Training in progress, step 800, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 723674912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfc7459b8070f26a9a864b85343d1738e3d2dcd6020a04f5fb8b9aca1951ffd2
|
| 3 |
size 723674912
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 735625626
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b945b56cf643054d93848122565520049285ab0e46c861ff6ab04f75d42ed166
|
| 3 |
size 735625626
|
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 sha256:3c431bcafebc4c8ee346d130e382b11c81be579ca0bfd3918fae07b16e10b92f
|
| 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 sha256:40b6b717644e21f80a22ec98694b3a2fd9d62a6467e549d64314725dba905d52
|
| 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": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -311,6 +311,302 @@
|
|
| 311 |
"eval_samples_per_second": 63.015,
|
| 312 |
"eval_steps_per_second": 15.775,
|
| 313 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 314 |
}
|
| 315 |
],
|
| 316 |
"logging_steps": 10,
|
|
@@ -330,7 +626,7 @@
|
|
| 330 |
"attributes": {}
|
| 331 |
}
|
| 332 |
},
|
| 333 |
-
"total_flos":
|
| 334 |
"train_batch_size": 4,
|
| 335 |
"trial_name": null,
|
| 336 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.23675643681562591,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 311 |
"eval_samples_per_second": 63.015,
|
| 312 |
"eval_steps_per_second": 15.775,
|
| 313 |
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.12133767386800828,
|
| 317 |
+
"grad_norm": 2.15625,
|
| 318 |
+
"learning_rate": 0.00019297764858882514,
|
| 319 |
+
"loss": 2.3663,
|
| 320 |
+
"step": 410
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.12429712932820361,
|
| 324 |
+
"grad_norm": 3.15625,
|
| 325 |
+
"learning_rate": 0.00019248258232139388,
|
| 326 |
+
"loss": 2.1701,
|
| 327 |
+
"step": 420
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.12725658478839894,
|
| 331 |
+
"grad_norm": 4.34375,
|
| 332 |
+
"learning_rate": 0.00019197133427991436,
|
| 333 |
+
"loss": 2.0932,
|
| 334 |
+
"step": 430
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.13021604024859426,
|
| 338 |
+
"grad_norm": 4.21875,
|
| 339 |
+
"learning_rate": 0.00019144399391799043,
|
| 340 |
+
"loss": 1.914,
|
| 341 |
+
"step": 440
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.1331754957087896,
|
| 345 |
+
"grad_norm": 18.0,
|
| 346 |
+
"learning_rate": 0.00019090065350491626,
|
| 347 |
+
"loss": 2.2622,
|
| 348 |
+
"step": 450
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.1361349511689849,
|
| 352 |
+
"grad_norm": 2.21875,
|
| 353 |
+
"learning_rate": 0.0001903414081095315,
|
| 354 |
+
"loss": 2.3188,
|
| 355 |
+
"step": 460
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.13909440662918024,
|
| 359 |
+
"grad_norm": 2.484375,
|
| 360 |
+
"learning_rate": 0.00018976635558358722,
|
| 361 |
+
"loss": 2.0455,
|
| 362 |
+
"step": 470
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.14205386208937557,
|
| 366 |
+
"grad_norm": 4.4375,
|
| 367 |
+
"learning_rate": 0.00018917559654462474,
|
| 368 |
+
"loss": 2.1161,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.1450133175495709,
|
| 373 |
+
"grad_norm": 5.21875,
|
| 374 |
+
"learning_rate": 0.00018856923435837022,
|
| 375 |
+
"loss": 2.073,
|
| 376 |
+
"step": 490
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.1479727730097662,
|
| 380 |
+
"grad_norm": 12.25,
|
| 381 |
+
"learning_rate": 0.0001879473751206489,
|
| 382 |
+
"loss": 1.5186,
|
| 383 |
+
"step": 500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.15093222846996152,
|
| 387 |
+
"grad_norm": 2.1875,
|
| 388 |
+
"learning_rate": 0.00018731012763882133,
|
| 389 |
+
"loss": 2.3347,
|
| 390 |
+
"step": 510
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.15389168393015684,
|
| 394 |
+
"grad_norm": 3.125,
|
| 395 |
+
"learning_rate": 0.00018665760341274505,
|
| 396 |
+
"loss": 2.1125,
|
| 397 |
+
"step": 520
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.15685113939035217,
|
| 401 |
+
"grad_norm": 3.75,
|
| 402 |
+
"learning_rate": 0.00018598991661526572,
|
| 403 |
+
"loss": 2.203,
|
| 404 |
+
"step": 530
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.1598105948505475,
|
| 408 |
+
"grad_norm": 3.859375,
|
| 409 |
+
"learning_rate": 0.00018530718407223974,
|
| 410 |
+
"loss": 2.1003,
|
| 411 |
+
"step": 540
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.16277005031074282,
|
| 415 |
+
"grad_norm": 15.9375,
|
| 416 |
+
"learning_rate": 0.00018460952524209355,
|
| 417 |
+
"loss": 1.8457,
|
| 418 |
+
"step": 550
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.16572950577093815,
|
| 422 |
+
"grad_norm": 2.109375,
|
| 423 |
+
"learning_rate": 0.00018389706219492147,
|
| 424 |
+
"loss": 2.1732,
|
| 425 |
+
"step": 560
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.16868896123113347,
|
| 429 |
+
"grad_norm": 2.515625,
|
| 430 |
+
"learning_rate": 0.00018316991959112716,
|
| 431 |
+
"loss": 2.309,
|
| 432 |
+
"step": 570
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.1716484166913288,
|
| 436 |
+
"grad_norm": 3.25,
|
| 437 |
+
"learning_rate": 0.00018242822465961176,
|
| 438 |
+
"loss": 1.7926,
|
| 439 |
+
"step": 580
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.17460787215152412,
|
| 443 |
+
"grad_norm": 6.96875,
|
| 444 |
+
"learning_rate": 0.00018167210717551224,
|
| 445 |
+
"loss": 1.9797,
|
| 446 |
+
"step": 590
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.17756732761171945,
|
| 450 |
+
"grad_norm": 15.0625,
|
| 451 |
+
"learning_rate": 0.00018090169943749476,
|
| 452 |
+
"loss": 1.748,
|
| 453 |
+
"step": 600
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.17756732761171945,
|
| 457 |
+
"eval_loss": 2.0752952098846436,
|
| 458 |
+
"eval_runtime": 23.9564,
|
| 459 |
+
"eval_samples_per_second": 62.697,
|
| 460 |
+
"eval_steps_per_second": 15.695,
|
| 461 |
+
"step": 600
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.18052678307191478,
|
| 465 |
+
"grad_norm": 2.8125,
|
| 466 |
+
"learning_rate": 0.00018011713624460608,
|
| 467 |
+
"loss": 1.9757,
|
| 468 |
+
"step": 610
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.1834862385321101,
|
| 472 |
+
"grad_norm": 2.46875,
|
| 473 |
+
"learning_rate": 0.00017931855487268782,
|
| 474 |
+
"loss": 1.9936,
|
| 475 |
+
"step": 620
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.18644569399230543,
|
| 479 |
+
"grad_norm": 3.171875,
|
| 480 |
+
"learning_rate": 0.0001785060950503568,
|
| 481 |
+
"loss": 2.3718,
|
| 482 |
+
"step": 630
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.18940514945250073,
|
| 486 |
+
"grad_norm": 10.125,
|
| 487 |
+
"learning_rate": 0.00017767989893455698,
|
| 488 |
+
"loss": 2.0974,
|
| 489 |
+
"step": 640
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.19236460491269605,
|
| 493 |
+
"grad_norm": 16.25,
|
| 494 |
+
"learning_rate": 0.00017684011108568592,
|
| 495 |
+
"loss": 2.0872,
|
| 496 |
+
"step": 650
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.19532406037289138,
|
| 500 |
+
"grad_norm": 2.0625,
|
| 501 |
+
"learning_rate": 0.00017598687844230088,
|
| 502 |
+
"loss": 2.3763,
|
| 503 |
+
"step": 660
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.1982835158330867,
|
| 507 |
+
"grad_norm": 2.640625,
|
| 508 |
+
"learning_rate": 0.00017512035029540885,
|
| 509 |
+
"loss": 2.102,
|
| 510 |
+
"step": 670
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.20124297129328203,
|
| 514 |
+
"grad_norm": 4.03125,
|
| 515 |
+
"learning_rate": 0.000174240678262345,
|
| 516 |
+
"loss": 2.1481,
|
| 517 |
+
"step": 680
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.20420242675347736,
|
| 521 |
+
"grad_norm": 6.0625,
|
| 522 |
+
"learning_rate": 0.000173348016260244,
|
| 523 |
+
"loss": 1.8523,
|
| 524 |
+
"step": 690
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.20716188221367268,
|
| 528 |
+
"grad_norm": 18.75,
|
| 529 |
+
"learning_rate": 0.00017244252047910892,
|
| 530 |
+
"loss": 1.7534,
|
| 531 |
+
"step": 700
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.210121337673868,
|
| 535 |
+
"grad_norm": 2.265625,
|
| 536 |
+
"learning_rate": 0.00017152434935448256,
|
| 537 |
+
"loss": 2.1479,
|
| 538 |
+
"step": 710
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.21308079313406333,
|
| 542 |
+
"grad_norm": 2.8125,
|
| 543 |
+
"learning_rate": 0.0001705936635397259,
|
| 544 |
+
"loss": 2.2207,
|
| 545 |
+
"step": 720
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.21604024859425866,
|
| 549 |
+
"grad_norm": 3.59375,
|
| 550 |
+
"learning_rate": 0.00016965062587790823,
|
| 551 |
+
"loss": 2.0364,
|
| 552 |
+
"step": 730
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.218999704054454,
|
| 556 |
+
"grad_norm": 3.265625,
|
| 557 |
+
"learning_rate": 0.00016869540137331445,
|
| 558 |
+
"loss": 1.8523,
|
| 559 |
+
"step": 740
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.2219591595146493,
|
| 563 |
+
"grad_norm": 10.4375,
|
| 564 |
+
"learning_rate": 0.00016772815716257412,
|
| 565 |
+
"loss": 1.8113,
|
| 566 |
+
"step": 750
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.22491861497484464,
|
| 570 |
+
"grad_norm": 2.21875,
|
| 571 |
+
"learning_rate": 0.00016674906248541726,
|
| 572 |
+
"loss": 2.2365,
|
| 573 |
+
"step": 760
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.22787807043503996,
|
| 577 |
+
"grad_norm": 3.9375,
|
| 578 |
+
"learning_rate": 0.00016575828865506245,
|
| 579 |
+
"loss": 2.0369,
|
| 580 |
+
"step": 770
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.2308375258952353,
|
| 584 |
+
"grad_norm": 4.0625,
|
| 585 |
+
"learning_rate": 0.0001647560090282419,
|
| 586 |
+
"loss": 1.9434,
|
| 587 |
+
"step": 780
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.2337969813554306,
|
| 591 |
+
"grad_norm": 6.8125,
|
| 592 |
+
"learning_rate": 0.000163742398974869,
|
| 593 |
+
"loss": 1.822,
|
| 594 |
+
"step": 790
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.23675643681562591,
|
| 598 |
+
"grad_norm": 29.0,
|
| 599 |
+
"learning_rate": 0.0001627176358473537,
|
| 600 |
+
"loss": 1.9161,
|
| 601 |
+
"step": 800
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.23675643681562591,
|
| 605 |
+
"eval_loss": 2.0661604404449463,
|
| 606 |
+
"eval_runtime": 24.0938,
|
| 607 |
+
"eval_samples_per_second": 62.34,
|
| 608 |
+
"eval_steps_per_second": 15.606,
|
| 609 |
+
"step": 800
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 10,
|
|
|
|
| 626 |
"attributes": {}
|
| 627 |
}
|
| 628 |
},
|
| 629 |
+
"total_flos": 1.24028893790208e+16,
|
| 630 |
"train_batch_size": 4,
|
| 631 |
"trial_name": null,
|
| 632 |
"trial_params": null
|