End of training
Browse files- README.md +14 -24
- pytorch_model.bin +1 -1
- trainer_state.json +883 -983
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -13,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# text-normalization-ru-new
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on
|
| 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 |
|
|
@@ -43,32 +43,22 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.0006 | 11.0 | 81466 | 0.0005 | 0 | 3 |
|
| 63 |
-
| 0.0004 | 12.0 | 88872 | 0.0005 | 0 | 3 |
|
| 64 |
-
| 0.0004 | 13.0 | 96278 | 0.0005 | 0 | 3 |
|
| 65 |
-
| 0.0005 | 14.0 | 103684 | 0.0005 | 0 | 3 |
|
| 66 |
-
| 0.0004 | 15.0 | 111090 | 0.0004 | 0 | 3 |
|
| 67 |
-
| 0.0004 | 16.0 | 118496 | 0.0004 | 0 | 3 |
|
| 68 |
-
| 0.0004 | 17.0 | 125902 | 0.0004 | 0 | 3 |
|
| 69 |
-
| 0.0004 | 18.0 | 133308 | 0.0005 | 0 | 3 |
|
| 70 |
-
| 0.0004 | 19.0 | 140714 | 0.0005 | 0 | 3 |
|
| 71 |
-
| 0.0004 | 20.0 | 148120 | 0.0005 | 0 | 3 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
# text-normalization-ru-new
|
| 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: 0.0480
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 40
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 10
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0163 | 1.0 | 23701 | 0.0428 | 0 | 43 |
|
| 53 |
+
| 0.0132 | 2.0 | 47402 | 0.0420 | 0 | 44 |
|
| 54 |
+
| 0.0111 | 3.0 | 71103 | 0.0444 | 0 | 35 |
|
| 55 |
+
| 0.0095 | 4.0 | 94804 | 0.0449 | 0 | 43 |
|
| 56 |
+
| 0.0088 | 5.0 | 118505 | 0.0446 | 0 | 40 |
|
| 57 |
+
| 0.0076 | 6.0 | 142206 | 0.0462 | 0 | 33 |
|
| 58 |
+
| 0.0074 | 7.0 | 165907 | 0.0466 | 0 | 38 |
|
| 59 |
+
| 0.0068 | 8.0 | 189608 | 0.0478 | 0 | 39 |
|
| 60 |
+
| 0.0069 | 9.0 | 213309 | 0.0489 | 0 | 39 |
|
| 61 |
+
| 0.0061 | 10.0 | 237010 | 0.0480 | 0 | 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### 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 sha256:62d9ab81d1f15680b1091a69a3fcb0d3aa6dd8840f3113d83f54bc29fa9fec0a
|
| 3 |
size 258643461
|
trainer_state.json
CHANGED
|
@@ -1,1428 +1,1328 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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.
|
| 19 |
-
"learning_rate": 5.
|
| 20 |
-
"loss": 0.
|
| 21 |
-
"step":
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.2,
|
| 25 |
-
"learning_rate": 1.0005401026194977e-05,
|
| 26 |
-
"loss": 0.0027,
|
| 27 |
-
"step": 1482
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 0.
|
| 39 |
-
"step":
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 2.
|
| 44 |
-
"loss": 0.
|
| 45 |
-
"step":
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 3.
|
| 56 |
-
"loss": 0.
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 0.
|
| 63 |
-
"step":
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 4.
|
| 68 |
-
"loss": 0.
|
| 69 |
-
"step":
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch":
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"eval_runtime": 12.6183,
|
| 77 |
-
"eval_samples_per_second": 15.85,
|
| 78 |
-
"eval_steps_per_second": 1.11,
|
| 79 |
-
"step": 7406
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"learning_rate": 5.
|
| 84 |
-
"loss": 0.
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch":
|
| 89 |
-
"learning_rate": 5.
|
| 90 |
-
"loss": 0.
|
| 91 |
-
"step":
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"epoch":
|
| 95 |
-
"learning_rate": 6.
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"epoch":
|
| 101 |
-
"learning_rate": 6.
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"step":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
-
"epoch":
|
| 107 |
-
"learning_rate": 7.
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch":
|
| 113 |
-
"learning_rate": 7.
|
| 114 |
-
"loss": 0.
|
| 115 |
-
"step":
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch":
|
| 119 |
-
"learning_rate": 8.
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"learning_rate": 8.
|
| 126 |
-
"loss": 0.
|
| 127 |
-
"step":
|
| 128 |
},
|
| 129 |
{
|
| 130 |
-
"epoch":
|
| 131 |
-
"learning_rate": 9.
|
| 132 |
-
"loss": 0.
|
| 133 |
-
"step":
|
| 134 |
},
|
| 135 |
{
|
| 136 |
-
"epoch":
|
| 137 |
-
"learning_rate": 9.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
| 140 |
},
|
| 141 |
{
|
| 142 |
-
"epoch":
|
| 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": 9.999399885978337e-05,
|
| 154 |
-
"loss": 0.0013,
|
| 155 |
-
"step": 14820
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch":
|
| 159 |
-
"learning_rate": 9.
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch":
|
| 165 |
-
"learning_rate": 9.
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch":
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch":
|
| 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":
|
| 189 |
-
"learning_rate": 9.
|
| 190 |
-
"loss": 0.
|
| 191 |
-
"step":
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch":
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
-
"learning_rate": 9.
|
| 208 |
-
"loss": 0.
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"eval_runtime": 11.7305,
|
| 217 |
-
"eval_samples_per_second": 17.05,
|
| 218 |
-
"eval_steps_per_second": 1.193,
|
| 219 |
-
"step": 22218
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate": 9.
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate": 9.
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"learning_rate": 9.
|
| 236 |
-
"loss": 0.
|
| 237 |
-
"step":
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate": 9.
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate": 9.
|
| 248 |
-
"loss": 0.
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"learning_rate": 9.
|
| 254 |
-
"loss": 0.
|
| 255 |
-
"step":
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
-
"learning_rate": 9.
|
| 260 |
-
"loss": 0.
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"learning_rate": 9.
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"learning_rate": 8.
|
| 272 |
-
"loss": 0.
|
| 273 |
-
"step":
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch":
|
| 277 |
-
"learning_rate": 8.
|
| 278 |
-
"loss": 0.
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 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": 8.88768866084556e-05,
|
| 294 |
-
"loss": 0.0009,
|
| 295 |
-
"step": 29640
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch":
|
| 299 |
-
"learning_rate": 8.
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"step":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
-
"epoch":
|
| 305 |
-
"learning_rate": 8.
|
| 306 |
-
"loss": 0.
|
| 307 |
-
"step":
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"learning_rate": 8.
|
| 312 |
-
"loss": 0.
|
| 313 |
-
"step":
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch":
|
| 317 |
-
"learning_rate": 8.
|
| 318 |
-
"loss": 0.
|
| 319 |
-
"step":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"epoch":
|
| 323 |
-
"learning_rate": 8.
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch":
|
| 329 |
-
"learning_rate": 8.
|
| 330 |
-
"loss": 0.
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch":
|
| 335 |
-
"learning_rate": 8.
|
| 336 |
-
"loss": 0.
|
| 337 |
-
"step":
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch":
|
| 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":
|
| 353 |
-
"
|
| 354 |
-
"
|
| 355 |
-
"
|
| 356 |
-
"eval_runtime": 11.6179,
|
| 357 |
-
"eval_samples_per_second": 17.215,
|
| 358 |
-
"eval_steps_per_second": 1.205,
|
| 359 |
-
"step": 37030
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 5
|
| 363 |
-
"learning_rate": 8.
|
| 364 |
-
"loss": 0.
|
| 365 |
-
"step":
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch":
|
| 369 |
-
"learning_rate": 8.
|
| 370 |
-
"loss": 0.
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch":
|
| 375 |
-
"learning_rate": 8.
|
| 376 |
-
"loss": 0.
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch":
|
| 381 |
-
"learning_rate": 8.
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"step":
|
| 384 |
},
|
| 385 |
{
|
| 386 |
-
"epoch":
|
| 387 |
-
"learning_rate": 8.
|
| 388 |
-
"loss": 0.
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"learning_rate": 8.
|
| 394 |
-
"loss": 0.
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch":
|
| 399 |
-
"learning_rate": 7.
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"step":
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch":
|
| 405 |
-
"learning_rate": 7.
|
| 406 |
-
"loss": 0.
|
| 407 |
-
"step":
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch":
|
| 411 |
-
"learning_rate": 7.
|
| 412 |
-
"loss": 0.
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"epoch":
|
| 417 |
-
"learning_rate": 7.
|
| 418 |
-
"loss": 0.
|
| 419 |
-
"step":
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch":
|
| 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": 7.775977435712786e-05,
|
| 434 |
-
"loss": 0.0007,
|
| 435 |
-
"step": 44460
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch":
|
| 439 |
-
"learning_rate": 7.
|
| 440 |
-
"loss": 0.
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch":
|
| 445 |
-
"learning_rate": 7.
|
| 446 |
-
"loss": 0.
|
| 447 |
-
"step":
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch":
|
| 451 |
-
"learning_rate": 7.
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch":
|
| 457 |
-
"learning_rate": 7.
|
| 458 |
-
"loss": 0.
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch":
|
| 463 |
-
"learning_rate": 7.
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch":
|
| 469 |
-
"learning_rate": 7.
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch":
|
| 475 |
-
"learning_rate": 7.
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch":
|
| 481 |
-
"learning_rate": 7.
|
| 482 |
-
"loss": 0.
|
| 483 |
-
"step":
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"learning_rate": 7.
|
| 488 |
-
"loss": 0.
|
| 489 |
-
"step":
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
-
"
|
| 494 |
-
"
|
| 495 |
-
"
|
| 496 |
-
"eval_runtime": 11.6249,
|
| 497 |
-
"eval_samples_per_second": 17.204,
|
| 498 |
-
"eval_steps_per_second": 1.204,
|
| 499 |
-
"step": 51842
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch":
|
| 503 |
-
"learning_rate": 7.
|
| 504 |
-
"loss": 0.
|
| 505 |
-
"step":
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch":
|
| 509 |
-
"learning_rate": 7.
|
| 510 |
-
"loss": 0.
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
-
"learning_rate": 7.
|
| 516 |
-
"loss": 0.
|
| 517 |
-
"step":
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch":
|
| 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":
|
| 533 |
-
"learning_rate": 6.
|
| 534 |
-
"loss": 0.
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch":
|
| 539 |
-
"learning_rate": 6.
|
| 540 |
-
"loss": 0.
|
| 541 |
-
"step":
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch":
|
| 545 |
-
"learning_rate": 6.
|
| 546 |
-
"loss": 0.
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch":
|
| 551 |
-
"learning_rate": 6.
|
| 552 |
-
"loss": 0.
|
| 553 |
-
"step":
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch":
|
| 557 |
-
"learning_rate": 6.
|
| 558 |
-
"loss": 0.
|
| 559 |
-
"step":
|
| 560 |
},
|
| 561 |
{
|
| 562 |
-
"epoch":
|
| 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":
|
| 573 |
-
"learning_rate": 6.
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 8.1,
|
| 579 |
-
"learning_rate": 6.608680649323372e-05,
|
| 580 |
-
"loss": 0.0006,
|
| 581 |
-
"step": 60021
|
| 582 |
},
|
| 583 |
{
|
| 584 |
-
"epoch":
|
| 585 |
-
"learning_rate": 6.
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
-
"epoch":
|
| 591 |
-
"learning_rate": 6.
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch":
|
| 597 |
-
"learning_rate": 6.
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
-
"epoch":
|
| 603 |
-
"learning_rate": 6.
|
| 604 |
-
"loss": 0.
|
| 605 |
-
"step":
|
| 606 |
},
|
| 607 |
{
|
| 608 |
-
"epoch":
|
| 609 |
-
"learning_rate": 6.
|
| 610 |
-
"loss": 0.
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"learning_rate": 6.
|
| 616 |
-
"loss": 0.
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch":
|
| 621 |
-
"learning_rate": 6.
|
| 622 |
-
"loss": 0.
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch":
|
| 627 |
-
"learning_rate": 6.
|
| 628 |
-
"loss": 0.
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
-
"epoch":
|
| 633 |
-
"
|
| 634 |
-
"
|
| 635 |
-
"
|
| 636 |
-
"eval_runtime": 11.584,
|
| 637 |
-
"eval_samples_per_second": 17.265,
|
| 638 |
-
"eval_steps_per_second": 1.209,
|
| 639 |
-
"step": 66654
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"learning_rate": 6.
|
| 644 |
-
"loss": 0.
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
-
"learning_rate": 6.
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch":
|
| 655 |
-
"learning_rate": 5.
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"step":
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch":
|
| 661 |
-
"learning_rate": 5.
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch":
|
| 667 |
-
"learning_rate": 5.
|
| 668 |
-
"loss": 0.
|
| 669 |
-
"step":
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch":
|
| 673 |
-
"learning_rate": 5.
|
| 674 |
-
"loss": 0.
|
| 675 |
-
"step":
|
| 676 |
},
|
| 677 |
{
|
| 678 |
-
"epoch":
|
| 679 |
-
"learning_rate": 5.
|
| 680 |
-
"loss": 0.
|
| 681 |
-
"step":
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 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":
|
| 697 |
-
"learning_rate": 5.
|
| 698 |
-
"loss": 0.
|
| 699 |
-
"step":
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch":
|
| 703 |
-
"eval_loss": 0.
|
| 704 |
-
"eval_max_distance":
|
| 705 |
"eval_mean_distance": 0,
|
| 706 |
-
"eval_runtime":
|
| 707 |
-
"eval_samples_per_second":
|
| 708 |
-
"eval_steps_per_second": 1.
|
| 709 |
-
"step":
|
| 710 |
-
},
|
| 711 |
-
{
|
| 712 |
-
"epoch": 10.01,
|
| 713 |
-
"learning_rate": 5.5525549854472346e-05,
|
| 714 |
-
"loss": 0.0005,
|
| 715 |
-
"step": 74100
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch":
|
| 719 |
-
"learning_rate": 5.
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch":
|
| 725 |
-
"learning_rate": 5.
|
| 726 |
-
"loss": 0.
|
| 727 |
-
"step":
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"epoch":
|
| 731 |
-
"learning_rate": 5.
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"step":
|
| 734 |
},
|
| 735 |
{
|
| 736 |
-
"epoch":
|
| 737 |
-
"learning_rate": 5.
|
| 738 |
-
"loss": 0.
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch":
|
| 743 |
-
"learning_rate": 5.
|
| 744 |
-
"loss": 0.
|
| 745 |
-
"step":
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch":
|
| 749 |
-
"learning_rate": 5.
|
| 750 |
-
"loss": 0.
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch":
|
| 755 |
-
"learning_rate": 5.
|
| 756 |
-
"loss": 0.
|
| 757 |
-
"step":
|
| 758 |
},
|
| 759 |
{
|
| 760 |
-
"epoch":
|
| 761 |
-
"learning_rate": 5.
|
| 762 |
-
"loss": 0.
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
-
"epoch":
|
| 767 |
-
"learning_rate": 5.
|
| 768 |
-
"loss": 0.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
-
"epoch":
|
| 773 |
-
"
|
| 774 |
-
"
|
| 775 |
-
"
|
| 776 |
-
"eval_runtime": 11.4873,
|
| 777 |
-
"eval_samples_per_second": 17.411,
|
| 778 |
-
"eval_steps_per_second": 1.219,
|
| 779 |
-
"step": 81466
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch":
|
| 783 |
-
"learning_rate": 4.
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch":
|
| 789 |
-
"learning_rate": 4.
|
| 790 |
-
"loss": 0.
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch":
|
| 795 |
-
"learning_rate": 4.
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
-
"learning_rate": 4.
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch":
|
| 807 |
-
"learning_rate": 4.
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch":
|
| 813 |
-
"learning_rate": 4.
|
| 814 |
-
"loss": 0.
|
| 815 |
-
"step":
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch":
|
| 819 |
-
"learning_rate": 4.
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch":
|
| 825 |
-
"learning_rate": 4.
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch":
|
| 831 |
-
"learning_rate": 4.
|
| 832 |
-
"loss": 0.
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch":
|
| 837 |
-
"learning_rate": 4.
|
| 838 |
-
"loss": 0.
|
| 839 |
-
"step":
|
| 840 |
},
|
| 841 |
{
|
| 842 |
-
"epoch":
|
| 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":
|
| 853 |
-
"learning_rate": 4.
|
| 854 |
-
"loss": 0.
|
| 855 |
-
"step":
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 12.11,
|
| 859 |
-
"learning_rate": 4.3852581990578214e-05,
|
| 860 |
-
"loss": 0.0005,
|
| 861 |
-
"step": 89661
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"learning_rate": 4.
|
| 866 |
-
"loss": 0.
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"learning_rate": 4.
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
},
|
| 875 |
{
|
| 876 |
-
"epoch":
|
| 877 |
-
"learning_rate": 4.
|
| 878 |
-
"loss": 0.
|
| 879 |
-
"step":
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch":
|
| 883 |
-
"learning_rate": 4.
|
| 884 |
-
"loss": 0.
|
| 885 |
-
"step":
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch":
|
| 889 |
-
"learning_rate": 4.
|
| 890 |
-
"loss": 0.
|
| 891 |
-
"step":
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch":
|
| 895 |
-
"learning_rate": 4.
|
| 896 |
-
"loss": 0.
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate":
|
| 902 |
-
"loss": 0.
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"learning_rate": 3.
|
| 908 |
-
"loss": 0.
|
| 909 |
-
"step":
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch":
|
| 913 |
-
"
|
| 914 |
-
"
|
| 915 |
-
"
|
| 916 |
-
"eval_runtime": 11.6638,
|
| 917 |
-
"eval_samples_per_second": 17.147,
|
| 918 |
-
"eval_steps_per_second": 1.2,
|
| 919 |
-
"step": 96278
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch":
|
| 923 |
-
"learning_rate": 3.
|
| 924 |
-
"loss": 0.
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch":
|
| 929 |
-
"learning_rate": 3.
|
| 930 |
-
"loss": 0.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch":
|
| 935 |
-
"learning_rate": 3.
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch":
|
| 941 |
-
"learning_rate": 3.
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch":
|
| 947 |
-
"learning_rate": 3.
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch":
|
| 953 |
-
"learning_rate": 3.
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch":
|
| 959 |
-
"learning_rate": 3.
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch":
|
| 965 |
-
"learning_rate": 3.
|
| 966 |
-
"loss": 0.
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch":
|
| 971 |
-
"learning_rate": 3.
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch":
|
| 977 |
-
"learning_rate": 3.
|
| 978 |
-
"loss": 0.
|
| 979 |
-
"step":
|
| 980 |
},
|
| 981 |
{
|
| 982 |
-
"epoch":
|
| 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": 14.01,
|
| 993 |
-
"learning_rate": 3.329132535181685e-05,
|
| 994 |
-
"loss": 0.0005,
|
| 995 |
-
"step": 103740
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch":
|
| 999 |
-
"learning_rate": 3.
|
| 1000 |
-
"loss": 0.
|
| 1001 |
-
"step":
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch":
|
| 1005 |
-
"learning_rate": 3.
|
| 1006 |
-
"loss": 0.
|
| 1007 |
-
"step":
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch":
|
| 1011 |
-
"learning_rate": 3.
|
| 1012 |
-
"loss": 0.
|
| 1013 |
-
"step":
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch":
|
| 1017 |
-
"learning_rate": 3.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
-
"step":
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
-
"epoch":
|
| 1023 |
-
"learning_rate": 3.
|
| 1024 |
-
"loss": 0.
|
| 1025 |
-
"step":
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
-
"epoch":
|
| 1029 |
-
"learning_rate":
|
| 1030 |
-
"loss": 0.
|
| 1031 |
-
"step":
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
-
"epoch":
|
| 1035 |
-
"learning_rate": 2.
|
| 1036 |
-
"loss": 0.
|
| 1037 |
-
"step":
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
-
"epoch":
|
| 1041 |
-
"learning_rate": 2.
|
| 1042 |
-
"loss": 0.
|
| 1043 |
-
"step":
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"learning_rate": 2.
|
| 1048 |
-
"loss": 0.
|
| 1049 |
-
"step":
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch":
|
| 1053 |
-
"
|
| 1054 |
-
"
|
| 1055 |
-
"
|
| 1056 |
-
"eval_runtime": 11.6927,
|
| 1057 |
-
"eval_samples_per_second": 17.105,
|
| 1058 |
-
"eval_steps_per_second": 1.197,
|
| 1059 |
-
"step": 111090
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
-
"epoch":
|
| 1063 |
-
"learning_rate": 2.
|
| 1064 |
-
"loss": 0.
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch":
|
| 1069 |
-
"learning_rate": 2.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch":
|
| 1075 |
-
"learning_rate": 2.
|
| 1076 |
-
"loss": 0.
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch":
|
| 1081 |
-
"learning_rate": 2.
|
| 1082 |
-
"loss": 0.
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch":
|
| 1087 |
-
"learning_rate": 2.
|
| 1088 |
-
"loss": 0.
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch":
|
| 1093 |
-
"learning_rate": 2.
|
| 1094 |
-
"loss": 0.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch":
|
| 1099 |
-
"learning_rate": 2.
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch":
|
| 1105 |
-
"learning_rate": 2.
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch":
|
| 1111 |
-
"learning_rate": 2.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch":
|
| 1117 |
-
"learning_rate": 2.
|
| 1118 |
-
"loss": 0.
|
| 1119 |
-
"step":
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
-
"epoch":
|
| 1123 |
-
"eval_loss": 0.
|
| 1124 |
-
"eval_max_distance":
|
| 1125 |
"eval_mean_distance": 0,
|
| 1126 |
-
"eval_runtime":
|
| 1127 |
-
"eval_samples_per_second":
|
| 1128 |
-
"eval_steps_per_second": 1.
|
| 1129 |
-
"step":
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 16.01,
|
| 1133 |
-
"learning_rate": 2.2174213100489093e-05,
|
| 1134 |
-
"loss": 0.0004,
|
| 1135 |
-
"step": 118560
|
| 1136 |
},
|
| 1137 |
{
|
| 1138 |
-
"epoch":
|
| 1139 |
-
"learning_rate": 2.
|
| 1140 |
-
"loss": 0.
|
| 1141 |
-
"step":
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch":
|
| 1145 |
-
"learning_rate": 2.
|
| 1146 |
-
"loss": 0.
|
| 1147 |
-
"step":
|
| 1148 |
},
|
| 1149 |
{
|
| 1150 |
-
"epoch":
|
| 1151 |
-
"learning_rate": 2.
|
| 1152 |
-
"loss": 0.
|
| 1153 |
-
"step":
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
-
"epoch": 16
|
| 1157 |
-
"learning_rate":
|
| 1158 |
-
"loss": 0.
|
| 1159 |
-
"step":
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch":
|
| 1163 |
-
"learning_rate": 1.
|
| 1164 |
-
"loss": 0.
|
| 1165 |
-
"step":
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
-
"epoch":
|
| 1169 |
-
"learning_rate": 1.
|
| 1170 |
-
"loss": 0.
|
| 1171 |
-
"step":
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch":
|
| 1175 |
-
"learning_rate": 1.
|
| 1176 |
-
"loss": 0.
|
| 1177 |
-
"step":
|
| 1178 |
},
|
| 1179 |
{
|
| 1180 |
-
"epoch":
|
| 1181 |
-
"learning_rate": 1.
|
| 1182 |
-
"loss": 0.
|
| 1183 |
-
"step":
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch":
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
-
"loss": 0.
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
-
"epoch":
|
| 1193 |
-
"
|
| 1194 |
-
"
|
| 1195 |
-
"
|
| 1196 |
-
"eval_runtime": 11.7083,
|
| 1197 |
-
"eval_samples_per_second": 17.082,
|
| 1198 |
-
"eval_steps_per_second": 1.196,
|
| 1199 |
-
"step": 125902
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch":
|
| 1203 |
-
"learning_rate": 1.
|
| 1204 |
-
"loss": 0.
|
| 1205 |
-
"step":
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
-
"epoch":
|
| 1209 |
-
"learning_rate": 1.
|
| 1210 |
-
"loss": 0.
|
| 1211 |
-
"step":
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
-
"epoch":
|
| 1215 |
-
"learning_rate": 1.
|
| 1216 |
-
"loss": 0.
|
| 1217 |
-
"step":
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
-
"epoch":
|
| 1221 |
-
"learning_rate": 1.
|
| 1222 |
-
"loss": 0.
|
| 1223 |
-
"step":
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
-
"epoch":
|
| 1227 |
-
"learning_rate": 1.
|
| 1228 |
-
"loss": 0.
|
| 1229 |
-
"step":
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
-
"epoch":
|
| 1233 |
-
"learning_rate": 1.
|
| 1234 |
-
"loss": 0.
|
| 1235 |
-
"step":
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch":
|
| 1239 |
-
"learning_rate": 1.
|
| 1240 |
-
"loss": 0.
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch":
|
| 1245 |
-
"learning_rate": 1.
|
| 1246 |
-
"loss": 0.
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch":
|
| 1251 |
-
"learning_rate": 1.
|
| 1252 |
-
"loss": 0.
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch":
|
| 1257 |
-
"learning_rate": 1.
|
| 1258 |
-
"loss": 0.
|
| 1259 |
-
"step":
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
-
"epoch":
|
| 1263 |
-
"eval_loss": 0.
|
| 1264 |
-
"eval_max_distance":
|
| 1265 |
"eval_mean_distance": 0,
|
| 1266 |
-
"eval_runtime":
|
| 1267 |
-
"eval_samples_per_second":
|
| 1268 |
-
"eval_steps_per_second": 1.
|
| 1269 |
-
"step":
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch":
|
| 1273 |
-
"learning_rate": 1.
|
| 1274 |
-
"loss": 0.
|
| 1275 |
-
"step":
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch":
|
| 1279 |
-
"learning_rate": 1.
|
| 1280 |
-
"loss": 0.
|
| 1281 |
-
"step":
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
-
"epoch":
|
| 1285 |
-
"learning_rate": 9.
|
| 1286 |
-
"loss": 0.
|
| 1287 |
-
"step":
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch":
|
| 1291 |
-
"learning_rate": 9.
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
-
"epoch":
|
| 1297 |
-
"learning_rate": 8.
|
| 1298 |
-
"loss": 0.
|
| 1299 |
-
"step":
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
-
"epoch":
|
| 1303 |
-
"learning_rate": 8.
|
| 1304 |
-
"loss": 0.
|
| 1305 |
-
"step":
|
| 1306 |
},
|
| 1307 |
{
|
| 1308 |
-
"epoch":
|
| 1309 |
-
"learning_rate": 7.
|
| 1310 |
-
"loss": 0.
|
| 1311 |
-
"step":
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
-
"epoch":
|
| 1315 |
-
"learning_rate": 7.
|
| 1316 |
-
"loss": 0.
|
| 1317 |
-
"step":
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch":
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
-
"loss": 0.
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch":
|
| 1327 |
-
"learning_rate": 6.
|
| 1328 |
-
"loss": 0.
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
-
"epoch":
|
| 1333 |
-
"
|
| 1334 |
-
"
|
| 1335 |
-
"
|
| 1336 |
-
"eval_runtime": 12.022,
|
| 1337 |
-
"eval_samples_per_second": 16.636,
|
| 1338 |
-
"eval_steps_per_second": 1.165,
|
| 1339 |
-
"step": 140714
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
-
"epoch":
|
| 1343 |
-
"learning_rate":
|
| 1344 |
-
"loss": 0.
|
| 1345 |
-
"step":
|
| 1346 |
},
|
| 1347 |
{
|
| 1348 |
-
"epoch":
|
| 1349 |
-
"learning_rate": 4.
|
| 1350 |
-
"loss": 0.
|
| 1351 |
-
"step":
|
| 1352 |
},
|
| 1353 |
{
|
| 1354 |
-
"epoch":
|
| 1355 |
-
"learning_rate":
|
| 1356 |
-
"loss": 0.
|
| 1357 |
-
"step":
|
| 1358 |
},
|
| 1359 |
{
|
| 1360 |
-
"epoch":
|
| 1361 |
-
"learning_rate": 3.
|
| 1362 |
-
"loss": 0.
|
| 1363 |
-
"step":
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
-
"epoch":
|
| 1367 |
-
"learning_rate":
|
| 1368 |
-
"loss": 0.
|
| 1369 |
-
"step":
|
| 1370 |
},
|
| 1371 |
{
|
| 1372 |
-
"epoch":
|
| 1373 |
-
"learning_rate": 2.
|
| 1374 |
-
"loss": 0.
|
| 1375 |
-
"step":
|
| 1376 |
},
|
| 1377 |
{
|
| 1378 |
-
"epoch":
|
| 1379 |
-
"learning_rate":
|
| 1380 |
-
"loss": 0.
|
| 1381 |
-
"step":
|
| 1382 |
},
|
| 1383 |
{
|
| 1384 |
-
"epoch":
|
| 1385 |
-
"learning_rate": 1.
|
| 1386 |
-
"loss": 0.
|
| 1387 |
-
"step":
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
-
"epoch":
|
| 1391 |
-
"learning_rate":
|
| 1392 |
-
"loss": 0.
|
| 1393 |
-
"step":
|
| 1394 |
},
|
| 1395 |
{
|
| 1396 |
-
"epoch":
|
| 1397 |
-
"
|
| 1398 |
-
"
|
| 1399 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1400 |
},
|
| 1401 |
{
|
| 1402 |
-
"epoch":
|
| 1403 |
-
"
|
| 1404 |
-
"
|
| 1405 |
-
"
|
| 1406 |
-
"
|
| 1407 |
-
"
|
| 1408 |
-
"
|
| 1409 |
-
"step": 148120
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 20.0,
|
| 1413 |
-
"step": 148120,
|
| 1414 |
-
"total_flos": 4.156808335340544e+16,
|
| 1415 |
-
"train_loss": 0.0007127845361891936,
|
| 1416 |
-
"train_runtime": 10957.7889,
|
| 1417 |
-
"train_samples_per_second": 202.738,
|
| 1418 |
-
"train_steps_per_second": 13.517
|
| 1419 |
}
|
| 1420 |
],
|
| 1421 |
-
"logging_steps":
|
| 1422 |
-
"max_steps":
|
| 1423 |
-
"num_train_epochs":
|
| 1424 |
-
"save_steps":
|
| 1425 |
-
"total_flos":
|
| 1426 |
"trial_name": null,
|
| 1427 |
"trial_params": null
|
| 1428 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 237010,
|
| 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": 4.219231256065145e-09,
|
| 14 |
+
"loss": 0.0425,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 5.004008269693263e-06,
|
| 20 |
+
"loss": 0.1718,
|
| 21 |
+
"step": 1186
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 1.0008016539386525e-05,
|
| 26 |
+
"loss": 0.0835,
|
| 27 |
+
"step": 2372
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 1.5012024809079786e-05,
|
| 32 |
+
"loss": 0.0432,
|
| 33 |
+
"step": 3558
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.2,
|
| 37 |
+
"learning_rate": 2.001603307877305e-05,
|
| 38 |
+
"loss": 0.0324,
|
| 39 |
+
"step": 4744
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.25,
|
| 43 |
+
"learning_rate": 2.5020041348466312e-05,
|
| 44 |
+
"loss": 0.03,
|
| 45 |
+
"step": 5930
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.3,
|
| 49 |
+
"learning_rate": 3.0024049618159573e-05,
|
| 50 |
+
"loss": 0.0266,
|
| 51 |
+
"step": 7116
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"learning_rate": 3.5028057887852834e-05,
|
| 56 |
+
"loss": 0.0236,
|
| 57 |
+
"step": 8302
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.4,
|
| 61 |
+
"learning_rate": 4.00320661575461e-05,
|
| 62 |
+
"loss": 0.0219,
|
| 63 |
+
"step": 9488
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.45,
|
| 67 |
+
"learning_rate": 4.503607442723936e-05,
|
| 68 |
+
"loss": 0.0202,
|
| 69 |
+
"step": 10674
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.5,
|
| 73 |
+
"learning_rate": 5.0040082696932624e-05,
|
| 74 |
+
"loss": 0.0196,
|
| 75 |
+
"step": 11860
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.55,
|
| 79 |
+
"learning_rate": 5.5044090966625885e-05,
|
| 80 |
+
"loss": 0.0195,
|
| 81 |
+
"step": 13046
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.6,
|
| 85 |
+
"learning_rate": 6.0048099236319146e-05,
|
| 86 |
+
"loss": 0.0183,
|
| 87 |
+
"step": 14232
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.65,
|
| 91 |
+
"learning_rate": 6.50521075060124e-05,
|
| 92 |
+
"loss": 0.0181,
|
| 93 |
+
"step": 15418
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.7,
|
| 97 |
+
"learning_rate": 7.005611577570567e-05,
|
| 98 |
+
"loss": 0.0174,
|
| 99 |
+
"step": 16604
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.75,
|
| 103 |
+
"learning_rate": 7.506012404539893e-05,
|
| 104 |
+
"loss": 0.0175,
|
| 105 |
+
"step": 17790
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.8,
|
| 109 |
+
"learning_rate": 8.00641323150922e-05,
|
| 110 |
+
"loss": 0.0159,
|
| 111 |
+
"step": 18976
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.85,
|
| 115 |
+
"learning_rate": 8.506814058478546e-05,
|
| 116 |
+
"loss": 0.0165,
|
| 117 |
+
"step": 20162
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.9,
|
| 121 |
+
"learning_rate": 9.007214885447873e-05,
|
| 122 |
+
"loss": 0.0164,
|
| 123 |
+
"step": 21348
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.95,
|
| 127 |
+
"learning_rate": 9.507615712417199e-05,
|
| 128 |
+
"loss": 0.0163,
|
| 129 |
+
"step": 22534
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 1.0,
|
| 133 |
+
"eval_loss": 0.04283371567726135,
|
| 134 |
+
"eval_max_distance": 43,
|
| 135 |
"eval_mean_distance": 0,
|
| 136 |
+
"eval_runtime": 16.0673,
|
| 137 |
+
"eval_samples_per_second": 15.56,
|
| 138 |
+
"eval_steps_per_second": 1.058,
|
| 139 |
+
"step": 23701
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
+
"epoch": 1.0,
|
| 143 |
+
"learning_rate": 9.999109273401498e-05,
|
| 144 |
+
"loss": 0.0161,
|
| 145 |
+
"step": 23720
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 1.05,
|
| 149 |
+
"learning_rate": 9.943509181516017e-05,
|
| 150 |
+
"loss": 0.0146,
|
| 151 |
+
"step": 24906
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.1,
|
| 155 |
+
"learning_rate": 9.887909089630536e-05,
|
| 156 |
+
"loss": 0.0151,
|
| 157 |
+
"step": 26092
|
| 158 |
},
|
| 159 |
{
|
| 160 |
+
"epoch": 1.15,
|
| 161 |
+
"learning_rate": 9.832308997745055e-05,
|
| 162 |
+
"loss": 0.0144,
|
| 163 |
+
"step": 27278
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 1.2,
|
| 167 |
+
"learning_rate": 9.776708905859574e-05,
|
| 168 |
+
"loss": 0.0135,
|
| 169 |
+
"step": 28464
|
| 170 |
},
|
| 171 |
{
|
| 172 |
+
"epoch": 1.25,
|
| 173 |
+
"learning_rate": 9.721108813974095e-05,
|
| 174 |
+
"loss": 0.0146,
|
| 175 |
+
"step": 29650
|
| 176 |
},
|
| 177 |
{
|
| 178 |
+
"epoch": 1.3,
|
| 179 |
+
"learning_rate": 9.665508722088614e-05,
|
| 180 |
+
"loss": 0.0139,
|
| 181 |
+
"step": 30836
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 1.35,
|
| 185 |
+
"learning_rate": 9.609908630203133e-05,
|
| 186 |
+
"loss": 0.0135,
|
| 187 |
+
"step": 32022
|
| 188 |
},
|
| 189 |
{
|
| 190 |
+
"epoch": 1.4,
|
| 191 |
+
"learning_rate": 9.554308538317653e-05,
|
| 192 |
+
"loss": 0.0137,
|
| 193 |
+
"step": 33208
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 1.45,
|
| 197 |
+
"learning_rate": 9.498708446432172e-05,
|
| 198 |
+
"loss": 0.0137,
|
| 199 |
+
"step": 34394
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 1.5,
|
| 203 |
+
"learning_rate": 9.443108354546691e-05,
|
| 204 |
+
"loss": 0.0141,
|
| 205 |
+
"step": 35580
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 1.55,
|
| 209 |
+
"learning_rate": 9.38750826266121e-05,
|
| 210 |
+
"loss": 0.0126,
|
| 211 |
+
"step": 36766
|
| 212 |
},
|
| 213 |
{
|
| 214 |
+
"epoch": 1.6,
|
| 215 |
+
"learning_rate": 9.331908170775729e-05,
|
| 216 |
+
"loss": 0.014,
|
| 217 |
+
"step": 37952
|
| 218 |
},
|
| 219 |
{
|
| 220 |
+
"epoch": 1.65,
|
| 221 |
+
"learning_rate": 9.276308078890248e-05,
|
| 222 |
+
"loss": 0.0133,
|
| 223 |
+
"step": 39138
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 1.7,
|
| 227 |
+
"learning_rate": 9.220707987004769e-05,
|
| 228 |
+
"loss": 0.0134,
|
| 229 |
+
"step": 40324
|
| 230 |
},
|
| 231 |
{
|
| 232 |
+
"epoch": 1.75,
|
| 233 |
+
"learning_rate": 9.165107895119287e-05,
|
| 234 |
+
"loss": 0.0126,
|
| 235 |
+
"step": 41510
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 1.8,
|
| 239 |
+
"learning_rate": 9.109507803233807e-05,
|
| 240 |
+
"loss": 0.0137,
|
| 241 |
+
"step": 42696
|
| 242 |
},
|
| 243 |
{
|
| 244 |
+
"epoch": 1.85,
|
| 245 |
+
"learning_rate": 9.053907711348326e-05,
|
| 246 |
+
"loss": 0.0145,
|
| 247 |
+
"step": 43882
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 1.9,
|
| 251 |
+
"learning_rate": 8.998307619462846e-05,
|
| 252 |
+
"loss": 0.0126,
|
| 253 |
+
"step": 45068
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 1.95,
|
| 257 |
+
"learning_rate": 8.942707527577365e-05,
|
| 258 |
+
"loss": 0.0132,
|
| 259 |
+
"step": 46254
|
| 260 |
},
|
| 261 |
{
|
| 262 |
+
"epoch": 2.0,
|
| 263 |
+
"eval_loss": 0.042018186300992966,
|
| 264 |
+
"eval_max_distance": 44,
|
| 265 |
"eval_mean_distance": 0,
|
| 266 |
+
"eval_runtime": 15.8905,
|
| 267 |
+
"eval_samples_per_second": 15.733,
|
| 268 |
+
"eval_steps_per_second": 1.07,
|
| 269 |
+
"step": 47402
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 2.0,
|
| 273 |
+
"learning_rate": 8.887107435691884e-05,
|
| 274 |
+
"loss": 0.0132,
|
| 275 |
+
"step": 47440
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 2.05,
|
| 279 |
+
"learning_rate": 8.831507343806403e-05,
|
| 280 |
+
"loss": 0.0107,
|
| 281 |
+
"step": 48626
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 2.1,
|
| 285 |
+
"learning_rate": 8.775907251920922e-05,
|
| 286 |
+
"loss": 0.0108,
|
| 287 |
+
"step": 49812
|
| 288 |
},
|
| 289 |
{
|
| 290 |
+
"epoch": 2.15,
|
| 291 |
+
"learning_rate": 8.720307160035443e-05,
|
| 292 |
+
"loss": 0.0115,
|
| 293 |
+
"step": 50998
|
| 294 |
},
|
| 295 |
{
|
| 296 |
+
"epoch": 2.2,
|
| 297 |
+
"learning_rate": 8.66470706814996e-05,
|
| 298 |
+
"loss": 0.0107,
|
| 299 |
+
"step": 52184
|
| 300 |
},
|
| 301 |
{
|
| 302 |
+
"epoch": 2.25,
|
| 303 |
+
"learning_rate": 8.609106976264481e-05,
|
| 304 |
+
"loss": 0.0113,
|
| 305 |
+
"step": 53370
|
| 306 |
},
|
| 307 |
{
|
| 308 |
+
"epoch": 2.3,
|
| 309 |
+
"learning_rate": 8.553506884379e-05,
|
| 310 |
+
"loss": 0.011,
|
| 311 |
+
"step": 54556
|
| 312 |
},
|
| 313 |
{
|
| 314 |
+
"epoch": 2.35,
|
| 315 |
+
"learning_rate": 8.49790679249352e-05,
|
| 316 |
+
"loss": 0.0119,
|
| 317 |
+
"step": 55742
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 2.4,
|
| 321 |
+
"learning_rate": 8.442306700608039e-05,
|
| 322 |
+
"loss": 0.0106,
|
| 323 |
+
"step": 56928
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 2.45,
|
| 327 |
+
"learning_rate": 8.386706608722558e-05,
|
| 328 |
+
"loss": 0.0118,
|
| 329 |
+
"step": 58114
|
|
|
|
|
|
|
|
|
|
|
|
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 2.5,
|
| 333 |
+
"learning_rate": 8.331106516837077e-05,
|
| 334 |
+
"loss": 0.0116,
|
| 335 |
+
"step": 59300
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 2.55,
|
| 339 |
+
"learning_rate": 8.275506424951596e-05,
|
| 340 |
+
"loss": 0.0111,
|
| 341 |
+
"step": 60486
|
| 342 |
},
|
| 343 |
{
|
| 344 |
+
"epoch": 2.6,
|
| 345 |
+
"learning_rate": 8.219906333066115e-05,
|
| 346 |
+
"loss": 0.0112,
|
| 347 |
+
"step": 61672
|
| 348 |
},
|
| 349 |
{
|
| 350 |
+
"epoch": 2.65,
|
| 351 |
+
"learning_rate": 8.164306241180635e-05,
|
| 352 |
+
"loss": 0.0111,
|
| 353 |
+
"step": 62858
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 2.7,
|
| 357 |
+
"learning_rate": 8.108706149295155e-05,
|
| 358 |
+
"loss": 0.0109,
|
| 359 |
+
"step": 64044
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 2.75,
|
| 363 |
+
"learning_rate": 8.053106057409674e-05,
|
| 364 |
+
"loss": 0.0113,
|
| 365 |
+
"step": 65230
|
| 366 |
},
|
| 367 |
{
|
| 368 |
+
"epoch": 2.8,
|
| 369 |
+
"learning_rate": 7.997505965524193e-05,
|
| 370 |
+
"loss": 0.0117,
|
| 371 |
+
"step": 66416
|
| 372 |
},
|
| 373 |
{
|
| 374 |
+
"epoch": 2.85,
|
| 375 |
+
"learning_rate": 7.941905873638713e-05,
|
| 376 |
+
"loss": 0.0108,
|
| 377 |
+
"step": 67602
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 2.9,
|
| 381 |
+
"learning_rate": 7.886305781753232e-05,
|
| 382 |
+
"loss": 0.011,
|
| 383 |
+
"step": 68788
|
| 384 |
},
|
| 385 |
{
|
| 386 |
+
"epoch": 2.95,
|
| 387 |
+
"learning_rate": 7.830705689867751e-05,
|
| 388 |
+
"loss": 0.0111,
|
| 389 |
+
"step": 69974
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 3.0,
|
| 393 |
+
"eval_loss": 0.04441571980714798,
|
| 394 |
+
"eval_max_distance": 35,
|
| 395 |
"eval_mean_distance": 0,
|
| 396 |
+
"eval_runtime": 15.9553,
|
| 397 |
+
"eval_samples_per_second": 15.669,
|
| 398 |
+
"eval_steps_per_second": 1.065,
|
| 399 |
+
"step": 71103
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 3.0,
|
| 403 |
+
"learning_rate": 7.77510559798227e-05,
|
| 404 |
+
"loss": 0.0115,
|
| 405 |
+
"step": 71160
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 3.05,
|
| 409 |
+
"learning_rate": 7.719505506096789e-05,
|
| 410 |
+
"loss": 0.0101,
|
| 411 |
+
"step": 72346
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 3.1,
|
| 415 |
+
"learning_rate": 7.663905414211308e-05,
|
| 416 |
+
"loss": 0.0093,
|
| 417 |
+
"step": 73532
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 3.15,
|
| 421 |
+
"learning_rate": 7.608305322325828e-05,
|
| 422 |
+
"loss": 0.0091,
|
| 423 |
+
"step": 74718
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 3.2,
|
| 427 |
+
"learning_rate": 7.552705230440348e-05,
|
| 428 |
+
"loss": 0.0094,
|
| 429 |
+
"step": 75904
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 3.25,
|
| 433 |
+
"learning_rate": 7.497105138554866e-05,
|
| 434 |
+
"loss": 0.0099,
|
| 435 |
+
"step": 77090
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 3.3,
|
| 439 |
+
"learning_rate": 7.441505046669386e-05,
|
| 440 |
+
"loss": 0.01,
|
| 441 |
+
"step": 78276
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 3.35,
|
| 445 |
+
"learning_rate": 7.385904954783906e-05,
|
| 446 |
+
"loss": 0.0097,
|
| 447 |
+
"step": 79462
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 3.4,
|
| 451 |
+
"learning_rate": 7.330304862898425e-05,
|
| 452 |
+
"loss": 0.0099,
|
| 453 |
+
"step": 80648
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 3.45,
|
| 457 |
+
"learning_rate": 7.274704771012944e-05,
|
| 458 |
+
"loss": 0.0098,
|
| 459 |
+
"step": 81834
|
|
|
|
|
|
|
|
|
|
|
|
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 3.5,
|
| 463 |
+
"learning_rate": 7.219104679127463e-05,
|
| 464 |
+
"loss": 0.0095,
|
| 465 |
+
"step": 83020
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 3.55,
|
| 469 |
+
"learning_rate": 7.163504587241982e-05,
|
| 470 |
+
"loss": 0.0097,
|
| 471 |
+
"step": 84206
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 3.6,
|
| 475 |
+
"learning_rate": 7.107904495356501e-05,
|
| 476 |
+
"loss": 0.0094,
|
| 477 |
+
"step": 85392
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 3.65,
|
| 481 |
+
"learning_rate": 7.052304403471022e-05,
|
| 482 |
+
"loss": 0.0093,
|
| 483 |
+
"step": 86578
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 3.7,
|
| 487 |
+
"learning_rate": 6.99670431158554e-05,
|
| 488 |
+
"loss": 0.0103,
|
| 489 |
+
"step": 87764
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 3.75,
|
| 493 |
+
"learning_rate": 6.94110421970006e-05,
|
| 494 |
+
"loss": 0.0091,
|
| 495 |
+
"step": 88950
|
| 496 |
},
|
| 497 |
{
|
| 498 |
+
"epoch": 3.8,
|
| 499 |
+
"learning_rate": 6.88550412781458e-05,
|
| 500 |
+
"loss": 0.0094,
|
| 501 |
+
"step": 90136
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 3.85,
|
| 505 |
+
"learning_rate": 6.829904035929099e-05,
|
| 506 |
+
"loss": 0.0099,
|
| 507 |
+
"step": 91322
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 3.9,
|
| 511 |
+
"learning_rate": 6.774303944043618e-05,
|
| 512 |
+
"loss": 0.0095,
|
| 513 |
+
"step": 92508
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 3.95,
|
| 517 |
+
"learning_rate": 6.718703852158137e-05,
|
| 518 |
+
"loss": 0.0095,
|
| 519 |
+
"step": 93694
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 4.0,
|
| 523 |
+
"eval_loss": 0.04494529217481613,
|
| 524 |
+
"eval_max_distance": 43,
|
| 525 |
"eval_mean_distance": 0,
|
| 526 |
+
"eval_runtime": 15.8606,
|
| 527 |
+
"eval_samples_per_second": 15.762,
|
| 528 |
+
"eval_steps_per_second": 1.072,
|
| 529 |
+
"step": 94804
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 4.0,
|
| 533 |
+
"learning_rate": 6.663103760272656e-05,
|
| 534 |
+
"loss": 0.0102,
|
| 535 |
+
"step": 94880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 536 |
},
|
| 537 |
{
|
| 538 |
+
"epoch": 4.05,
|
| 539 |
+
"learning_rate": 6.607503668387175e-05,
|
| 540 |
+
"loss": 0.0085,
|
| 541 |
+
"step": 96066
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 4.1,
|
| 545 |
+
"learning_rate": 6.551903576501695e-05,
|
| 546 |
+
"loss": 0.0084,
|
| 547 |
+
"step": 97252
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 4.15,
|
| 551 |
+
"learning_rate": 6.496303484616214e-05,
|
| 552 |
+
"loss": 0.0086,
|
| 553 |
+
"step": 98438
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 4.2,
|
| 557 |
+
"learning_rate": 6.440703392730734e-05,
|
| 558 |
+
"loss": 0.008,
|
| 559 |
+
"step": 99624
|
| 560 |
},
|
| 561 |
{
|
| 562 |
+
"epoch": 4.25,
|
| 563 |
+
"learning_rate": 6.385103300845253e-05,
|
| 564 |
+
"loss": 0.0084,
|
| 565 |
+
"step": 100810
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"epoch": 4.3,
|
| 569 |
+
"learning_rate": 6.329503208959773e-05,
|
| 570 |
+
"loss": 0.0088,
|
| 571 |
+
"step": 101996
|
| 572 |
},
|
| 573 |
{
|
| 574 |
+
"epoch": 4.35,
|
| 575 |
+
"learning_rate": 6.273903117074292e-05,
|
| 576 |
+
"loss": 0.0087,
|
| 577 |
+
"step": 103182
|
| 578 |
},
|
| 579 |
{
|
| 580 |
+
"epoch": 4.4,
|
| 581 |
+
"learning_rate": 6.218303025188811e-05,
|
| 582 |
+
"loss": 0.0086,
|
| 583 |
+
"step": 104368
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 4.45,
|
| 587 |
+
"learning_rate": 6.16270293330333e-05,
|
| 588 |
+
"loss": 0.0087,
|
| 589 |
+
"step": 105554
|
|
|
|
|
|
|
|
|
|
|
|
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 4.5,
|
| 593 |
+
"learning_rate": 6.107102841417849e-05,
|
| 594 |
+
"loss": 0.0086,
|
| 595 |
+
"step": 106740
|
| 596 |
},
|
| 597 |
{
|
| 598 |
+
"epoch": 4.55,
|
| 599 |
+
"learning_rate": 6.0515027495323685e-05,
|
| 600 |
+
"loss": 0.0092,
|
| 601 |
+
"step": 107926
|
| 602 |
},
|
| 603 |
{
|
| 604 |
+
"epoch": 4.6,
|
| 605 |
+
"learning_rate": 5.9959026576468876e-05,
|
| 606 |
+
"loss": 0.0087,
|
| 607 |
+
"step": 109112
|
| 608 |
},
|
| 609 |
{
|
| 610 |
+
"epoch": 4.65,
|
| 611 |
+
"learning_rate": 5.9403025657614075e-05,
|
| 612 |
+
"loss": 0.0091,
|
| 613 |
+
"step": 110298
|
| 614 |
},
|
| 615 |
{
|
| 616 |
+
"epoch": 4.7,
|
| 617 |
+
"learning_rate": 5.884702473875927e-05,
|
| 618 |
+
"loss": 0.0084,
|
| 619 |
+
"step": 111484
|
| 620 |
},
|
| 621 |
{
|
| 622 |
+
"epoch": 4.75,
|
| 623 |
+
"learning_rate": 5.829102381990446e-05,
|
| 624 |
+
"loss": 0.0083,
|
| 625 |
+
"step": 112670
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 4.8,
|
| 629 |
+
"learning_rate": 5.773502290104965e-05,
|
| 630 |
+
"loss": 0.0085,
|
| 631 |
+
"step": 113856
|
| 632 |
},
|
| 633 |
{
|
| 634 |
+
"epoch": 4.85,
|
| 635 |
+
"learning_rate": 5.717902198219485e-05,
|
| 636 |
+
"loss": 0.0092,
|
| 637 |
+
"step": 115042
|
| 638 |
},
|
| 639 |
{
|
| 640 |
+
"epoch": 4.9,
|
| 641 |
+
"learning_rate": 5.662302106334004e-05,
|
| 642 |
+
"loss": 0.0083,
|
| 643 |
+
"step": 116228
|
| 644 |
},
|
| 645 |
{
|
| 646 |
+
"epoch": 4.95,
|
| 647 |
+
"learning_rate": 5.606702014448524e-05,
|
| 648 |
+
"loss": 0.0088,
|
| 649 |
+
"step": 117414
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"epoch": 5.0,
|
| 653 |
+
"eval_loss": 0.0445968434214592,
|
| 654 |
+
"eval_max_distance": 40,
|
| 655 |
"eval_mean_distance": 0,
|
| 656 |
+
"eval_runtime": 15.8709,
|
| 657 |
+
"eval_samples_per_second": 15.752,
|
| 658 |
+
"eval_steps_per_second": 1.071,
|
| 659 |
+
"step": 118505
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 660 |
},
|
| 661 |
{
|
| 662 |
+
"epoch": 5.0,
|
| 663 |
+
"learning_rate": 5.5511019225630424e-05,
|
| 664 |
+
"loss": 0.0084,
|
| 665 |
+
"step": 118600
|
| 666 |
},
|
| 667 |
{
|
| 668 |
+
"epoch": 5.05,
|
| 669 |
+
"learning_rate": 5.4955018306775615e-05,
|
| 670 |
+
"loss": 0.0072,
|
| 671 |
+
"step": 119786
|
| 672 |
},
|
| 673 |
{
|
| 674 |
+
"epoch": 5.1,
|
| 675 |
+
"learning_rate": 5.4399017387920814e-05,
|
| 676 |
+
"loss": 0.0078,
|
| 677 |
+
"step": 120972
|
| 678 |
},
|
| 679 |
{
|
| 680 |
+
"epoch": 5.15,
|
| 681 |
+
"learning_rate": 5.384301646906601e-05,
|
| 682 |
+
"loss": 0.0082,
|
| 683 |
+
"step": 122158
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 5.2,
|
| 687 |
+
"learning_rate": 5.32870155502112e-05,
|
| 688 |
+
"loss": 0.0079,
|
| 689 |
+
"step": 123344
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 5.25,
|
| 693 |
+
"learning_rate": 5.273101463135639e-05,
|
| 694 |
+
"loss": 0.008,
|
| 695 |
+
"step": 124530
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 5.3,
|
| 699 |
+
"learning_rate": 5.217501371250159e-05,
|
| 700 |
+
"loss": 0.008,
|
| 701 |
+
"step": 125716
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 5.35,
|
| 705 |
+
"learning_rate": 5.161901279364678e-05,
|
| 706 |
+
"loss": 0.0081,
|
| 707 |
+
"step": 126902
|
| 708 |
},
|
| 709 |
{
|
| 710 |
+
"epoch": 5.4,
|
| 711 |
+
"learning_rate": 5.1063011874791964e-05,
|
| 712 |
+
"loss": 0.0078,
|
| 713 |
+
"step": 128088
|
| 714 |
},
|
| 715 |
{
|
| 716 |
+
"epoch": 5.45,
|
| 717 |
+
"learning_rate": 5.050701095593716e-05,
|
| 718 |
+
"loss": 0.0076,
|
| 719 |
+
"step": 129274
|
|
|
|
|
|
|
|
|
|
|
|
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"epoch": 5.5,
|
| 723 |
+
"learning_rate": 4.9951010037082354e-05,
|
| 724 |
+
"loss": 0.0079,
|
| 725 |
+
"step": 130460
|
| 726 |
},
|
| 727 |
{
|
| 728 |
+
"epoch": 5.55,
|
| 729 |
+
"learning_rate": 4.9395009118227546e-05,
|
| 730 |
+
"loss": 0.0074,
|
| 731 |
+
"step": 131646
|
| 732 |
},
|
| 733 |
{
|
| 734 |
+
"epoch": 5.6,
|
| 735 |
+
"learning_rate": 4.8839008199372745e-05,
|
| 736 |
+
"loss": 0.0077,
|
| 737 |
+
"step": 132832
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 5.65,
|
| 741 |
+
"learning_rate": 4.8283007280517936e-05,
|
| 742 |
+
"loss": 0.0079,
|
| 743 |
+
"step": 134018
|
| 744 |
},
|
| 745 |
{
|
| 746 |
+
"epoch": 5.7,
|
| 747 |
+
"learning_rate": 4.772700636166313e-05,
|
| 748 |
+
"loss": 0.0077,
|
| 749 |
+
"step": 135204
|
| 750 |
},
|
| 751 |
{
|
| 752 |
+
"epoch": 5.75,
|
| 753 |
+
"learning_rate": 4.7171005442808326e-05,
|
| 754 |
+
"loss": 0.0078,
|
| 755 |
+
"step": 136390
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"epoch": 5.8,
|
| 759 |
+
"learning_rate": 4.661500452395352e-05,
|
| 760 |
+
"loss": 0.0081,
|
| 761 |
+
"step": 137576
|
| 762 |
},
|
| 763 |
{
|
| 764 |
+
"epoch": 5.85,
|
| 765 |
+
"learning_rate": 4.605900360509871e-05,
|
| 766 |
+
"loss": 0.0077,
|
| 767 |
+
"step": 138762
|
| 768 |
},
|
| 769 |
{
|
| 770 |
+
"epoch": 5.9,
|
| 771 |
+
"learning_rate": 4.55030026862439e-05,
|
| 772 |
+
"loss": 0.0075,
|
| 773 |
+
"step": 139948
|
| 774 |
},
|
| 775 |
{
|
| 776 |
+
"epoch": 5.95,
|
| 777 |
+
"learning_rate": 4.494700176738909e-05,
|
| 778 |
+
"loss": 0.0076,
|
| 779 |
+
"step": 141134
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 6.0,
|
| 783 |
+
"eval_loss": 0.046243954449892044,
|
| 784 |
+
"eval_max_distance": 33,
|
| 785 |
"eval_mean_distance": 0,
|
| 786 |
+
"eval_runtime": 15.8654,
|
| 787 |
+
"eval_samples_per_second": 15.758,
|
| 788 |
+
"eval_steps_per_second": 1.072,
|
| 789 |
+
"step": 142206
|
| 790 |
},
|
| 791 |
{
|
| 792 |
+
"epoch": 6.0,
|
| 793 |
+
"learning_rate": 4.4391000848534285e-05,
|
| 794 |
+
"loss": 0.0079,
|
| 795 |
+
"step": 142320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 796 |
},
|
| 797 |
{
|
| 798 |
+
"epoch": 6.05,
|
| 799 |
+
"learning_rate": 4.3834999929679484e-05,
|
| 800 |
+
"loss": 0.0073,
|
| 801 |
+
"step": 143506
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 6.1,
|
| 805 |
+
"learning_rate": 4.3278999010824675e-05,
|
| 806 |
+
"loss": 0.007,
|
| 807 |
+
"step": 144692
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 6.15,
|
| 811 |
+
"learning_rate": 4.272299809196987e-05,
|
| 812 |
+
"loss": 0.0076,
|
| 813 |
+
"step": 145878
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 6.2,
|
| 817 |
+
"learning_rate": 4.216699717311506e-05,
|
| 818 |
+
"loss": 0.0072,
|
| 819 |
+
"step": 147064
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 6.26,
|
| 823 |
+
"learning_rate": 4.161099625426026e-05,
|
| 824 |
+
"loss": 0.007,
|
| 825 |
+
"step": 148250
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 6.31,
|
| 829 |
+
"learning_rate": 4.105499533540544e-05,
|
| 830 |
+
"loss": 0.0073,
|
| 831 |
+
"step": 149436
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 6.36,
|
| 835 |
+
"learning_rate": 4.049899441655064e-05,
|
| 836 |
+
"loss": 0.0073,
|
| 837 |
+
"step": 150622
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 6.41,
|
| 841 |
+
"learning_rate": 3.994299349769583e-05,
|
| 842 |
+
"loss": 0.0072,
|
| 843 |
+
"step": 151808
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 6.46,
|
| 847 |
+
"learning_rate": 3.9386992578841024e-05,
|
| 848 |
+
"loss": 0.0073,
|
| 849 |
+
"step": 152994
|
|
|
|
|
|
|
|
|
|
|
|
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 6.51,
|
| 853 |
+
"learning_rate": 3.883099165998622e-05,
|
| 854 |
+
"loss": 0.007,
|
| 855 |
+
"step": 154180
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 6.56,
|
| 859 |
+
"learning_rate": 3.8274990741131414e-05,
|
| 860 |
+
"loss": 0.0073,
|
| 861 |
+
"step": 155366
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 6.61,
|
| 865 |
+
"learning_rate": 3.7718989822276606e-05,
|
| 866 |
+
"loss": 0.0074,
|
| 867 |
+
"step": 156552
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 6.66,
|
| 871 |
+
"learning_rate": 3.71629889034218e-05,
|
| 872 |
+
"loss": 0.0071,
|
| 873 |
+
"step": 157738
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 6.71,
|
| 877 |
+
"learning_rate": 3.660698798456699e-05,
|
| 878 |
+
"loss": 0.0077,
|
| 879 |
+
"step": 158924
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 6.76,
|
| 883 |
+
"learning_rate": 3.605098706571218e-05,
|
| 884 |
+
"loss": 0.0072,
|
| 885 |
+
"step": 160110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 6.81,
|
| 889 |
+
"learning_rate": 3.549498614685738e-05,
|
| 890 |
+
"loss": 0.0069,
|
| 891 |
+
"step": 161296
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 6.86,
|
| 895 |
+
"learning_rate": 3.493898522800257e-05,
|
| 896 |
+
"loss": 0.0074,
|
| 897 |
+
"step": 162482
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 6.91,
|
| 901 |
+
"learning_rate": 3.438298430914776e-05,
|
| 902 |
+
"loss": 0.0072,
|
| 903 |
+
"step": 163668
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 6.96,
|
| 907 |
+
"learning_rate": 3.3826983390292955e-05,
|
| 908 |
+
"loss": 0.0074,
|
| 909 |
+
"step": 164854
|
| 910 |
},
|
| 911 |
{
|
| 912 |
+
"epoch": 7.0,
|
| 913 |
+
"eval_loss": 0.046568483114242554,
|
| 914 |
+
"eval_max_distance": 38,
|
| 915 |
"eval_mean_distance": 0,
|
| 916 |
+
"eval_runtime": 15.7578,
|
| 917 |
+
"eval_samples_per_second": 15.865,
|
| 918 |
+
"eval_steps_per_second": 1.079,
|
| 919 |
+
"step": 165907
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 7.01,
|
| 923 |
+
"learning_rate": 3.327098247143815e-05,
|
| 924 |
+
"loss": 0.0071,
|
| 925 |
+
"step": 166040
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 7.06,
|
| 929 |
+
"learning_rate": 3.2714981552583345e-05,
|
| 930 |
+
"loss": 0.0065,
|
| 931 |
+
"step": 167226
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 7.11,
|
| 935 |
+
"learning_rate": 3.215898063372854e-05,
|
| 936 |
+
"loss": 0.0066,
|
| 937 |
+
"step": 168412
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 7.16,
|
| 941 |
+
"learning_rate": 3.160297971487373e-05,
|
| 942 |
+
"loss": 0.0067,
|
| 943 |
+
"step": 169598
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 7.21,
|
| 947 |
+
"learning_rate": 3.104697879601892e-05,
|
| 948 |
+
"loss": 0.0067,
|
| 949 |
+
"step": 170784
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 7.26,
|
| 953 |
+
"learning_rate": 3.049097787716412e-05,
|
| 954 |
+
"loss": 0.0066,
|
| 955 |
+
"step": 171970
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 7.31,
|
| 959 |
+
"learning_rate": 2.9934976958309307e-05,
|
| 960 |
+
"loss": 0.0071,
|
| 961 |
+
"step": 173156
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 7.36,
|
| 965 |
+
"learning_rate": 2.9378976039454502e-05,
|
| 966 |
+
"loss": 0.0067,
|
| 967 |
+
"step": 174342
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 7.41,
|
| 971 |
+
"learning_rate": 2.8822975120599694e-05,
|
| 972 |
+
"loss": 0.0064,
|
| 973 |
+
"step": 175528
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 7.46,
|
| 977 |
+
"learning_rate": 2.826697420174489e-05,
|
| 978 |
+
"loss": 0.0064,
|
| 979 |
+
"step": 176714
|
|
|
|
|
|
|
|
|
|
|
|
|
| 980 |
},
|
| 981 |
{
|
| 982 |
+
"epoch": 7.51,
|
| 983 |
+
"learning_rate": 2.771097328289008e-05,
|
| 984 |
+
"loss": 0.0067,
|
| 985 |
+
"step": 177900
|
| 986 |
},
|
| 987 |
{
|
| 988 |
+
"epoch": 7.56,
|
| 989 |
+
"learning_rate": 2.7154972364035276e-05,
|
| 990 |
+
"loss": 0.0068,
|
| 991 |
+
"step": 179086
|
| 992 |
},
|
| 993 |
{
|
| 994 |
+
"epoch": 7.61,
|
| 995 |
+
"learning_rate": 2.6598971445180464e-05,
|
| 996 |
+
"loss": 0.0071,
|
| 997 |
+
"step": 180272
|
| 998 |
},
|
| 999 |
{
|
| 1000 |
+
"epoch": 7.66,
|
| 1001 |
+
"learning_rate": 2.604297052632566e-05,
|
| 1002 |
+
"loss": 0.0065,
|
| 1003 |
+
"step": 181458
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
+
"epoch": 7.71,
|
| 1007 |
+
"learning_rate": 2.548696960747085e-05,
|
| 1008 |
+
"loss": 0.0065,
|
| 1009 |
+
"step": 182644
|
| 1010 |
},
|
| 1011 |
{
|
| 1012 |
+
"epoch": 7.76,
|
| 1013 |
+
"learning_rate": 2.4930968688616046e-05,
|
| 1014 |
+
"loss": 0.007,
|
| 1015 |
+
"step": 183830
|
| 1016 |
},
|
| 1017 |
{
|
| 1018 |
+
"epoch": 7.81,
|
| 1019 |
+
"learning_rate": 2.437496776976124e-05,
|
| 1020 |
+
"loss": 0.007,
|
| 1021 |
+
"step": 185016
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
+
"epoch": 7.86,
|
| 1025 |
+
"learning_rate": 2.3818966850906433e-05,
|
| 1026 |
+
"loss": 0.007,
|
| 1027 |
+
"step": 186202
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 7.91,
|
| 1031 |
+
"learning_rate": 2.3262965932051624e-05,
|
| 1032 |
+
"loss": 0.0069,
|
| 1033 |
+
"step": 187388
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
+
"epoch": 7.96,
|
| 1037 |
+
"learning_rate": 2.270696501319682e-05,
|
| 1038 |
+
"loss": 0.0068,
|
| 1039 |
+
"step": 188574
|
| 1040 |
},
|
| 1041 |
{
|
| 1042 |
+
"epoch": 8.0,
|
| 1043 |
+
"eval_loss": 0.04775545746088028,
|
| 1044 |
+
"eval_max_distance": 39,
|
| 1045 |
"eval_mean_distance": 0,
|
| 1046 |
+
"eval_runtime": 15.8132,
|
| 1047 |
+
"eval_samples_per_second": 15.81,
|
| 1048 |
+
"eval_steps_per_second": 1.075,
|
| 1049 |
+
"step": 189608
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
+
"epoch": 8.01,
|
| 1053 |
+
"learning_rate": 2.215096409434201e-05,
|
| 1054 |
+
"loss": 0.0067,
|
| 1055 |
+
"step": 189760
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 8.06,
|
| 1059 |
+
"learning_rate": 2.1594963175487203e-05,
|
| 1060 |
+
"loss": 0.0062,
|
| 1061 |
+
"step": 190946
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 8.11,
|
| 1065 |
+
"learning_rate": 2.1038962256632398e-05,
|
| 1066 |
+
"loss": 0.0066,
|
| 1067 |
+
"step": 192132
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 8.16,
|
| 1071 |
+
"learning_rate": 2.0482961337777593e-05,
|
| 1072 |
+
"loss": 0.0062,
|
| 1073 |
+
"step": 193318
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 8.21,
|
| 1077 |
+
"learning_rate": 1.9926960418922785e-05,
|
| 1078 |
+
"loss": 0.0064,
|
| 1079 |
+
"step": 194504
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
+
"epoch": 8.26,
|
| 1083 |
+
"learning_rate": 1.9370959500067977e-05,
|
| 1084 |
+
"loss": 0.0062,
|
| 1085 |
+
"step": 195690
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
+
"epoch": 8.31,
|
| 1089 |
+
"learning_rate": 1.8814958581213172e-05,
|
| 1090 |
+
"loss": 0.0063,
|
| 1091 |
+
"step": 196876
|
| 1092 |
},
|
| 1093 |
{
|
| 1094 |
+
"epoch": 8.36,
|
| 1095 |
+
"learning_rate": 1.8258957662358363e-05,
|
| 1096 |
+
"loss": 0.0068,
|
| 1097 |
+
"step": 198062
|
| 1098 |
},
|
| 1099 |
{
|
| 1100 |
+
"epoch": 8.41,
|
| 1101 |
+
"learning_rate": 1.770295674350356e-05,
|
| 1102 |
+
"loss": 0.0064,
|
| 1103 |
+
"step": 199248
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
+
"epoch": 8.46,
|
| 1107 |
+
"learning_rate": 1.714695582464875e-05,
|
| 1108 |
+
"loss": 0.0066,
|
| 1109 |
+
"step": 200434
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
+
"epoch": 8.51,
|
| 1113 |
+
"learning_rate": 1.6590954905793942e-05,
|
| 1114 |
+
"loss": 0.0062,
|
| 1115 |
+
"step": 201620
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
+
"epoch": 8.56,
|
| 1119 |
+
"learning_rate": 1.6034953986939137e-05,
|
| 1120 |
+
"loss": 0.0068,
|
| 1121 |
+
"step": 202806
|
| 1122 |
},
|
| 1123 |
{
|
| 1124 |
+
"epoch": 8.61,
|
| 1125 |
+
"learning_rate": 1.547895306808433e-05,
|
| 1126 |
+
"loss": 0.0065,
|
| 1127 |
+
"step": 203992
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
+
"epoch": 8.66,
|
| 1131 |
+
"learning_rate": 1.4922952149229522e-05,
|
| 1132 |
+
"loss": 0.0062,
|
| 1133 |
+
"step": 205178
|
| 1134 |
},
|
| 1135 |
{
|
| 1136 |
+
"epoch": 8.71,
|
| 1137 |
+
"learning_rate": 1.4366951230374714e-05,
|
| 1138 |
+
"loss": 0.0065,
|
| 1139 |
+
"step": 206364
|
| 1140 |
},
|
| 1141 |
{
|
| 1142 |
+
"epoch": 8.76,
|
| 1143 |
+
"learning_rate": 1.3810950311519907e-05,
|
| 1144 |
+
"loss": 0.0064,
|
| 1145 |
+
"step": 207550
|
| 1146 |
},
|
| 1147 |
{
|
| 1148 |
+
"epoch": 8.81,
|
| 1149 |
+
"learning_rate": 1.32549493926651e-05,
|
| 1150 |
+
"loss": 0.0066,
|
| 1151 |
+
"step": 208736
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
+
"epoch": 8.86,
|
| 1155 |
+
"learning_rate": 1.2698948473810296e-05,
|
| 1156 |
+
"loss": 0.0064,
|
| 1157 |
+
"step": 209922
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
+
"epoch": 8.91,
|
| 1161 |
+
"learning_rate": 1.2142947554955488e-05,
|
| 1162 |
+
"loss": 0.0061,
|
| 1163 |
+
"step": 211108
|
| 1164 |
},
|
| 1165 |
{
|
| 1166 |
+
"epoch": 8.96,
|
| 1167 |
+
"learning_rate": 1.1586946636100681e-05,
|
| 1168 |
+
"loss": 0.0069,
|
| 1169 |
+
"step": 212294
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
+
"epoch": 9.0,
|
| 1173 |
+
"eval_loss": 0.04885172098875046,
|
| 1174 |
+
"eval_max_distance": 39,
|
| 1175 |
"eval_mean_distance": 0,
|
| 1176 |
+
"eval_runtime": 15.685,
|
| 1177 |
+
"eval_samples_per_second": 15.939,
|
| 1178 |
+
"eval_steps_per_second": 1.084,
|
| 1179 |
+
"step": 213309
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
+
"epoch": 9.01,
|
| 1183 |
+
"learning_rate": 1.1030945717245873e-05,
|
| 1184 |
+
"loss": 0.0062,
|
| 1185 |
+
"step": 213480
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 9.06,
|
| 1189 |
+
"learning_rate": 1.0474944798391068e-05,
|
| 1190 |
+
"loss": 0.006,
|
| 1191 |
+
"step": 214666
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
+
"epoch": 9.11,
|
| 1195 |
+
"learning_rate": 9.918943879536261e-06,
|
| 1196 |
+
"loss": 0.0059,
|
| 1197 |
+
"step": 215852
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
+
"epoch": 9.16,
|
| 1201 |
+
"learning_rate": 9.362942960681453e-06,
|
| 1202 |
+
"loss": 0.0059,
|
| 1203 |
+
"step": 217038
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
+
"epoch": 9.21,
|
| 1207 |
+
"learning_rate": 8.806942041826646e-06,
|
| 1208 |
+
"loss": 0.0062,
|
| 1209 |
+
"step": 218224
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
+
"epoch": 9.26,
|
| 1213 |
+
"learning_rate": 8.25094112297184e-06,
|
| 1214 |
+
"loss": 0.006,
|
| 1215 |
+
"step": 219410
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
+
"epoch": 9.31,
|
| 1219 |
+
"learning_rate": 7.694940204117032e-06,
|
| 1220 |
+
"loss": 0.0062,
|
| 1221 |
+
"step": 220596
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
+
"epoch": 9.36,
|
| 1225 |
+
"learning_rate": 7.138939285262225e-06,
|
| 1226 |
+
"loss": 0.0062,
|
| 1227 |
+
"step": 221782
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
+
"epoch": 9.41,
|
| 1231 |
+
"learning_rate": 6.582938366407419e-06,
|
| 1232 |
+
"loss": 0.0064,
|
| 1233 |
+
"step": 222968
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
+
"epoch": 9.46,
|
| 1237 |
+
"learning_rate": 6.026937447552612e-06,
|
| 1238 |
+
"loss": 0.0063,
|
| 1239 |
+
"step": 224154
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
+
"epoch": 9.51,
|
| 1243 |
+
"learning_rate": 5.470936528697805e-06,
|
| 1244 |
+
"loss": 0.0064,
|
| 1245 |
+
"step": 225340
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
+
"epoch": 9.56,
|
| 1249 |
+
"learning_rate": 4.914935609842998e-06,
|
| 1250 |
+
"loss": 0.0057,
|
| 1251 |
+
"step": 226526
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
+
"epoch": 9.61,
|
| 1255 |
+
"learning_rate": 4.358934690988191e-06,
|
| 1256 |
+
"loss": 0.0065,
|
| 1257 |
+
"step": 227712
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
+
"epoch": 9.66,
|
| 1261 |
+
"learning_rate": 3.8029337721333837e-06,
|
| 1262 |
+
"loss": 0.0062,
|
| 1263 |
+
"step": 228898
|
| 1264 |
},
|
| 1265 |
{
|
| 1266 |
+
"epoch": 9.71,
|
| 1267 |
+
"learning_rate": 3.2469328532785775e-06,
|
| 1268 |
+
"loss": 0.006,
|
| 1269 |
+
"step": 230084
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
+
"epoch": 9.76,
|
| 1273 |
+
"learning_rate": 2.69093193442377e-06,
|
| 1274 |
+
"loss": 0.0062,
|
| 1275 |
+
"step": 231270
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
+
"epoch": 9.81,
|
| 1279 |
+
"learning_rate": 2.1349310155689635e-06,
|
| 1280 |
+
"loss": 0.006,
|
| 1281 |
+
"step": 232456
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
+
"epoch": 9.86,
|
| 1285 |
+
"learning_rate": 1.5789300967141565e-06,
|
| 1286 |
+
"loss": 0.0062,
|
| 1287 |
+
"step": 233642
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
+
"epoch": 9.91,
|
| 1291 |
+
"learning_rate": 1.0229291778593495e-06,
|
| 1292 |
+
"loss": 0.0058,
|
| 1293 |
+
"step": 234828
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 9.96,
|
| 1297 |
+
"learning_rate": 4.669282590045427e-07,
|
| 1298 |
+
"loss": 0.0061,
|
| 1299 |
+
"step": 236014
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 10.0,
|
| 1303 |
+
"eval_loss": 0.04803793504834175,
|
| 1304 |
+
"eval_max_distance": 40,
|
| 1305 |
+
"eval_mean_distance": 0,
|
| 1306 |
+
"eval_runtime": 15.7597,
|
| 1307 |
+
"eval_samples_per_second": 15.863,
|
| 1308 |
+
"eval_steps_per_second": 1.079,
|
| 1309 |
+
"step": 237010
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
+
"epoch": 10.0,
|
| 1313 |
+
"step": 237010,
|
| 1314 |
+
"total_flos": 5.639707743740928e+16,
|
| 1315 |
+
"train_loss": 0.010972068954725507,
|
| 1316 |
+
"train_runtime": 17115.447,
|
| 1317 |
+
"train_samples_per_second": 207.713,
|
| 1318 |
+
"train_steps_per_second": 13.848
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1319 |
}
|
| 1320 |
],
|
| 1321 |
+
"logging_steps": 1186,
|
| 1322 |
+
"max_steps": 237010,
|
| 1323 |
+
"num_train_epochs": 10,
|
| 1324 |
+
"save_steps": 2371,
|
| 1325 |
+
"total_flos": 5.639707743740928e+16,
|
| 1326 |
"trial_name": null,
|
| 1327 |
"trial_params": null
|
| 1328 |
}
|
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 sha256:6a3764d1b8a8fe63d5a87771d5f5e5731bd1ffe973ccd8860bfcb988f646825c
|
| 3 |
size 4091
|