End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +338 -538
README.md
CHANGED
|
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amazingvince/huggingface/runs/atvo6d3z)
|
| 15 |
# jina_embeddings_v2_base_code_multi_regression-simple
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-code](https://huggingface.co/jinaai/jina-embeddings-v2-base-code) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Mse: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 14 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amazingvince/huggingface/runs/atvo6d3z)
|
| 15 |
# jina_embeddings_v2_base_code_multi_regression-simple
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-code](https://huggingface.co/jinaai/jina-embeddings-v2-base-code) on the amazingvince/the-stack-smol-xs-scored-and-annotated-all dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6115
|
| 20 |
+
- Mse: 0.6115
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mse": 0.
|
| 5 |
-
"eval_runtime": 13.
|
| 6 |
"eval_samples": 435,
|
| 7 |
-
"eval_samples_per_second": 32.
|
| 8 |
-
"eval_steps_per_second": 16.
|
| 9 |
-
"total_flos":
|
| 10 |
-
"train_loss": 1.
|
| 11 |
-
"train_runtime":
|
| 12 |
"train_samples": 8265,
|
| 13 |
-
"train_samples_per_second":
|
| 14 |
-
"train_steps_per_second": 0.
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.9963706750544397,
|
| 3 |
+
"eval_loss": 0.6114735007286072,
|
| 4 |
+
"eval_mse": 0.6114734868893679,
|
| 5 |
+
"eval_runtime": 13.3226,
|
| 6 |
"eval_samples": 435,
|
| 7 |
+
"eval_samples_per_second": 32.651,
|
| 8 |
+
"eval_steps_per_second": 16.363,
|
| 9 |
+
"total_flos": 2.606459925823488e+16,
|
| 10 |
+
"train_loss": 1.1786008090627902,
|
| 11 |
+
"train_runtime": 1155.1053,
|
| 12 |
"train_samples": 8265,
|
| 13 |
+
"train_samples_per_second": 21.466,
|
| 14 |
+
"train_steps_per_second": 0.335
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mse": 0.
|
| 5 |
-
"eval_runtime": 13.
|
| 6 |
"eval_samples": 435,
|
| 7 |
-
"eval_samples_per_second": 32.
|
| 8 |
-
"eval_steps_per_second": 16.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.9963706750544397,
|
| 3 |
+
"eval_loss": 0.6114735007286072,
|
| 4 |
+
"eval_mse": 0.6114734868893679,
|
| 5 |
+
"eval_runtime": 13.3226,
|
| 6 |
"eval_samples": 435,
|
| 7 |
+
"eval_samples_per_second": 32.651,
|
| 8 |
+
"eval_steps_per_second": 16.363
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 8265,
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2.9963706750544397,
|
| 3 |
+
"total_flos": 2.606459925823488e+16,
|
| 4 |
+
"train_loss": 1.1786008090627902,
|
| 5 |
+
"train_runtime": 1155.1053,
|
| 6 |
"train_samples": 8265,
|
| 7 |
+
"train_samples_per_second": 21.466,
|
| 8 |
+
"train_steps_per_second": 0.335
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,793 +1,593 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 12.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 12.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 9.
|
| 43 |
-
"loss":
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 9.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 9.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 9.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 9.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate": 9.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate": 9.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 55
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 65
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 75
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate": 8.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate": 8.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 85
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate": 8.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 95
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"eval_loss": 0.
|
| 154 |
-
"eval_mse": 0.
|
| 155 |
-
"eval_runtime": 12.
|
| 156 |
-
"eval_samples_per_second":
|
| 157 |
-
"eval_steps_per_second":
|
| 158 |
"step": 100
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
-
"grad_norm":
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 105
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
-
"grad_norm":
|
| 170 |
-
"learning_rate":
|
| 171 |
-
"loss": 0.
|
| 172 |
"step": 110
|
| 173 |
},
|
| 174 |
{
|
| 175 |
-
"epoch": 0.
|
| 176 |
-
"grad_norm":
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 0.
|
| 179 |
"step": 115
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 0.
|
| 183 |
-
"grad_norm": 3.
|
| 184 |
-
"learning_rate":
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 120
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch": 0.
|
| 190 |
-
"grad_norm":
|
| 191 |
-
"learning_rate": 7.
|
| 192 |
-
"loss": 0.
|
| 193 |
"step": 125
|
| 194 |
},
|
| 195 |
{
|
| 196 |
-
"epoch":
|
| 197 |
-
"grad_norm":
|
| 198 |
-
"learning_rate": 7.
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 130
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"grad_norm":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 135
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"grad_norm":
|
| 212 |
-
"learning_rate":
|
| 213 |
-
"loss": 0.
|
| 214 |
"step": 140
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch":
|
| 218 |
-
"grad_norm":
|
| 219 |
-
"learning_rate":
|
| 220 |
-
"loss": 0.
|
| 221 |
"step": 145
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch":
|
| 225 |
-
"grad_norm":
|
| 226 |
-
"learning_rate":
|
| 227 |
-
"loss": 0.
|
| 228 |
"step": 150
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch":
|
| 232 |
-
"grad_norm":
|
| 233 |
-
"learning_rate":
|
| 234 |
-
"loss": 0.
|
| 235 |
"step": 155
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch":
|
| 239 |
-
"grad_norm":
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 160
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"grad_norm":
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss": 0.
|
| 249 |
"step": 165
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"grad_norm":
|
| 254 |
-
"learning_rate":
|
| 255 |
-
"loss": 0.
|
| 256 |
"step": 170
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch":
|
| 260 |
-
"grad_norm":
|
| 261 |
-
"learning_rate":
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 175
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
-
"grad_norm":
|
| 268 |
-
"learning_rate":
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 180
|
| 271 |
},
|
| 272 |
{
|
| 273 |
-
"epoch":
|
| 274 |
-
"grad_norm":
|
| 275 |
-
"learning_rate":
|
| 276 |
-
"loss": 0.
|
| 277 |
"step": 185
|
| 278 |
},
|
| 279 |
{
|
| 280 |
-
"epoch":
|
| 281 |
-
"grad_norm":
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 190
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch":
|
| 288 |
-
"grad_norm":
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 195
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch":
|
| 295 |
-
"grad_norm":
|
| 296 |
-
"learning_rate":
|
| 297 |
-
"loss": 0.
|
| 298 |
"step": 200
|
| 299 |
},
|
| 300 |
{
|
| 301 |
-
"epoch":
|
| 302 |
-
"eval_loss": 0.
|
| 303 |
-
"eval_mse": 0.
|
| 304 |
-
"eval_runtime": 12.
|
| 305 |
-
"eval_samples_per_second":
|
| 306 |
-
"eval_steps_per_second":
|
| 307 |
"step": 200
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"grad_norm":
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 205
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch":
|
| 318 |
-
"grad_norm":
|
| 319 |
-
"learning_rate":
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 210
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch":
|
| 325 |
-
"grad_norm":
|
| 326 |
-
"learning_rate":
|
| 327 |
-
"loss": 0.
|
| 328 |
"step": 215
|
| 329 |
},
|
| 330 |
{
|
| 331 |
-
"epoch":
|
| 332 |
-
"grad_norm":
|
| 333 |
-
"learning_rate":
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 220
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch":
|
| 339 |
-
"grad_norm": 6.
|
| 340 |
-
"learning_rate":
|
| 341 |
-
"loss": 0.
|
| 342 |
"step": 225
|
| 343 |
},
|
| 344 |
{
|
| 345 |
-
"epoch":
|
| 346 |
-
"grad_norm":
|
| 347 |
-
"learning_rate":
|
| 348 |
-
"loss": 0.
|
| 349 |
"step": 230
|
| 350 |
},
|
| 351 |
{
|
| 352 |
-
"epoch":
|
| 353 |
-
"grad_norm":
|
| 354 |
-
"learning_rate":
|
| 355 |
-
"loss": 0.
|
| 356 |
"step": 235
|
| 357 |
},
|
| 358 |
{
|
| 359 |
-
"epoch":
|
| 360 |
-
"grad_norm":
|
| 361 |
-
"learning_rate":
|
| 362 |
-
"loss": 0.
|
| 363 |
"step": 240
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch":
|
| 367 |
-
"grad_norm": 18.
|
| 368 |
-
"learning_rate":
|
| 369 |
-
"loss": 0.
|
| 370 |
"step": 245
|
| 371 |
},
|
| 372 |
{
|
| 373 |
-
"epoch":
|
| 374 |
-
"grad_norm":
|
| 375 |
-
"learning_rate":
|
| 376 |
-
"loss": 0.
|
| 377 |
"step": 250
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch":
|
| 381 |
-
"grad_norm":
|
| 382 |
-
"learning_rate":
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 255
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"epoch":
|
| 388 |
-
"grad_norm":
|
| 389 |
-
"learning_rate":
|
| 390 |
-
"loss": 0.
|
| 391 |
"step": 260
|
| 392 |
},
|
| 393 |
{
|
| 394 |
-
"epoch":
|
| 395 |
-
"grad_norm":
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss": 0.
|
| 398 |
"step": 265
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch":
|
| 402 |
-
"grad_norm":
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 0.
|
| 405 |
"step": 270
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch":
|
| 409 |
-
"grad_norm":
|
| 410 |
-
"learning_rate":
|
| 411 |
-
"loss": 0.
|
| 412 |
"step": 275
|
| 413 |
},
|
| 414 |
{
|
| 415 |
-
"epoch":
|
| 416 |
-
"grad_norm":
|
| 417 |
-
"learning_rate":
|
| 418 |
-
"loss": 0.
|
| 419 |
"step": 280
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch":
|
| 423 |
-
"grad_norm":
|
| 424 |
-
"learning_rate":
|
| 425 |
-
"loss": 0.
|
| 426 |
"step": 285
|
| 427 |
},
|
| 428 |
{
|
| 429 |
-
"epoch":
|
| 430 |
-
"grad_norm":
|
| 431 |
-
"learning_rate":
|
| 432 |
-
"loss": 0.
|
| 433 |
"step": 290
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch":
|
| 437 |
-
"grad_norm":
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 295
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch":
|
| 444 |
-
"grad_norm":
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 300
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch":
|
| 451 |
-
"eval_loss": 0.
|
| 452 |
-
"eval_mse": 0.
|
| 453 |
-
"eval_runtime":
|
| 454 |
-
"eval_samples_per_second":
|
| 455 |
-
"eval_steps_per_second":
|
| 456 |
"step": 300
|
| 457 |
},
|
| 458 |
{
|
| 459 |
-
"epoch":
|
| 460 |
-
"grad_norm":
|
| 461 |
-
"learning_rate":
|
| 462 |
-
"loss": 0.
|
| 463 |
"step": 305
|
| 464 |
},
|
| 465 |
{
|
| 466 |
-
"epoch":
|
| 467 |
-
"grad_norm": 2.
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 310
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch":
|
| 474 |
-
"grad_norm":
|
| 475 |
-
"learning_rate":
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 315
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch":
|
| 481 |
-
"grad_norm":
|
| 482 |
-
"learning_rate":
|
| 483 |
-
"loss": 0.
|
| 484 |
"step": 320
|
| 485 |
},
|
| 486 |
{
|
| 487 |
-
"epoch":
|
| 488 |
-
"grad_norm":
|
| 489 |
-
"learning_rate":
|
| 490 |
-
"loss": 0.
|
| 491 |
"step": 325
|
| 492 |
},
|
| 493 |
{
|
| 494 |
-
"epoch":
|
| 495 |
-
"grad_norm":
|
| 496 |
-
"learning_rate":
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 330
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"epoch":
|
| 502 |
-
"grad_norm":
|
| 503 |
-
"learning_rate":
|
| 504 |
-
"loss": 0.
|
| 505 |
"step": 335
|
| 506 |
},
|
| 507 |
{
|
| 508 |
-
"epoch":
|
| 509 |
-
"grad_norm":
|
| 510 |
-
"learning_rate":
|
| 511 |
-
"loss": 0.
|
| 512 |
"step": 340
|
| 513 |
},
|
| 514 |
{
|
| 515 |
-
"epoch":
|
| 516 |
-
"grad_norm":
|
| 517 |
-
"learning_rate":
|
| 518 |
-
"loss": 0.
|
| 519 |
"step": 345
|
| 520 |
},
|
| 521 |
{
|
| 522 |
-
"epoch":
|
| 523 |
-
"grad_norm":
|
| 524 |
-
"learning_rate":
|
| 525 |
-
"loss": 0.
|
| 526 |
"step": 350
|
| 527 |
},
|
| 528 |
{
|
| 529 |
-
"epoch":
|
| 530 |
-
"grad_norm":
|
| 531 |
-
"learning_rate":
|
| 532 |
-
"loss": 0.
|
| 533 |
"step": 355
|
| 534 |
},
|
| 535 |
{
|
| 536 |
-
"epoch":
|
| 537 |
-
"grad_norm":
|
| 538 |
-
"learning_rate":
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 360
|
| 541 |
},
|
| 542 |
{
|
| 543 |
-
"epoch":
|
| 544 |
-
"grad_norm":
|
| 545 |
-
"learning_rate":
|
| 546 |
-
"loss": 0.
|
| 547 |
"step": 365
|
| 548 |
},
|
| 549 |
{
|
| 550 |
-
"epoch":
|
| 551 |
-
"grad_norm":
|
| 552 |
-
"learning_rate":
|
| 553 |
-
"loss": 0.
|
| 554 |
"step": 370
|
| 555 |
},
|
| 556 |
{
|
| 557 |
-
"epoch":
|
| 558 |
-
"grad_norm":
|
| 559 |
-
"learning_rate":
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 375
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch":
|
| 565 |
-
"grad_norm":
|
| 566 |
-
"learning_rate":
|
| 567 |
-
"loss": 0.
|
| 568 |
"step": 380
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch":
|
| 572 |
-
"grad_norm":
|
| 573 |
-
"learning_rate":
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 385
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch":
|
| 579 |
-
"
|
| 580 |
-
"
|
| 581 |
-
"
|
| 582 |
-
"
|
| 583 |
-
|
| 584 |
-
|
| 585 |
-
"epoch": 1.5291555770626664,
|
| 586 |
-
"grad_norm": 1.2320411205291748,
|
| 587 |
-
"learning_rate": 2.469387755102041e-06,
|
| 588 |
-
"loss": 0.6542,
|
| 589 |
-
"step": 395
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"epoch": 1.5485119767723203,
|
| 593 |
-
"grad_norm": 1.8463209867477417,
|
| 594 |
-
"learning_rate": 2.3673469387755103e-06,
|
| 595 |
-
"loss": 0.6077,
|
| 596 |
-
"step": 400
|
| 597 |
-
},
|
| 598 |
-
{
|
| 599 |
-
"epoch": 1.5485119767723203,
|
| 600 |
-
"eval_loss": 0.6124882102012634,
|
| 601 |
-
"eval_mse": 0.612488213900862,
|
| 602 |
-
"eval_runtime": 12.2194,
|
| 603 |
-
"eval_samples_per_second": 35.599,
|
| 604 |
-
"eval_steps_per_second": 17.841,
|
| 605 |
-
"step": 400
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 1.5678683764819743,
|
| 609 |
-
"grad_norm": 7.903787612915039,
|
| 610 |
-
"learning_rate": 2.2653061224489797e-06,
|
| 611 |
-
"loss": 0.5056,
|
| 612 |
-
"step": 405
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 1.5872247761916283,
|
| 616 |
-
"grad_norm": 1.824765682220459,
|
| 617 |
-
"learning_rate": 2.1632653061224495e-06,
|
| 618 |
-
"loss": 0.5517,
|
| 619 |
-
"step": 410
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 1.6065811759012822,
|
| 623 |
-
"grad_norm": 1.7653071880340576,
|
| 624 |
-
"learning_rate": 2.0612244897959184e-06,
|
| 625 |
-
"loss": 0.5645,
|
| 626 |
-
"step": 415
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 1.6259375756109362,
|
| 630 |
-
"grad_norm": 8.513703346252441,
|
| 631 |
-
"learning_rate": 1.9591836734693877e-06,
|
| 632 |
-
"loss": 0.5903,
|
| 633 |
-
"step": 420
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 1.6452939753205904,
|
| 637 |
-
"grad_norm": 0.14550276100635529,
|
| 638 |
-
"learning_rate": 1.8571428571428573e-06,
|
| 639 |
-
"loss": 0.5852,
|
| 640 |
-
"step": 425
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 1.6646503750302444,
|
| 644 |
-
"grad_norm": 1.8322155475616455,
|
| 645 |
-
"learning_rate": 1.7551020408163267e-06,
|
| 646 |
-
"loss": 0.5202,
|
| 647 |
-
"step": 430
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 1.6840067747398983,
|
| 651 |
-
"grad_norm": 8.522052764892578,
|
| 652 |
-
"learning_rate": 1.6530612244897962e-06,
|
| 653 |
-
"loss": 0.7683,
|
| 654 |
-
"step": 435
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 1.7033631744495525,
|
| 658 |
-
"grad_norm": 9.164407730102539,
|
| 659 |
-
"learning_rate": 1.5510204081632654e-06,
|
| 660 |
-
"loss": 0.663,
|
| 661 |
-
"step": 440
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 1.7227195741592065,
|
| 665 |
-
"grad_norm": 1.7836110591888428,
|
| 666 |
-
"learning_rate": 1.4489795918367347e-06,
|
| 667 |
-
"loss": 0.6314,
|
| 668 |
-
"step": 445
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 1.7420759738688605,
|
| 672 |
-
"grad_norm": 1.4566117525100708,
|
| 673 |
-
"learning_rate": 1.3469387755102043e-06,
|
| 674 |
-
"loss": 0.6647,
|
| 675 |
-
"step": 450
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 1.7614323735785145,
|
| 679 |
-
"grad_norm": 1.814237117767334,
|
| 680 |
-
"learning_rate": 1.2448979591836734e-06,
|
| 681 |
-
"loss": 0.5117,
|
| 682 |
-
"step": 455
|
| 683 |
-
},
|
| 684 |
-
{
|
| 685 |
-
"epoch": 1.7807887732881684,
|
| 686 |
-
"grad_norm": 6.711891174316406,
|
| 687 |
-
"learning_rate": 1.142857142857143e-06,
|
| 688 |
-
"loss": 0.557,
|
| 689 |
-
"step": 460
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 1.8001451729978224,
|
| 693 |
-
"grad_norm": 0.6150693297386169,
|
| 694 |
-
"learning_rate": 1.0408163265306123e-06,
|
| 695 |
-
"loss": 0.477,
|
| 696 |
-
"step": 465
|
| 697 |
-
},
|
| 698 |
-
{
|
| 699 |
-
"epoch": 1.8195015727074764,
|
| 700 |
-
"grad_norm": 3.6564579010009766,
|
| 701 |
-
"learning_rate": 9.387755102040817e-07,
|
| 702 |
-
"loss": 0.5492,
|
| 703 |
-
"step": 470
|
| 704 |
-
},
|
| 705 |
-
{
|
| 706 |
-
"epoch": 1.8388579724171303,
|
| 707 |
-
"grad_norm": 2.0056779384613037,
|
| 708 |
-
"learning_rate": 8.367346938775512e-07,
|
| 709 |
-
"loss": 0.6527,
|
| 710 |
-
"step": 475
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 1.8582143721267843,
|
| 714 |
-
"grad_norm": 4.872880935668945,
|
| 715 |
-
"learning_rate": 7.346938775510205e-07,
|
| 716 |
-
"loss": 0.616,
|
| 717 |
-
"step": 480
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 1.8775707718364383,
|
| 721 |
-
"grad_norm": 6.090467929840088,
|
| 722 |
-
"learning_rate": 6.326530612244898e-07,
|
| 723 |
-
"loss": 0.6453,
|
| 724 |
-
"step": 485
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 1.8969271715460925,
|
| 728 |
-
"grad_norm": 6.719366073608398,
|
| 729 |
-
"learning_rate": 5.306122448979592e-07,
|
| 730 |
-
"loss": 0.5115,
|
| 731 |
-
"step": 490
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 1.9162835712557464,
|
| 735 |
-
"grad_norm": 8.526107788085938,
|
| 736 |
-
"learning_rate": 4.285714285714286e-07,
|
| 737 |
-
"loss": 0.5886,
|
| 738 |
-
"step": 495
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 1.9356399709654004,
|
| 742 |
-
"grad_norm": 6.093981742858887,
|
| 743 |
-
"learning_rate": 3.2653061224489803e-07,
|
| 744 |
-
"loss": 0.6943,
|
| 745 |
-
"step": 500
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 1.9356399709654004,
|
| 749 |
-
"eval_loss": 0.611698567867279,
|
| 750 |
-
"eval_mse": 0.6116985452586207,
|
| 751 |
-
"eval_runtime": 12.5863,
|
| 752 |
-
"eval_samples_per_second": 34.561,
|
| 753 |
-
"eval_steps_per_second": 17.32,
|
| 754 |
-
"step": 500
|
| 755 |
-
},
|
| 756 |
-
{
|
| 757 |
-
"epoch": 1.9549963706750544,
|
| 758 |
-
"grad_norm": 4.887479305267334,
|
| 759 |
-
"learning_rate": 2.2448979591836735e-07,
|
| 760 |
-
"loss": 0.7463,
|
| 761 |
-
"step": 505
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 1.9743527703847086,
|
| 765 |
-
"grad_norm": 3.6627864837646484,
|
| 766 |
-
"learning_rate": 1.2244897959183673e-07,
|
| 767 |
-
"loss": 0.6146,
|
| 768 |
-
"step": 510
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 1.9937091700943625,
|
| 772 |
-
"grad_norm": 2.4411888122558594,
|
| 773 |
-
"learning_rate": 2.0408163265306127e-08,
|
| 774 |
-
"loss": 0.71,
|
| 775 |
-
"step": 515
|
| 776 |
-
},
|
| 777 |
-
{
|
| 778 |
-
"epoch": 1.9975804500362933,
|
| 779 |
-
"step": 516,
|
| 780 |
-
"total_flos": 1.737675031707648e+16,
|
| 781 |
-
"train_loss": 1.0921991518301557,
|
| 782 |
-
"train_runtime": 835.9482,
|
| 783 |
-
"train_samples_per_second": 19.774,
|
| 784 |
-
"train_steps_per_second": 0.617
|
| 785 |
}
|
| 786 |
],
|
| 787 |
"logging_steps": 5,
|
| 788 |
-
"max_steps":
|
| 789 |
"num_input_tokens_seen": 0,
|
| 790 |
-
"num_train_epochs":
|
| 791 |
"save_steps": 100,
|
| 792 |
"stateful_callbacks": {
|
| 793 |
"TrainerControl": {
|
|
@@ -801,7 +601,7 @@
|
|
| 801 |
"attributes": {}
|
| 802 |
}
|
| 803 |
},
|
| 804 |
-
"total_flos":
|
| 805 |
"train_batch_size": 2,
|
| 806 |
"trial_name": null,
|
| 807 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9963706750544397,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 387,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03871279941930801,
|
| 13 |
+
"grad_norm": 132.01553344726562,
|
| 14 |
+
"learning_rate": 2.5e-06,
|
| 15 |
+
"loss": 12.7967,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.07742559883861602,
|
| 20 |
+
"grad_norm": 132.22860717773438,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 12.7632,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.11613839825792402,
|
| 27 |
+
"grad_norm": 127.19441986083984,
|
| 28 |
+
"learning_rate": 7.500000000000001e-06,
|
| 29 |
+
"loss": 10.7405,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.15485119767723204,
|
| 34 |
+
"grad_norm": 131.84519958496094,
|
| 35 |
+
"learning_rate": 1e-05,
|
| 36 |
+
"loss": 7.2418,
|
| 37 |
"step": 20
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.19356399709654004,
|
| 41 |
+
"grad_norm": 45.38945007324219,
|
| 42 |
+
"learning_rate": 9.863760217983652e-06,
|
| 43 |
+
"loss": 3.0355,
|
| 44 |
"step": 25
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.23227679651584804,
|
| 48 |
+
"grad_norm": 52.082942962646484,
|
| 49 |
+
"learning_rate": 9.727520435967303e-06,
|
| 50 |
+
"loss": 1.3251,
|
| 51 |
"step": 30
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.27098959593515604,
|
| 55 |
+
"grad_norm": 11.499299049377441,
|
| 56 |
+
"learning_rate": 9.591280653950955e-06,
|
| 57 |
+
"loss": 0.6864,
|
| 58 |
"step": 35
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.3097023953544641,
|
| 62 |
+
"grad_norm": 18.093923568725586,
|
| 63 |
+
"learning_rate": 9.455040871934606e-06,
|
| 64 |
+
"loss": 0.652,
|
| 65 |
"step": 40
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.3484151947737721,
|
| 69 |
+
"grad_norm": 3.510300397872925,
|
| 70 |
+
"learning_rate": 9.318801089918257e-06,
|
| 71 |
+
"loss": 0.6286,
|
| 72 |
"step": 45
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.3871279941930801,
|
| 76 |
+
"grad_norm": 5.945786952972412,
|
| 77 |
+
"learning_rate": 9.182561307901908e-06,
|
| 78 |
+
"loss": 0.4977,
|
| 79 |
"step": 50
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.4258407936123881,
|
| 83 |
+
"grad_norm": 37.19482421875,
|
| 84 |
+
"learning_rate": 9.04632152588556e-06,
|
| 85 |
+
"loss": 0.6305,
|
| 86 |
"step": 55
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.4645535930316961,
|
| 90 |
+
"grad_norm": 5.250940799713135,
|
| 91 |
+
"learning_rate": 8.91008174386921e-06,
|
| 92 |
+
"loss": 0.693,
|
| 93 |
"step": 60
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.5032663924510041,
|
| 97 |
+
"grad_norm": 15.312704086303711,
|
| 98 |
+
"learning_rate": 8.773841961852862e-06,
|
| 99 |
+
"loss": 0.6779,
|
| 100 |
"step": 65
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.5419791918703121,
|
| 104 |
+
"grad_norm": 14.1633882522583,
|
| 105 |
+
"learning_rate": 8.637602179836513e-06,
|
| 106 |
+
"loss": 0.6297,
|
| 107 |
"step": 70
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.5806919912896201,
|
| 111 |
+
"grad_norm": 16.27649688720703,
|
| 112 |
+
"learning_rate": 8.501362397820165e-06,
|
| 113 |
+
"loss": 0.5674,
|
| 114 |
"step": 75
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.6194047907089282,
|
| 118 |
+
"grad_norm": 18.839599609375,
|
| 119 |
+
"learning_rate": 8.365122615803816e-06,
|
| 120 |
+
"loss": 0.735,
|
| 121 |
"step": 80
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.6581175901282361,
|
| 125 |
+
"grad_norm": 4.531907081604004,
|
| 126 |
+
"learning_rate": 8.228882833787467e-06,
|
| 127 |
+
"loss": 0.4994,
|
| 128 |
"step": 85
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.6968303895475442,
|
| 132 |
+
"grad_norm": 3.412825345993042,
|
| 133 |
+
"learning_rate": 8.092643051771117e-06,
|
| 134 |
+
"loss": 0.6938,
|
| 135 |
"step": 90
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.7355431889668521,
|
| 139 |
+
"grad_norm": 11.98742389678955,
|
| 140 |
+
"learning_rate": 7.95640326975477e-06,
|
| 141 |
+
"loss": 0.6628,
|
| 142 |
"step": 95
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.7742559883861602,
|
| 146 |
+
"grad_norm": 7.5615081787109375,
|
| 147 |
+
"learning_rate": 7.82016348773842e-06,
|
| 148 |
+
"loss": 0.5611,
|
| 149 |
"step": 100
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.7742559883861602,
|
| 153 |
+
"eval_loss": 0.6137279868125916,
|
| 154 |
+
"eval_mse": 0.6137279992816091,
|
| 155 |
+
"eval_runtime": 12.4934,
|
| 156 |
+
"eval_samples_per_second": 34.818,
|
| 157 |
+
"eval_steps_per_second": 17.449,
|
| 158 |
"step": 100
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 0.8129687878054682,
|
| 162 |
+
"grad_norm": 5.634002208709717,
|
| 163 |
+
"learning_rate": 7.683923705722072e-06,
|
| 164 |
+
"loss": 0.5883,
|
| 165 |
"step": 105
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.8516815872247762,
|
| 169 |
+
"grad_norm": 8.587458610534668,
|
| 170 |
+
"learning_rate": 7.547683923705723e-06,
|
| 171 |
+
"loss": 0.5996,
|
| 172 |
"step": 110
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 0.8903943866440842,
|
| 176 |
+
"grad_norm": 6.751793384552002,
|
| 177 |
+
"learning_rate": 7.411444141689374e-06,
|
| 178 |
+
"loss": 0.5587,
|
| 179 |
"step": 115
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 0.9291071860633922,
|
| 183 |
+
"grad_norm": 3.9238288402557373,
|
| 184 |
+
"learning_rate": 7.275204359673025e-06,
|
| 185 |
+
"loss": 0.66,
|
| 186 |
"step": 120
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 0.9678199854827002,
|
| 190 |
+
"grad_norm": 2.3443965911865234,
|
| 191 |
+
"learning_rate": 7.138964577656676e-06,
|
| 192 |
+
"loss": 0.523,
|
| 193 |
"step": 125
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 1.0065327849020083,
|
| 197 |
+
"grad_norm": 9.468040466308594,
|
| 198 |
+
"learning_rate": 7.002724795640327e-06,
|
| 199 |
+
"loss": 0.6157,
|
| 200 |
"step": 130
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 1.0452455843213162,
|
| 204 |
+
"grad_norm": 10.286754608154297,
|
| 205 |
+
"learning_rate": 6.8664850136239795e-06,
|
| 206 |
+
"loss": 0.5813,
|
| 207 |
"step": 135
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.0839583837406241,
|
| 211 |
+
"grad_norm": 1.447935700416565,
|
| 212 |
+
"learning_rate": 6.730245231607629e-06,
|
| 213 |
+
"loss": 0.5564,
|
| 214 |
"step": 140
|
| 215 |
},
|
| 216 |
{
|
| 217 |
+
"epoch": 1.1226711831599323,
|
| 218 |
+
"grad_norm": 4.448881149291992,
|
| 219 |
+
"learning_rate": 6.594005449591281e-06,
|
| 220 |
+
"loss": 0.5708,
|
| 221 |
"step": 145
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 1.1613839825792402,
|
| 225 |
+
"grad_norm": 0.6417679190635681,
|
| 226 |
+
"learning_rate": 6.457765667574932e-06,
|
| 227 |
+
"loss": 0.6145,
|
| 228 |
"step": 150
|
| 229 |
},
|
| 230 |
{
|
| 231 |
+
"epoch": 1.2000967819985482,
|
| 232 |
+
"grad_norm": 1.2481282949447632,
|
| 233 |
+
"learning_rate": 6.321525885558584e-06,
|
| 234 |
+
"loss": 0.5985,
|
| 235 |
"step": 155
|
| 236 |
},
|
| 237 |
{
|
| 238 |
+
"epoch": 1.2388095814178564,
|
| 239 |
+
"grad_norm": 8.027632713317871,
|
| 240 |
+
"learning_rate": 6.185286103542235e-06,
|
| 241 |
+
"loss": 0.6178,
|
| 242 |
"step": 160
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 1.2775223808371643,
|
| 246 |
+
"grad_norm": 7.15224027633667,
|
| 247 |
+
"learning_rate": 6.049046321525886e-06,
|
| 248 |
+
"loss": 0.7308,
|
| 249 |
"step": 165
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 1.3162351802564722,
|
| 253 |
+
"grad_norm": 10.559642791748047,
|
| 254 |
+
"learning_rate": 5.9128065395095365e-06,
|
| 255 |
+
"loss": 0.6057,
|
| 256 |
"step": 170
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"epoch": 1.3549479796757802,
|
| 260 |
+
"grad_norm": 3.033139705657959,
|
| 261 |
+
"learning_rate": 5.776566757493189e-06,
|
| 262 |
+
"loss": 0.5388,
|
| 263 |
"step": 175
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 1.3936607790950883,
|
| 267 |
+
"grad_norm": 9.217206954956055,
|
| 268 |
+
"learning_rate": 5.64032697547684e-06,
|
| 269 |
+
"loss": 0.4886,
|
| 270 |
"step": 180
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 1.4323735785143963,
|
| 274 |
+
"grad_norm": 8.655097007751465,
|
| 275 |
+
"learning_rate": 5.504087193460491e-06,
|
| 276 |
+
"loss": 0.5852,
|
| 277 |
"step": 185
|
| 278 |
},
|
| 279 |
{
|
| 280 |
+
"epoch": 1.4710863779337044,
|
| 281 |
+
"grad_norm": 14.92773723602295,
|
| 282 |
+
"learning_rate": 5.367847411444142e-06,
|
| 283 |
+
"loss": 0.615,
|
| 284 |
"step": 190
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 1.5097991773530124,
|
| 288 |
+
"grad_norm": 6.135091781616211,
|
| 289 |
+
"learning_rate": 5.231607629427793e-06,
|
| 290 |
+
"loss": 0.6194,
|
| 291 |
"step": 195
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 1.5485119767723203,
|
| 295 |
+
"grad_norm": 14.746587753295898,
|
| 296 |
+
"learning_rate": 5.095367847411444e-06,
|
| 297 |
+
"loss": 0.6542,
|
| 298 |
"step": 200
|
| 299 |
},
|
| 300 |
{
|
| 301 |
+
"epoch": 1.5485119767723203,
|
| 302 |
+
"eval_loss": 0.6139479875564575,
|
| 303 |
+
"eval_mse": 0.6139480064655173,
|
| 304 |
+
"eval_runtime": 12.9867,
|
| 305 |
+
"eval_samples_per_second": 33.496,
|
| 306 |
+
"eval_steps_per_second": 16.786,
|
| 307 |
"step": 200
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 1.5872247761916283,
|
| 311 |
+
"grad_norm": 6.090452194213867,
|
| 312 |
+
"learning_rate": 4.959128065395096e-06,
|
| 313 |
+
"loss": 0.5262,
|
| 314 |
"step": 205
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 1.6259375756109362,
|
| 318 |
+
"grad_norm": 9.420876502990723,
|
| 319 |
+
"learning_rate": 4.822888283378747e-06,
|
| 320 |
+
"loss": 0.5827,
|
| 321 |
"step": 210
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 1.6646503750302444,
|
| 325 |
+
"grad_norm": 5.127752304077148,
|
| 326 |
+
"learning_rate": 4.686648501362398e-06,
|
| 327 |
+
"loss": 0.5495,
|
| 328 |
"step": 215
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"epoch": 1.7033631744495525,
|
| 332 |
+
"grad_norm": 13.193638801574707,
|
| 333 |
+
"learning_rate": 4.55040871934605e-06,
|
| 334 |
+
"loss": 0.7189,
|
| 335 |
"step": 220
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 1.7420759738688605,
|
| 339 |
+
"grad_norm": 6.717041492462158,
|
| 340 |
+
"learning_rate": 4.414168937329701e-06,
|
| 341 |
+
"loss": 0.6618,
|
| 342 |
"step": 225
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 1.7807887732881684,
|
| 346 |
+
"grad_norm": 3.5996382236480713,
|
| 347 |
+
"learning_rate": 4.2779291553133515e-06,
|
| 348 |
+
"loss": 0.5368,
|
| 349 |
"step": 230
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 1.8195015727074764,
|
| 353 |
+
"grad_norm": 13.474601745605469,
|
| 354 |
+
"learning_rate": 4.141689373297003e-06,
|
| 355 |
+
"loss": 0.5235,
|
| 356 |
"step": 235
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 1.8582143721267843,
|
| 360 |
+
"grad_norm": 4.9880852699279785,
|
| 361 |
+
"learning_rate": 4.005449591280654e-06,
|
| 362 |
+
"loss": 0.6603,
|
| 363 |
"step": 240
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 1.8969271715460925,
|
| 367 |
+
"grad_norm": 18.385284423828125,
|
| 368 |
+
"learning_rate": 3.869209809264305e-06,
|
| 369 |
+
"loss": 0.5856,
|
| 370 |
"step": 245
|
| 371 |
},
|
| 372 |
{
|
| 373 |
+
"epoch": 1.9356399709654004,
|
| 374 |
+
"grad_norm": 8.442005157470703,
|
| 375 |
+
"learning_rate": 3.732970027247957e-06,
|
| 376 |
+
"loss": 0.6516,
|
| 377 |
"step": 250
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 1.9743527703847086,
|
| 381 |
+
"grad_norm": 7.920212268829346,
|
| 382 |
+
"learning_rate": 3.5967302452316077e-06,
|
| 383 |
+
"loss": 0.6733,
|
| 384 |
"step": 255
|
| 385 |
},
|
| 386 |
{
|
| 387 |
+
"epoch": 2.0130655698040165,
|
| 388 |
+
"grad_norm": 5.7283430099487305,
|
| 389 |
+
"learning_rate": 3.460490463215259e-06,
|
| 390 |
+
"loss": 0.6598,
|
| 391 |
"step": 260
|
| 392 |
},
|
| 393 |
{
|
| 394 |
+
"epoch": 2.0517783692233245,
|
| 395 |
+
"grad_norm": 9.823247909545898,
|
| 396 |
+
"learning_rate": 3.3242506811989107e-06,
|
| 397 |
+
"loss": 0.5799,
|
| 398 |
"step": 265
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 2.0904911686426324,
|
| 402 |
+
"grad_norm": 10.975919723510742,
|
| 403 |
+
"learning_rate": 3.1880108991825615e-06,
|
| 404 |
+
"loss": 0.6606,
|
| 405 |
"step": 270
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 2.1292039680619403,
|
| 409 |
+
"grad_norm": 12.75275707244873,
|
| 410 |
+
"learning_rate": 3.0517711171662127e-06,
|
| 411 |
+
"loss": 0.5614,
|
| 412 |
"step": 275
|
| 413 |
},
|
| 414 |
{
|
| 415 |
+
"epoch": 2.1679167674812483,
|
| 416 |
+
"grad_norm": 6.546001434326172,
|
| 417 |
+
"learning_rate": 2.9155313351498636e-06,
|
| 418 |
+
"loss": 0.5947,
|
| 419 |
"step": 280
|
| 420 |
},
|
| 421 |
{
|
| 422 |
+
"epoch": 2.2066295669005567,
|
| 423 |
+
"grad_norm": 6.290523052215576,
|
| 424 |
+
"learning_rate": 2.7792915531335152e-06,
|
| 425 |
+
"loss": 0.6092,
|
| 426 |
"step": 285
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 2.2453423663198646,
|
| 430 |
+
"grad_norm": 2.127336025238037,
|
| 431 |
+
"learning_rate": 2.6430517711171665e-06,
|
| 432 |
+
"loss": 0.5901,
|
| 433 |
"step": 290
|
| 434 |
},
|
| 435 |
{
|
| 436 |
+
"epoch": 2.2840551657391726,
|
| 437 |
+
"grad_norm": 5.803460121154785,
|
| 438 |
+
"learning_rate": 2.5068119891008173e-06,
|
| 439 |
+
"loss": 0.5735,
|
| 440 |
"step": 295
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 2.3227679651584805,
|
| 444 |
+
"grad_norm": 3.169969081878662,
|
| 445 |
+
"learning_rate": 2.370572207084469e-06,
|
| 446 |
+
"loss": 0.5106,
|
| 447 |
"step": 300
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 2.3227679651584805,
|
| 451 |
+
"eval_loss": 0.6125330924987793,
|
| 452 |
+
"eval_mse": 0.6125331133261495,
|
| 453 |
+
"eval_runtime": 13.1593,
|
| 454 |
+
"eval_samples_per_second": 33.057,
|
| 455 |
+
"eval_steps_per_second": 16.566,
|
| 456 |
"step": 300
|
| 457 |
},
|
| 458 |
{
|
| 459 |
+
"epoch": 2.3614807645777884,
|
| 460 |
+
"grad_norm": 3.102710485458374,
|
| 461 |
+
"learning_rate": 2.2343324250681202e-06,
|
| 462 |
+
"loss": 0.5843,
|
| 463 |
"step": 305
|
| 464 |
},
|
| 465 |
{
|
| 466 |
+
"epoch": 2.4001935639970964,
|
| 467 |
+
"grad_norm": 2.053990602493286,
|
| 468 |
+
"learning_rate": 2.098092643051771e-06,
|
| 469 |
+
"loss": 0.6371,
|
| 470 |
"step": 310
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 2.4389063634164048,
|
| 474 |
+
"grad_norm": 10.483580589294434,
|
| 475 |
+
"learning_rate": 1.9618528610354227e-06,
|
| 476 |
+
"loss": 0.5718,
|
| 477 |
"step": 315
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 2.4776191628357127,
|
| 481 |
+
"grad_norm": 3.1228301525115967,
|
| 482 |
+
"learning_rate": 1.8256130790190738e-06,
|
| 483 |
+
"loss": 0.5231,
|
| 484 |
"step": 320
|
| 485 |
},
|
| 486 |
{
|
| 487 |
+
"epoch": 2.5163319622550206,
|
| 488 |
+
"grad_norm": 5.304292678833008,
|
| 489 |
+
"learning_rate": 1.689373297002725e-06,
|
| 490 |
+
"loss": 0.6116,
|
| 491 |
"step": 325
|
| 492 |
},
|
| 493 |
{
|
| 494 |
+
"epoch": 2.5550447616743286,
|
| 495 |
+
"grad_norm": 6.294493675231934,
|
| 496 |
+
"learning_rate": 1.553133514986376e-06,
|
| 497 |
+
"loss": 0.6674,
|
| 498 |
"step": 330
|
| 499 |
},
|
| 500 |
{
|
| 501 |
+
"epoch": 2.5937575610936365,
|
| 502 |
+
"grad_norm": 3.730954647064209,
|
| 503 |
+
"learning_rate": 1.4168937329700275e-06,
|
| 504 |
+
"loss": 0.6522,
|
| 505 |
"step": 335
|
| 506 |
},
|
| 507 |
{
|
| 508 |
+
"epoch": 2.6324703605129445,
|
| 509 |
+
"grad_norm": 1.1117771863937378,
|
| 510 |
+
"learning_rate": 1.2806539509536785e-06,
|
| 511 |
+
"loss": 0.7333,
|
| 512 |
"step": 340
|
| 513 |
},
|
| 514 |
{
|
| 515 |
+
"epoch": 2.6711831599322524,
|
| 516 |
+
"grad_norm": 2.0916991233825684,
|
| 517 |
+
"learning_rate": 1.1444141689373298e-06,
|
| 518 |
+
"loss": 0.6361,
|
| 519 |
"step": 345
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 2.7098959593515604,
|
| 523 |
+
"grad_norm": 1.0104436874389648,
|
| 524 |
+
"learning_rate": 1.008174386920981e-06,
|
| 525 |
+
"loss": 0.621,
|
| 526 |
"step": 350
|
| 527 |
},
|
| 528 |
{
|
| 529 |
+
"epoch": 2.7486087587708687,
|
| 530 |
+
"grad_norm": 10.215568542480469,
|
| 531 |
+
"learning_rate": 8.719346049046322e-07,
|
| 532 |
+
"loss": 0.5874,
|
| 533 |
"step": 355
|
| 534 |
},
|
| 535 |
{
|
| 536 |
+
"epoch": 2.7873215581901767,
|
| 537 |
+
"grad_norm": 5.2254557609558105,
|
| 538 |
+
"learning_rate": 7.356948228882835e-07,
|
| 539 |
+
"loss": 0.621,
|
| 540 |
"step": 360
|
| 541 |
},
|
| 542 |
{
|
| 543 |
+
"epoch": 2.8260343576094846,
|
| 544 |
+
"grad_norm": 5.230953693389893,
|
| 545 |
+
"learning_rate": 5.994550408719347e-07,
|
| 546 |
+
"loss": 0.5851,
|
| 547 |
"step": 365
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 2.8647471570287926,
|
| 551 |
+
"grad_norm": 1.5109760761260986,
|
| 552 |
+
"learning_rate": 4.6321525885558585e-07,
|
| 553 |
+
"loss": 0.5377,
|
| 554 |
"step": 370
|
| 555 |
},
|
| 556 |
{
|
| 557 |
+
"epoch": 2.9034599564481005,
|
| 558 |
+
"grad_norm": 5.254393100738525,
|
| 559 |
+
"learning_rate": 3.2697547683923705e-07,
|
| 560 |
+
"loss": 0.6476,
|
| 561 |
"step": 375
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 2.942172755867409,
|
| 565 |
+
"grad_norm": 7.337405681610107,
|
| 566 |
+
"learning_rate": 1.907356948228883e-07,
|
| 567 |
+
"loss": 0.5664,
|
| 568 |
"step": 380
|
| 569 |
},
|
| 570 |
{
|
| 571 |
+
"epoch": 2.980885555286717,
|
| 572 |
+
"grad_norm": 4.144803524017334,
|
| 573 |
+
"learning_rate": 5.449591280653951e-08,
|
| 574 |
+
"loss": 0.5508,
|
| 575 |
"step": 385
|
| 576 |
},
|
| 577 |
{
|
| 578 |
+
"epoch": 2.9963706750544397,
|
| 579 |
+
"step": 387,
|
| 580 |
+
"total_flos": 2.606459925823488e+16,
|
| 581 |
+
"train_loss": 1.1786008090627902,
|
| 582 |
+
"train_runtime": 1155.1053,
|
| 583 |
+
"train_samples_per_second": 21.466,
|
| 584 |
+
"train_steps_per_second": 0.335
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 585 |
}
|
| 586 |
],
|
| 587 |
"logging_steps": 5,
|
| 588 |
+
"max_steps": 387,
|
| 589 |
"num_input_tokens_seen": 0,
|
| 590 |
+
"num_train_epochs": 3,
|
| 591 |
"save_steps": 100,
|
| 592 |
"stateful_callbacks": {
|
| 593 |
"TrainerControl": {
|
|
|
|
| 601 |
"attributes": {}
|
| 602 |
}
|
| 603 |
},
|
| 604 |
+
"total_flos": 2.606459925823488e+16,
|
| 605 |
"train_batch_size": 2,
|
| 606 |
"trial_name": null,
|
| 607 |
"trial_params": null
|