End of training
Browse files- README.md +22 -22
- pytorch_model.bin +1 -1
- trainer_state.json +751 -751
- 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 |
|
|
@@ -49,26 +49,26 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.0005 | 2.0 |
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.0005 | 6.0 |
|
| 58 |
-
| 0.0005 | 7.0 |
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.0004 | 11.0 |
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.0004 | 13.0 |
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.0003 | 16.0 |
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.0003 | 18.0 |
|
| 70 |
-
| 0.0003 | 19.0 |
|
| 71 |
-
| 0.0003 | 20.0 |
|
| 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: 0.0170
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 3
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0004 | 1.0 | 13982 | 0.0145 | 0 | 4 |
|
| 53 |
+
| 0.0005 | 2.0 | 27964 | 0.0164 | 0 | 4 |
|
| 54 |
+
| 0.0005 | 3.0 | 41946 | 0.0167 | 0 | 3 |
|
| 55 |
+
| 0.0005 | 4.0 | 55928 | 0.0125 | 0 | 3 |
|
| 56 |
+
| 0.0005 | 5.0 | 69910 | 0.0185 | 0 | 3 |
|
| 57 |
+
| 0.0005 | 6.0 | 83892 | 0.0173 | 0 | 3 |
|
| 58 |
+
| 0.0005 | 7.0 | 97874 | 0.0168 | 0 | 5 |
|
| 59 |
+
| 0.0004 | 8.0 | 111856 | 0.0201 | 0 | 5 |
|
| 60 |
+
| 0.0004 | 9.0 | 125838 | 0.0215 | 0 | 2 |
|
| 61 |
+
| 0.0004 | 10.0 | 139820 | 0.0226 | 0 | 3 |
|
| 62 |
+
| 0.0004 | 11.0 | 153802 | 0.0199 | 0 | 3 |
|
| 63 |
+
| 0.0003 | 12.0 | 167784 | 0.0184 | 0 | 3 |
|
| 64 |
+
| 0.0004 | 13.0 | 181766 | 0.0196 | 0 | 3 |
|
| 65 |
+
| 0.0003 | 14.0 | 195748 | 0.0167 | 0 | 1 |
|
| 66 |
+
| 0.0003 | 15.0 | 209730 | 0.0177 | 0 | 3 |
|
| 67 |
+
| 0.0003 | 16.0 | 223712 | 0.0173 | 0 | 3 |
|
| 68 |
+
| 0.0003 | 17.0 | 237694 | 0.0173 | 0 | 3 |
|
| 69 |
+
| 0.0003 | 18.0 | 251676 | 0.0169 | 0 | 3 |
|
| 70 |
+
| 0.0003 | 19.0 | 265658 | 0.0167 | 0 | 3 |
|
| 71 |
+
| 0.0003 | 20.0 | 279640 | 0.0170 | 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 sha256:0faab56c1613c68c3c5f4b631273360760561866b59ee610afd96d410f0b2012
|
| 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": 0.0004,
|
| 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": 0.0004,
|
| 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": 16.
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 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": 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": 0.0005,
|
| 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": 0.0006,
|
| 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": 0.0006,
|
| 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": 0.0005,
|
| 237 |
-
"step":
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 3.3,
|
| 241 |
-
"learning_rate": 9.
|
| 242 |
"loss": 0.0006,
|
| 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": 0.0006,
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.1,
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
"loss": 0.0005,
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.2,
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
"loss": 0.0005,
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.3,
|
| 521 |
-
"learning_rate": 7.
|
| 522 |
-
"loss": 0.
|
| 523 |
-
"step":
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.4,
|
| 527 |
-
"learning_rate": 6.
|
| 528 |
"loss": 0.0005,
|
| 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.
|
| 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": 0.0005,
|
| 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": 0.0005,
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.4,
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
"loss": 0.0005,
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.5,
|
| 603 |
-
"learning_rate": 6.
|
| 604 |
"loss": 0.0005,
|
| 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.
|
| 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": 1.
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 9.
|
| 643 |
-
"learning_rate": 6.
|
| 644 |
"loss": 0.0004,
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch": 9.
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
"loss": 0.0004,
|
| 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": 0.0005,
|
| 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": 15.
|
| 707 |
-
"eval_samples_per_second":
|
| 708 |
-
"eval_steps_per_second": 1.
|
| 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": 0.0004,
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 10.
|
| 755 |
-
"learning_rate": 5.
|
| 756 |
"loss": 0.0004,
|
| 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": 0.0004,
|
| 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": 1.
|
| 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": 0.0004,
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch": 11.
|
| 801 |
-
"learning_rate": 4.
|
| 802 |
"loss": 0.0004,
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch": 11.
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
"loss": 0.0004,
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch": 11.
|
| 813 |
-
"learning_rate": 4.
|
| 814 |
"loss": 0.0004,
|
| 815 |
-
"step":
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch": 11.
|
| 819 |
-
"learning_rate": 4.
|
| 820 |
"loss": 0.0004,
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 11.
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
"loss": 0.0004,
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch": 11.
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
"loss": 0.0004,
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch": 11.
|
| 837 |
-
"learning_rate": 4.
|
| 838 |
-
"loss": 0.
|
| 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.
|
| 853 |
-
"learning_rate": 4.
|
| 854 |
-
"loss": 0.
|
| 855 |
-
"step":
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch": 12.
|
| 859 |
-
"learning_rate": 4.
|
| 860 |
"loss": 0.0004,
|
| 861 |
-
"step":
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch": 12.
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch": 12.
|
| 871 |
-
"learning_rate": 4.
|
| 872 |
-
"loss": 0.
|
| 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": 0.0004,
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch": 12.
|
| 901 |
-
"learning_rate": 3.
|
| 902 |
-
"loss": 0.
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch": 12.
|
| 907 |
-
"learning_rate": 3.
|
| 908 |
"loss": 0.0004,
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
-
"eval_loss": 0.
|
| 914 |
"eval_max_distance": 3,
|
| 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.
|
| 923 |
-
"learning_rate": 3.
|
| 924 |
"loss": 0.0004,
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch": 13.
|
| 929 |
-
"learning_rate": 3.
|
| 930 |
"loss": 0.0004,
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch": 13.
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
-
"loss": 0.
|
| 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": 0.0003,
|
| 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": 0.0004,
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch": 13.
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
"loss": 0.0003,
|
| 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": 1.
|
| 989 |
-
"step":
|
| 990 |
},
|
| 991 |
{
|
| 992 |
-
"epoch": 14.
|
| 993 |
-
"learning_rate": 3.
|
| 994 |
"loss": 0.0004,
|
| 995 |
-
"step":
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch": 14.
|
| 999 |
-
"learning_rate": 3.
|
| 1000 |
"loss": 0.0003,
|
| 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": 0.0003,
|
| 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": 0.0003,
|
| 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": 0.0003,
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch": 14.
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch": 14.
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
-
"loss": 0.
|
| 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.
|
| 1063 |
-
"learning_rate": 2.
|
| 1064 |
"loss": 0.0003,
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch": 15.
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
"loss": 0.0003,
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch": 15.
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
"loss": 0.0003,
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch": 15.
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
"loss": 0.0003,
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch": 15.
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
"loss": 0.0003,
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch": 15.
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
-
"loss": 0.
|
| 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": 0.0003,
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch": 15.
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
"loss": 0.0003,
|
| 1119 |
-
"step":
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
"eval_max_distance": 3,
|
| 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.
|
| 1133 |
-
"learning_rate": 2.
|
| 1134 |
"loss": 0.0003,
|
| 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": 0.0003,
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch": 16.
|
| 1157 |
-
"learning_rate": 1.
|
| 1158 |
"loss": 0.0003,
|
| 1159 |
-
"step":
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch": 16.
|
| 1163 |
-
"learning_rate": 1.
|
| 1164 |
-
"loss": 0.
|
| 1165 |
-
"step":
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
-
"epoch": 16.
|
| 1169 |
-
"learning_rate": 1.
|
| 1170 |
"loss": 0.0003,
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch": 16.
|
| 1175 |
-
"learning_rate": 1.
|
| 1176 |
"loss": 0.0003,
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch": 16.
|
| 1181 |
-
"learning_rate": 1.
|
| 1182 |
"loss": 0.0003,
|
| 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": 1.
|
| 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": 0.0003,
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch": 17.
|
| 1215 |
-
"learning_rate": 1.
|
| 1216 |
"loss": 0.0003,
|
| 1217 |
-
"step":
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch": 17.
|
| 1221 |
-
"learning_rate": 1.
|
| 1222 |
"loss": 0.0003,
|
| 1223 |
-
"step":
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"epoch": 17.
|
| 1227 |
-
"learning_rate": 1.
|
| 1228 |
"loss": 0.0003,
|
| 1229 |
-
"step":
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
-
"epoch": 17.
|
| 1233 |
-
"learning_rate": 1.
|
| 1234 |
"loss": 0.0003,
|
| 1235 |
-
"step":
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch": 17.
|
| 1239 |
-
"learning_rate": 1.
|
| 1240 |
"loss": 0.0003,
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch": 17.
|
| 1245 |
-
"learning_rate": 1.
|
| 1246 |
"loss": 0.0003,
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch": 17.
|
| 1251 |
-
"learning_rate": 1.
|
| 1252 |
"loss": 0.0003,
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch": 17.
|
| 1257 |
-
"learning_rate": 1.
|
| 1258 |
"loss": 0.0003,
|
| 1259 |
-
"step":
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
-
"eval_loss": 0.
|
| 1264 |
"eval_max_distance": 3,
|
| 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": 0.0003,
|
| 1275 |
-
"step":
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch": 18.
|
| 1279 |
-
"learning_rate": 1.
|
| 1280 |
"loss": 0.0003,
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch": 18.
|
| 1285 |
-
"learning_rate": 9.
|
| 1286 |
"loss": 0.0003,
|
| 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": 0.0003,
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch": 18.
|
| 1309 |
-
"learning_rate": 7.
|
| 1310 |
-
"loss": 0.
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch": 18.
|
| 1315 |
-
"learning_rate": 7.
|
| 1316 |
"loss": 0.0003,
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch": 18.
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
-
"loss": 0.
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18.
|
| 1327 |
-
"learning_rate": 6.
|
| 1328 |
"loss": 0.0003,
|
| 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": 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": 0.0003,
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch": 19.
|
| 1361 |
-
"learning_rate": 3.
|
| 1362 |
"loss": 0.0003,
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch": 19.
|
| 1367 |
-
"learning_rate": 3.
|
| 1368 |
"loss": 0.0003,
|
| 1369 |
-
"step":
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch": 19.
|
| 1373 |
-
"learning_rate": 2.
|
| 1374 |
"loss": 0.0003,
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch": 19.
|
| 1379 |
-
"learning_rate": 2.
|
| 1380 |
-
"loss": 0.
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch": 19.
|
| 1385 |
-
"learning_rate": 1.
|
| 1386 |
"loss": 0.0003,
|
| 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":
|
| 1398 |
"loss": 0.0003,
|
| 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": 1.
|
| 1409 |
-
"step":
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
-
"step":
|
| 1414 |
-
"total_flos": 7.
|
| 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": 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": 279640,
|
| 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": 3.576026319553712e-09,
|
| 14 |
"loss": 0.0,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 5.002860821055643e-06,
|
| 20 |
+
"loss": 0.0011,
|
| 21 |
+
"step": 1399
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.2,
|
| 25 |
+
"learning_rate": 1.0005721642111287e-05,
|
| 26 |
+
"loss": 0.0008,
|
| 27 |
+
"step": 2798
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
+
"learning_rate": 1.500858246316693e-05,
|
| 32 |
+
"loss": 0.0008,
|
| 33 |
+
"step": 4197
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 2.0011443284222573e-05,
|
| 38 |
"loss": 0.0004,
|
| 39 |
+
"step": 5596
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.5,
|
| 43 |
+
"learning_rate": 2.5014304105278213e-05,
|
| 44 |
+
"loss": 0.0004,
|
| 45 |
+
"step": 6995
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
+
"learning_rate": 3.001716492633386e-05,
|
| 50 |
"loss": 0.0004,
|
| 51 |
+
"step": 8394
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.7,
|
| 55 |
+
"learning_rate": 3.5020025747389504e-05,
|
| 56 |
+
"loss": 0.0005,
|
| 57 |
+
"step": 9793
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 4.002288656844515e-05,
|
| 62 |
+
"loss": 0.0003,
|
| 63 |
+
"step": 11192
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
+
"learning_rate": 4.502574738950079e-05,
|
| 68 |
+
"loss": 0.0004,
|
| 69 |
+
"step": 12591
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
+
"eval_loss": 0.01447892002761364,
|
| 74 |
+
"eval_max_distance": 4,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
+
"eval_runtime": 16.1519,
|
| 77 |
+
"eval_samples_per_second": 16.593,
|
| 78 |
+
"eval_steps_per_second": 1.114,
|
| 79 |
+
"step": 13982
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.0,
|
| 83 |
+
"learning_rate": 5.0028608210556425e-05,
|
| 84 |
+
"loss": 0.0004,
|
| 85 |
+
"step": 13990
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 1.1,
|
| 89 |
+
"learning_rate": 5.503146903161207e-05,
|
| 90 |
+
"loss": 0.0004,
|
| 91 |
+
"step": 15389
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
+
"learning_rate": 6.003432985266772e-05,
|
| 96 |
+
"loss": 0.0004,
|
| 97 |
+
"step": 16788
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 1.3,
|
| 101 |
+
"learning_rate": 6.503719067372336e-05,
|
| 102 |
+
"loss": 0.0004,
|
| 103 |
+
"step": 18187
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 1.4,
|
| 107 |
+
"learning_rate": 7.004005149477901e-05,
|
| 108 |
+
"loss": 0.0004,
|
| 109 |
+
"step": 19586
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.5,
|
| 113 |
+
"learning_rate": 7.504291231583464e-05,
|
| 114 |
+
"loss": 0.0004,
|
| 115 |
+
"step": 20985
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.6,
|
| 119 |
+
"learning_rate": 8.00457731368903e-05,
|
| 120 |
"loss": 0.0005,
|
| 121 |
+
"step": 22384
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 1.7,
|
| 125 |
+
"learning_rate": 8.504863395794593e-05,
|
| 126 |
+
"loss": 0.0004,
|
| 127 |
+
"step": 23783
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 1.8,
|
| 131 |
+
"learning_rate": 9.005149477900158e-05,
|
| 132 |
+
"loss": 0.0004,
|
| 133 |
+
"step": 25182
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 1.9,
|
| 137 |
+
"learning_rate": 9.505435560005721e-05,
|
| 138 |
"loss": 0.0005,
|
| 139 |
+
"step": 26581
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
+
"eval_loss": 0.01644507423043251,
|
| 144 |
+
"eval_max_distance": 4,
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
+
"eval_runtime": 14.8804,
|
| 147 |
+
"eval_samples_per_second": 18.01,
|
| 148 |
+
"eval_steps_per_second": 1.21,
|
| 149 |
+
"step": 27964
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 2.0,
|
| 153 |
+
"learning_rate": 9.999364261987636e-05,
|
| 154 |
+
"loss": 0.0004,
|
| 155 |
+
"step": 27980
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 2.1,
|
| 159 |
+
"learning_rate": 9.943776919531461e-05,
|
| 160 |
"loss": 0.0005,
|
| 161 |
+
"step": 29379
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.2,
|
| 165 |
+
"learning_rate": 9.888189577075288e-05,
|
| 166 |
+
"loss": 0.0005,
|
| 167 |
+
"step": 30778
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 2.3,
|
| 171 |
+
"learning_rate": 9.832602234619113e-05,
|
| 172 |
+
"loss": 0.0005,
|
| 173 |
+
"step": 32177
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.4,
|
| 177 |
+
"learning_rate": 9.77701489216294e-05,
|
| 178 |
+
"loss": 0.0005,
|
| 179 |
+
"step": 33576
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 2.5,
|
| 183 |
+
"learning_rate": 9.721427549706766e-05,
|
| 184 |
+
"loss": 0.0005,
|
| 185 |
+
"step": 34975
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 2.6,
|
| 189 |
+
"learning_rate": 9.665840207250593e-05,
|
| 190 |
+
"loss": 0.0006,
|
| 191 |
+
"step": 36374
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.7,
|
| 195 |
+
"learning_rate": 9.61025286479442e-05,
|
| 196 |
"loss": 0.0006,
|
| 197 |
+
"step": 37773
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.8,
|
| 201 |
+
"learning_rate": 9.554665522338245e-05,
|
| 202 |
+
"loss": 0.0005,
|
| 203 |
+
"step": 39172
|
| 204 |
},
|
| 205 |
{
|
| 206 |
"epoch": 2.9,
|
| 207 |
+
"learning_rate": 9.499078179882072e-05,
|
| 208 |
+
"loss": 0.0005,
|
| 209 |
+
"step": 40571
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
+
"eval_loss": 0.016705745831131935,
|
| 214 |
"eval_max_distance": 3,
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
+
"eval_runtime": 14.6064,
|
| 217 |
+
"eval_samples_per_second": 18.348,
|
| 218 |
+
"eval_steps_per_second": 1.232,
|
| 219 |
+
"step": 41946
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 3.0,
|
| 223 |
+
"learning_rate": 9.443490837425897e-05,
|
| 224 |
"loss": 0.0006,
|
| 225 |
+
"step": 41970
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 3.1,
|
| 229 |
+
"learning_rate": 9.387903494969723e-05,
|
| 230 |
+
"loss": 0.0005,
|
| 231 |
+
"step": 43369
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 3.2,
|
| 235 |
+
"learning_rate": 9.33231615251355e-05,
|
| 236 |
"loss": 0.0005,
|
| 237 |
+
"step": 44768
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 3.3,
|
| 241 |
+
"learning_rate": 9.276728810057375e-05,
|
| 242 |
"loss": 0.0006,
|
| 243 |
+
"step": 46167
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 3.4,
|
| 247 |
+
"learning_rate": 9.221141467601202e-05,
|
| 248 |
+
"loss": 0.0005,
|
| 249 |
+
"step": 47566
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 3.5,
|
| 253 |
+
"learning_rate": 9.165554125145028e-05,
|
| 254 |
+
"loss": 0.0006,
|
| 255 |
+
"step": 48965
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.6,
|
| 259 |
+
"learning_rate": 9.109966782688855e-05,
|
| 260 |
+
"loss": 0.0005,
|
| 261 |
+
"step": 50364
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 3.7,
|
| 265 |
+
"learning_rate": 9.054379440232682e-05,
|
| 266 |
+
"loss": 0.0005,
|
| 267 |
+
"step": 51763
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 3.8,
|
| 271 |
+
"learning_rate": 8.998792097776507e-05,
|
| 272 |
+
"loss": 0.0005,
|
| 273 |
+
"step": 53162
|
| 274 |
},
|
| 275 |
{
|
| 276 |
"epoch": 3.9,
|
| 277 |
+
"learning_rate": 8.943204755320333e-05,
|
| 278 |
+
"loss": 0.0005,
|
| 279 |
+
"step": 54561
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 4.0,
|
| 283 |
+
"eval_loss": 0.012466676533222198,
|
| 284 |
+
"eval_max_distance": 3,
|
| 285 |
"eval_mean_distance": 0,
|
| 286 |
+
"eval_runtime": 14.6723,
|
| 287 |
+
"eval_samples_per_second": 18.266,
|
| 288 |
+
"eval_steps_per_second": 1.227,
|
| 289 |
+
"step": 55928
|
| 290 |
},
|
| 291 |
{
|
| 292 |
"epoch": 4.0,
|
| 293 |
+
"learning_rate": 8.887617412864158e-05,
|
| 294 |
"loss": 0.0006,
|
| 295 |
+
"step": 55960
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 4.1,
|
| 299 |
+
"learning_rate": 8.832030070407985e-05,
|
| 300 |
+
"loss": 0.0005,
|
| 301 |
+
"step": 57359
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 4.2,
|
| 305 |
+
"learning_rate": 8.776442727951812e-05,
|
| 306 |
+
"loss": 0.0005,
|
| 307 |
+
"step": 58758
|
| 308 |
},
|
| 309 |
{
|
| 310 |
"epoch": 4.3,
|
| 311 |
+
"learning_rate": 8.720855385495637e-05,
|
| 312 |
"loss": 0.0005,
|
| 313 |
+
"step": 60157
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 4.4,
|
| 317 |
+
"learning_rate": 8.665268043039464e-05,
|
| 318 |
+
"loss": 0.0005,
|
| 319 |
+
"step": 61556
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 4.5,
|
| 323 |
+
"learning_rate": 8.60968070058329e-05,
|
| 324 |
"loss": 0.0005,
|
| 325 |
+
"step": 62955
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.6,
|
| 329 |
+
"learning_rate": 8.554093358127117e-05,
|
| 330 |
+
"loss": 0.0005,
|
| 331 |
+
"step": 64354
|
| 332 |
},
|
| 333 |
{
|
| 334 |
"epoch": 4.7,
|
| 335 |
+
"learning_rate": 8.498506015670943e-05,
|
| 336 |
+
"loss": 0.0006,
|
| 337 |
+
"step": 65753
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.8,
|
| 341 |
+
"learning_rate": 8.442918673214769e-05,
|
| 342 |
+
"loss": 0.0005,
|
| 343 |
+
"step": 67152
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"epoch": 4.9,
|
| 347 |
+
"learning_rate": 8.387331330758594e-05,
|
| 348 |
+
"loss": 0.0005,
|
| 349 |
+
"step": 68551
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 5.0,
|
| 353 |
+
"eval_loss": 0.018481934443116188,
|
| 354 |
+
"eval_max_distance": 3,
|
| 355 |
"eval_mean_distance": 0,
|
| 356 |
+
"eval_runtime": 14.7593,
|
| 357 |
+
"eval_samples_per_second": 18.158,
|
| 358 |
+
"eval_steps_per_second": 1.22,
|
| 359 |
+
"step": 69910
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 5.0,
|
| 363 |
+
"learning_rate": 8.33174398830242e-05,
|
| 364 |
+
"loss": 0.0005,
|
| 365 |
+
"step": 69950
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.1,
|
| 369 |
+
"learning_rate": 8.276156645846247e-05,
|
| 370 |
+
"loss": 0.0005,
|
| 371 |
+
"step": 71349
|
| 372 |
},
|
| 373 |
{
|
| 374 |
"epoch": 5.2,
|
| 375 |
+
"learning_rate": 8.220569303390074e-05,
|
| 376 |
+
"loss": 0.0005,
|
| 377 |
+
"step": 72748
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 5.3,
|
| 381 |
+
"learning_rate": 8.164981960933899e-05,
|
| 382 |
+
"loss": 0.0005,
|
| 383 |
+
"step": 74147
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.4,
|
| 387 |
+
"learning_rate": 8.109394618477726e-05,
|
| 388 |
+
"loss": 0.0005,
|
| 389 |
+
"step": 75546
|
| 390 |
},
|
| 391 |
{
|
| 392 |
"epoch": 5.5,
|
| 393 |
+
"learning_rate": 8.053807276021552e-05,
|
| 394 |
+
"loss": 0.0005,
|
| 395 |
+
"step": 76945
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 5.6,
|
| 399 |
+
"learning_rate": 7.998219933565379e-05,
|
| 400 |
+
"loss": 0.0005,
|
| 401 |
+
"step": 78344
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 5.7,
|
| 405 |
+
"learning_rate": 7.942632591109205e-05,
|
| 406 |
+
"loss": 0.0004,
|
| 407 |
+
"step": 79743
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 5.8,
|
| 411 |
+
"learning_rate": 7.88704524865303e-05,
|
| 412 |
+
"loss": 0.0005,
|
| 413 |
+
"step": 81142
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 5.9,
|
| 417 |
+
"learning_rate": 7.831457906196856e-05,
|
| 418 |
"loss": 0.0005,
|
| 419 |
+
"step": 82541
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.0,
|
| 423 |
+
"eval_loss": 0.017317254096269608,
|
| 424 |
+
"eval_max_distance": 3,
|
| 425 |
"eval_mean_distance": 0,
|
| 426 |
+
"eval_runtime": 14.4763,
|
| 427 |
+
"eval_samples_per_second": 18.513,
|
| 428 |
+
"eval_steps_per_second": 1.243,
|
| 429 |
+
"step": 83892
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 6.0,
|
| 433 |
+
"learning_rate": 7.775870563740682e-05,
|
| 434 |
+
"loss": 0.0005,
|
| 435 |
+
"step": 83940
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 6.1,
|
| 439 |
+
"learning_rate": 7.720283221284509e-05,
|
| 440 |
+
"loss": 0.0004,
|
| 441 |
+
"step": 85339
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 6.2,
|
| 445 |
+
"learning_rate": 7.664695878828336e-05,
|
| 446 |
+
"loss": 0.0006,
|
| 447 |
+
"step": 86738
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.3,
|
| 451 |
+
"learning_rate": 7.609108536372161e-05,
|
| 452 |
+
"loss": 0.0004,
|
| 453 |
+
"step": 88137
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 6.4,
|
| 457 |
+
"learning_rate": 7.553521193915988e-05,
|
| 458 |
+
"loss": 0.0005,
|
| 459 |
+
"step": 89536
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 6.5,
|
| 463 |
+
"learning_rate": 7.497933851459814e-05,
|
| 464 |
+
"loss": 0.0004,
|
| 465 |
+
"step": 90935
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 6.6,
|
| 469 |
+
"learning_rate": 7.44234650900364e-05,
|
| 470 |
+
"loss": 0.0004,
|
| 471 |
+
"step": 92334
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 6.7,
|
| 475 |
+
"learning_rate": 7.386759166547467e-05,
|
| 476 |
"loss": 0.0005,
|
| 477 |
+
"step": 93733
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 6.8,
|
| 481 |
+
"learning_rate": 7.331171824091292e-05,
|
| 482 |
+
"loss": 0.0004,
|
| 483 |
+
"step": 95132
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.9,
|
| 487 |
+
"learning_rate": 7.275584481635118e-05,
|
| 488 |
"loss": 0.0005,
|
| 489 |
+
"step": 96531
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.0,
|
| 493 |
+
"eval_loss": 0.016764231026172638,
|
| 494 |
+
"eval_max_distance": 5,
|
| 495 |
"eval_mean_distance": 0,
|
| 496 |
+
"eval_runtime": 14.4483,
|
| 497 |
+
"eval_samples_per_second": 18.549,
|
| 498 |
+
"eval_steps_per_second": 1.246,
|
| 499 |
+
"step": 97874
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.0,
|
| 503 |
+
"learning_rate": 7.219997139178944e-05,
|
| 504 |
"loss": 0.0005,
|
| 505 |
+
"step": 97930
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 7.1,
|
| 509 |
+
"learning_rate": 7.164409796722771e-05,
|
| 510 |
"loss": 0.0005,
|
| 511 |
+
"step": 99329
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 7.2,
|
| 515 |
+
"learning_rate": 7.108822454266598e-05,
|
| 516 |
"loss": 0.0005,
|
| 517 |
+
"step": 100728
|
| 518 |
},
|
| 519 |
{
|
| 520 |
"epoch": 7.3,
|
| 521 |
+
"learning_rate": 7.053235111810423e-05,
|
| 522 |
+
"loss": 0.0005,
|
| 523 |
+
"step": 102127
|
| 524 |
},
|
| 525 |
{
|
| 526 |
"epoch": 7.4,
|
| 527 |
+
"learning_rate": 6.99764776935425e-05,
|
| 528 |
"loss": 0.0005,
|
| 529 |
+
"step": 103526
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.5,
|
| 533 |
+
"learning_rate": 6.942060426898076e-05,
|
| 534 |
+
"loss": 0.0005,
|
| 535 |
+
"step": 104925
|
| 536 |
},
|
| 537 |
{
|
| 538 |
"epoch": 7.6,
|
| 539 |
+
"learning_rate": 6.886473084441902e-05,
|
| 540 |
+
"loss": 0.0004,
|
| 541 |
+
"step": 106324
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 7.7,
|
| 545 |
+
"learning_rate": 6.830885741985728e-05,
|
| 546 |
+
"loss": 0.0005,
|
| 547 |
+
"step": 107723
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 7.8,
|
| 551 |
+
"learning_rate": 6.775298399529553e-05,
|
| 552 |
+
"loss": 0.0004,
|
| 553 |
+
"step": 109122
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 7.9,
|
| 557 |
+
"learning_rate": 6.71971105707338e-05,
|
| 558 |
+
"loss": 0.0004,
|
| 559 |
+
"step": 110521
|
| 560 |
},
|
| 561 |
{
|
| 562 |
"epoch": 8.0,
|
| 563 |
+
"eval_loss": 0.020108750090003014,
|
| 564 |
+
"eval_max_distance": 5,
|
| 565 |
"eval_mean_distance": 0,
|
| 566 |
+
"eval_runtime": 14.4845,
|
| 567 |
+
"eval_samples_per_second": 18.503,
|
| 568 |
+
"eval_steps_per_second": 1.243,
|
| 569 |
+
"step": 111856
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 8.0,
|
| 573 |
+
"learning_rate": 6.664123714617206e-05,
|
| 574 |
+
"loss": 0.0004,
|
| 575 |
+
"step": 111920
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.1,
|
| 579 |
+
"learning_rate": 6.608536372161033e-05,
|
| 580 |
"loss": 0.0005,
|
| 581 |
+
"step": 113319
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 8.2,
|
| 585 |
+
"learning_rate": 6.55294902970486e-05,
|
| 586 |
+
"loss": 0.0004,
|
| 587 |
+
"step": 114718
|
| 588 |
},
|
| 589 |
{
|
| 590 |
"epoch": 8.3,
|
| 591 |
+
"learning_rate": 6.497361687248685e-05,
|
| 592 |
"loss": 0.0005,
|
| 593 |
+
"step": 116117
|
| 594 |
},
|
| 595 |
{
|
| 596 |
"epoch": 8.4,
|
| 597 |
+
"learning_rate": 6.441774344792512e-05,
|
| 598 |
"loss": 0.0005,
|
| 599 |
+
"step": 117516
|
| 600 |
},
|
| 601 |
{
|
| 602 |
"epoch": 8.5,
|
| 603 |
+
"learning_rate": 6.386187002336337e-05,
|
| 604 |
"loss": 0.0005,
|
| 605 |
+
"step": 118915
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 8.6,
|
| 609 |
+
"learning_rate": 6.330599659880164e-05,
|
| 610 |
+
"loss": 0.0004,
|
| 611 |
+
"step": 120314
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 8.7,
|
| 615 |
+
"learning_rate": 6.27501231742399e-05,
|
| 616 |
+
"loss": 0.0004,
|
| 617 |
+
"step": 121713
|
| 618 |
},
|
| 619 |
{
|
| 620 |
+
"epoch": 8.81,
|
| 621 |
+
"learning_rate": 6.219424974967815e-05,
|
| 622 |
+
"loss": 0.0004,
|
| 623 |
+
"step": 123112
|
| 624 |
},
|
| 625 |
{
|
| 626 |
+
"epoch": 8.91,
|
| 627 |
+
"learning_rate": 6.163837632511642e-05,
|
| 628 |
+
"loss": 0.0004,
|
| 629 |
+
"step": 124511
|
| 630 |
},
|
| 631 |
{
|
| 632 |
"epoch": 9.0,
|
| 633 |
+
"eval_loss": 0.021496200934052467,
|
| 634 |
+
"eval_max_distance": 2,
|
| 635 |
"eval_mean_distance": 0,
|
| 636 |
+
"eval_runtime": 14.5428,
|
| 637 |
+
"eval_samples_per_second": 18.428,
|
| 638 |
+
"eval_steps_per_second": 1.238,
|
| 639 |
+
"step": 125838
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 9.01,
|
| 643 |
+
"learning_rate": 6.108250290055468e-05,
|
| 644 |
"loss": 0.0004,
|
| 645 |
+
"step": 125910
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 9.11,
|
| 649 |
+
"learning_rate": 6.0526629475992947e-05,
|
| 650 |
"loss": 0.0004,
|
| 651 |
+
"step": 127309
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 9.21,
|
| 655 |
+
"learning_rate": 5.997075605143121e-05,
|
| 656 |
+
"loss": 0.0004,
|
| 657 |
+
"step": 128708
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 9.31,
|
| 661 |
+
"learning_rate": 5.941488262686947e-05,
|
| 662 |
+
"loss": 0.0004,
|
| 663 |
+
"step": 130107
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 9.41,
|
| 667 |
+
"learning_rate": 5.885900920230773e-05,
|
| 668 |
+
"loss": 0.0004,
|
| 669 |
+
"step": 131506
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 9.51,
|
| 673 |
+
"learning_rate": 5.8303135777746e-05,
|
| 674 |
+
"loss": 0.0004,
|
| 675 |
+
"step": 132905
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 9.61,
|
| 679 |
+
"learning_rate": 5.774726235318425e-05,
|
| 680 |
+
"loss": 0.0004,
|
| 681 |
+
"step": 134304
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 9.71,
|
| 685 |
+
"learning_rate": 5.719138892862251e-05,
|
| 686 |
"loss": 0.0005,
|
| 687 |
+
"step": 135703
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 9.81,
|
| 691 |
+
"learning_rate": 5.663551550406077e-05,
|
| 692 |
+
"loss": 0.0004,
|
| 693 |
+
"step": 137102
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 9.91,
|
| 697 |
+
"learning_rate": 5.607964207949904e-05,
|
| 698 |
+
"loss": 0.0004,
|
| 699 |
+
"step": 138501
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 10.0,
|
| 703 |
+
"eval_loss": 0.0225870031863451,
|
| 704 |
+
"eval_max_distance": 3,
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
+
"eval_runtime": 15.0837,
|
| 707 |
+
"eval_samples_per_second": 17.768,
|
| 708 |
+
"eval_steps_per_second": 1.193,
|
| 709 |
+
"step": 139820
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 10.01,
|
| 713 |
+
"learning_rate": 5.5523768654937304e-05,
|
| 714 |
+
"loss": 0.0004,
|
| 715 |
+
"step": 139900
|
| 716 |
},
|
| 717 |
{
|
| 718 |
+
"epoch": 10.11,
|
| 719 |
+
"learning_rate": 5.4967895230375566e-05,
|
| 720 |
+
"loss": 0.0004,
|
| 721 |
+
"step": 141299
|
| 722 |
},
|
| 723 |
{
|
| 724 |
+
"epoch": 10.21,
|
| 725 |
+
"learning_rate": 5.441202180581383e-05,
|
| 726 |
+
"loss": 0.0004,
|
| 727 |
+
"step": 142698
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 10.31,
|
| 731 |
+
"learning_rate": 5.385614838125209e-05,
|
| 732 |
+
"loss": 0.0004,
|
| 733 |
+
"step": 144097
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"epoch": 10.41,
|
| 737 |
+
"learning_rate": 5.330027495669035e-05,
|
| 738 |
+
"loss": 0.0004,
|
| 739 |
+
"step": 145496
|
| 740 |
},
|
| 741 |
{
|
| 742 |
+
"epoch": 10.51,
|
| 743 |
+
"learning_rate": 5.274440153212862e-05,
|
| 744 |
+
"loss": 0.0004,
|
| 745 |
+
"step": 146895
|
| 746 |
},
|
| 747 |
{
|
| 748 |
+
"epoch": 10.61,
|
| 749 |
+
"learning_rate": 5.218852810756687e-05,
|
| 750 |
"loss": 0.0004,
|
| 751 |
+
"step": 148294
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 10.71,
|
| 755 |
+
"learning_rate": 5.163265468300513e-05,
|
| 756 |
"loss": 0.0004,
|
| 757 |
+
"step": 149693
|
| 758 |
},
|
| 759 |
{
|
| 760 |
+
"epoch": 10.81,
|
| 761 |
+
"learning_rate": 5.107678125844339e-05,
|
| 762 |
+
"loss": 0.0004,
|
| 763 |
+
"step": 151092
|
| 764 |
},
|
| 765 |
{
|
| 766 |
+
"epoch": 10.91,
|
| 767 |
+
"learning_rate": 5.052090783388166e-05,
|
| 768 |
"loss": 0.0004,
|
| 769 |
+
"step": 152491
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 11.0,
|
| 773 |
+
"eval_loss": 0.019947679713368416,
|
| 774 |
+
"eval_max_distance": 3,
|
| 775 |
"eval_mean_distance": 0,
|
| 776 |
+
"eval_runtime": 14.3656,
|
| 777 |
+
"eval_samples_per_second": 18.656,
|
| 778 |
+
"eval_steps_per_second": 1.253,
|
| 779 |
+
"step": 153802
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 11.01,
|
| 783 |
+
"learning_rate": 4.9965034409319923e-05,
|
| 784 |
+
"loss": 0.0004,
|
| 785 |
+
"step": 153890
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 11.11,
|
| 789 |
+
"learning_rate": 4.9409160984758185e-05,
|
| 790 |
+
"loss": 0.0003,
|
| 791 |
+
"step": 155289
|
| 792 |
},
|
| 793 |
{
|
| 794 |
+
"epoch": 11.21,
|
| 795 |
+
"learning_rate": 4.885328756019645e-05,
|
| 796 |
"loss": 0.0004,
|
| 797 |
+
"step": 156688
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 11.31,
|
| 801 |
+
"learning_rate": 4.82974141356347e-05,
|
| 802 |
"loss": 0.0004,
|
| 803 |
+
"step": 158087
|
| 804 |
},
|
| 805 |
{
|
| 806 |
+
"epoch": 11.41,
|
| 807 |
+
"learning_rate": 4.774154071107297e-05,
|
| 808 |
"loss": 0.0004,
|
| 809 |
+
"step": 159486
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 11.51,
|
| 813 |
+
"learning_rate": 4.718566728651123e-05,
|
| 814 |
"loss": 0.0004,
|
| 815 |
+
"step": 160885
|
| 816 |
},
|
| 817 |
{
|
| 818 |
+
"epoch": 11.61,
|
| 819 |
+
"learning_rate": 4.6629793861949495e-05,
|
| 820 |
"loss": 0.0004,
|
| 821 |
+
"step": 162284
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 11.71,
|
| 825 |
+
"learning_rate": 4.607392043738775e-05,
|
| 826 |
"loss": 0.0004,
|
| 827 |
+
"step": 163683
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 11.81,
|
| 831 |
+
"learning_rate": 4.551804701282601e-05,
|
| 832 |
"loss": 0.0004,
|
| 833 |
+
"step": 165082
|
| 834 |
},
|
| 835 |
{
|
| 836 |
+
"epoch": 11.91,
|
| 837 |
+
"learning_rate": 4.496217358826428e-05,
|
| 838 |
+
"loss": 0.0003,
|
| 839 |
+
"step": 166481
|
| 840 |
},
|
| 841 |
{
|
| 842 |
"epoch": 12.0,
|
| 843 |
+
"eval_loss": 0.018351813778281212,
|
| 844 |
+
"eval_max_distance": 3,
|
| 845 |
"eval_mean_distance": 0,
|
| 846 |
+
"eval_runtime": 14.3946,
|
| 847 |
+
"eval_samples_per_second": 18.618,
|
| 848 |
+
"eval_steps_per_second": 1.25,
|
| 849 |
+
"step": 167784
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 12.01,
|
| 853 |
+
"learning_rate": 4.440630016370254e-05,
|
| 854 |
+
"loss": 0.0003,
|
| 855 |
+
"step": 167880
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 12.11,
|
| 859 |
+
"learning_rate": 4.3850426739140805e-05,
|
| 860 |
"loss": 0.0004,
|
| 861 |
+
"step": 169279
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 12.21,
|
| 865 |
+
"learning_rate": 4.329455331457906e-05,
|
| 866 |
+
"loss": 0.0003,
|
| 867 |
+
"step": 170678
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 12.31,
|
| 871 |
+
"learning_rate": 4.273867989001732e-05,
|
| 872 |
+
"loss": 0.0003,
|
| 873 |
+
"step": 172077
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 12.41,
|
| 877 |
+
"learning_rate": 4.218280646545559e-05,
|
| 878 |
+
"loss": 0.0003,
|
| 879 |
+
"step": 173476
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 12.51,
|
| 883 |
+
"learning_rate": 4.162693304089385e-05,
|
| 884 |
+
"loss": 0.0003,
|
| 885 |
+
"step": 174875
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 12.61,
|
| 889 |
+
"learning_rate": 4.1071059616332115e-05,
|
| 890 |
+
"loss": 0.0003,
|
| 891 |
+
"step": 176274
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 12.71,
|
| 895 |
+
"learning_rate": 4.051518619177037e-05,
|
| 896 |
"loss": 0.0004,
|
| 897 |
+
"step": 177673
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 12.81,
|
| 901 |
+
"learning_rate": 3.995931276720863e-05,
|
| 902 |
+
"loss": 0.0003,
|
| 903 |
+
"step": 179072
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 12.91,
|
| 907 |
+
"learning_rate": 3.94034393426469e-05,
|
| 908 |
"loss": 0.0004,
|
| 909 |
+
"step": 180471
|
| 910 |
},
|
| 911 |
{
|
| 912 |
"epoch": 13.0,
|
| 913 |
+
"eval_loss": 0.019636347889900208,
|
| 914 |
"eval_max_distance": 3,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 14.3221,
|
| 917 |
+
"eval_samples_per_second": 18.712,
|
| 918 |
+
"eval_steps_per_second": 1.257,
|
| 919 |
+
"step": 181766
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 13.01,
|
| 923 |
+
"learning_rate": 3.884756591808516e-05,
|
| 924 |
"loss": 0.0004,
|
| 925 |
+
"step": 181870
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 13.11,
|
| 929 |
+
"learning_rate": 3.8291692493523424e-05,
|
| 930 |
"loss": 0.0004,
|
| 931 |
+
"step": 183269
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 13.21,
|
| 935 |
+
"learning_rate": 3.773581906896168e-05,
|
| 936 |
+
"loss": 0.0004,
|
| 937 |
+
"step": 184668
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 13.31,
|
| 941 |
+
"learning_rate": 3.717994564439994e-05,
|
| 942 |
+
"loss": 0.0003,
|
| 943 |
+
"step": 186067
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 13.41,
|
| 947 |
+
"learning_rate": 3.662407221983821e-05,
|
| 948 |
"loss": 0.0003,
|
| 949 |
+
"step": 187466
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 13.51,
|
| 953 |
+
"learning_rate": 3.606819879527647e-05,
|
| 954 |
+
"loss": 0.0003,
|
| 955 |
+
"step": 188865
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 13.61,
|
| 959 |
+
"learning_rate": 3.551232537071473e-05,
|
| 960 |
+
"loss": 0.0003,
|
| 961 |
+
"step": 190264
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 13.71,
|
| 965 |
+
"learning_rate": 3.495645194615299e-05,
|
| 966 |
"loss": 0.0004,
|
| 967 |
+
"step": 191663
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 13.81,
|
| 971 |
+
"learning_rate": 3.440057852159125e-05,
|
| 972 |
"loss": 0.0003,
|
| 973 |
+
"step": 193062
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 13.91,
|
| 977 |
+
"learning_rate": 3.384470509702952e-05,
|
| 978 |
+
"loss": 0.0003,
|
| 979 |
+
"step": 194461
|
| 980 |
},
|
| 981 |
{
|
| 982 |
"epoch": 14.0,
|
| 983 |
+
"eval_loss": 0.01673734560608864,
|
| 984 |
+
"eval_max_distance": 1,
|
| 985 |
"eval_mean_distance": 0,
|
| 986 |
+
"eval_runtime": 14.3426,
|
| 987 |
+
"eval_samples_per_second": 18.686,
|
| 988 |
+
"eval_steps_per_second": 1.255,
|
| 989 |
+
"step": 195748
|
| 990 |
},
|
| 991 |
{
|
| 992 |
+
"epoch": 14.01,
|
| 993 |
+
"learning_rate": 3.328883167246778e-05,
|
| 994 |
"loss": 0.0004,
|
| 995 |
+
"step": 195860
|
| 996 |
},
|
| 997 |
{
|
| 998 |
+
"epoch": 14.11,
|
| 999 |
+
"learning_rate": 3.273295824790604e-05,
|
| 1000 |
"loss": 0.0003,
|
| 1001 |
+
"step": 197259
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 14.21,
|
| 1005 |
+
"learning_rate": 3.21770848233443e-05,
|
| 1006 |
+
"loss": 0.0003,
|
| 1007 |
+
"step": 198658
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 14.31,
|
| 1011 |
+
"learning_rate": 3.162121139878256e-05,
|
| 1012 |
"loss": 0.0003,
|
| 1013 |
+
"step": 200057
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 14.41,
|
| 1017 |
+
"learning_rate": 3.106533797422082e-05,
|
| 1018 |
+
"loss": 0.0003,
|
| 1019 |
+
"step": 201456
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 14.51,
|
| 1023 |
+
"learning_rate": 3.0509464549659088e-05,
|
| 1024 |
"loss": 0.0003,
|
| 1025 |
+
"step": 202855
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 14.61,
|
| 1029 |
+
"learning_rate": 2.9953591125097347e-05,
|
| 1030 |
+
"loss": 0.0003,
|
| 1031 |
+
"step": 204254
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 14.71,
|
| 1035 |
+
"learning_rate": 2.939771770053561e-05,
|
| 1036 |
"loss": 0.0003,
|
| 1037 |
+
"step": 205653
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 14.81,
|
| 1041 |
+
"learning_rate": 2.8841844275973874e-05,
|
| 1042 |
"loss": 0.0004,
|
| 1043 |
+
"step": 207052
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 14.91,
|
| 1047 |
+
"learning_rate": 2.8285970851412136e-05,
|
| 1048 |
+
"loss": 0.0003,
|
| 1049 |
+
"step": 208451
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.0,
|
| 1053 |
+
"eval_loss": 0.017744125798344612,
|
| 1054 |
+
"eval_max_distance": 3,
|
| 1055 |
"eval_mean_distance": 0,
|
| 1056 |
+
"eval_runtime": 14.4379,
|
| 1057 |
+
"eval_samples_per_second": 18.562,
|
| 1058 |
+
"eval_steps_per_second": 1.247,
|
| 1059 |
+
"step": 209730
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
+
"epoch": 15.01,
|
| 1063 |
+
"learning_rate": 2.7730097426850398e-05,
|
| 1064 |
"loss": 0.0003,
|
| 1065 |
+
"step": 209850
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 15.11,
|
| 1069 |
+
"learning_rate": 2.7174224002288656e-05,
|
| 1070 |
"loss": 0.0003,
|
| 1071 |
+
"step": 211249
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 15.21,
|
| 1075 |
+
"learning_rate": 2.661835057772692e-05,
|
| 1076 |
"loss": 0.0003,
|
| 1077 |
+
"step": 212648
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
+
"epoch": 15.31,
|
| 1081 |
+
"learning_rate": 2.6062477153165184e-05,
|
| 1082 |
"loss": 0.0003,
|
| 1083 |
+
"step": 214047
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
+
"epoch": 15.41,
|
| 1087 |
+
"learning_rate": 2.5506603728603446e-05,
|
| 1088 |
"loss": 0.0003,
|
| 1089 |
+
"step": 215446
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 15.51,
|
| 1093 |
+
"learning_rate": 2.4950730304041704e-05,
|
| 1094 |
+
"loss": 0.0003,
|
| 1095 |
+
"step": 216845
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 15.61,
|
| 1099 |
+
"learning_rate": 2.439485687947997e-05,
|
| 1100 |
+
"loss": 0.0003,
|
| 1101 |
+
"step": 218244
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 15.71,
|
| 1105 |
+
"learning_rate": 2.3838983454918228e-05,
|
| 1106 |
+
"loss": 0.0003,
|
| 1107 |
+
"step": 219643
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 15.81,
|
| 1111 |
+
"learning_rate": 2.3283110030356493e-05,
|
| 1112 |
"loss": 0.0003,
|
| 1113 |
+
"step": 221042
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 15.91,
|
| 1117 |
+
"learning_rate": 2.2727236605794752e-05,
|
| 1118 |
"loss": 0.0003,
|
| 1119 |
+
"step": 222441
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 16.0,
|
| 1123 |
+
"eval_loss": 0.01732315868139267,
|
| 1124 |
"eval_max_distance": 3,
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
+
"eval_runtime": 14.4573,
|
| 1127 |
+
"eval_samples_per_second": 18.537,
|
| 1128 |
+
"eval_steps_per_second": 1.245,
|
| 1129 |
+
"step": 223712
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 16.01,
|
| 1133 |
+
"learning_rate": 2.2171363181233014e-05,
|
| 1134 |
"loss": 0.0003,
|
| 1135 |
+
"step": 223840
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
+
"epoch": 16.11,
|
| 1139 |
+
"learning_rate": 2.1615489756671276e-05,
|
| 1140 |
+
"loss": 0.0003,
|
| 1141 |
+
"step": 225239
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
+
"epoch": 16.21,
|
| 1145 |
+
"learning_rate": 2.1059616332109538e-05,
|
| 1146 |
+
"loss": 0.0003,
|
| 1147 |
+
"step": 226638
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
+
"epoch": 16.31,
|
| 1151 |
+
"learning_rate": 2.0503742907547803e-05,
|
| 1152 |
"loss": 0.0003,
|
| 1153 |
+
"step": 228037
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
+
"epoch": 16.41,
|
| 1157 |
+
"learning_rate": 1.994786948298606e-05,
|
| 1158 |
"loss": 0.0003,
|
| 1159 |
+
"step": 229436
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
+
"epoch": 16.51,
|
| 1163 |
+
"learning_rate": 1.9391996058424324e-05,
|
| 1164 |
+
"loss": 0.0003,
|
| 1165 |
+
"step": 230835
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
+
"epoch": 16.61,
|
| 1169 |
+
"learning_rate": 1.8836122633862586e-05,
|
| 1170 |
"loss": 0.0003,
|
| 1171 |
+
"step": 232234
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 16.71,
|
| 1175 |
+
"learning_rate": 1.8280249209300847e-05,
|
| 1176 |
"loss": 0.0003,
|
| 1177 |
+
"step": 233633
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
+
"epoch": 16.81,
|
| 1181 |
+
"learning_rate": 1.7724375784739113e-05,
|
| 1182 |
"loss": 0.0003,
|
| 1183 |
+
"step": 235032
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 16.91,
|
| 1187 |
+
"learning_rate": 1.716850236017737e-05,
|
| 1188 |
+
"loss": 0.0003,
|
| 1189 |
+
"step": 236431
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
"epoch": 17.0,
|
| 1193 |
+
"eval_loss": 0.01732039824128151,
|
| 1194 |
+
"eval_max_distance": 3,
|
| 1195 |
"eval_mean_distance": 0,
|
| 1196 |
+
"eval_runtime": 14.4615,
|
| 1197 |
+
"eval_samples_per_second": 18.532,
|
| 1198 |
+
"eval_steps_per_second": 1.245,
|
| 1199 |
+
"step": 237694
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
+
"epoch": 17.01,
|
| 1203 |
+
"learning_rate": 1.6612628935615633e-05,
|
| 1204 |
+
"loss": 0.0003,
|
| 1205 |
+
"step": 237830
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
+
"epoch": 17.11,
|
| 1209 |
+
"learning_rate": 1.6056755511053895e-05,
|
| 1210 |
"loss": 0.0003,
|
| 1211 |
+
"step": 239229
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
+
"epoch": 17.21,
|
| 1215 |
+
"learning_rate": 1.5500882086492157e-05,
|
| 1216 |
"loss": 0.0003,
|
| 1217 |
+
"step": 240628
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
+
"epoch": 17.31,
|
| 1221 |
+
"learning_rate": 1.4945008661930417e-05,
|
| 1222 |
"loss": 0.0003,
|
| 1223 |
+
"step": 242027
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
+
"epoch": 17.41,
|
| 1227 |
+
"learning_rate": 1.4389135237368681e-05,
|
| 1228 |
"loss": 0.0003,
|
| 1229 |
+
"step": 243426
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
+
"epoch": 17.51,
|
| 1233 |
+
"learning_rate": 1.3833261812806945e-05,
|
| 1234 |
"loss": 0.0003,
|
| 1235 |
+
"step": 244825
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
+
"epoch": 17.61,
|
| 1239 |
+
"learning_rate": 1.3277388388245205e-05,
|
| 1240 |
"loss": 0.0003,
|
| 1241 |
+
"step": 246224
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
+
"epoch": 17.71,
|
| 1245 |
+
"learning_rate": 1.2721514963683467e-05,
|
| 1246 |
"loss": 0.0003,
|
| 1247 |
+
"step": 247623
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
+
"epoch": 17.81,
|
| 1251 |
+
"learning_rate": 1.2165641539121729e-05,
|
| 1252 |
"loss": 0.0003,
|
| 1253 |
+
"step": 249022
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
+
"epoch": 17.91,
|
| 1257 |
+
"learning_rate": 1.160976811455999e-05,
|
| 1258 |
"loss": 0.0003,
|
| 1259 |
+
"step": 250421
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 18.0,
|
| 1263 |
+
"eval_loss": 0.016897281631827354,
|
| 1264 |
"eval_max_distance": 3,
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
+
"eval_runtime": 14.4833,
|
| 1267 |
+
"eval_samples_per_second": 18.504,
|
| 1268 |
+
"eval_steps_per_second": 1.243,
|
| 1269 |
+
"step": 251676
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 18.01,
|
| 1273 |
+
"learning_rate": 1.1053894689998253e-05,
|
| 1274 |
"loss": 0.0003,
|
| 1275 |
+
"step": 251820
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 18.11,
|
| 1279 |
+
"learning_rate": 1.0498021265436515e-05,
|
| 1280 |
"loss": 0.0003,
|
| 1281 |
+
"step": 253219
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 18.21,
|
| 1285 |
+
"learning_rate": 9.942147840874775e-06,
|
| 1286 |
"loss": 0.0003,
|
| 1287 |
+
"step": 254618
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 18.31,
|
| 1291 |
+
"learning_rate": 9.386274416313037e-06,
|
| 1292 |
"loss": 0.0003,
|
| 1293 |
+
"step": 256017
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 18.41,
|
| 1297 |
+
"learning_rate": 8.8304009917513e-06,
|
| 1298 |
+
"loss": 0.0002,
|
| 1299 |
+
"step": 257416
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 18.51,
|
| 1303 |
+
"learning_rate": 8.274527567189562e-06,
|
| 1304 |
"loss": 0.0003,
|
| 1305 |
+
"step": 258815
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
+
"epoch": 18.61,
|
| 1309 |
+
"learning_rate": 7.718654142627824e-06,
|
| 1310 |
+
"loss": 0.0003,
|
| 1311 |
+
"step": 260214
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
+
"epoch": 18.71,
|
| 1315 |
+
"learning_rate": 7.1627807180660855e-06,
|
| 1316 |
"loss": 0.0003,
|
| 1317 |
+
"step": 261613
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
+
"epoch": 18.81,
|
| 1321 |
+
"learning_rate": 6.606907293504347e-06,
|
| 1322 |
+
"loss": 0.0002,
|
| 1323 |
+
"step": 263012
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 18.91,
|
| 1327 |
+
"learning_rate": 6.051033868942609e-06,
|
| 1328 |
"loss": 0.0003,
|
| 1329 |
+
"step": 264411
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 19.0,
|
| 1333 |
+
"eval_loss": 0.016652461141347885,
|
| 1334 |
+
"eval_max_distance": 3,
|
| 1335 |
"eval_mean_distance": 0,
|
| 1336 |
+
"eval_runtime": 14.4508,
|
| 1337 |
+
"eval_samples_per_second": 18.546,
|
| 1338 |
+
"eval_steps_per_second": 1.246,
|
| 1339 |
+
"step": 265658
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
+
"epoch": 19.01,
|
| 1343 |
+
"learning_rate": 5.4951604443808705e-06,
|
| 1344 |
+
"loss": 0.0002,
|
| 1345 |
+
"step": 265810
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
+
"epoch": 19.11,
|
| 1349 |
+
"learning_rate": 4.9392870198191324e-06,
|
| 1350 |
+
"loss": 0.0002,
|
| 1351 |
+
"step": 267209
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
+
"epoch": 19.21,
|
| 1355 |
+
"learning_rate": 4.383413595257395e-06,
|
| 1356 |
"loss": 0.0003,
|
| 1357 |
+
"step": 268608
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
+
"epoch": 19.31,
|
| 1361 |
+
"learning_rate": 3.827540170695656e-06,
|
| 1362 |
"loss": 0.0003,
|
| 1363 |
+
"step": 270007
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
+
"epoch": 19.41,
|
| 1367 |
+
"learning_rate": 3.2716667461339183e-06,
|
| 1368 |
"loss": 0.0003,
|
| 1369 |
+
"step": 271406
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
+
"epoch": 19.51,
|
| 1373 |
+
"learning_rate": 2.71579332157218e-06,
|
| 1374 |
"loss": 0.0003,
|
| 1375 |
+
"step": 272805
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
+
"epoch": 19.61,
|
| 1379 |
+
"learning_rate": 2.159919897010442e-06,
|
| 1380 |
+
"loss": 0.0002,
|
| 1381 |
+
"step": 274204
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
+
"epoch": 19.71,
|
| 1385 |
+
"learning_rate": 1.604046472448704e-06,
|
| 1386 |
"loss": 0.0003,
|
| 1387 |
+
"step": 275603
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
+
"epoch": 19.81,
|
| 1391 |
+
"learning_rate": 1.0481730478869658e-06,
|
| 1392 |
"loss": 0.0003,
|
| 1393 |
+
"step": 277002
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
+
"epoch": 19.91,
|
| 1397 |
+
"learning_rate": 4.922996233252277e-07,
|
| 1398 |
"loss": 0.0003,
|
| 1399 |
+
"step": 278401
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
"epoch": 20.0,
|
| 1403 |
+
"eval_loss": 0.017029350623488426,
|
| 1404 |
+
"eval_max_distance": 3,
|
| 1405 |
"eval_mean_distance": 0,
|
| 1406 |
+
"eval_runtime": 14.4724,
|
| 1407 |
+
"eval_samples_per_second": 18.518,
|
| 1408 |
+
"eval_steps_per_second": 1.244,
|
| 1409 |
+
"step": 279640
|
| 1410 |
},
|
| 1411 |
{
|
| 1412 |
"epoch": 20.0,
|
| 1413 |
+
"step": 279640,
|
| 1414 |
+
"total_flos": 7.310805087246336e+16,
|
| 1415 |
+
"train_loss": 0.00039881850996483783,
|
| 1416 |
+
"train_runtime": 20247.2262,
|
| 1417 |
+
"train_samples_per_second": 207.164,
|
| 1418 |
+
"train_steps_per_second": 13.811
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
+
"logging_steps": 1399,
|
| 1422 |
+
"max_steps": 279640,
|
| 1423 |
"num_train_epochs": 20,
|
| 1424 |
+
"save_steps": 2797,
|
| 1425 |
+
"total_flos": 7.310805087246336e+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 sha256:7d8a3d0207b71233d440dfc4ea0e1be195fbf0ff77bc164bd8950b614fbebbd5
|
| 3 |
size 4091
|