Training in progress, step 76, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598799664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5184a9f855392b369617a571c4fe8c407c7dbd8eba55d46eea4846faa6eef1da
|
| 3 |
size 598799664
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42898516
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:123b917ce2349c1a74d8844eac29f8c6cf2dc99b9a864c096be4ff65462b6328
|
| 3 |
size 42898516
|
last-checkpoint/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 sha256:51a053afc2b69b6892ee05d33f3fb3716eac75fd7fbab8c36a6324da423adb8d
|
| 3 |
size 14244
|
last-checkpoint/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:dc8e5f98da37dd5d6e76ad1dcd9560295d5ddc12e8c320cbe967800911c3d6c0
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 38,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -289,6 +289,280 @@
|
|
| 289 |
"eval_samples_per_second": 7.503,
|
| 290 |
"eval_steps_per_second": 3.751,
|
| 291 |
"step": 38
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 292 |
}
|
| 293 |
],
|
| 294 |
"logging_steps": 1,
|
|
@@ -308,7 +582,7 @@
|
|
| 308 |
"attributes": {}
|
| 309 |
}
|
| 310 |
},
|
| 311 |
-
"total_flos":
|
| 312 |
"train_batch_size": 2,
|
| 313 |
"trial_name": null,
|
| 314 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0708955223880597,
|
| 5 |
"eval_steps": 38,
|
| 6 |
+
"global_step": 76,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 289 |
"eval_samples_per_second": 7.503,
|
| 290 |
"eval_steps_per_second": 3.751,
|
| 291 |
"step": 38
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.036380597014925374,
|
| 295 |
+
"grad_norm": 1.4865802526474,
|
| 296 |
+
"learning_rate": 0.00035912490977635625,
|
| 297 |
+
"loss": 2.2656,
|
| 298 |
+
"step": 39
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.03731343283582089,
|
| 302 |
+
"grad_norm": 1.3488837480545044,
|
| 303 |
+
"learning_rate": 0.000356366296493606,
|
| 304 |
+
"loss": 1.9688,
|
| 305 |
+
"step": 40
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.03824626865671642,
|
| 309 |
+
"grad_norm": 1.4332904815673828,
|
| 310 |
+
"learning_rate": 0.0003535289480716022,
|
| 311 |
+
"loss": 2.2615,
|
| 312 |
+
"step": 41
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.03917910447761194,
|
| 316 |
+
"grad_norm": 1.516402006149292,
|
| 317 |
+
"learning_rate": 0.00035061429320072223,
|
| 318 |
+
"loss": 2.059,
|
| 319 |
+
"step": 42
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.04011194029850746,
|
| 323 |
+
"grad_norm": 1.4039419889450073,
|
| 324 |
+
"learning_rate": 0.00034762379949746815,
|
| 325 |
+
"loss": 2.1295,
|
| 326 |
+
"step": 43
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.041044776119402986,
|
| 330 |
+
"grad_norm": 1.2742645740509033,
|
| 331 |
+
"learning_rate": 0.0003445589727654783,
|
| 332 |
+
"loss": 2.1964,
|
| 333 |
+
"step": 44
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.04197761194029851,
|
| 337 |
+
"grad_norm": 1.115033507347107,
|
| 338 |
+
"learning_rate": 0.0003414213562373095,
|
| 339 |
+
"loss": 1.8306,
|
| 340 |
+
"step": 45
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.04291044776119403,
|
| 344 |
+
"grad_norm": 1.1708894968032837,
|
| 345 |
+
"learning_rate": 0.00033821252979737297,
|
| 346 |
+
"loss": 1.9652,
|
| 347 |
+
"step": 46
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.043843283582089554,
|
| 351 |
+
"grad_norm": 1.185393214225769,
|
| 352 |
+
"learning_rate": 0.0003349341091864149,
|
| 353 |
+
"loss": 1.8172,
|
| 354 |
+
"step": 47
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.04477611940298507,
|
| 358 |
+
"grad_norm": 1.1099275350570679,
|
| 359 |
+
"learning_rate": 0.00033158774518794254,
|
| 360 |
+
"loss": 1.7576,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.0457089552238806,
|
| 365 |
+
"grad_norm": 1.0703908205032349,
|
| 366 |
+
"learning_rate": 0.0003281751227970048,
|
| 367 |
+
"loss": 1.9036,
|
| 368 |
+
"step": 49
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.04664179104477612,
|
| 372 |
+
"grad_norm": 1.1421232223510742,
|
| 373 |
+
"learning_rate": 0.00032469796037174674,
|
| 374 |
+
"loss": 1.9759,
|
| 375 |
+
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.04757462686567164,
|
| 379 |
+
"grad_norm": 1.1319009065628052,
|
| 380 |
+
"learning_rate": 0.000321158008768164,
|
| 381 |
+
"loss": 1.7476,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.048507462686567165,
|
| 386 |
+
"grad_norm": 1.1899311542510986,
|
| 387 |
+
"learning_rate": 0.00031755705045849464,
|
| 388 |
+
"loss": 1.8308,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.049440298507462684,
|
| 393 |
+
"grad_norm": 1.246800184249878,
|
| 394 |
+
"learning_rate": 0.0003138968986336904,
|
| 395 |
+
"loss": 1.9183,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.05037313432835821,
|
| 400 |
+
"grad_norm": 1.207138180732727,
|
| 401 |
+
"learning_rate": 0.0003101793962904205,
|
| 402 |
+
"loss": 1.8768,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.051305970149253734,
|
| 407 |
+
"grad_norm": 0.9686072468757629,
|
| 408 |
+
"learning_rate": 0.00030640641530306733,
|
| 409 |
+
"loss": 1.6107,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.05223880597014925,
|
| 414 |
+
"grad_norm": 1.1268424987792969,
|
| 415 |
+
"learning_rate": 0.00030257985548118126,
|
| 416 |
+
"loss": 1.9169,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.05317164179104478,
|
| 421 |
+
"grad_norm": 1.3243463039398193,
|
| 422 |
+
"learning_rate": 0.0002987016436128694,
|
| 423 |
+
"loss": 2.1651,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.054104477611940295,
|
| 428 |
+
"grad_norm": 1.230141043663025,
|
| 429 |
+
"learning_rate": 0.0002947737324945997,
|
| 430 |
+
"loss": 2.0871,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.05503731343283582,
|
| 435 |
+
"grad_norm": 1.0468418598175049,
|
| 436 |
+
"learning_rate": 0.00029079809994790937,
|
| 437 |
+
"loss": 1.7348,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.055970149253731345,
|
| 442 |
+
"grad_norm": 1.3394778966903687,
|
| 443 |
+
"learning_rate": 0.00028677674782351165,
|
| 444 |
+
"loss": 2.3597,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.05690298507462686,
|
| 449 |
+
"grad_norm": 1.2126855850219727,
|
| 450 |
+
"learning_rate": 0.00028271170099330415,
|
| 451 |
+
"loss": 2.0063,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.05783582089552239,
|
| 456 |
+
"grad_norm": 1.2102502584457397,
|
| 457 |
+
"learning_rate": 0.00027860500633078477,
|
| 458 |
+
"loss": 2.0048,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.058768656716417914,
|
| 463 |
+
"grad_norm": 1.2987444400787354,
|
| 464 |
+
"learning_rate": 0.00027445873168038907,
|
| 465 |
+
"loss": 2.6436,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.05970149253731343,
|
| 470 |
+
"grad_norm": 1.1055057048797607,
|
| 471 |
+
"learning_rate": 0.0002702749648162686,
|
| 472 |
+
"loss": 1.8015,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.06063432835820896,
|
| 477 |
+
"grad_norm": 1.1894230842590332,
|
| 478 |
+
"learning_rate": 0.00026605581239103347,
|
| 479 |
+
"loss": 2.0075,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.061567164179104475,
|
| 484 |
+
"grad_norm": 0.9544552564620972,
|
| 485 |
+
"learning_rate": 0.00026180339887498953,
|
| 486 |
+
"loss": 1.5043,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0625,
|
| 491 |
+
"grad_norm": 1.2134445905685425,
|
| 492 |
+
"learning_rate": 0.00025751986548640346,
|
| 493 |
+
"loss": 1.9537,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.06343283582089553,
|
| 498 |
+
"grad_norm": 1.061187505722046,
|
| 499 |
+
"learning_rate": 0.00025320736911333503,
|
| 500 |
+
"loss": 1.6231,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.06436567164179105,
|
| 505 |
+
"grad_norm": 1.1641594171524048,
|
| 506 |
+
"learning_rate": 0.0002488680812275788,
|
| 507 |
+
"loss": 1.6016,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.06529850746268656,
|
| 512 |
+
"grad_norm": 1.1650375127792358,
|
| 513 |
+
"learning_rate": 0.0002445041867912629,
|
| 514 |
+
"loss": 1.8811,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.06623134328358209,
|
| 519 |
+
"grad_norm": 1.319548487663269,
|
| 520 |
+
"learning_rate": 0.00024011788315665458,
|
| 521 |
+
"loss": 1.7969,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.06716417910447761,
|
| 526 |
+
"grad_norm": 1.009516954421997,
|
| 527 |
+
"learning_rate": 0.00023571137895972733,
|
| 528 |
+
"loss": 1.4261,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.06809701492537314,
|
| 533 |
+
"grad_norm": 1.1219674348831177,
|
| 534 |
+
"learning_rate": 0.0002312868930080462,
|
| 535 |
+
"loss": 1.5247,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.06902985074626866,
|
| 540 |
+
"grad_norm": 1.0498907566070557,
|
| 541 |
+
"learning_rate": 0.0002268466531635311,
|
| 542 |
+
"loss": 1.7131,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.06996268656716417,
|
| 547 |
+
"grad_norm": 1.0986140966415405,
|
| 548 |
+
"learning_rate": 0.00022239289522066157,
|
| 549 |
+
"loss": 1.7584,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.0708955223880597,
|
| 554 |
+
"grad_norm": 1.2214365005493164,
|
| 555 |
+
"learning_rate": 0.00021792786178068672,
|
| 556 |
+
"loss": 1.7782,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0708955223880597,
|
| 561 |
+
"eval_loss": 0.47117629647254944,
|
| 562 |
+
"eval_runtime": 60.2201,
|
| 563 |
+
"eval_samples_per_second": 7.506,
|
| 564 |
+
"eval_steps_per_second": 3.753,
|
| 565 |
+
"step": 76
|
| 566 |
}
|
| 567 |
],
|
| 568 |
"logging_steps": 1,
|
|
|
|
| 582 |
"attributes": {}
|
| 583 |
}
|
| 584 |
},
|
| 585 |
+
"total_flos": 9963999823134720.0,
|
| 586 |
"train_batch_size": 2,
|
| 587 |
"trial_name": null,
|
| 588 |
"trial_params": null
|