Upload folder using huggingface_hub
Browse files- metadata.json +1 -1
- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +257 -355
- training_args.bin +1 -1
metadata.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"test_split": 0.2,
|
| 5 |
"num_train_epochs": 5,
|
| 6 |
"learning_rate": 0.0001,
|
| 7 |
-
"max_value": 4.
|
| 8 |
}
|
|
|
|
| 4 |
"test_split": 0.2,
|
| 5 |
"num_train_epochs": 5,
|
| 6 |
"learning_rate": 0.0001,
|
| 7 |
+
"max_value": 4.7
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346369012
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a429d6e9dd7b8331ab63dd6bfd04ac606070e943440dda89310ccd63b0ff3bc
|
| 3 |
size 346369012
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 688135226
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2f3b1a17adfd7884a2073c6c7710ad622bccbc8ba65095976d119fe19584384
|
| 3 |
size 688135226
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3148a8d97e8830d98360d94641551b15906e3f95088bf5e2cc8a4d3a6f0d9f35
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6fdd0d2efe599d523a0c70a69f7cc358a16054c4b550b1f3b3e5e6fe4b01b1c
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -3,533 +3,435 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 1.
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"eval_samples_per_second": 6.984,
|
| 108 |
-
"eval_steps_per_second": 0.222,
|
| 109 |
-
"step": 138
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 1.0144927536231885,
|
| 113 |
-
"grad_norm": 10.701089859008789,
|
| 114 |
-
"learning_rate": 0.0007971014492753623,
|
| 115 |
-
"loss": 0.4652,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 1.
|
| 120 |
-
"grad_norm":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 1.
|
| 127 |
-
"grad_norm":
|
| 128 |
-
"learning_rate":
|
| 129 |
-
"loss":
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 1.
|
| 134 |
-
"grad_norm":
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 1.
|
| 141 |
-
"grad_norm":
|
| 142 |
-
"learning_rate":
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 1.
|
| 148 |
-
"grad_norm":
|
| 149 |
-
"learning_rate":
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
-
"epoch": 1.
|
| 155 |
-
"grad_norm":
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 1.
|
| 162 |
-
"grad_norm":
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 210
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch":
|
| 169 |
-
"grad_norm": 1.
|
| 170 |
-
"learning_rate":
|
| 171 |
-
"loss": 0.
|
| 172 |
"step": 220
|
| 173 |
},
|
| 174 |
{
|
| 175 |
-
"epoch":
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
"step": 230
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch":
|
| 183 |
-
"grad_norm":
|
| 184 |
-
"learning_rate":
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 240
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch":
|
| 190 |
-
"grad_norm": 2.
|
| 191 |
-
"learning_rate":
|
| 192 |
-
"loss": 0.
|
| 193 |
"step": 250
|
| 194 |
},
|
| 195 |
{
|
| 196 |
-
"epoch":
|
| 197 |
-
"grad_norm":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 260
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"grad_norm":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 2.
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"eval_samples_per_second": 6.987,
|
| 215 |
-
"eval_steps_per_second": 0.222,
|
| 216 |
-
"step": 276
|
| 217 |
-
},
|
| 218 |
-
{
|
| 219 |
-
"epoch": 2.028985507246377,
|
| 220 |
-
"grad_norm": 1.6650645732879639,
|
| 221 |
-
"learning_rate": 0.0005942028985507247,
|
| 222 |
-
"loss": 0.4403,
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
-
"epoch": 2.
|
| 227 |
-
"grad_norm": 2.
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch": 2.
|
| 234 |
-
"grad_norm":
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch": 2.
|
| 241 |
-
"grad_norm":
|
| 242 |
-
"learning_rate":
|
| 243 |
-
"loss": 0.
|
| 244 |
"step": 310
|
| 245 |
},
|
| 246 |
{
|
| 247 |
-
"epoch": 2.
|
| 248 |
-
"grad_norm":
|
| 249 |
-
"learning_rate":
|
| 250 |
-
"loss": 0.
|
| 251 |
"step": 320
|
| 252 |
},
|
| 253 |
{
|
| 254 |
-
"epoch":
|
| 255 |
-
"grad_norm": 1.
|
| 256 |
-
"learning_rate":
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 330
|
| 259 |
},
|
| 260 |
{
|
| 261 |
-
"epoch":
|
| 262 |
-
"
|
| 263 |
-
"
|
| 264 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 265 |
"step": 340
|
| 266 |
},
|
| 267 |
{
|
| 268 |
-
"epoch":
|
| 269 |
-
"grad_norm": 1.
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 350
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"grad_norm":
|
| 277 |
-
"learning_rate":
|
| 278 |
-
"loss": 0.
|
| 279 |
"step": 360
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch":
|
| 283 |
-
"grad_norm":
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss": 0.
|
| 286 |
"step": 370
|
| 287 |
},
|
| 288 |
{
|
| 289 |
-
"epoch":
|
| 290 |
-
"grad_norm":
|
| 291 |
-
"learning_rate":
|
| 292 |
-
"loss": 0.
|
| 293 |
"step": 380
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch":
|
| 297 |
-
"grad_norm":
|
| 298 |
-
"learning_rate":
|
| 299 |
-
"loss": 0.
|
| 300 |
"step": 390
|
| 301 |
},
|
| 302 |
{
|
| 303 |
-
"epoch":
|
| 304 |
-
"grad_norm":
|
| 305 |
-
"learning_rate":
|
| 306 |
-
"loss": 0.
|
| 307 |
"step": 400
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"grad_norm":
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 410
|
| 315 |
},
|
| 316 |
{
|
| 317 |
-
"epoch": 3.
|
| 318 |
-
"
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"eval_samples_per_second": 7.05,
|
| 322 |
-
"eval_steps_per_second": 0.224,
|
| 323 |
-
"step": 414
|
| 324 |
-
},
|
| 325 |
-
{
|
| 326 |
-
"epoch": 3.0434782608695654,
|
| 327 |
-
"grad_norm": 2.937997341156006,
|
| 328 |
-
"learning_rate": 0.000391304347826087,
|
| 329 |
-
"loss": 0.3433,
|
| 330 |
"step": 420
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"epoch": 3.
|
| 334 |
-
"grad_norm":
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"loss": 0.
|
| 337 |
"step": 430
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch":
|
| 341 |
-
"grad_norm": 2.
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 344 |
"step": 440
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"grad_norm":
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 450
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"grad_norm":
|
| 356 |
-
"learning_rate":
|
| 357 |
-
"loss": 0.
|
| 358 |
"step": 460
|
| 359 |
},
|
| 360 |
{
|
| 361 |
-
"epoch":
|
| 362 |
-
"grad_norm":
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 470
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch":
|
| 369 |
-
"grad_norm":
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 480
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch":
|
| 376 |
-
"grad_norm":
|
| 377 |
-
"learning_rate":
|
| 378 |
-
"loss": 0.
|
| 379 |
"step": 490
|
| 380 |
},
|
| 381 |
{
|
| 382 |
-
"epoch":
|
| 383 |
-
"grad_norm":
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 500
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"grad_norm": 2.
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 510
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch":
|
| 397 |
-
"grad_norm":
|
| 398 |
-
"learning_rate":
|
| 399 |
-
"loss": 0.
|
| 400 |
"step": 520
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"epoch":
|
| 404 |
-
"grad_norm":
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"loss": 0.
|
| 407 |
"step": 530
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch":
|
| 411 |
-
"grad_norm":
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 540
|
| 415 |
},
|
| 416 |
-
{
|
| 417 |
-
"epoch": 3.9855072463768115,
|
| 418 |
-
"grad_norm": 4.2478556632995605,
|
| 419 |
-
"learning_rate": 0.0002028985507246377,
|
| 420 |
-
"loss": 0.3838,
|
| 421 |
-
"step": 550
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 4.0,
|
| 425 |
-
"eval_loss": 0.32314667105674744,
|
| 426 |
-
"eval_mse": 0.32314667105674744,
|
| 427 |
-
"eval_runtime": 155.3243,
|
| 428 |
-
"eval_samples_per_second": 7.082,
|
| 429 |
-
"eval_steps_per_second": 0.225,
|
| 430 |
-
"step": 552
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 4.057971014492754,
|
| 434 |
-
"grad_norm": 1.7417830228805542,
|
| 435 |
-
"learning_rate": 0.0001884057971014493,
|
| 436 |
-
"loss": 0.3127,
|
| 437 |
-
"step": 560
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 4.130434782608695,
|
| 441 |
-
"grad_norm": 1.917121171951294,
|
| 442 |
-
"learning_rate": 0.00017391304347826088,
|
| 443 |
-
"loss": 0.237,
|
| 444 |
-
"step": 570
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 4.202898550724638,
|
| 448 |
-
"grad_norm": 3.26930570602417,
|
| 449 |
-
"learning_rate": 0.00015942028985507244,
|
| 450 |
-
"loss": 0.3469,
|
| 451 |
-
"step": 580
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 4.27536231884058,
|
| 455 |
-
"grad_norm": 5.88498592376709,
|
| 456 |
-
"learning_rate": 0.00014492753623188405,
|
| 457 |
-
"loss": 0.3593,
|
| 458 |
-
"step": 590
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 4.3478260869565215,
|
| 462 |
-
"grad_norm": 1.4033972024917603,
|
| 463 |
-
"learning_rate": 0.00013043478260869564,
|
| 464 |
-
"loss": 0.3329,
|
| 465 |
-
"step": 600
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 4.420289855072464,
|
| 469 |
-
"grad_norm": 1.2302778959274292,
|
| 470 |
-
"learning_rate": 0.00011594202898550725,
|
| 471 |
-
"loss": 0.2557,
|
| 472 |
-
"step": 610
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 4.492753623188406,
|
| 476 |
-
"grad_norm": 4.078396797180176,
|
| 477 |
-
"learning_rate": 0.00010144927536231885,
|
| 478 |
-
"loss": 0.3529,
|
| 479 |
-
"step": 620
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 4.565217391304348,
|
| 483 |
-
"grad_norm": 2.3110668659210205,
|
| 484 |
-
"learning_rate": 8.695652173913044e-05,
|
| 485 |
-
"loss": 0.3067,
|
| 486 |
-
"step": 630
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 4.63768115942029,
|
| 490 |
-
"grad_norm": 1.3999638557434082,
|
| 491 |
-
"learning_rate": 7.246376811594203e-05,
|
| 492 |
-
"loss": 0.28,
|
| 493 |
-
"step": 640
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 4.710144927536232,
|
| 497 |
-
"grad_norm": 1.5551191568374634,
|
| 498 |
-
"learning_rate": 5.797101449275363e-05,
|
| 499 |
-
"loss": 0.3179,
|
| 500 |
-
"step": 650
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 4.782608695652174,
|
| 504 |
-
"grad_norm": 2.349597454071045,
|
| 505 |
-
"learning_rate": 4.347826086956522e-05,
|
| 506 |
-
"loss": 0.3387,
|
| 507 |
-
"step": 660
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 4.855072463768116,
|
| 511 |
-
"grad_norm": 4.118350505828857,
|
| 512 |
-
"learning_rate": 2.8985507246376814e-05,
|
| 513 |
-
"loss": 0.3174,
|
| 514 |
-
"step": 670
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 4.927536231884058,
|
| 518 |
-
"grad_norm": 4.2804365158081055,
|
| 519 |
-
"learning_rate": 1.4492753623188407e-05,
|
| 520 |
-
"loss": 0.3202,
|
| 521 |
-
"step": 680
|
| 522 |
-
},
|
| 523 |
{
|
| 524 |
"epoch": 5.0,
|
| 525 |
-
"grad_norm":
|
| 526 |
"learning_rate": 0.0,
|
| 527 |
-
"loss": 0.
|
| 528 |
-
"step":
|
| 529 |
}
|
| 530 |
],
|
| 531 |
"logging_steps": 10,
|
| 532 |
-
"max_steps":
|
| 533 |
"num_input_tokens_seen": 0,
|
| 534 |
"num_train_epochs": 5,
|
| 535 |
"save_steps": 10,
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 550,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.09090909090909091,
|
| 13 |
+
"grad_norm": 2.9437830448150635,
|
| 14 |
+
"learning_rate": 9.818181818181818e-05,
|
| 15 |
+
"loss": 0.2953,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.18181818181818182,
|
| 20 |
+
"grad_norm": 5.8472676277160645,
|
| 21 |
+
"learning_rate": 9.636363636363637e-05,
|
| 22 |
+
"loss": 0.349,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.2727272727272727,
|
| 27 |
+
"grad_norm": 2.7091057300567627,
|
| 28 |
+
"learning_rate": 9.454545454545455e-05,
|
| 29 |
+
"loss": 0.2583,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.36363636363636365,
|
| 34 |
+
"grad_norm": 3.0798821449279785,
|
| 35 |
+
"learning_rate": 9.272727272727273e-05,
|
| 36 |
+
"loss": 0.2806,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.45454545454545453,
|
| 41 |
+
"grad_norm": 0.9187162518501282,
|
| 42 |
+
"learning_rate": 9.090909090909092e-05,
|
| 43 |
+
"loss": 0.3229,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.5454545454545454,
|
| 48 |
+
"grad_norm": 1.0290968418121338,
|
| 49 |
+
"learning_rate": 8.90909090909091e-05,
|
| 50 |
+
"loss": 0.271,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.6363636363636364,
|
| 55 |
+
"grad_norm": 1.4106591939926147,
|
| 56 |
+
"learning_rate": 8.727272727272727e-05,
|
| 57 |
+
"loss": 0.3005,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.7272727272727273,
|
| 62 |
+
"grad_norm": 2.5027103424072266,
|
| 63 |
+
"learning_rate": 8.545454545454545e-05,
|
| 64 |
+
"loss": 0.3279,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.8181818181818182,
|
| 69 |
+
"grad_norm": 1.4250562191009521,
|
| 70 |
+
"learning_rate": 8.363636363636364e-05,
|
| 71 |
+
"loss": 0.261,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.9090909090909091,
|
| 76 |
+
"grad_norm": 2.6990318298339844,
|
| 77 |
+
"learning_rate": 8.181818181818183e-05,
|
| 78 |
+
"loss": 0.3056,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"grad_norm": 1.4321504831314087,
|
| 84 |
+
"learning_rate": 8e-05,
|
| 85 |
+
"loss": 0.3135,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_loss": 0.26422303915023804,
|
| 91 |
+
"eval_mse": 0.26422300934791565,
|
| 92 |
+
"eval_runtime": 146.8663,
|
| 93 |
+
"eval_samples_per_second": 5.992,
|
| 94 |
+
"eval_steps_per_second": 0.191,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 1.0909090909090908,
|
| 99 |
+
"grad_norm": 1.3414746522903442,
|
| 100 |
+
"learning_rate": 7.818181818181818e-05,
|
| 101 |
+
"loss": 0.2876,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 1.1818181818181819,
|
| 106 |
+
"grad_norm": 2.420074939727783,
|
| 107 |
+
"learning_rate": 7.636363636363637e-05,
|
| 108 |
+
"loss": 0.2263,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 1.2727272727272727,
|
| 113 |
+
"grad_norm": 1.7859795093536377,
|
| 114 |
+
"learning_rate": 7.454545454545455e-05,
|
| 115 |
+
"loss": 0.2656,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 1.3636363636363638,
|
| 120 |
+
"grad_norm": 1.711840033531189,
|
| 121 |
+
"learning_rate": 7.272727272727273e-05,
|
| 122 |
+
"loss": 0.3181,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.4545454545454546,
|
| 127 |
+
"grad_norm": 1.9030543565750122,
|
| 128 |
+
"learning_rate": 7.090909090909092e-05,
|
| 129 |
+
"loss": 0.2948,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 1.5454545454545454,
|
| 134 |
+
"grad_norm": 4.079201698303223,
|
| 135 |
+
"learning_rate": 6.90909090909091e-05,
|
| 136 |
+
"loss": 0.3092,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.6363636363636362,
|
| 141 |
+
"grad_norm": 1.5639630556106567,
|
| 142 |
+
"learning_rate": 6.727272727272727e-05,
|
| 143 |
+
"loss": 0.3237,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.7272727272727273,
|
| 148 |
+
"grad_norm": 1.0921226739883423,
|
| 149 |
+
"learning_rate": 6.545454545454546e-05,
|
| 150 |
+
"loss": 0.2761,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.8181818181818183,
|
| 155 |
+
"grad_norm": 1.2289607524871826,
|
| 156 |
+
"learning_rate": 6.363636363636364e-05,
|
| 157 |
+
"loss": 0.2839,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 1.9090909090909092,
|
| 162 |
+
"grad_norm": 7.732837677001953,
|
| 163 |
+
"learning_rate": 6.181818181818182e-05,
|
| 164 |
+
"loss": 0.3596,
|
| 165 |
"step": 210
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 2.0,
|
| 169 |
+
"grad_norm": 1.0822261571884155,
|
| 170 |
+
"learning_rate": 6e-05,
|
| 171 |
+
"loss": 0.2541,
|
| 172 |
"step": 220
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 2.0,
|
| 176 |
+
"eval_loss": 0.2631426453590393,
|
| 177 |
+
"eval_mse": 0.2631426453590393,
|
| 178 |
+
"eval_runtime": 144.7981,
|
| 179 |
+
"eval_samples_per_second": 6.077,
|
| 180 |
+
"eval_steps_per_second": 0.193,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.090909090909091,
|
| 185 |
+
"grad_norm": 7.311972618103027,
|
| 186 |
+
"learning_rate": 5.818181818181818e-05,
|
| 187 |
+
"loss": 0.2924,
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 2.1818181818181817,
|
| 192 |
+
"grad_norm": 2.816499948501587,
|
| 193 |
+
"learning_rate": 5.636363636363636e-05,
|
| 194 |
+
"loss": 0.2654,
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.2727272727272725,
|
| 199 |
+
"grad_norm": 2.1038618087768555,
|
| 200 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 201 |
+
"loss": 0.3056,
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 2.3636363636363638,
|
| 206 |
+
"grad_norm": 2.7272915840148926,
|
| 207 |
+
"learning_rate": 5.272727272727272e-05,
|
| 208 |
+
"loss": 0.2994,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 2.4545454545454546,
|
| 213 |
+
"grad_norm": 1.5483731031417847,
|
| 214 |
+
"learning_rate": 5.090909090909091e-05,
|
| 215 |
+
"loss": 0.2938,
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 2.5454545454545454,
|
| 220 |
+
"grad_norm": 1.6636422872543335,
|
| 221 |
+
"learning_rate": 4.909090909090909e-05,
|
| 222 |
+
"loss": 0.2762,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 2.6363636363636362,
|
| 227 |
+
"grad_norm": 2.477865219116211,
|
| 228 |
+
"learning_rate": 4.7272727272727275e-05,
|
| 229 |
+
"loss": 0.3129,
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 2.7272727272727275,
|
| 234 |
+
"grad_norm": 2.1476693153381348,
|
| 235 |
+
"learning_rate": 4.545454545454546e-05,
|
| 236 |
+
"loss": 0.2656,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 2.8181818181818183,
|
| 241 |
+
"grad_norm": 1.3794795274734497,
|
| 242 |
+
"learning_rate": 4.3636363636363636e-05,
|
| 243 |
+
"loss": 0.2629,
|
| 244 |
"step": 310
|
| 245 |
},
|
| 246 |
{
|
| 247 |
+
"epoch": 2.909090909090909,
|
| 248 |
+
"grad_norm": 0.8552964925765991,
|
| 249 |
+
"learning_rate": 4.181818181818182e-05,
|
| 250 |
+
"loss": 0.2593,
|
| 251 |
"step": 320
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 3.0,
|
| 255 |
+
"grad_norm": 1.4841196537017822,
|
| 256 |
+
"learning_rate": 4e-05,
|
| 257 |
+
"loss": 0.2589,
|
| 258 |
"step": 330
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 3.0,
|
| 262 |
+
"eval_loss": 0.2576321065425873,
|
| 263 |
+
"eval_mse": 0.2576321065425873,
|
| 264 |
+
"eval_runtime": 145.7562,
|
| 265 |
+
"eval_samples_per_second": 6.037,
|
| 266 |
+
"eval_steps_per_second": 0.192,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.090909090909091,
|
| 271 |
+
"grad_norm": 3.3481814861297607,
|
| 272 |
+
"learning_rate": 3.818181818181819e-05,
|
| 273 |
+
"loss": 0.267,
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 3.1818181818181817,
|
| 278 |
+
"grad_norm": 1.704964280128479,
|
| 279 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 280 |
+
"loss": 0.2177,
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 3.2727272727272725,
|
| 285 |
+
"grad_norm": 1.3325728178024292,
|
| 286 |
+
"learning_rate": 3.454545454545455e-05,
|
| 287 |
+
"loss": 0.2815,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 3.3636363636363638,
|
| 292 |
+
"grad_norm": 2.831594705581665,
|
| 293 |
+
"learning_rate": 3.272727272727273e-05,
|
| 294 |
+
"loss": 0.2813,
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 3.4545454545454546,
|
| 299 |
+
"grad_norm": 1.7833585739135742,
|
| 300 |
+
"learning_rate": 3.090909090909091e-05,
|
| 301 |
+
"loss": 0.2745,
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 3.5454545454545454,
|
| 306 |
+
"grad_norm": 2.4361367225646973,
|
| 307 |
+
"learning_rate": 2.909090909090909e-05,
|
| 308 |
+
"loss": 0.3067,
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 3.6363636363636362,
|
| 313 |
+
"grad_norm": 1.7597070932388306,
|
| 314 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 315 |
+
"loss": 0.2706,
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 3.7272727272727275,
|
| 320 |
+
"grad_norm": 2.5651698112487793,
|
| 321 |
+
"learning_rate": 2.5454545454545454e-05,
|
| 322 |
+
"loss": 0.2742,
|
| 323 |
"step": 410
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 3.8181818181818183,
|
| 327 |
+
"grad_norm": 1.827591896057129,
|
| 328 |
+
"learning_rate": 2.3636363636363637e-05,
|
| 329 |
+
"loss": 0.2732,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 330 |
"step": 420
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 3.909090909090909,
|
| 334 |
+
"grad_norm": 3.2626404762268066,
|
| 335 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 336 |
+
"loss": 0.2653,
|
| 337 |
"step": 430
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 4.0,
|
| 341 |
+
"grad_norm": 2.742932081222534,
|
| 342 |
+
"learning_rate": 2e-05,
|
| 343 |
+
"loss": 0.3396,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.0,
|
| 348 |
+
"eval_loss": 0.2595486342906952,
|
| 349 |
+
"eval_mse": 0.2595486640930176,
|
| 350 |
+
"eval_runtime": 142.819,
|
| 351 |
+
"eval_samples_per_second": 6.162,
|
| 352 |
+
"eval_steps_per_second": 0.196,
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 4.090909090909091,
|
| 357 |
+
"grad_norm": 1.4092158079147339,
|
| 358 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 359 |
+
"loss": 0.2322,
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 4.181818181818182,
|
| 364 |
+
"grad_norm": 4.581083297729492,
|
| 365 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 366 |
+
"loss": 0.3015,
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 4.2727272727272725,
|
| 371 |
+
"grad_norm": 1.8915051221847534,
|
| 372 |
+
"learning_rate": 1.4545454545454545e-05,
|
| 373 |
+
"loss": 0.2979,
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 4.363636363636363,
|
| 378 |
+
"grad_norm": 2.127157688140869,
|
| 379 |
+
"learning_rate": 1.2727272727272727e-05,
|
| 380 |
+
"loss": 0.2525,
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 4.454545454545454,
|
| 385 |
+
"grad_norm": 3.3702645301818848,
|
| 386 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 387 |
+
"loss": 0.2603,
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 4.545454545454545,
|
| 392 |
+
"grad_norm": 2.1041481494903564,
|
| 393 |
+
"learning_rate": 9.090909090909091e-06,
|
| 394 |
+
"loss": 0.2564,
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 4.636363636363637,
|
| 399 |
+
"grad_norm": 2.5933034420013428,
|
| 400 |
+
"learning_rate": 7.272727272727272e-06,
|
| 401 |
+
"loss": 0.2677,
|
| 402 |
"step": 510
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 4.7272727272727275,
|
| 406 |
+
"grad_norm": 2.349623918533325,
|
| 407 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 408 |
+
"loss": 0.2752,
|
| 409 |
"step": 520
|
| 410 |
},
|
| 411 |
{
|
| 412 |
+
"epoch": 4.818181818181818,
|
| 413 |
+
"grad_norm": 5.803585529327393,
|
| 414 |
+
"learning_rate": 3.636363636363636e-06,
|
| 415 |
+
"loss": 0.2943,
|
| 416 |
"step": 530
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 4.909090909090909,
|
| 420 |
+
"grad_norm": 1.2074114084243774,
|
| 421 |
+
"learning_rate": 1.818181818181818e-06,
|
| 422 |
+
"loss": 0.2917,
|
| 423 |
"step": 540
|
| 424 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 425 |
{
|
| 426 |
"epoch": 5.0,
|
| 427 |
+
"grad_norm": 0.9745060801506042,
|
| 428 |
"learning_rate": 0.0,
|
| 429 |
+
"loss": 0.2587,
|
| 430 |
+
"step": 550
|
| 431 |
}
|
| 432 |
],
|
| 433 |
"logging_steps": 10,
|
| 434 |
+
"max_steps": 550,
|
| 435 |
"num_input_tokens_seen": 0,
|
| 436 |
"num_train_epochs": 5,
|
| 437 |
"save_steps": 10,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7716c33f1858dd6ff2ffb2de2e8d23b576e34581b35f49405c7a306bea32562b
|
| 3 |
size 5112
|