End of training
Browse files- README.md +20 -25
- pytorch_model.bin +1 -1
- trainer_state.json +904 -954
- 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 |
|
|
@@ -43,32 +43,27 @@ 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 |
|
| 51 |
-
|
| 52 |
-
| 0.0052 | 1.0 |
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.0043 | 3.0 |
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.0032 | 6.0 |
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.0023 | 10.0 |
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.0014 | 16.0 | 224704 | 0.0407 | 0 | 6 |
|
| 68 |
-
| 0.0014 | 17.0 | 238748 | 0.0427 | 0 | 6 |
|
| 69 |
-
| 0.0014 | 18.0 | 252792 | 0.0411 | 0 | 6 |
|
| 70 |
-
| 0.0013 | 19.0 | 266836 | 0.0406 | 0 | 6 |
|
| 71 |
-
| 0.0013 | 20.0 | 280880 | 0.0405 | 0 | 6 |
|
| 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: 0.0366
|
| 19 |
- Mean Distance: 0
|
| 20 |
+
- Max Distance: 8
|
| 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: 15
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:|
|
| 52 |
+
| 0.0052 | 1.0 | 22916 | 0.0271 | 0 | 9 |
|
| 53 |
+
| 0.0051 | 2.0 | 45832 | 0.0261 | 0 | 8 |
|
| 54 |
+
| 0.0043 | 3.0 | 68748 | 0.0313 | 0 | 8 |
|
| 55 |
+
| 0.0041 | 4.0 | 91664 | 0.0278 | 0 | 10 |
|
| 56 |
+
| 0.0037 | 5.0 | 114580 | 0.0280 | 0 | 8 |
|
| 57 |
+
| 0.0032 | 6.0 | 137496 | 0.0288 | 0 | 8 |
|
| 58 |
+
| 0.003 | 7.0 | 160412 | 0.0308 | 0 | 8 |
|
| 59 |
+
| 0.0025 | 8.0 | 183328 | 0.0305 | 0 | 8 |
|
| 60 |
+
| 0.0025 | 9.0 | 206244 | 0.0303 | 0 | 8 |
|
| 61 |
+
| 0.0023 | 10.0 | 229160 | 0.0341 | 0 | 8 |
|
| 62 |
+
| 0.0022 | 11.0 | 252076 | 0.0329 | 0 | 8 |
|
| 63 |
+
| 0.0019 | 12.0 | 274992 | 0.0336 | 0 | 8 |
|
| 64 |
+
| 0.002 | 13.0 | 297908 | 0.0358 | 0 | 8 |
|
| 65 |
+
| 0.0018 | 14.0 | 320824 | 0.0355 | 0 | 8 |
|
| 66 |
+
| 0.0019 | 15.0 | 343740 | 0.0366 | 0 | 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
|
| 69 |
### 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:f02dda551ed1f056d9fed08e40df3447ff8597cf88883f5f1ca2067d54133a61
|
| 3 |
size 258643461
|
trainer_state.json
CHANGED
|
@@ -1,1428 +1,1378 @@
|
|
| 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.
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss": 0.
|
| 27 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.3,
|
| 31 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"loss": 0.0052,
|
| 33 |
-
"step":
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 0.
|
| 39 |
-
"step":
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 0.
|
| 45 |
-
"step":
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.6,
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
-
"step":
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss": 0.
|
| 57 |
-
"step":
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate":
|
| 62 |
"loss": 0.0051,
|
| 63 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.9,
|
| 67 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
"loss": 0.0052,
|
| 69 |
-
"step":
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 1.0,
|
| 73 |
-
"eval_loss": 0.
|
| 74 |
"eval_max_distance": 9,
|
| 75 |
"eval_mean_distance": 0,
|
| 76 |
-
"eval_runtime":
|
| 77 |
-
"eval_samples_per_second": 17.
|
| 78 |
-
"eval_steps_per_second": 1.
|
| 79 |
-
"step":
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 1.
|
| 83 |
-
"learning_rate":
|
| 84 |
"loss": 0.0045,
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 1.
|
| 89 |
-
"learning_rate":
|
| 90 |
-
"loss": 0.
|
| 91 |
-
"step":
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.2,
|
| 95 |
-
"learning_rate":
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"epoch": 1.
|
| 101 |
-
"learning_rate":
|
| 102 |
"loss": 0.0045,
|
| 103 |
-
"step":
|
| 104 |
},
|
| 105 |
{
|
| 106 |
-
"epoch": 1.
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss": 0.
|
| 109 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.5,
|
| 113 |
-
"learning_rate":
|
| 114 |
-
"loss": 0.
|
| 115 |
-
"step":
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 1.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
-
"step":
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 1.
|
| 125 |
-
"learning_rate":
|
| 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.
|
| 137 |
-
"learning_rate": 9.
|
| 138 |
-
"loss": 0.
|
| 139 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 2.0,
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_max_distance":
|
| 145 |
"eval_mean_distance": 0,
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second": 1.
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 2.
|
| 153 |
-
"learning_rate": 9.
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 2.1,
|
| 159 |
-
"learning_rate": 9.
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 2.
|
| 165 |
-
"learning_rate": 9.
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 2.
|
| 171 |
-
"learning_rate": 9.
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.4,
|
| 177 |
-
"learning_rate": 9.
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 2.
|
| 183 |
-
"learning_rate": 9.
|
| 184 |
-
"loss": 0.
|
| 185 |
-
"step":
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 2.
|
| 189 |
-
"learning_rate": 9.
|
| 190 |
-
"loss": 0.
|
| 191 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 2.7,
|
| 195 |
-
"learning_rate": 9.
|
| 196 |
-
"loss": 0.
|
| 197 |
-
"step":
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch": 2.
|
| 201 |
-
"learning_rate": 9.
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"step":
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch": 2.
|
| 207 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
"loss": 0.0043,
|
| 209 |
-
"step":
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 3.0,
|
| 213 |
-
"eval_loss": 0.
|
| 214 |
-
"eval_max_distance":
|
| 215 |
"eval_mean_distance": 0,
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second": 1.
|
| 219 |
-
"step":
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 3.0,
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch": 3.
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"step":
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 3.
|
| 235 |
-
"learning_rate":
|
| 236 |
"loss": 0.0036,
|
| 237 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 3.3,
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 0.
|
| 243 |
-
"step":
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch": 3.
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 0.
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 3.
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss": 0.
|
| 255 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.6,
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 3.
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss": 0.
|
| 267 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 3.
|
| 271 |
-
"learning_rate": 8.
|
| 272 |
"loss": 0.0039,
|
| 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.
|
| 293 |
-
"learning_rate": 8.
|
| 294 |
-
"loss": 0.
|
| 295 |
-
"step":
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 4.
|
| 299 |
-
"learning_rate": 8.
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"step":
|
| 302 |
},
|
| 303 |
{
|
| 304 |
"epoch": 4.2,
|
| 305 |
-
"learning_rate":
|
| 306 |
-
"loss": 0.
|
| 307 |
-
"step":
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch": 4.
|
| 311 |
-
"learning_rate":
|
| 312 |
"loss": 0.0034,
|
| 313 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch": 4.
|
| 317 |
-
"learning_rate":
|
| 318 |
"loss": 0.0034,
|
| 319 |
-
"step":
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 4.5,
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss": 0.
|
| 325 |
-
"step":
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch": 4.
|
| 329 |
-
"learning_rate":
|
| 330 |
"loss": 0.0035,
|
| 331 |
-
"step":
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 4.
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"loss": 0.
|
| 337 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 4.8,
|
| 341 |
-
"learning_rate":
|
| 342 |
-
"loss": 0.
|
| 343 |
-
"step":
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch": 4.
|
| 347 |
-
"learning_rate":
|
| 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.
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"loss": 0.
|
| 365 |
-
"step":
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.1,
|
| 369 |
-
"learning_rate":
|
| 370 |
-
"loss": 0.
|
| 371 |
-
"step":
|
| 372 |
},
|
| 373 |
{
|
| 374 |
-
"epoch": 5.
|
| 375 |
-
"learning_rate":
|
| 376 |
-
"loss": 0.
|
| 377 |
-
"step":
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 5.
|
| 381 |
-
"learning_rate":
|
| 382 |
-
"loss": 0.
|
| 383 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"epoch": 5.4,
|
| 387 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 388 |
"loss": 0.0031,
|
| 389 |
-
"step":
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch": 5.
|
| 393 |
-
"learning_rate":
|
| 394 |
"loss": 0.0032,
|
| 395 |
-
"step":
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch": 5.
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"step":
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 5.7,
|
| 405 |
-
"learning_rate":
|
| 406 |
"loss": 0.0032,
|
| 407 |
-
"step":
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch": 5.
|
| 411 |
-
"learning_rate":
|
| 412 |
"loss": 0.0031,
|
| 413 |
-
"step":
|
| 414 |
},
|
| 415 |
{
|
| 416 |
-
"epoch": 5.
|
| 417 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 418 |
"loss": 0.0032,
|
| 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":
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch": 6.
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss": 0.
|
| 441 |
-
"step":
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 6.
|
| 445 |
-
"learning_rate":
|
| 446 |
"loss": 0.0026,
|
| 447 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.3,
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
-
"step":
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 6.
|
| 457 |
-
"learning_rate":
|
| 458 |
"loss": 0.0029,
|
| 459 |
-
"step":
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 6.
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 0.
|
| 465 |
-
"step":
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 6.
|
| 469 |
-
"learning_rate":
|
| 470 |
"loss": 0.0028,
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 6.
|
| 475 |
-
"learning_rate":
|
| 476 |
-
"loss": 0.
|
| 477 |
-
"step":
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch": 6.
|
| 481 |
-
"learning_rate":
|
| 482 |
-
"loss": 0.
|
| 483 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 6.9,
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 0.
|
| 489 |
-
"step":
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
-
"
|
| 494 |
-
"
|
| 495 |
-
"
|
| 496 |
-
"eval_runtime": 12.1827,
|
| 497 |
-
"eval_samples_per_second": 20.521,
|
| 498 |
-
"eval_steps_per_second": 1.395,
|
| 499 |
-
"step": 98308
|
| 500 |
},
|
| 501 |
{
|
| 502 |
"epoch": 7.0,
|
| 503 |
-
"
|
| 504 |
-
"
|
| 505 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch": 7.
|
| 509 |
-
"learning_rate":
|
| 510 |
"loss": 0.0027,
|
| 511 |
-
"step":
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch": 7.
|
| 515 |
-
"learning_rate":
|
| 516 |
"loss": 0.0025,
|
| 517 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 7.
|
| 521 |
-
"learning_rate":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 522 |
"loss": 0.0025,
|
| 523 |
-
"step":
|
| 524 |
},
|
| 525 |
{
|
| 526 |
-
"epoch": 7.
|
| 527 |
-
"learning_rate":
|
| 528 |
-
"loss": 0.
|
| 529 |
-
"step":
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 7.5,
|
| 533 |
-
"learning_rate":
|
| 534 |
"loss": 0.0026,
|
| 535 |
-
"step":
|
| 536 |
},
|
| 537 |
{
|
| 538 |
-
"epoch": 7.
|
| 539 |
-
"learning_rate":
|
| 540 |
"loss": 0.0026,
|
| 541 |
-
"step":
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 7.
|
| 545 |
-
"learning_rate":
|
| 546 |
"loss": 0.0026,
|
| 547 |
-
"step":
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch": 7.
|
| 551 |
-
"learning_rate":
|
| 552 |
"loss": 0.0025,
|
| 553 |
-
"step":
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch": 7.
|
| 557 |
-
"learning_rate":
|
| 558 |
"loss": 0.0027,
|
| 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.
|
| 573 |
-
"learning_rate":
|
| 574 |
-
"loss": 0.
|
| 575 |
-
"step":
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 8.1,
|
| 579 |
-
"learning_rate":
|
| 580 |
"loss": 0.0023,
|
| 581 |
-
"step":
|
| 582 |
},
|
| 583 |
{
|
| 584 |
-
"epoch": 8.
|
| 585 |
-
"learning_rate":
|
| 586 |
-
"loss": 0.
|
| 587 |
-
"step":
|
| 588 |
},
|
| 589 |
{
|
| 590 |
-
"epoch": 8.
|
| 591 |
-
"learning_rate":
|
| 592 |
-
"loss": 0.
|
| 593 |
-
"step":
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch": 8.
|
| 597 |
-
"learning_rate":
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"step":
|
| 600 |
},
|
| 601 |
{
|
| 602 |
-
"epoch": 8.
|
| 603 |
-
"learning_rate":
|
| 604 |
"loss": 0.0024,
|
| 605 |
-
"step":
|
| 606 |
},
|
| 607 |
{
|
| 608 |
-
"epoch": 8.
|
| 609 |
-
"learning_rate":
|
| 610 |
"loss": 0.0025,
|
| 611 |
-
"step":
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 8.
|
| 615 |
-
"learning_rate":
|
| 616 |
"loss": 0.0024,
|
| 617 |
-
"step":
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch": 8.
|
| 621 |
-
"learning_rate":
|
| 622 |
-
"loss": 0.
|
| 623 |
-
"step":
|
| 624 |
},
|
| 625 |
{
|
| 626 |
-
"epoch": 8.
|
| 627 |
-
"learning_rate":
|
| 628 |
"loss": 0.0023,
|
| 629 |
-
"step":
|
| 630 |
},
|
| 631 |
{
|
| 632 |
-
"epoch":
|
| 633 |
-
"
|
| 634 |
-
"
|
| 635 |
-
"
|
| 636 |
-
"eval_runtime": 12.3201,
|
| 637 |
-
"eval_samples_per_second": 20.292,
|
| 638 |
-
"eval_steps_per_second": 1.38,
|
| 639 |
-
"step": 126396
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"learning_rate":
|
| 644 |
"loss": 0.0024,
|
| 645 |
-
"step":
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
-
"learning_rate":
|
| 650 |
-
"loss": 0.
|
| 651 |
-
"step":
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch": 9.
|
| 655 |
-
"
|
| 656 |
-
"
|
| 657 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 658 |
},
|
| 659 |
{
|
| 660 |
-
"epoch": 9.
|
| 661 |
-
"learning_rate":
|
| 662 |
-
"loss": 0.
|
| 663 |
-
"step":
|
| 664 |
},
|
| 665 |
{
|
| 666 |
-
"epoch": 9.
|
| 667 |
-
"learning_rate":
|
| 668 |
-
"loss": 0.
|
| 669 |
-
"step":
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch": 9.
|
| 673 |
-
"learning_rate":
|
| 674 |
"loss": 0.0022,
|
| 675 |
-
"step":
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 9.6,
|
| 679 |
-
"learning_rate": 5.775499224659009e-05,
|
| 680 |
-
"loss": 0.0021,
|
| 681 |
-
"step": 134880
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 9.
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"loss": 0.
|
| 687 |
-
"step":
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch": 9.
|
| 691 |
-
"learning_rate":
|
| 692 |
-
"loss": 0.
|
| 693 |
-
"step":
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch": 9.
|
| 697 |
-
"learning_rate":
|
| 698 |
"loss": 0.0023,
|
| 699 |
-
"step":
|
| 700 |
},
|
| 701 |
{
|
| 702 |
-
"epoch":
|
| 703 |
-
"
|
| 704 |
-
"
|
| 705 |
-
"
|
| 706 |
-
"eval_runtime": 12.131,
|
| 707 |
-
"eval_samples_per_second": 20.608,
|
| 708 |
-
"eval_steps_per_second": 1.401,
|
| 709 |
-
"step": 140440
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch":
|
| 713 |
-
"learning_rate":
|
| 714 |
"loss": 0.0023,
|
| 715 |
-
"step":
|
| 716 |
},
|
| 717 |
{
|
| 718 |
-
"epoch":
|
| 719 |
-
"learning_rate":
|
| 720 |
-
"loss": 0.
|
| 721 |
-
"step":
|
| 722 |
},
|
| 723 |
{
|
| 724 |
-
"epoch":
|
| 725 |
-
"learning_rate":
|
| 726 |
-
"loss": 0.
|
| 727 |
-
"step":
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"epoch":
|
| 731 |
-
"learning_rate":
|
| 732 |
-
"loss": 0.
|
| 733 |
-
"step":
|
| 734 |
},
|
| 735 |
{
|
| 736 |
-
"epoch":
|
| 737 |
-
"learning_rate":
|
| 738 |
-
"loss": 0.
|
| 739 |
-
"step":
|
| 740 |
},
|
| 741 |
{
|
| 742 |
-
"epoch":
|
| 743 |
-
"learning_rate":
|
| 744 |
-
"loss": 0.
|
| 745 |
-
"step":
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch":
|
| 749 |
-
"learning_rate":
|
| 750 |
-
"loss": 0.
|
| 751 |
-
"step":
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 10.
|
| 755 |
-
"
|
| 756 |
-
"
|
| 757 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 758 |
},
|
| 759 |
{
|
| 760 |
-
"epoch": 10.
|
| 761 |
-
"learning_rate":
|
| 762 |
-
"loss": 0.
|
| 763 |
-
"step":
|
| 764 |
},
|
| 765 |
{
|
| 766 |
-
"epoch": 10.
|
| 767 |
-
"learning_rate":
|
| 768 |
-
"loss": 0.
|
| 769 |
-
"step":
|
| 770 |
},
|
| 771 |
{
|
| 772 |
-
"epoch":
|
| 773 |
-
"
|
| 774 |
-
"
|
| 775 |
-
"
|
| 776 |
-
"eval_runtime": 12.2718,
|
| 777 |
-
"eval_samples_per_second": 20.372,
|
| 778 |
-
"eval_steps_per_second": 1.385,
|
| 779 |
-
"step": 154484
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch":
|
| 783 |
-
"learning_rate":
|
| 784 |
-
"loss": 0.
|
| 785 |
-
"step":
|
| 786 |
},
|
| 787 |
{
|
| 788 |
-
"epoch":
|
| 789 |
-
"learning_rate":
|
| 790 |
-
"loss": 0.
|
| 791 |
-
"step":
|
| 792 |
},
|
| 793 |
{
|
| 794 |
-
"epoch":
|
| 795 |
-
"learning_rate":
|
| 796 |
-
"loss": 0.
|
| 797 |
-
"step":
|
| 798 |
},
|
| 799 |
{
|
| 800 |
-
"epoch":
|
| 801 |
-
"learning_rate":
|
| 802 |
-
"loss": 0.
|
| 803 |
-
"step":
|
| 804 |
},
|
| 805 |
{
|
| 806 |
-
"epoch":
|
| 807 |
-
"learning_rate":
|
| 808 |
-
"loss": 0.
|
| 809 |
-
"step":
|
| 810 |
},
|
| 811 |
{
|
| 812 |
-
"epoch":
|
| 813 |
-
"learning_rate":
|
| 814 |
-
"loss": 0.
|
| 815 |
-
"step":
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch":
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
-
"step":
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch":
|
| 825 |
-
"learning_rate":
|
| 826 |
-
"loss": 0.
|
| 827 |
-
"step":
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch":
|
| 831 |
-
"learning_rate":
|
| 832 |
"loss": 0.002,
|
| 833 |
-
"step":
|
| 834 |
},
|
| 835 |
{
|
| 836 |
-
"epoch":
|
| 837 |
-
"learning_rate":
|
| 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": 12.01,
|
| 853 |
-
"learning_rate": 4.4415962530459824e-05,
|
| 854 |
-
"loss": 0.0017,
|
| 855 |
-
"step": 168600
|
| 856 |
-
},
|
| 857 |
-
{
|
| 858 |
-
"epoch": 12.11,
|
| 859 |
-
"learning_rate": 4.386016962562107e-05,
|
| 860 |
-
"loss": 0.0016,
|
| 861 |
-
"step": 170005
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"epoch": 12.21,
|
| 865 |
-
"learning_rate": 4.33043767207823e-05,
|
| 866 |
-
"loss": 0.0018,
|
| 867 |
-
"step": 171410
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"learning_rate":
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 12.41,
|
| 877 |
-
"learning_rate": 4.219279091110478e-05,
|
| 878 |
-
"loss": 0.0018,
|
| 879 |
-
"step": 174220
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 12.51,
|
| 883 |
-
"learning_rate": 4.163699800626602e-05,
|
| 884 |
-
"loss": 0.0018,
|
| 885 |
-
"step": 175625
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 12.61,
|
| 889 |
-
"learning_rate": 4.108120510142726e-05,
|
| 890 |
-
"loss": 0.0018,
|
| 891 |
-
"step": 177030
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 12.71,
|
| 895 |
-
"learning_rate": 4.05254121965885e-05,
|
| 896 |
-
"loss": 0.0016,
|
| 897 |
-
"step": 178435
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate":
|
| 902 |
"loss": 0.002,
|
| 903 |
-
"step":
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"learning_rate":
|
| 908 |
-
"loss": 0.
|
| 909 |
-
"step":
|
| 910 |
-
},
|
| 911 |
-
{
|
| 912 |
-
"epoch": 13.0,
|
| 913 |
-
"eval_loss": 0.042234089225530624,
|
| 914 |
-
"eval_max_distance": 6,
|
| 915 |
-
"eval_mean_distance": 0,
|
| 916 |
-
"eval_runtime": 13.9619,
|
| 917 |
-
"eval_samples_per_second": 17.906,
|
| 918 |
-
"eval_steps_per_second": 1.218,
|
| 919 |
-
"step": 182572
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch":
|
| 923 |
-
"learning_rate":
|
| 924 |
-
"loss": 0.
|
| 925 |
-
"step":
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch":
|
| 929 |
-
"learning_rate":
|
| 930 |
-
"loss": 0.
|
| 931 |
-
"step":
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch":
|
| 935 |
-
"learning_rate":
|
| 936 |
-
"loss": 0.
|
| 937 |
-
"step":
|
| 938 |
},
|
| 939 |
{
|
| 940 |
-
"epoch":
|
| 941 |
-
"learning_rate":
|
| 942 |
-
"loss": 0.
|
| 943 |
-
"step":
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch":
|
| 947 |
-
"learning_rate":
|
| 948 |
-
"loss": 0.
|
| 949 |
-
"step":
|
| 950 |
},
|
| 951 |
{
|
| 952 |
-
"epoch":
|
| 953 |
-
"learning_rate":
|
| 954 |
-
"loss": 0.
|
| 955 |
-
"step":
|
| 956 |
},
|
| 957 |
{
|
| 958 |
-
"epoch":
|
| 959 |
-
"learning_rate":
|
| 960 |
-
"loss": 0.
|
| 961 |
-
"step":
|
| 962 |
},
|
| 963 |
{
|
| 964 |
-
"epoch":
|
| 965 |
-
"learning_rate":
|
| 966 |
-
"loss": 0.
|
| 967 |
-
"step":
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch":
|
| 971 |
-
"learning_rate":
|
| 972 |
-
"loss": 0.
|
| 973 |
-
"step":
|
| 974 |
},
|
| 975 |
{
|
| 976 |
-
"epoch":
|
| 977 |
-
"learning_rate":
|
| 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": 3.330010443368462e-05,
|
| 994 |
-
"loss": 0.0016,
|
| 995 |
-
"step": 196700
|
| 996 |
},
|
| 997 |
{
|
| 998 |
-
"epoch":
|
| 999 |
-
"learning_rate":
|
| 1000 |
-
"loss": 0.
|
| 1001 |
-
"step":
|
| 1002 |
-
},
|
| 1003 |
-
{
|
| 1004 |
-
"epoch": 14.21,
|
| 1005 |
-
"learning_rate": 3.218851862400709e-05,
|
| 1006 |
-
"loss": 0.0015,
|
| 1007 |
-
"step": 199510
|
| 1008 |
-
},
|
| 1009 |
-
{
|
| 1010 |
-
"epoch": 14.31,
|
| 1011 |
-
"learning_rate": 3.163272571916833e-05,
|
| 1012 |
-
"loss": 0.0016,
|
| 1013 |
-
"step": 200915
|
| 1014 |
-
},
|
| 1015 |
-
{
|
| 1016 |
-
"epoch": 14.41,
|
| 1017 |
-
"learning_rate": 3.107693281432957e-05,
|
| 1018 |
-
"loss": 0.0016,
|
| 1019 |
-
"step": 202320
|
| 1020 |
-
},
|
| 1021 |
-
{
|
| 1022 |
-
"epoch": 14.51,
|
| 1023 |
-
"learning_rate": 3.052113990949081e-05,
|
| 1024 |
-
"loss": 0.0016,
|
| 1025 |
-
"step": 203725
|
| 1026 |
-
},
|
| 1027 |
-
{
|
| 1028 |
-
"epoch": 14.61,
|
| 1029 |
-
"learning_rate": 2.9965347004652052e-05,
|
| 1030 |
-
"loss": 0.0016,
|
| 1031 |
-
"step": 205130
|
| 1032 |
-
},
|
| 1033 |
-
{
|
| 1034 |
-
"epoch": 14.71,
|
| 1035 |
-
"learning_rate": 2.9409554099813286e-05,
|
| 1036 |
-
"loss": 0.0015,
|
| 1037 |
-
"step": 206535
|
| 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": 12.1736,
|
| 1057 |
-
"eval_samples_per_second": 20.536,
|
| 1058 |
-
"eval_steps_per_second": 1.396,
|
| 1059 |
-
"step": 210660
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
-
"epoch":
|
| 1063 |
-
"learning_rate":
|
| 1064 |
-
"loss": 0.
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch":
|
| 1069 |
-
"learning_rate":
|
| 1070 |
-
"loss": 0.
|
| 1071 |
-
"step":
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch":
|
| 1075 |
-
"learning_rate":
|
| 1076 |
-
"loss": 0.
|
| 1077 |
-
"step":
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch":
|
| 1081 |
-
"learning_rate":
|
| 1082 |
-
"loss": 0.
|
| 1083 |
-
"step":
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch":
|
| 1087 |
-
"learning_rate":
|
| 1088 |
-
"loss": 0.
|
| 1089 |
-
"step":
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
-
"epoch":
|
| 1093 |
-
"learning_rate":
|
| 1094 |
-
"loss": 0.
|
| 1095 |
-
"step":
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
-
"epoch":
|
| 1099 |
-
"learning_rate":
|
| 1100 |
-
"loss": 0.
|
| 1101 |
-
"step":
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
-
"epoch":
|
| 1105 |
-
"learning_rate":
|
| 1106 |
-
"loss": 0.
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch":
|
| 1111 |
-
"learning_rate":
|
| 1112 |
-
"loss": 0.
|
| 1113 |
-
"step":
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch":
|
| 1117 |
-
"learning_rate":
|
| 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": 2.2184246336909397e-05,
|
| 1134 |
-
"loss": 0.0015,
|
| 1135 |
-
"step": 224800
|
| 1136 |
-
},
|
| 1137 |
-
{
|
| 1138 |
-
"epoch": 16.11,
|
| 1139 |
-
"learning_rate": 2.1628453432070635e-05,
|
| 1140 |
-
"loss": 0.0013,
|
| 1141 |
-
"step": 226205
|
| 1142 |
-
},
|
| 1143 |
-
{
|
| 1144 |
-
"epoch": 16.21,
|
| 1145 |
-
"learning_rate": 2.1072660527231873e-05,
|
| 1146 |
-
"loss": 0.0014,
|
| 1147 |
-
"step": 227610
|
| 1148 |
-
},
|
| 1149 |
-
{
|
| 1150 |
-
"epoch": 16.31,
|
| 1151 |
-
"learning_rate": 2.0516867622393114e-05,
|
| 1152 |
-
"loss": 0.0014,
|
| 1153 |
-
"step": 229015
|
| 1154 |
-
},
|
| 1155 |
-
{
|
| 1156 |
-
"epoch": 16.41,
|
| 1157 |
-
"learning_rate": 1.9961074717554352e-05,
|
| 1158 |
-
"loss": 0.0015,
|
| 1159 |
-
"step": 230420
|
| 1160 |
},
|
| 1161 |
{
|
| 1162 |
-
"epoch":
|
| 1163 |
-
"learning_rate": 1.
|
| 1164 |
-
"loss": 0.
|
| 1165 |
-
"step":
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 16.61,
|
| 1169 |
-
"learning_rate": 1.8849488907876832e-05,
|
| 1170 |
-
"loss": 0.0015,
|
| 1171 |
-
"step": 233230
|
| 1172 |
-
},
|
| 1173 |
-
{
|
| 1174 |
-
"epoch": 16.71,
|
| 1175 |
-
"learning_rate": 1.8293696003038073e-05,
|
| 1176 |
-
"loss": 0.0014,
|
| 1177 |
-
"step": 234635
|
| 1178 |
-
},
|
| 1179 |
-
{
|
| 1180 |
-
"epoch": 16.81,
|
| 1181 |
-
"learning_rate": 1.773790309819931e-05,
|
| 1182 |
-
"loss": 0.0013,
|
| 1183 |
-
"step": 236040
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
-
"epoch":
|
| 1187 |
-
"learning_rate": 1.
|
| 1188 |
-
"loss": 0.
|
| 1189 |
-
"step":
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
-
"epoch":
|
| 1193 |
-
"
|
| 1194 |
-
"
|
| 1195 |
-
"
|
| 1196 |
-
"eval_runtime": 12.1336,
|
| 1197 |
-
"eval_samples_per_second": 20.604,
|
| 1198 |
-
"eval_steps_per_second": 1.401,
|
| 1199 |
-
"step": 238748
|
| 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":
|
| 1234 |
-
"loss": 0.
|
| 1235 |
-
"step":
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
-
"epoch":
|
| 1239 |
-
"learning_rate":
|
| 1240 |
-
"loss": 0.
|
| 1241 |
-
"step":
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
-
"epoch":
|
| 1245 |
-
"learning_rate":
|
| 1246 |
-
"loss": 0.
|
| 1247 |
-
"step":
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
-
"epoch":
|
| 1251 |
-
"learning_rate":
|
| 1252 |
-
"loss": 0.
|
| 1253 |
-
"step":
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
-
"epoch":
|
| 1257 |
-
"learning_rate":
|
| 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": 18.01,
|
| 1273 |
-
"learning_rate": 1.1068388240134182e-05,
|
| 1274 |
-
"loss": 0.0014,
|
| 1275 |
-
"step": 252900
|
| 1276 |
-
},
|
| 1277 |
-
{
|
| 1278 |
-
"epoch": 18.11,
|
| 1279 |
-
"learning_rate": 1.051259533529542e-05,
|
| 1280 |
-
"loss": 0.0014,
|
| 1281 |
-
"step": 254305
|
| 1282 |
-
},
|
| 1283 |
-
{
|
| 1284 |
-
"epoch": 18.21,
|
| 1285 |
-
"learning_rate": 9.95680243045666e-06,
|
| 1286 |
-
"loss": 0.0012,
|
| 1287 |
-
"step": 255710
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
-
"epoch":
|
| 1291 |
-
"learning_rate":
|
| 1292 |
-
"loss": 0.
|
| 1293 |
-
"step":
|
| 1294 |
-
},
|
| 1295 |
-
{
|
| 1296 |
-
"epoch": 18.41,
|
| 1297 |
-
"learning_rate": 8.84521662077914e-06,
|
| 1298 |
-
"loss": 0.0014,
|
| 1299 |
-
"step": 258520
|
| 1300 |
-
},
|
| 1301 |
-
{
|
| 1302 |
-
"epoch": 18.51,
|
| 1303 |
-
"learning_rate": 8.289423715940379e-06,
|
| 1304 |
-
"loss": 0.0012,
|
| 1305 |
-
"step": 259925
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 18.61,
|
| 1309 |
-
"learning_rate": 7.733630811101619e-06,
|
| 1310 |
-
"loss": 0.0013,
|
| 1311 |
-
"step": 261330
|
| 1312 |
-
},
|
| 1313 |
-
{
|
| 1314 |
-
"epoch": 18.71,
|
| 1315 |
-
"learning_rate": 7.1778379062628565e-06,
|
| 1316 |
-
"loss": 0.0014,
|
| 1317 |
-
"step": 262735
|
| 1318 |
},
|
| 1319 |
{
|
| 1320 |
-
"epoch":
|
| 1321 |
-
"learning_rate": 6.
|
| 1322 |
-
"loss": 0.
|
| 1323 |
-
"step":
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
-
"epoch": 18
|
| 1327 |
-
"learning_rate": 6.
|
| 1328 |
-
"loss": 0.
|
| 1329 |
-
"step":
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
-
"epoch":
|
| 1333 |
-
"
|
| 1334 |
-
"
|
| 1335 |
-
"
|
| 1336 |
-
"eval_runtime": 12.0757,
|
| 1337 |
-
"eval_samples_per_second": 20.703,
|
| 1338 |
-
"eval_steps_per_second": 1.408,
|
| 1339 |
-
"step": 266836
|
| 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": 280880
|
| 1410 |
-
},
|
| 1411 |
-
{
|
| 1412 |
-
"epoch": 20.0,
|
| 1413 |
-
"step": 280880,
|
| 1414 |
-
"total_flos": 7.269950341627085e+16,
|
| 1415 |
-
"train_loss": 0.0021448437322240947,
|
| 1416 |
-
"train_runtime": 20054.4611,
|
| 1417 |
-
"train_samples_per_second": 210.084,
|
| 1418 |
-
"train_steps_per_second": 14.006
|
| 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": 15.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 343740,
|
| 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": 2.909175539652063e-09,
|
| 14 |
+
"loss": 0.0085,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 5.000872752661896e-06,
|
| 20 |
+
"loss": 0.0066,
|
| 21 |
+
"step": 1719
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 1.0001745505323792e-05,
|
| 26 |
+
"loss": 0.0061,
|
| 27 |
+
"step": 3438
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 1.5002618257985687e-05,
|
| 32 |
+
"loss": 0.0059,
|
| 33 |
+
"step": 5157
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.3,
|
| 37 |
+
"learning_rate": 2.0003491010647585e-05,
|
| 38 |
+
"loss": 0.0056,
|
| 39 |
+
"step": 6876
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.38,
|
| 43 |
+
"learning_rate": 2.500436376330948e-05,
|
| 44 |
"loss": 0.0052,
|
| 45 |
+
"step": 8595
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.45,
|
| 49 |
+
"learning_rate": 3.0005236515971374e-05,
|
| 50 |
+
"loss": 0.0052,
|
| 51 |
+
"step": 10314
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.53,
|
| 55 |
+
"learning_rate": 3.500610926863327e-05,
|
| 56 |
+
"loss": 0.0049,
|
| 57 |
+
"step": 12033
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.6,
|
| 61 |
+
"learning_rate": 4.000698202129517e-05,
|
| 62 |
+
"loss": 0.0049,
|
| 63 |
+
"step": 13752
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.68,
|
| 67 |
+
"learning_rate": 4.5007854773957064e-05,
|
| 68 |
+
"loss": 0.0052,
|
| 69 |
+
"step": 15471
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.75,
|
| 73 |
+
"learning_rate": 5.000872752661896e-05,
|
| 74 |
"loss": 0.0051,
|
| 75 |
+
"step": 17190
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.83,
|
| 79 |
+
"learning_rate": 5.500960027928086e-05,
|
| 80 |
+
"loss": 0.0052,
|
| 81 |
+
"step": 18909
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.9,
|
| 85 |
+
"learning_rate": 6.001047303194275e-05,
|
| 86 |
+
"loss": 0.0048,
|
| 87 |
+
"step": 20628
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.98,
|
| 91 |
+
"learning_rate": 6.501134578460465e-05,
|
| 92 |
"loss": 0.0052,
|
| 93 |
+
"step": 22347
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 1.0,
|
| 97 |
+
"eval_loss": 0.027106985449790955,
|
| 98 |
"eval_max_distance": 9,
|
| 99 |
"eval_mean_distance": 0,
|
| 100 |
+
"eval_runtime": 14.4629,
|
| 101 |
+
"eval_samples_per_second": 17.355,
|
| 102 |
+
"eval_steps_per_second": 1.175,
|
| 103 |
+
"step": 22916
|
| 104 |
},
|
| 105 |
{
|
| 106 |
+
"epoch": 1.05,
|
| 107 |
+
"learning_rate": 7.001221853726654e-05,
|
| 108 |
"loss": 0.0045,
|
| 109 |
+
"step": 24066
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 1.13,
|
| 113 |
+
"learning_rate": 7.501309128992844e-05,
|
| 114 |
+
"loss": 0.0044,
|
| 115 |
+
"step": 25785
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 1.2,
|
| 119 |
+
"learning_rate": 8.001396404259034e-05,
|
| 120 |
+
"loss": 0.0048,
|
| 121 |
+
"step": 27504
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 1.28,
|
| 125 |
+
"learning_rate": 8.501483679525223e-05,
|
| 126 |
"loss": 0.0045,
|
| 127 |
+
"step": 29223
|
| 128 |
},
|
| 129 |
{
|
| 130 |
+
"epoch": 1.35,
|
| 131 |
+
"learning_rate": 9.001570954791413e-05,
|
| 132 |
+
"loss": 0.0044,
|
| 133 |
+
"step": 30942
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.43,
|
| 137 |
+
"learning_rate": 9.501658230057602e-05,
|
| 138 |
+
"loss": 0.0047,
|
| 139 |
+
"step": 32661
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 1.5,
|
| 143 |
+
"learning_rate": 9.999806054964024e-05,
|
| 144 |
+
"loss": 0.005,
|
| 145 |
+
"step": 34380
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 1.58,
|
| 149 |
+
"learning_rate": 9.944240802156669e-05,
|
| 150 |
+
"loss": 0.0049,
|
| 151 |
+
"step": 36099
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.65,
|
| 155 |
+
"learning_rate": 9.888675549349314e-05,
|
| 156 |
+
"loss": 0.0053,
|
| 157 |
+
"step": 37818
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.73,
|
| 161 |
+
"learning_rate": 9.83311029654196e-05,
|
| 162 |
+
"loss": 0.0047,
|
| 163 |
+
"step": 39537
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 1.8,
|
| 167 |
+
"learning_rate": 9.777545043734606e-05,
|
| 168 |
+
"loss": 0.005,
|
| 169 |
+
"step": 41256
|
| 170 |
},
|
| 171 |
{
|
| 172 |
+
"epoch": 1.88,
|
| 173 |
+
"learning_rate": 9.721979790927251e-05,
|
| 174 |
+
"loss": 0.0048,
|
| 175 |
+
"step": 42975
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.95,
|
| 179 |
+
"learning_rate": 9.666414538119898e-05,
|
| 180 |
+
"loss": 0.0051,
|
| 181 |
+
"step": 44694
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 2.0,
|
| 185 |
+
"eval_loss": 0.026126669719815254,
|
| 186 |
+
"eval_max_distance": 8,
|
| 187 |
"eval_mean_distance": 0,
|
| 188 |
+
"eval_runtime": 13.5883,
|
| 189 |
+
"eval_samples_per_second": 18.472,
|
| 190 |
+
"eval_steps_per_second": 1.251,
|
| 191 |
+
"step": 45832
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 2.03,
|
| 195 |
+
"learning_rate": 9.610849285312543e-05,
|
| 196 |
+
"loss": 0.0047,
|
| 197 |
+
"step": 46413
|
| 198 |
},
|
| 199 |
{
|
| 200 |
"epoch": 2.1,
|
| 201 |
+
"learning_rate": 9.555284032505189e-05,
|
| 202 |
+
"loss": 0.004,
|
| 203 |
+
"step": 48132
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 2.18,
|
| 207 |
+
"learning_rate": 9.499718779697834e-05,
|
| 208 |
+
"loss": 0.004,
|
| 209 |
+
"step": 49851
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 2.25,
|
| 213 |
+
"learning_rate": 9.44415352689048e-05,
|
| 214 |
+
"loss": 0.0042,
|
| 215 |
+
"step": 51570
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.33,
|
| 219 |
+
"learning_rate": 9.388588274083125e-05,
|
| 220 |
+
"loss": 0.004,
|
| 221 |
+
"step": 53289
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 2.4,
|
| 225 |
+
"learning_rate": 9.333023021275771e-05,
|
| 226 |
+
"loss": 0.0043,
|
| 227 |
+
"step": 55008
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 2.48,
|
| 231 |
+
"learning_rate": 9.277457768468416e-05,
|
| 232 |
+
"loss": 0.0042,
|
| 233 |
+
"step": 56727
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 2.55,
|
| 237 |
+
"learning_rate": 9.221892515661063e-05,
|
| 238 |
+
"loss": 0.004,
|
| 239 |
+
"step": 58446
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.63,
|
| 243 |
+
"learning_rate": 9.166327262853708e-05,
|
| 244 |
+
"loss": 0.0045,
|
| 245 |
+
"step": 60165
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 2.7,
|
| 249 |
+
"learning_rate": 9.110762010046352e-05,
|
| 250 |
+
"loss": 0.0044,
|
| 251 |
+
"step": 61884
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 2.78,
|
| 255 |
+
"learning_rate": 9.055196757238999e-05,
|
| 256 |
+
"loss": 0.0044,
|
| 257 |
+
"step": 63603
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 2.85,
|
| 261 |
+
"learning_rate": 8.999631504431645e-05,
|
| 262 |
+
"loss": 0.0044,
|
| 263 |
+
"step": 65322
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.93,
|
| 267 |
+
"learning_rate": 8.94406625162429e-05,
|
| 268 |
"loss": 0.0043,
|
| 269 |
+
"step": 67041
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 3.0,
|
| 273 |
+
"eval_loss": 0.03130079433321953,
|
| 274 |
+
"eval_max_distance": 8,
|
| 275 |
"eval_mean_distance": 0,
|
| 276 |
+
"eval_runtime": 13.4308,
|
| 277 |
+
"eval_samples_per_second": 18.688,
|
| 278 |
+
"eval_steps_per_second": 1.266,
|
| 279 |
+
"step": 68748
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 3.0,
|
| 283 |
+
"learning_rate": 8.888500998816935e-05,
|
| 284 |
+
"loss": 0.0046,
|
| 285 |
+
"step": 68760
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 3.08,
|
| 289 |
+
"learning_rate": 8.832935746009581e-05,
|
| 290 |
+
"loss": 0.0036,
|
| 291 |
+
"step": 70479
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 3.15,
|
| 295 |
+
"learning_rate": 8.777370493202228e-05,
|
| 296 |
"loss": 0.0036,
|
| 297 |
+
"step": 72198
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.23,
|
| 301 |
+
"learning_rate": 8.721805240394872e-05,
|
| 302 |
+
"loss": 0.0038,
|
| 303 |
+
"step": 73917
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 3.3,
|
| 307 |
+
"learning_rate": 8.666239987587517e-05,
|
| 308 |
+
"loss": 0.0036,
|
| 309 |
+
"step": 75636
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 3.38,
|
| 313 |
+
"learning_rate": 8.610674734780164e-05,
|
| 314 |
+
"loss": 0.0038,
|
| 315 |
+
"step": 77355
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 3.45,
|
| 319 |
+
"learning_rate": 8.55510948197281e-05,
|
| 320 |
+
"loss": 0.0038,
|
| 321 |
+
"step": 79074
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.53,
|
| 325 |
+
"learning_rate": 8.499544229165455e-05,
|
| 326 |
+
"loss": 0.0038,
|
| 327 |
+
"step": 80793
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 3.6,
|
| 331 |
+
"learning_rate": 8.4439789763581e-05,
|
| 332 |
+
"loss": 0.004,
|
| 333 |
+
"step": 82512
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 3.68,
|
| 337 |
+
"learning_rate": 8.388413723550746e-05,
|
| 338 |
+
"loss": 0.0037,
|
| 339 |
+
"step": 84231
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.75,
|
| 343 |
+
"learning_rate": 8.332848470743392e-05,
|
| 344 |
+
"loss": 0.0038,
|
| 345 |
+
"step": 85950
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 3.83,
|
| 349 |
+
"learning_rate": 8.277283217936037e-05,
|
| 350 |
"loss": 0.0039,
|
| 351 |
+
"step": 87669
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 3.9,
|
| 355 |
+
"learning_rate": 8.221717965128682e-05,
|
| 356 |
+
"loss": 0.0039,
|
| 357 |
+
"step": 89388
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.98,
|
| 361 |
+
"learning_rate": 8.166152712321329e-05,
|
| 362 |
+
"loss": 0.0041,
|
| 363 |
+
"step": 91107
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 4.0,
|
| 367 |
+
"eval_loss": 0.02780107595026493,
|
| 368 |
+
"eval_max_distance": 10,
|
| 369 |
"eval_mean_distance": 0,
|
| 370 |
+
"eval_runtime": 13.351,
|
| 371 |
+
"eval_samples_per_second": 18.8,
|
| 372 |
+
"eval_steps_per_second": 1.273,
|
| 373 |
+
"step": 91664
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 4.05,
|
| 377 |
+
"learning_rate": 8.110587459513974e-05,
|
| 378 |
+
"loss": 0.0037,
|
| 379 |
+
"step": 92826
|
| 380 |
},
|
| 381 |
{
|
| 382 |
+
"epoch": 4.13,
|
| 383 |
+
"learning_rate": 8.05502220670662e-05,
|
| 384 |
+
"loss": 0.0032,
|
| 385 |
+
"step": 94545
|
| 386 |
},
|
| 387 |
{
|
| 388 |
"epoch": 4.2,
|
| 389 |
+
"learning_rate": 7.999456953899266e-05,
|
| 390 |
+
"loss": 0.0034,
|
| 391 |
+
"step": 96264
|
| 392 |
},
|
| 393 |
{
|
| 394 |
+
"epoch": 4.28,
|
| 395 |
+
"learning_rate": 7.943891701091911e-05,
|
| 396 |
"loss": 0.0034,
|
| 397 |
+
"step": 97983
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 4.35,
|
| 401 |
+
"learning_rate": 7.888326448284556e-05,
|
| 402 |
+
"loss": 0.0035,
|
| 403 |
+
"step": 99702
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 4.43,
|
| 407 |
+
"learning_rate": 7.832761195477202e-05,
|
| 408 |
"loss": 0.0034,
|
| 409 |
+
"step": 101421
|
| 410 |
},
|
| 411 |
{
|
| 412 |
"epoch": 4.5,
|
| 413 |
+
"learning_rate": 7.777195942669849e-05,
|
| 414 |
+
"loss": 0.0036,
|
| 415 |
+
"step": 103140
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 4.58,
|
| 419 |
+
"learning_rate": 7.721630689862494e-05,
|
| 420 |
"loss": 0.0035,
|
| 421 |
+
"step": 104859
|
| 422 |
},
|
| 423 |
{
|
| 424 |
+
"epoch": 4.65,
|
| 425 |
+
"learning_rate": 7.666065437055139e-05,
|
| 426 |
+
"loss": 0.0034,
|
| 427 |
+
"step": 106578
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.73,
|
| 431 |
+
"learning_rate": 7.610500184247783e-05,
|
| 432 |
+
"loss": 0.0034,
|
| 433 |
+
"step": 108297
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 4.8,
|
| 437 |
+
"learning_rate": 7.554934931440431e-05,
|
| 438 |
+
"loss": 0.0036,
|
| 439 |
+
"step": 110016
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 4.88,
|
| 443 |
+
"learning_rate": 7.499369678633076e-05,
|
| 444 |
+
"loss": 0.0034,
|
| 445 |
+
"step": 111735
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 4.95,
|
| 449 |
+
"learning_rate": 7.443804425825721e-05,
|
| 450 |
+
"loss": 0.0037,
|
| 451 |
+
"step": 113454
|
| 452 |
},
|
| 453 |
{
|
| 454 |
"epoch": 5.0,
|
| 455 |
+
"eval_loss": 0.028013188391923904,
|
| 456 |
+
"eval_max_distance": 8,
|
| 457 |
"eval_mean_distance": 0,
|
| 458 |
+
"eval_runtime": 13.4584,
|
| 459 |
+
"eval_samples_per_second": 18.65,
|
| 460 |
+
"eval_steps_per_second": 1.263,
|
| 461 |
+
"step": 114580
|
| 462 |
},
|
| 463 |
{
|
| 464 |
+
"epoch": 5.03,
|
| 465 |
+
"learning_rate": 7.388239173018366e-05,
|
| 466 |
+
"loss": 0.0033,
|
| 467 |
+
"step": 115173
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 5.1,
|
| 471 |
+
"learning_rate": 7.332673920211012e-05,
|
| 472 |
+
"loss": 0.0031,
|
| 473 |
+
"step": 116892
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"epoch": 5.18,
|
| 477 |
+
"learning_rate": 7.277108667403659e-05,
|
| 478 |
+
"loss": 0.0031,
|
| 479 |
+
"step": 118611
|
| 480 |
},
|
| 481 |
{
|
| 482 |
+
"epoch": 5.25,
|
| 483 |
+
"learning_rate": 7.221543414596303e-05,
|
| 484 |
+
"loss": 0.0032,
|
| 485 |
+
"step": 120330
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.33,
|
| 489 |
+
"learning_rate": 7.16597816178895e-05,
|
| 490 |
+
"loss": 0.0031,
|
| 491 |
+
"step": 122049
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 5.4,
|
| 495 |
+
"learning_rate": 7.110412908981595e-05,
|
| 496 |
+
"loss": 0.0032,
|
| 497 |
+
"step": 123768
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 5.48,
|
| 501 |
+
"learning_rate": 7.054847656174241e-05,
|
| 502 |
"loss": 0.0031,
|
| 503 |
+
"step": 125487
|
| 504 |
},
|
| 505 |
{
|
| 506 |
+
"epoch": 5.55,
|
| 507 |
+
"learning_rate": 6.999282403366886e-05,
|
| 508 |
"loss": 0.0032,
|
| 509 |
+
"step": 127206
|
| 510 |
},
|
| 511 |
{
|
| 512 |
+
"epoch": 5.63,
|
| 513 |
+
"learning_rate": 6.943717150559532e-05,
|
| 514 |
+
"loss": 0.0032,
|
| 515 |
+
"step": 128925
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 5.7,
|
| 519 |
+
"learning_rate": 6.888151897752177e-05,
|
| 520 |
"loss": 0.0032,
|
| 521 |
+
"step": 130644
|
| 522 |
},
|
| 523 |
{
|
| 524 |
+
"epoch": 5.78,
|
| 525 |
+
"learning_rate": 6.832586644944823e-05,
|
| 526 |
"loss": 0.0031,
|
| 527 |
+
"step": 132363
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 5.85,
|
| 531 |
+
"learning_rate": 6.777021392137468e-05,
|
| 532 |
+
"loss": 0.0031,
|
| 533 |
+
"step": 134082
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.93,
|
| 537 |
+
"learning_rate": 6.721456139330115e-05,
|
| 538 |
"loss": 0.0032,
|
| 539 |
+
"step": 135801
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 6.0,
|
| 543 |
+
"eval_loss": 0.028835317119956017,
|
| 544 |
+
"eval_max_distance": 8,
|
| 545 |
"eval_mean_distance": 0,
|
| 546 |
+
"eval_runtime": 13.4137,
|
| 547 |
+
"eval_samples_per_second": 18.712,
|
| 548 |
+
"eval_steps_per_second": 1.267,
|
| 549 |
+
"step": 137496
|
| 550 |
},
|
| 551 |
{
|
| 552 |
"epoch": 6.0,
|
| 553 |
+
"learning_rate": 6.66589088652276e-05,
|
| 554 |
+
"loss": 0.0033,
|
| 555 |
+
"step": 137520
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 6.08,
|
| 559 |
+
"learning_rate": 6.610325633715405e-05,
|
| 560 |
+
"loss": 0.0028,
|
| 561 |
+
"step": 139239
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 6.15,
|
| 565 |
+
"learning_rate": 6.554760380908051e-05,
|
| 566 |
"loss": 0.0026,
|
| 567 |
+
"step": 140958
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.23,
|
| 571 |
+
"learning_rate": 6.499195128100697e-05,
|
| 572 |
+
"loss": 0.0027,
|
| 573 |
+
"step": 142677
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 6.3,
|
| 577 |
+
"learning_rate": 6.443629875293342e-05,
|
| 578 |
+
"loss": 0.0029,
|
| 579 |
+
"step": 144396
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"epoch": 6.38,
|
| 583 |
+
"learning_rate": 6.388064622485987e-05,
|
| 584 |
"loss": 0.0029,
|
| 585 |
+
"step": 146115
|
| 586 |
},
|
| 587 |
{
|
| 588 |
+
"epoch": 6.45,
|
| 589 |
+
"learning_rate": 6.332499369678633e-05,
|
| 590 |
+
"loss": 0.0029,
|
| 591 |
+
"step": 147834
|
| 592 |
},
|
| 593 |
{
|
| 594 |
+
"epoch": 6.53,
|
| 595 |
+
"learning_rate": 6.27693411687128e-05,
|
| 596 |
"loss": 0.0028,
|
| 597 |
+
"step": 149553
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 6.6,
|
| 601 |
+
"learning_rate": 6.221368864063925e-05,
|
| 602 |
+
"loss": 0.0029,
|
| 603 |
+
"step": 151272
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 6.68,
|
| 607 |
+
"learning_rate": 6.16580361125657e-05,
|
| 608 |
+
"loss": 0.0029,
|
| 609 |
+
"step": 152991
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 6.75,
|
| 613 |
+
"learning_rate": 6.110238358449216e-05,
|
| 614 |
+
"loss": 0.0029,
|
| 615 |
+
"step": 154710
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 6.83,
|
| 619 |
+
"learning_rate": 6.0546731056418614e-05,
|
| 620 |
+
"loss": 0.0028,
|
| 621 |
+
"step": 156429
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 6.9,
|
| 625 |
+
"learning_rate": 5.999107852834507e-05,
|
| 626 |
+
"loss": 0.0029,
|
| 627 |
+
"step": 158148
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 6.98,
|
| 631 |
+
"learning_rate": 5.943542600027152e-05,
|
| 632 |
+
"loss": 0.003,
|
| 633 |
+
"step": 159867
|
|
|
|
|
|
|
|
|
|
|
|
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 7.0,
|
| 637 |
+
"eval_loss": 0.030847659334540367,
|
| 638 |
+
"eval_max_distance": 8,
|
| 639 |
+
"eval_mean_distance": 0,
|
| 640 |
+
"eval_runtime": 13.4895,
|
| 641 |
+
"eval_samples_per_second": 18.607,
|
| 642 |
+
"eval_steps_per_second": 1.26,
|
| 643 |
+
"step": 160412
|
| 644 |
},
|
| 645 |
{
|
| 646 |
+
"epoch": 7.05,
|
| 647 |
+
"learning_rate": 5.887977347219798e-05,
|
| 648 |
"loss": 0.0027,
|
| 649 |
+
"step": 161586
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"epoch": 7.13,
|
| 653 |
+
"learning_rate": 5.832412094412444e-05,
|
| 654 |
"loss": 0.0025,
|
| 655 |
+
"step": 163305
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 7.2,
|
| 659 |
+
"learning_rate": 5.7768468416050895e-05,
|
| 660 |
+
"loss": 0.0026,
|
| 661 |
+
"step": 165024
|
| 662 |
},
|
| 663 |
{
|
| 664 |
+
"epoch": 7.28,
|
| 665 |
+
"learning_rate": 5.7212815887977344e-05,
|
| 666 |
+
"loss": 0.0027,
|
| 667 |
+
"step": 166743
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.35,
|
| 671 |
+
"learning_rate": 5.665716335990381e-05,
|
| 672 |
"loss": 0.0025,
|
| 673 |
+
"step": 168462
|
| 674 |
},
|
| 675 |
{
|
| 676 |
+
"epoch": 7.43,
|
| 677 |
+
"learning_rate": 5.610151083183026e-05,
|
| 678 |
+
"loss": 0.0026,
|
| 679 |
+
"step": 170181
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 7.5,
|
| 683 |
+
"learning_rate": 5.554585830375671e-05,
|
| 684 |
"loss": 0.0026,
|
| 685 |
+
"step": 171900
|
| 686 |
},
|
| 687 |
{
|
| 688 |
+
"epoch": 7.58,
|
| 689 |
+
"learning_rate": 5.499020577568318e-05,
|
| 690 |
"loss": 0.0026,
|
| 691 |
+
"step": 173619
|
| 692 |
},
|
| 693 |
{
|
| 694 |
+
"epoch": 7.65,
|
| 695 |
+
"learning_rate": 5.443455324760963e-05,
|
| 696 |
"loss": 0.0026,
|
| 697 |
+
"step": 175338
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 7.73,
|
| 701 |
+
"learning_rate": 5.387890071953609e-05,
|
| 702 |
"loss": 0.0025,
|
| 703 |
+
"step": 177057
|
| 704 |
},
|
| 705 |
{
|
| 706 |
+
"epoch": 7.8,
|
| 707 |
+
"learning_rate": 5.332324819146254e-05,
|
| 708 |
"loss": 0.0027,
|
| 709 |
+
"step": 178776
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 7.88,
|
| 713 |
+
"learning_rate": 5.2767595663389e-05,
|
| 714 |
+
"loss": 0.0028,
|
| 715 |
+
"step": 180495
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 7.95,
|
| 719 |
+
"learning_rate": 5.2211943135315456e-05,
|
| 720 |
+
"loss": 0.0025,
|
| 721 |
+
"step": 182214
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 8.0,
|
| 725 |
+
"eval_loss": 0.03048335202038288,
|
| 726 |
+
"eval_max_distance": 8,
|
| 727 |
"eval_mean_distance": 0,
|
| 728 |
+
"eval_runtime": 13.5077,
|
| 729 |
+
"eval_samples_per_second": 18.582,
|
| 730 |
+
"eval_steps_per_second": 1.259,
|
| 731 |
+
"step": 183328
|
| 732 |
},
|
| 733 |
{
|
| 734 |
+
"epoch": 8.03,
|
| 735 |
+
"learning_rate": 5.1656290607241906e-05,
|
| 736 |
+
"loss": 0.0026,
|
| 737 |
+
"step": 183933
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 8.1,
|
| 741 |
+
"learning_rate": 5.110063807916836e-05,
|
| 742 |
"loss": 0.0023,
|
| 743 |
+
"step": 185652
|
| 744 |
},
|
| 745 |
{
|
| 746 |
+
"epoch": 8.18,
|
| 747 |
+
"learning_rate": 5.0544985551094825e-05,
|
| 748 |
+
"loss": 0.0024,
|
| 749 |
+
"step": 187371
|
| 750 |
},
|
| 751 |
{
|
| 752 |
+
"epoch": 8.25,
|
| 753 |
+
"learning_rate": 4.998933302302128e-05,
|
| 754 |
+
"loss": 0.0023,
|
| 755 |
+
"step": 189090
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"epoch": 8.33,
|
| 759 |
+
"learning_rate": 4.943368049494773e-05,
|
| 760 |
+
"loss": 0.0024,
|
| 761 |
+
"step": 190809
|
| 762 |
},
|
| 763 |
{
|
| 764 |
+
"epoch": 8.4,
|
| 765 |
+
"learning_rate": 4.887802796687419e-05,
|
| 766 |
"loss": 0.0024,
|
| 767 |
+
"step": 192528
|
| 768 |
},
|
| 769 |
{
|
| 770 |
+
"epoch": 8.48,
|
| 771 |
+
"learning_rate": 4.832237543880065e-05,
|
| 772 |
"loss": 0.0025,
|
| 773 |
+
"step": 194247
|
| 774 |
},
|
| 775 |
{
|
| 776 |
+
"epoch": 8.55,
|
| 777 |
+
"learning_rate": 4.77667229107271e-05,
|
| 778 |
"loss": 0.0024,
|
| 779 |
+
"step": 195966
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 8.63,
|
| 783 |
+
"learning_rate": 4.721107038265356e-05,
|
| 784 |
+
"loss": 0.0026,
|
| 785 |
+
"step": 197685
|
| 786 |
},
|
| 787 |
{
|
| 788 |
+
"epoch": 8.7,
|
| 789 |
+
"learning_rate": 4.665541785458001e-05,
|
| 790 |
"loss": 0.0023,
|
| 791 |
+
"step": 199404
|
| 792 |
},
|
| 793 |
{
|
| 794 |
+
"epoch": 8.78,
|
| 795 |
+
"learning_rate": 4.6099765326506474e-05,
|
| 796 |
+
"loss": 0.0024,
|
| 797 |
+
"step": 201123
|
|
|
|
|
|
|
|
|
|
|
|
|
| 798 |
},
|
| 799 |
{
|
| 800 |
+
"epoch": 8.85,
|
| 801 |
+
"learning_rate": 4.5544112798432924e-05,
|
| 802 |
"loss": 0.0024,
|
| 803 |
+
"step": 202842
|
| 804 |
},
|
| 805 |
{
|
| 806 |
+
"epoch": 8.93,
|
| 807 |
+
"learning_rate": 4.4988460270359386e-05,
|
| 808 |
+
"loss": 0.0025,
|
| 809 |
+
"step": 204561
|
| 810 |
},
|
| 811 |
{
|
| 812 |
+
"epoch": 9.0,
|
| 813 |
+
"eval_loss": 0.030335595831274986,
|
| 814 |
+
"eval_max_distance": 8,
|
| 815 |
+
"eval_mean_distance": 0,
|
| 816 |
+
"eval_runtime": 13.4109,
|
| 817 |
+
"eval_samples_per_second": 18.716,
|
| 818 |
+
"eval_steps_per_second": 1.268,
|
| 819 |
+
"step": 206244
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 9.0,
|
| 823 |
+
"learning_rate": 4.4432807742285836e-05,
|
| 824 |
+
"loss": 0.0026,
|
| 825 |
+
"step": 206280
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 9.08,
|
| 829 |
+
"learning_rate": 4.38771552142123e-05,
|
| 830 |
+
"loss": 0.0021,
|
| 831 |
+
"step": 207999
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 9.15,
|
| 835 |
+
"learning_rate": 4.332150268613875e-05,
|
| 836 |
"loss": 0.0022,
|
| 837 |
+
"step": 209718
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 9.23,
|
| 841 |
+
"learning_rate": 4.2765850158065204e-05,
|
| 842 |
+
"loss": 0.0022,
|
| 843 |
+
"step": 211437
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 9.3,
|
| 847 |
+
"learning_rate": 4.221019762999166e-05,
|
| 848 |
+
"loss": 0.0023,
|
| 849 |
+
"step": 213156
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 9.38,
|
| 853 |
+
"learning_rate": 4.165454510191812e-05,
|
| 854 |
"loss": 0.0023,
|
| 855 |
+
"step": 214875
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 9.45,
|
| 859 |
+
"learning_rate": 4.109889257384457e-05,
|
| 860 |
+
"loss": 0.0023,
|
| 861 |
+
"step": 216594
|
|
|
|
|
|
|
|
|
|
|
|
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 9.53,
|
| 865 |
+
"learning_rate": 4.054324004577103e-05,
|
| 866 |
"loss": 0.0023,
|
| 867 |
+
"step": 218313
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 9.6,
|
| 871 |
+
"learning_rate": 3.998758751769749e-05,
|
| 872 |
+
"loss": 0.0024,
|
| 873 |
+
"step": 220032
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 9.68,
|
| 877 |
+
"learning_rate": 3.943193498962394e-05,
|
| 878 |
+
"loss": 0.0024,
|
| 879 |
+
"step": 221751
|
| 880 |
},
|
| 881 |
{
|
| 882 |
+
"epoch": 9.75,
|
| 883 |
+
"learning_rate": 3.88762824615504e-05,
|
| 884 |
+
"loss": 0.0022,
|
| 885 |
+
"step": 223470
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 9.83,
|
| 889 |
+
"learning_rate": 3.8320629933476854e-05,
|
| 890 |
+
"loss": 0.0023,
|
| 891 |
+
"step": 225189
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 9.9,
|
| 895 |
+
"learning_rate": 3.776497740540331e-05,
|
| 896 |
+
"loss": 0.0024,
|
| 897 |
+
"step": 226908
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 9.98,
|
| 901 |
+
"learning_rate": 3.7209324877329766e-05,
|
| 902 |
+
"loss": 0.0023,
|
| 903 |
+
"step": 228627
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 10.0,
|
| 907 |
+
"eval_loss": 0.034065987914800644,
|
| 908 |
+
"eval_max_distance": 8,
|
| 909 |
+
"eval_mean_distance": 0,
|
| 910 |
+
"eval_runtime": 13.4726,
|
| 911 |
+
"eval_samples_per_second": 18.63,
|
| 912 |
+
"eval_steps_per_second": 1.262,
|
| 913 |
+
"step": 229160
|
| 914 |
},
|
| 915 |
{
|
| 916 |
+
"epoch": 10.05,
|
| 917 |
+
"learning_rate": 3.665367234925622e-05,
|
| 918 |
+
"loss": 0.0021,
|
| 919 |
+
"step": 230346
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 10.13,
|
| 923 |
+
"learning_rate": 3.609801982118268e-05,
|
| 924 |
+
"loss": 0.0021,
|
| 925 |
+
"step": 232065
|
| 926 |
},
|
| 927 |
{
|
| 928 |
+
"epoch": 10.2,
|
| 929 |
+
"learning_rate": 3.5542367293109135e-05,
|
| 930 |
+
"loss": 0.0021,
|
| 931 |
+
"step": 233784
|
|
|
|
|
|
|
|
|
|
|
|
|
| 932 |
},
|
| 933 |
{
|
| 934 |
+
"epoch": 10.28,
|
| 935 |
+
"learning_rate": 3.498671476503559e-05,
|
| 936 |
+
"loss": 0.0022,
|
| 937 |
+
"step": 235503
|
| 938 |
},
|
| 939 |
{
|
| 940 |
+
"epoch": 10.35,
|
| 941 |
+
"learning_rate": 3.443106223696205e-05,
|
| 942 |
+
"loss": 0.0021,
|
| 943 |
+
"step": 237222
|
| 944 |
},
|
| 945 |
{
|
| 946 |
+
"epoch": 10.43,
|
| 947 |
+
"learning_rate": 3.38754097088885e-05,
|
| 948 |
+
"loss": 0.0022,
|
| 949 |
+
"step": 238941
|
| 950 |
},
|
| 951 |
{
|
| 952 |
+
"epoch": 10.5,
|
| 953 |
+
"learning_rate": 3.331975718081496e-05,
|
| 954 |
+
"loss": 0.0021,
|
| 955 |
+
"step": 240660
|
| 956 |
},
|
| 957 |
{
|
| 958 |
+
"epoch": 10.58,
|
| 959 |
+
"learning_rate": 3.276410465274141e-05,
|
| 960 |
+
"loss": 0.0021,
|
| 961 |
+
"step": 242379
|
| 962 |
},
|
| 963 |
{
|
| 964 |
+
"epoch": 10.65,
|
| 965 |
+
"learning_rate": 3.220845212466787e-05,
|
| 966 |
+
"loss": 0.0021,
|
| 967 |
+
"step": 244098
|
| 968 |
},
|
| 969 |
{
|
| 970 |
+
"epoch": 10.73,
|
| 971 |
+
"learning_rate": 3.165279959659433e-05,
|
| 972 |
+
"loss": 0.0022,
|
| 973 |
+
"step": 245817
|
| 974 |
},
|
| 975 |
{
|
| 976 |
+
"epoch": 10.8,
|
| 977 |
+
"learning_rate": 3.1097147068520784e-05,
|
| 978 |
+
"loss": 0.0022,
|
| 979 |
+
"step": 247536
|
| 980 |
},
|
| 981 |
{
|
| 982 |
+
"epoch": 10.88,
|
| 983 |
+
"learning_rate": 3.054149454044724e-05,
|
| 984 |
"loss": 0.002,
|
| 985 |
+
"step": 249255
|
| 986 |
},
|
| 987 |
{
|
| 988 |
+
"epoch": 10.95,
|
| 989 |
+
"learning_rate": 2.9985842012373693e-05,
|
| 990 |
+
"loss": 0.0022,
|
| 991 |
+
"step": 250974
|
| 992 |
},
|
| 993 |
{
|
| 994 |
+
"epoch": 11.0,
|
| 995 |
+
"eval_loss": 0.03288768604397774,
|
| 996 |
+
"eval_max_distance": 8,
|
| 997 |
"eval_mean_distance": 0,
|
| 998 |
+
"eval_runtime": 13.3832,
|
| 999 |
+
"eval_samples_per_second": 18.755,
|
| 1000 |
+
"eval_steps_per_second": 1.27,
|
| 1001 |
+
"step": 252076
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
+
"epoch": 11.03,
|
| 1005 |
+
"learning_rate": 2.9430189484300152e-05,
|
| 1006 |
+
"loss": 0.0022,
|
| 1007 |
+
"step": 252693
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
+
"epoch": 11.1,
|
| 1011 |
+
"learning_rate": 2.8874536956226605e-05,
|
| 1012 |
"loss": 0.002,
|
| 1013 |
+
"step": 254412
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 11.18,
|
| 1017 |
+
"learning_rate": 2.8318884428153065e-05,
|
| 1018 |
+
"loss": 0.002,
|
| 1019 |
+
"step": 256131
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
+
"epoch": 11.25,
|
| 1023 |
+
"learning_rate": 2.7763231900079517e-05,
|
| 1024 |
+
"loss": 0.002,
|
| 1025 |
+
"step": 257850
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
+
"epoch": 11.33,
|
| 1029 |
+
"learning_rate": 2.7207579372005977e-05,
|
| 1030 |
+
"loss": 0.0021,
|
| 1031 |
+
"step": 259569
|
| 1032 |
},
|
| 1033 |
{
|
| 1034 |
+
"epoch": 11.4,
|
| 1035 |
+
"learning_rate": 2.665192684393243e-05,
|
| 1036 |
+
"loss": 0.0019,
|
| 1037 |
+
"step": 261288
|
| 1038 |
},
|
| 1039 |
{
|
| 1040 |
+
"epoch": 11.48,
|
| 1041 |
+
"learning_rate": 2.6096274315858886e-05,
|
| 1042 |
+
"loss": 0.002,
|
| 1043 |
+
"step": 263007
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 11.55,
|
| 1047 |
+
"learning_rate": 2.5540621787785342e-05,
|
| 1048 |
+
"loss": 0.002,
|
| 1049 |
+
"step": 264726
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
+
"epoch": 11.63,
|
| 1053 |
+
"learning_rate": 2.4984969259711798e-05,
|
| 1054 |
+
"loss": 0.002,
|
| 1055 |
+
"step": 266445
|
| 1056 |
},
|
| 1057 |
{
|
| 1058 |
+
"epoch": 11.7,
|
| 1059 |
+
"learning_rate": 2.4429316731638254e-05,
|
| 1060 |
+
"loss": 0.0019,
|
| 1061 |
+
"step": 268164
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
+
"epoch": 11.78,
|
| 1065 |
+
"learning_rate": 2.387366420356471e-05,
|
| 1066 |
+
"loss": 0.0021,
|
| 1067 |
+
"step": 269883
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
+
"epoch": 11.85,
|
| 1071 |
+
"learning_rate": 2.3318011675491167e-05,
|
| 1072 |
+
"loss": 0.0021,
|
| 1073 |
+
"step": 271602
|
| 1074 |
},
|
| 1075 |
{
|
| 1076 |
+
"epoch": 11.93,
|
| 1077 |
+
"learning_rate": 2.2762359147417623e-05,
|
| 1078 |
+
"loss": 0.0019,
|
| 1079 |
+
"step": 273321
|
| 1080 |
},
|
| 1081 |
{
|
| 1082 |
+
"epoch": 12.0,
|
| 1083 |
+
"eval_loss": 0.03355114161968231,
|
| 1084 |
+
"eval_max_distance": 8,
|
| 1085 |
"eval_mean_distance": 0,
|
| 1086 |
+
"eval_runtime": 13.4567,
|
| 1087 |
+
"eval_samples_per_second": 18.652,
|
| 1088 |
+
"eval_steps_per_second": 1.263,
|
| 1089 |
+
"step": 274992
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
+
"epoch": 12.0,
|
| 1093 |
+
"learning_rate": 2.220670661934408e-05,
|
| 1094 |
+
"loss": 0.0021,
|
| 1095 |
+
"step": 275040
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1096 |
},
|
| 1097 |
{
|
| 1098 |
+
"epoch": 12.08,
|
| 1099 |
+
"learning_rate": 2.1651054091270535e-05,
|
| 1100 |
+
"loss": 0.002,
|
| 1101 |
+
"step": 276759
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
+
"epoch": 12.15,
|
| 1105 |
+
"learning_rate": 2.109540156319699e-05,
|
| 1106 |
+
"loss": 0.002,
|
| 1107 |
+
"step": 278478
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 12.23,
|
| 1111 |
+
"learning_rate": 2.0539749035123444e-05,
|
| 1112 |
+
"loss": 0.0018,
|
| 1113 |
+
"step": 280197
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 12.3,
|
| 1117 |
+
"learning_rate": 1.9984096507049904e-05,
|
| 1118 |
+
"loss": 0.002,
|
| 1119 |
+
"step": 281916
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
+
"epoch": 12.38,
|
| 1123 |
+
"learning_rate": 1.942844397897636e-05,
|
| 1124 |
+
"loss": 0.0019,
|
| 1125 |
+
"step": 283635
|
| 1126 |
},
|
| 1127 |
{
|
| 1128 |
+
"epoch": 12.45,
|
| 1129 |
+
"learning_rate": 1.8872791450902816e-05,
|
| 1130 |
+
"loss": 0.0018,
|
| 1131 |
+
"step": 285354
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
+
"epoch": 12.53,
|
| 1135 |
+
"learning_rate": 1.8317138922829272e-05,
|
| 1136 |
+
"loss": 0.0019,
|
| 1137 |
+
"step": 287073
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
+
"epoch": 12.6,
|
| 1141 |
+
"learning_rate": 1.776148639475573e-05,
|
| 1142 |
+
"loss": 0.0018,
|
| 1143 |
+
"step": 288792
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
+
"epoch": 12.68,
|
| 1147 |
+
"learning_rate": 1.7205833866682185e-05,
|
| 1148 |
+
"loss": 0.0019,
|
| 1149 |
+
"step": 290511
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
+
"epoch": 12.75,
|
| 1153 |
+
"learning_rate": 1.665018133860864e-05,
|
| 1154 |
+
"loss": 0.0019,
|
| 1155 |
+
"step": 292230
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
+
"epoch": 12.83,
|
| 1159 |
+
"learning_rate": 1.6094528810535094e-05,
|
| 1160 |
+
"loss": 0.0021,
|
| 1161 |
+
"step": 293949
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
+
"epoch": 12.9,
|
| 1165 |
+
"learning_rate": 1.553887628246155e-05,
|
| 1166 |
+
"loss": 0.0019,
|
| 1167 |
+
"step": 295668
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
+
"epoch": 12.98,
|
| 1171 |
+
"learning_rate": 1.4983223754388006e-05,
|
| 1172 |
+
"loss": 0.002,
|
| 1173 |
+
"step": 297387
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
+
"epoch": 13.0,
|
| 1177 |
+
"eval_loss": 0.035788267850875854,
|
| 1178 |
+
"eval_max_distance": 8,
|
| 1179 |
"eval_mean_distance": 0,
|
| 1180 |
+
"eval_runtime": 13.4958,
|
| 1181 |
+
"eval_samples_per_second": 18.598,
|
| 1182 |
+
"eval_steps_per_second": 1.26,
|
| 1183 |
+
"step": 297908
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1184 |
},
|
| 1185 |
{
|
| 1186 |
+
"epoch": 13.05,
|
| 1187 |
+
"learning_rate": 1.4427571226314462e-05,
|
| 1188 |
+
"loss": 0.0019,
|
| 1189 |
+
"step": 299106
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1190 |
},
|
| 1191 |
{
|
| 1192 |
+
"epoch": 13.13,
|
| 1193 |
+
"learning_rate": 1.3871918698240918e-05,
|
| 1194 |
+
"loss": 0.0018,
|
| 1195 |
+
"step": 300825
|
| 1196 |
},
|
| 1197 |
{
|
| 1198 |
+
"epoch": 13.2,
|
| 1199 |
+
"learning_rate": 1.3316266170167374e-05,
|
| 1200 |
+
"loss": 0.0018,
|
| 1201 |
+
"step": 302544
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
+
"epoch": 13.28,
|
| 1205 |
+
"learning_rate": 1.276061364209383e-05,
|
| 1206 |
+
"loss": 0.0018,
|
| 1207 |
+
"step": 304263
|
| 1208 |
},
|
| 1209 |
{
|
| 1210 |
+
"epoch": 13.35,
|
| 1211 |
+
"learning_rate": 1.2204961114020287e-05,
|
| 1212 |
+
"loss": 0.0018,
|
| 1213 |
+
"step": 305982
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
+
"epoch": 13.43,
|
| 1217 |
+
"learning_rate": 1.1649308585946743e-05,
|
| 1218 |
+
"loss": 0.0018,
|
| 1219 |
+
"step": 307701
|
| 1220 |
},
|
| 1221 |
{
|
| 1222 |
+
"epoch": 13.5,
|
| 1223 |
+
"learning_rate": 1.1093656057873199e-05,
|
| 1224 |
+
"loss": 0.0019,
|
| 1225 |
+
"step": 309420
|
| 1226 |
},
|
| 1227 |
{
|
| 1228 |
+
"epoch": 13.58,
|
| 1229 |
+
"learning_rate": 1.0538003529799655e-05,
|
| 1230 |
+
"loss": 0.0018,
|
| 1231 |
+
"step": 311139
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
+
"epoch": 13.65,
|
| 1235 |
+
"learning_rate": 9.982351001726111e-06,
|
| 1236 |
+
"loss": 0.0017,
|
| 1237 |
+
"step": 312858
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
+
"epoch": 13.73,
|
| 1241 |
+
"learning_rate": 9.426698473652567e-06,
|
| 1242 |
+
"loss": 0.0018,
|
| 1243 |
+
"step": 314577
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
+
"epoch": 13.8,
|
| 1247 |
+
"learning_rate": 8.871045945579024e-06,
|
| 1248 |
+
"loss": 0.002,
|
| 1249 |
+
"step": 316296
|
| 1250 |
},
|
| 1251 |
{
|
| 1252 |
+
"epoch": 13.88,
|
| 1253 |
+
"learning_rate": 8.31539341750548e-06,
|
| 1254 |
+
"loss": 0.0018,
|
| 1255 |
+
"step": 318015
|
| 1256 |
},
|
| 1257 |
{
|
| 1258 |
+
"epoch": 13.95,
|
| 1259 |
+
"learning_rate": 7.759740889431934e-06,
|
| 1260 |
+
"loss": 0.0018,
|
| 1261 |
+
"step": 319734
|
| 1262 |
},
|
| 1263 |
{
|
| 1264 |
+
"epoch": 14.0,
|
| 1265 |
+
"eval_loss": 0.03550655022263527,
|
| 1266 |
+
"eval_max_distance": 8,
|
| 1267 |
"eval_mean_distance": 0,
|
| 1268 |
+
"eval_runtime": 13.4713,
|
| 1269 |
+
"eval_samples_per_second": 18.632,
|
| 1270 |
+
"eval_steps_per_second": 1.262,
|
| 1271 |
+
"step": 320824
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
+
"epoch": 14.03,
|
| 1275 |
+
"learning_rate": 7.204088361358391e-06,
|
| 1276 |
+
"loss": 0.0017,
|
| 1277 |
+
"step": 321453
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
+
"epoch": 14.1,
|
| 1281 |
+
"learning_rate": 6.648435833284847e-06,
|
| 1282 |
+
"loss": 0.0018,
|
| 1283 |
+
"step": 323172
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
+
"epoch": 14.18,
|
| 1287 |
+
"learning_rate": 6.092783305211304e-06,
|
| 1288 |
+
"loss": 0.0018,
|
| 1289 |
+
"step": 324891
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
+
"epoch": 14.25,
|
| 1293 |
+
"learning_rate": 5.537130777137759e-06,
|
| 1294 |
+
"loss": 0.0017,
|
| 1295 |
+
"step": 326610
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
+
"epoch": 14.33,
|
| 1299 |
+
"learning_rate": 4.981478249064216e-06,
|
| 1300 |
+
"loss": 0.0018,
|
| 1301 |
+
"step": 328329
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
+
"epoch": 14.4,
|
| 1305 |
+
"learning_rate": 4.425825720990671e-06,
|
| 1306 |
+
"loss": 0.0018,
|
| 1307 |
+
"step": 330048
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
+
"epoch": 14.48,
|
| 1311 |
+
"learning_rate": 3.8701731929171274e-06,
|
| 1312 |
+
"loss": 0.0018,
|
| 1313 |
+
"step": 331767
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
+
"epoch": 14.55,
|
| 1317 |
+
"learning_rate": 3.3145206648435836e-06,
|
| 1318 |
+
"loss": 0.0019,
|
| 1319 |
+
"step": 333486
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
+
"epoch": 14.63,
|
| 1323 |
+
"learning_rate": 2.7588681367700398e-06,
|
| 1324 |
+
"loss": 0.0017,
|
| 1325 |
+
"step": 335205
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
+
"epoch": 14.7,
|
| 1329 |
+
"learning_rate": 2.2032156086964955e-06,
|
| 1330 |
+
"loss": 0.0018,
|
| 1331 |
+
"step": 336924
|
| 1332 |
},
|
| 1333 |
{
|
| 1334 |
+
"epoch": 14.78,
|
| 1335 |
+
"learning_rate": 1.6475630806229517e-06,
|
| 1336 |
+
"loss": 0.0017,
|
| 1337 |
+
"step": 338643
|
| 1338 |
},
|
| 1339 |
{
|
| 1340 |
+
"epoch": 14.85,
|
| 1341 |
+
"learning_rate": 1.0919105525494076e-06,
|
| 1342 |
+
"loss": 0.0018,
|
| 1343 |
+
"step": 340362
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
+
"epoch": 14.93,
|
| 1347 |
+
"learning_rate": 5.362580244758636e-07,
|
| 1348 |
+
"loss": 0.0019,
|
| 1349 |
+
"step": 342081
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
+
"epoch": 15.0,
|
| 1353 |
+
"eval_loss": 0.03661360964179039,
|
| 1354 |
+
"eval_max_distance": 8,
|
| 1355 |
+
"eval_mean_distance": 0,
|
| 1356 |
+
"eval_runtime": 13.3536,
|
| 1357 |
+
"eval_samples_per_second": 18.796,
|
| 1358 |
+
"eval_steps_per_second": 1.273,
|
| 1359 |
+
"step": 343740
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
+
"epoch": 15.0,
|
| 1363 |
+
"step": 343740,
|
| 1364 |
+
"total_flos": 8.727792619277722e+16,
|
| 1365 |
+
"train_loss": 0.0029792904397642345,
|
| 1366 |
+
"train_runtime": 24306.5697,
|
| 1367 |
+
"train_samples_per_second": 212.119,
|
| 1368 |
+
"train_steps_per_second": 14.142
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1369 |
}
|
| 1370 |
],
|
| 1371 |
+
"logging_steps": 1719,
|
| 1372 |
+
"max_steps": 343740,
|
| 1373 |
+
"num_train_epochs": 15,
|
| 1374 |
+
"save_steps": 3438,
|
| 1375 |
+
"total_flos": 8.727792619277722e+16,
|
| 1376 |
"trial_name": null,
|
| 1377 |
"trial_params": null
|
| 1378 |
}
|
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 sha256:19cad5fdc011eae68aae9d7cd252dcf011f18199df3fd5c6b107c8e3cbed177f
|
| 3 |
size 4091
|