error577 commited on
Commit
11471e4
·
verified ·
1 Parent(s): e4aee78

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 sha256:9e36ed3eb44137ca523efd8833cb60762f1e61dbec2b0cd18e72b9aeb1f1e521
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97642e136151e3a09e808379eef2fecef73219b004ebb9f7a3309d2517a294e
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb062722d92b3fb966623ae1d137b24bd5ce1a08d81de396a6f8855d5b328d23
3
  size 325350676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5459f482f6f7da1227d483195156eddea6a6018406f5ff17d1cc998ad4b7e5c4
3
  size 325350676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5915d9c3b1deb3d66ce6ff11178835811888398e5199a01a9136f0a008ed6a10
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:087dcab9226ebf346313274a0882bdef04148af7ce47f7c1e36fc8cddaa638da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:334bbc899bb81da08f819d8b11c03beff0273a7dc775498883f219a1bc69024b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fddcf499277c4af2245b02791ec09b990baef798e350062113352bea3a46779c
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": 0.001757361146502412,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 4.668,
374
  "eval_steps_per_second": 4.668,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,12 +745,12 @@
387
  "should_evaluate": false,
388
  "should_log": false,
389
  "should_save": true,
390
- "should_training_stop": false
391
  },
392
  "attributes": {}
393
  }
394
  },
395
- "total_flos": 4482169061769216.0,
396
  "train_batch_size": 1,
397
  "trial_name": null,
398
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003514722293004824,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 4.668,
374
  "eval_steps_per_second": 4.668,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0017925083694324603,
379
+ "grad_norm": 6.184074878692627,
380
+ "learning_rate": 0.0001708759651440098,
381
+ "loss": 3.1531,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0018276555923625085,
386
+ "grad_norm": 10.926563262939453,
387
+ "learning_rate": 0.000165679269490148,
388
+ "loss": 3.6512,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0018628028152925568,
393
+ "grad_norm": 6.391138553619385,
394
+ "learning_rate": 0.00016046347106161876,
395
+ "loss": 2.8123,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.001897950038222605,
400
+ "grad_norm": 3.9918131828308105,
401
+ "learning_rate": 0.00015523492450537517,
402
+ "loss": 2.6699,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0019330972611526533,
407
+ "grad_norm": 5.609512805938721,
408
+ "learning_rate": 0.00015,
409
+ "loss": 2.3293,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0019682444840827015,
414
+ "grad_norm": 5.8025031089782715,
415
+ "learning_rate": 0.0001447650754946249,
416
+ "loss": 2.0517,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0020033917070127498,
421
+ "grad_norm": 7.59370756149292,
422
+ "learning_rate": 0.00013953652893838119,
423
+ "loss": 3.0335,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.002038538929942798,
428
+ "grad_norm": 7.709898948669434,
429
+ "learning_rate": 0.000134320730509852,
430
+ "loss": 3.0555,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.0020736861528728463,
435
+ "grad_norm": 5.140454292297363,
436
+ "learning_rate": 0.0001291240348559902,
437
+ "loss": 2.6652,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.0021088333758028945,
442
+ "grad_norm": 6.058025360107422,
443
+ "learning_rate": 0.00012395277334996044,
444
+ "loss": 2.7671,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0021439805987329428,
449
+ "grad_norm": 9.216087341308594,
450
+ "learning_rate": 0.00011881324637733611,
451
+ "loss": 2.7076,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.002179127821662991,
456
+ "grad_norm": 8.128350257873535,
457
+ "learning_rate": 0.00011371171566004985,
458
+ "loss": 2.7331,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0022142750445930393,
463
+ "grad_norm": 7.724212169647217,
464
+ "learning_rate": 0.00010865439662745013,
465
+ "loss": 2.625,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0022494222675230875,
470
+ "grad_norm": 5.113654613494873,
471
+ "learning_rate": 0.0001036474508437579,
472
+ "loss": 2.2554,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0022845694904531358,
477
+ "grad_norm": 7.291034698486328,
478
+ "learning_rate": 9.869697850114969e-05,
479
+ "loss": 2.0766,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.002319716713383184,
484
+ "grad_norm": 6.133238792419434,
485
+ "learning_rate": 9.380901098761319e-05,
486
+ "loss": 2.6534,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0023548639363132323,
491
+ "grad_norm": 8.07371711730957,
492
+ "learning_rate": 8.898950353862998e-05,
493
+ "loss": 3.2567,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0023900111592432805,
498
+ "grad_norm": 8.47569465637207,
499
+ "learning_rate": 8.424432798163836e-05,
500
+ "loss": 2.3998,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0024251583821733283,
505
+ "grad_norm": 6.5739850997924805,
506
+ "learning_rate": 7.957926558211642e-05,
507
+ "loss": 2.8606,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0024603056051033766,
512
+ "grad_norm": 10.502620697021484,
513
+ "learning_rate": 7.500000000000002e-05,
514
+ "loss": 2.7211,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.002495452828033425,
519
+ "grad_norm": 6.819766998291016,
520
+ "learning_rate": 7.051211036501928e-05,
521
+ "loss": 2.7132,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.002530600050963473,
526
+ "grad_norm": 8.332561492919922,
527
+ "learning_rate": 6.612106447938799e-05,
528
+ "loss": 3.0188,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0025657472738935213,
533
+ "grad_norm": 7.98085355758667,
534
+ "learning_rate": 6.183221215612904e-05,
535
+ "loss": 1.8015,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0026008944968235696,
540
+ "grad_norm": 7.219940662384033,
541
+ "learning_rate": 5.765077870115125e-05,
542
+ "loss": 2.4322,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.002636041719753618,
547
+ "grad_norm": 7.731595993041992,
548
+ "learning_rate": 5.358185854701909e-05,
549
+ "loss": 3.1412,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.002671188942683666,
554
+ "grad_norm": 6.916698932647705,
555
+ "learning_rate": 4.963040904617131e-05,
556
+ "loss": 4.0983,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0027063361656137143,
561
+ "grad_norm": 7.314121246337891,
562
+ "learning_rate": 4.5801244431150394e-05,
563
+ "loss": 2.8968,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0027414833885437626,
568
+ "grad_norm": 7.5785441398620605,
569
+ "learning_rate": 4.209902994920235e-05,
570
+ "loss": 2.643,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.002776630611473811,
575
+ "grad_norm": 6.763470649719238,
576
+ "learning_rate": 3.852827617839084e-05,
577
+ "loss": 2.8279,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.002811777834403859,
582
+ "grad_norm": 8.693899154663086,
583
+ "learning_rate": 3.509333353215331e-05,
584
+ "loss": 2.7579,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0028469250573339073,
589
+ "grad_norm": 5.903140068054199,
590
+ "learning_rate": 3.1798386958991714e-05,
591
+ "loss": 2.596,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0028820722802639556,
596
+ "grad_norm": 6.02622127532959,
597
+ "learning_rate": 2.8647450843757897e-05,
598
+ "loss": 2.5302,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.002917219503194004,
603
+ "grad_norm": 6.922908306121826,
604
+ "learning_rate": 2.5644364116743755e-05,
605
+ "loss": 2.5549,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.002952366726124052,
610
+ "grad_norm": 6.8705973625183105,
611
+ "learning_rate": 2.2792785576536105e-05,
612
+ "loss": 2.7103,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0029875139490541003,
617
+ "grad_norm": 8.229166030883789,
618
+ "learning_rate": 2.009618943233419e-05,
619
+ "loss": 3.2369,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0030226611719841485,
624
+ "grad_norm": 5.061288833618164,
625
+ "learning_rate": 1.755786107116095e-05,
626
+ "loss": 2.3396,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.003057808394914197,
631
+ "grad_norm": 5.73906946182251,
632
+ "learning_rate": 1.5180893055124977e-05,
633
+ "loss": 2.1163,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.003092955617844245,
638
+ "grad_norm": 6.186309814453125,
639
+ "learning_rate": 1.2968181353609852e-05,
640
+ "loss": 3.2023,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0031281028407742933,
645
+ "grad_norm": 8.73239517211914,
646
+ "learning_rate": 1.0922421814981901e-05,
647
+ "loss": 2.935,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0031632500637043415,
652
+ "grad_norm": 8.442344665527344,
653
+ "learning_rate": 9.046106882113751e-06,
654
+ "loss": 2.048,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.00319839728663439,
659
+ "grad_norm": 9.889983177185059,
660
+ "learning_rate": 7.34152255572697e-06,
661
+ "loss": 3.0998,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.003233544509564438,
666
+ "grad_norm": 7.554132461547852,
667
+ "learning_rate": 5.810745609252165e-06,
668
+ "loss": 2.7425,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0032686917324944863,
673
+ "grad_norm": 18.795644760131836,
674
+ "learning_rate": 4.455641058600528e-06,
675
+ "loss": 2.7303,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0033038389554245345,
680
+ "grad_norm": 9.423656463623047,
681
+ "learning_rate": 3.2778598899291465e-06,
682
+ "loss": 3.1626,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.003338986178354583,
687
+ "grad_norm": 10.255327224731445,
688
+ "learning_rate": 2.2788370481687965e-06,
689
+ "loss": 3.7099,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.003374133401284631,
694
+ "grad_norm": 7.863884925842285,
695
+ "learning_rate": 1.4597896887644456e-06,
696
+ "loss": 2.9709,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0034092806242146793,
701
+ "grad_norm": 9.880104064941406,
702
+ "learning_rate": 8.217156947590064e-07,
703
+ "loss": 3.5264,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0034444278471447275,
708
+ "grad_norm": 8.848705291748047,
709
+ "learning_rate": 3.653924610263703e-07,
710
+ "loss": 2.9102,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.003479575070074776,
715
+ "grad_norm": 8.545324325561523,
716
+ "learning_rate": 9.137594713563568e-08,
717
+ "loss": 2.644,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.003514722293004824,
722
+ "grad_norm": 14.05859088897705,
723
+ "learning_rate": 0.0,
724
+ "loss": 3.0055,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.003514722293004824,
729
+ "eval_loss": 2.7083585262298584,
730
+ "eval_runtime": 122.4923,
731
+ "eval_samples_per_second": 4.67,
732
+ "eval_steps_per_second": 4.67,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "should_evaluate": false,
746
  "should_log": false,
747
  "should_save": true,
748
+ "should_training_stop": true
749
  },
750
  "attributes": {}
751
  }
752
  },
753
+ "total_flos": 8964338123538432.0,
754
  "train_batch_size": 1,
755
  "trial_name": null,
756
  "trial_params": null