Training in progress, step 100, 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 1342238560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d9e480887b508a00767a77d5ab5f264a47cf2eef4edf4aac9915b7379c4804f
|
3 |
size 1342238560
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 682101396
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40f31d476c9a640c539e23646c8cda177082940ee4aab44f8f8316ef19c7804e
|
3 |
size 682101396
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -357,6 +357,356 @@
|
|
357 |
"learning_rate": 0.00011736481776669306,
|
358 |
"loss": 0.1313,
|
359 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 1,
|
@@ -371,12 +721,12 @@
|
|
371 |
"should_evaluate": false,
|
372 |
"should_log": false,
|
373 |
"should_save": true,
|
374 |
-
"should_training_stop":
|
375 |
},
|
376 |
"attributes": {}
|
377 |
}
|
378 |
},
|
379 |
-
"total_flos":
|
380 |
"train_batch_size": 8,
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07581141909500118,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
357 |
"learning_rate": 0.00011736481776669306,
|
358 |
"loss": 0.1313,
|
359 |
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.038663823738450606,
|
363 |
+
"grad_norm": 0.08683478832244873,
|
364 |
+
"learning_rate": 0.00011391731009600654,
|
365 |
+
"loss": 0.1169,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.039421937929400616,
|
370 |
+
"grad_norm": 0.09042470157146454,
|
371 |
+
"learning_rate": 0.00011045284632676536,
|
372 |
+
"loss": 0.1267,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.040180052120350626,
|
377 |
+
"grad_norm": 0.10689766705036163,
|
378 |
+
"learning_rate": 0.00010697564737441252,
|
379 |
+
"loss": 0.1159,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.04093816631130064,
|
384 |
+
"grad_norm": 0.09534477442502975,
|
385 |
+
"learning_rate": 0.00010348994967025012,
|
386 |
+
"loss": 0.1108,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.04169628050225065,
|
391 |
+
"grad_norm": 0.10675404220819473,
|
392 |
+
"learning_rate": 0.0001,
|
393 |
+
"loss": 0.1137,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.04245439469320066,
|
398 |
+
"grad_norm": 0.11125562340021133,
|
399 |
+
"learning_rate": 9.651005032974994e-05,
|
400 |
+
"loss": 0.1142,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.04321250888415067,
|
405 |
+
"grad_norm": 0.09316002577543259,
|
406 |
+
"learning_rate": 9.302435262558747e-05,
|
407 |
+
"loss": 0.1075,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.04397062307510069,
|
412 |
+
"grad_norm": 0.08302053809165955,
|
413 |
+
"learning_rate": 8.954715367323468e-05,
|
414 |
+
"loss": 0.1023,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.0447287372660507,
|
419 |
+
"grad_norm": 0.09984162449836731,
|
420 |
+
"learning_rate": 8.608268990399349e-05,
|
421 |
+
"loss": 0.1169,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.04548685145700071,
|
426 |
+
"grad_norm": 0.08475495129823685,
|
427 |
+
"learning_rate": 8.263518223330697e-05,
|
428 |
+
"loss": 0.1095,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.04624496564795072,
|
433 |
+
"grad_norm": 0.07810202986001968,
|
434 |
+
"learning_rate": 7.920883091822408e-05,
|
435 |
+
"loss": 0.1083,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.04700307983890074,
|
440 |
+
"grad_norm": 0.09930936992168427,
|
441 |
+
"learning_rate": 7.580781044003324e-05,
|
442 |
+
"loss": 0.105,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.04776119402985075,
|
447 |
+
"grad_norm": 0.0964718908071518,
|
448 |
+
"learning_rate": 7.243626441830009e-05,
|
449 |
+
"loss": 0.1216,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.04851930822080076,
|
454 |
+
"grad_norm": 0.07654120773077011,
|
455 |
+
"learning_rate": 6.909830056250527e-05,
|
456 |
+
"loss": 0.1085,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.04927742241175077,
|
461 |
+
"grad_norm": 0.08607843518257141,
|
462 |
+
"learning_rate": 6.579798566743314e-05,
|
463 |
+
"loss": 0.1176,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.050035536602700784,
|
468 |
+
"grad_norm": 0.09092072397470474,
|
469 |
+
"learning_rate": 6.25393406584088e-05,
|
470 |
+
"loss": 0.1036,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.050793650793650794,
|
475 |
+
"grad_norm": 0.07810676097869873,
|
476 |
+
"learning_rate": 5.9326335692419995e-05,
|
477 |
+
"loss": 0.1155,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.051551764984600804,
|
482 |
+
"grad_norm": 0.08400943875312805,
|
483 |
+
"learning_rate": 5.616288532109225e-05,
|
484 |
+
"loss": 0.1016,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.05230987917555082,
|
489 |
+
"grad_norm": 0.08304097503423691,
|
490 |
+
"learning_rate": 5.305284372141095e-05,
|
491 |
+
"loss": 0.1015,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.05306799336650083,
|
496 |
+
"grad_norm": 0.08529230207204819,
|
497 |
+
"learning_rate": 5.000000000000002e-05,
|
498 |
+
"loss": 0.1138,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.05382610755745084,
|
503 |
+
"grad_norm": 0.09477388858795166,
|
504 |
+
"learning_rate": 4.700807357667952e-05,
|
505 |
+
"loss": 0.1105,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.05458422174840085,
|
510 |
+
"grad_norm": 0.0729258805513382,
|
511 |
+
"learning_rate": 4.4080709652925336e-05,
|
512 |
+
"loss": 0.111,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.05534233593935087,
|
517 |
+
"grad_norm": 0.07976260036230087,
|
518 |
+
"learning_rate": 4.12214747707527e-05,
|
519 |
+
"loss": 0.1065,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.05610045013030088,
|
524 |
+
"grad_norm": 0.0769440159201622,
|
525 |
+
"learning_rate": 3.843385246743417e-05,
|
526 |
+
"loss": 0.0954,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.05685856432125089,
|
531 |
+
"grad_norm": 0.07518622279167175,
|
532 |
+
"learning_rate": 3.5721239031346066e-05,
|
533 |
+
"loss": 0.1006,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.0576166785122009,
|
538 |
+
"grad_norm": 0.07788234204053879,
|
539 |
+
"learning_rate": 3.308693936411421e-05,
|
540 |
+
"loss": 0.1035,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.058374792703150914,
|
545 |
+
"grad_norm": 0.07939758896827698,
|
546 |
+
"learning_rate": 3.053416295410026e-05,
|
547 |
+
"loss": 0.1026,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.059132906894100924,
|
552 |
+
"grad_norm": 0.07357849180698395,
|
553 |
+
"learning_rate": 2.8066019966134904e-05,
|
554 |
+
"loss": 0.0985,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.059891021085050934,
|
559 |
+
"grad_norm": 0.0757596343755722,
|
560 |
+
"learning_rate": 2.5685517452260567e-05,
|
561 |
+
"loss": 0.0959,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.06064913527600095,
|
566 |
+
"grad_norm": 0.07817908376455307,
|
567 |
+
"learning_rate": 2.339555568810221e-05,
|
568 |
+
"loss": 0.1014,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.06140724946695096,
|
573 |
+
"grad_norm": 0.07738906890153885,
|
574 |
+
"learning_rate": 2.119892463932781e-05,
|
575 |
+
"loss": 0.0998,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.06216536365790097,
|
580 |
+
"grad_norm": 0.0873928815126419,
|
581 |
+
"learning_rate": 1.9098300562505266e-05,
|
582 |
+
"loss": 0.1085,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.06292347784885098,
|
587 |
+
"grad_norm": 0.09719298779964447,
|
588 |
+
"learning_rate": 1.7096242744495837e-05,
|
589 |
+
"loss": 0.1136,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.06368159203980099,
|
594 |
+
"grad_norm": 0.08729561418294907,
|
595 |
+
"learning_rate": 1.5195190384357404e-05,
|
596 |
+
"loss": 0.0954,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.064439706230751,
|
601 |
+
"grad_norm": 0.07439972460269928,
|
602 |
+
"learning_rate": 1.339745962155613e-05,
|
603 |
+
"loss": 0.0975,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.06519782042170102,
|
608 |
+
"grad_norm": 0.07854153960943222,
|
609 |
+
"learning_rate": 1.1705240714107302e-05,
|
610 |
+
"loss": 0.1158,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.06595593461265103,
|
615 |
+
"grad_norm": 0.07700039446353912,
|
616 |
+
"learning_rate": 1.0120595370083318e-05,
|
617 |
+
"loss": 0.0953,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.06671404880360104,
|
622 |
+
"grad_norm": 0.07031956315040588,
|
623 |
+
"learning_rate": 8.645454235739903e-06,
|
624 |
+
"loss": 0.0964,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.06747216299455105,
|
629 |
+
"grad_norm": 0.07747888565063477,
|
630 |
+
"learning_rate": 7.281614543321269e-06,
|
631 |
+
"loss": 0.1031,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.06823027718550106,
|
636 |
+
"grad_norm": 0.07711505889892578,
|
637 |
+
"learning_rate": 6.030737921409169e-06,
|
638 |
+
"loss": 0.0956,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.06898839137645107,
|
643 |
+
"grad_norm": 0.07614322006702423,
|
644 |
+
"learning_rate": 4.8943483704846475e-06,
|
645 |
+
"loss": 0.0981,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.06974650556740108,
|
650 |
+
"grad_norm": 0.0747898519039154,
|
651 |
+
"learning_rate": 3.873830406168111e-06,
|
652 |
+
"loss": 0.1131,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.0705046197583511,
|
657 |
+
"grad_norm": 0.07443447411060333,
|
658 |
+
"learning_rate": 2.970427372400353e-06,
|
659 |
+
"loss": 0.0941,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.07126273394930112,
|
664 |
+
"grad_norm": 0.07219017297029495,
|
665 |
+
"learning_rate": 2.1852399266194314e-06,
|
666 |
+
"loss": 0.0929,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.07202084814025113,
|
671 |
+
"grad_norm": 0.07864456623792648,
|
672 |
+
"learning_rate": 1.5192246987791981e-06,
|
673 |
+
"loss": 0.1065,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.07277896233120114,
|
678 |
+
"grad_norm": 0.08817560970783234,
|
679 |
+
"learning_rate": 9.731931258429638e-07,
|
680 |
+
"loss": 0.0988,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.07353707652215115,
|
685 |
+
"grad_norm": 0.08454511314630508,
|
686 |
+
"learning_rate": 5.478104631726711e-07,
|
687 |
+
"loss": 0.1063,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.07429519071310116,
|
692 |
+
"grad_norm": 0.08038944005966187,
|
693 |
+
"learning_rate": 2.4359497401758024e-07,
|
694 |
+
"loss": 0.097,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.07505330490405117,
|
699 |
+
"grad_norm": 0.0755147784948349,
|
700 |
+
"learning_rate": 6.09172980904238e-08,
|
701 |
+
"loss": 0.1059,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.07581141909500118,
|
706 |
+
"grad_norm": 0.07618386298418045,
|
707 |
+
"learning_rate": 0.0,
|
708 |
+
"loss": 0.1015,
|
709 |
+
"step": 100
|
710 |
}
|
711 |
],
|
712 |
"logging_steps": 1,
|
|
|
721 |
"should_evaluate": false,
|
722 |
"should_log": false,
|
723 |
"should_save": true,
|
724 |
+
"should_training_stop": true
|
725 |
},
|
726 |
"attributes": {}
|
727 |
}
|
728 |
},
|
729 |
+
"total_flos": 1.804942449135452e+17,
|
730 |
"train_batch_size": 8,
|
731 |
"trial_name": null,
|
732 |
"trial_params": null
|