Training in progress, step 500, checkpoint
Browse files- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +23 -513
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1235573136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:224bbc547320cbc7a57a274bef9f525f2e4be737031df14b601959f9380cb929
|
| 3 |
size 1235573136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2471218763
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f014f1f8cf2eb9a4ff44ad059ad7d7ab8356457d91805882d791c32ab849f992
|
| 3 |
size 2471218763
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68b03f74e10591ff22477365642275703166a34b306471da2a9df3e87497356f
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0471ce3745a36e49a3e0d19eac020ddc42dff8b92447d06fa38e6a682e228b19
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -291,563 +291,73 @@
|
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.0082,
|
| 294 |
-
"grad_norm": 28.
|
| 295 |
"learning_rate": 0.00029814228456913827,
|
| 296 |
-
"loss":
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.0084,
|
| 301 |
-
"grad_norm": 12.
|
| 302 |
"learning_rate": 0.00029808216432865726,
|
| 303 |
-
"loss": 83.
|
| 304 |
"step": 420
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 0.0086,
|
| 308 |
-
"grad_norm": 7.
|
| 309 |
"learning_rate": 0.0002980220440881763,
|
| 310 |
-
"loss": 73.
|
| 311 |
"step": 430
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 0.0088,
|
| 315 |
-
"grad_norm": 11.
|
| 316 |
"learning_rate": 0.00029796192384769535,
|
| 317 |
-
"loss": 77.
|
| 318 |
"step": 440
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 0.009,
|
| 322 |
-
"grad_norm": 8.
|
| 323 |
"learning_rate": 0.0002979018036072144,
|
| 324 |
-
"loss": 77.
|
| 325 |
"step": 450
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 0.0092,
|
| 329 |
-
"grad_norm":
|
| 330 |
"learning_rate": 0.00029784168336673345,
|
| 331 |
-
"loss": 78.
|
| 332 |
"step": 460
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.0094,
|
| 336 |
-
"grad_norm": 9.
|
| 337 |
"learning_rate": 0.0002977815631262525,
|
| 338 |
-
"loss": 71.
|
| 339 |
"step": 470
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.0096,
|
| 343 |
-
"grad_norm": 7.
|
| 344 |
"learning_rate": 0.00029772144288577155,
|
| 345 |
-
"loss": 73.
|
| 346 |
"step": 480
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.0098,
|
| 350 |
-
"grad_norm": 9.
|
| 351 |
"learning_rate": 0.00029766132264529054,
|
| 352 |
-
"loss": 75.
|
| 353 |
"step": 490
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.01,
|
| 357 |
-
"grad_norm": 11.
|
| 358 |
"learning_rate": 0.0002976012024048096,
|
| 359 |
-
"loss": 78.
|
| 360 |
"step": 500
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 0.0102,
|
| 364 |
-
"grad_norm": 9.10632610321045,
|
| 365 |
-
"learning_rate": 0.00029754108216432863,
|
| 366 |
-
"loss": 78.6921875,
|
| 367 |
-
"step": 510
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 0.0104,
|
| 371 |
-
"grad_norm": 9.557915687561035,
|
| 372 |
-
"learning_rate": 0.0002974809619238477,
|
| 373 |
-
"loss": 71.66650390625,
|
| 374 |
-
"step": 520
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 0.0106,
|
| 378 |
-
"grad_norm": 8.777642250061035,
|
| 379 |
-
"learning_rate": 0.0002974208416833667,
|
| 380 |
-
"loss": 70.4987548828125,
|
| 381 |
-
"step": 530
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.0108,
|
| 385 |
-
"grad_norm": 13.94754409790039,
|
| 386 |
-
"learning_rate": 0.0002973607214428857,
|
| 387 |
-
"loss": 72.32754516601562,
|
| 388 |
-
"step": 540
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 0.011,
|
| 392 |
-
"grad_norm": 8.856101989746094,
|
| 393 |
-
"learning_rate": 0.0002973006012024048,
|
| 394 |
-
"loss": 70.21427612304687,
|
| 395 |
-
"step": 550
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 0.0112,
|
| 399 |
-
"grad_norm": 9.487411499023438,
|
| 400 |
-
"learning_rate": 0.0002972404809619238,
|
| 401 |
-
"loss": 76.47840576171875,
|
| 402 |
-
"step": 560
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 0.0114,
|
| 406 |
-
"grad_norm": 8.979376792907715,
|
| 407 |
-
"learning_rate": 0.00029718036072144287,
|
| 408 |
-
"loss": 77.88162231445312,
|
| 409 |
-
"step": 570
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 0.0116,
|
| 413 |
-
"grad_norm": 9.910178184509277,
|
| 414 |
-
"learning_rate": 0.0002971202404809619,
|
| 415 |
-
"loss": 77.7337646484375,
|
| 416 |
-
"step": 580
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 0.0118,
|
| 420 |
-
"grad_norm": 5.745482444763184,
|
| 421 |
-
"learning_rate": 0.00029706012024048096,
|
| 422 |
-
"loss": 71.672021484375,
|
| 423 |
-
"step": 590
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 0.012,
|
| 427 |
-
"grad_norm": 9.654470443725586,
|
| 428 |
-
"learning_rate": 0.00029699999999999996,
|
| 429 |
-
"loss": 74.40623168945312,
|
| 430 |
-
"step": 600
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 0.0122,
|
| 434 |
-
"grad_norm": 8.696991920471191,
|
| 435 |
-
"learning_rate": 0.000296939879759519,
|
| 436 |
-
"loss": 74.297412109375,
|
| 437 |
-
"step": 610
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 0.0124,
|
| 441 |
-
"grad_norm": 11.501073837280273,
|
| 442 |
-
"learning_rate": 0.00029687975951903805,
|
| 443 |
-
"loss": 70.46600952148438,
|
| 444 |
-
"step": 620
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 0.0126,
|
| 448 |
-
"grad_norm": 6.01923131942749,
|
| 449 |
-
"learning_rate": 0.0002968196392785571,
|
| 450 |
-
"loss": 68.65836181640626,
|
| 451 |
-
"step": 630
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 0.0128,
|
| 455 |
-
"grad_norm": 7.358704090118408,
|
| 456 |
-
"learning_rate": 0.0002967595190380761,
|
| 457 |
-
"loss": 69.74998779296875,
|
| 458 |
-
"step": 640
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 0.013,
|
| 462 |
-
"grad_norm": 9.420614242553711,
|
| 463 |
-
"learning_rate": 0.0002966993987975952,
|
| 464 |
-
"loss": 76.11289672851562,
|
| 465 |
-
"step": 650
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 0.0132,
|
| 469 |
-
"grad_norm": 8.627158164978027,
|
| 470 |
-
"learning_rate": 0.0002966392785571142,
|
| 471 |
-
"loss": 77.244384765625,
|
| 472 |
-
"step": 660
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 0.0134,
|
| 476 |
-
"grad_norm": 8.27780818939209,
|
| 477 |
-
"learning_rate": 0.00029657915831663323,
|
| 478 |
-
"loss": 72.63546142578124,
|
| 479 |
-
"step": 670
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 0.0136,
|
| 483 |
-
"grad_norm": 8.197218894958496,
|
| 484 |
-
"learning_rate": 0.0002965190380761523,
|
| 485 |
-
"loss": 75.8551513671875,
|
| 486 |
-
"step": 680
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 0.0138,
|
| 490 |
-
"grad_norm": 9.352670669555664,
|
| 491 |
-
"learning_rate": 0.00029645891783567133,
|
| 492 |
-
"loss": 70.17238159179688,
|
| 493 |
-
"step": 690
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 0.014,
|
| 497 |
-
"grad_norm": 10.278020858764648,
|
| 498 |
-
"learning_rate": 0.0002963987975951904,
|
| 499 |
-
"loss": 72.43441772460938,
|
| 500 |
-
"step": 700
|
| 501 |
-
},
|
| 502 |
-
{
|
| 503 |
-
"epoch": 0.0142,
|
| 504 |
-
"grad_norm": 8.186079978942871,
|
| 505 |
-
"learning_rate": 0.00029633867735470937,
|
| 506 |
-
"loss": 69.34667358398437,
|
| 507 |
-
"step": 710
|
| 508 |
-
},
|
| 509 |
-
{
|
| 510 |
-
"epoch": 0.0144,
|
| 511 |
-
"grad_norm": 8.636640548706055,
|
| 512 |
-
"learning_rate": 0.0002962785571142284,
|
| 513 |
-
"loss": 71.52565307617188,
|
| 514 |
-
"step": 720
|
| 515 |
-
},
|
| 516 |
-
{
|
| 517 |
-
"epoch": 0.0146,
|
| 518 |
-
"grad_norm": 8.615554809570312,
|
| 519 |
-
"learning_rate": 0.00029621843687374747,
|
| 520 |
-
"loss": 66.20573120117187,
|
| 521 |
-
"step": 730
|
| 522 |
-
},
|
| 523 |
-
{
|
| 524 |
-
"epoch": 0.0148,
|
| 525 |
-
"grad_norm": 9.266575813293457,
|
| 526 |
-
"learning_rate": 0.0002961583166332665,
|
| 527 |
-
"loss": 66.66327514648438,
|
| 528 |
-
"step": 740
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 0.015,
|
| 532 |
-
"grad_norm": 6.957458972930908,
|
| 533 |
-
"learning_rate": 0.00029609819639278556,
|
| 534 |
-
"loss": 69.37461547851562,
|
| 535 |
-
"step": 750
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 0.0152,
|
| 539 |
-
"grad_norm": 10.149578094482422,
|
| 540 |
-
"learning_rate": 0.0002960380761523046,
|
| 541 |
-
"loss": 75.38046264648438,
|
| 542 |
-
"step": 760
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 0.0154,
|
| 546 |
-
"grad_norm": 8.38595962524414,
|
| 547 |
-
"learning_rate": 0.0002959779559118236,
|
| 548 |
-
"loss": 72.13077392578126,
|
| 549 |
-
"step": 770
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 0.0156,
|
| 553 |
-
"grad_norm": 9.602531433105469,
|
| 554 |
-
"learning_rate": 0.00029591783567134265,
|
| 555 |
-
"loss": 73.194677734375,
|
| 556 |
-
"step": 780
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 0.0158,
|
| 560 |
-
"grad_norm": 11.321459770202637,
|
| 561 |
-
"learning_rate": 0.0002958577154308617,
|
| 562 |
-
"loss": 67.77056884765625,
|
| 563 |
-
"step": 790
|
| 564 |
-
},
|
| 565 |
-
{
|
| 566 |
-
"epoch": 0.016,
|
| 567 |
-
"grad_norm": 9.131096839904785,
|
| 568 |
-
"learning_rate": 0.00029579759519038075,
|
| 569 |
-
"loss": 68.58425903320312,
|
| 570 |
-
"step": 800
|
| 571 |
-
},
|
| 572 |
-
{
|
| 573 |
-
"epoch": 0.0162,
|
| 574 |
-
"grad_norm": 9.43658447265625,
|
| 575 |
-
"learning_rate": 0.00029573747494989974,
|
| 576 |
-
"loss": 71.80587158203124,
|
| 577 |
-
"step": 810
|
| 578 |
-
},
|
| 579 |
-
{
|
| 580 |
-
"epoch": 0.0164,
|
| 581 |
-
"grad_norm": 7.688558578491211,
|
| 582 |
-
"learning_rate": 0.0002956773547094188,
|
| 583 |
-
"loss": 73.39664916992187,
|
| 584 |
-
"step": 820
|
| 585 |
-
},
|
| 586 |
-
{
|
| 587 |
-
"epoch": 0.0166,
|
| 588 |
-
"grad_norm": 9.346514701843262,
|
| 589 |
-
"learning_rate": 0.00029561723446893784,
|
| 590 |
-
"loss": 73.8046142578125,
|
| 591 |
-
"step": 830
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.0168,
|
| 595 |
-
"grad_norm": 7.071310997009277,
|
| 596 |
-
"learning_rate": 0.0002955571142284569,
|
| 597 |
-
"loss": 69.04111938476562,
|
| 598 |
-
"step": 840
|
| 599 |
-
},
|
| 600 |
-
{
|
| 601 |
-
"epoch": 0.017,
|
| 602 |
-
"grad_norm": 10.125195503234863,
|
| 603 |
-
"learning_rate": 0.00029549699398797593,
|
| 604 |
-
"loss": 69.92824096679688,
|
| 605 |
-
"step": 850
|
| 606 |
-
},
|
| 607 |
-
{
|
| 608 |
-
"epoch": 0.0172,
|
| 609 |
-
"grad_norm": 8.768003463745117,
|
| 610 |
-
"learning_rate": 0.000295436873747495,
|
| 611 |
-
"loss": 74.65200805664062,
|
| 612 |
-
"step": 860
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 0.0174,
|
| 616 |
-
"grad_norm": 8.981837272644043,
|
| 617 |
-
"learning_rate": 0.000295376753507014,
|
| 618 |
-
"loss": 72.95183715820312,
|
| 619 |
-
"step": 870
|
| 620 |
-
},
|
| 621 |
-
{
|
| 622 |
-
"epoch": 0.0176,
|
| 623 |
-
"grad_norm": 9.743247032165527,
|
| 624 |
-
"learning_rate": 0.000295316633266533,
|
| 625 |
-
"loss": 68.19429321289063,
|
| 626 |
-
"step": 880
|
| 627 |
-
},
|
| 628 |
-
{
|
| 629 |
-
"epoch": 0.0178,
|
| 630 |
-
"grad_norm": 7.722388744354248,
|
| 631 |
-
"learning_rate": 0.00029525651302605207,
|
| 632 |
-
"loss": 71.07997436523438,
|
| 633 |
-
"step": 890
|
| 634 |
-
},
|
| 635 |
-
{
|
| 636 |
-
"epoch": 0.018,
|
| 637 |
-
"grad_norm": 7.273824214935303,
|
| 638 |
-
"learning_rate": 0.0002951963927855711,
|
| 639 |
-
"loss": 71.75267333984375,
|
| 640 |
-
"step": 900
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 0.0182,
|
| 644 |
-
"grad_norm": 7.856244087219238,
|
| 645 |
-
"learning_rate": 0.00029513627254509016,
|
| 646 |
-
"loss": 73.38182983398437,
|
| 647 |
-
"step": 910
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 0.0184,
|
| 651 |
-
"grad_norm": 7.895908355712891,
|
| 652 |
-
"learning_rate": 0.00029507615230460916,
|
| 653 |
-
"loss": 70.02378540039062,
|
| 654 |
-
"step": 920
|
| 655 |
-
},
|
| 656 |
-
{
|
| 657 |
-
"epoch": 0.0186,
|
| 658 |
-
"grad_norm": 9.500384330749512,
|
| 659 |
-
"learning_rate": 0.0002950160320641282,
|
| 660 |
-
"loss": 69.76512451171875,
|
| 661 |
-
"step": 930
|
| 662 |
-
},
|
| 663 |
-
{
|
| 664 |
-
"epoch": 0.0188,
|
| 665 |
-
"grad_norm": 8.77175235748291,
|
| 666 |
-
"learning_rate": 0.0002949559118236473,
|
| 667 |
-
"loss": 69.60545654296875,
|
| 668 |
-
"step": 940
|
| 669 |
-
},
|
| 670 |
-
{
|
| 671 |
-
"epoch": 0.019,
|
| 672 |
-
"grad_norm": 9.102203369140625,
|
| 673 |
-
"learning_rate": 0.0002948957915831663,
|
| 674 |
-
"loss": 71.84405517578125,
|
| 675 |
-
"step": 950
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 0.0192,
|
| 679 |
-
"grad_norm": 8.29865837097168,
|
| 680 |
-
"learning_rate": 0.00029483567134268535,
|
| 681 |
-
"loss": 67.64026489257813,
|
| 682 |
-
"step": 960
|
| 683 |
-
},
|
| 684 |
-
{
|
| 685 |
-
"epoch": 0.0194,
|
| 686 |
-
"grad_norm": 6.868947505950928,
|
| 687 |
-
"learning_rate": 0.0002947755511022044,
|
| 688 |
-
"loss": 65.34761962890624,
|
| 689 |
-
"step": 970
|
| 690 |
-
},
|
| 691 |
-
{
|
| 692 |
-
"epoch": 0.0196,
|
| 693 |
-
"grad_norm": 9.127030372619629,
|
| 694 |
-
"learning_rate": 0.00029471543086172344,
|
| 695 |
-
"loss": 69.42554321289063,
|
| 696 |
-
"step": 980
|
| 697 |
-
},
|
| 698 |
-
{
|
| 699 |
-
"epoch": 0.0198,
|
| 700 |
-
"grad_norm": 7.779689311981201,
|
| 701 |
-
"learning_rate": 0.00029465531062124244,
|
| 702 |
-
"loss": 72.64813842773438,
|
| 703 |
-
"step": 990
|
| 704 |
-
},
|
| 705 |
-
{
|
| 706 |
-
"epoch": 0.02,
|
| 707 |
-
"grad_norm": 9.583319664001465,
|
| 708 |
-
"learning_rate": 0.0002945951903807615,
|
| 709 |
-
"loss": 71.14970703125,
|
| 710 |
-
"step": 1000
|
| 711 |
-
},
|
| 712 |
-
{
|
| 713 |
-
"epoch": 0.0202,
|
| 714 |
-
"grad_norm": 9.4298677444458,
|
| 715 |
-
"learning_rate": 0.00029453507014028053,
|
| 716 |
-
"loss": 68.8579345703125,
|
| 717 |
-
"step": 1010
|
| 718 |
-
},
|
| 719 |
-
{
|
| 720 |
-
"epoch": 0.0204,
|
| 721 |
-
"grad_norm": 11.69355583190918,
|
| 722 |
-
"learning_rate": 0.0002944749498997996,
|
| 723 |
-
"loss": 66.29926147460938,
|
| 724 |
-
"step": 1020
|
| 725 |
-
},
|
| 726 |
-
{
|
| 727 |
-
"epoch": 0.0206,
|
| 728 |
-
"grad_norm": 9.638633728027344,
|
| 729 |
-
"learning_rate": 0.00029441482965931857,
|
| 730 |
-
"loss": 69.4812744140625,
|
| 731 |
-
"step": 1030
|
| 732 |
-
},
|
| 733 |
-
{
|
| 734 |
-
"epoch": 0.0208,
|
| 735 |
-
"grad_norm": 7.3949384689331055,
|
| 736 |
-
"learning_rate": 0.0002943547094188377,
|
| 737 |
-
"loss": 69.908984375,
|
| 738 |
-
"step": 1040
|
| 739 |
-
},
|
| 740 |
-
{
|
| 741 |
-
"epoch": 0.021,
|
| 742 |
-
"grad_norm": 9.138998031616211,
|
| 743 |
-
"learning_rate": 0.0002942945891783567,
|
| 744 |
-
"loss": 68.20003662109374,
|
| 745 |
-
"step": 1050
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 0.0212,
|
| 749 |
-
"grad_norm": 9.650430679321289,
|
| 750 |
-
"learning_rate": 0.0002942344689378757,
|
| 751 |
-
"loss": 64.76406860351562,
|
| 752 |
-
"step": 1060
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 0.0214,
|
| 756 |
-
"grad_norm": 8.263360977172852,
|
| 757 |
-
"learning_rate": 0.00029417434869739476,
|
| 758 |
-
"loss": 73.39156494140624,
|
| 759 |
-
"step": 1070
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 0.0216,
|
| 763 |
-
"grad_norm": 8.509857177734375,
|
| 764 |
-
"learning_rate": 0.0002941142284569138,
|
| 765 |
-
"loss": 65.55498657226562,
|
| 766 |
-
"step": 1080
|
| 767 |
-
},
|
| 768 |
-
{
|
| 769 |
-
"epoch": 0.0218,
|
| 770 |
-
"grad_norm": 10.162703514099121,
|
| 771 |
-
"learning_rate": 0.00029405410821643286,
|
| 772 |
-
"loss": 71.94191284179688,
|
| 773 |
-
"step": 1090
|
| 774 |
-
},
|
| 775 |
-
{
|
| 776 |
-
"epoch": 0.022,
|
| 777 |
-
"grad_norm": 10.938014030456543,
|
| 778 |
-
"learning_rate": 0.00029399398797595185,
|
| 779 |
-
"loss": 68.12153930664063,
|
| 780 |
-
"step": 1100
|
| 781 |
-
},
|
| 782 |
-
{
|
| 783 |
-
"epoch": 0.0222,
|
| 784 |
-
"grad_norm": 9.84087085723877,
|
| 785 |
-
"learning_rate": 0.0002939338677354709,
|
| 786 |
-
"loss": 73.03311767578126,
|
| 787 |
-
"step": 1110
|
| 788 |
-
},
|
| 789 |
-
{
|
| 790 |
-
"epoch": 0.0224,
|
| 791 |
-
"grad_norm": 8.5576171875,
|
| 792 |
-
"learning_rate": 0.00029387374749498995,
|
| 793 |
-
"loss": 67.728662109375,
|
| 794 |
-
"step": 1120
|
| 795 |
-
},
|
| 796 |
-
{
|
| 797 |
-
"epoch": 0.0226,
|
| 798 |
-
"grad_norm": 6.275845050811768,
|
| 799 |
-
"learning_rate": 0.000293813627254509,
|
| 800 |
-
"loss": 59.14338989257813,
|
| 801 |
-
"step": 1130
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 0.0228,
|
| 805 |
-
"grad_norm": 10.62365436553955,
|
| 806 |
-
"learning_rate": 0.00029375350701402804,
|
| 807 |
-
"loss": 68.015625,
|
| 808 |
-
"step": 1140
|
| 809 |
-
},
|
| 810 |
-
{
|
| 811 |
-
"epoch": 0.023,
|
| 812 |
-
"grad_norm": 10.124994277954102,
|
| 813 |
-
"learning_rate": 0.0002936933867735471,
|
| 814 |
-
"loss": 67.996630859375,
|
| 815 |
-
"step": 1150
|
| 816 |
-
},
|
| 817 |
-
{
|
| 818 |
-
"epoch": 0.0232,
|
| 819 |
-
"grad_norm": 9.192570686340332,
|
| 820 |
-
"learning_rate": 0.00029363326653306614,
|
| 821 |
-
"loss": 69.9107177734375,
|
| 822 |
-
"step": 1160
|
| 823 |
-
},
|
| 824 |
-
{
|
| 825 |
-
"epoch": 0.0234,
|
| 826 |
-
"grad_norm": 11.012198448181152,
|
| 827 |
-
"learning_rate": 0.00029357314629258513,
|
| 828 |
-
"loss": 72.0302978515625,
|
| 829 |
-
"step": 1170
|
| 830 |
-
},
|
| 831 |
-
{
|
| 832 |
-
"epoch": 0.0236,
|
| 833 |
-
"grad_norm": 8.58188533782959,
|
| 834 |
-
"learning_rate": 0.0002935130260521042,
|
| 835 |
-
"loss": 73.009423828125,
|
| 836 |
-
"step": 1180
|
| 837 |
-
},
|
| 838 |
-
{
|
| 839 |
-
"epoch": 0.0238,
|
| 840 |
-
"grad_norm": 11.214829444885254,
|
| 841 |
-
"learning_rate": 0.0002934529058116232,
|
| 842 |
-
"loss": 69.40020141601562,
|
| 843 |
-
"step": 1190
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 0.024,
|
| 847 |
-
"grad_norm": 8.615409851074219,
|
| 848 |
-
"learning_rate": 0.0002933927855711423,
|
| 849 |
-
"loss": 73.381103515625,
|
| 850 |
-
"step": 1200
|
| 851 |
}
|
| 852 |
],
|
| 853 |
"logging_steps": 10,
|
|
@@ -867,7 +377,7 @@
|
|
| 867 |
"attributes": {}
|
| 868 |
}
|
| 869 |
},
|
| 870 |
-
"total_flos":
|
| 871 |
"train_batch_size": 2,
|
| 872 |
"trial_name": null,
|
| 873 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.01,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.0082,
|
| 294 |
+
"grad_norm": 28.707782745361328,
|
| 295 |
"learning_rate": 0.00029814228456913827,
|
| 296 |
+
"loss": 103.1381591796875,
|
| 297 |
"step": 410
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 0.0084,
|
| 301 |
+
"grad_norm": 12.400252342224121,
|
| 302 |
"learning_rate": 0.00029808216432865726,
|
| 303 |
+
"loss": 83.130029296875,
|
| 304 |
"step": 420
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 0.0086,
|
| 308 |
+
"grad_norm": 7.325169563293457,
|
| 309 |
"learning_rate": 0.0002980220440881763,
|
| 310 |
+
"loss": 73.54479370117187,
|
| 311 |
"step": 430
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 0.0088,
|
| 315 |
+
"grad_norm": 11.358526229858398,
|
| 316 |
"learning_rate": 0.00029796192384769535,
|
| 317 |
+
"loss": 77.26640625,
|
| 318 |
"step": 440
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 0.009,
|
| 322 |
+
"grad_norm": 8.655184745788574,
|
| 323 |
"learning_rate": 0.0002979018036072144,
|
| 324 |
+
"loss": 77.83007202148437,
|
| 325 |
"step": 450
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 0.0092,
|
| 329 |
+
"grad_norm": 10.999149322509766,
|
| 330 |
"learning_rate": 0.00029784168336673345,
|
| 331 |
+
"loss": 78.61140747070313,
|
| 332 |
"step": 460
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.0094,
|
| 336 |
+
"grad_norm": 9.994011878967285,
|
| 337 |
"learning_rate": 0.0002977815631262525,
|
| 338 |
+
"loss": 71.70507202148437,
|
| 339 |
"step": 470
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 0.0096,
|
| 343 |
+
"grad_norm": 7.690250873565674,
|
| 344 |
"learning_rate": 0.00029772144288577155,
|
| 345 |
+
"loss": 73.41466674804687,
|
| 346 |
"step": 480
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 0.0098,
|
| 350 |
+
"grad_norm": 9.543883323669434,
|
| 351 |
"learning_rate": 0.00029766132264529054,
|
| 352 |
+
"loss": 75.77626953125,
|
| 353 |
"step": 490
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 0.01,
|
| 357 |
+
"grad_norm": 11.137728691101074,
|
| 358 |
"learning_rate": 0.0002976012024048096,
|
| 359 |
+
"loss": 78.9918212890625,
|
| 360 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 361 |
}
|
| 362 |
],
|
| 363 |
"logging_steps": 10,
|
|
|
|
| 377 |
"attributes": {}
|
| 378 |
}
|
| 379 |
},
|
| 380 |
+
"total_flos": 8161860202859520.0,
|
| 381 |
"train_batch_size": 2,
|
| 382 |
"trial_name": null,
|
| 383 |
"trial_params": null
|