End of training
Browse files- README.md +23 -23
- pytorch_model.bin +1 -1
- trainer_state.json +728 -728
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -15,7 +15,7 @@ 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: 1
|
| 21 |
|
|
@@ -47,28 +47,28 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
-
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.0004 | 15.0 |
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.0004 | 17.0 |
|
| 69 |
-
| 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: 0.0152
|
| 19 |
- Mean Distance: 0
|
| 20 |
- Max Distance: 1
|
| 21 |
|
|
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0005 | 1.0 | 13747 | 0.0151 | 0 | 3 |
|
| 53 |
+
| 0.0005 | 2.0 | 27494 | 0.0173 | 0 | 3 |
|
| 54 |
+
| 0.0006 | 3.0 | 41241 | 0.0136 | 0 | 3 |
|
| 55 |
+
| 0.0007 | 4.0 | 54988 | 0.0141 | 0 | 2 |
|
| 56 |
+
| 0.0006 | 5.0 | 68735 | 0.0155 | 0 | 4 |
|
| 57 |
+
| 0.0005 | 6.0 | 82482 | 0.0183 | 0 | 4 |
|
| 58 |
+
| 0.0005 | 7.0 | 96229 | 0.0218 | 0 | 4 |
|
| 59 |
+
| 0.0005 | 8.0 | 109976 | 0.0162 | 0 | 1 |
|
| 60 |
+
| 0.0005 | 9.0 | 123723 | 0.0147 | 0 | 3 |
|
| 61 |
+
| 0.0005 | 10.0 | 137470 | 0.0188 | 0 | 5 |
|
| 62 |
+
| 0.0004 | 11.0 | 151217 | 0.0168 | 0 | 1 |
|
| 63 |
+
| 0.0004 | 12.0 | 164964 | 0.0172 | 0 | 4 |
|
| 64 |
+
| 0.0004 | 13.0 | 178711 | 0.0168 | 0 | 3 |
|
| 65 |
+
| 0.0004 | 14.0 | 192458 | 0.0162 | 0 | 2 |
|
| 66 |
+
| 0.0004 | 15.0 | 206205 | 0.0165 | 0 | 2 |
|
| 67 |
+
| 0.0003 | 16.0 | 219952 | 0.0151 | 0 | 3 |
|
| 68 |
+
| 0.0004 | 17.0 | 233699 | 0.0137 | 0 | 1 |
|
| 69 |
+
| 0.0003 | 18.0 | 247446 | 0.0146 | 0 | 3 |
|
| 70 |
+
| 0.0003 | 19.0 | 261193 | 0.0152 | 0 | 1 |
|
| 71 |
+
| 0.0003 | 20.0 | 274940 | 0.0152 | 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:a29ed1864021c806a6e456100ae3fbfee4fceac880782c5f20ef94edb2442cf9
|
| 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": 3.
|
| 14 |
"loss": 0.0,
|
| 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": 0.
|
| 74 |
-
"eval_max_distance":
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
-
"eval_runtime":
|
| 77 |
-
"eval_samples_per_second":
|
| 78 |
-
"eval_steps_per_second": 1.
|
| 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": 0.
|
| 144 |
"eval_max_distance": 3,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second": 1.
|
| 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": 0.
|
| 214 |
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second": 1.
|
| 219 |
-
"step":
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 3.0,
|
| 223 |
-
"learning_rate": 9.
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 3.1,
|
| 229 |
-
"learning_rate": 9.
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 3.2,
|
| 235 |
-
"learning_rate": 9.
|
| 236 |
-
"loss": 0.
|
| 237 |
-
"step":
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 3.3,
|
| 241 |
-
"learning_rate": 9.
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 3.4,
|
| 247 |
-
"learning_rate": 9.
|
| 248 |
-
"loss": 0.
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 3.5,
|
| 253 |
-
"learning_rate": 9.
|
| 254 |
-
"loss": 0.
|
| 255 |
-
"step":
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.6,
|
| 259 |
-
"learning_rate": 9.
|
| 260 |
-
"loss": 0.
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 3.7,
|
| 265 |
-
"learning_rate": 9.
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.8,
|
| 271 |
-
"learning_rate": 8.
|
| 272 |
-
"loss": 0.
|
| 273 |
-
"step":
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 3.9,
|
| 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": 1.
|
| 289 |
-
"step":
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 4.0,
|
| 293 |
-
"learning_rate": 8.
|
| 294 |
-
"loss": 0.
|
| 295 |
-
"step":
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 4.1,
|
| 299 |
-
"learning_rate": 8.
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"step":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 4.2,
|
| 305 |
-
"learning_rate": 8.
|
| 306 |
-
"loss": 0.
|
| 307 |
-
"step":
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 4.3,
|
| 311 |
-
"learning_rate": 8.
|
| 312 |
-
"loss": 0.
|
| 313 |
-
"step":
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 4.4,
|
| 317 |
-
"learning_rate": 8.
|
| 318 |
-
"loss": 0.
|
| 319 |
-
"step":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 4.5,
|
| 323 |
-
"learning_rate": 8.
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.6,
|
| 329 |
-
"learning_rate": 8.
|
| 330 |
-
"loss": 0.
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 4.7,
|
| 335 |
-
"learning_rate": 8.
|
| 336 |
-
"loss": 0.
|
| 337 |
-
"step":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.8,
|
| 341 |
-
"learning_rate": 8.
|
| 342 |
-
"loss": 0.
|
| 343 |
-
"step":
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 4.9,
|
| 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": 1.
|
| 359 |
-
"step":
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 5.0,
|
| 363 |
-
"learning_rate": 8.
|
| 364 |
-
"loss": 0.
|
| 365 |
-
"step":
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.1,
|
| 369 |
-
"learning_rate": 8.
|
| 370 |
-
"loss": 0.
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 5.2,
|
| 375 |
-
"learning_rate": 8.
|
| 376 |
-
"loss": 0.
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 5.3,
|
| 381 |
-
"learning_rate": 8.
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.4,
|
| 387 |
-
"learning_rate": 8.
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 5.5,
|
| 393 |
-
"learning_rate": 8.
|
| 394 |
-
"loss": 0.
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 5.6,
|
| 399 |
-
"learning_rate": 7.
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"step":
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 5.7,
|
| 405 |
-
"learning_rate": 7.
|
| 406 |
-
"loss": 0.
|
| 407 |
-
"step":
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 5.8,
|
| 411 |
-
"learning_rate": 7.
|
| 412 |
-
"loss": 0.
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 5.9,
|
| 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": 1.
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 6.0,
|
| 433 |
-
"learning_rate": 7.
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.1,
|
| 439 |
-
"learning_rate": 7.
|
| 440 |
-
"loss": 0.
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.2,
|
| 445 |
-
"learning_rate": 7.
|
| 446 |
-
"loss": 0.
|
| 447 |
-
"step":
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.3,
|
| 451 |
-
"learning_rate": 7.
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 6.4,
|
| 457 |
-
"learning_rate": 7.
|
| 458 |
-
"loss": 0.
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 6.5,
|
| 463 |
-
"learning_rate": 7.
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 6.6,
|
| 469 |
-
"learning_rate": 7.
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 6.7,
|
| 475 |
-
"learning_rate": 7.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 6.8,
|
| 481 |
-
"learning_rate": 7.
|
| 482 |
-
"loss": 0.
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.9,
|
| 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": 1.
|
| 499 |
-
"step":
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.0,
|
| 503 |
-
"learning_rate": 7.
|
| 504 |
-
"loss": 0.
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.1,
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.2,
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
-
"loss": 0.
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.3,
|
| 521 |
-
"learning_rate": 7.
|
| 522 |
"loss": 0.0006,
|
| 523 |
-
"step":
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.4,
|
| 527 |
-
"learning_rate": 6.
|
| 528 |
-
"loss": 0.
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.5,
|
| 533 |
-
"learning_rate": 6.
|
| 534 |
-
"loss": 0.
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 7.6,
|
| 539 |
-
"learning_rate": 6.
|
| 540 |
"loss": 0.0006,
|
| 541 |
-
"step":
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.7,
|
| 545 |
-
"learning_rate": 6.
|
| 546 |
-
"loss": 0.
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 7.8,
|
| 551 |
-
"learning_rate": 6.
|
| 552 |
-
"loss": 0.
|
| 553 |
-
"step":
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 7.9,
|
| 557 |
-
"learning_rate": 6.
|
| 558 |
-
"loss": 0.
|
| 559 |
-
"step":
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
-
"eval_loss": 0.
|
| 564 |
-
"eval_max_distance":
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
-
"eval_runtime":
|
| 567 |
-
"eval_samples_per_second":
|
| 568 |
-
"eval_steps_per_second": 1.
|
| 569 |
-
"step":
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 8.0,
|
| 573 |
-
"learning_rate": 6.
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.1,
|
| 579 |
-
"learning_rate": 6.
|
| 580 |
-
"loss": 0.
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 8.2,
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 8.3,
|
| 591 |
-
"learning_rate": 6.
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.4,
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.5,
|
| 603 |
-
"learning_rate": 6.
|
| 604 |
-
"loss": 0.
|
| 605 |
-
"step":
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 8.6,
|
| 609 |
-
"learning_rate": 6.
|
| 610 |
-
"loss": 0.
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 8.7,
|
| 615 |
-
"learning_rate": 6.
|
| 616 |
-
"loss": 0.
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 8.8,
|
| 621 |
-
"learning_rate": 6.
|
| 622 |
-
"loss": 0.
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 8.9,
|
| 627 |
-
"learning_rate": 6.
|
| 628 |
-
"loss": 0.
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
-
"eval_loss": 0.
|
| 634 |
-
"eval_max_distance":
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
-
"eval_runtime":
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second": 1.
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 9.0,
|
| 643 |
-
"learning_rate": 6.
|
| 644 |
-
"loss": 0.
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 9.1,
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 9.2,
|
| 655 |
-
"learning_rate": 5.
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 9.3,
|
| 661 |
-
"learning_rate": 5.
|
| 662 |
"loss": 0.0005,
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 9.4,
|
| 667 |
-
"learning_rate": 5.
|
| 668 |
-
"loss": 0.
|
| 669 |
-
"step":
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 9.5,
|
| 673 |
-
"learning_rate": 5.
|
| 674 |
-
"loss": 0.
|
| 675 |
-
"step":
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 9.6,
|
| 679 |
-
"learning_rate": 5.
|
| 680 |
"loss": 0.0006,
|
| 681 |
-
"step":
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 9.7,
|
| 685 |
-
"learning_rate": 5.
|
| 686 |
-
"loss": 0.
|
| 687 |
-
"step":
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 9.8,
|
| 691 |
-
"learning_rate": 5.
|
| 692 |
-
"loss": 0.
|
| 693 |
-
"step":
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 9.9,
|
| 697 |
-
"learning_rate": 5.
|
| 698 |
-
"loss": 0.
|
| 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": 1.
|
| 709 |
-
"step":
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 10.0,
|
| 713 |
-
"learning_rate": 5.
|
| 714 |
-
"loss": 0.
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 10.1,
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 10.2,
|
| 725 |
-
"learning_rate": 5.
|
| 726 |
-
"loss": 0.
|
| 727 |
-
"step":
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 10.3,
|
| 731 |
-
"learning_rate": 5.
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"step":
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 10.4,
|
| 737 |
-
"learning_rate": 5.
|
| 738 |
-
"loss": 0.
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 10.5,
|
| 743 |
-
"learning_rate": 5.
|
| 744 |
"loss": 0.0005,
|
| 745 |
-
"step":
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 10.6,
|
| 749 |
-
"learning_rate": 5.
|
| 750 |
-
"loss": 0.
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 10.7,
|
| 755 |
-
"learning_rate": 5.
|
| 756 |
-
"loss": 0.
|
| 757 |
-
"step":
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 10.8,
|
| 761 |
-
"learning_rate": 5.
|
| 762 |
"loss": 0.0006,
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 10.9,
|
| 767 |
-
"learning_rate": 5.
|
| 768 |
-
"loss": 0.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
-
"eval_loss": 0.
|
| 774 |
"eval_max_distance": 1,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
-
"eval_runtime":
|
| 777 |
-
"eval_samples_per_second":
|
| 778 |
-
"eval_steps_per_second": 1.
|
| 779 |
-
"step":
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 11.0,
|
| 783 |
-
"learning_rate": 4.
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
"epoch": 11.1,
|
| 789 |
-
"learning_rate": 4.
|
| 790 |
-
"loss": 0.
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 11.2,
|
| 795 |
-
"learning_rate": 4.
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 11.3,
|
| 801 |
-
"learning_rate": 4.
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 11.4,
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 11.5,
|
| 813 |
-
"learning_rate": 4.
|
| 814 |
-
"loss": 0.
|
| 815 |
-
"step":
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 11.6,
|
| 819 |
-
"learning_rate": 4.
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 11.7,
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 11.8,
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
-
"loss": 0.
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 11.9,
|
| 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": 1.
|
| 849 |
-
"step":
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 12.0,
|
| 853 |
-
"learning_rate": 4.
|
| 854 |
-
"loss": 0.
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 12.1,
|
| 859 |
-
"learning_rate": 4.
|
| 860 |
-
"loss": 0.
|
| 861 |
-
"step":
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 12.2,
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 12.3,
|
| 871 |
-
"learning_rate": 4.
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 12.4,
|
| 877 |
-
"learning_rate": 4.
|
| 878 |
-
"loss": 0.
|
| 879 |
-
"step":
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 12.5,
|
| 883 |
-
"learning_rate": 4.
|
| 884 |
"loss": 0.0004,
|
| 885 |
-
"step":
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 12.6,
|
| 889 |
-
"learning_rate": 4.
|
| 890 |
-
"loss": 0.
|
| 891 |
-
"step":
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 12.7,
|
| 895 |
-
"learning_rate": 4.
|
| 896 |
-
"loss": 0.
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 12.8,
|
| 901 |
-
"learning_rate": 3.
|
| 902 |
-
"loss": 0.
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 12.9,
|
| 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": 1.
|
| 919 |
-
"step":
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 13.0,
|
| 923 |
-
"learning_rate": 3.
|
| 924 |
-
"loss": 0.
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 13.1,
|
| 929 |
-
"learning_rate": 3.
|
| 930 |
-
"loss": 0.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"epoch": 13.2,
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 13.3,
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 13.4,
|
| 947 |
-
"learning_rate": 3.
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 13.5,
|
| 953 |
-
"learning_rate": 3.
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 13.6,
|
| 959 |
-
"learning_rate": 3.
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
"epoch": 13.7,
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
-
"loss": 0.
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 13.8,
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 13.9,
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
-
"loss": 0.
|
| 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": 1.
|
| 989 |
-
"step":
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 14.0,
|
| 993 |
-
"learning_rate": 3.
|
| 994 |
"loss": 0.0004,
|
| 995 |
-
"step":
|
| 996 |
},
|
| 997 |
{
|
| 998 |
"epoch": 14.1,
|
| 999 |
-
"learning_rate": 3.
|
| 1000 |
-
"loss": 0.
|
| 1001 |
-
"step":
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 14.2,
|
| 1005 |
-
"learning_rate": 3.
|
| 1006 |
-
"loss": 0.
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 14.3,
|
| 1011 |
-
"learning_rate": 3.
|
| 1012 |
-
"loss": 0.
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 14.4,
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
"loss": 0.0004,
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 14.5,
|
| 1023 |
-
"learning_rate": 3.
|
| 1024 |
-
"loss": 0.
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 14.6,
|
| 1029 |
-
"learning_rate": 2.
|
| 1030 |
-
"loss": 0.
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
"epoch": 14.7,
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
-
"loss": 0.
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
"epoch": 14.8,
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 14.9,
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
"loss": 0.0004,
|
| 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": 1.
|
| 1059 |
-
"step":
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 15.0,
|
| 1063 |
-
"learning_rate": 2.
|
| 1064 |
-
"loss": 0.
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 15.1,
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 15.2,
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
-
"loss": 0.
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 15.3,
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
-
"loss": 0.
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 15.4,
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
-
"loss": 0.
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 15.5,
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
-
"loss": 0.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 15.6,
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
"loss": 0.0004,
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 15.7,
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
"loss": 0.0004,
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 15.8,
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 15.9,
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
-
"loss": 0.
|
| 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": 1.
|
| 1129 |
-
"step":
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 16.0,
|
| 1133 |
-
"learning_rate": 2.
|
| 1134 |
-
"loss": 0.
|
| 1135 |
-
"step":
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
"epoch": 16.1,
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
"loss": 0.0004,
|
| 1141 |
-
"step":
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 16.2,
|
| 1145 |
-
"learning_rate": 2.
|
| 1146 |
"loss": 0.0004,
|
| 1147 |
-
"step":
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
"epoch": 16.3,
|
| 1151 |
-
"learning_rate": 2.
|
| 1152 |
-
"loss": 0.
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
"epoch": 16.4,
|
| 1157 |
-
"learning_rate": 1.
|
| 1158 |
-
"loss": 0.
|
| 1159 |
-
"step":
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
"epoch": 16.5,
|
| 1163 |
-
"learning_rate": 1.
|
| 1164 |
"loss": 0.0004,
|
| 1165 |
-
"step":
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
"epoch": 16.6,
|
| 1169 |
-
"learning_rate": 1.
|
| 1170 |
-
"loss": 0.
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 16.7,
|
| 1175 |
-
"learning_rate": 1.
|
| 1176 |
-
"loss": 0.
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 16.8,
|
| 1181 |
-
"learning_rate": 1.
|
| 1182 |
-
"loss": 0.
|
| 1183 |
-
"step":
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 16.9,
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
"loss": 0.0004,
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
-
"eval_loss": 0.
|
| 1194 |
"eval_max_distance": 1,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
-
"eval_runtime":
|
| 1197 |
-
"eval_samples_per_second":
|
| 1198 |
-
"eval_steps_per_second": 1.
|
| 1199 |
-
"step":
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 17.0,
|
| 1203 |
-
"learning_rate": 1.
|
| 1204 |
"loss": 0.0004,
|
| 1205 |
-
"step":
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 17.1,
|
| 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.
|
| 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": 1.
|
| 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": 0.0004,
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch": 18.
|
| 1315 |
-
"learning_rate": 7.
|
| 1316 |
-
"loss": 0.
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch": 18.
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
"loss": 0.0003,
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18.
|
| 1327 |
-
"learning_rate": 6.
|
| 1328 |
-
"loss": 0.
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
-
"eval_loss": 0.
|
| 1334 |
"eval_max_distance": 1,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
-
"eval_runtime":
|
| 1337 |
-
"eval_samples_per_second":
|
| 1338 |
-
"eval_steps_per_second": 1.
|
| 1339 |
-
"step":
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
-
"epoch": 19.
|
| 1343 |
-
"learning_rate": 5.
|
| 1344 |
-
"loss": 0.
|
| 1345 |
-
"step":
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
-
"epoch": 19.
|
| 1349 |
-
"learning_rate": 4.
|
| 1350 |
-
"loss": 0.
|
| 1351 |
-
"step":
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"epoch": 19.
|
| 1355 |
-
"learning_rate": 4.
|
| 1356 |
-
"loss": 0.
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch": 19.
|
| 1361 |
-
"learning_rate": 3.
|
| 1362 |
-
"loss": 0.
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch": 19.
|
| 1367 |
-
"learning_rate": 3.
|
| 1368 |
-
"loss": 0.
|
| 1369 |
-
"step":
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch": 19.
|
| 1373 |
-
"learning_rate": 2.
|
| 1374 |
-
"loss": 0.
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch": 19.
|
| 1379 |
-
"learning_rate": 2.
|
| 1380 |
"loss": 0.0003,
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch": 19.
|
| 1385 |
-
"learning_rate": 1.
|
| 1386 |
-
"loss": 0.
|
| 1387 |
-
"step":
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
-
"epoch": 19.
|
| 1391 |
-
"learning_rate": 1.
|
| 1392 |
"loss": 0.0003,
|
| 1393 |
-
"step":
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"epoch": 19.
|
| 1397 |
-
"learning_rate": 5.
|
| 1398 |
-
"loss": 0.
|
| 1399 |
-
"step":
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
-
"eval_loss": 0.
|
| 1404 |
"eval_max_distance": 1,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
-
"eval_runtime":
|
| 1407 |
-
"eval_samples_per_second":
|
| 1408 |
-
"eval_steps_per_second": 1.
|
| 1409 |
-
"step":
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
-
"step":
|
| 1414 |
-
"total_flos": 7.
|
| 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": 7.
|
| 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": 274940,
|
| 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": 3.6371571979340947e-09,
|
| 14 |
"loss": 0.0,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.001091147159381e-06,
|
| 20 |
+
"loss": 0.0005,
|
| 21 |
+
"step": 1375
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.0002182294318761e-05,
|
| 26 |
+
"loss": 0.0005,
|
| 27 |
+
"step": 2750
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.5003273441478141e-05,
|
| 32 |
+
"loss": 0.0004,
|
| 33 |
+
"step": 4125
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.0004364588637523e-05,
|
| 38 |
+
"loss": 0.0004,
|
| 39 |
+
"step": 5500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.50054557357969e-05,
|
| 44 |
+
"loss": 0.0005,
|
| 45 |
+
"step": 6875
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.0006546882956283e-05,
|
| 50 |
+
"loss": 0.0004,
|
| 51 |
+
"step": 8250
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.5007638030115664e-05,
|
| 56 |
+
"loss": 0.0004,
|
| 57 |
+
"step": 9625
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.0008729177275046e-05,
|
| 62 |
+
"loss": 0.0005,
|
| 63 |
+
"step": 11000
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.500982032443443e-05,
|
| 68 |
+
"loss": 0.0005,
|
| 69 |
+
"step": 12375
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 0.015108300372958183,
|
| 74 |
+
"eval_max_distance": 3,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 16.7885,
|
| 77 |
+
"eval_samples_per_second": 15.963,
|
| 78 |
+
"eval_steps_per_second": 1.072,
|
| 79 |
+
"step": 13747
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.00109114715938e-05,
|
| 84 |
+
"loss": 0.0005,
|
| 85 |
+
"step": 13750
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 5.501200261875319e-05,
|
| 90 |
+
"loss": 0.0005,
|
| 91 |
+
"step": 15125
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 6.0013093765912565e-05,
|
| 96 |
+
"loss": 0.0005,
|
| 97 |
+
"step": 16500
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 6.501418491307195e-05,
|
| 102 |
+
"loss": 0.0005,
|
| 103 |
+
"step": 17875
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 7.001527606023133e-05,
|
| 108 |
+
"loss": 0.0005,
|
| 109 |
+
"step": 19250
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 7.50163672073907e-05,
|
| 114 |
+
"loss": 0.0005,
|
| 115 |
+
"step": 20625
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 8.001745835455009e-05,
|
| 120 |
+
"loss": 0.0005,
|
| 121 |
+
"step": 22000
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 8.501854950170947e-05,
|
| 126 |
+
"loss": 0.0005,
|
| 127 |
+
"step": 23375
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 9.001964064886885e-05,
|
| 132 |
+
"loss": 0.0005,
|
| 133 |
+
"step": 24750
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 9.502073179602823e-05,
|
| 138 |
+
"loss": 0.0005,
|
| 139 |
+
"step": 26125
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 0.0173035915941,
|
| 144 |
"eval_max_distance": 3,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 16.2636,
|
| 147 |
+
"eval_samples_per_second": 16.479,
|
| 148 |
+
"eval_steps_per_second": 1.107,
|
| 149 |
+
"step": 27494
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 9.999757522853471e-05,
|
| 154 |
+
"loss": 0.0006,
|
| 155 |
+
"step": 27500
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 2.1,
|
| 159 |
+
"learning_rate": 9.94418984344059e-05,
|
| 160 |
+
"loss": 0.0005,
|
| 161 |
+
"step": 28875
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.2,
|
| 165 |
+
"learning_rate": 9.888622164027708e-05,
|
| 166 |
+
"loss": 0.0006,
|
| 167 |
+
"step": 30250
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.3,
|
| 171 |
+
"learning_rate": 9.833054484614825e-05,
|
| 172 |
+
"loss": 0.0006,
|
| 173 |
+
"step": 31625
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.4,
|
| 177 |
+
"learning_rate": 9.777486805201943e-05,
|
| 178 |
+
"loss": 0.0006,
|
| 179 |
+
"step": 33000
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 2.5,
|
| 183 |
+
"learning_rate": 9.721919125789062e-05,
|
| 184 |
+
"loss": 0.0006,
|
| 185 |
+
"step": 34375
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.6,
|
| 189 |
+
"learning_rate": 9.66635144637618e-05,
|
| 190 |
+
"loss": 0.0007,
|
| 191 |
+
"step": 35750
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.7,
|
| 195 |
+
"learning_rate": 9.610783766963298e-05,
|
| 196 |
+
"loss": 0.0006,
|
| 197 |
+
"step": 37125
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.8,
|
| 201 |
+
"learning_rate": 9.555216087550416e-05,
|
| 202 |
+
"loss": 0.0006,
|
| 203 |
+
"step": 38500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.9,
|
| 207 |
+
"learning_rate": 9.499648408137534e-05,
|
| 208 |
+
"loss": 0.0006,
|
| 209 |
+
"step": 39875
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 0.013588453643023968,
|
| 214 |
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 15.87,
|
| 217 |
+
"eval_samples_per_second": 16.887,
|
| 218 |
+
"eval_steps_per_second": 1.134,
|
| 219 |
+
"step": 41241
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 3.0,
|
| 223 |
+
"learning_rate": 9.444080728724652e-05,
|
| 224 |
+
"loss": 0.0006,
|
| 225 |
+
"step": 41250
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 3.1,
|
| 229 |
+
"learning_rate": 9.38851304931177e-05,
|
| 230 |
+
"loss": 0.0006,
|
| 231 |
+
"step": 42625
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 3.2,
|
| 235 |
+
"learning_rate": 9.332945369898887e-05,
|
| 236 |
+
"loss": 0.0005,
|
| 237 |
+
"step": 44000
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 3.3,
|
| 241 |
+
"learning_rate": 9.277377690486005e-05,
|
| 242 |
+
"loss": 0.0006,
|
| 243 |
+
"step": 45375
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 3.4,
|
| 247 |
+
"learning_rate": 9.221810011073123e-05,
|
| 248 |
+
"loss": 0.0006,
|
| 249 |
+
"step": 46750
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 3.5,
|
| 253 |
+
"learning_rate": 9.166242331660242e-05,
|
| 254 |
+
"loss": 0.0007,
|
| 255 |
+
"step": 48125
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.6,
|
| 259 |
+
"learning_rate": 9.110674652247359e-05,
|
| 260 |
+
"loss": 0.0006,
|
| 261 |
+
"step": 49500
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 3.7,
|
| 265 |
+
"learning_rate": 9.055106972834477e-05,
|
| 266 |
+
"loss": 0.0006,
|
| 267 |
+
"step": 50875
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.8,
|
| 271 |
+
"learning_rate": 8.999539293421595e-05,
|
| 272 |
+
"loss": 0.0007,
|
| 273 |
+
"step": 52250
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 3.9,
|
| 277 |
+
"learning_rate": 8.943971614008714e-05,
|
| 278 |
+
"loss": 0.0007,
|
| 279 |
+
"step": 53625
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 0.014065152034163475,
|
| 284 |
+
"eval_max_distance": 2,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 15.9652,
|
| 287 |
+
"eval_samples_per_second": 16.787,
|
| 288 |
+
"eval_steps_per_second": 1.127,
|
| 289 |
+
"step": 54988
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 4.0,
|
| 293 |
+
"learning_rate": 8.888403934595832e-05,
|
| 294 |
+
"loss": 0.0006,
|
| 295 |
+
"step": 55000
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 4.1,
|
| 299 |
+
"learning_rate": 8.832836255182949e-05,
|
| 300 |
+
"loss": 0.0006,
|
| 301 |
+
"step": 56375
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 4.2,
|
| 305 |
+
"learning_rate": 8.777268575770068e-05,
|
| 306 |
+
"loss": 0.0006,
|
| 307 |
+
"step": 57750
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 4.3,
|
| 311 |
+
"learning_rate": 8.721700896357186e-05,
|
| 312 |
+
"loss": 0.0005,
|
| 313 |
+
"step": 59125
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 4.4,
|
| 317 |
+
"learning_rate": 8.666133216944304e-05,
|
| 318 |
+
"loss": 0.0006,
|
| 319 |
+
"step": 60500
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 4.5,
|
| 323 |
+
"learning_rate": 8.610565537531422e-05,
|
| 324 |
+
"loss": 0.0005,
|
| 325 |
+
"step": 61875
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.6,
|
| 329 |
+
"learning_rate": 8.55499785811854e-05,
|
| 330 |
+
"loss": 0.0006,
|
| 331 |
+
"step": 63250
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 4.7,
|
| 335 |
+
"learning_rate": 8.499430178705657e-05,
|
| 336 |
+
"loss": 0.0007,
|
| 337 |
+
"step": 64625
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.8,
|
| 341 |
+
"learning_rate": 8.443862499292775e-05,
|
| 342 |
+
"loss": 0.0006,
|
| 343 |
+
"step": 66000
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 4.9,
|
| 347 |
+
"learning_rate": 8.388294819879895e-05,
|
| 348 |
+
"loss": 0.0006,
|
| 349 |
+
"step": 67375
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 0.015543907880783081,
|
| 354 |
+
"eval_max_distance": 4,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 15.8832,
|
| 357 |
+
"eval_samples_per_second": 16.873,
|
| 358 |
+
"eval_steps_per_second": 1.133,
|
| 359 |
+
"step": 68735
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 5.0,
|
| 363 |
+
"learning_rate": 8.332727140467011e-05,
|
| 364 |
+
"loss": 0.0006,
|
| 365 |
+
"step": 68750
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.1,
|
| 369 |
+
"learning_rate": 8.277159461054129e-05,
|
| 370 |
+
"loss": 0.0006,
|
| 371 |
+
"step": 70125
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 5.2,
|
| 375 |
+
"learning_rate": 8.221591781641247e-05,
|
| 376 |
+
"loss": 0.0006,
|
| 377 |
+
"step": 71500
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 5.3,
|
| 381 |
+
"learning_rate": 8.166024102228366e-05,
|
| 382 |
+
"loss": 0.0006,
|
| 383 |
+
"step": 72875
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.4,
|
| 387 |
+
"learning_rate": 8.110456422815483e-05,
|
| 388 |
+
"loss": 0.0006,
|
| 389 |
+
"step": 74250
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 5.5,
|
| 393 |
+
"learning_rate": 8.0548887434026e-05,
|
| 394 |
+
"loss": 0.0006,
|
| 395 |
+
"step": 75625
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 5.6,
|
| 399 |
+
"learning_rate": 7.99932106398972e-05,
|
| 400 |
+
"loss": 0.0006,
|
| 401 |
+
"step": 77000
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 5.7,
|
| 405 |
+
"learning_rate": 7.943753384576838e-05,
|
| 406 |
+
"loss": 0.0006,
|
| 407 |
+
"step": 78375
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 5.8,
|
| 411 |
+
"learning_rate": 7.888185705163956e-05,
|
| 412 |
+
"loss": 0.0006,
|
| 413 |
+
"step": 79750
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 5.9,
|
| 417 |
+
"learning_rate": 7.832618025751072e-05,
|
| 418 |
+
"loss": 0.0005,
|
| 419 |
+
"step": 81125
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 0.018322547897696495,
|
| 424 |
+
"eval_max_distance": 4,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 15.9589,
|
| 427 |
+
"eval_samples_per_second": 16.793,
|
| 428 |
+
"eval_steps_per_second": 1.128,
|
| 429 |
+
"step": 82482
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 6.0,
|
| 433 |
+
"learning_rate": 7.777050346338192e-05,
|
| 434 |
+
"loss": 0.0006,
|
| 435 |
+
"step": 82500
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.1,
|
| 439 |
+
"learning_rate": 7.72148266692531e-05,
|
| 440 |
+
"loss": 0.0005,
|
| 441 |
+
"step": 83875
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.2,
|
| 445 |
+
"learning_rate": 7.665914987512427e-05,
|
| 446 |
+
"loss": 0.0005,
|
| 447 |
+
"step": 85250
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.3,
|
| 451 |
+
"learning_rate": 7.610347308099545e-05,
|
| 452 |
+
"loss": 0.0005,
|
| 453 |
+
"step": 86625
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 6.4,
|
| 457 |
+
"learning_rate": 7.554779628686663e-05,
|
| 458 |
+
"loss": 0.0006,
|
| 459 |
+
"step": 88000
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 6.5,
|
| 463 |
+
"learning_rate": 7.499211949273781e-05,
|
| 464 |
+
"loss": 0.0005,
|
| 465 |
+
"step": 89375
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 6.6,
|
| 469 |
+
"learning_rate": 7.443644269860899e-05,
|
| 470 |
+
"loss": 0.0005,
|
| 471 |
+
"step": 90750
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 6.7,
|
| 475 |
+
"learning_rate": 7.388076590448018e-05,
|
| 476 |
+
"loss": 0.0005,
|
| 477 |
+
"step": 92125
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 6.8,
|
| 481 |
+
"learning_rate": 7.332508911035135e-05,
|
| 482 |
+
"loss": 0.0006,
|
| 483 |
+
"step": 93500
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.9,
|
| 487 |
+
"learning_rate": 7.276941231622253e-05,
|
| 488 |
+
"loss": 0.0005,
|
| 489 |
+
"step": 94875
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 0.021769728511571884,
|
| 494 |
+
"eval_max_distance": 4,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 15.9282,
|
| 497 |
+
"eval_samples_per_second": 16.825,
|
| 498 |
+
"eval_steps_per_second": 1.13,
|
| 499 |
+
"step": 96229
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.0,
|
| 503 |
+
"learning_rate": 7.221373552209372e-05,
|
| 504 |
+
"loss": 0.0005,
|
| 505 |
+
"step": 96250
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.1,
|
| 509 |
+
"learning_rate": 7.16580587279649e-05,
|
| 510 |
+
"loss": 0.0005,
|
| 511 |
+
"step": 97625
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.2,
|
| 515 |
+
"learning_rate": 7.110238193383608e-05,
|
| 516 |
+
"loss": 0.0005,
|
| 517 |
+
"step": 99000
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.3,
|
| 521 |
+
"learning_rate": 7.054670513970724e-05,
|
| 522 |
"loss": 0.0006,
|
| 523 |
+
"step": 100375
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.4,
|
| 527 |
+
"learning_rate": 6.999102834557844e-05,
|
| 528 |
+
"loss": 0.0005,
|
| 529 |
+
"step": 101750
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.5,
|
| 533 |
+
"learning_rate": 6.943535155144961e-05,
|
| 534 |
+
"loss": 0.0007,
|
| 535 |
+
"step": 103125
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 7.6,
|
| 539 |
+
"learning_rate": 6.88796747573208e-05,
|
| 540 |
"loss": 0.0006,
|
| 541 |
+
"step": 104500
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.7,
|
| 545 |
+
"learning_rate": 6.832399796319197e-05,
|
| 546 |
+
"loss": 0.0006,
|
| 547 |
+
"step": 105875
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 7.8,
|
| 551 |
+
"learning_rate": 6.776832116906315e-05,
|
| 552 |
+
"loss": 0.0005,
|
| 553 |
+
"step": 107250
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 7.9,
|
| 557 |
+
"learning_rate": 6.721264437493433e-05,
|
| 558 |
+
"loss": 0.0005,
|
| 559 |
+
"step": 108625
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 0.016180865466594696,
|
| 564 |
+
"eval_max_distance": 1,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 15.9709,
|
| 567 |
+
"eval_samples_per_second": 16.781,
|
| 568 |
+
"eval_steps_per_second": 1.127,
|
| 569 |
+
"step": 109976
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 8.0,
|
| 573 |
+
"learning_rate": 6.665696758080551e-05,
|
| 574 |
+
"loss": 0.0005,
|
| 575 |
+
"step": 110000
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.1,
|
| 579 |
+
"learning_rate": 6.610129078667669e-05,
|
| 580 |
+
"loss": 0.0005,
|
| 581 |
+
"step": 111375
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 8.2,
|
| 585 |
+
"learning_rate": 6.554561399254787e-05,
|
| 586 |
+
"loss": 0.0006,
|
| 587 |
+
"step": 112750
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 8.3,
|
| 591 |
+
"learning_rate": 6.498993719841905e-05,
|
| 592 |
+
"loss": 0.0005,
|
| 593 |
+
"step": 114125
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.4,
|
| 597 |
+
"learning_rate": 6.443426040429024e-05,
|
| 598 |
+
"loss": 0.0005,
|
| 599 |
+
"step": 115500
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.5,
|
| 603 |
+
"learning_rate": 6.387858361016142e-05,
|
| 604 |
+
"loss": 0.0005,
|
| 605 |
+
"step": 116875
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 8.6,
|
| 609 |
+
"learning_rate": 6.332290681603258e-05,
|
| 610 |
+
"loss": 0.0005,
|
| 611 |
+
"step": 118250
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 8.7,
|
| 615 |
+
"learning_rate": 6.276723002190376e-05,
|
| 616 |
+
"loss": 0.0005,
|
| 617 |
+
"step": 119625
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 8.8,
|
| 621 |
+
"learning_rate": 6.221155322777496e-05,
|
| 622 |
+
"loss": 0.0005,
|
| 623 |
+
"step": 121000
|
| 624 |
},
|
| 625 |
{
|
| 626 |
"epoch": 8.9,
|
| 627 |
+
"learning_rate": 6.165587643364614e-05,
|
| 628 |
+
"loss": 0.0005,
|
| 629 |
+
"step": 122375
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 0.014703923836350441,
|
| 634 |
+
"eval_max_distance": 3,
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 15.6578,
|
| 637 |
+
"eval_samples_per_second": 17.116,
|
| 638 |
+
"eval_steps_per_second": 1.15,
|
| 639 |
+
"step": 123723
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 9.0,
|
| 643 |
+
"learning_rate": 6.110019963951731e-05,
|
| 644 |
+
"loss": 0.0004,
|
| 645 |
+
"step": 123750
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 9.1,
|
| 649 |
+
"learning_rate": 6.0544522845388493e-05,
|
| 650 |
+
"loss": 0.0004,
|
| 651 |
+
"step": 125125
|
| 652 |
},
|
| 653 |
{
|
| 654 |
"epoch": 9.2,
|
| 655 |
+
"learning_rate": 5.998884605125967e-05,
|
| 656 |
+
"loss": 0.0005,
|
| 657 |
+
"step": 126500
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 9.3,
|
| 661 |
+
"learning_rate": 5.943316925713085e-05,
|
| 662 |
"loss": 0.0005,
|
| 663 |
+
"step": 127875
|
| 664 |
},
|
| 665 |
{
|
| 666 |
"epoch": 9.4,
|
| 667 |
+
"learning_rate": 5.8877492463002024e-05,
|
| 668 |
+
"loss": 0.0005,
|
| 669 |
+
"step": 129250
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 9.5,
|
| 673 |
+
"learning_rate": 5.8321815668873216e-05,
|
| 674 |
+
"loss": 0.0005,
|
| 675 |
+
"step": 130625
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 9.6,
|
| 679 |
+
"learning_rate": 5.776613887474439e-05,
|
| 680 |
"loss": 0.0006,
|
| 681 |
+
"step": 132000
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 9.7,
|
| 685 |
+
"learning_rate": 5.721046208061557e-05,
|
| 686 |
+
"loss": 0.0005,
|
| 687 |
+
"step": 133375
|
| 688 |
},
|
| 689 |
{
|
| 690 |
"epoch": 9.8,
|
| 691 |
+
"learning_rate": 5.6654785286486754e-05,
|
| 692 |
+
"loss": 0.0005,
|
| 693 |
+
"step": 134750
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 9.9,
|
| 697 |
+
"learning_rate": 5.609910849235793e-05,
|
| 698 |
+
"loss": 0.0005,
|
| 699 |
+
"step": 136125
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 0.018843844532966614,
|
| 704 |
+
"eval_max_distance": 5,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 15.9456,
|
| 707 |
+
"eval_samples_per_second": 16.807,
|
| 708 |
+
"eval_steps_per_second": 1.129,
|
| 709 |
+
"step": 137470
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 10.0,
|
| 713 |
+
"learning_rate": 5.554343169822911e-05,
|
| 714 |
+
"loss": 0.0005,
|
| 715 |
+
"step": 137500
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 10.1,
|
| 719 |
+
"learning_rate": 5.4987754904100284e-05,
|
| 720 |
+
"loss": 0.0005,
|
| 721 |
+
"step": 138875
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 10.2,
|
| 725 |
+
"learning_rate": 5.443207810997148e-05,
|
| 726 |
+
"loss": 0.0005,
|
| 727 |
+
"step": 140250
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 10.3,
|
| 731 |
+
"learning_rate": 5.387640131584265e-05,
|
| 732 |
+
"loss": 0.0005,
|
| 733 |
+
"step": 141625
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 10.4,
|
| 737 |
+
"learning_rate": 5.332072452171383e-05,
|
| 738 |
+
"loss": 0.0005,
|
| 739 |
+
"step": 143000
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 10.5,
|
| 743 |
+
"learning_rate": 5.2765047727585014e-05,
|
| 744 |
"loss": 0.0005,
|
| 745 |
+
"step": 144375
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 10.6,
|
| 749 |
+
"learning_rate": 5.220937093345619e-05,
|
| 750 |
+
"loss": 0.0004,
|
| 751 |
+
"step": 145750
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 10.7,
|
| 755 |
+
"learning_rate": 5.165369413932737e-05,
|
| 756 |
+
"loss": 0.0004,
|
| 757 |
+
"step": 147125
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 10.8,
|
| 761 |
+
"learning_rate": 5.1098017345198544e-05,
|
| 762 |
"loss": 0.0006,
|
| 763 |
+
"step": 148500
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 10.9,
|
| 767 |
+
"learning_rate": 5.054234055106973e-05,
|
| 768 |
+
"loss": 0.0004,
|
| 769 |
+
"step": 149875
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 0.016838768497109413,
|
| 774 |
"eval_max_distance": 1,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 15.6708,
|
| 777 |
+
"eval_samples_per_second": 17.102,
|
| 778 |
+
"eval_steps_per_second": 1.149,
|
| 779 |
+
"step": 151217
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 11.0,
|
| 783 |
+
"learning_rate": 4.998666375694091e-05,
|
| 784 |
+
"loss": 0.0005,
|
| 785 |
+
"step": 151250
|
| 786 |
},
|
| 787 |
{
|
| 788 |
"epoch": 11.1,
|
| 789 |
+
"learning_rate": 4.9430986962812095e-05,
|
| 790 |
+
"loss": 0.0004,
|
| 791 |
+
"step": 152625
|
| 792 |
},
|
| 793 |
{
|
| 794 |
"epoch": 11.2,
|
| 795 |
+
"learning_rate": 4.887531016868327e-05,
|
| 796 |
+
"loss": 0.0004,
|
| 797 |
+
"step": 154000
|
| 798 |
},
|
| 799 |
{
|
| 800 |
"epoch": 11.3,
|
| 801 |
+
"learning_rate": 4.831963337455445e-05,
|
| 802 |
+
"loss": 0.0004,
|
| 803 |
+
"step": 155375
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 11.4,
|
| 807 |
+
"learning_rate": 4.7763956580425626e-05,
|
| 808 |
+
"loss": 0.0004,
|
| 809 |
+
"step": 156750
|
| 810 |
},
|
| 811 |
{
|
| 812 |
"epoch": 11.5,
|
| 813 |
+
"learning_rate": 4.720827978629681e-05,
|
| 814 |
+
"loss": 0.0004,
|
| 815 |
+
"step": 158125
|
| 816 |
},
|
| 817 |
{
|
| 818 |
"epoch": 11.6,
|
| 819 |
+
"learning_rate": 4.665260299216799e-05,
|
| 820 |
+
"loss": 0.0004,
|
| 821 |
+
"step": 159500
|
| 822 |
},
|
| 823 |
{
|
| 824 |
"epoch": 11.7,
|
| 825 |
+
"learning_rate": 4.609692619803917e-05,
|
| 826 |
+
"loss": 0.0004,
|
| 827 |
+
"step": 160875
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 11.8,
|
| 831 |
+
"learning_rate": 4.5541249403910355e-05,
|
| 832 |
+
"loss": 0.0004,
|
| 833 |
+
"step": 162250
|
| 834 |
},
|
| 835 |
{
|
| 836 |
"epoch": 11.9,
|
| 837 |
+
"learning_rate": 4.498557260978153e-05,
|
| 838 |
+
"loss": 0.0004,
|
| 839 |
+
"step": 163625
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 0.017172418534755707,
|
| 844 |
+
"eval_max_distance": 4,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 15.706,
|
| 847 |
+
"eval_samples_per_second": 17.064,
|
| 848 |
+
"eval_steps_per_second": 1.146,
|
| 849 |
+
"step": 164964
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 12.0,
|
| 853 |
+
"learning_rate": 4.4429895815652714e-05,
|
| 854 |
+
"loss": 0.0004,
|
| 855 |
+
"step": 165000
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 12.1,
|
| 859 |
+
"learning_rate": 4.3874219021523886e-05,
|
| 860 |
+
"loss": 0.0004,
|
| 861 |
+
"step": 166375
|
| 862 |
},
|
| 863 |
{
|
| 864 |
"epoch": 12.2,
|
| 865 |
+
"learning_rate": 4.331854222739507e-05,
|
| 866 |
+
"loss": 0.0004,
|
| 867 |
+
"step": 167750
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 12.3,
|
| 871 |
+
"learning_rate": 4.276286543326625e-05,
|
| 872 |
+
"loss": 0.0004,
|
| 873 |
+
"step": 169125
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 12.4,
|
| 877 |
+
"learning_rate": 4.220718863913743e-05,
|
| 878 |
+
"loss": 0.0004,
|
| 879 |
+
"step": 170500
|
| 880 |
},
|
| 881 |
{
|
| 882 |
"epoch": 12.5,
|
| 883 |
+
"learning_rate": 4.165151184500861e-05,
|
| 884 |
"loss": 0.0004,
|
| 885 |
+
"step": 171875
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 12.6,
|
| 889 |
+
"learning_rate": 4.109583505087979e-05,
|
| 890 |
+
"loss": 0.0004,
|
| 891 |
+
"step": 173250
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 12.7,
|
| 895 |
+
"learning_rate": 4.0540158256750974e-05,
|
| 896 |
+
"loss": 0.0004,
|
| 897 |
+
"step": 174625
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 12.8,
|
| 901 |
+
"learning_rate": 3.9984481462622146e-05,
|
| 902 |
+
"loss": 0.0004,
|
| 903 |
+
"step": 176000
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 12.9,
|
| 907 |
+
"learning_rate": 3.942880466849333e-05,
|
| 908 |
+
"loss": 0.0004,
|
| 909 |
+
"step": 177375
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 0.01684817485511303,
|
| 914 |
+
"eval_max_distance": 3,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 15.8959,
|
| 917 |
+
"eval_samples_per_second": 16.86,
|
| 918 |
+
"eval_steps_per_second": 1.132,
|
| 919 |
+
"step": 178711
|
| 920 |
},
|
| 921 |
{
|
| 922 |
"epoch": 13.0,
|
| 923 |
+
"learning_rate": 3.887312787436451e-05,
|
| 924 |
+
"loss": 0.0004,
|
| 925 |
+
"step": 178750
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 13.1,
|
| 929 |
+
"learning_rate": 3.831745108023569e-05,
|
| 930 |
+
"loss": 0.0004,
|
| 931 |
+
"step": 180125
|
| 932 |
},
|
| 933 |
{
|
| 934 |
"epoch": 13.2,
|
| 935 |
+
"learning_rate": 3.776177428610687e-05,
|
| 936 |
+
"loss": 0.0003,
|
| 937 |
+
"step": 181500
|
| 938 |
},
|
| 939 |
{
|
| 940 |
"epoch": 13.3,
|
| 941 |
+
"learning_rate": 3.720609749197805e-05,
|
| 942 |
+
"loss": 0.0004,
|
| 943 |
+
"step": 182875
|
| 944 |
},
|
| 945 |
{
|
| 946 |
"epoch": 13.4,
|
| 947 |
+
"learning_rate": 3.665042069784923e-05,
|
| 948 |
+
"loss": 0.0003,
|
| 949 |
+
"step": 184250
|
| 950 |
},
|
| 951 |
{
|
| 952 |
"epoch": 13.5,
|
| 953 |
+
"learning_rate": 3.6094743903720406e-05,
|
| 954 |
+
"loss": 0.0005,
|
| 955 |
+
"step": 185625
|
| 956 |
},
|
| 957 |
{
|
| 958 |
"epoch": 13.6,
|
| 959 |
+
"learning_rate": 3.553906710959159e-05,
|
| 960 |
+
"loss": 0.0004,
|
| 961 |
+
"step": 187000
|
| 962 |
},
|
| 963 |
{
|
| 964 |
"epoch": 13.7,
|
| 965 |
+
"learning_rate": 3.498339031546277e-05,
|
| 966 |
+
"loss": 0.0004,
|
| 967 |
+
"step": 188375
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 13.8,
|
| 971 |
+
"learning_rate": 3.442771352133395e-05,
|
| 972 |
+
"loss": 0.0003,
|
| 973 |
+
"step": 189750
|
| 974 |
},
|
| 975 |
{
|
| 976 |
"epoch": 13.9,
|
| 977 |
+
"learning_rate": 3.387203672720513e-05,
|
| 978 |
+
"loss": 0.0004,
|
| 979 |
+
"step": 191125
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 0.01621120423078537,
|
| 984 |
+
"eval_max_distance": 2,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 15.9061,
|
| 987 |
+
"eval_samples_per_second": 16.849,
|
| 988 |
+
"eval_steps_per_second": 1.132,
|
| 989 |
+
"step": 192458
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 14.0,
|
| 993 |
+
"learning_rate": 3.331635993307631e-05,
|
| 994 |
"loss": 0.0004,
|
| 995 |
+
"step": 192500
|
| 996 |
},
|
| 997 |
{
|
| 998 |
"epoch": 14.1,
|
| 999 |
+
"learning_rate": 3.276068313894749e-05,
|
| 1000 |
+
"loss": 0.0003,
|
| 1001 |
+
"step": 193875
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
"epoch": 14.2,
|
| 1005 |
+
"learning_rate": 3.220500634481867e-05,
|
| 1006 |
+
"loss": 0.0004,
|
| 1007 |
+
"step": 195250
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 14.3,
|
| 1011 |
+
"learning_rate": 3.1649329550689846e-05,
|
| 1012 |
+
"loss": 0.0003,
|
| 1013 |
+
"step": 196625
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 14.4,
|
| 1017 |
+
"learning_rate": 3.109365275656103e-05,
|
| 1018 |
"loss": 0.0004,
|
| 1019 |
+
"step": 198000
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 14.5,
|
| 1023 |
+
"learning_rate": 3.053797596243221e-05,
|
| 1024 |
+
"loss": 0.0003,
|
| 1025 |
+
"step": 199375
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 14.6,
|
| 1029 |
+
"learning_rate": 2.998229916830339e-05,
|
| 1030 |
+
"loss": 0.0004,
|
| 1031 |
+
"step": 200750
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
"epoch": 14.7,
|
| 1035 |
+
"learning_rate": 2.942662237417457e-05,
|
| 1036 |
+
"loss": 0.0003,
|
| 1037 |
+
"step": 202125
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
"epoch": 14.8,
|
| 1041 |
+
"learning_rate": 2.8870945580045748e-05,
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
+
"step": 203500
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 14.9,
|
| 1047 |
+
"learning_rate": 2.8315268785916927e-05,
|
| 1048 |
"loss": 0.0004,
|
| 1049 |
+
"step": 204875
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 0.016450826078653336,
|
| 1054 |
+
"eval_max_distance": 2,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 15.843,
|
| 1057 |
+
"eval_samples_per_second": 16.916,
|
| 1058 |
+
"eval_steps_per_second": 1.136,
|
| 1059 |
+
"step": 206205
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 15.0,
|
| 1063 |
+
"learning_rate": 2.775959199178811e-05,
|
| 1064 |
+
"loss": 0.0003,
|
| 1065 |
+
"step": 206250
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
"epoch": 15.1,
|
| 1069 |
+
"learning_rate": 2.7203915197659292e-05,
|
| 1070 |
+
"loss": 0.0003,
|
| 1071 |
+
"step": 207625
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 15.2,
|
| 1075 |
+
"learning_rate": 2.6648238403530468e-05,
|
| 1076 |
+
"loss": 0.0003,
|
| 1077 |
+
"step": 209000
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
"epoch": 15.3,
|
| 1081 |
+
"learning_rate": 2.609256160940165e-05,
|
| 1082 |
+
"loss": 0.0003,
|
| 1083 |
+
"step": 210375
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
"epoch": 15.4,
|
| 1087 |
+
"learning_rate": 2.5536884815272826e-05,
|
| 1088 |
+
"loss": 0.0003,
|
| 1089 |
+
"step": 211750
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 15.5,
|
| 1093 |
+
"learning_rate": 2.4981208021144008e-05,
|
| 1094 |
+
"loss": 0.0004,
|
| 1095 |
+
"step": 213125
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
"epoch": 15.6,
|
| 1099 |
+
"learning_rate": 2.4425531227015187e-05,
|
| 1100 |
"loss": 0.0004,
|
| 1101 |
+
"step": 214500
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 15.7,
|
| 1105 |
+
"learning_rate": 2.386985443288637e-05,
|
| 1106 |
"loss": 0.0004,
|
| 1107 |
+
"step": 215875
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
"epoch": 15.8,
|
| 1111 |
+
"learning_rate": 2.331417763875755e-05,
|
| 1112 |
+
"loss": 0.0003,
|
| 1113 |
+
"step": 217250
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 15.9,
|
| 1117 |
+
"learning_rate": 2.2758500844628728e-05,
|
| 1118 |
+
"loss": 0.0003,
|
| 1119 |
+
"step": 218625
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 0.015056570991873741,
|
| 1124 |
+
"eval_max_distance": 3,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 15.5877,
|
| 1127 |
+
"eval_samples_per_second": 17.193,
|
| 1128 |
+
"eval_steps_per_second": 1.155,
|
| 1129 |
+
"step": 219952
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 16.0,
|
| 1133 |
+
"learning_rate": 2.2202824050499907e-05,
|
| 1134 |
+
"loss": 0.0003,
|
| 1135 |
+
"step": 220000
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
"epoch": 16.1,
|
| 1139 |
+
"learning_rate": 2.164714725637109e-05,
|
| 1140 |
"loss": 0.0004,
|
| 1141 |
+
"step": 221375
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
"epoch": 16.2,
|
| 1145 |
+
"learning_rate": 2.109147046224227e-05,
|
| 1146 |
"loss": 0.0004,
|
| 1147 |
+
"step": 222750
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
"epoch": 16.3,
|
| 1151 |
+
"learning_rate": 2.0535793668113448e-05,
|
| 1152 |
+
"loss": 0.0003,
|
| 1153 |
+
"step": 224125
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
"epoch": 16.4,
|
| 1157 |
+
"learning_rate": 1.9980116873984627e-05,
|
| 1158 |
+
"loss": 0.0003,
|
| 1159 |
+
"step": 225500
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
"epoch": 16.5,
|
| 1163 |
+
"learning_rate": 1.9424440079855806e-05,
|
| 1164 |
"loss": 0.0004,
|
| 1165 |
+
"step": 226875
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
"epoch": 16.6,
|
| 1169 |
+
"learning_rate": 1.8868763285726988e-05,
|
| 1170 |
+
"loss": 0.0003,
|
| 1171 |
+
"step": 228250
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 16.7,
|
| 1175 |
+
"learning_rate": 1.8313086491598167e-05,
|
| 1176 |
+
"loss": 0.0003,
|
| 1177 |
+
"step": 229625
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
"epoch": 16.8,
|
| 1181 |
+
"learning_rate": 1.775740969746935e-05,
|
| 1182 |
+
"loss": 0.0003,
|
| 1183 |
+
"step": 231000
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
"epoch": 16.9,
|
| 1187 |
+
"learning_rate": 1.720173290334053e-05,
|
| 1188 |
"loss": 0.0004,
|
| 1189 |
+
"step": 232375
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 0.01368328370153904,
|
| 1194 |
"eval_max_distance": 1,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 15.9295,
|
| 1197 |
+
"eval_samples_per_second": 16.824,
|
| 1198 |
+
"eval_steps_per_second": 1.13,
|
| 1199 |
+
"step": 233699
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 17.0,
|
| 1203 |
+
"learning_rate": 1.6646056109211708e-05,
|
| 1204 |
"loss": 0.0004,
|
| 1205 |
+
"step": 233750
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 17.1,
|
| 1209 |
+
"learning_rate": 1.6090379315082887e-05,
|
| 1210 |
+
"loss": 0.0003,
|
| 1211 |
+
"step": 235125
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
+
"epoch": 17.2,
|
| 1215 |
+
"learning_rate": 1.5534702520954066e-05,
|
| 1216 |
+
"loss": 0.0003,
|
| 1217 |
+
"step": 236500
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 17.3,
|
| 1221 |
+
"learning_rate": 1.4979025726825247e-05,
|
| 1222 |
+
"loss": 0.0003,
|
| 1223 |
+
"step": 237875
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"epoch": 17.4,
|
| 1227 |
+
"learning_rate": 1.4423348932696426e-05,
|
| 1228 |
+
"loss": 0.0003,
|
| 1229 |
+
"step": 239250
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
+
"epoch": 17.5,
|
| 1233 |
+
"learning_rate": 1.3867672138567608e-05,
|
| 1234 |
+
"loss": 0.0003,
|
| 1235 |
+
"step": 240625
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
+
"epoch": 17.6,
|
| 1239 |
+
"learning_rate": 1.3311995344438787e-05,
|
| 1240 |
+
"loss": 0.0003,
|
| 1241 |
+
"step": 242000
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 17.7,
|
| 1245 |
+
"learning_rate": 1.2756318550309968e-05,
|
| 1246 |
+
"loss": 0.0003,
|
| 1247 |
+
"step": 243375
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
+
"epoch": 17.8,
|
| 1251 |
+
"learning_rate": 1.2200641756181147e-05,
|
| 1252 |
+
"loss": 0.0003,
|
| 1253 |
+
"step": 244750
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
+
"epoch": 17.9,
|
| 1257 |
+
"learning_rate": 1.1644964962052326e-05,
|
| 1258 |
+
"loss": 0.0003,
|
| 1259 |
+
"step": 246125
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 0.014638499356806278,
|
| 1264 |
+
"eval_max_distance": 3,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 15.7143,
|
| 1267 |
+
"eval_samples_per_second": 17.054,
|
| 1268 |
+
"eval_steps_per_second": 1.145,
|
| 1269 |
+
"step": 247446
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 18.0,
|
| 1273 |
+
"learning_rate": 1.1089288167923507e-05,
|
| 1274 |
+
"loss": 0.0003,
|
| 1275 |
+
"step": 247500
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 18.1,
|
| 1279 |
+
"learning_rate": 1.0533611373794686e-05,
|
| 1280 |
+
"loss": 0.0003,
|
| 1281 |
+
"step": 248875
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 18.2,
|
| 1285 |
+
"learning_rate": 9.977934579665867e-06,
|
| 1286 |
+
"loss": 0.0003,
|
| 1287 |
+
"step": 250250
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 18.3,
|
| 1291 |
+
"learning_rate": 9.422257785537048e-06,
|
| 1292 |
"loss": 0.0003,
|
| 1293 |
+
"step": 251625
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 18.4,
|
| 1297 |
+
"learning_rate": 8.866580991408227e-06,
|
| 1298 |
+
"loss": 0.0003,
|
| 1299 |
+
"step": 253000
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 18.5,
|
| 1303 |
+
"learning_rate": 8.310904197279406e-06,
|
| 1304 |
+
"loss": 0.0003,
|
| 1305 |
+
"step": 254375
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
+
"epoch": 18.6,
|
| 1309 |
+
"learning_rate": 7.755227403150587e-06,
|
| 1310 |
"loss": 0.0004,
|
| 1311 |
+
"step": 255750
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
+
"epoch": 18.7,
|
| 1315 |
+
"learning_rate": 7.199550609021767e-06,
|
| 1316 |
+
"loss": 0.0003,
|
| 1317 |
+
"step": 257125
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
+
"epoch": 18.8,
|
| 1321 |
+
"learning_rate": 6.6438738148929465e-06,
|
| 1322 |
"loss": 0.0003,
|
| 1323 |
+
"step": 258500
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 18.9,
|
| 1327 |
+
"learning_rate": 6.088197020764127e-06,
|
| 1328 |
+
"loss": 0.0003,
|
| 1329 |
+
"step": 259875
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 0.015229469165205956,
|
| 1334 |
"eval_max_distance": 1,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
+
"eval_runtime": 15.6105,
|
| 1337 |
+
"eval_samples_per_second": 17.168,
|
| 1338 |
+
"eval_steps_per_second": 1.153,
|
| 1339 |
+
"step": 261193
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
+
"epoch": 19.0,
|
| 1343 |
+
"learning_rate": 5.532520226635306e-06,
|
| 1344 |
+
"loss": 0.0003,
|
| 1345 |
+
"step": 261250
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
+
"epoch": 19.1,
|
| 1349 |
+
"learning_rate": 4.976843432506486e-06,
|
| 1350 |
+
"loss": 0.0003,
|
| 1351 |
+
"step": 262625
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"epoch": 19.2,
|
| 1355 |
+
"learning_rate": 4.421166638377666e-06,
|
| 1356 |
+
"loss": 0.0003,
|
| 1357 |
+
"step": 264000
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
+
"epoch": 19.3,
|
| 1361 |
+
"learning_rate": 3.865489844248846e-06,
|
| 1362 |
+
"loss": 0.0003,
|
| 1363 |
+
"step": 265375
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 19.4,
|
| 1367 |
+
"learning_rate": 3.309813050120027e-06,
|
| 1368 |
+
"loss": 0.0003,
|
| 1369 |
+
"step": 266750
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 19.5,
|
| 1373 |
+
"learning_rate": 2.7541362559912064e-06,
|
| 1374 |
+
"loss": 0.0003,
|
| 1375 |
+
"step": 268125
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 19.6,
|
| 1379 |
+
"learning_rate": 2.1984594618623863e-06,
|
| 1380 |
"loss": 0.0003,
|
| 1381 |
+
"step": 269500
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 19.7,
|
| 1385 |
+
"learning_rate": 1.6427826677335664e-06,
|
| 1386 |
+
"loss": 0.0003,
|
| 1387 |
+
"step": 270875
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 19.8,
|
| 1391 |
+
"learning_rate": 1.0871058736047461e-06,
|
| 1392 |
"loss": 0.0003,
|
| 1393 |
+
"step": 272250
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 19.9,
|
| 1397 |
+
"learning_rate": 5.31429079475926e-07,
|
| 1398 |
+
"loss": 0.0003,
|
| 1399 |
+
"step": 273625
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 0.015233452431857586,
|
| 1404 |
"eval_max_distance": 1,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 15.6363,
|
| 1407 |
+
"eval_samples_per_second": 17.14,
|
| 1408 |
+
"eval_steps_per_second": 1.151,
|
| 1409 |
+
"step": 274940
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
+
"step": 274940,
|
| 1414 |
+
"total_flos": 7.20387481955881e+16,
|
| 1415 |
+
"train_loss": 0.00045419663040463374,
|
| 1416 |
+
"train_runtime": 19389.5827,
|
| 1417 |
+
"train_samples_per_second": 212.682,
|
| 1418 |
+
"train_steps_per_second": 14.18
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
+
"logging_steps": 1375,
|
| 1422 |
+
"max_steps": 274940,
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 2750,
|
| 1425 |
+
"total_flos": 7.20387481955881e+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 sha256:11404ac3fc96ba698fa232f738237fb864a527c9cdcf006042014fef3b60a4aa
|
| 3 |
size 4091
|