
|
| 848 |
-
"eval_steps_per_second": 0.
|
| 849 |
-
"step":
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch": 12.
|
| 853 |
-
"learning_rate": 4.
|
| 854 |
-
"loss": 0.
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch": 12.
|
| 859 |
-
"learning_rate": 4.
|
| 860 |
"loss": 0.0004,
|
| 861 |
-
"step":
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch": 12.
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch": 12.
|
| 871 |
-
"learning_rate": 4.
|
| 872 |
"loss": 0.0004,
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch": 12.
|
| 877 |
-
"learning_rate": 4.
|
| 878 |
"loss": 0.0004,
|
| 879 |
-
"step":
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch": 12.
|
| 883 |
-
"learning_rate": 4.
|
| 884 |
"loss": 0.0004,
|
| 885 |
-
"step":
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch": 12.
|
| 889 |
-
"learning_rate": 4.
|
| 890 |
-
"loss": 0.
|
| 891 |
-
"step":
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch": 12.
|
| 895 |
-
"learning_rate": 4.
|
| 896 |
-
"loss": 0.
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch": 12.
|
| 901 |
-
"learning_rate": 3.
|
| 902 |
-
"loss": 0.
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch": 12.
|
| 907 |
-
"learning_rate": 3.
|
| 908 |
"loss": 0.0004,
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
-
"eval_loss":
|
| 914 |
"eval_max_distance": 0,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
-
"eval_runtime": 2.
|
| 917 |
-
"eval_samples_per_second":
|
| 918 |
-
"eval_steps_per_second": 0.
|
| 919 |
-
"step":
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 13.
|
| 923 |
-
"learning_rate": 3.
|
| 924 |
-
"loss": 0.
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch": 13.
|
| 929 |
-
"learning_rate": 3.
|
| 930 |
"loss": 0.0004,
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch": 13.
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
"loss": 0.0004,
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch": 13.
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
"loss": 0.0004,
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch": 13.
|
| 947 |
-
"learning_rate": 3.
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch": 13.
|
| 953 |
-
"learning_rate": 3.
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch": 13.
|
| 959 |
-
"learning_rate": 3.
|
| 960 |
"loss": 0.0004,
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch": 13.
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
"loss": 0.0004,
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch": 13.
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
"loss": 0.0004,
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch": 13.
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
-
"loss": 0.
|
| 979 |
-
"step":
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
-
"eval_loss":
|
| 984 |
"eval_max_distance": 0,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
-
"eval_runtime": 2.
|
| 987 |
-
"eval_samples_per_second":
|
| 988 |
-
"eval_steps_per_second": 0.
|
| 989 |
-
"step":
|
| 990 |
-
},
|
| 991 |
-
{
|
| 992 |
-
"epoch": 14.02,
|
| 993 |
-
"learning_rate": 3.3202760678977806e-05,
|
| 994 |
-
"loss": 0.0004,
|
| 995 |
-
"step": 50120
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch": 14.
|
| 999 |
-
"learning_rate": 3.
|
| 1000 |
-
"loss": 0.
|
| 1001 |
-
"step":
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch": 14.
|
| 1005 |
-
"learning_rate": 3.
|
| 1006 |
"loss": 0.0005,
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch": 14.
|
| 1011 |
-
"learning_rate": 3.
|
| 1012 |
"loss": 0.0003,
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch": 14.
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
"loss": 0.0004,
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch": 14.
|
| 1023 |
-
"learning_rate": 3.
|
| 1024 |
"loss": 0.0004,
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch": 14.
|
| 1029 |
-
"learning_rate":
|
| 1030 |
"loss": 0.0004,
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch": 14.
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
-
"loss": 0.
|
| 1037 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch": 14.
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch": 14.
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
"loss": 0.0004,
|
| 1049 |
-
"step":
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
-
"eval_loss":
|
| 1054 |
"eval_max_distance": 0,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
-
"eval_runtime": 2.
|
| 1057 |
-
"eval_samples_per_second":
|
| 1058 |
-
"eval_steps_per_second": 0.
|
| 1059 |
-
"step":
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
-
"epoch": 15.
|
| 1063 |
-
"learning_rate": 2.
|
| 1064 |
-
"loss": 0.
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch": 15.
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch": 15.
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
"loss": 0.0003,
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch": 15.
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
"loss": 0.0003,
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch": 15.
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
"loss": 0.0003,
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch": 15.
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
"loss": 0.0003,
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch": 15.
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
"loss": 0.0004,
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch": 15.
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch": 15.
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch": 15.
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
"loss": 0.0004,
|
| 1119 |
-
"step":
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
-
"eval_loss":
|
| 1124 |
"eval_max_distance": 0,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
-
"eval_runtime": 2.
|
| 1127 |
-
"eval_samples_per_second":
|
| 1128 |
-
"eval_steps_per_second": 0.
|
| 1129 |
-
"step":
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch": 16.
|
| 1133 |
-
"learning_rate": 2.
|
| 1134 |
"loss": 0.0004,
|
| 1135 |
-
"step":
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch": 16.
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
"loss": 0.0004,
|
| 1141 |
-
"step":
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch": 16.
|
| 1145 |
-
"learning_rate": 2.
|
| 1146 |
-
"loss": 0.
|
| 1147 |
-
"step":
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
-
"epoch": 16.
|
| 1151 |
-
"learning_rate": 2.
|
| 1152 |
"loss": 0.0004,
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch": 16.
|
| 1157 |
-
"learning_rate": 1.
|
| 1158 |
"loss": 0.0003,
|
| 1159 |
-
"step":
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch": 16.
|
| 1163 |
-
"learning_rate": 1.
|
| 1164 |
-
"loss": 0.
|
| 1165 |
-
"step":
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
-
"epoch": 16.
|
| 1169 |
-
"learning_rate": 1.
|
| 1170 |
"loss": 0.0003,
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch": 16.
|
| 1175 |
-
"learning_rate": 1.
|
| 1176 |
"loss": 0.0004,
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch": 16.
|
| 1181 |
-
"learning_rate": 1.
|
| 1182 |
-
"loss": 0.
|
| 1183 |
-
"step":
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch": 16.
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
-
"loss": 0.
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
-
"eval_loss":
|
| 1194 |
"eval_max_distance": 0,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
-
"eval_runtime": 2.
|
| 1197 |
-
"eval_samples_per_second":
|
| 1198 |
-
"eval_steps_per_second": 0.
|
| 1199 |
-
"step":
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch": 17.
|
| 1203 |
-
"learning_rate": 1.
|
| 1204 |
"loss": 0.0004,
|
| 1205 |
-
"step":
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
-
"epoch": 17.
|
| 1209 |
-
"learning_rate": 1.
|
| 1210 |
"loss": 0.0003,
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch": 17.
|
| 1215 |
-
"learning_rate": 1.
|
| 1216 |
"loss": 0.0003,
|
| 1217 |
-
"step":
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch": 17.
|
| 1221 |
-
"learning_rate": 1.
|
| 1222 |
-
"loss": 0.
|
| 1223 |
-
"step":
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"epoch": 17.
|
| 1227 |
-
"learning_rate": 1.
|
| 1228 |
"loss": 0.0003,
|
| 1229 |
-
"step":
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
-
"epoch": 17.
|
| 1233 |
-
"learning_rate": 1.
|
| 1234 |
"loss": 0.0004,
|
| 1235 |
-
"step":
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch": 17.
|
| 1239 |
-
"learning_rate": 1.
|
| 1240 |
-
"loss": 0.
|
| 1241 |
-
"step":
|
| 1242 |
-
},
|
| 1243 |
-
{
|
| 1244 |
-
"epoch": 17.73,
|
| 1245 |
-
"learning_rate": 1.2612696636199714e-05,
|
| 1246 |
-
"loss": 0.0003,
|
| 1247 |
-
"step": 63366
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch": 17.
|
| 1251 |
-
"learning_rate": 1.
|
| 1252 |
"loss": 0.0004,
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch": 17.
|
| 1257 |
-
"learning_rate": 1.
|
| 1258 |
"loss": 0.0003,
|
| 1259 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
-
"eval_loss":
|
| 1264 |
"eval_max_distance": 0,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
-
"eval_runtime": 2.
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second": 0.
|
| 1269 |
-
"step":
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch": 18.
|
| 1273 |
-
"learning_rate": 1.
|
| 1274 |
-
"loss": 0.
|
| 1275 |
-
"step":
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch": 18.
|
| 1279 |
-
"learning_rate": 1.
|
| 1280 |
-
"loss": 0.
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch": 18.
|
| 1285 |
-
"learning_rate": 9.
|
| 1286 |
-
"loss": 0.
|
| 1287 |
-
"step":
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch": 18.
|
| 1291 |
-
"learning_rate": 9.
|
| 1292 |
"loss": 0.0003,
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch": 18.
|
| 1297 |
-
"learning_rate": 8.
|
| 1298 |
-
"loss": 0.
|
| 1299 |
-
"step":
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch": 18.
|
| 1303 |
-
"learning_rate": 8.
|
| 1304 |
-
"loss": 0.
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch": 18.
|
| 1309 |
-
"learning_rate": 7.
|
| 1310 |
-
"loss": 0.
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch": 18.
|
| 1315 |
-
"learning_rate": 7.
|
| 1316 |
"loss": 0.0004,
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch": 18.
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
"loss": 0.0004,
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18.
|
| 1327 |
-
"learning_rate":
|
| 1328 |
-
"loss": 0.
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
-
"eval_loss":
|
| 1334 |
"eval_max_distance": 0,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
-
"eval_runtime": 2.
|
| 1337 |
-
"eval_samples_per_second":
|
| 1338 |
-
"eval_steps_per_second": 0.
|
| 1339 |
-
"step":
|
| 1340 |
-
},
|
| 1341 |
-
{
|
| 1342 |
-
"epoch": 19.03,
|
| 1343 |
-
"learning_rate": 5.378349810358764e-06,
|
| 1344 |
-
"loss": 0.0004,
|
| 1345 |
-
"step": 68020
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
-
"epoch": 19.
|
| 1349 |
-
"learning_rate":
|
| 1350 |
"loss": 0.0003,
|
| 1351 |
-
"step":
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"epoch": 19.
|
| 1355 |
-
"learning_rate": 4.
|
| 1356 |
"loss": 0.0003,
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch": 19.
|
| 1361 |
-
"learning_rate":
|
| 1362 |
"loss": 0.0004,
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch": 19.
|
| 1367 |
-
"learning_rate": 3.
|
| 1368 |
"loss": 0.0003,
|
| 1369 |
-
"step":
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch": 19.
|
| 1373 |
-
"learning_rate":
|
| 1374 |
-
"loss": 0.
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch": 19.
|
| 1379 |
-
"learning_rate": 2.
|
| 1380 |
"loss": 0.0004,
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch": 19.
|
| 1385 |
-
"learning_rate":
|
| 1386 |
-
"loss": 0.
|
| 1387 |
-
"step":
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
-
"epoch": 19.
|
| 1391 |
-
"learning_rate":
|
| 1392 |
"loss": 0.0003,
|
| 1393 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"epoch": 19.
|
| 1397 |
-
"learning_rate":
|
| 1398 |
"loss": 0.0004,
|
| 1399 |
-
"step":
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
-
"eval_loss":
|
| 1404 |
"eval_max_distance": 0,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
-
"eval_runtime": 2.
|
| 1407 |
-
"eval_samples_per_second":
|
| 1408 |
-
"eval_steps_per_second": 0.
|
| 1409 |
-
"step":
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
-
"step":
|
| 1414 |
-
"total_flos": 4.
|
| 1415 |
-
"train_loss": 0.
|
| 1416 |
-
"train_runtime":
|
| 1417 |
-
"train_samples_per_second":
|
| 1418 |
-
"train_steps_per_second": 10.
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
-
"logging_steps":
|
| 1422 |
-
"max_steps":
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
-
"save_steps":
|
| 1425 |
-
"total_flos": 4.
|
| 1426 |
"trial_name": null,
|
| 1427 |
"trial_params": null
|
| 1428 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 72740,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.3747594171020073e-08,
|
| 14 |
+
"loss": 0.0014,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.0041242782513065e-06,
|
| 20 |
+
"loss": 0.0035,
|
| 21 |
+
"step": 364
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.0008248556502613e-05,
|
| 26 |
+
"loss": 0.0031,
|
| 27 |
+
"step": 728
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.5012372834753918e-05,
|
| 32 |
+
"loss": 0.003,
|
| 33 |
+
"step": 1092
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.0016497113005226e-05,
|
| 38 |
+
"loss": 0.0026,
|
| 39 |
+
"step": 1456
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.5020621391256532e-05,
|
| 44 |
+
"loss": 0.0029,
|
| 45 |
+
"step": 1820
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.0024745669507835e-05,
|
| 50 |
+
"loss": 0.0017,
|
| 51 |
+
"step": 2184
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.5028869947759145e-05,
|
| 56 |
+
"loss": 0.002,
|
| 57 |
+
"step": 2548
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.003299422601045e-05,
|
| 62 |
+
"loss": 0.0016,
|
| 63 |
+
"step": 2912
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.503711850426176e-05,
|
| 68 |
+
"loss": 0.0016,
|
| 69 |
+
"step": 3276
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 8.495924816998013e-07,
|
| 74 |
"eval_max_distance": 0,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 2.3681,
|
| 77 |
+
"eval_samples_per_second": 21.114,
|
| 78 |
+
"eval_steps_per_second": 0.845,
|
| 79 |
+
"step": 3637
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.0041242782513065e-05,
|
| 84 |
+
"loss": 0.0018,
|
| 85 |
+
"step": 3640
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 5.5045367060764364e-05,
|
| 90 |
+
"loss": 0.0018,
|
| 91 |
+
"step": 4004
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 6.004949133901567e-05,
|
| 96 |
+
"loss": 0.0014,
|
| 97 |
+
"step": 4368
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 6.505361561726698e-05,
|
| 102 |
+
"loss": 0.0017,
|
| 103 |
+
"step": 4732
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 7.005773989551829e-05,
|
| 108 |
+
"loss": 0.001,
|
| 109 |
+
"step": 5096
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 7.506186417376959e-05,
|
| 114 |
+
"loss": 0.0012,
|
| 115 |
+
"step": 5460
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 8.00659884520209e-05,
|
| 120 |
+
"loss": 0.0012,
|
| 121 |
+
"step": 5824
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 8.507011273027222e-05,
|
| 126 |
+
"loss": 0.0011,
|
| 127 |
+
"step": 6188
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 9.007423700852352e-05,
|
| 132 |
+
"loss": 0.0009,
|
| 133 |
+
"step": 6552
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 9.507836128677482e-05,
|
| 138 |
+
"loss": 0.0015,
|
| 139 |
+
"step": 6916
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 1.1638746855169302e-06,
|
| 144 |
"eval_max_distance": 0,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 2.3712,
|
| 147 |
+
"eval_samples_per_second": 21.087,
|
| 148 |
+
"eval_steps_per_second": 0.843,
|
| 149 |
+
"step": 7274
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 9.999083493721932e-05,
|
| 154 |
+
"loss": 0.001,
|
| 155 |
+
"step": 7280
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 2.1,
|
| 159 |
+
"learning_rate": 9.943482112852474e-05,
|
| 160 |
+
"loss": 0.0012,
|
| 161 |
+
"step": 7644
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.2,
|
| 165 |
+
"learning_rate": 9.887880731983015e-05,
|
| 166 |
+
"loss": 0.001,
|
| 167 |
+
"step": 8008
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.3,
|
| 171 |
+
"learning_rate": 9.832279351113555e-05,
|
| 172 |
+
"loss": 0.0011,
|
| 173 |
+
"step": 8372
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.4,
|
| 177 |
+
"learning_rate": 9.776677970244097e-05,
|
| 178 |
+
"loss": 0.001,
|
| 179 |
+
"step": 8736
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 2.5,
|
| 183 |
+
"learning_rate": 9.721076589374639e-05,
|
| 184 |
+
"loss": 0.001,
|
| 185 |
+
"step": 9100
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.6,
|
| 189 |
+
"learning_rate": 9.665475208505179e-05,
|
| 190 |
+
"loss": 0.0008,
|
| 191 |
+
"step": 9464
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.7,
|
| 195 |
+
"learning_rate": 9.60987382763572e-05,
|
| 196 |
+
"loss": 0.001,
|
| 197 |
+
"step": 9828
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.8,
|
| 201 |
+
"learning_rate": 9.55427244676626e-05,
|
| 202 |
+
"loss": 0.001,
|
| 203 |
+
"step": 10192
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.9,
|
| 207 |
+
"learning_rate": 9.498671065896801e-05,
|
| 208 |
+
"loss": 0.0011,
|
| 209 |
+
"step": 10556
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 1.2921987035952043e-06,
|
| 214 |
"eval_max_distance": 0,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 2.3627,
|
| 217 |
+
"eval_samples_per_second": 21.162,
|
| 218 |
+
"eval_steps_per_second": 0.846,
|
| 219 |
+
"step": 10911
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 3.0,
|
| 223 |
+
"learning_rate": 9.443069685027342e-05,
|
| 224 |
+
"loss": 0.0009,
|
| 225 |
+
"step": 10920
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 3.1,
|
| 229 |
+
"learning_rate": 9.387468304157884e-05,
|
| 230 |
+
"loss": 0.0008,
|
| 231 |
+
"step": 11284
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 3.2,
|
| 235 |
+
"learning_rate": 9.331866923288425e-05,
|
| 236 |
+
"loss": 0.001,
|
| 237 |
+
"step": 11648
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 3.3,
|
| 241 |
+
"learning_rate": 9.276265542418966e-05,
|
| 242 |
+
"loss": 0.0008,
|
| 243 |
+
"step": 12012
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 3.4,
|
| 247 |
+
"learning_rate": 9.220664161549507e-05,
|
| 248 |
"loss": 0.0006,
|
| 249 |
+
"step": 12376
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 3.5,
|
| 253 |
+
"learning_rate": 9.165062780680049e-05,
|
| 254 |
+
"loss": 0.0008,
|
| 255 |
+
"step": 12740
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 3.6,
|
| 259 |
+
"learning_rate": 9.109461399810589e-05,
|
| 260 |
+
"loss": 0.0008,
|
| 261 |
+
"step": 13104
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 3.7,
|
| 265 |
+
"learning_rate": 9.05386001894113e-05,
|
| 266 |
+
"loss": 0.0009,
|
| 267 |
+
"step": 13468
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 3.8,
|
| 271 |
+
"learning_rate": 8.998258638071672e-05,
|
| 272 |
+
"loss": 0.0007,
|
| 273 |
+
"step": 13832
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 3.9,
|
| 277 |
+
"learning_rate": 8.942657257202212e-05,
|
| 278 |
+
"loss": 0.001,
|
| 279 |
+
"step": 14196
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 2.308262310179998e-06,
|
| 284 |
"eval_max_distance": 0,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 2.356,
|
| 287 |
+
"eval_samples_per_second": 21.223,
|
| 288 |
+
"eval_steps_per_second": 0.849,
|
| 289 |
+
"step": 14548
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 4.0,
|
| 293 |
+
"learning_rate": 8.887055876332754e-05,
|
| 294 |
+
"loss": 0.0009,
|
| 295 |
+
"step": 14560
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.1,
|
| 299 |
+
"learning_rate": 8.831454495463294e-05,
|
| 300 |
+
"loss": 0.0008,
|
| 301 |
+
"step": 14924
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 4.2,
|
| 305 |
+
"learning_rate": 8.775853114593834e-05,
|
| 306 |
"loss": 0.0006,
|
| 307 |
+
"step": 15288
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 4.3,
|
| 311 |
+
"learning_rate": 8.720251733724376e-05,
|
| 312 |
+
"loss": 0.0005,
|
| 313 |
+
"step": 15652
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 4.4,
|
| 317 |
+
"learning_rate": 8.664650352854918e-05,
|
| 318 |
"loss": 0.0007,
|
| 319 |
+
"step": 16016
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 4.5,
|
| 323 |
+
"learning_rate": 8.609048971985458e-05,
|
| 324 |
+
"loss": 0.0007,
|
| 325 |
+
"step": 16380
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 4.6,
|
| 329 |
+
"learning_rate": 8.553447591115999e-05,
|
| 330 |
+
"loss": 0.0008,
|
| 331 |
+
"step": 16744
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 4.7,
|
| 335 |
+
"learning_rate": 8.497846210246541e-05,
|
| 336 |
"loss": 0.0006,
|
| 337 |
+
"step": 17108
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 4.8,
|
| 341 |
+
"learning_rate": 8.442244829377081e-05,
|
| 342 |
"loss": 0.0007,
|
| 343 |
+
"step": 17472
|
| 344 |
},
|
| 345 |
{
|
| 346 |
+
"epoch": 4.9,
|
| 347 |
+
"learning_rate": 8.386643448507623e-05,
|
| 348 |
+
"loss": 0.0007,
|
| 349 |
+
"step": 17836
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 5.198210146772908e-07,
|
| 354 |
"eval_max_distance": 0,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 2.3541,
|
| 357 |
+
"eval_samples_per_second": 21.24,
|
| 358 |
+
"eval_steps_per_second": 0.85,
|
| 359 |
+
"step": 18185
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 5.0,
|
| 363 |
+
"learning_rate": 8.331042067638164e-05,
|
| 364 |
"loss": 0.0007,
|
| 365 |
+
"step": 18200
|
| 366 |
},
|
| 367 |
{
|
| 368 |
+
"epoch": 5.1,
|
| 369 |
+
"learning_rate": 8.275440686768706e-05,
|
| 370 |
"loss": 0.0006,
|
| 371 |
+
"step": 18564
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 5.2,
|
| 375 |
+
"learning_rate": 8.219839305899246e-05,
|
| 376 |
+
"loss": 0.0007,
|
| 377 |
+
"step": 18928
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 5.3,
|
| 381 |
+
"learning_rate": 8.164237925029788e-05,
|
| 382 |
+
"loss": 0.0008,
|
| 383 |
+
"step": 19292
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 5.4,
|
| 387 |
+
"learning_rate": 8.108636544160328e-05,
|
| 388 |
+
"loss": 0.0007,
|
| 389 |
+
"step": 19656
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 5.5,
|
| 393 |
+
"learning_rate": 8.053035163290868e-05,
|
| 394 |
+
"loss": 0.0006,
|
| 395 |
+
"step": 20020
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 5.6,
|
| 399 |
+
"learning_rate": 7.99743378242141e-05,
|
| 400 |
+
"loss": 0.0006,
|
| 401 |
+
"step": 20384
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 5.7,
|
| 405 |
+
"learning_rate": 7.941832401551951e-05,
|
| 406 |
+
"loss": 0.0007,
|
| 407 |
+
"step": 20748
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 5.8,
|
| 411 |
+
"learning_rate": 7.886231020682491e-05,
|
| 412 |
"loss": 0.0006,
|
| 413 |
+
"step": 21112
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.9,
|
| 417 |
+
"learning_rate": 7.830629639813033e-05,
|
| 418 |
+
"loss": 0.0008,
|
| 419 |
+
"step": 21476
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 5.296922722664021e-07,
|
| 424 |
"eval_max_distance": 0,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 2.3254,
|
| 427 |
+
"eval_samples_per_second": 21.501,
|
| 428 |
+
"eval_steps_per_second": 0.86,
|
| 429 |
+
"step": 21822
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 6.0,
|
| 433 |
+
"learning_rate": 7.775028258943574e-05,
|
| 434 |
+
"loss": 0.0007,
|
| 435 |
+
"step": 21840
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.11,
|
| 439 |
+
"learning_rate": 7.719426878074115e-05,
|
| 440 |
"loss": 0.0005,
|
| 441 |
+
"step": 22204
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.21,
|
| 445 |
+
"learning_rate": 7.663825497204656e-05,
|
| 446 |
"loss": 0.0006,
|
| 447 |
+
"step": 22568
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.31,
|
| 451 |
+
"learning_rate": 7.608224116335198e-05,
|
| 452 |
+
"loss": 0.0006,
|
| 453 |
+
"step": 22932
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 6.41,
|
| 457 |
+
"learning_rate": 7.552622735465738e-05,
|
| 458 |
+
"loss": 0.0006,
|
| 459 |
+
"step": 23296
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 6.51,
|
| 463 |
+
"learning_rate": 7.49702135459628e-05,
|
| 464 |
+
"loss": 0.0006,
|
| 465 |
+
"step": 23660
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 6.61,
|
| 469 |
+
"learning_rate": 7.441419973726821e-05,
|
| 470 |
+
"loss": 0.0006,
|
| 471 |
+
"step": 24024
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 6.71,
|
| 475 |
+
"learning_rate": 7.385818592857361e-05,
|
| 476 |
+
"loss": 0.0008,
|
| 477 |
+
"step": 24388
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 6.81,
|
| 481 |
+
"learning_rate": 7.330217211987902e-05,
|
| 482 |
"loss": 0.0005,
|
| 483 |
+
"step": 24752
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.91,
|
| 487 |
+
"learning_rate": 7.274615831118443e-05,
|
| 488 |
+
"loss": 0.0006,
|
| 489 |
+
"step": 25116
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 8.367381951757125e-07,
|
| 494 |
"eval_max_distance": 0,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 2.3096,
|
| 497 |
+
"eval_samples_per_second": 21.649,
|
| 498 |
+
"eval_steps_per_second": 0.866,
|
| 499 |
+
"step": 25459
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.01,
|
| 503 |
+
"learning_rate": 7.219014450248985e-05,
|
| 504 |
+
"loss": 0.0006,
|
| 505 |
+
"step": 25480
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.11,
|
| 509 |
+
"learning_rate": 7.163413069379525e-05,
|
| 510 |
+
"loss": 0.0007,
|
| 511 |
+
"step": 25844
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.21,
|
| 515 |
+
"learning_rate": 7.107811688510066e-05,
|
| 516 |
"loss": 0.0005,
|
| 517 |
+
"step": 26208
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.31,
|
| 521 |
+
"learning_rate": 7.052210307640608e-05,
|
| 522 |
"loss": 0.0005,
|
| 523 |
+
"step": 26572
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.41,
|
| 527 |
+
"learning_rate": 6.996608926771148e-05,
|
| 528 |
+
"loss": 0.0006,
|
| 529 |
+
"step": 26936
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.51,
|
| 533 |
+
"learning_rate": 6.94100754590169e-05,
|
| 534 |
"loss": 0.0004,
|
| 535 |
+
"step": 27300
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 7.61,
|
| 539 |
+
"learning_rate": 6.885406165032231e-05,
|
| 540 |
+
"loss": 0.0006,
|
| 541 |
+
"step": 27664
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.71,
|
| 545 |
+
"learning_rate": 6.829804784162772e-05,
|
| 546 |
+
"loss": 0.0005,
|
| 547 |
+
"step": 28028
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 7.81,
|
| 551 |
+
"learning_rate": 6.774203403293313e-05,
|
| 552 |
+
"loss": 0.0006,
|
| 553 |
+
"step": 28392
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 7.91,
|
| 557 |
+
"learning_rate": 6.718602022423855e-05,
|
| 558 |
+
"loss": 0.0007,
|
| 559 |
+
"step": 28756
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 7.714121466051438e-07,
|
| 564 |
"eval_max_distance": 0,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 2.3368,
|
| 567 |
+
"eval_samples_per_second": 21.397,
|
| 568 |
+
"eval_steps_per_second": 0.856,
|
| 569 |
+
"step": 29096
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 8.01,
|
| 573 |
+
"learning_rate": 6.663000641554395e-05,
|
| 574 |
+
"loss": 0.0006,
|
| 575 |
+
"step": 29120
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.11,
|
| 579 |
+
"learning_rate": 6.607399260684935e-05,
|
| 580 |
+
"loss": 0.0004,
|
| 581 |
+
"step": 29484
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 8.21,
|
| 585 |
+
"learning_rate": 6.551797879815477e-05,
|
| 586 |
+
"loss": 0.0006,
|
| 587 |
+
"step": 29848
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 8.31,
|
| 591 |
+
"learning_rate": 6.496196498946018e-05,
|
| 592 |
"loss": 0.0005,
|
| 593 |
+
"step": 30212
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.41,
|
| 597 |
+
"learning_rate": 6.440595118076558e-05,
|
| 598 |
+
"loss": 0.0006,
|
| 599 |
+
"step": 30576
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.51,
|
| 603 |
+
"learning_rate": 6.3849937372071e-05,
|
| 604 |
"loss": 0.0005,
|
| 605 |
+
"step": 30940
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 8.61,
|
| 609 |
+
"learning_rate": 6.329392356337642e-05,
|
| 610 |
+
"loss": 0.0004,
|
| 611 |
+
"step": 31304
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 8.71,
|
| 615 |
+
"learning_rate": 6.273790975468182e-05,
|
| 616 |
"loss": 0.0005,
|
| 617 |
+
"step": 31668
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 8.81,
|
| 621 |
+
"learning_rate": 6.218189594598723e-05,
|
| 622 |
"loss": 0.0005,
|
| 623 |
+
"step": 32032
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 8.91,
|
| 627 |
+
"learning_rate": 6.162588213729265e-05,
|
| 628 |
+
"loss": 0.0006,
|
| 629 |
+
"step": 32396
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 7.54007260184153e-07,
|
| 634 |
"eval_max_distance": 0,
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 2.3672,
|
| 637 |
+
"eval_samples_per_second": 21.122,
|
| 638 |
+
"eval_steps_per_second": 0.845,
|
| 639 |
+
"step": 32733
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 9.01,
|
| 643 |
+
"learning_rate": 6.106986832859805e-05,
|
| 644 |
"loss": 0.0005,
|
| 645 |
+
"step": 32760
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 9.11,
|
| 649 |
+
"learning_rate": 6.051385451990347e-05,
|
| 650 |
+
"loss": 0.0006,
|
| 651 |
+
"step": 33124
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 9.21,
|
| 655 |
+
"learning_rate": 5.9957840711208876e-05,
|
| 656 |
+
"loss": 0.0005,
|
| 657 |
+
"step": 33488
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 9.31,
|
| 661 |
+
"learning_rate": 5.940182690251429e-05,
|
| 662 |
"loss": 0.0005,
|
| 663 |
+
"step": 33852
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 9.41,
|
| 667 |
+
"learning_rate": 5.884581309381969e-05,
|
| 668 |
+
"loss": 0.0005,
|
| 669 |
+
"step": 34216
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 9.51,
|
| 673 |
+
"learning_rate": 5.82897992851251e-05,
|
| 674 |
"loss": 0.0005,
|
| 675 |
+
"step": 34580
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 9.61,
|
| 679 |
+
"learning_rate": 5.773378547643051e-05,
|
| 680 |
+
"loss": 0.0004,
|
| 681 |
+
"step": 34944
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.71,
|
| 685 |
+
"learning_rate": 5.717777166773593e-05,
|
| 686 |
+
"loss": 0.0004,
|
| 687 |
+
"step": 35308
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 9.81,
|
| 691 |
+
"learning_rate": 5.6621757859041336e-05,
|
| 692 |
"loss": 0.0005,
|
| 693 |
+
"step": 35672
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 9.91,
|
| 697 |
+
"learning_rate": 5.6065744050346745e-05,
|
| 698 |
"loss": 0.0004,
|
| 699 |
+
"step": 36036
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 1.4673248642793624e-06,
|
| 704 |
"eval_max_distance": 0,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 2.3769,
|
| 707 |
+
"eval_samples_per_second": 21.036,
|
| 708 |
+
"eval_steps_per_second": 0.841,
|
| 709 |
+
"step": 36370
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 10.01,
|
| 713 |
+
"learning_rate": 5.550973024165216e-05,
|
| 714 |
"loss": 0.0005,
|
| 715 |
+
"step": 36400
|
| 716 |
},
|
| 717 |
{
|
| 718 |
+
"epoch": 10.11,
|
| 719 |
+
"learning_rate": 5.495371643295757e-05,
|
| 720 |
+
"loss": 0.0005,
|
| 721 |
+
"step": 36764
|
| 722 |
},
|
| 723 |
{
|
| 724 |
+
"epoch": 10.21,
|
| 725 |
+
"learning_rate": 5.439770262426298e-05,
|
| 726 |
"loss": 0.0005,
|
| 727 |
+
"step": 37128
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 10.31,
|
| 731 |
+
"learning_rate": 5.3841688815568394e-05,
|
| 732 |
+
"loss": 0.0004,
|
| 733 |
+
"step": 37492
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"epoch": 10.41,
|
| 737 |
+
"learning_rate": 5.32856750068738e-05,
|
| 738 |
"loss": 0.0005,
|
| 739 |
+
"step": 37856
|
| 740 |
},
|
| 741 |
{
|
| 742 |
+
"epoch": 10.51,
|
| 743 |
+
"learning_rate": 5.272966119817921e-05,
|
| 744 |
"loss": 0.0004,
|
| 745 |
+
"step": 38220
|
| 746 |
},
|
| 747 |
{
|
| 748 |
+
"epoch": 10.61,
|
| 749 |
+
"learning_rate": 5.217364738948463e-05,
|
| 750 |
"loss": 0.0005,
|
| 751 |
+
"step": 38584
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 10.71,
|
| 755 |
+
"learning_rate": 5.161763358079002e-05,
|
| 756 |
+
"loss": 0.0005,
|
| 757 |
+
"step": 38948
|
| 758 |
},
|
| 759 |
{
|
| 760 |
+
"epoch": 10.81,
|
| 761 |
+
"learning_rate": 5.106161977209544e-05,
|
| 762 |
+
"loss": 0.0004,
|
| 763 |
+
"step": 39312
|
| 764 |
},
|
| 765 |
{
|
| 766 |
+
"epoch": 10.91,
|
| 767 |
+
"learning_rate": 5.050560596340085e-05,
|
| 768 |
"loss": 0.0005,
|
| 769 |
+
"step": 39676
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 8.162444373738253e-07,
|
| 774 |
"eval_max_distance": 0,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 2.3085,
|
| 777 |
+
"eval_samples_per_second": 21.66,
|
| 778 |
+
"eval_steps_per_second": 0.866,
|
| 779 |
+
"step": 40007
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 11.01,
|
| 783 |
+
"learning_rate": 4.9949592154706257e-05,
|
| 784 |
+
"loss": 0.0005,
|
| 785 |
+
"step": 40040
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 11.11,
|
| 789 |
+
"learning_rate": 4.939357834601167e-05,
|
| 790 |
"loss": 0.0004,
|
| 791 |
+
"step": 40404
|
| 792 |
},
|
| 793 |
{
|
| 794 |
+
"epoch": 11.21,
|
| 795 |
+
"learning_rate": 4.883756453731708e-05,
|
| 796 |
+
"loss": 0.0004,
|
| 797 |
+
"step": 40768
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 11.31,
|
| 801 |
+
"learning_rate": 4.828155072862249e-05,
|
| 802 |
"loss": 0.0004,
|
| 803 |
+
"step": 41132
|
| 804 |
},
|
| 805 |
{
|
| 806 |
+
"epoch": 11.41,
|
| 807 |
+
"learning_rate": 4.7725536919927906e-05,
|
| 808 |
"loss": 0.0005,
|
| 809 |
+
"step": 41496
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 11.51,
|
| 813 |
+
"learning_rate": 4.7169523111233314e-05,
|
| 814 |
+
"loss": 0.0005,
|
| 815 |
+
"step": 41860
|
| 816 |
},
|
| 817 |
{
|
| 818 |
+
"epoch": 11.61,
|
| 819 |
+
"learning_rate": 4.661350930253873e-05,
|
| 820 |
+
"loss": 0.0005,
|
| 821 |
+
"step": 42224
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 11.71,
|
| 825 |
+
"learning_rate": 4.605749549384413e-05,
|
| 826 |
+
"loss": 0.0004,
|
| 827 |
+
"step": 42588
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 11.81,
|
| 831 |
+
"learning_rate": 4.550148168514954e-05,
|
| 832 |
"loss": 0.0004,
|
| 833 |
+
"step": 42952
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 11.91,
|
| 837 |
+
"learning_rate": 4.494546787645496e-05,
|
| 838 |
"loss": 0.0004,
|
| 839 |
+
"step": 43316
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 1.4554426570612122e-06,
|
| 844 |
"eval_max_distance": 0,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 2.31,
|
| 847 |
+
"eval_samples_per_second": 21.645,
|
| 848 |
+
"eval_steps_per_second": 0.866,
|
| 849 |
+
"step": 43644
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 12.01,
|
| 853 |
+
"learning_rate": 4.4389454067760366e-05,
|
| 854 |
+
"loss": 0.0003,
|
| 855 |
+
"step": 43680
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 12.11,
|
| 859 |
+
"learning_rate": 4.3833440259065775e-05,
|
| 860 |
"loss": 0.0004,
|
| 861 |
+
"step": 44044
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 12.21,
|
| 865 |
+
"learning_rate": 4.327742645037119e-05,
|
| 866 |
+
"loss": 0.0003,
|
| 867 |
+
"step": 44408
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 12.31,
|
| 871 |
+
"learning_rate": 4.27214126416766e-05,
|
| 872 |
"loss": 0.0004,
|
| 873 |
+
"step": 44772
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 12.41,
|
| 877 |
+
"learning_rate": 4.216539883298201e-05,
|
| 878 |
"loss": 0.0004,
|
| 879 |
+
"step": 45136
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 12.51,
|
| 883 |
+
"learning_rate": 4.160938502428742e-05,
|
| 884 |
"loss": 0.0004,
|
| 885 |
+
"step": 45500
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 12.61,
|
| 889 |
+
"learning_rate": 4.1053371215592826e-05,
|
| 890 |
+
"loss": 0.0004,
|
| 891 |
+
"step": 45864
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 12.71,
|
| 895 |
+
"learning_rate": 4.049735740689824e-05,
|
| 896 |
+
"loss": 0.0005,
|
| 897 |
+
"step": 46228
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 12.81,
|
| 901 |
+
"learning_rate": 3.994134359820365e-05,
|
| 902 |
+
"loss": 0.0005,
|
| 903 |
+
"step": 46592
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 12.91,
|
| 907 |
+
"learning_rate": 3.938532978950906e-05,
|
| 908 |
"loss": 0.0004,
|
| 909 |
+
"step": 46956
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 8.021904704946792e-07,
|
| 914 |
"eval_max_distance": 0,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 2.3634,
|
| 917 |
+
"eval_samples_per_second": 21.156,
|
| 918 |
+
"eval_steps_per_second": 0.846,
|
| 919 |
+
"step": 47281
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 13.01,
|
| 923 |
+
"learning_rate": 3.882931598081447e-05,
|
| 924 |
+
"loss": 0.0003,
|
| 925 |
+
"step": 47320
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 13.11,
|
| 929 |
+
"learning_rate": 3.827330217211988e-05,
|
| 930 |
"loss": 0.0004,
|
| 931 |
+
"step": 47684
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 13.21,
|
| 935 |
+
"learning_rate": 3.771728836342529e-05,
|
| 936 |
"loss": 0.0004,
|
| 937 |
+
"step": 48048
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 13.31,
|
| 941 |
+
"learning_rate": 3.71612745547307e-05,
|
| 942 |
"loss": 0.0004,
|
| 943 |
+
"step": 48412
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 13.41,
|
| 947 |
+
"learning_rate": 3.660526074603611e-05,
|
| 948 |
+
"loss": 0.0004,
|
| 949 |
+
"step": 48776
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 13.51,
|
| 953 |
+
"learning_rate": 3.6049246937341526e-05,
|
| 954 |
+
"loss": 0.0004,
|
| 955 |
+
"step": 49140
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 13.61,
|
| 959 |
+
"learning_rate": 3.5493233128646935e-05,
|
| 960 |
"loss": 0.0004,
|
| 961 |
+
"step": 49504
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 13.71,
|
| 965 |
+
"learning_rate": 3.4937219319952344e-05,
|
| 966 |
"loss": 0.0004,
|
| 967 |
+
"step": 49868
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 13.81,
|
| 971 |
+
"learning_rate": 3.438120551125775e-05,
|
| 972 |
"loss": 0.0004,
|
| 973 |
+
"step": 50232
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 13.91,
|
| 977 |
+
"learning_rate": 3.382519170256316e-05,
|
| 978 |
+
"loss": 0.0005,
|
| 979 |
+
"step": 50596
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 6.187271992530441e-07,
|
| 984 |
"eval_max_distance": 0,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 2.322,
|
| 987 |
+
"eval_samples_per_second": 21.533,
|
| 988 |
+
"eval_steps_per_second": 0.861,
|
| 989 |
+
"step": 50918
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 14.01,
|
| 993 |
+
"learning_rate": 3.326917789386858e-05,
|
| 994 |
+
"loss": 0.0005,
|
| 995 |
+
"step": 50960
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 14.11,
|
| 999 |
+
"learning_rate": 3.2713164085173986e-05,
|
| 1000 |
"loss": 0.0005,
|
| 1001 |
+
"step": 51324
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 14.21,
|
| 1005 |
+
"learning_rate": 3.2157150276479395e-05,
|
| 1006 |
"loss": 0.0003,
|
| 1007 |
+
"step": 51688
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 14.31,
|
| 1011 |
+
"learning_rate": 3.1601136467784804e-05,
|
| 1012 |
"loss": 0.0004,
|
| 1013 |
+
"step": 52052
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 14.41,
|
| 1017 |
+
"learning_rate": 3.104512265909021e-05,
|
| 1018 |
"loss": 0.0004,
|
| 1019 |
+
"step": 52416
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 14.51,
|
| 1023 |
+
"learning_rate": 3.0489108850395625e-05,
|
| 1024 |
"loss": 0.0004,
|
| 1025 |
+
"step": 52780
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 14.61,
|
| 1029 |
+
"learning_rate": 2.9933095041701037e-05,
|
| 1030 |
+
"loss": 0.0004,
|
| 1031 |
+
"step": 53144
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 14.71,
|
| 1035 |
+
"learning_rate": 2.937708123300645e-05,
|
| 1036 |
+
"loss": 0.0004,
|
| 1037 |
+
"step": 53508
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 14.81,
|
| 1041 |
+
"learning_rate": 2.882106742431186e-05,
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
+
"step": 53872
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 14.91,
|
| 1047 |
+
"learning_rate": 2.826505361561727e-05,
|
| 1048 |
"loss": 0.0004,
|
| 1049 |
+
"step": 54236
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 4.629501972885919e-07,
|
| 1054 |
"eval_max_distance": 0,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 2.3761,
|
| 1057 |
+
"eval_samples_per_second": 21.043,
|
| 1058 |
+
"eval_steps_per_second": 0.842,
|
| 1059 |
+
"step": 54555
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
+
"epoch": 15.01,
|
| 1063 |
+
"learning_rate": 2.7709039806922676e-05,
|
| 1064 |
+
"loss": 0.0005,
|
| 1065 |
+
"step": 54600
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 15.11,
|
| 1069 |
+
"learning_rate": 2.715302599822809e-05,
|
| 1070 |
+
"loss": 0.0003,
|
| 1071 |
+
"step": 54964
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 15.21,
|
| 1075 |
+
"learning_rate": 2.6597012189533497e-05,
|
| 1076 |
"loss": 0.0003,
|
| 1077 |
+
"step": 55328
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
+
"epoch": 15.31,
|
| 1081 |
+
"learning_rate": 2.604099838083891e-05,
|
| 1082 |
"loss": 0.0003,
|
| 1083 |
+
"step": 55692
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
+
"epoch": 15.41,
|
| 1087 |
+
"learning_rate": 2.5484984572144322e-05,
|
| 1088 |
"loss": 0.0003,
|
| 1089 |
+
"step": 56056
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 15.51,
|
| 1093 |
+
"learning_rate": 2.492897076344973e-05,
|
| 1094 |
"loss": 0.0003,
|
| 1095 |
+
"step": 56420
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 15.61,
|
| 1099 |
+
"learning_rate": 2.437295695475514e-05,
|
| 1100 |
"loss": 0.0004,
|
| 1101 |
+
"step": 56784
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 15.71,
|
| 1105 |
+
"learning_rate": 2.3816943146060552e-05,
|
| 1106 |
+
"loss": 0.0003,
|
| 1107 |
+
"step": 57148
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 15.81,
|
| 1111 |
+
"learning_rate": 2.326092933736596e-05,
|
| 1112 |
+
"loss": 0.0004,
|
| 1113 |
+
"step": 57512
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 15.91,
|
| 1117 |
+
"learning_rate": 2.2704915528671373e-05,
|
| 1118 |
"loss": 0.0004,
|
| 1119 |
+
"step": 57876
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 4.1432366515437025e-07,
|
| 1124 |
"eval_max_distance": 0,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 2.3527,
|
| 1127 |
+
"eval_samples_per_second": 21.253,
|
| 1128 |
+
"eval_steps_per_second": 0.85,
|
| 1129 |
+
"step": 58192
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 16.01,
|
| 1133 |
+
"learning_rate": 2.2148901719976782e-05,
|
| 1134 |
"loss": 0.0004,
|
| 1135 |
+
"step": 58240
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 16.11,
|
| 1139 |
+
"learning_rate": 2.1592887911282194e-05,
|
| 1140 |
"loss": 0.0004,
|
| 1141 |
+
"step": 58604
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 16.21,
|
| 1145 |
+
"learning_rate": 2.1036874102587603e-05,
|
| 1146 |
+
"loss": 0.0004,
|
| 1147 |
+
"step": 58968
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 16.31,
|
| 1151 |
+
"learning_rate": 2.0480860293893016e-05,
|
| 1152 |
"loss": 0.0004,
|
| 1153 |
+
"step": 59332
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 16.41,
|
| 1157 |
+
"learning_rate": 1.9924846485198424e-05,
|
| 1158 |
"loss": 0.0003,
|
| 1159 |
+
"step": 59696
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 16.51,
|
| 1163 |
+
"learning_rate": 1.9368832676503833e-05,
|
| 1164 |
+
"loss": 0.0004,
|
| 1165 |
+
"step": 60060
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 16.61,
|
| 1169 |
+
"learning_rate": 1.8812818867809246e-05,
|
| 1170 |
"loss": 0.0003,
|
| 1171 |
+
"step": 60424
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 16.71,
|
| 1175 |
+
"learning_rate": 1.8256805059114658e-05,
|
| 1176 |
"loss": 0.0004,
|
| 1177 |
+
"step": 60788
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 16.81,
|
| 1181 |
+
"learning_rate": 1.7700791250420067e-05,
|
| 1182 |
+
"loss": 0.0005,
|
| 1183 |
+
"step": 61152
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 16.91,
|
| 1187 |
+
"learning_rate": 1.7144777441725476e-05,
|
| 1188 |
+
"loss": 0.0004,
|
| 1189 |
+
"step": 61516
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 6.78707863244199e-07,
|
| 1194 |
"eval_max_distance": 0,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 2.3415,
|
| 1197 |
+
"eval_samples_per_second": 21.354,
|
| 1198 |
+
"eval_steps_per_second": 0.854,
|
| 1199 |
+
"step": 61829
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
+
"epoch": 17.01,
|
| 1203 |
+
"learning_rate": 1.6588763633030888e-05,
|
| 1204 |
"loss": 0.0004,
|
| 1205 |
+
"step": 61880
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
+
"epoch": 17.11,
|
| 1209 |
+
"learning_rate": 1.6032749824336297e-05,
|
| 1210 |
"loss": 0.0003,
|
| 1211 |
+
"step": 62244
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
+
"epoch": 17.21,
|
| 1215 |
+
"learning_rate": 1.547673601564171e-05,
|
| 1216 |
"loss": 0.0003,
|
| 1217 |
+
"step": 62608
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 17.31,
|
| 1221 |
+
"learning_rate": 1.4920722206947118e-05,
|
| 1222 |
+
"loss": 0.0003,
|
| 1223 |
+
"step": 62972
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"epoch": 17.41,
|
| 1227 |
+
"learning_rate": 1.436470839825253e-05,
|
| 1228 |
"loss": 0.0003,
|
| 1229 |
+
"step": 63336
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
+
"epoch": 17.51,
|
| 1233 |
+
"learning_rate": 1.3808694589557939e-05,
|
| 1234 |
"loss": 0.0004,
|
| 1235 |
+
"step": 63700
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
+
"epoch": 17.61,
|
| 1239 |
+
"learning_rate": 1.325268078086335e-05,
|
| 1240 |
+
"loss": 0.0004,
|
| 1241 |
+
"step": 64064
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 17.71,
|
| 1245 |
+
"learning_rate": 1.269666697216876e-05,
|
| 1246 |
"loss": 0.0004,
|
| 1247 |
+
"step": 64428
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
+
"epoch": 17.81,
|
| 1251 |
+
"learning_rate": 1.2140653163474171e-05,
|
| 1252 |
"loss": 0.0003,
|
| 1253 |
+
"step": 64792
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 17.91,
|
| 1257 |
+
"learning_rate": 1.1584639354779581e-05,
|
| 1258 |
+
"loss": 0.0004,
|
| 1259 |
+
"step": 65156
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 4.647758657938539e-07,
|
| 1264 |
"eval_max_distance": 0,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 2.3851,
|
| 1267 |
+
"eval_samples_per_second": 20.964,
|
| 1268 |
+
"eval_steps_per_second": 0.839,
|
| 1269 |
+
"step": 65466
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 18.01,
|
| 1273 |
+
"learning_rate": 1.1028625546084992e-05,
|
| 1274 |
+
"loss": 0.0003,
|
| 1275 |
+
"step": 65520
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 18.11,
|
| 1279 |
+
"learning_rate": 1.0472611737390403e-05,
|
| 1280 |
+
"loss": 0.0003,
|
| 1281 |
+
"step": 65884
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 18.22,
|
| 1285 |
+
"learning_rate": 9.916597928695811e-06,
|
| 1286 |
+
"loss": 0.0005,
|
| 1287 |
+
"step": 66248
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 18.32,
|
| 1291 |
+
"learning_rate": 9.360584120001222e-06,
|
| 1292 |
"loss": 0.0003,
|
| 1293 |
+
"step": 66612
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 18.42,
|
| 1297 |
+
"learning_rate": 8.804570311306633e-06,
|
| 1298 |
+
"loss": 0.0003,
|
| 1299 |
+
"step": 66976
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 18.52,
|
| 1303 |
+
"learning_rate": 8.248556502612043e-06,
|
| 1304 |
+
"loss": 0.0004,
|
| 1305 |
+
"step": 67340
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
+
"epoch": 18.62,
|
| 1309 |
+
"learning_rate": 7.692542693917454e-06,
|
| 1310 |
+
"loss": 0.0004,
|
| 1311 |
+
"step": 67704
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
+
"epoch": 18.72,
|
| 1315 |
+
"learning_rate": 7.1365288852228635e-06,
|
| 1316 |
"loss": 0.0004,
|
| 1317 |
+
"step": 68068
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
+
"epoch": 18.82,
|
| 1321 |
+
"learning_rate": 6.580515076528275e-06,
|
| 1322 |
"loss": 0.0004,
|
| 1323 |
+
"step": 68432
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 18.92,
|
| 1327 |
+
"learning_rate": 6.024501267833685e-06,
|
| 1328 |
+
"loss": 0.0004,
|
| 1329 |
+
"step": 68796
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 6.43872112959798e-07,
|
| 1334 |
"eval_max_distance": 0,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
+
"eval_runtime": 2.3968,
|
| 1337 |
+
"eval_samples_per_second": 20.861,
|
| 1338 |
+
"eval_steps_per_second": 0.834,
|
| 1339 |
+
"step": 69103
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
+
"epoch": 19.02,
|
| 1343 |
+
"learning_rate": 5.468487459139095e-06,
|
| 1344 |
"loss": 0.0003,
|
| 1345 |
+
"step": 69160
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
+
"epoch": 19.12,
|
| 1349 |
+
"learning_rate": 4.912473650444506e-06,
|
| 1350 |
"loss": 0.0003,
|
| 1351 |
+
"step": 69524
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"epoch": 19.22,
|
| 1355 |
+
"learning_rate": 4.3564598417499164e-06,
|
| 1356 |
"loss": 0.0004,
|
| 1357 |
+
"step": 69888
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
+
"epoch": 19.32,
|
| 1361 |
+
"learning_rate": 3.8004460330553266e-06,
|
| 1362 |
"loss": 0.0003,
|
| 1363 |
+
"step": 70252
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 19.42,
|
| 1367 |
+
"learning_rate": 3.244432224360737e-06,
|
| 1368 |
+
"loss": 0.0003,
|
| 1369 |
+
"step": 70616
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 19.52,
|
| 1373 |
+
"learning_rate": 2.6884184156661473e-06,
|
| 1374 |
"loss": 0.0004,
|
| 1375 |
+
"step": 70980
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 19.62,
|
| 1379 |
+
"learning_rate": 2.132404606971558e-06,
|
| 1380 |
+
"loss": 0.0003,
|
| 1381 |
+
"step": 71344
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 19.72,
|
| 1385 |
+
"learning_rate": 1.5763907982769683e-06,
|
| 1386 |
"loss": 0.0003,
|
| 1387 |
+
"step": 71708
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 19.82,
|
| 1391 |
+
"learning_rate": 1.0203769895823786e-06,
|
| 1392 |
+
"loss": 0.0004,
|
| 1393 |
+
"step": 72072
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 19.92,
|
| 1397 |
+
"learning_rate": 4.6436318088778905e-07,
|
| 1398 |
"loss": 0.0004,
|
| 1399 |
+
"step": 72436
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 7.036084070932702e-07,
|
| 1404 |
"eval_max_distance": 0,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 2.3249,
|
| 1407 |
+
"eval_samples_per_second": 21.506,
|
| 1408 |
+
"eval_steps_per_second": 0.86,
|
| 1409 |
+
"step": 72740
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
+
"step": 72740,
|
| 1414 |
+
"total_flos": 4.361497895702938e+16,
|
| 1415 |
+
"train_loss": 0.0006492722850091394,
|
| 1416 |
+
"train_runtime": 7118.3904,
|
| 1417 |
+
"train_samples_per_second": 306.491,
|
| 1418 |
+
"train_steps_per_second": 10.219
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
+
"logging_steps": 364,
|
| 1422 |
+
"max_steps": 72740,
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 728,
|
| 1425 |
+
"total_flos": 4.361497895702938e+16,
|
| 1426 |
"trial_name": null,
|
| 1427 |
"trial_params": null
|
| 1428 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4091
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efa11b33c5881932f7e5525ef2d0553bd74534e69955ef581a50e49241b464b
|
| 3 |
size 4091
|