nttx commited on
Commit
46dbd26
·
verified ·
1 Parent(s): 05416a8

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:aa9585de44930e347b229ca4290d805d98fb91cbc8f11cb42f875d66077312d3
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789690cd1836515e90630dec5035db3f5034b060ca001e213162f9284ee40a8d
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e94aa8600fd446b1d3a8ac1dcd0606eb1b32a331d9abd2bce14fbec34ff8aee6
3
  size 204106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf11943cff04c02a0b28adaeb360c33dab52c123cf72bd75608ebb10f8d1bea8
3
  size 204106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b49280e55e47f07ac1a2e05a8f85f02d49d998ec0ace0f44a5538b3ae005d52
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8a86acba02d2940ce4773ab584fa08e1eb6c394e28514e3d0450b0e0e5988a
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": 11.932246208190918,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.08107012565869477,
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": 188.476,
374
  "eval_steps_per_second": 23.582,
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": 242246615040.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.932085037231445,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.16214025131738954,
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": 188.476,
374
  "eval_steps_per_second": 23.582,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.08269152817186867,
379
+ "grad_norm": 0.06557369232177734,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 11.9359,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.08431293068504256,
386
+ "grad_norm": 0.054183050990104675,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 11.9378,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.08593433319821646,
393
+ "grad_norm": 0.06125367805361748,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 11.9401,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.08755573571139036,
400
+ "grad_norm": 0.07734334468841553,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 11.9367,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.08917713822456425,
407
+ "grad_norm": 0.07164815068244934,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 11.9412,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.09079854073773815,
414
+ "grad_norm": 0.07205943763256073,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 11.9377,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.09241994325091205,
421
+ "grad_norm": 0.06834626942873001,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 11.9395,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.09404134576408593,
428
+ "grad_norm": 0.07087212055921555,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 11.9404,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.09566274827725983,
435
+ "grad_norm": 0.06267399340867996,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 11.9416,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.09728415079043372,
442
+ "grad_norm": 0.05978712439537048,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 11.9396,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.09890555330360762,
449
+ "grad_norm": 0.06278885900974274,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 11.938,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.10052695581678152,
456
+ "grad_norm": 0.06936422735452652,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 11.9391,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1021483583299554,
463
+ "grad_norm": 0.06972584128379822,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 11.9379,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1037697608431293,
470
+ "grad_norm": 0.06474191695451736,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 11.9415,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1053911633563032,
477
+ "grad_norm": 0.0643126517534256,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 11.9368,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.10701256586947709,
484
+ "grad_norm": 0.060131411999464035,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 11.9366,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.10863396838265099,
491
+ "grad_norm": 0.07099177688360214,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 11.9369,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.11025537089582489,
498
+ "grad_norm": 0.0853051170706749,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 11.9387,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.11187677340899878,
505
+ "grad_norm": 0.07782307267189026,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 11.9346,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.11349817592217268,
512
+ "grad_norm": 0.07038868218660355,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 11.9369,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.11511957843534658,
519
+ "grad_norm": 0.06611315160989761,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 11.9369,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.11674098094852046,
526
+ "grad_norm": 0.06813161075115204,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 11.9355,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.11836238346169436,
533
+ "grad_norm": 0.07219278067350388,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 11.9318,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.11998378597486827,
540
+ "grad_norm": 0.07824105024337769,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 11.9312,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.12160518848804215,
547
+ "grad_norm": 0.08129618316888809,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 11.9319,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.12322659100121605,
554
+ "grad_norm": 0.06890939921140671,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 11.9365,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.12484799351438995,
561
+ "grad_norm": 0.08247758448123932,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 11.9334,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.12646939602756385,
568
+ "grad_norm": 0.09313575178384781,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 11.9232,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.12809079854073774,
575
+ "grad_norm": 0.05831461772322655,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 11.9322,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.12971220105391162,
582
+ "grad_norm": 0.06037887558341026,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 11.9308,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.13133360356708554,
589
+ "grad_norm": 0.07506049424409866,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 11.9268,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.13295500608025942,
596
+ "grad_norm": 0.0684242770075798,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 11.9232,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1345764085934333,
603
+ "grad_norm": 0.07387068122625351,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 11.9302,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.13619781110660723,
610
+ "grad_norm": 0.09172695875167847,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 11.9247,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1378192136197811,
617
+ "grad_norm": 0.07359951734542847,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 11.9305,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.139440616132955,
624
+ "grad_norm": 0.09183831512928009,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 11.9322,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.1410620186461289,
631
+ "grad_norm": 0.0872773602604866,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 11.9244,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.1426834211593028,
638
+ "grad_norm": 0.10315699130296707,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 11.9244,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.14430482367247668,
645
+ "grad_norm": 0.10300548374652863,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 11.9305,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1459262261856506,
652
+ "grad_norm": 0.09078492969274521,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 11.9307,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.14754762869882448,
659
+ "grad_norm": 0.08630198240280151,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 11.9279,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.14916903121199837,
666
+ "grad_norm": 0.11776189506053925,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 11.928,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.15079043372517228,
673
+ "grad_norm": 0.11010502278804779,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 11.9303,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.15241183623834617,
680
+ "grad_norm": 0.10045027732849121,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 11.9332,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.15403323875152006,
687
+ "grad_norm": 0.10060346871614456,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 11.9345,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.15565464126469397,
694
+ "grad_norm": 0.092365562915802,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 11.9306,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.15727604377786786,
701
+ "grad_norm": 0.13334056735038757,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 11.9357,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.15889744629104174,
708
+ "grad_norm": 0.1075684055685997,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 11.9331,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.16051884880421566,
715
+ "grad_norm": 0.1268085241317749,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 11.936,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.16214025131738954,
722
+ "grad_norm": 0.13361109793186188,
723
+ "learning_rate": 0.0,
724
+ "loss": 11.9422,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.16214025131738954,
729
+ "eval_loss": 11.932085037231445,
730
+ "eval_runtime": 5.5292,
731
+ "eval_samples_per_second": 187.91,
732
+ "eval_steps_per_second": 23.511,
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": 484493230080.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null