Commit
•
8d53a12
1
Parent(s):
b97fda3
Upload 8 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +231 -631
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995641861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff010bc66fd61f1d34710e22fc453cbd4986ef52cbca0f808e71d2287359c01a
|
| 3 |
size 995641861
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497807197
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86bf6ab09b64321efc94f3bc379e531d0a1338c8c5fa3b38c7c52464847c79d8
|
| 3 |
size 497807197
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dd3a816ab8628e6038ecf426e93a907752049203fbc39b63fcde557182a866f
|
| 3 |
size 14575
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41b18054e524341e87a895cc798ffc44bc6c3d095dc41640d72b87475609e792
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,851 +1,451 @@
|
|
| 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.
|
| 13 |
-
"learning_rate": 9.
|
| 14 |
-
"loss": 3.
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 9.
|
| 20 |
-
"loss":
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 9.
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 9.
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 9.
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 9.
|
| 44 |
-
"loss":
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 9.
|
| 50 |
-
"loss":
|
| 51 |
"step": 3500
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 9.
|
| 56 |
-
"loss":
|
| 57 |
"step": 4000
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 9.
|
| 62 |
-
"loss":
|
| 63 |
"step": 4500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 9.
|
| 68 |
-
"loss":
|
| 69 |
"step": 5000
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 9.
|
| 74 |
-
"loss":
|
| 75 |
"step": 5500
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 9.
|
| 80 |
-
"loss":
|
| 81 |
"step": 6000
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 9.
|
| 86 |
-
"loss":
|
| 87 |
"step": 6500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 9.
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 7000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 9.
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 7500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate": 9.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 8000
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"eval_samples_per_second": 42.421,
|
| 112 |
-
"eval_steps_per_second": 5.314,
|
| 113 |
-
"step": 8007
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 1.06,
|
| 117 |
-
"learning_rate": 9.469214437367304e-06,
|
| 118 |
-
"loss": 1.9463,
|
| 119 |
"step": 8500
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"epoch":
|
| 123 |
-
"learning_rate": 9.
|
| 124 |
-
"loss": 1.
|
| 125 |
"step": 9000
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch":
|
| 129 |
-
"learning_rate":
|
| 130 |
-
"loss": 1.
|
| 131 |
"step": 9500
|
| 132 |
},
|
| 133 |
{
|
| 134 |
-
"epoch":
|
| 135 |
-
"learning_rate":
|
| 136 |
-
"loss": 1.
|
| 137 |
"step": 10000
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch":
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss": 1.
|
| 143 |
"step": 10500
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 11000
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 1.
|
| 153 |
-
"
|
| 154 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 155 |
"step": 11500
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch": 1.
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 1.
|
| 161 |
"step": 12000
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 1.
|
| 165 |
-
"learning_rate":
|
| 166 |
-
"loss": 1.
|
| 167 |
"step": 12500
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 1.
|
| 171 |
-
"learning_rate":
|
| 172 |
-
"loss": 1.
|
| 173 |
"step": 13000
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 1.
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 1.
|
| 179 |
"step": 13500
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 1.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss": 1.
|
| 185 |
"step": 14000
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 1.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 1.
|
| 191 |
"step": 14500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 1.
|
| 195 |
-
"learning_rate":
|
| 196 |
-
"loss": 1.
|
| 197 |
"step": 15000
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch": 1.
|
| 201 |
-
"learning_rate":
|
| 202 |
-
"loss": 1.
|
| 203 |
"step": 15500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch":
|
| 207 |
-
"learning_rate":
|
| 208 |
-
"loss": 1.
|
| 209 |
"step": 16000
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"eval_samples_per_second": 42.392,
|
| 216 |
-
"eval_steps_per_second": 5.31,
|
| 217 |
-
"step": 16014
|
| 218 |
-
},
|
| 219 |
-
{
|
| 220 |
-
"epoch": 2.06,
|
| 221 |
-
"learning_rate": 8.969651554889472e-06,
|
| 222 |
-
"loss": 1.8129,
|
| 223 |
"step": 16500
|
| 224 |
},
|
| 225 |
{
|
| 226 |
-
"epoch":
|
| 227 |
-
"learning_rate": 8.
|
| 228 |
-
"loss": 1.
|
| 229 |
"step": 17000
|
| 230 |
},
|
| 231 |
{
|
| 232 |
-
"epoch":
|
| 233 |
-
"learning_rate": 8.
|
| 234 |
-
"loss": 1.
|
| 235 |
"step": 17500
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch":
|
| 239 |
-
"learning_rate": 8.
|
| 240 |
-
"loss": 1.
|
| 241 |
"step": 18000
|
| 242 |
},
|
| 243 |
{
|
| 244 |
-
"epoch":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 1.
|
| 247 |
"step": 18500
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"learning_rate":
|
| 252 |
-
"loss": 1.
|
| 253 |
"step": 19000
|
| 254 |
},
|
| 255 |
{
|
| 256 |
-
"epoch":
|
| 257 |
-
"learning_rate":
|
| 258 |
-
"loss": 1.
|
| 259 |
"step": 19500
|
| 260 |
},
|
| 261 |
{
|
| 262 |
-
"epoch":
|
| 263 |
-
"learning_rate":
|
| 264 |
-
"loss": 1.
|
| 265 |
"step": 20000
|
| 266 |
},
|
| 267 |
{
|
| 268 |
-
"epoch":
|
| 269 |
-
"learning_rate":
|
| 270 |
-
"loss": 1.
|
| 271 |
"step": 20500
|
| 272 |
},
|
| 273 |
{
|
| 274 |
-
"epoch":
|
| 275 |
-
"learning_rate":
|
| 276 |
-
"loss": 1.
|
| 277 |
"step": 21000
|
| 278 |
},
|
| 279 |
{
|
| 280 |
-
"epoch":
|
| 281 |
-
"learning_rate":
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 21500
|
| 284 |
},
|
| 285 |
{
|
| 286 |
-
"epoch":
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 1.
|
| 289 |
"step": 22000
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"learning_rate":
|
| 294 |
-
"loss": 1.
|
| 295 |
"step": 22500
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 2.
|
| 299 |
-
"
|
| 300 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 301 |
"step": 23000
|
| 302 |
},
|
| 303 |
{
|
| 304 |
-
"epoch": 2.
|
| 305 |
-
"learning_rate":
|
| 306 |
-
"loss": 1.
|
| 307 |
"step": 23500
|
| 308 |
},
|
| 309 |
{
|
| 310 |
-
"epoch":
|
| 311 |
-
"learning_rate":
|
| 312 |
-
"loss": 1.
|
| 313 |
"step": 24000
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch":
|
| 317 |
-
"
|
| 318 |
-
"
|
| 319 |
-
"eval_samples_per_second": 42.374,
|
| 320 |
-
"eval_steps_per_second": 5.308,
|
| 321 |
-
"step": 24021
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 3.06,
|
| 325 |
-
"learning_rate": 8.470088672411641e-06,
|
| 326 |
-
"loss": 1.7503,
|
| 327 |
"step": 24500
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch":
|
| 331 |
-
"learning_rate":
|
| 332 |
-
"loss": 1.
|
| 333 |
"step": 25000
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch":
|
| 337 |
-
"learning_rate":
|
| 338 |
-
"loss": 1.
|
| 339 |
"step": 25500
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch":
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 1.
|
| 345 |
"step": 26000
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 1.
|
| 351 |
"step": 26500
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss": 1.
|
| 357 |
"step": 27000
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"learning_rate":
|
| 362 |
-
"loss": 1.
|
| 363 |
"step": 27500
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch":
|
| 367 |
-
"learning_rate":
|
| 368 |
-
"loss": 1.
|
| 369 |
"step": 28000
|
| 370 |
},
|
| 371 |
{
|
| 372 |
-
"epoch":
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss": 1.
|
| 375 |
"step": 28500
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 1.
|
| 381 |
"step": 29000
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch":
|
| 385 |
-
"learning_rate":
|
| 386 |
-
"loss": 1.
|
| 387 |
"step": 29500
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch":
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"loss": 1.
|
| 393 |
"step": 30000
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch":
|
| 397 |
-
"learning_rate":
|
| 398 |
-
"loss": 1.
|
| 399 |
"step": 30500
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch":
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 1.
|
| 405 |
"step": 31000
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch":
|
| 409 |
-
"learning_rate":
|
| 410 |
-
"loss": 1.
|
| 411 |
"step": 31500
|
| 412 |
},
|
| 413 |
{
|
| 414 |
-
"epoch":
|
| 415 |
-
"learning_rate":
|
| 416 |
-
"loss": 1.
|
| 417 |
"step": 32000
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch":
|
| 421 |
-
"
|
| 422 |
-
"
|
| 423 |
-
"eval_samples_per_second": 42.38,
|
| 424 |
-
"eval_steps_per_second": 5.309,
|
| 425 |
-
"step": 32028
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 4.06,
|
| 429 |
-
"learning_rate": 7.970525789933809e-06,
|
| 430 |
-
"loss": 1.6913,
|
| 431 |
"step": 32500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
-
"epoch":
|
| 435 |
-
"learning_rate":
|
| 436 |
-
"loss": 1.
|
| 437 |
"step": 33000
|
| 438 |
},
|
| 439 |
{
|
| 440 |
-
"epoch":
|
| 441 |
-
"learning_rate":
|
| 442 |
-
"loss": 1.
|
| 443 |
"step": 33500
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch":
|
| 447 |
-
"learning_rate":
|
| 448 |
-
"loss": 1.
|
| 449 |
"step": 34000
|
| 450 |
},
|
| 451 |
{
|
| 452 |
-
"epoch":
|
| 453 |
-
"
|
| 454 |
-
"
|
| 455 |
-
"
|
| 456 |
-
|
| 457 |
-
|
| 458 |
-
"epoch": 4.37,
|
| 459 |
-
"learning_rate": 7.814412389159486e-06,
|
| 460 |
-
"loss": 1.6834,
|
| 461 |
-
"step": 35000
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 4.43,
|
| 465 |
-
"learning_rate": 7.783189709004622e-06,
|
| 466 |
-
"loss": 1.6717,
|
| 467 |
-
"step": 35500
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 4.5,
|
| 471 |
-
"learning_rate": 7.751967028849757e-06,
|
| 472 |
-
"loss": 1.6712,
|
| 473 |
-
"step": 36000
|
| 474 |
-
},
|
| 475 |
-
{
|
| 476 |
-
"epoch": 4.56,
|
| 477 |
-
"learning_rate": 7.720744348694893e-06,
|
| 478 |
-
"loss": 1.6873,
|
| 479 |
-
"step": 36500
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 4.62,
|
| 483 |
-
"learning_rate": 7.689521668540028e-06,
|
| 484 |
-
"loss": 1.6688,
|
| 485 |
-
"step": 37000
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 4.68,
|
| 489 |
-
"learning_rate": 7.658298988385164e-06,
|
| 490 |
-
"loss": 1.6589,
|
| 491 |
-
"step": 37500
|
| 492 |
-
},
|
| 493 |
-
{
|
| 494 |
-
"epoch": 4.75,
|
| 495 |
-
"learning_rate": 7.627076308230299e-06,
|
| 496 |
-
"loss": 1.6668,
|
| 497 |
-
"step": 38000
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 4.81,
|
| 501 |
-
"learning_rate": 7.5958536280754345e-06,
|
| 502 |
-
"loss": 1.6665,
|
| 503 |
-
"step": 38500
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 4.87,
|
| 507 |
-
"learning_rate": 7.564630947920571e-06,
|
| 508 |
-
"loss": 1.6679,
|
| 509 |
-
"step": 39000
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 4.93,
|
| 513 |
-
"learning_rate": 7.533408267765706e-06,
|
| 514 |
-
"loss": 1.6624,
|
| 515 |
-
"step": 39500
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 5.0,
|
| 519 |
-
"learning_rate": 7.502185587610841e-06,
|
| 520 |
-
"loss": 1.6621,
|
| 521 |
-
"step": 40000
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 5.0,
|
| 525 |
-
"eval_loss": 1.6710957288742065,
|
| 526 |
-
"eval_runtime": 33.5526,
|
| 527 |
-
"eval_samples_per_second": 42.351,
|
| 528 |
-
"eval_steps_per_second": 5.305,
|
| 529 |
-
"step": 40035
|
| 530 |
-
},
|
| 531 |
-
{
|
| 532 |
-
"epoch": 5.06,
|
| 533 |
-
"learning_rate": 7.470962907455977e-06,
|
| 534 |
-
"loss": 1.6497,
|
| 535 |
-
"step": 40500
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 5.12,
|
| 539 |
-
"learning_rate": 7.439740227301112e-06,
|
| 540 |
-
"loss": 1.6487,
|
| 541 |
-
"step": 41000
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 5.18,
|
| 545 |
-
"learning_rate": 7.4085175471462475e-06,
|
| 546 |
-
"loss": 1.6439,
|
| 547 |
-
"step": 41500
|
| 548 |
-
},
|
| 549 |
-
{
|
| 550 |
-
"epoch": 5.25,
|
| 551 |
-
"learning_rate": 7.377294866991384e-06,
|
| 552 |
-
"loss": 1.6552,
|
| 553 |
-
"step": 42000
|
| 554 |
-
},
|
| 555 |
-
{
|
| 556 |
-
"epoch": 5.31,
|
| 557 |
-
"learning_rate": 7.346072186836518e-06,
|
| 558 |
-
"loss": 1.6473,
|
| 559 |
-
"step": 42500
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 5.37,
|
| 563 |
-
"learning_rate": 7.314849506681654e-06,
|
| 564 |
-
"loss": 1.6447,
|
| 565 |
-
"step": 43000
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"epoch": 5.43,
|
| 569 |
-
"learning_rate": 7.28362682652679e-06,
|
| 570 |
-
"loss": 1.6463,
|
| 571 |
-
"step": 43500
|
| 572 |
-
},
|
| 573 |
-
{
|
| 574 |
-
"epoch": 5.5,
|
| 575 |
-
"learning_rate": 7.252404146371925e-06,
|
| 576 |
-
"loss": 1.6493,
|
| 577 |
-
"step": 44000
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 5.56,
|
| 581 |
-
"learning_rate": 7.2211814662170606e-06,
|
| 582 |
-
"loss": 1.6433,
|
| 583 |
-
"step": 44500
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 5.62,
|
| 587 |
-
"learning_rate": 7.189958786062197e-06,
|
| 588 |
-
"loss": 1.6483,
|
| 589 |
-
"step": 45000
|
| 590 |
-
},
|
| 591 |
-
{
|
| 592 |
-
"epoch": 5.68,
|
| 593 |
-
"learning_rate": 7.158736105907331e-06,
|
| 594 |
-
"loss": 1.6347,
|
| 595 |
-
"step": 45500
|
| 596 |
-
},
|
| 597 |
-
{
|
| 598 |
-
"epoch": 5.74,
|
| 599 |
-
"learning_rate": 7.127513425752467e-06,
|
| 600 |
-
"loss": 1.6363,
|
| 601 |
-
"step": 46000
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 5.81,
|
| 605 |
-
"learning_rate": 7.096290745597603e-06,
|
| 606 |
-
"loss": 1.6284,
|
| 607 |
-
"step": 46500
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 5.87,
|
| 611 |
-
"learning_rate": 7.065068065442738e-06,
|
| 612 |
-
"loss": 1.6268,
|
| 613 |
-
"step": 47000
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"epoch": 5.93,
|
| 617 |
-
"learning_rate": 7.033845385287874e-06,
|
| 618 |
-
"loss": 1.633,
|
| 619 |
-
"step": 47500
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 5.99,
|
| 623 |
-
"learning_rate": 7.002622705133009e-06,
|
| 624 |
-
"loss": 1.6313,
|
| 625 |
-
"step": 48000
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 6.0,
|
| 629 |
-
"eval_loss": 1.644548773765564,
|
| 630 |
-
"eval_runtime": 33.5436,
|
| 631 |
-
"eval_samples_per_second": 42.363,
|
| 632 |
-
"eval_steps_per_second": 5.307,
|
| 633 |
-
"step": 48042
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 6.06,
|
| 637 |
-
"learning_rate": 6.971400024978144e-06,
|
| 638 |
-
"loss": 1.628,
|
| 639 |
-
"step": 48500
|
| 640 |
-
},
|
| 641 |
-
{
|
| 642 |
-
"epoch": 6.12,
|
| 643 |
-
"learning_rate": 6.9401773448232805e-06,
|
| 644 |
-
"loss": 1.6263,
|
| 645 |
-
"step": 49000
|
| 646 |
-
},
|
| 647 |
-
{
|
| 648 |
-
"epoch": 6.18,
|
| 649 |
-
"learning_rate": 6.908954664668416e-06,
|
| 650 |
-
"loss": 1.6154,
|
| 651 |
-
"step": 49500
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 6.24,
|
| 655 |
-
"learning_rate": 6.877731984513551e-06,
|
| 656 |
-
"loss": 1.6141,
|
| 657 |
-
"step": 50000
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 6.31,
|
| 661 |
-
"learning_rate": 6.846509304358687e-06,
|
| 662 |
-
"loss": 1.6198,
|
| 663 |
-
"step": 50500
|
| 664 |
-
},
|
| 665 |
-
{
|
| 666 |
-
"epoch": 6.37,
|
| 667 |
-
"learning_rate": 6.815286624203822e-06,
|
| 668 |
-
"loss": 1.6131,
|
| 669 |
-
"step": 51000
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 6.43,
|
| 673 |
-
"learning_rate": 6.784063944048957e-06,
|
| 674 |
-
"loss": 1.6178,
|
| 675 |
-
"step": 51500
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 6.49,
|
| 679 |
-
"learning_rate": 6.7528412638940935e-06,
|
| 680 |
-
"loss": 1.6108,
|
| 681 |
-
"step": 52000
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 6.56,
|
| 685 |
-
"learning_rate": 6.721618583739229e-06,
|
| 686 |
-
"loss": 1.619,
|
| 687 |
-
"step": 52500
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 6.62,
|
| 691 |
-
"learning_rate": 6.690395903584364e-06,
|
| 692 |
-
"loss": 1.6167,
|
| 693 |
-
"step": 53000
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"epoch": 6.68,
|
| 697 |
-
"learning_rate": 6.6591732234294996e-06,
|
| 698 |
-
"loss": 1.6051,
|
| 699 |
-
"step": 53500
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 6.74,
|
| 703 |
-
"learning_rate": 6.627950543274635e-06,
|
| 704 |
-
"loss": 1.6156,
|
| 705 |
-
"step": 54000
|
| 706 |
-
},
|
| 707 |
-
{
|
| 708 |
-
"epoch": 6.81,
|
| 709 |
-
"learning_rate": 6.59672786311977e-06,
|
| 710 |
-
"loss": 1.6155,
|
| 711 |
-
"step": 54500
|
| 712 |
-
},
|
| 713 |
-
{
|
| 714 |
-
"epoch": 6.87,
|
| 715 |
-
"learning_rate": 6.5655051829649065e-06,
|
| 716 |
-
"loss": 1.6074,
|
| 717 |
-
"step": 55000
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 6.93,
|
| 721 |
-
"learning_rate": 6.534282502810042e-06,
|
| 722 |
-
"loss": 1.6082,
|
| 723 |
-
"step": 55500
|
| 724 |
-
},
|
| 725 |
-
{
|
| 726 |
-
"epoch": 6.99,
|
| 727 |
-
"learning_rate": 6.503059822655178e-06,
|
| 728 |
-
"loss": 1.6009,
|
| 729 |
-
"step": 56000
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 7.0,
|
| 733 |
-
"eval_loss": 1.6238889694213867,
|
| 734 |
-
"eval_runtime": 33.6415,
|
| 735 |
-
"eval_samples_per_second": 42.24,
|
| 736 |
-
"eval_steps_per_second": 5.291,
|
| 737 |
-
"step": 56049
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 7.06,
|
| 741 |
-
"learning_rate": 6.471837142500313e-06,
|
| 742 |
-
"loss": 1.6086,
|
| 743 |
-
"step": 56500
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 7.12,
|
| 747 |
-
"learning_rate": 6.440614462345448e-06,
|
| 748 |
-
"loss": 1.597,
|
| 749 |
-
"step": 57000
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 7.18,
|
| 753 |
-
"learning_rate": 6.409391782190584e-06,
|
| 754 |
-
"loss": 1.5983,
|
| 755 |
-
"step": 57500
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 7.24,
|
| 759 |
-
"learning_rate": 6.3781691020357195e-06,
|
| 760 |
-
"loss": 1.6085,
|
| 761 |
-
"step": 58000
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 7.31,
|
| 765 |
-
"learning_rate": 6.346946421880855e-06,
|
| 766 |
-
"loss": 1.5866,
|
| 767 |
-
"step": 58500
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 7.37,
|
| 771 |
-
"learning_rate": 6.315723741725989e-06,
|
| 772 |
-
"loss": 1.5995,
|
| 773 |
-
"step": 59000
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 7.43,
|
| 777 |
-
"learning_rate": 6.284501061571126e-06,
|
| 778 |
-
"loss": 1.5943,
|
| 779 |
-
"step": 59500
|
| 780 |
-
},
|
| 781 |
-
{
|
| 782 |
-
"epoch": 7.49,
|
| 783 |
-
"learning_rate": 6.253278381416261e-06,
|
| 784 |
-
"loss": 1.5994,
|
| 785 |
-
"step": 60000
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 7.56,
|
| 789 |
-
"learning_rate": 6.222055701261397e-06,
|
| 790 |
-
"loss": 1.5913,
|
| 791 |
-
"step": 60500
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 7.62,
|
| 795 |
-
"learning_rate": 6.1908330211065325e-06,
|
| 796 |
-
"loss": 1.6005,
|
| 797 |
-
"step": 61000
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 7.68,
|
| 801 |
-
"learning_rate": 6.159610340951669e-06,
|
| 802 |
-
"loss": 1.5857,
|
| 803 |
-
"step": 61500
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 7.74,
|
| 807 |
-
"learning_rate": 6.128387660796803e-06,
|
| 808 |
-
"loss": 1.5808,
|
| 809 |
-
"step": 62000
|
| 810 |
-
},
|
| 811 |
-
{
|
| 812 |
-
"epoch": 7.81,
|
| 813 |
-
"learning_rate": 6.097164980641939e-06,
|
| 814 |
-
"loss": 1.582,
|
| 815 |
-
"step": 62500
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 7.87,
|
| 819 |
-
"learning_rate": 6.065942300487074e-06,
|
| 820 |
-
"loss": 1.587,
|
| 821 |
-
"step": 63000
|
| 822 |
-
},
|
| 823 |
-
{
|
| 824 |
-
"epoch": 7.93,
|
| 825 |
-
"learning_rate": 6.03471962033221e-06,
|
| 826 |
-
"loss": 1.5858,
|
| 827 |
-
"step": 63500
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 7.99,
|
| 831 |
-
"learning_rate": 6.0034969401773455e-06,
|
| 832 |
-
"loss": 1.5835,
|
| 833 |
-
"step": 64000
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 8.0,
|
| 837 |
-
"eval_loss": 1.6067923307418823,
|
| 838 |
-
"eval_runtime": 33.5833,
|
| 839 |
-
"eval_samples_per_second": 42.313,
|
| 840 |
-
"eval_steps_per_second": 5.3,
|
| 841 |
-
"step": 64056
|
| 842 |
}
|
| 843 |
],
|
| 844 |
"logging_steps": 500,
|
| 845 |
-
"max_steps":
|
| 846 |
-
"num_train_epochs":
|
| 847 |
"save_steps": 500,
|
| 848 |
-
"total_flos":
|
| 849 |
"trial_name": null,
|
| 850 |
"trial_params": null
|
| 851 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 34431,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 9.945543260433913e-06,
|
| 14 |
+
"loss": 3.7697,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 9.891086520867823e-06,
|
| 20 |
+
"loss": 2.9544,
|
| 21 |
"step": 1000
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.13,
|
| 25 |
+
"learning_rate": 9.836629781301735e-06,
|
| 26 |
+
"loss": 2.4309,
|
| 27 |
"step": 1500
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.17,
|
| 31 |
+
"learning_rate": 9.782173041735646e-06,
|
| 32 |
+
"loss": 2.1416,
|
| 33 |
"step": 2000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.22,
|
| 37 |
+
"learning_rate": 9.727716302169558e-06,
|
| 38 |
+
"loss": 2.0346,
|
| 39 |
"step": 2500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.26,
|
| 43 |
+
"learning_rate": 9.673259562603468e-06,
|
| 44 |
+
"loss": 1.9859,
|
| 45 |
"step": 3000
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.3,
|
| 49 |
+
"learning_rate": 9.61880282303738e-06,
|
| 50 |
+
"loss": 1.9512,
|
| 51 |
"step": 3500
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"learning_rate": 9.56434608347129e-06,
|
| 56 |
+
"loss": 1.9171,
|
| 57 |
"step": 4000
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.39,
|
| 61 |
+
"learning_rate": 9.509889343905202e-06,
|
| 62 |
+
"loss": 1.8989,
|
| 63 |
"step": 4500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.44,
|
| 67 |
+
"learning_rate": 9.455432604339114e-06,
|
| 68 |
+
"loss": 1.868,
|
| 69 |
"step": 5000
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.48,
|
| 73 |
+
"learning_rate": 9.400975864773026e-06,
|
| 74 |
+
"loss": 1.8423,
|
| 75 |
"step": 5500
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.52,
|
| 79 |
+
"learning_rate": 9.346519125206936e-06,
|
| 80 |
+
"loss": 1.8311,
|
| 81 |
"step": 6000
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.57,
|
| 85 |
+
"learning_rate": 9.292062385640848e-06,
|
| 86 |
+
"loss": 1.8139,
|
| 87 |
"step": 6500
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.61,
|
| 91 |
+
"learning_rate": 9.237605646074758e-06,
|
| 92 |
+
"loss": 1.809,
|
| 93 |
"step": 7000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"learning_rate": 9.18314890650867e-06,
|
| 98 |
+
"loss": 1.7932,
|
| 99 |
"step": 7500
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.7,
|
| 103 |
+
"learning_rate": 9.128692166942582e-06,
|
| 104 |
+
"loss": 1.7807,
|
| 105 |
"step": 8000
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.74,
|
| 109 |
+
"learning_rate": 9.074235427376494e-06,
|
| 110 |
+
"loss": 1.7729,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
"step": 8500
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.78,
|
| 115 |
+
"learning_rate": 9.019778687810404e-06,
|
| 116 |
+
"loss": 1.7695,
|
| 117 |
"step": 9000
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.83,
|
| 121 |
+
"learning_rate": 8.965321948244316e-06,
|
| 122 |
+
"loss": 1.7464,
|
| 123 |
"step": 9500
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.87,
|
| 127 |
+
"learning_rate": 8.910865208678226e-06,
|
| 128 |
+
"loss": 1.7436,
|
| 129 |
"step": 10000
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.91,
|
| 133 |
+
"learning_rate": 8.856408469112138e-06,
|
| 134 |
+
"loss": 1.736,
|
| 135 |
"step": 10500
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.96,
|
| 139 |
+
"learning_rate": 8.80195172954605e-06,
|
| 140 |
+
"loss": 1.729,
|
| 141 |
"step": 11000
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 1.0,
|
| 145 |
+
"eval_loss": 1.7001079320907593,
|
| 146 |
+
"eval_runtime": 3.4215,
|
| 147 |
+
"eval_samples_per_second": 39.748,
|
| 148 |
+
"eval_steps_per_second": 4.969,
|
| 149 |
+
"step": 11477
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"learning_rate": 8.747494989979961e-06,
|
| 154 |
+
"loss": 1.7264,
|
| 155 |
"step": 11500
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 1.05,
|
| 159 |
+
"learning_rate": 8.693038250413871e-06,
|
| 160 |
+
"loss": 1.708,
|
| 161 |
"step": 12000
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 1.09,
|
| 165 |
+
"learning_rate": 8.638581510847783e-06,
|
| 166 |
+
"loss": 1.6948,
|
| 167 |
"step": 12500
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 1.13,
|
| 171 |
+
"learning_rate": 8.584124771281695e-06,
|
| 172 |
+
"loss": 1.698,
|
| 173 |
"step": 13000
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 1.18,
|
| 177 |
+
"learning_rate": 8.529668031715605e-06,
|
| 178 |
+
"loss": 1.692,
|
| 179 |
"step": 13500
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 1.22,
|
| 183 |
+
"learning_rate": 8.475211292149517e-06,
|
| 184 |
+
"loss": 1.684,
|
| 185 |
"step": 14000
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 1.26,
|
| 189 |
+
"learning_rate": 8.420754552583429e-06,
|
| 190 |
+
"loss": 1.6879,
|
| 191 |
"step": 14500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 1.31,
|
| 195 |
+
"learning_rate": 8.36629781301734e-06,
|
| 196 |
+
"loss": 1.6804,
|
| 197 |
"step": 15000
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 1.35,
|
| 201 |
+
"learning_rate": 8.311841073451251e-06,
|
| 202 |
+
"loss": 1.6713,
|
| 203 |
"step": 15500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 1.39,
|
| 207 |
+
"learning_rate": 8.257384333885163e-06,
|
| 208 |
+
"loss": 1.6703,
|
| 209 |
"step": 16000
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 1.44,
|
| 213 |
+
"learning_rate": 8.202927594319073e-06,
|
| 214 |
+
"loss": 1.6646,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 215 |
"step": 16500
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 1.48,
|
| 219 |
+
"learning_rate": 8.148470854752985e-06,
|
| 220 |
+
"loss": 1.651,
|
| 221 |
"step": 17000
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 1.52,
|
| 225 |
+
"learning_rate": 8.094014115186897e-06,
|
| 226 |
+
"loss": 1.6488,
|
| 227 |
"step": 17500
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 1.57,
|
| 231 |
+
"learning_rate": 8.039557375620808e-06,
|
| 232 |
+
"loss": 1.6452,
|
| 233 |
"step": 18000
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 1.61,
|
| 237 |
+
"learning_rate": 7.985100636054719e-06,
|
| 238 |
+
"loss": 1.6386,
|
| 239 |
"step": 18500
|
| 240 |
},
|
| 241 |
{
|
| 242 |
+
"epoch": 1.66,
|
| 243 |
+
"learning_rate": 7.93064389648863e-06,
|
| 244 |
+
"loss": 1.6349,
|
| 245 |
"step": 19000
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 1.7,
|
| 249 |
+
"learning_rate": 7.87618715692254e-06,
|
| 250 |
+
"loss": 1.6345,
|
| 251 |
"step": 19500
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 1.74,
|
| 255 |
+
"learning_rate": 7.821730417356452e-06,
|
| 256 |
+
"loss": 1.6294,
|
| 257 |
"step": 20000
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 1.79,
|
| 261 |
+
"learning_rate": 7.767273677790364e-06,
|
| 262 |
+
"loss": 1.631,
|
| 263 |
"step": 20500
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 1.83,
|
| 267 |
+
"learning_rate": 7.712816938224276e-06,
|
| 268 |
+
"loss": 1.6261,
|
| 269 |
"step": 21000
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 1.87,
|
| 273 |
+
"learning_rate": 7.658360198658186e-06,
|
| 274 |
+
"loss": 1.6281,
|
| 275 |
"step": 21500
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 1.92,
|
| 279 |
+
"learning_rate": 7.603903459092098e-06,
|
| 280 |
+
"loss": 1.611,
|
| 281 |
"step": 22000
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 1.96,
|
| 285 |
+
"learning_rate": 7.549446719526009e-06,
|
| 286 |
+
"loss": 1.6155,
|
| 287 |
"step": 22500
|
| 288 |
},
|
| 289 |
{
|
| 290 |
+
"epoch": 2.0,
|
| 291 |
+
"eval_loss": 1.596663475036621,
|
| 292 |
+
"eval_runtime": 3.4296,
|
| 293 |
+
"eval_samples_per_second": 39.655,
|
| 294 |
+
"eval_steps_per_second": 4.957,
|
| 295 |
+
"step": 22954
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.0,
|
| 299 |
+
"learning_rate": 7.49498997995992e-06,
|
| 300 |
+
"loss": 1.6029,
|
| 301 |
"step": 23000
|
| 302 |
},
|
| 303 |
{
|
| 304 |
+
"epoch": 2.05,
|
| 305 |
+
"learning_rate": 7.440533240393831e-06,
|
| 306 |
+
"loss": 1.607,
|
| 307 |
"step": 23500
|
| 308 |
},
|
| 309 |
{
|
| 310 |
+
"epoch": 2.09,
|
| 311 |
+
"learning_rate": 7.386076500827744e-06,
|
| 312 |
+
"loss": 1.5977,
|
| 313 |
"step": 24000
|
| 314 |
},
|
| 315 |
{
|
| 316 |
+
"epoch": 2.13,
|
| 317 |
+
"learning_rate": 7.331619761261655e-06,
|
| 318 |
+
"loss": 1.5922,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 319 |
"step": 24500
|
| 320 |
},
|
| 321 |
{
|
| 322 |
+
"epoch": 2.18,
|
| 323 |
+
"learning_rate": 7.277163021695566e-06,
|
| 324 |
+
"loss": 1.5956,
|
| 325 |
"step": 25000
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 2.22,
|
| 329 |
+
"learning_rate": 7.222706282129477e-06,
|
| 330 |
+
"loss": 1.5855,
|
| 331 |
"step": 25500
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 2.27,
|
| 335 |
+
"learning_rate": 7.168249542563388e-06,
|
| 336 |
+
"loss": 1.5826,
|
| 337 |
"step": 26000
|
| 338 |
},
|
| 339 |
{
|
| 340 |
+
"epoch": 2.31,
|
| 341 |
+
"learning_rate": 7.1137928029972995e-06,
|
| 342 |
+
"loss": 1.5846,
|
| 343 |
"step": 26500
|
| 344 |
},
|
| 345 |
{
|
| 346 |
+
"epoch": 2.35,
|
| 347 |
+
"learning_rate": 7.059336063431211e-06,
|
| 348 |
+
"loss": 1.5899,
|
| 349 |
"step": 27000
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 2.4,
|
| 353 |
+
"learning_rate": 7.004879323865122e-06,
|
| 354 |
+
"loss": 1.5828,
|
| 355 |
"step": 27500
|
| 356 |
},
|
| 357 |
{
|
| 358 |
+
"epoch": 2.44,
|
| 359 |
+
"learning_rate": 6.950422584299033e-06,
|
| 360 |
+
"loss": 1.5762,
|
| 361 |
"step": 28000
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 2.48,
|
| 365 |
+
"learning_rate": 6.895965844732945e-06,
|
| 366 |
+
"loss": 1.5739,
|
| 367 |
"step": 28500
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 2.53,
|
| 371 |
+
"learning_rate": 6.841509105166856e-06,
|
| 372 |
+
"loss": 1.574,
|
| 373 |
"step": 29000
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 2.57,
|
| 377 |
+
"learning_rate": 6.787052365600767e-06,
|
| 378 |
+
"loss": 1.5759,
|
| 379 |
"step": 29500
|
| 380 |
},
|
| 381 |
{
|
| 382 |
+
"epoch": 2.61,
|
| 383 |
+
"learning_rate": 6.732595626034678e-06,
|
| 384 |
+
"loss": 1.5737,
|
| 385 |
"step": 30000
|
| 386 |
},
|
| 387 |
{
|
| 388 |
+
"epoch": 2.66,
|
| 389 |
+
"learning_rate": 6.67813888646859e-06,
|
| 390 |
+
"loss": 1.5637,
|
| 391 |
"step": 30500
|
| 392 |
},
|
| 393 |
{
|
| 394 |
+
"epoch": 2.7,
|
| 395 |
+
"learning_rate": 6.623682146902502e-06,
|
| 396 |
+
"loss": 1.5635,
|
| 397 |
"step": 31000
|
| 398 |
},
|
| 399 |
{
|
| 400 |
+
"epoch": 2.74,
|
| 401 |
+
"learning_rate": 6.569225407336413e-06,
|
| 402 |
+
"loss": 1.5641,
|
| 403 |
"step": 31500
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 2.79,
|
| 407 |
+
"learning_rate": 6.514768667770324e-06,
|
| 408 |
+
"loss": 1.553,
|
| 409 |
"step": 32000
|
| 410 |
},
|
| 411 |
{
|
| 412 |
+
"epoch": 2.83,
|
| 413 |
+
"learning_rate": 6.460311928204235e-06,
|
| 414 |
+
"loss": 1.5699,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 415 |
"step": 32500
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 2.88,
|
| 419 |
+
"learning_rate": 6.405855188638146e-06,
|
| 420 |
+
"loss": 1.5695,
|
| 421 |
"step": 33000
|
| 422 |
},
|
| 423 |
{
|
| 424 |
+
"epoch": 2.92,
|
| 425 |
+
"learning_rate": 6.3513984490720584e-06,
|
| 426 |
+
"loss": 1.5665,
|
| 427 |
"step": 33500
|
| 428 |
},
|
| 429 |
{
|
| 430 |
+
"epoch": 2.96,
|
| 431 |
+
"learning_rate": 6.296941709505969e-06,
|
| 432 |
+
"loss": 1.5527,
|
| 433 |
"step": 34000
|
| 434 |
},
|
| 435 |
{
|
| 436 |
+
"epoch": 3.0,
|
| 437 |
+
"eval_loss": 1.5436657667160034,
|
| 438 |
+
"eval_runtime": 3.2624,
|
| 439 |
+
"eval_samples_per_second": 41.687,
|
| 440 |
+
"eval_steps_per_second": 5.211,
|
| 441 |
+
"step": 34431
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 442 |
}
|
| 443 |
],
|
| 444 |
"logging_steps": 500,
|
| 445 |
+
"max_steps": 91816,
|
| 446 |
+
"num_train_epochs": 8,
|
| 447 |
"save_steps": 500,
|
| 448 |
+
"total_flos": 5.397574828032e+16,
|
| 449 |
"trial_name": null,
|
| 450 |
"trial_params": null
|
| 451 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed2cc3807546f2cb55ecbce521c3690c744d9469e27b3404476816476ca082c6
|
| 3 |
size 4027
|