End of training
Browse files- README.md +24 -24
- pytorch_model.bin +1 -1
- trainer_state.json +868 -868
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
- Mean Distance: 0
|
| 20 |
-
- Max Distance:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -47,28 +47,28 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
-
| Training Loss | Epoch | Step
|
| 51 |
-
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.0006 | 9.0 |
|
| 61 |
-
| 0.0006 | 10.0 |
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.0005 | 14.0 |
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.0004 | 16.0 |
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.0004 | 18.0 |
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0169
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 1
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Max Distance | Mean Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:------------:|:-------------:|
|
| 52 |
+
| 0.001 | 1.0 | 13726 | 0.0114 | 5 | 0 |
|
| 53 |
+
| 0.0009 | 2.0 | 27452 | 0.0143 | 3 | 0 |
|
| 54 |
+
| 0.0008 | 3.0 | 41178 | 0.0145 | 3 | 0 |
|
| 55 |
+
| 0.0009 | 4.0 | 54904 | 0.0098 | 1 | 0 |
|
| 56 |
+
| 0.0007 | 5.0 | 68630 | 0.0130 | 2 | 0 |
|
| 57 |
+
| 0.0008 | 6.0 | 82356 | 0.0153 | 2 | 0 |
|
| 58 |
+
| 0.0007 | 7.0 | 96082 | 0.0128 | 2 | 0 |
|
| 59 |
+
| 0.0006 | 8.0 | 109808 | 0.0130 | 3 | 0 |
|
| 60 |
+
| 0.0006 | 9.0 | 123534 | 0.0158 | 5 | 0 |
|
| 61 |
+
| 0.0006 | 10.0 | 137260 | 0.0151 | 1 | 0 |
|
| 62 |
+
| 0.0005 | 11.0 | 150986 | 0.0167 | 1 | 0 |
|
| 63 |
+
| 0.0005 | 12.0 | 164712 | 0.0145 | 1 | 0 |
|
| 64 |
+
| 0.0005 | 13.0 | 178438 | 0.0160 | 1 | 0 |
|
| 65 |
+
| 0.0005 | 14.0 | 192164 | 0.0157 | 1 | 0 |
|
| 66 |
+
| 0.0004 | 15.0 | 205890 | 0.0157 | 1 | 0 |
|
| 67 |
+
| 0.0004 | 16.0 | 219616 | 0.0173 | 1 | 0 |
|
| 68 |
+
| 0.0004 | 17.0 | 233342 | 0.0159 | 1 | 0 |
|
| 69 |
+
| 0.0004 | 18.0 | 247068 | 0.0168 | 2 | 0 |
|
| 70 |
+
| 0.0004 | 19.0 | 260794 | 0.0168 | 0 | 1 |
|
| 71 |
+
| 0.0004 | 20.0 | 274520 | 0.0169 | 0 | 1 |
|
| 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 sha256:9727576aa431487c27ceb1092c700d9e76b20865987fbc3ac38d6006432aac18
|
| 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":
|
| 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": 0.0014,
|
| 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": 0.
|
| 74 |
-
"eval_max_distance":
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
-
"eval_runtime":
|
| 77 |
-
"eval_samples_per_second":
|
| 78 |
-
"eval_steps_per_second":
|
| 79 |
-
"step":
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
-
"learning_rate": 5.
|
| 84 |
-
"loss": 0.
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 1.
|
| 89 |
-
"learning_rate": 5.
|
| 90 |
"loss": 0.0008,
|
| 91 |
-
"step":
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"epoch": 1.
|
| 95 |
-
"learning_rate": 6.
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"epoch": 1.
|
| 101 |
-
"learning_rate": 6.
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"step":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
-
"epoch": 1.
|
| 107 |
-
"learning_rate": 7.
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch": 1.
|
| 113 |
-
"learning_rate": 7.
|
| 114 |
-
"loss": 0.
|
| 115 |
-
"step":
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 1.
|
| 119 |
-
"learning_rate": 8.
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 1.
|
| 125 |
-
"learning_rate": 8.
|
| 126 |
-
"loss": 0.
|
| 127 |
-
"step":
|
| 128 |
},
|
| 129 |
{
|
| 130 |
-
"epoch": 1.
|
| 131 |
-
"learning_rate": 9.
|
| 132 |
"loss": 0.0008,
|
| 133 |
-
"step":
|
| 134 |
},
|
| 135 |
{
|
| 136 |
-
"epoch": 1.
|
| 137 |
-
"learning_rate": 9.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
"eval_max_distance": 3,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second":
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 2.
|
| 153 |
-
"learning_rate": 9.
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch": 2.
|
| 159 |
-
"learning_rate": 9.
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 2.
|
| 165 |
-
"learning_rate": 9.
|
| 166 |
"loss": 0.0008,
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 2.
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 2.
|
| 177 |
-
"learning_rate": 9.
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 2.
|
| 183 |
-
"learning_rate": 9.
|
| 184 |
-
"loss": 0.
|
| 185 |
-
"step":
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 2.
|
| 189 |
-
"learning_rate": 9.
|
| 190 |
-
"loss": 0.
|
| 191 |
-
"step":
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 2.
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
"loss": 0.0008,
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch": 2.
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch": 2.
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
-
"eval_loss": 0.
|
| 214 |
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second":
|
| 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": 0.0008,
|
| 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.
|
| 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": 0.
|
| 284 |
-
"eval_max_distance":
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
-
"eval_runtime":
|
| 287 |
-
"eval_samples_per_second":
|
| 288 |
-
"eval_steps_per_second":
|
| 289 |
-
"step":
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 4.
|
| 293 |
-
"learning_rate": 8.
|
| 294 |
"loss": 0.0009,
|
| 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.
|
| 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.
|
| 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.
|
| 337 |
-
"step":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch": 4.
|
| 341 |
-
"learning_rate": 8.
|
| 342 |
-
"loss": 0.
|
| 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": 0.
|
| 354 |
-
"eval_max_distance":
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
-
"eval_runtime":
|
| 357 |
-
"eval_samples_per_second":
|
| 358 |
-
"eval_steps_per_second":
|
| 359 |
-
"step":
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 5.
|
| 363 |
-
"learning_rate": 8.
|
| 364 |
-
"loss": 0.
|
| 365 |
-
"step":
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch": 5.
|
| 369 |
-
"learning_rate": 8.
|
| 370 |
-
"loss": 0.
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch": 5.
|
| 375 |
-
"learning_rate": 8.
|
| 376 |
-
"loss": 0.
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 5.
|
| 381 |
-
"learning_rate": 8.
|
| 382 |
"loss": 0.0008,
|
| 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": 0.0007,
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 5.
|
| 399 |
-
"learning_rate": 7.
|
| 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.
|
| 419 |
-
"step":
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
-
"eval_loss": 0.
|
| 424 |
-
"eval_max_distance":
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
-
"eval_runtime":
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second":
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 6.
|
| 433 |
-
"learning_rate": 7.
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch": 6.
|
| 439 |
-
"learning_rate": 7.
|
| 440 |
-
"loss": 0.
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 6.
|
| 445 |
-
"learning_rate": 7.
|
| 446 |
-
"loss": 0.
|
| 447 |
-
"step":
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch": 6.
|
| 451 |
-
"learning_rate": 7.
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 6.
|
| 457 |
-
"learning_rate": 7.
|
| 458 |
"loss": 0.0007,
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 6.
|
| 463 |
-
"learning_rate": 7.
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 6.
|
| 469 |
-
"learning_rate": 7.
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 6.
|
| 475 |
-
"learning_rate": 7.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch": 6.
|
| 481 |
-
"learning_rate": 7.
|
| 482 |
-
"loss": 0.
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch": 6.
|
| 487 |
-
"learning_rate": 7.
|
| 488 |
-
"loss": 0.
|
| 489 |
-
"step":
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
-
"eval_loss": 0.
|
| 494 |
-
"eval_max_distance":
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
-
"eval_runtime":
|
| 497 |
-
"eval_samples_per_second":
|
| 498 |
-
"eval_steps_per_second":
|
| 499 |
-
"step":
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 7.
|
| 503 |
-
"learning_rate": 7.
|
| 504 |
"loss": 0.0007,
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch": 7.
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch": 7.
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
-
"loss": 0.
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 7.
|
| 521 |
-
"learning_rate": 7.
|
| 522 |
-
"loss": 0.
|
| 523 |
-
"step":
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch": 7.
|
| 527 |
-
"learning_rate": 6.
|
| 528 |
"loss": 0.0007,
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch": 7.
|
| 533 |
-
"learning_rate": 6.
|
| 534 |
"loss": 0.0006,
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch": 7.
|
| 539 |
-
"learning_rate": 6.
|
| 540 |
-
"loss": 0.
|
| 541 |
-
"step":
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 7.
|
| 545 |
-
"learning_rate": 6.
|
| 546 |
"loss": 0.0007,
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch": 7.
|
| 551 |
-
"learning_rate": 6.
|
| 552 |
-
"loss": 0.
|
| 553 |
-
"step":
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch": 7.
|
| 557 |
-
"learning_rate": 6.
|
| 558 |
-
"loss": 0.
|
| 559 |
-
"step":
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
-
"eval_loss": 0.
|
| 564 |
"eval_max_distance": 3,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
-
"eval_runtime":
|
| 567 |
-
"eval_samples_per_second":
|
| 568 |
-
"eval_steps_per_second":
|
| 569 |
-
"step":
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch": 8.
|
| 573 |
-
"learning_rate": 6.
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch": 8.
|
| 579 |
-
"learning_rate": 6.
|
| 580 |
"loss": 0.0007,
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
-
"epoch": 8.
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
"loss": 0.0005,
|
| 587 |
-
"step":
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 8.34,
|
| 591 |
-
"learning_rate": 6.478198056212241e-05,
|
| 592 |
-
"loss": 0.0006,
|
| 593 |
-
"step": 7055
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch": 8.
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
"loss": 0.0007,
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
-
"epoch": 8.
|
| 603 |
-
"learning_rate": 6.
|
| 604 |
-
"loss": 0.
|
| 605 |
-
"step":
|
| 606 |
},
|
| 607 |
{
|
| 608 |
-
"epoch": 8.
|
| 609 |
-
"learning_rate": 6.
|
| 610 |
"loss": 0.0006,
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 8.
|
| 615 |
-
"learning_rate": 6.
|
| 616 |
-
"loss": 0.
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch": 8.
|
| 621 |
-
"learning_rate": 6.
|
| 622 |
-
"loss": 0.
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch": 8.
|
| 627 |
-
"learning_rate": 6.
|
| 628 |
"loss": 0.0006,
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
-
"epoch": 9
|
| 633 |
-
"
|
| 634 |
-
"
|
| 635 |
-
"
|
| 636 |
-
"eval_runtime": 29.9284,
|
| 637 |
-
"eval_samples_per_second": 8.687,
|
| 638 |
-
"eval_steps_per_second": 0.601,
|
| 639 |
-
"step": 7614
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 9.
|
| 643 |
-
"
|
| 644 |
-
"
|
| 645 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch": 9.
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch": 9.
|
| 655 |
-
"learning_rate":
|
| 656 |
"loss": 0.0005,
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch": 9.
|
| 661 |
-
"learning_rate": 5.
|
| 662 |
"loss": 0.0006,
|
| 663 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch": 9.
|
| 667 |
-
"learning_rate": 5.
|
| 668 |
"loss": 0.0006,
|
| 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.
|
| 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.
|
| 693 |
-
"step":
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch": 9.
|
| 697 |
-
"learning_rate": 5.
|
| 698 |
"loss": 0.0006,
|
| 699 |
-
"step":
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
-
"eval_loss": 0.
|
| 704 |
-
"eval_max_distance":
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
-
"eval_runtime":
|
| 707 |
-
"eval_samples_per_second":
|
| 708 |
-
"eval_steps_per_second":
|
| 709 |
-
"step":
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 10.
|
| 713 |
-
"learning_rate": 5.
|
| 714 |
-
"loss": 0.
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch": 10.
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
"loss": 0.0006,
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch": 10.
|
| 725 |
-
"learning_rate": 5.
|
| 726 |
-
"loss": 0.
|
| 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.
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch": 10.
|
| 743 |
-
"learning_rate": 5.
|
| 744 |
-
"loss": 0.
|
| 745 |
-
"step":
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch": 10.
|
| 749 |
-
"learning_rate": 5.
|
| 750 |
"loss": 0.0006,
|
| 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.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
-
"eval_loss": 0.
|
| 774 |
-
"eval_max_distance":
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
-
"eval_runtime":
|
| 777 |
-
"eval_samples_per_second":
|
| 778 |
-
"eval_steps_per_second":
|
| 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": 0.0005,
|
| 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.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch": 11.
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
-
"loss": 0.
|
| 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": 0.0005,
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 11.
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
"loss": 0.0005,
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch": 11.
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
-
"loss": 0.
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch": 11.
|
| 837 |
-
"learning_rate": 4.
|
| 838 |
-
"loss": 0.
|
| 839 |
-
"step":
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
-
"eval_loss": 0.
|
| 844 |
-
"eval_max_distance":
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
-
"eval_runtime":
|
| 847 |
-
"eval_samples_per_second":
|
| 848 |
-
"eval_steps_per_second":
|
| 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.
|
| 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.
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch": 12.
|
| 877 |
-
"learning_rate": 4.
|
| 878 |
-
"loss": 0.
|
| 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.
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
-
"eval_loss": 0.
|
| 914 |
-
"eval_max_distance":
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
-
"eval_runtime":
|
| 917 |
-
"eval_samples_per_second":
|
| 918 |
-
"eval_steps_per_second":
|
| 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.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch": 13.
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch": 13.
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
-
"loss": 0.
|
| 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.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch": 13.
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
"loss": 0.0005,
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch": 13.
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch": 13.
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
"loss": 0.0005,
|
| 979 |
-
"step":
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
-
"eval_loss": 0.
|
| 984 |
-
"eval_max_distance":
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
-
"eval_runtime":
|
| 987 |
-
"eval_samples_per_second":
|
| 988 |
-
"eval_steps_per_second":
|
| 989 |
-
"step":
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch": 14.
|
| 993 |
-
"learning_rate": 3.
|
| 994 |
-
"loss": 0.
|
| 995 |
-
"step":
|
| 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": 0.0004,
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch": 14.
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
-
"loss": 0.0005,
|
| 1019 |
-
"step": 12240
|
| 1020 |
-
},
|
| 1021 |
-
{
|
| 1022 |
-
"epoch": 14.57,
|
| 1023 |
-
"learning_rate": 3.0174678224323616e-05,
|
| 1024 |
"loss": 0.0004,
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch": 14.
|
| 1029 |
-
"learning_rate":
|
| 1030 |
"loss": 0.0005,
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch": 14.
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
"loss": 0.0005,
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch": 14.
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
-
"loss": 0.
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch": 14.
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
-
"loss": 0.
|
| 1049 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
-
"eval_loss": 0.
|
| 1054 |
-
"eval_max_distance":
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
-
"eval_runtime":
|
| 1057 |
-
"eval_samples_per_second":
|
| 1058 |
-
"eval_steps_per_second":
|
| 1059 |
-
"step":
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
-
"epoch": 15.
|
| 1063 |
-
"learning_rate": 2.
|
| 1064 |
"loss": 0.0004,
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch": 15.
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
"loss": 0.0004,
|
| 1071 |
-
"step":
|
| 1072 |
-
},
|
| 1073 |
-
{
|
| 1074 |
-
"epoch": 15.27,
|
| 1075 |
-
"learning_rate": 2.626740215392698e-05,
|
| 1076 |
-
"loss": 0.0007,
|
| 1077 |
-
"step": 12920
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch": 15.
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
-
"loss": 0.
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch": 15.
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
-
"loss": 0.
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch": 15.
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
"loss": 0.0004,
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch": 15.
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
"loss": 0.0005,
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch": 15.
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
"loss": 0.0004,
|
| 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": 0.
|
| 1124 |
-
"eval_max_distance":
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
-
"eval_runtime":
|
| 1127 |
-
"eval_samples_per_second":
|
| 1128 |
-
"eval_steps_per_second":
|
| 1129 |
-
"step":
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch": 16.
|
| 1133 |
-
"learning_rate": 2.
|
| 1134 |
-
"loss": 0.
|
| 1135 |
-
"step":
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch": 16.
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
-
"loss": 0.
|
| 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.
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch": 16.
|
| 1157 |
-
"learning_rate": 1.
|
| 1158 |
"loss": 0.0004,
|
| 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": 0.0004,
|
| 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": 0.0004,
|
| 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": 0.
|
| 1194 |
-
"eval_max_distance":
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
-
"eval_runtime":
|
| 1197 |
-
"eval_samples_per_second":
|
| 1198 |
-
"eval_steps_per_second":
|
| 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.
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch": 17.
|
| 1215 |
-
"learning_rate": 1.
|
| 1216 |
-
"loss": 0.
|
| 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.
|
| 1229 |
-
"step":
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
-
"epoch": 17.
|
| 1233 |
-
"learning_rate": 1.
|
| 1234 |
-
"loss": 0.
|
| 1235 |
-
"step":
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch": 17.
|
| 1239 |
-
"learning_rate": 1.
|
| 1240 |
-
"loss": 0.
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch": 17.
|
| 1245 |
-
"learning_rate": 1.
|
| 1246 |
-
"loss": 0.
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch": 17.
|
| 1251 |
-
"learning_rate": 1.
|
| 1252 |
-
"loss": 0.
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch": 17.
|
| 1257 |
-
"learning_rate": 1.
|
| 1258 |
"loss": 0.0004,
|
| 1259 |
-
"step":
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
-
"eval_loss": 0.
|
| 1264 |
-
"eval_max_distance":
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
-
"eval_runtime":
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second":
|
| 1269 |
-
"step":
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch": 18.
|
| 1273 |
-
"learning_rate": 1.
|
| 1274 |
-
"loss": 0.0003,
|
| 1275 |
-
"step": 15300
|
| 1276 |
-
},
|
| 1277 |
-
{
|
| 1278 |
-
"epoch": 18.19,
|
| 1279 |
-
"learning_rate": 1.0080115576569477e-05,
|
| 1280 |
"loss": 0.0004,
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch": 18.
|
| 1285 |
-
"learning_rate":
|
| 1286 |
"loss": 0.0004,
|
| 1287 |
-
"step":
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch": 18.
|
| 1291 |
-
"learning_rate":
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch": 18.
|
| 1297 |
-
"learning_rate":
|
| 1298 |
"loss": 0.0003,
|
| 1299 |
-
"step":
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch": 18.
|
| 1303 |
-
"learning_rate":
|
| 1304 |
"loss": 0.0004,
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch": 18.
|
| 1309 |
-
"learning_rate":
|
| 1310 |
"loss": 0.0004,
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch": 18.
|
| 1315 |
-
"learning_rate":
|
| 1316 |
"loss": 0.0004,
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch": 18.
|
| 1321 |
-
"learning_rate":
|
| 1322 |
"loss": 0.0004,
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18.
|
| 1327 |
-
"learning_rate":
|
| 1328 |
"loss": 0.0003,
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
-
"epoch":
|
| 1333 |
-
"
|
| 1334 |
-
"
|
| 1335 |
-
"
|
| 1336 |
-
"eval_runtime": 29.5322,
|
| 1337 |
-
"eval_samples_per_second": 8.804,
|
| 1338 |
-
"eval_steps_per_second": 0.61,
|
| 1339 |
-
"step": 16074
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
-
"epoch": 19.
|
| 1343 |
-
"
|
| 1344 |
-
"
|
| 1345 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
-
"epoch": 19.
|
| 1349 |
-
"learning_rate":
|
| 1350 |
"loss": 0.0004,
|
| 1351 |
-
"step":
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"epoch": 19.
|
| 1355 |
-
"learning_rate":
|
| 1356 |
-
"loss": 0.
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch": 19.
|
| 1361 |
-
"learning_rate":
|
| 1362 |
-
"loss": 0.
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch": 19.
|
| 1367 |
-
"learning_rate":
|
| 1368 |
-
"loss": 0.
|
| 1369 |
-
"step":
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch": 19.
|
| 1373 |
-
"learning_rate":
|
| 1374 |
-
"loss": 0.
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch": 19.
|
| 1379 |
-
"learning_rate":
|
| 1380 |
"loss": 0.0004,
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch": 19.
|
| 1385 |
-
"learning_rate":
|
| 1386 |
"loss": 0.0003,
|
| 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.
|
| 1399 |
-
"step":
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
-
"eval_loss": 0.
|
| 1404 |
-
"eval_max_distance":
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
-
"eval_runtime":
|
| 1407 |
-
"eval_samples_per_second":
|
| 1408 |
-
"eval_steps_per_second":
|
| 1409 |
-
"step":
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
-
"step":
|
| 1414 |
-
"total_flos":
|
| 1415 |
-
"train_loss":
|
| 1416 |
-
"train_runtime":
|
| 1417 |
-
"train_samples_per_second":
|
| 1418 |
-
"train_steps_per_second":
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
-
"logging_steps":
|
| 1422 |
-
"max_steps":
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
-
"save_steps":
|
| 1425 |
-
"total_flos":
|
| 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": 274520,
|
| 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": 3.6427218417601638e-09,
|
| 14 |
+
"loss": 0.0,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.001457088736705e-06,
|
| 20 |
+
"loss": 0.0052,
|
| 21 |
+
"step": 1373
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.000291417747341e-05,
|
| 26 |
+
"loss": 0.0041,
|
| 27 |
+
"step": 2746
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.5004371266210113e-05,
|
| 32 |
+
"loss": 0.0025,
|
| 33 |
+
"step": 4119
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.000582835494682e-05,
|
| 38 |
+
"loss": 0.002,
|
| 39 |
+
"step": 5492
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.500728544368352e-05,
|
| 44 |
+
"loss": 0.0018,
|
| 45 |
+
"step": 6865
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.0008742532420226e-05,
|
| 50 |
"loss": 0.0014,
|
| 51 |
+
"step": 8238
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.501019962115693e-05,
|
| 56 |
+
"loss": 0.0015,
|
| 57 |
+
"step": 9611
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.001165670989364e-05,
|
| 62 |
+
"loss": 0.0012,
|
| 63 |
+
"step": 10984
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.501311379863034e-05,
|
| 68 |
+
"loss": 0.001,
|
| 69 |
+
"step": 12357
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 0.011379459872841835,
|
| 74 |
+
"eval_max_distance": 5,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 13.5607,
|
| 77 |
+
"eval_samples_per_second": 19.763,
|
| 78 |
+
"eval_steps_per_second": 1.327,
|
| 79 |
+
"step": 13726
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.001457088736704e-05,
|
| 84 |
+
"loss": 0.0009,
|
| 85 |
+
"step": 13730
|
| 86 |
},
|
| 87 |
{
|
| 88 |
+
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 5.501602797610374e-05,
|
| 90 |
"loss": 0.0008,
|
| 91 |
+
"step": 15103
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 6.001748506484045e-05,
|
| 96 |
+
"loss": 0.0009,
|
| 97 |
+
"step": 16476
|
| 98 |
},
|
| 99 |
{
|
| 100 |
+
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 6.501894215357715e-05,
|
| 102 |
+
"loss": 0.0008,
|
| 103 |
+
"step": 17849
|
| 104 |
},
|
| 105 |
{
|
| 106 |
+
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 7.002039924231386e-05,
|
| 108 |
+
"loss": 0.0007,
|
| 109 |
+
"step": 19222
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 7.502185633105057e-05,
|
| 114 |
+
"loss": 0.0008,
|
| 115 |
+
"step": 20595
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 8.002331341978728e-05,
|
| 120 |
+
"loss": 0.0008,
|
| 121 |
+
"step": 21968
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 8.502477050852397e-05,
|
| 126 |
+
"loss": 0.0009,
|
| 127 |
+
"step": 23341
|
| 128 |
},
|
| 129 |
{
|
| 130 |
+
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 9.002622759726068e-05,
|
| 132 |
"loss": 0.0008,
|
| 133 |
+
"step": 24714
|
| 134 |
},
|
| 135 |
{
|
| 136 |
+
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 9.502768468599739e-05,
|
| 138 |
+
"loss": 0.0009,
|
| 139 |
+
"step": 26087
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 0.01430370844900608,
|
| 144 |
"eval_max_distance": 3,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 14.233,
|
| 147 |
+
"eval_samples_per_second": 18.829,
|
| 148 |
+
"eval_steps_per_second": 1.265,
|
| 149 |
+
"step": 27452
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 9.999676202502955e-05,
|
| 154 |
+
"loss": 0.0008,
|
| 155 |
+
"step": 27460
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 2.1,
|
| 159 |
+
"learning_rate": 9.944104457072547e-05,
|
| 160 |
+
"loss": 0.0008,
|
| 161 |
+
"step": 28833
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 2.2,
|
| 165 |
+
"learning_rate": 9.88853271164214e-05,
|
| 166 |
"loss": 0.0008,
|
| 167 |
+
"step": 30206
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 2.3,
|
| 171 |
+
"learning_rate": 9.832960966211731e-05,
|
| 172 |
+
"loss": 0.0008,
|
| 173 |
+
"step": 31579
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 2.4,
|
| 177 |
+
"learning_rate": 9.777389220781323e-05,
|
| 178 |
+
"loss": 0.0009,
|
| 179 |
+
"step": 32952
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 2.5,
|
| 183 |
+
"learning_rate": 9.721817475350917e-05,
|
| 184 |
+
"loss": 0.0008,
|
| 185 |
+
"step": 34325
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 2.6,
|
| 189 |
+
"learning_rate": 9.666245729920507e-05,
|
| 190 |
+
"loss": 0.0009,
|
| 191 |
+
"step": 35698
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 2.7,
|
| 195 |
+
"learning_rate": 9.6106739844901e-05,
|
| 196 |
"loss": 0.0008,
|
| 197 |
+
"step": 37071
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 2.8,
|
| 201 |
+
"learning_rate": 9.555102239059693e-05,
|
| 202 |
+
"loss": 0.0008,
|
| 203 |
+
"step": 38444
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 2.9,
|
| 207 |
+
"learning_rate": 9.499530493629284e-05,
|
| 208 |
+
"loss": 0.0008,
|
| 209 |
+
"step": 39817
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 0.014528523199260235,
|
| 214 |
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 12.815,
|
| 217 |
+
"eval_samples_per_second": 20.913,
|
| 218 |
+
"eval_steps_per_second": 1.405,
|
| 219 |
+
"step": 41178
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 3.0,
|
| 223 |
+
"learning_rate": 9.443958748198876e-05,
|
| 224 |
+
"loss": 0.0009,
|
| 225 |
+
"step": 41190
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 3.1,
|
| 229 |
+
"learning_rate": 9.38838700276847e-05,
|
| 230 |
"loss": 0.0008,
|
| 231 |
+
"step": 42563
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 3.2,
|
| 235 |
+
"learning_rate": 9.332815257338062e-05,
|
| 236 |
+
"loss": 0.0008,
|
| 237 |
+
"step": 43936
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 3.3,
|
| 241 |
+
"learning_rate": 9.277243511907654e-05,
|
| 242 |
+
"loss": 0.0008,
|
| 243 |
+
"step": 45309
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 3.4,
|
| 247 |
+
"learning_rate": 9.221671766477246e-05,
|
| 248 |
+
"loss": 0.0008,
|
| 249 |
+
"step": 46682
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 3.5,
|
| 253 |
+
"learning_rate": 9.166100021046838e-05,
|
| 254 |
+
"loss": 0.0008,
|
| 255 |
+
"step": 48055
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 3.6,
|
| 259 |
+
"learning_rate": 9.11052827561643e-05,
|
| 260 |
+
"loss": 0.0008,
|
| 261 |
+
"step": 49428
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 3.7,
|
| 265 |
+
"learning_rate": 9.054956530186022e-05,
|
| 266 |
+
"loss": 0.0008,
|
| 267 |
+
"step": 50801
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 3.8,
|
| 271 |
+
"learning_rate": 8.999384784755615e-05,
|
| 272 |
+
"loss": 0.0008,
|
| 273 |
+
"step": 52174
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 3.9,
|
| 277 |
+
"learning_rate": 8.943813039325206e-05,
|
| 278 |
+
"loss": 0.0009,
|
| 279 |
+
"step": 53547
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 0.009767626412212849,
|
| 284 |
+
"eval_max_distance": 1,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 13.1075,
|
| 287 |
+
"eval_samples_per_second": 20.446,
|
| 288 |
+
"eval_steps_per_second": 1.373,
|
| 289 |
+
"step": 54904
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 4.0,
|
| 293 |
+
"learning_rate": 8.888241293894799e-05,
|
| 294 |
"loss": 0.0009,
|
| 295 |
+
"step": 54920
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.1,
|
| 299 |
+
"learning_rate": 8.832669548464391e-05,
|
| 300 |
+
"loss": 0.0008,
|
| 301 |
+
"step": 56293
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 4.2,
|
| 305 |
+
"learning_rate": 8.777097803033983e-05,
|
| 306 |
+
"loss": 0.0008,
|
| 307 |
+
"step": 57666
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 4.3,
|
| 311 |
+
"learning_rate": 8.721526057603575e-05,
|
| 312 |
+
"loss": 0.0007,
|
| 313 |
+
"step": 59039
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 4.4,
|
| 317 |
+
"learning_rate": 8.665954312173167e-05,
|
| 318 |
+
"loss": 0.0008,
|
| 319 |
+
"step": 60412
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 4.5,
|
| 323 |
+
"learning_rate": 8.61038256674276e-05,
|
| 324 |
+
"loss": 0.0008,
|
| 325 |
+
"step": 61785
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 4.6,
|
| 329 |
+
"learning_rate": 8.554810821312351e-05,
|
| 330 |
+
"loss": 0.0008,
|
| 331 |
+
"step": 63158
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 4.7,
|
| 335 |
+
"learning_rate": 8.499239075881944e-05,
|
| 336 |
+
"loss": 0.0008,
|
| 337 |
+
"step": 64531
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 4.8,
|
| 341 |
+
"learning_rate": 8.443667330451536e-05,
|
| 342 |
+
"loss": 0.0008,
|
| 343 |
+
"step": 65904
|
| 344 |
},
|
| 345 |
{
|
| 346 |
+
"epoch": 4.9,
|
| 347 |
+
"learning_rate": 8.388095585021128e-05,
|
| 348 |
+
"loss": 0.0007,
|
| 349 |
+
"step": 67277
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 0.012975725345313549,
|
| 354 |
+
"eval_max_distance": 2,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 13.0896,
|
| 357 |
+
"eval_samples_per_second": 20.474,
|
| 358 |
+
"eval_steps_per_second": 1.375,
|
| 359 |
+
"step": 68630
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 5.0,
|
| 363 |
+
"learning_rate": 8.33252383959072e-05,
|
| 364 |
+
"loss": 0.0008,
|
| 365 |
+
"step": 68650
|
| 366 |
},
|
| 367 |
{
|
| 368 |
+
"epoch": 5.1,
|
| 369 |
+
"learning_rate": 8.276952094160313e-05,
|
| 370 |
+
"loss": 0.0008,
|
| 371 |
+
"step": 70023
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 5.2,
|
| 375 |
+
"learning_rate": 8.221380348729904e-05,
|
| 376 |
+
"loss": 0.0007,
|
| 377 |
+
"step": 71396
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 5.3,
|
| 381 |
+
"learning_rate": 8.165808603299497e-05,
|
| 382 |
"loss": 0.0008,
|
| 383 |
+
"step": 72769
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 5.4,
|
| 387 |
+
"learning_rate": 8.11023685786909e-05,
|
| 388 |
+
"loss": 0.0008,
|
| 389 |
+
"step": 74142
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 5.5,
|
| 393 |
+
"learning_rate": 8.054665112438681e-05,
|
| 394 |
"loss": 0.0007,
|
| 395 |
+
"step": 75515
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 5.6,
|
| 399 |
+
"learning_rate": 7.999093367008273e-05,
|
| 400 |
+
"loss": 0.0008,
|
| 401 |
+
"step": 76888
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 5.7,
|
| 405 |
+
"learning_rate": 7.943521621577865e-05,
|
| 406 |
+
"loss": 0.0007,
|
| 407 |
+
"step": 78261
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 5.8,
|
| 411 |
+
"learning_rate": 7.887949876147457e-05,
|
| 412 |
+
"loss": 0.0008,
|
| 413 |
+
"step": 79634
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 5.9,
|
| 417 |
+
"learning_rate": 7.832378130717049e-05,
|
| 418 |
+
"loss": 0.0008,
|
| 419 |
+
"step": 81007
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 0.015315458178520203,
|
| 424 |
+
"eval_max_distance": 2,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 13.1351,
|
| 427 |
+
"eval_samples_per_second": 20.403,
|
| 428 |
+
"eval_steps_per_second": 1.37,
|
| 429 |
+
"step": 82356
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 6.0,
|
| 433 |
+
"learning_rate": 7.776806385286643e-05,
|
| 434 |
+
"loss": 0.0008,
|
| 435 |
+
"step": 82380
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 6.1,
|
| 439 |
+
"learning_rate": 7.721234639856235e-05,
|
| 440 |
+
"loss": 0.0007,
|
| 441 |
+
"step": 83753
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 6.2,
|
| 445 |
+
"learning_rate": 7.665662894425827e-05,
|
| 446 |
+
"loss": 0.0007,
|
| 447 |
+
"step": 85126
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 6.3,
|
| 451 |
+
"learning_rate": 7.610091148995419e-05,
|
| 452 |
+
"loss": 0.0006,
|
| 453 |
+
"step": 86499
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 6.4,
|
| 457 |
+
"learning_rate": 7.554519403565012e-05,
|
| 458 |
"loss": 0.0007,
|
| 459 |
+
"step": 87872
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 6.5,
|
| 463 |
+
"learning_rate": 7.498947658134603e-05,
|
| 464 |
+
"loss": 0.0007,
|
| 465 |
+
"step": 89245
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 6.6,
|
| 469 |
+
"learning_rate": 7.443375912704195e-05,
|
| 470 |
+
"loss": 0.0007,
|
| 471 |
+
"step": 90618
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 6.7,
|
| 475 |
+
"learning_rate": 7.387804167273788e-05,
|
| 476 |
+
"loss": 0.0007,
|
| 477 |
+
"step": 91991
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 6.8,
|
| 481 |
+
"learning_rate": 7.332232421843378e-05,
|
| 482 |
+
"loss": 0.0007,
|
| 483 |
+
"step": 93364
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 6.9,
|
| 487 |
+
"learning_rate": 7.276660676412972e-05,
|
| 488 |
+
"loss": 0.0007,
|
| 489 |
+
"step": 94737
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 0.01277723629027605,
|
| 494 |
+
"eval_max_distance": 2,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 13.169,
|
| 497 |
+
"eval_samples_per_second": 20.351,
|
| 498 |
+
"eval_steps_per_second": 1.367,
|
| 499 |
+
"step": 96082
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 7.0,
|
| 503 |
+
"learning_rate": 7.221088930982564e-05,
|
| 504 |
"loss": 0.0007,
|
| 505 |
+
"step": 96110
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 7.1,
|
| 509 |
+
"learning_rate": 7.165517185552156e-05,
|
| 510 |
+
"loss": 0.0007,
|
| 511 |
+
"step": 97483
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 7.2,
|
| 515 |
+
"learning_rate": 7.109945440121748e-05,
|
| 516 |
+
"loss": 0.0006,
|
| 517 |
+
"step": 98856
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 7.3,
|
| 521 |
+
"learning_rate": 7.054373694691341e-05,
|
| 522 |
+
"loss": 0.0006,
|
| 523 |
+
"step": 100229
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"epoch": 7.4,
|
| 527 |
+
"learning_rate": 6.998801949260933e-05,
|
| 528 |
"loss": 0.0007,
|
| 529 |
+
"step": 101602
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 7.5,
|
| 533 |
+
"learning_rate": 6.943230203830525e-05,
|
| 534 |
"loss": 0.0006,
|
| 535 |
+
"step": 102975
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 7.6,
|
| 539 |
+
"learning_rate": 6.887658458400117e-05,
|
| 540 |
+
"loss": 0.0006,
|
| 541 |
+
"step": 104348
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 7.7,
|
| 545 |
+
"learning_rate": 6.832086712969709e-05,
|
| 546 |
"loss": 0.0007,
|
| 547 |
+
"step": 105721
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 7.8,
|
| 551 |
+
"learning_rate": 6.776514967539301e-05,
|
| 552 |
+
"loss": 0.0006,
|
| 553 |
+
"step": 107094
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 7.9,
|
| 557 |
+
"learning_rate": 6.720943222108893e-05,
|
| 558 |
+
"loss": 0.0006,
|
| 559 |
+
"step": 108467
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 0.013012989424169064,
|
| 564 |
"eval_max_distance": 3,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 12.4679,
|
| 567 |
+
"eval_samples_per_second": 21.495,
|
| 568 |
+
"eval_steps_per_second": 1.444,
|
| 569 |
+
"step": 109808
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 8.0,
|
| 573 |
+
"learning_rate": 6.665371476678486e-05,
|
| 574 |
+
"loss": 0.0007,
|
| 575 |
+
"step": 109840
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 8.1,
|
| 579 |
+
"learning_rate": 6.609799731248077e-05,
|
| 580 |
"loss": 0.0007,
|
| 581 |
+
"step": 111213
|
| 582 |
},
|
| 583 |
{
|
| 584 |
+
"epoch": 8.2,
|
| 585 |
+
"learning_rate": 6.55422798581767e-05,
|
| 586 |
"loss": 0.0005,
|
| 587 |
+
"step": 112586
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 588 |
},
|
| 589 |
{
|
| 590 |
+
"epoch": 8.3,
|
| 591 |
+
"learning_rate": 6.498656240387262e-05,
|
| 592 |
"loss": 0.0007,
|
| 593 |
+
"step": 113959
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"epoch": 8.4,
|
| 597 |
+
"learning_rate": 6.443084494956854e-05,
|
| 598 |
+
"loss": 0.0006,
|
| 599 |
+
"step": 115332
|
| 600 |
},
|
| 601 |
{
|
| 602 |
+
"epoch": 8.5,
|
| 603 |
+
"learning_rate": 6.387512749526446e-05,
|
| 604 |
"loss": 0.0006,
|
| 605 |
+
"step": 116705
|
| 606 |
},
|
| 607 |
{
|
| 608 |
+
"epoch": 8.6,
|
| 609 |
+
"learning_rate": 6.33194100409604e-05,
|
| 610 |
+
"loss": 0.0007,
|
| 611 |
+
"step": 118078
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 8.7,
|
| 615 |
+
"learning_rate": 6.276369258665632e-05,
|
| 616 |
+
"loss": 0.0006,
|
| 617 |
+
"step": 119451
|
| 618 |
},
|
| 619 |
{
|
| 620 |
+
"epoch": 8.8,
|
| 621 |
+
"learning_rate": 6.220797513235222e-05,
|
| 622 |
"loss": 0.0006,
|
| 623 |
+
"step": 120824
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 8.9,
|
| 627 |
+
"learning_rate": 6.165225767804815e-05,
|
| 628 |
+
"loss": 0.0006,
|
| 629 |
+
"step": 122197
|
|
|
|
|
|
|
|
|
|
|
|
|
| 630 |
},
|
| 631 |
{
|
| 632 |
+
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 0.015804793685674667,
|
| 634 |
+
"eval_max_distance": 5,
|
| 635 |
+
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 12.8641,
|
| 637 |
+
"eval_samples_per_second": 20.833,
|
| 638 |
+
"eval_steps_per_second": 1.399,
|
| 639 |
+
"step": 123534
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 9.0,
|
| 643 |
+
"learning_rate": 6.109654022374407e-05,
|
| 644 |
+
"loss": 0.0005,
|
| 645 |
+
"step": 123570
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 9.1,
|
| 649 |
+
"learning_rate": 6.0540822769439994e-05,
|
| 650 |
"loss": 0.0005,
|
| 651 |
+
"step": 124943
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 9.2,
|
| 655 |
+
"learning_rate": 5.9985105315135914e-05,
|
| 656 |
"loss": 0.0006,
|
| 657 |
+
"step": 126316
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.3,
|
| 661 |
+
"learning_rate": 5.942938786083184e-05,
|
| 662 |
+
"loss": 0.0005,
|
| 663 |
+
"step": 127689
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 9.4,
|
| 667 |
+
"learning_rate": 5.887367040652776e-05,
|
| 668 |
"loss": 0.0006,
|
| 669 |
+
"step": 129062
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 9.5,
|
| 673 |
+
"learning_rate": 5.831795295222369e-05,
|
| 674 |
+
"loss": 0.0006,
|
| 675 |
+
"step": 130435
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 9.6,
|
| 679 |
+
"learning_rate": 5.77622354979196e-05,
|
| 680 |
+
"loss": 0.0006,
|
| 681 |
+
"step": 131808
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 9.7,
|
| 685 |
+
"learning_rate": 5.720651804361552e-05,
|
| 686 |
+
"loss": 0.0007,
|
| 687 |
+
"step": 133181
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 9.8,
|
| 691 |
+
"learning_rate": 5.6650800589311447e-05,
|
| 692 |
+
"loss": 0.0006,
|
| 693 |
+
"step": 134554
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 9.9,
|
| 697 |
+
"learning_rate": 5.6095083135007366e-05,
|
| 698 |
"loss": 0.0006,
|
| 699 |
+
"step": 135927
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 0.015074091032147408,
|
| 704 |
+
"eval_max_distance": 1,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 12.5962,
|
| 707 |
+
"eval_samples_per_second": 21.276,
|
| 708 |
+
"eval_steps_per_second": 1.429,
|
| 709 |
+
"step": 137260
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 10.0,
|
| 713 |
+
"learning_rate": 5.553936568070329e-05,
|
| 714 |
+
"loss": 0.0006,
|
| 715 |
+
"step": 137300
|
| 716 |
},
|
| 717 |
{
|
| 718 |
+
"epoch": 10.1,
|
| 719 |
+
"learning_rate": 5.4983648226399206e-05,
|
| 720 |
"loss": 0.0006,
|
| 721 |
+
"step": 138673
|
| 722 |
},
|
| 723 |
{
|
| 724 |
+
"epoch": 10.2,
|
| 725 |
+
"learning_rate": 5.442793077209514e-05,
|
| 726 |
+
"loss": 0.0006,
|
| 727 |
+
"step": 140046
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 10.3,
|
| 731 |
+
"learning_rate": 5.387221331779105e-05,
|
| 732 |
+
"loss": 0.0006,
|
| 733 |
+
"step": 141419
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"epoch": 10.4,
|
| 737 |
+
"learning_rate": 5.331649586348698e-05,
|
| 738 |
+
"loss": 0.0008,
|
| 739 |
+
"step": 142792
|
| 740 |
},
|
| 741 |
{
|
| 742 |
+
"epoch": 10.5,
|
| 743 |
+
"learning_rate": 5.27607784091829e-05,
|
| 744 |
+
"loss": 0.0005,
|
| 745 |
+
"step": 144165
|
| 746 |
},
|
| 747 |
{
|
| 748 |
+
"epoch": 10.6,
|
| 749 |
+
"learning_rate": 5.2205060954878825e-05,
|
| 750 |
"loss": 0.0006,
|
| 751 |
+
"step": 145538
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 10.7,
|
| 755 |
+
"learning_rate": 5.1649343500574745e-05,
|
| 756 |
+
"loss": 0.0006,
|
| 757 |
+
"step": 146911
|
| 758 |
},
|
| 759 |
{
|
| 760 |
+
"epoch": 10.8,
|
| 761 |
+
"learning_rate": 5.109362604627066e-05,
|
| 762 |
+
"loss": 0.0006,
|
| 763 |
+
"step": 148284
|
| 764 |
},
|
| 765 |
{
|
| 766 |
+
"epoch": 10.9,
|
| 767 |
+
"learning_rate": 5.0537908591966585e-05,
|
| 768 |
+
"loss": 0.0005,
|
| 769 |
+
"step": 149657
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 0.016692565754055977,
|
| 774 |
+
"eval_max_distance": 1,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 12.5906,
|
| 777 |
+
"eval_samples_per_second": 21.286,
|
| 778 |
+
"eval_steps_per_second": 1.43,
|
| 779 |
+
"step": 150986
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 11.0,
|
| 783 |
+
"learning_rate": 4.998219113766251e-05,
|
| 784 |
+
"loss": 0.0006,
|
| 785 |
+
"step": 151030
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 11.1,
|
| 789 |
+
"learning_rate": 4.942647368335843e-05,
|
| 790 |
"loss": 0.0005,
|
| 791 |
+
"step": 152403
|
| 792 |
},
|
| 793 |
{
|
| 794 |
+
"epoch": 11.2,
|
| 795 |
+
"learning_rate": 4.887075622905435e-05,
|
| 796 |
+
"loss": 0.0005,
|
| 797 |
+
"step": 153776
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 11.3,
|
| 801 |
+
"learning_rate": 4.831503877475027e-05,
|
| 802 |
+
"loss": 0.0005,
|
| 803 |
+
"step": 155149
|
| 804 |
},
|
| 805 |
{
|
| 806 |
+
"epoch": 11.4,
|
| 807 |
+
"learning_rate": 4.775932132044619e-05,
|
| 808 |
+
"loss": 0.0005,
|
| 809 |
+
"step": 156522
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 11.5,
|
| 813 |
+
"learning_rate": 4.720360386614212e-05,
|
| 814 |
+
"loss": 0.0005,
|
| 815 |
+
"step": 157895
|
| 816 |
},
|
| 817 |
{
|
| 818 |
+
"epoch": 11.6,
|
| 819 |
+
"learning_rate": 4.664788641183804e-05,
|
| 820 |
"loss": 0.0005,
|
| 821 |
+
"step": 159268
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 11.7,
|
| 825 |
+
"learning_rate": 4.6092168957533957e-05,
|
| 826 |
"loss": 0.0005,
|
| 827 |
+
"step": 160641
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 11.8,
|
| 831 |
+
"learning_rate": 4.553645150322988e-05,
|
| 832 |
+
"loss": 0.0005,
|
| 833 |
+
"step": 162014
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 11.9,
|
| 837 |
+
"learning_rate": 4.49807340489258e-05,
|
| 838 |
+
"loss": 0.0005,
|
| 839 |
+
"step": 163387
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 0.014475121162831783,
|
| 844 |
+
"eval_max_distance": 1,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 12.6623,
|
| 847 |
+
"eval_samples_per_second": 21.165,
|
| 848 |
+
"eval_steps_per_second": 1.422,
|
| 849 |
+
"step": 164712
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 12.0,
|
| 853 |
+
"learning_rate": 4.442501659462173e-05,
|
| 854 |
+
"loss": 0.0005,
|
| 855 |
+
"step": 164760
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 12.1,
|
| 859 |
+
"learning_rate": 4.386929914031765e-05,
|
| 860 |
+
"loss": 0.0005,
|
| 861 |
+
"step": 166133
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 12.2,
|
| 865 |
+
"learning_rate": 4.331358168601357e-05,
|
| 866 |
+
"loss": 0.0005,
|
| 867 |
+
"step": 167506
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 12.3,
|
| 871 |
+
"learning_rate": 4.2757864231709496e-05,
|
| 872 |
+
"loss": 0.0005,
|
| 873 |
+
"step": 168879
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 12.4,
|
| 877 |
+
"learning_rate": 4.220214677740541e-05,
|
| 878 |
+
"loss": 0.0005,
|
| 879 |
+
"step": 170252
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 12.5,
|
| 883 |
+
"learning_rate": 4.1646429323101335e-05,
|
| 884 |
"loss": 0.0004,
|
| 885 |
+
"step": 171625
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 12.6,
|
| 889 |
+
"learning_rate": 4.1090711868797255e-05,
|
| 890 |
+
"loss": 0.0006,
|
| 891 |
+
"step": 172998
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 12.7,
|
| 895 |
+
"learning_rate": 4.0534994414493175e-05,
|
| 896 |
+
"loss": 0.0006,
|
| 897 |
+
"step": 174371
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 12.8,
|
| 901 |
+
"learning_rate": 3.99792769601891e-05,
|
| 902 |
+
"loss": 0.0006,
|
| 903 |
+
"step": 175744
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 12.9,
|
| 907 |
+
"learning_rate": 3.942355950588502e-05,
|
| 908 |
+
"loss": 0.0005,
|
| 909 |
+
"step": 177117
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 0.016049271449446678,
|
| 914 |
+
"eval_max_distance": 1,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 12.7374,
|
| 917 |
+
"eval_samples_per_second": 21.04,
|
| 918 |
+
"eval_steps_per_second": 1.413,
|
| 919 |
+
"step": 178438
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 13.0,
|
| 923 |
+
"learning_rate": 3.886784205158094e-05,
|
| 924 |
+
"loss": 0.0005,
|
| 925 |
+
"step": 178490
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 13.1,
|
| 929 |
+
"learning_rate": 3.831212459727687e-05,
|
| 930 |
+
"loss": 0.0005,
|
| 931 |
+
"step": 179863
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 13.2,
|
| 935 |
+
"learning_rate": 3.775640714297279e-05,
|
| 936 |
+
"loss": 0.0005,
|
| 937 |
+
"step": 181236
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 13.3,
|
| 941 |
+
"learning_rate": 3.720068968866871e-05,
|
| 942 |
+
"loss": 0.0005,
|
| 943 |
+
"step": 182609
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 13.4,
|
| 947 |
+
"learning_rate": 3.6644972234364634e-05,
|
| 948 |
+
"loss": 0.0005,
|
| 949 |
+
"step": 183982
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 13.5,
|
| 953 |
+
"learning_rate": 3.608925478006055e-05,
|
| 954 |
+
"loss": 0.0004,
|
| 955 |
+
"step": 185355
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 13.6,
|
| 959 |
+
"learning_rate": 3.5533537325756473e-05,
|
| 960 |
+
"loss": 0.0005,
|
| 961 |
+
"step": 186728
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 13.7,
|
| 965 |
+
"learning_rate": 3.497781987145239e-05,
|
| 966 |
"loss": 0.0005,
|
| 967 |
+
"step": 188101
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 13.8,
|
| 971 |
+
"learning_rate": 3.442210241714832e-05,
|
| 972 |
+
"loss": 0.0005,
|
| 973 |
+
"step": 189474
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 13.9,
|
| 977 |
+
"learning_rate": 3.386638496284424e-05,
|
| 978 |
"loss": 0.0005,
|
| 979 |
+
"step": 190847
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 0.015727248042821884,
|
| 984 |
+
"eval_max_distance": 1,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 12.6356,
|
| 987 |
+
"eval_samples_per_second": 21.21,
|
| 988 |
+
"eval_steps_per_second": 1.425,
|
| 989 |
+
"step": 192164
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 14.0,
|
| 993 |
+
"learning_rate": 3.331066750854016e-05,
|
| 994 |
+
"loss": 0.0004,
|
| 995 |
+
"step": 192220
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 14.1,
|
| 999 |
+
"learning_rate": 3.2754950054236086e-05,
|
| 1000 |
+
"loss": 0.0005,
|
| 1001 |
+
"step": 193593
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 14.2,
|
| 1005 |
+
"learning_rate": 3.2199232599932006e-05,
|
| 1006 |
"loss": 0.0005,
|
| 1007 |
+
"step": 194966
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 14.3,
|
| 1011 |
+
"learning_rate": 3.1643515145627926e-05,
|
| 1012 |
"loss": 0.0004,
|
| 1013 |
+
"step": 196339
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 14.4,
|
| 1017 |
+
"learning_rate": 3.108779769132385e-05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1018 |
"loss": 0.0004,
|
| 1019 |
+
"step": 197712
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 14.5,
|
| 1023 |
+
"learning_rate": 3.0532080237019765e-05,
|
| 1024 |
"loss": 0.0005,
|
| 1025 |
+
"step": 199085
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 14.6,
|
| 1029 |
+
"learning_rate": 2.997636278271569e-05,
|
| 1030 |
"loss": 0.0005,
|
| 1031 |
+
"step": 200458
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 14.7,
|
| 1035 |
+
"learning_rate": 2.942064532841161e-05,
|
| 1036 |
+
"loss": 0.0004,
|
| 1037 |
+
"step": 201831
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 14.8,
|
| 1041 |
+
"learning_rate": 2.8864927874107535e-05,
|
| 1042 |
+
"loss": 0.0004,
|
| 1043 |
+
"step": 203204
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 14.9,
|
| 1047 |
+
"learning_rate": 2.8309210419803455e-05,
|
| 1048 |
+
"loss": 0.0004,
|
| 1049 |
+
"step": 204577
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 0.015685711055994034,
|
| 1054 |
+
"eval_max_distance": 1,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 12.7509,
|
| 1057 |
+
"eval_samples_per_second": 21.018,
|
| 1058 |
+
"eval_steps_per_second": 1.412,
|
| 1059 |
+
"step": 205890
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
+
"epoch": 15.0,
|
| 1063 |
+
"learning_rate": 2.7753492965499378e-05,
|
| 1064 |
"loss": 0.0004,
|
| 1065 |
+
"step": 205950
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 15.1,
|
| 1069 |
+
"learning_rate": 2.71977755111953e-05,
|
| 1070 |
"loss": 0.0004,
|
| 1071 |
+
"step": 207323
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 15.2,
|
| 1075 |
+
"learning_rate": 2.6642058056891224e-05,
|
| 1076 |
+
"loss": 0.0004,
|
| 1077 |
+
"step": 208696
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
+
"epoch": 15.3,
|
| 1081 |
+
"learning_rate": 2.6086340602587144e-05,
|
| 1082 |
+
"loss": 0.0004,
|
| 1083 |
+
"step": 210069
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
+
"epoch": 15.4,
|
| 1087 |
+
"learning_rate": 2.5530623148283067e-05,
|
| 1088 |
"loss": 0.0004,
|
| 1089 |
+
"step": 211442
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 15.5,
|
| 1093 |
+
"learning_rate": 2.4974905693978987e-05,
|
| 1094 |
"loss": 0.0005,
|
| 1095 |
+
"step": 212815
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 15.6,
|
| 1099 |
+
"learning_rate": 2.441918823967491e-05,
|
| 1100 |
"loss": 0.0004,
|
| 1101 |
+
"step": 214188
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 15.7,
|
| 1105 |
+
"learning_rate": 2.386347078537083e-05,
|
| 1106 |
+
"loss": 0.0004,
|
| 1107 |
+
"step": 215561
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 15.8,
|
| 1111 |
+
"learning_rate": 2.330775333106675e-05,
|
| 1112 |
+
"loss": 0.0005,
|
| 1113 |
+
"step": 216934
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 15.9,
|
| 1117 |
+
"learning_rate": 2.2752035876762673e-05,
|
| 1118 |
"loss": 0.0004,
|
| 1119 |
+
"step": 218307
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 0.017339130863547325,
|
| 1124 |
+
"eval_max_distance": 1,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 12.871,
|
| 1127 |
+
"eval_samples_per_second": 20.822,
|
| 1128 |
+
"eval_steps_per_second": 1.398,
|
| 1129 |
+
"step": 219616
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 16.0,
|
| 1133 |
+
"learning_rate": 2.2196318422458596e-05,
|
| 1134 |
+
"loss": 0.0004,
|
| 1135 |
+
"step": 219680
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 16.1,
|
| 1139 |
+
"learning_rate": 2.1640600968154516e-05,
|
| 1140 |
+
"loss": 0.0004,
|
| 1141 |
+
"step": 221053
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 16.2,
|
| 1145 |
+
"learning_rate": 2.108488351385044e-05,
|
| 1146 |
+
"loss": 0.0004,
|
| 1147 |
+
"step": 222426
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 16.3,
|
| 1151 |
+
"learning_rate": 2.0529166059546362e-05,
|
| 1152 |
+
"loss": 0.0004,
|
| 1153 |
+
"step": 223799
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 16.4,
|
| 1157 |
+
"learning_rate": 1.9973448605242282e-05,
|
| 1158 |
"loss": 0.0004,
|
| 1159 |
+
"step": 225172
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 16.5,
|
| 1163 |
+
"learning_rate": 1.9417731150938205e-05,
|
| 1164 |
+
"loss": 0.0004,
|
| 1165 |
+
"step": 226545
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 16.6,
|
| 1169 |
+
"learning_rate": 1.8862013696634125e-05,
|
| 1170 |
"loss": 0.0004,
|
| 1171 |
+
"step": 227918
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 16.7,
|
| 1175 |
+
"learning_rate": 1.8306296242330048e-05,
|
| 1176 |
"loss": 0.0004,
|
| 1177 |
+
"step": 229291
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 16.8,
|
| 1181 |
+
"learning_rate": 1.775057878802597e-05,
|
| 1182 |
"loss": 0.0004,
|
| 1183 |
+
"step": 230664
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 16.9,
|
| 1187 |
+
"learning_rate": 1.719486133372189e-05,
|
| 1188 |
+
"loss": 0.0004,
|
| 1189 |
+
"step": 232037
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 0.015850957483053207,
|
| 1194 |
+
"eval_max_distance": 1,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 12.7459,
|
| 1197 |
+
"eval_samples_per_second": 21.026,
|
| 1198 |
+
"eval_steps_per_second": 1.412,
|
| 1199 |
+
"step": 233342
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
+
"epoch": 17.0,
|
| 1203 |
+
"learning_rate": 1.663914387941781e-05,
|
| 1204 |
"loss": 0.0004,
|
| 1205 |
+
"step": 233410
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
+
"epoch": 17.1,
|
| 1209 |
+
"learning_rate": 1.6083426425113734e-05,
|
| 1210 |
+
"loss": 0.0004,
|
| 1211 |
+
"step": 234783
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
+
"epoch": 17.21,
|
| 1215 |
+
"learning_rate": 1.5527708970809657e-05,
|
| 1216 |
+
"loss": 0.0004,
|
| 1217 |
+
"step": 236156
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 17.31,
|
| 1221 |
+
"learning_rate": 1.4971991516505579e-05,
|
| 1222 |
+
"loss": 0.0004,
|
| 1223 |
+
"step": 237529
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"epoch": 17.41,
|
| 1227 |
+
"learning_rate": 1.4416274062201499e-05,
|
| 1228 |
+
"loss": 0.0005,
|
| 1229 |
+
"step": 238902
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
+
"epoch": 17.51,
|
| 1233 |
+
"learning_rate": 1.386055660789742e-05,
|
| 1234 |
+
"loss": 0.0004,
|
| 1235 |
+
"step": 240275
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
+
"epoch": 17.61,
|
| 1239 |
+
"learning_rate": 1.3304839153593343e-05,
|
| 1240 |
+
"loss": 0.0004,
|
| 1241 |
+
"step": 241648
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 17.71,
|
| 1245 |
+
"learning_rate": 1.2749121699289265e-05,
|
| 1246 |
+
"loss": 0.0004,
|
| 1247 |
+
"step": 243021
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
+
"epoch": 17.81,
|
| 1251 |
+
"learning_rate": 1.2193404244985186e-05,
|
| 1252 |
+
"loss": 0.0004,
|
| 1253 |
+
"step": 244394
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
+
"epoch": 17.91,
|
| 1257 |
+
"learning_rate": 1.1637686790681108e-05,
|
| 1258 |
"loss": 0.0004,
|
| 1259 |
+
"step": 245767
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 0.016846980899572372,
|
| 1264 |
+
"eval_max_distance": 2,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 14.3322,
|
| 1267 |
+
"eval_samples_per_second": 18.699,
|
| 1268 |
+
"eval_steps_per_second": 1.256,
|
| 1269 |
+
"step": 247068
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 18.01,
|
| 1273 |
+
"learning_rate": 1.1081969336377031e-05,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1274 |
"loss": 0.0004,
|
| 1275 |
+
"step": 247140
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 18.11,
|
| 1279 |
+
"learning_rate": 1.0526251882072952e-05,
|
| 1280 |
"loss": 0.0004,
|
| 1281 |
+
"step": 248513
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 18.21,
|
| 1285 |
+
"learning_rate": 9.970534427768874e-06,
|
| 1286 |
+
"loss": 0.0004,
|
| 1287 |
+
"step": 249886
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 18.31,
|
| 1291 |
+
"learning_rate": 9.414816973464795e-06,
|
| 1292 |
"loss": 0.0003,
|
| 1293 |
+
"step": 251259
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 18.41,
|
| 1297 |
+
"learning_rate": 8.859099519160717e-06,
|
| 1298 |
"loss": 0.0004,
|
| 1299 |
+
"step": 252632
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 18.51,
|
| 1303 |
+
"learning_rate": 8.30338206485664e-06,
|
| 1304 |
"loss": 0.0004,
|
| 1305 |
+
"step": 254005
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
+
"epoch": 18.61,
|
| 1309 |
+
"learning_rate": 7.74766461055256e-06,
|
| 1310 |
"loss": 0.0004,
|
| 1311 |
+
"step": 255378
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
+
"epoch": 18.71,
|
| 1315 |
+
"learning_rate": 7.191947156248482e-06,
|
| 1316 |
"loss": 0.0004,
|
| 1317 |
+
"step": 256751
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
+
"epoch": 18.81,
|
| 1321 |
+
"learning_rate": 6.636229701944405e-06,
|
| 1322 |
"loss": 0.0003,
|
| 1323 |
+
"step": 258124
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 18.91,
|
| 1327 |
+
"learning_rate": 6.080512247640326e-06,
|
| 1328 |
+
"loss": 0.0004,
|
| 1329 |
+
"step": 259497
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
+
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 0.01681215688586235,
|
| 1334 |
+
"eval_max_distance": 1,
|
| 1335 |
+
"eval_mean_distance": 0,
|
| 1336 |
+
"eval_runtime": 12.5068,
|
| 1337 |
+
"eval_samples_per_second": 21.428,
|
| 1338 |
+
"eval_steps_per_second": 1.439,
|
| 1339 |
+
"step": 260794
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
+
"epoch": 19.01,
|
| 1343 |
+
"learning_rate": 5.524794793336248e-06,
|
| 1344 |
"loss": 0.0004,
|
| 1345 |
+
"step": 260870
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
+
"epoch": 19.11,
|
| 1349 |
+
"learning_rate": 4.969077339032169e-06,
|
| 1350 |
+
"loss": 0.0004,
|
| 1351 |
+
"step": 262243
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"epoch": 19.21,
|
| 1355 |
+
"learning_rate": 4.4133598847280914e-06,
|
| 1356 |
+
"loss": 0.0004,
|
| 1357 |
+
"step": 263616
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
+
"epoch": 19.31,
|
| 1361 |
+
"learning_rate": 3.857642430424013e-06,
|
| 1362 |
+
"loss": 0.0004,
|
| 1363 |
+
"step": 264989
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 19.41,
|
| 1367 |
+
"learning_rate": 3.301924976119935e-06,
|
| 1368 |
+
"loss": 0.0004,
|
| 1369 |
+
"step": 266362
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 19.51,
|
| 1373 |
+
"learning_rate": 2.7462075218158563e-06,
|
| 1374 |
"loss": 0.0004,
|
| 1375 |
+
"step": 267735
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 19.61,
|
| 1379 |
+
"learning_rate": 2.1904900675117783e-06,
|
| 1380 |
"loss": 0.0003,
|
| 1381 |
+
"step": 269108
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 19.71,
|
| 1385 |
+
"learning_rate": 1.6347726132077e-06,
|
| 1386 |
+
"loss": 0.0004,
|
| 1387 |
+
"step": 270481
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 19.81,
|
| 1391 |
+
"learning_rate": 1.0790551589036217e-06,
|
| 1392 |
"loss": 0.0003,
|
| 1393 |
+
"step": 271854
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 19.91,
|
| 1397 |
+
"learning_rate": 5.233377045995435e-07,
|
| 1398 |
+
"loss": 0.0004,
|
| 1399 |
+
"step": 273227
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 0.016863718628883362,
|
| 1404 |
+
"eval_max_distance": 1,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 12.4816,
|
| 1407 |
+
"eval_samples_per_second": 21.472,
|
| 1408 |
+
"eval_steps_per_second": 1.442,
|
| 1409 |
+
"step": 274520
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
+
"step": 274520,
|
| 1414 |
+
"total_flos": 7.204011364904141e+16,
|
| 1415 |
+
"train_loss": 2.2036947758330143e-05,
|
| 1416 |
+
"train_runtime": 1601.2933,
|
| 1417 |
+
"train_samples_per_second": 2571.434,
|
| 1418 |
+
"train_steps_per_second": 171.436
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
+
"logging_steps": 1373,
|
| 1422 |
+
"max_steps": 274520,
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 2746,
|
| 1425 |
+
"total_flos": 7.204011364904141e+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 sha256:3fcbb4734a1034f7e19548fb8450d8c0a52da16d2253c49bf3ef5741ac2faac2
|
| 3 |
size 4091
|