End of training
Browse files- README.md +24 -24
- pytorch_model.bin +1 -1
- trainer_state.json +915 -915
- 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.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 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: 0.0061
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 3
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0013 | 1.0 | 846 | 0.0053 | 0 | 3 |
|
| 53 |
+
| 0.0011 | 2.0 | 1692 | 0.0043 | 0 | 3 |
|
| 54 |
+
| 0.0009 | 3.0 | 2538 | 0.0049 | 0 | 3 |
|
| 55 |
+
| 0.0008 | 4.0 | 3384 | 0.0043 | 0 | 3 |
|
| 56 |
+
| 0.0005 | 5.0 | 4230 | 0.0048 | 0 | 3 |
|
| 57 |
+
| 0.0006 | 6.0 | 5076 | 0.0024 | 0 | 3 |
|
| 58 |
+
| 0.0005 | 7.0 | 5922 | 0.0029 | 0 | 3 |
|
| 59 |
+
| 0.0008 | 8.0 | 6768 | 0.0061 | 0 | 3 |
|
| 60 |
+
| 0.0006 | 9.0 | 7614 | 0.0050 | 0 | 3 |
|
| 61 |
+
| 0.0006 | 10.0 | 8460 | 0.0092 | 0 | 3 |
|
| 62 |
+
| 0.0004 | 11.0 | 9306 | 0.0066 | 0 | 3 |
|
| 63 |
+
| 0.0004 | 12.0 | 10152 | 0.0065 | 0 | 3 |
|
| 64 |
+
| 0.0003 | 13.0 | 10998 | 0.0066 | 0 | 3 |
|
| 65 |
+
| 0.0005 | 14.0 | 11844 | 0.0062 | 0 | 3 |
|
| 66 |
+
| 0.0003 | 15.0 | 12690 | 0.0061 | 0 | 3 |
|
| 67 |
+
| 0.0004 | 16.0 | 13536 | 0.0059 | 0 | 3 |
|
| 68 |
+
| 0.0003 | 17.0 | 14382 | 0.0060 | 0 | 3 |
|
| 69 |
+
| 0.0004 | 18.0 | 15228 | 0.0061 | 0 | 3 |
|
| 70 |
+
| 0.0003 | 19.0 | 16074 | 0.0061 | 0 | 3 |
|
| 71 |
+
| 0.0005 | 20.0 | 16920 | 0.0061 | 0 | 3 |
|
| 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 sha256:78b0e0c08d3da00bb77130eb2c3c6172ba691bea22a870c4dbca3b69010646ea
|
| 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.
|
| 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": 0.001,
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 1.
|
| 89 |
-
"learning_rate": 5.
|
| 90 |
-
"loss": 0.
|
| 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": 0.0012,
|
| 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.
|
| 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":
|
| 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.
|
| 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.
|
| 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":
|
| 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.
|
| 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.
|
| 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.
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch": 5.
|
| 387 |
-
"learning_rate": 8.
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch": 5.
|
| 393 |
-
"learning_rate": 8.
|
| 394 |
-
"loss": 0.
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 5.
|
| 399 |
-
"learning_rate": 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.
|
| 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.
|
| 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.
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch": 7.
|
| 533 |
-
"learning_rate": 6.
|
| 534 |
-
"loss": 0.
|
| 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.
|
| 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":
|
| 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.
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
-
"epoch": 8.
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
-
"epoch": 8.
|
| 591 |
-
"learning_rate": 6.
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch": 8.
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
-
"loss": 0.
|
| 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.
|
| 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.
|
| 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":
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 9.
|
| 643 |
-
"learning_rate": 6.
|
| 644 |
-
"loss": 0.
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch": 9.
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch": 9.
|
| 655 |
-
"learning_rate": 5.
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch": 9.
|
| 661 |
-
"learning_rate": 5.
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch": 9.
|
| 667 |
-
"learning_rate": 5.
|
| 668 |
-
"loss": 0.
|
| 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.
|
| 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.
|
| 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.
|
| 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.
|
| 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.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 11.
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch": 11.
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
-
"loss": 0.
|
| 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": 3,
|
| 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.
|
| 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.
|
| 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.
|
| 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.
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch": 14.
|
| 1011 |
-
"learning_rate": 3.
|
| 1012 |
-
"loss": 0.
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch": 14.
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch": 14.
|
| 1023 |
-
"learning_rate": 3.
|
| 1024 |
-
"loss": 0.
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch": 14.
|
| 1029 |
-
"learning_rate": 2.
|
| 1030 |
-
"loss": 0.
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch": 14.
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
-
"loss": 0.
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch": 14.
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
-
"loss": 0.
|
| 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.
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch": 15.
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch": 15.
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
"loss": 0.0007,
|
| 1077 |
-
"step":
|
| 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.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch": 15.
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch": 15.
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch": 15.
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch": 15.
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
-
"loss": 0.
|
| 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.
|
| 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.
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch": 16.
|
| 1175 |
-
"learning_rate": 1.
|
| 1176 |
-
"loss": 0.
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch": 16.
|
| 1181 |
-
"learning_rate": 1.
|
| 1182 |
-
"loss": 0.
|
| 1183 |
-
"step":
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch": 16.
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
-
"loss": 0.
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
-
"eval_loss": 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.
|
| 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.
|
| 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.
|
| 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":
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch": 18.
|
| 1297 |
-
"learning_rate": 8.
|
| 1298 |
-
"loss": 0.
|
| 1299 |
-
"step":
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch": 18.
|
| 1303 |
-
"learning_rate":
|
| 1304 |
-
"loss": 0.
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch": 18.
|
| 1309 |
-
"learning_rate": 7.
|
| 1310 |
-
"loss": 0.
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch": 18.
|
| 1315 |
-
"learning_rate":
|
| 1316 |
-
"loss": 0.
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch": 18.
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
-
"loss": 0.
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18.
|
| 1327 |
-
"learning_rate":
|
| 1328 |
-
"loss": 0.
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
-
"eval_loss": 0.
|
| 1334 |
-
"eval_max_distance":
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
-
"eval_runtime":
|
| 1337 |
-
"eval_samples_per_second":
|
| 1338 |
-
"eval_steps_per_second":
|
| 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":
|
| 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":
|
| 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":
|
| 1380 |
-
"loss": 0.
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch": 19.
|
| 1385 |
-
"learning_rate": 1.
|
| 1386 |
-
"loss": 0.
|
| 1387 |
-
"step":
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
-
"epoch": 19.
|
| 1391 |
-
"learning_rate":
|
| 1392 |
-
"loss": 0.
|
| 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": 0.
|
| 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": 16920,
|
| 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": 5.91016548463357e-08,
|
| 14 |
+
"loss": 0.0002,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.023640661938535e-06,
|
| 20 |
+
"loss": 0.0009,
|
| 21 |
+
"step": 85
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.004728132387707e-05,
|
| 26 |
+
"loss": 0.0012,
|
| 27 |
+
"step": 170
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.5070921985815603e-05,
|
| 32 |
+
"loss": 0.0012,
|
| 33 |
+
"step": 255
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.009456264775414e-05,
|
| 38 |
+
"loss": 0.0007,
|
| 39 |
+
"step": 340
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.5118203309692672e-05,
|
| 44 |
+
"loss": 0.0012,
|
| 45 |
+
"step": 425
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.0141843971631207e-05,
|
| 50 |
+
"loss": 0.0014,
|
| 51 |
+
"step": 510
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.516548463356974e-05,
|
| 56 |
+
"loss": 0.0016,
|
| 57 |
+
"step": 595
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.018912529550828e-05,
|
| 62 |
+
"loss": 0.0018,
|
| 63 |
+
"step": 680
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.5212765957446815e-05,
|
| 68 |
+
"loss": 0.0013,
|
| 69 |
+
"step": 765
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 0.005299737676978111,
|
| 74 |
+
"eval_max_distance": 3,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 34.0947,
|
| 77 |
+
"eval_samples_per_second": 7.626,
|
| 78 |
+
"eval_steps_per_second": 0.528,
|
| 79 |
+
"step": 846
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.0236406619385343e-05,
|
| 84 |
"loss": 0.001,
|
| 85 |
+
"step": 850
|
| 86 |
},
|
| 87 |
{
|
| 88 |
+
"epoch": 1.11,
|
| 89 |
+
"learning_rate": 5.526004728132388e-05,
|
| 90 |
+
"loss": 0.0008,
|
| 91 |
+
"step": 935
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"epoch": 1.21,
|
| 95 |
+
"learning_rate": 6.0283687943262414e-05,
|
| 96 |
+
"loss": 0.0012,
|
| 97 |
+
"step": 1020
|
| 98 |
},
|
| 99 |
{
|
| 100 |
+
"epoch": 1.31,
|
| 101 |
+
"learning_rate": 6.530732860520094e-05,
|
| 102 |
+
"loss": 0.0015,
|
| 103 |
+
"step": 1105
|
| 104 |
},
|
| 105 |
{
|
| 106 |
+
"epoch": 1.41,
|
| 107 |
+
"learning_rate": 7.033096926713948e-05,
|
| 108 |
+
"loss": 0.0019,
|
| 109 |
+
"step": 1190
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 1.51,
|
| 113 |
+
"learning_rate": 7.535460992907801e-05,
|
| 114 |
+
"loss": 0.001,
|
| 115 |
+
"step": 1275
|
| 116 |
},
|
| 117 |
{
|
| 118 |
+
"epoch": 1.61,
|
| 119 |
+
"learning_rate": 8.037825059101656e-05,
|
| 120 |
"loss": 0.0012,
|
| 121 |
+
"step": 1360
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 1.71,
|
| 125 |
+
"learning_rate": 8.54018912529551e-05,
|
| 126 |
+
"loss": 0.0007,
|
| 127 |
+
"step": 1445
|
| 128 |
},
|
| 129 |
{
|
| 130 |
+
"epoch": 1.81,
|
| 131 |
+
"learning_rate": 9.042553191489363e-05,
|
| 132 |
+
"loss": 0.0008,
|
| 133 |
+
"step": 1530
|
| 134 |
},
|
| 135 |
{
|
| 136 |
+
"epoch": 1.91,
|
| 137 |
+
"learning_rate": 9.544917257683215e-05,
|
| 138 |
+
"loss": 0.0011,
|
| 139 |
+
"step": 1615
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 0.004299119580537081,
|
| 144 |
+
"eval_max_distance": 3,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 30.4314,
|
| 147 |
+
"eval_samples_per_second": 8.544,
|
| 148 |
+
"eval_steps_per_second": 0.591,
|
| 149 |
+
"step": 1692
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 2.01,
|
| 153 |
+
"learning_rate": 9.994746519569215e-05,
|
| 154 |
+
"loss": 0.0007,
|
| 155 |
+
"step": 1700
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 2.11,
|
| 159 |
+
"learning_rate": 9.93892828999212e-05,
|
| 160 |
+
"loss": 0.001,
|
| 161 |
+
"step": 1785
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 2.21,
|
| 165 |
+
"learning_rate": 9.883110060415024e-05,
|
| 166 |
+
"loss": 0.0008,
|
| 167 |
+
"step": 1870
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 2.31,
|
| 171 |
+
"learning_rate": 9.82729183083793e-05,
|
| 172 |
+
"loss": 0.0015,
|
| 173 |
+
"step": 1955
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 2.41,
|
| 177 |
+
"learning_rate": 9.771473601260836e-05,
|
| 178 |
+
"loss": 0.0011,
|
| 179 |
+
"step": 2040
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 2.51,
|
| 183 |
+
"learning_rate": 9.715655371683741e-05,
|
| 184 |
+
"loss": 0.0011,
|
| 185 |
+
"step": 2125
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 2.61,
|
| 189 |
+
"learning_rate": 9.659837142106646e-05,
|
| 190 |
+
"loss": 0.0008,
|
| 191 |
+
"step": 2210
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 2.71,
|
| 195 |
+
"learning_rate": 9.604018912529551e-05,
|
| 196 |
+
"loss": 0.0008,
|
| 197 |
+
"step": 2295
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 2.81,
|
| 201 |
+
"learning_rate": 9.548200682952457e-05,
|
| 202 |
+
"loss": 0.0009,
|
| 203 |
+
"step": 2380
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 2.91,
|
| 207 |
+
"learning_rate": 9.492382453375361e-05,
|
| 208 |
+
"loss": 0.0009,
|
| 209 |
+
"step": 2465
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 0.004937924910336733,
|
| 214 |
+
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 30.2916,
|
| 217 |
+
"eval_samples_per_second": 8.583,
|
| 218 |
+
"eval_steps_per_second": 0.594,
|
| 219 |
+
"step": 2538
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 3.01,
|
| 223 |
+
"learning_rate": 9.436564223798267e-05,
|
| 224 |
+
"loss": 0.0013,
|
| 225 |
+
"step": 2550
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 3.11,
|
| 229 |
+
"learning_rate": 9.380745994221172e-05,
|
| 230 |
+
"loss": 0.0008,
|
| 231 |
+
"step": 2635
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 3.22,
|
| 235 |
+
"learning_rate": 9.324927764644077e-05,
|
| 236 |
+
"loss": 0.0006,
|
| 237 |
+
"step": 2720
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 3.32,
|
| 241 |
+
"learning_rate": 9.269109535066982e-05,
|
| 242 |
+
"loss": 0.0009,
|
| 243 |
+
"step": 2805
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 3.42,
|
| 247 |
+
"learning_rate": 9.213291305489888e-05,
|
| 248 |
+
"loss": 0.0007,
|
| 249 |
+
"step": 2890
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 3.52,
|
| 253 |
+
"learning_rate": 9.157473075912792e-05,
|
| 254 |
+
"loss": 0.0007,
|
| 255 |
+
"step": 2975
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 3.62,
|
| 259 |
+
"learning_rate": 9.101654846335698e-05,
|
| 260 |
+
"loss": 0.001,
|
| 261 |
+
"step": 3060
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 3.72,
|
| 265 |
+
"learning_rate": 9.045836616758603e-05,
|
| 266 |
+
"loss": 0.0007,
|
| 267 |
+
"step": 3145
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 3.82,
|
| 271 |
+
"learning_rate": 8.990018387181508e-05,
|
| 272 |
+
"loss": 0.0009,
|
| 273 |
+
"step": 3230
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 3.92,
|
| 277 |
+
"learning_rate": 8.934200157604413e-05,
|
| 278 |
+
"loss": 0.0008,
|
| 279 |
+
"step": 3315
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 0.004295715596526861,
|
| 284 |
+
"eval_max_distance": 3,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 30.309,
|
| 287 |
+
"eval_samples_per_second": 8.578,
|
| 288 |
+
"eval_steps_per_second": 0.594,
|
| 289 |
+
"step": 3384
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 4.02,
|
| 293 |
+
"learning_rate": 8.878381928027319e-05,
|
| 294 |
+
"loss": 0.0009,
|
| 295 |
+
"step": 3400
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.12,
|
| 299 |
+
"learning_rate": 8.822563698450223e-05,
|
| 300 |
+
"loss": 0.0007,
|
| 301 |
+
"step": 3485
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 4.22,
|
| 305 |
+
"learning_rate": 8.766745468873129e-05,
|
| 306 |
+
"loss": 0.0005,
|
| 307 |
+
"step": 3570
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 4.32,
|
| 311 |
+
"learning_rate": 8.710927239296034e-05,
|
| 312 |
+
"loss": 0.0004,
|
| 313 |
+
"step": 3655
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 4.42,
|
| 317 |
+
"learning_rate": 8.655109009718939e-05,
|
| 318 |
+
"loss": 0.0009,
|
| 319 |
+
"step": 3740
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 4.52,
|
| 323 |
+
"learning_rate": 8.599290780141844e-05,
|
| 324 |
+
"loss": 0.0009,
|
| 325 |
+
"step": 3825
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 4.62,
|
| 329 |
+
"learning_rate": 8.54347255056475e-05,
|
| 330 |
+
"loss": 0.0005,
|
| 331 |
+
"step": 3910
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 4.72,
|
| 335 |
+
"learning_rate": 8.487654320987654e-05,
|
| 336 |
+
"loss": 0.0006,
|
| 337 |
+
"step": 3995
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 4.82,
|
| 341 |
+
"learning_rate": 8.43183609141056e-05,
|
| 342 |
+
"loss": 0.0004,
|
| 343 |
+
"step": 4080
|
| 344 |
},
|
| 345 |
{
|
| 346 |
+
"epoch": 4.92,
|
| 347 |
+
"learning_rate": 8.376017861833465e-05,
|
| 348 |
+
"loss": 0.0005,
|
| 349 |
+
"step": 4165
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 0.004825934302061796,
|
| 354 |
+
"eval_max_distance": 3,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 31.3644,
|
| 357 |
+
"eval_samples_per_second": 8.29,
|
| 358 |
+
"eval_steps_per_second": 0.574,
|
| 359 |
+
"step": 4230
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 5.02,
|
| 363 |
+
"learning_rate": 8.320199632256371e-05,
|
| 364 |
+
"loss": 0.0007,
|
| 365 |
+
"step": 4250
|
| 366 |
},
|
| 367 |
{
|
| 368 |
+
"epoch": 5.12,
|
| 369 |
+
"learning_rate": 8.264381402679275e-05,
|
| 370 |
+
"loss": 0.0007,
|
| 371 |
+
"step": 4335
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 5.22,
|
| 375 |
+
"learning_rate": 8.208563173102181e-05,
|
| 376 |
+
"loss": 0.0006,
|
| 377 |
+
"step": 4420
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 5.33,
|
| 381 |
+
"learning_rate": 8.152744943525086e-05,
|
| 382 |
+
"loss": 0.0008,
|
| 383 |
+
"step": 4505
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 5.43,
|
| 387 |
+
"learning_rate": 8.09692671394799e-05,
|
| 388 |
+
"loss": 0.0009,
|
| 389 |
+
"step": 4590
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 5.53,
|
| 393 |
+
"learning_rate": 8.041108484370896e-05,
|
| 394 |
+
"loss": 0.0007,
|
| 395 |
+
"step": 4675
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 5.63,
|
| 399 |
+
"learning_rate": 7.985290254793802e-05,
|
| 400 |
+
"loss": 0.0007,
|
| 401 |
+
"step": 4760
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 5.73,
|
| 405 |
+
"learning_rate": 7.929472025216706e-05,
|
| 406 |
+
"loss": 0.0004,
|
| 407 |
+
"step": 4845
|
| 408 |
},
|
| 409 |
{
|
| 410 |
+
"epoch": 5.83,
|
| 411 |
+
"learning_rate": 7.873653795639612e-05,
|
| 412 |
+
"loss": 0.0007,
|
| 413 |
+
"step": 4930
|
| 414 |
},
|
| 415 |
{
|
| 416 |
+
"epoch": 5.93,
|
| 417 |
+
"learning_rate": 7.817835566062517e-05,
|
| 418 |
+
"loss": 0.0006,
|
| 419 |
+
"step": 5015
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 0.0023884631227701902,
|
| 424 |
+
"eval_max_distance": 3,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 30.4064,
|
| 427 |
+
"eval_samples_per_second": 8.551,
|
| 428 |
+
"eval_steps_per_second": 0.592,
|
| 429 |
+
"step": 5076
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 6.03,
|
| 433 |
+
"learning_rate": 7.762017336485422e-05,
|
| 434 |
+
"loss": 0.0005,
|
| 435 |
+
"step": 5100
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 6.13,
|
| 439 |
+
"learning_rate": 7.706199106908327e-05,
|
| 440 |
+
"loss": 0.0006,
|
| 441 |
+
"step": 5185
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 6.23,
|
| 445 |
+
"learning_rate": 7.650380877331233e-05,
|
| 446 |
+
"loss": 0.0005,
|
| 447 |
+
"step": 5270
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 6.33,
|
| 451 |
+
"learning_rate": 7.594562647754137e-05,
|
| 452 |
+
"loss": 0.0003,
|
| 453 |
+
"step": 5355
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 6.43,
|
| 457 |
+
"learning_rate": 7.538744418177043e-05,
|
| 458 |
+
"loss": 0.0007,
|
| 459 |
+
"step": 5440
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 6.53,
|
| 463 |
+
"learning_rate": 7.482926188599948e-05,
|
| 464 |
+
"loss": 0.0008,
|
| 465 |
+
"step": 5525
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 6.63,
|
| 469 |
+
"learning_rate": 7.427107959022853e-05,
|
| 470 |
+
"loss": 0.0004,
|
| 471 |
+
"step": 5610
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 6.73,
|
| 475 |
+
"learning_rate": 7.371289729445758e-05,
|
| 476 |
+
"loss": 0.0009,
|
| 477 |
+
"step": 5695
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 6.83,
|
| 481 |
+
"learning_rate": 7.315471499868664e-05,
|
| 482 |
+
"loss": 0.0008,
|
| 483 |
+
"step": 5780
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 6.93,
|
| 487 |
+
"learning_rate": 7.259653270291568e-05,
|
| 488 |
+
"loss": 0.0005,
|
| 489 |
+
"step": 5865
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 0.002862530527636409,
|
| 494 |
+
"eval_max_distance": 3,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 30.524,
|
| 497 |
+
"eval_samples_per_second": 8.518,
|
| 498 |
+
"eval_steps_per_second": 0.59,
|
| 499 |
+
"step": 5922
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 7.03,
|
| 503 |
+
"learning_rate": 7.203835040714474e-05,
|
| 504 |
+
"loss": 0.0007,
|
| 505 |
+
"step": 5950
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 7.13,
|
| 509 |
+
"learning_rate": 7.14801681113738e-05,
|
| 510 |
+
"loss": 0.0006,
|
| 511 |
+
"step": 6035
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 7.23,
|
| 515 |
+
"learning_rate": 7.092198581560284e-05,
|
| 516 |
+
"loss": 0.0005,
|
| 517 |
+
"step": 6120
|
| 518 |
},
|
| 519 |
{
|
| 520 |
+
"epoch": 7.33,
|
| 521 |
+
"learning_rate": 7.036380351983189e-05,
|
| 522 |
+
"loss": 0.0004,
|
| 523 |
+
"step": 6205
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"epoch": 7.43,
|
| 527 |
+
"learning_rate": 6.980562122406095e-05,
|
| 528 |
+
"loss": 0.0007,
|
| 529 |
+
"step": 6290
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 7.54,
|
| 533 |
+
"learning_rate": 6.924743892829e-05,
|
| 534 |
+
"loss": 0.0006,
|
| 535 |
+
"step": 6375
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 7.64,
|
| 539 |
+
"learning_rate": 6.868925663251905e-05,
|
| 540 |
+
"loss": 0.0005,
|
| 541 |
+
"step": 6460
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 7.74,
|
| 545 |
+
"learning_rate": 6.81310743367481e-05,
|
| 546 |
+
"loss": 0.0007,
|
| 547 |
+
"step": 6545
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 7.84,
|
| 551 |
+
"learning_rate": 6.757289204097716e-05,
|
| 552 |
+
"loss": 0.0012,
|
| 553 |
+
"step": 6630
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 7.94,
|
| 557 |
+
"learning_rate": 6.70147097452062e-05,
|
| 558 |
+
"loss": 0.0008,
|
| 559 |
+
"step": 6715
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 0.006056753918528557,
|
| 564 |
+
"eval_max_distance": 3,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 30.8852,
|
| 567 |
+
"eval_samples_per_second": 8.418,
|
| 568 |
+
"eval_steps_per_second": 0.583,
|
| 569 |
+
"step": 6768
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 8.04,
|
| 573 |
+
"learning_rate": 6.645652744943526e-05,
|
| 574 |
+
"loss": 0.0008,
|
| 575 |
+
"step": 6800
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 8.14,
|
| 579 |
+
"learning_rate": 6.589834515366431e-05,
|
| 580 |
+
"loss": 0.0007,
|
| 581 |
+
"step": 6885
|
| 582 |
},
|
| 583 |
{
|
| 584 |
+
"epoch": 8.24,
|
| 585 |
+
"learning_rate": 6.534016285789336e-05,
|
| 586 |
+
"loss": 0.0005,
|
| 587 |
+
"step": 6970
|
| 588 |
},
|
| 589 |
{
|
| 590 |
+
"epoch": 8.34,
|
| 591 |
+
"learning_rate": 6.478198056212241e-05,
|
| 592 |
+
"loss": 0.0006,
|
| 593 |
+
"step": 7055
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"epoch": 8.44,
|
| 597 |
+
"learning_rate": 6.422379826635147e-05,
|
| 598 |
+
"loss": 0.0007,
|
| 599 |
+
"step": 7140
|
| 600 |
},
|
| 601 |
{
|
| 602 |
+
"epoch": 8.54,
|
| 603 |
+
"learning_rate": 6.366561597058051e-05,
|
| 604 |
+
"loss": 0.0004,
|
| 605 |
+
"step": 7225
|
| 606 |
},
|
| 607 |
{
|
| 608 |
+
"epoch": 8.64,
|
| 609 |
+
"learning_rate": 6.310743367480957e-05,
|
| 610 |
+
"loss": 0.0006,
|
| 611 |
+
"step": 7310
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 8.74,
|
| 615 |
+
"learning_rate": 6.254925137903862e-05,
|
| 616 |
+
"loss": 0.0004,
|
| 617 |
+
"step": 7395
|
| 618 |
},
|
| 619 |
{
|
| 620 |
+
"epoch": 8.84,
|
| 621 |
+
"learning_rate": 6.199106908326767e-05,
|
| 622 |
+
"loss": 0.0005,
|
| 623 |
+
"step": 7480
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 8.94,
|
| 627 |
+
"learning_rate": 6.143288678749672e-05,
|
| 628 |
+
"loss": 0.0006,
|
| 629 |
+
"step": 7565
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 0.005007054656744003,
|
| 634 |
+
"eval_max_distance": 3,
|
| 635 |
"eval_mean_distance": 0,
|
| 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": 9.04,
|
| 643 |
+
"learning_rate": 6.087470449172577e-05,
|
| 644 |
+
"loss": 0.0006,
|
| 645 |
+
"step": 7650
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 9.14,
|
| 649 |
+
"learning_rate": 6.031652219595483e-05,
|
| 650 |
+
"loss": 0.0007,
|
| 651 |
+
"step": 7735
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 9.24,
|
| 655 |
+
"learning_rate": 5.975833990018388e-05,
|
| 656 |
+
"loss": 0.0005,
|
| 657 |
+
"step": 7820
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 9.34,
|
| 661 |
+
"learning_rate": 5.9200157604412935e-05,
|
| 662 |
+
"loss": 0.0006,
|
| 663 |
+
"step": 7905
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 9.44,
|
| 667 |
+
"learning_rate": 5.8641975308641984e-05,
|
| 668 |
+
"loss": 0.0006,
|
| 669 |
+
"step": 7990
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 9.54,
|
| 673 |
+
"learning_rate": 5.8083793012871034e-05,
|
| 674 |
+
"loss": 0.0004,
|
| 675 |
+
"step": 8075
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 9.65,
|
| 679 |
+
"learning_rate": 5.752561071710009e-05,
|
| 680 |
+
"loss": 0.0004,
|
| 681 |
+
"step": 8160
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 9.75,
|
| 685 |
+
"learning_rate": 5.696742842132914e-05,
|
| 686 |
+
"loss": 0.0004,
|
| 687 |
+
"step": 8245
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 9.85,
|
| 691 |
+
"learning_rate": 5.640924612555819e-05,
|
| 692 |
+
"loss": 0.0004,
|
| 693 |
+
"step": 8330
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 9.95,
|
| 697 |
+
"learning_rate": 5.585106382978723e-05,
|
| 698 |
+
"loss": 0.0006,
|
| 699 |
+
"step": 8415
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 0.009199680760502815,
|
| 704 |
+
"eval_max_distance": 3,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 29.8643,
|
| 707 |
+
"eval_samples_per_second": 8.706,
|
| 708 |
+
"eval_steps_per_second": 0.603,
|
| 709 |
+
"step": 8460
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 10.05,
|
| 713 |
+
"learning_rate": 5.529288153401628e-05,
|
| 714 |
+
"loss": 0.0005,
|
| 715 |
+
"step": 8500
|
| 716 |
},
|
| 717 |
{
|
| 718 |
+
"epoch": 10.15,
|
| 719 |
+
"learning_rate": 5.473469923824534e-05,
|
| 720 |
+
"loss": 0.0006,
|
| 721 |
+
"step": 8585
|
| 722 |
},
|
| 723 |
{
|
| 724 |
+
"epoch": 10.25,
|
| 725 |
+
"learning_rate": 5.4176516942474386e-05,
|
| 726 |
+
"loss": 0.0005,
|
| 727 |
+
"step": 8670
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 10.35,
|
| 731 |
+
"learning_rate": 5.3618334646703436e-05,
|
| 732 |
+
"loss": 0.0004,
|
| 733 |
+
"step": 8755
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"epoch": 10.45,
|
| 737 |
+
"learning_rate": 5.306015235093249e-05,
|
| 738 |
+
"loss": 0.0004,
|
| 739 |
+
"step": 8840
|
| 740 |
},
|
| 741 |
{
|
| 742 |
+
"epoch": 10.55,
|
| 743 |
+
"learning_rate": 5.250197005516154e-05,
|
| 744 |
+
"loss": 0.0004,
|
| 745 |
+
"step": 8925
|
| 746 |
},
|
| 747 |
{
|
| 748 |
+
"epoch": 10.65,
|
| 749 |
+
"learning_rate": 5.19437877593906e-05,
|
| 750 |
+
"loss": 0.0006,
|
| 751 |
+
"step": 9010
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 10.75,
|
| 755 |
+
"learning_rate": 5.138560546361965e-05,
|
| 756 |
+
"loss": 0.0005,
|
| 757 |
+
"step": 9095
|
| 758 |
},
|
| 759 |
{
|
| 760 |
+
"epoch": 10.85,
|
| 761 |
+
"learning_rate": 5.0827423167848696e-05,
|
| 762 |
+
"loss": 0.0005,
|
| 763 |
+
"step": 9180
|
| 764 |
},
|
| 765 |
{
|
| 766 |
+
"epoch": 10.95,
|
| 767 |
+
"learning_rate": 5.026924087207775e-05,
|
| 768 |
+
"loss": 0.0004,
|
| 769 |
+
"step": 9265
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 0.006612914614379406,
|
| 774 |
+
"eval_max_distance": 3,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 30.0706,
|
| 777 |
+
"eval_samples_per_second": 8.646,
|
| 778 |
+
"eval_steps_per_second": 0.599,
|
| 779 |
+
"step": 9306
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 11.05,
|
| 783 |
+
"learning_rate": 4.971105857630681e-05,
|
| 784 |
+
"loss": 0.0005,
|
| 785 |
+
"step": 9350
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 11.15,
|
| 789 |
+
"learning_rate": 4.915287628053586e-05,
|
| 790 |
+
"loss": 0.0005,
|
| 791 |
+
"step": 9435
|
| 792 |
},
|
| 793 |
{
|
| 794 |
+
"epoch": 11.25,
|
| 795 |
+
"learning_rate": 4.8594693984764914e-05,
|
| 796 |
+
"loss": 0.0006,
|
| 797 |
+
"step": 9520
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 11.35,
|
| 801 |
+
"learning_rate": 4.8036511688993963e-05,
|
| 802 |
+
"loss": 0.0004,
|
| 803 |
+
"step": 9605
|
| 804 |
},
|
| 805 |
{
|
| 806 |
+
"epoch": 11.45,
|
| 807 |
+
"learning_rate": 4.747832939322301e-05,
|
| 808 |
+
"loss": 0.0006,
|
| 809 |
+
"step": 9690
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 11.55,
|
| 813 |
+
"learning_rate": 4.692014709745207e-05,
|
| 814 |
+
"loss": 0.0004,
|
| 815 |
+
"step": 9775
|
| 816 |
},
|
| 817 |
{
|
| 818 |
+
"epoch": 11.65,
|
| 819 |
+
"learning_rate": 4.636196480168112e-05,
|
| 820 |
+
"loss": 0.0005,
|
| 821 |
+
"step": 9860
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 11.76,
|
| 825 |
+
"learning_rate": 4.580378250591017e-05,
|
| 826 |
+
"loss": 0.0005,
|
| 827 |
+
"step": 9945
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 11.86,
|
| 831 |
+
"learning_rate": 4.5245600210139224e-05,
|
| 832 |
+
"loss": 0.0006,
|
| 833 |
+
"step": 10030
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 11.96,
|
| 837 |
+
"learning_rate": 4.4687417914368273e-05,
|
| 838 |
+
"loss": 0.0004,
|
| 839 |
+
"step": 10115
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 0.006491700652986765,
|
| 844 |
"eval_max_distance": 3,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 29.5704,
|
| 847 |
+
"eval_samples_per_second": 8.793,
|
| 848 |
+
"eval_steps_per_second": 0.609,
|
| 849 |
+
"step": 10152
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 12.06,
|
| 853 |
+
"learning_rate": 4.412923561859732e-05,
|
| 854 |
+
"loss": 0.0004,
|
| 855 |
+
"step": 10200
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 12.16,
|
| 859 |
+
"learning_rate": 4.357105332282638e-05,
|
| 860 |
+
"loss": 0.0004,
|
| 861 |
+
"step": 10285
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 12.26,
|
| 865 |
+
"learning_rate": 4.301287102705542e-05,
|
| 866 |
+
"loss": 0.0003,
|
| 867 |
+
"step": 10370
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 12.36,
|
| 871 |
+
"learning_rate": 4.245468873128448e-05,
|
| 872 |
+
"loss": 0.0004,
|
| 873 |
+
"step": 10455
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 12.46,
|
| 877 |
+
"learning_rate": 4.189650643551353e-05,
|
| 878 |
+
"loss": 0.0003,
|
| 879 |
+
"step": 10540
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 12.56,
|
| 883 |
+
"learning_rate": 4.133832413974258e-05,
|
| 884 |
+
"loss": 0.0004,
|
| 885 |
+
"step": 10625
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 12.66,
|
| 889 |
+
"learning_rate": 4.078014184397163e-05,
|
| 890 |
+
"loss": 0.0003,
|
| 891 |
+
"step": 10710
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 12.76,
|
| 895 |
+
"learning_rate": 4.022195954820068e-05,
|
| 896 |
+
"loss": 0.0004,
|
| 897 |
+
"step": 10795
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 12.86,
|
| 901 |
+
"learning_rate": 3.966377725242973e-05,
|
| 902 |
+
"loss": 0.0005,
|
| 903 |
+
"step": 10880
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 12.96,
|
| 907 |
+
"learning_rate": 3.910559495665879e-05,
|
| 908 |
+
"loss": 0.0003,
|
| 909 |
+
"step": 10965
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 0.006619863212108612,
|
| 914 |
+
"eval_max_distance": 3,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 29.8838,
|
| 917 |
+
"eval_samples_per_second": 8.7,
|
| 918 |
+
"eval_steps_per_second": 0.602,
|
| 919 |
+
"step": 10998
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 13.06,
|
| 923 |
+
"learning_rate": 3.854741266088784e-05,
|
| 924 |
+
"loss": 0.0004,
|
| 925 |
+
"step": 11050
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 13.16,
|
| 929 |
+
"learning_rate": 3.7989230365116893e-05,
|
| 930 |
+
"loss": 0.0003,
|
| 931 |
+
"step": 11135
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 13.26,
|
| 935 |
+
"learning_rate": 3.743104806934594e-05,
|
| 936 |
+
"loss": 0.0003,
|
| 937 |
+
"step": 11220
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 13.36,
|
| 941 |
+
"learning_rate": 3.687286577357499e-05,
|
| 942 |
+
"loss": 0.0004,
|
| 943 |
+
"step": 11305
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 13.46,
|
| 947 |
+
"learning_rate": 3.631468347780405e-05,
|
| 948 |
+
"loss": 0.0003,
|
| 949 |
+
"step": 11390
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 13.56,
|
| 953 |
+
"learning_rate": 3.57565011820331e-05,
|
| 954 |
+
"loss": 0.0003,
|
| 955 |
+
"step": 11475
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 13.66,
|
| 959 |
+
"learning_rate": 3.519831888626215e-05,
|
| 960 |
+
"loss": 0.0004,
|
| 961 |
+
"step": 11560
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 13.76,
|
| 965 |
+
"learning_rate": 3.4640136590491203e-05,
|
| 966 |
+
"loss": 0.0005,
|
| 967 |
+
"step": 11645
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 13.87,
|
| 971 |
+
"learning_rate": 3.408195429472025e-05,
|
| 972 |
+
"loss": 0.0004,
|
| 973 |
+
"step": 11730
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 13.97,
|
| 977 |
+
"learning_rate": 3.35237719989493e-05,
|
| 978 |
+
"loss": 0.0005,
|
| 979 |
+
"step": 11815
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 0.006221045274287462,
|
| 984 |
+
"eval_max_distance": 3,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 30.0954,
|
| 987 |
+
"eval_samples_per_second": 8.639,
|
| 988 |
+
"eval_steps_per_second": 0.598,
|
| 989 |
+
"step": 11844
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 14.07,
|
| 993 |
+
"learning_rate": 3.296558970317836e-05,
|
| 994 |
+
"loss": 0.0005,
|
| 995 |
+
"step": 11900
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 14.17,
|
| 999 |
+
"learning_rate": 3.240740740740741e-05,
|
| 1000 |
+
"loss": 0.0003,
|
| 1001 |
+
"step": 11985
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 14.27,
|
| 1005 |
+
"learning_rate": 3.184922511163646e-05,
|
| 1006 |
+
"loss": 0.0005,
|
| 1007 |
+
"step": 12070
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 14.37,
|
| 1011 |
+
"learning_rate": 3.1291042815865513e-05,
|
| 1012 |
+
"loss": 0.0004,
|
| 1013 |
+
"step": 12155
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 14.47,
|
| 1017 |
+
"learning_rate": 3.073286052009456e-05,
|
| 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": 12325
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 14.67,
|
| 1029 |
+
"learning_rate": 2.961649592855267e-05,
|
| 1030 |
+
"loss": 0.0005,
|
| 1031 |
+
"step": 12410
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 14.77,
|
| 1035 |
+
"learning_rate": 2.905831363278172e-05,
|
| 1036 |
+
"loss": 0.0005,
|
| 1037 |
+
"step": 12495
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 14.87,
|
| 1041 |
+
"learning_rate": 2.850013133701077e-05,
|
| 1042 |
+
"loss": 0.0006,
|
| 1043 |
+
"step": 12580
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 14.97,
|
| 1047 |
+
"learning_rate": 2.7941949041239823e-05,
|
| 1048 |
+
"loss": 0.0003,
|
| 1049 |
+
"step": 12665
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 0.006079429294914007,
|
| 1054 |
+
"eval_max_distance": 3,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 29.8562,
|
| 1057 |
+
"eval_samples_per_second": 8.708,
|
| 1058 |
+
"eval_steps_per_second": 0.603,
|
| 1059 |
+
"step": 12690
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
+
"epoch": 15.07,
|
| 1063 |
+
"learning_rate": 2.7383766745468876e-05,
|
| 1064 |
+
"loss": 0.0004,
|
| 1065 |
+
"step": 12750
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 15.17,
|
| 1069 |
+
"learning_rate": 2.6825584449697926e-05,
|
| 1070 |
+
"loss": 0.0004,
|
| 1071 |
+
"step": 12835
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 15.27,
|
| 1075 |
+
"learning_rate": 2.626740215392698e-05,
|
| 1076 |
"loss": 0.0007,
|
| 1077 |
+
"step": 12920
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
+
"epoch": 15.37,
|
| 1081 |
+
"learning_rate": 2.570921985815603e-05,
|
| 1082 |
+
"loss": 0.0003,
|
| 1083 |
+
"step": 13005
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
+
"epoch": 15.47,
|
| 1087 |
+
"learning_rate": 2.5151037562385084e-05,
|
| 1088 |
+
"loss": 0.0005,
|
| 1089 |
+
"step": 13090
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 15.57,
|
| 1093 |
+
"learning_rate": 2.4592855266614133e-05,
|
| 1094 |
+
"loss": 0.0004,
|
| 1095 |
+
"step": 13175
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 15.67,
|
| 1099 |
+
"learning_rate": 2.4034672970843186e-05,
|
| 1100 |
+
"loss": 0.0005,
|
| 1101 |
+
"step": 13260
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 15.77,
|
| 1105 |
+
"learning_rate": 2.3476490675072236e-05,
|
| 1106 |
+
"loss": 0.0004,
|
| 1107 |
+
"step": 13345
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 15.87,
|
| 1111 |
+
"learning_rate": 2.291830837930129e-05,
|
| 1112 |
+
"loss": 0.0002,
|
| 1113 |
+
"step": 13430
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 15.98,
|
| 1117 |
+
"learning_rate": 2.2360126083530338e-05,
|
| 1118 |
+
"loss": 0.0004,
|
| 1119 |
+
"step": 13515
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 0.005943103693425655,
|
| 1124 |
+
"eval_max_distance": 3,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 29.5405,
|
| 1127 |
+
"eval_samples_per_second": 8.801,
|
| 1128 |
+
"eval_steps_per_second": 0.609,
|
| 1129 |
+
"step": 13536
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 16.08,
|
| 1133 |
+
"learning_rate": 2.180194378775939e-05,
|
| 1134 |
+
"loss": 0.0005,
|
| 1135 |
+
"step": 13600
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 16.18,
|
| 1139 |
+
"learning_rate": 2.1243761491988443e-05,
|
| 1140 |
+
"loss": 0.0003,
|
| 1141 |
+
"step": 13685
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 16.28,
|
| 1145 |
+
"learning_rate": 2.0685579196217493e-05,
|
| 1146 |
+
"loss": 0.0005,
|
| 1147 |
+
"step": 13770
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 16.38,
|
| 1151 |
+
"learning_rate": 2.0127396900446546e-05,
|
| 1152 |
+
"loss": 0.0003,
|
| 1153 |
+
"step": 13855
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 16.48,
|
| 1157 |
+
"learning_rate": 1.95692146046756e-05,
|
| 1158 |
+
"loss": 0.0004,
|
| 1159 |
+
"step": 13940
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 16.58,
|
| 1163 |
+
"learning_rate": 1.901103230890465e-05,
|
| 1164 |
+
"loss": 0.0003,
|
| 1165 |
+
"step": 14025
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 16.68,
|
| 1169 |
+
"learning_rate": 1.84528500131337e-05,
|
| 1170 |
+
"loss": 0.0004,
|
| 1171 |
+
"step": 14110
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 16.78,
|
| 1175 |
+
"learning_rate": 1.7894667717362753e-05,
|
| 1176 |
+
"loss": 0.0004,
|
| 1177 |
+
"step": 14195
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 16.88,
|
| 1181 |
+
"learning_rate": 1.7336485421591806e-05,
|
| 1182 |
+
"loss": 0.0004,
|
| 1183 |
+
"step": 14280
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 16.98,
|
| 1187 |
+
"learning_rate": 1.677830312582086e-05,
|
| 1188 |
+
"loss": 0.0003,
|
| 1189 |
+
"step": 14365
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 0.006018976215273142,
|
| 1194 |
+
"eval_max_distance": 3,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 29.8665,
|
| 1197 |
+
"eval_samples_per_second": 8.705,
|
| 1198 |
+
"eval_steps_per_second": 0.603,
|
| 1199 |
+
"step": 14382
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
+
"epoch": 17.08,
|
| 1203 |
+
"learning_rate": 1.622012083004991e-05,
|
| 1204 |
+
"loss": 0.0004,
|
| 1205 |
+
"step": 14450
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
+
"epoch": 17.18,
|
| 1209 |
+
"learning_rate": 1.566193853427896e-05,
|
| 1210 |
+
"loss": 0.0002,
|
| 1211 |
+
"step": 14535
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
+
"epoch": 17.28,
|
| 1215 |
+
"learning_rate": 1.5103756238508012e-05,
|
| 1216 |
+
"loss": 0.0003,
|
| 1217 |
+
"step": 14620
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 17.38,
|
| 1221 |
+
"learning_rate": 1.4545573942737065e-05,
|
| 1222 |
+
"loss": 0.0005,
|
| 1223 |
+
"step": 14705
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"epoch": 17.48,
|
| 1227 |
+
"learning_rate": 1.3987391646966116e-05,
|
| 1228 |
+
"loss": 0.0008,
|
| 1229 |
+
"step": 14790
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
+
"epoch": 17.58,
|
| 1233 |
+
"learning_rate": 1.3429209351195169e-05,
|
| 1234 |
+
"loss": 0.0003,
|
| 1235 |
+
"step": 14875
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
+
"epoch": 17.68,
|
| 1239 |
+
"learning_rate": 1.287102705542422e-05,
|
| 1240 |
+
"loss": 0.0003,
|
| 1241 |
+
"step": 14960
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 17.78,
|
| 1245 |
+
"learning_rate": 1.2312844759653271e-05,
|
| 1246 |
+
"loss": 0.0005,
|
| 1247 |
+
"step": 15045
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
+
"epoch": 17.88,
|
| 1251 |
+
"learning_rate": 1.1754662463882322e-05,
|
| 1252 |
+
"loss": 0.0003,
|
| 1253 |
+
"step": 15130
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
+
"epoch": 17.98,
|
| 1257 |
+
"learning_rate": 1.1196480168111375e-05,
|
| 1258 |
+
"loss": 0.0004,
|
| 1259 |
+
"step": 15215
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 0.006091571878641844,
|
| 1264 |
+
"eval_max_distance": 3,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 29.7889,
|
| 1267 |
+
"eval_samples_per_second": 8.728,
|
| 1268 |
+
"eval_steps_per_second": 0.604,
|
| 1269 |
+
"step": 15228
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 18.09,
|
| 1273 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 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": 15385
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 18.29,
|
| 1285 |
+
"learning_rate": 9.52193328079853e-06,
|
| 1286 |
+
"loss": 0.0004,
|
| 1287 |
+
"step": 15470
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 18.39,
|
| 1291 |
+
"learning_rate": 8.963750985027581e-06,
|
| 1292 |
+
"loss": 0.0003,
|
| 1293 |
+
"step": 15555
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 18.49,
|
| 1297 |
+
"learning_rate": 8.405568689256634e-06,
|
| 1298 |
+
"loss": 0.0003,
|
| 1299 |
+
"step": 15640
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 18.59,
|
| 1303 |
+
"learning_rate": 7.847386393485685e-06,
|
| 1304 |
+
"loss": 0.0004,
|
| 1305 |
+
"step": 15725
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
+
"epoch": 18.69,
|
| 1309 |
+
"learning_rate": 7.289204097714736e-06,
|
| 1310 |
+
"loss": 0.0004,
|
| 1311 |
+
"step": 15810
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
+
"epoch": 18.79,
|
| 1315 |
+
"learning_rate": 6.731021801943787e-06,
|
| 1316 |
+
"loss": 0.0004,
|
| 1317 |
+
"step": 15895
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
+
"epoch": 18.89,
|
| 1321 |
+
"learning_rate": 6.172839506172839e-06,
|
| 1322 |
+
"loss": 0.0004,
|
| 1323 |
+
"step": 15980
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 18.99,
|
| 1327 |
+
"learning_rate": 5.614657210401891e-06,
|
| 1328 |
+
"loss": 0.0003,
|
| 1329 |
+
"step": 16065
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 0.006117388140410185,
|
| 1334 |
+
"eval_max_distance": 3,
|
| 1335 |
"eval_mean_distance": 0,
|
| 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": 19.09,
|
| 1343 |
+
"learning_rate": 5.056474914630943e-06,
|
| 1344 |
+
"loss": 0.0003,
|
| 1345 |
+
"step": 16150
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
+
"epoch": 19.19,
|
| 1349 |
+
"learning_rate": 4.498292618859995e-06,
|
| 1350 |
+
"loss": 0.0004,
|
| 1351 |
+
"step": 16235
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"epoch": 19.29,
|
| 1355 |
+
"learning_rate": 3.940110323089047e-06,
|
| 1356 |
+
"loss": 0.0002,
|
| 1357 |
+
"step": 16320
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
+
"epoch": 19.39,
|
| 1361 |
+
"learning_rate": 3.3819280273180985e-06,
|
| 1362 |
+
"loss": 0.0003,
|
| 1363 |
+
"step": 16405
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 19.49,
|
| 1367 |
+
"learning_rate": 2.82374573154715e-06,
|
| 1368 |
+
"loss": 0.0003,
|
| 1369 |
+
"step": 16490
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 19.59,
|
| 1373 |
+
"learning_rate": 2.265563435776202e-06,
|
| 1374 |
+
"loss": 0.0002,
|
| 1375 |
+
"step": 16575
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 19.69,
|
| 1379 |
+
"learning_rate": 1.7073811400052534e-06,
|
| 1380 |
+
"loss": 0.0004,
|
| 1381 |
+
"step": 16660
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 19.79,
|
| 1385 |
+
"learning_rate": 1.1491988442343054e-06,
|
| 1386 |
+
"loss": 0.0003,
|
| 1387 |
+
"step": 16745
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 19.89,
|
| 1391 |
+
"learning_rate": 5.91016548463357e-07,
|
| 1392 |
+
"loss": 0.0003,
|
| 1393 |
+
"step": 16830
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 19.99,
|
| 1397 |
+
"learning_rate": 3.2834252692408726e-08,
|
| 1398 |
+
"loss": 0.0005,
|
| 1399 |
+
"step": 16915
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 0.00614793598651886,
|
| 1404 |
+
"eval_max_distance": 3,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 29.6354,
|
| 1407 |
+
"eval_samples_per_second": 8.773,
|
| 1408 |
+
"eval_steps_per_second": 0.607,
|
| 1409 |
+
"step": 16920
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
+
"step": 16920,
|
| 1414 |
+
"total_flos": 4933712379248640.0,
|
| 1415 |
+
"train_loss": 0.0005908621804599912,
|
| 1416 |
+
"train_runtime": 1909.7013,
|
| 1417 |
+
"train_samples_per_second": 132.796,
|
| 1418 |
+
"train_steps_per_second": 8.86
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
+
"logging_steps": 85,
|
| 1422 |
+
"max_steps": 16920,
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 170,
|
| 1425 |
+
"total_flos": 4933712379248640.0,
|
| 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:ff328fa272f719329d317d9c2a268053f31d067183e9227f052a9647a6837e34
|
| 3 |
size 4091
|