bbytxt commited on
Commit
c0979bb
·
verified ·
1 Parent(s): 29492f7

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 sha256:844ca6a710741dbae123f11124fd45ebbd775591069ae1c095be0531420e8c4e
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f3f00a37526f73aa9a46d560965c6e512d7db6f8250c623eb7a8320f53366f
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb6c68918be405ebbaf472903b2638500b74510dcf4a42e3b722d651b33f0c3a
3
  size 403961210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0dfc927ce63e88f3d2b41db98fac65d0659fb38ae2b36aa9d40314117c7af06
3
  size 403961210
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f02a89b1300864a6f89aa0f8d373a538621b90c0581e0d6ef037d60eb8b9092d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04287158be3dd25edf2b56f89647fe89f21b744c8af7c8a445ffcfef6d76d93f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.852181434631348,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 1.415492957746479,
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": 48.819,
374
  "eval_steps_per_second": 6.509,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.06657392623616e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.300358295440674,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 2.830985915492958,
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": 48.819,
374
  "eval_steps_per_second": 6.509,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.443661971830986,
379
+ "grad_norm": 5.88961124420166,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 5.3644,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 1.471830985915493,
386
+ "grad_norm": 4.989941120147705,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 5.3129,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 1.5,
393
+ "grad_norm": 5.352567672729492,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 5.1404,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 1.528169014084507,
400
+ "grad_norm": 5.720556259155273,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 4.8448,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 1.556338028169014,
407
+ "grad_norm": 5.738869667053223,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 5.2918,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.584507042253521,
414
+ "grad_norm": 5.720866680145264,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 4.7,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.612676056338028,
421
+ "grad_norm": 5.672741413116455,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 5.124,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.6408450704225352,
428
+ "grad_norm": 5.708094120025635,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 5.3825,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.6690140845070423,
435
+ "grad_norm": 4.969758033752441,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 5.2906,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.6971830985915493,
442
+ "grad_norm": 4.994139194488525,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 5.1099,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.7253521126760565,
449
+ "grad_norm": 5.776417255401611,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 4.8853,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.7535211267605635,
456
+ "grad_norm": 5.504635334014893,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 4.8793,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.7816901408450705,
463
+ "grad_norm": 5.382895469665527,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 4.9927,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.8098591549295775,
470
+ "grad_norm": 5.304967403411865,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 4.8314,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.8380281690140845,
477
+ "grad_norm": 5.1869893074035645,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 5.233,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.8661971830985915,
484
+ "grad_norm": 6.1123366355896,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 4.9092,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.8943661971830985,
491
+ "grad_norm": 5.411812782287598,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 5.1397,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.9225352112676055,
498
+ "grad_norm": 5.654954433441162,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 4.6659,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.9507042253521125,
505
+ "grad_norm": 5.411698341369629,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 4.8395,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.9788732394366197,
512
+ "grad_norm": 5.4398064613342285,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 5.1385,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 2.0140845070422535,
519
+ "grad_norm": 10.192140579223633,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 7.7338,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 2.0422535211267605,
526
+ "grad_norm": 5.421514511108398,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 4.567,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 2.0704225352112675,
533
+ "grad_norm": 5.557625770568848,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 4.3131,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 2.0985915492957745,
540
+ "grad_norm": 5.216914653778076,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 4.5585,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 2.1267605633802815,
547
+ "grad_norm": 5.993343830108643,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 4.6337,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 2.1549295774647885,
554
+ "grad_norm": 5.094235420227051,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 4.8541,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 2.183098591549296,
561
+ "grad_norm": 5.717433929443359,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 5.2967,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 2.211267605633803,
568
+ "grad_norm": 5.293563365936279,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 4.8659,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 2.23943661971831,
575
+ "grad_norm": 5.073064804077148,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 4.9172,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 2.267605633802817,
582
+ "grad_norm": 5.354030609130859,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 4.6161,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 2.295774647887324,
589
+ "grad_norm": 5.201179504394531,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 4.7591,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 2.323943661971831,
596
+ "grad_norm": 5.040406227111816,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 4.7533,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 2.352112676056338,
603
+ "grad_norm": 5.279065132141113,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 4.6149,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 2.380281690140845,
610
+ "grad_norm": 5.657581329345703,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 4.4146,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 2.408450704225352,
617
+ "grad_norm": 5.0008931159973145,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 4.374,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 2.436619718309859,
624
+ "grad_norm": 5.283320426940918,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 4.5699,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 2.464788732394366,
631
+ "grad_norm": 5.353503704071045,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 4.6215,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 2.492957746478873,
638
+ "grad_norm": 5.431240081787109,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 4.5881,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 2.52112676056338,
645
+ "grad_norm": 5.6447858810424805,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 4.2597,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 2.5492957746478875,
652
+ "grad_norm": 5.344186305999756,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 4.4999,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 2.5774647887323945,
659
+ "grad_norm": 5.2609477043151855,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 4.5457,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 2.6056338028169015,
666
+ "grad_norm": 5.623130798339844,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 4.4276,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 2.6338028169014085,
673
+ "grad_norm": 5.679134845733643,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 4.7285,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 2.6619718309859155,
680
+ "grad_norm": 5.343556880950928,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 4.7053,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 2.6901408450704225,
687
+ "grad_norm": 4.940552711486816,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 4.4612,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 2.7183098591549295,
694
+ "grad_norm": 5.611880779266357,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 4.37,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 2.7464788732394365,
701
+ "grad_norm": 5.197037220001221,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 4.5959,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 2.7746478873239435,
708
+ "grad_norm": 5.572286605834961,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 4.5331,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 2.802816901408451,
715
+ "grad_norm": 5.335962772369385,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 4.3457,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 2.830985915492958,
722
+ "grad_norm": 5.259434223175049,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.7794,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 2.830985915492958,
729
+ "eval_loss": 4.300358295440674,
730
+ "eval_runtime": 1.2256,
731
+ "eval_samples_per_second": 48.955,
732
+ "eval_steps_per_second": 6.527,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.13314785247232e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null