CocoRoF commited on
Commit
e4908aa
·
verified ·
1 Parent(s): d429ac7

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e35c0a039e011c6e00ef634a8dc0f2cda4896d950cbec75fb392478d5d17482
3
  size 737580392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a424a2b0f4bba2668648fad242ba4bc01129a8dfff560cb28160583a32cc8795
3
  size 737580392
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bd911e53eca1edc6531cdaf03144775e49eec62caac968aadbcc0c56c01cdb4
3
  size 1475248442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4147564c0aebe4adfc533256efb0c26f7c34d829d8cfd1faf86069796ae5e92b
3
  size 1475248442
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1b787e89d41eb6f9d786f351cf52ef6900e90a96d79898c6e78dbb6b0c072cc
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1798148c8ddbef876c6eb294160aa711b50b4fbc294eeefa2c2edd714ea4965e
3
  size 1000
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.23430178069353327,
5
  "eval_steps": 2.0,
6
- "global_step": 500,
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": 2.9707122774133083e-05,
358
  "loss": 0.4085,
359
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
360
  }
361
  ],
362
  "logging_steps": 10,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.46860356138706655,
5
  "eval_steps": 2.0,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
357
  "learning_rate": 2.9707122774133083e-05,
358
  "loss": 0.4085,
359
  "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.23898781630740393,
363
+ "grad_norm": 1.9792900085449219,
364
+ "learning_rate": 2.970126522961575e-05,
365
+ "loss": 0.4074,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.2436738519212746,
370
+ "grad_norm": 2.3620975017547607,
371
+ "learning_rate": 2.9695407685098408e-05,
372
+ "loss": 0.4076,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.24835988753514526,
377
+ "grad_norm": 1.7499839067459106,
378
+ "learning_rate": 2.968955014058107e-05,
379
+ "loss": 0.4033,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.2530459231490159,
384
+ "grad_norm": 2.367208480834961,
385
+ "learning_rate": 2.968369259606373e-05,
386
+ "loss": 0.4166,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.25773195876288657,
391
+ "grad_norm": 1.5346542596817017,
392
+ "learning_rate": 2.9677835051546395e-05,
393
+ "loss": 0.3523,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.2624179943767573,
398
+ "grad_norm": 2.177263021469116,
399
+ "learning_rate": 2.9671977507029054e-05,
400
+ "loss": 0.379,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.26710402999062793,
405
+ "grad_norm": 1.6328988075256348,
406
+ "learning_rate": 2.9666119962511716e-05,
407
+ "loss": 0.3885,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.2717900656044986,
412
+ "grad_norm": 2.2757279872894287,
413
+ "learning_rate": 2.9660262417994375e-05,
414
+ "loss": 0.3579,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.27647610121836924,
419
+ "grad_norm": 1.8637791872024536,
420
+ "learning_rate": 2.965440487347704e-05,
421
+ "loss": 0.4114,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.28116213683223995,
426
+ "grad_norm": 1.9911636114120483,
427
+ "learning_rate": 2.96485473289597e-05,
428
+ "loss": 0.3793,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.2858481724461106,
433
+ "grad_norm": 2.3302886486053467,
434
+ "learning_rate": 2.9642689784442362e-05,
435
+ "loss": 0.3858,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.29053420805998126,
440
+ "grad_norm": 1.5424076318740845,
441
+ "learning_rate": 2.9636832239925025e-05,
442
+ "loss": 0.3759,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.2952202436738519,
447
+ "grad_norm": 2.340257406234741,
448
+ "learning_rate": 2.9630974695407687e-05,
449
+ "loss": 0.3868,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.29990627928772257,
454
+ "grad_norm": 1.9387434720993042,
455
+ "learning_rate": 2.9625117150890346e-05,
456
+ "loss": 0.381,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.3045923149015933,
461
+ "grad_norm": 1.7054346799850464,
462
+ "learning_rate": 2.961925960637301e-05,
463
+ "loss": 0.3469,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.30927835051546393,
468
+ "grad_norm": 1.667858600616455,
469
+ "learning_rate": 2.961340206185567e-05,
470
+ "loss": 0.3419,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.3139643861293346,
475
+ "grad_norm": 2.5740160942077637,
476
+ "learning_rate": 2.9607544517338333e-05,
477
+ "loss": 0.3887,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.31865042174320524,
482
+ "grad_norm": 1.893171787261963,
483
+ "learning_rate": 2.9601686972820992e-05,
484
+ "loss": 0.3661,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.3233364573570759,
489
+ "grad_norm": 2.29376220703125,
490
+ "learning_rate": 2.9595829428303655e-05,
491
+ "loss": 0.408,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.3280224929709466,
496
+ "grad_norm": 1.6235976219177246,
497
+ "learning_rate": 2.958997188378632e-05,
498
+ "loss": 0.3872,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.33270852858481725,
503
+ "grad_norm": 1.8210023641586304,
504
+ "learning_rate": 2.958411433926898e-05,
505
+ "loss": 0.3276,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.3373945641986879,
510
+ "grad_norm": 2.2085988521575928,
511
+ "learning_rate": 2.9578256794751642e-05,
512
+ "loss": 0.378,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.34208059981255856,
517
+ "grad_norm": 1.9474214315414429,
518
+ "learning_rate": 2.95723992502343e-05,
519
+ "loss": 0.3429,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.3467666354264292,
524
+ "grad_norm": 1.4176770448684692,
525
+ "learning_rate": 2.9566541705716967e-05,
526
+ "loss": 0.3686,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.3514526710402999,
531
+ "grad_norm": 1.9044578075408936,
532
+ "learning_rate": 2.9560684161199626e-05,
533
+ "loss": 0.3359,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.3561387066541706,
538
+ "grad_norm": 2.1233558654785156,
539
+ "learning_rate": 2.9554826616682288e-05,
540
+ "loss": 0.3344,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.36082474226804123,
545
+ "grad_norm": 2.1498265266418457,
546
+ "learning_rate": 2.954896907216495e-05,
547
+ "loss": 0.3844,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.3655107778819119,
552
+ "grad_norm": 1.8201932907104492,
553
+ "learning_rate": 2.9543111527647613e-05,
554
+ "loss": 0.3395,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.3701968134957826,
559
+ "grad_norm": 1.6369259357452393,
560
+ "learning_rate": 2.953725398313027e-05,
561
+ "loss": 0.3046,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.37488284910965325,
566
+ "grad_norm": 1.9067765474319458,
567
+ "learning_rate": 2.9531396438612934e-05,
568
+ "loss": 0.3411,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.3795688847235239,
573
+ "grad_norm": 1.7853655815124512,
574
+ "learning_rate": 2.9525538894095596e-05,
575
+ "loss": 0.3942,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.38425492033739456,
580
+ "grad_norm": 1.6428436040878296,
581
+ "learning_rate": 2.951968134957826e-05,
582
+ "loss": 0.3446,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.3889409559512652,
587
+ "grad_norm": 1.761293649673462,
588
+ "learning_rate": 2.9513823805060918e-05,
589
+ "loss": 0.3368,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.3936269915651359,
594
+ "grad_norm": 1.8849061727523804,
595
+ "learning_rate": 2.950796626054358e-05,
596
+ "loss": 0.3595,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.3983130271790066,
601
+ "grad_norm": 1.6948515176773071,
602
+ "learning_rate": 2.9502108716026243e-05,
603
+ "loss": 0.3225,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.4029990627928772,
608
+ "grad_norm": 1.8712960481643677,
609
+ "learning_rate": 2.9496251171508905e-05,
610
+ "loss": 0.3528,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.4076850984067479,
615
+ "grad_norm": 2.2388830184936523,
616
+ "learning_rate": 2.9490393626991564e-05,
617
+ "loss": 0.3981,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.41237113402061853,
622
+ "grad_norm": 1.8384082317352295,
623
+ "learning_rate": 2.9484536082474226e-05,
624
+ "loss": 0.3575,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.41705716963448924,
629
+ "grad_norm": 2.068216323852539,
630
+ "learning_rate": 2.947867853795689e-05,
631
+ "loss": 0.3448,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.4217432052483599,
636
+ "grad_norm": 1.5086658000946045,
637
+ "learning_rate": 2.947282099343955e-05,
638
+ "loss": 0.3214,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.42642924086223055,
643
+ "grad_norm": 1.5989112854003906,
644
+ "learning_rate": 2.946696344892221e-05,
645
+ "loss": 0.2719,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.4311152764761012,
650
+ "grad_norm": 2.223735809326172,
651
+ "learning_rate": 2.9461105904404876e-05,
652
+ "loss": 0.3691,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.43580131208997186,
657
+ "grad_norm": 1.928982138633728,
658
+ "learning_rate": 2.9455248359887535e-05,
659
+ "loss": 0.3446,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.44048734770384257,
664
+ "grad_norm": 1.7856864929199219,
665
+ "learning_rate": 2.9449390815370197e-05,
666
+ "loss": 0.2984,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.4451733833177132,
671
+ "grad_norm": 2.044851779937744,
672
+ "learning_rate": 2.944353327085286e-05,
673
+ "loss": 0.3396,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.4498594189315839,
678
+ "grad_norm": 1.5885918140411377,
679
+ "learning_rate": 2.9437675726335522e-05,
680
+ "loss": 0.3529,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.45454545454545453,
685
+ "grad_norm": 2.08933162689209,
686
+ "learning_rate": 2.9431818181818184e-05,
687
+ "loss": 0.3561,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.4592314901593252,
692
+ "grad_norm": 1.5980266332626343,
693
+ "learning_rate": 2.9425960637300843e-05,
694
+ "loss": 0.3512,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.4639175257731959,
699
+ "grad_norm": 1.570770025253296,
700
+ "learning_rate": 2.9420103092783506e-05,
701
+ "loss": 0.3678,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.46860356138706655,
706
+ "grad_norm": 1.8862972259521484,
707
+ "learning_rate": 2.9414245548266168e-05,
708
+ "loss": 0.3148,
709
+ "step": 1000
710
  }
711
  ],
712
  "logging_steps": 10,