bbytxt commited on
Commit
7d56552
·
verified ·
1 Parent(s): aec4668

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 sha256:7004c75f4713ba81fe22db0daa33c543bafa5e7e0ddb559a6ff38f60534430d5
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99533a9d7c2857fdc4e955ca7997556f75c499406b0f6cb5f1286c89ee5d0480
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:837f54eb808950e13e093cce8baf81f5655ba0fe3c557bdc77d47e594d261d90
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76d5b50b6da299efbc02ab1166f36e67b83169d691db4a8a78090c7ffbb4793
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:269ec53bbf81fd110d90521b68dd3c780de6fea460696bdaff8eefb598563448
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482236dbef88e7c380ab00a82b450ba23d9758454612771f37e26613148477e6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.869421005249023,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.033818058843422386,
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": 85.006,
374
  "eval_steps_per_second": 21.269,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 71616430080000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.861373901367188,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06763611768684477,
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": 85.006,
374
  "eval_steps_per_second": 21.269,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.034494420020290836,
379
+ "grad_norm": 0.10370208323001862,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 11.8716,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03517078119715928,
386
+ "grad_norm": 0.11750881373882294,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 11.8691,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03584714237402773,
393
+ "grad_norm": 0.12145090848207474,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 11.8695,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03652350355089618,
400
+ "grad_norm": 0.13088250160217285,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 11.8705,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.037199864727764625,
407
+ "grad_norm": 0.09613314270973206,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 11.8733,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.037876225904633076,
414
+ "grad_norm": 0.1183629110455513,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 11.8643,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03855258708150152,
421
+ "grad_norm": 0.12383581697940826,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 11.8681,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03922894825836997,
428
+ "grad_norm": 0.11309259384870529,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 11.875,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.039905309435238415,
435
+ "grad_norm": 0.11675012856721878,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 11.8738,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.040581670612106865,
442
+ "grad_norm": 0.10582835972309113,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 11.87,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.041258031788975316,
449
+ "grad_norm": 0.09874629229307175,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 11.8641,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04193439296584376,
456
+ "grad_norm": 0.12302418053150177,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 11.8709,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04261075414271221,
463
+ "grad_norm": 0.10224100947380066,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 11.8673,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.043287115319580655,
470
+ "grad_norm": 0.10085669159889221,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 11.8668,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.043963476496449105,
477
+ "grad_norm": 0.13070064783096313,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 11.8688,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04463983767331755,
484
+ "grad_norm": 0.13864661753177643,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 11.8677,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.045316198850186,
491
+ "grad_norm": 0.09276090562343597,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 11.8625,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.045992560027054444,
498
+ "grad_norm": 0.09893247485160828,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 11.87,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.046668921203922895,
505
+ "grad_norm": 0.13095833361148834,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 11.8678,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.047345282380791345,
512
+ "grad_norm": 0.11731155961751938,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 11.8673,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04802164355765979,
519
+ "grad_norm": 0.13166551291942596,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 11.8684,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04869800473452824,
526
+ "grad_norm": 0.09939809143543243,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 11.8639,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.049374365911396684,
533
+ "grad_norm": 0.10804695636034012,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 11.8663,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.050050727088265135,
540
+ "grad_norm": 0.132675901055336,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 11.8729,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05072708826513358,
547
+ "grad_norm": 0.07454847544431686,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 11.8687,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.05140344944200203,
554
+ "grad_norm": 0.0866214781999588,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 11.8705,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05207981061887048,
561
+ "grad_norm": 0.10776250809431076,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 11.8614,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.052756171795738924,
568
+ "grad_norm": 0.10304714739322662,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 11.8647,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.053432532972607374,
575
+ "grad_norm": 0.1364087164402008,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 11.8626,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05410889414947582,
582
+ "grad_norm": 0.10210411995649338,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 11.8653,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05478525532634427,
589
+ "grad_norm": 0.11438775807619095,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 11.8666,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05546161650321271,
596
+ "grad_norm": 0.10912539064884186,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 11.8596,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.056137977680081164,
603
+ "grad_norm": 0.09880189597606659,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 11.8633,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.056814338856949614,
610
+ "grad_norm": 0.12287990748882294,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 11.8604,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05749070003381806,
617
+ "grad_norm": 0.09658095985651016,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 11.858,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05816706121068651,
624
+ "grad_norm": 0.13980063796043396,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 11.8644,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05884342238755495,
631
+ "grad_norm": 0.08649631589651108,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 11.8617,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.059519783564423404,
638
+ "grad_norm": 0.08612903207540512,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 11.8668,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06019614474129185,
645
+ "grad_norm": 0.09304578602313995,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 11.8581,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0608725059181603,
652
+ "grad_norm": 0.13147549331188202,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 11.8606,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06154886709502874,
659
+ "grad_norm": 0.10700445622205734,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 11.8609,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06222522827189719,
666
+ "grad_norm": 0.08180303126573563,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 11.8625,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06290158944876564,
673
+ "grad_norm": 0.12455767393112183,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 11.8555,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0635779506256341,
680
+ "grad_norm": 0.12393002957105637,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 11.856,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06425431180250253,
687
+ "grad_norm": 0.11348329484462738,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 11.8579,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06493067297937098,
694
+ "grad_norm": 0.1379508674144745,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 11.8601,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06560703415623943,
701
+ "grad_norm": 0.12759019434452057,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 11.8519,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06628339533310788,
708
+ "grad_norm": 0.11706313490867615,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 11.8518,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06695975650997633,
715
+ "grad_norm": 0.11291486769914627,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 11.8508,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06763611768684477,
722
+ "grad_norm": 0.3588656783103943,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 11.8606,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06763611768684477,
729
+ "eval_loss": 11.861373901367188,
730
+ "eval_runtime": 29.5448,
731
+ "eval_samples_per_second": 84.279,
732
+ "eval_steps_per_second": 21.087,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 144885547008000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null