aleegis10 commited on
Commit
8b40467
·
verified ·
1 Parent(s): 45c251c

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:e40e8e5d3ddaf27017016c2a1db0d99a6fc5db98d86bd330c133cfbf767a2707
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbb8a273f5667f254f0d238807509b3f069005e83f5bdc74ef69a1c68f1eb46
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e152281f4279a852431b922dcc794ed1300456ba9b0021ea36637f045ca3e826
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba03b5426a4fbc5d39119191353a898be019ee65dcf3056ac1c3409ddccb1c8
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48c4ac59ba539a1bab1aa6f1cd57dc7898ffeeb7b0ba848f00c91522557030eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eca96ca022fed76831f59c0941b67503bf26655fc8a190514e5d44bfcef2c2
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": 1.0513248443603516,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.11723329425556858,
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": 13.464,
374
  "eval_steps_per_second": 3.375,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.19077308849193e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9207891225814819,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.23446658851113716,
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": 13.464,
374
  "eval_steps_per_second": 3.375,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.11957796014067995,
379
+ "grad_norm": 24.633373260498047,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.7308,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.12192262602579132,
386
+ "grad_norm": 17.573421478271484,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 5.7586,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1242672919109027,
393
+ "grad_norm": 8.933952331542969,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.2271,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.12661195779601406,
400
+ "grad_norm": 9.926009178161621,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 4.4827,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.12895662368112543,
407
+ "grad_norm": 10.70360279083252,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.7757,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.13130128956623682,
414
+ "grad_norm": 8.511175155639648,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.934,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1336459554513482,
421
+ "grad_norm": 7.956448078155518,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.9996,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.13599062133645956,
428
+ "grad_norm": 9.405022621154785,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.8999,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.13833528722157093,
435
+ "grad_norm": 7.946819305419922,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.9496,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1406799531066823,
442
+ "grad_norm": 8.405508041381836,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.579,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.14302461899179367,
449
+ "grad_norm": 8.906330108642578,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.6143,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.14536928487690504,
456
+ "grad_norm": 9.379605293273926,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.7798,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1477139507620164,
463
+ "grad_norm": 8.477218627929688,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.588,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.15005861664712777,
470
+ "grad_norm": 7.908034801483154,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.589,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.15240328253223914,
477
+ "grad_norm": 8.690335273742676,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.4561,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.15474794841735054,
484
+ "grad_norm": 8.06505298614502,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.8101,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1570926143024619,
491
+ "grad_norm": 6.990350246429443,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.4838,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.15943728018757328,
498
+ "grad_norm": 7.266732692718506,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.2637,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.16178194607268465,
505
+ "grad_norm": 8.722139358520508,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.803,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.16412661195779601,
512
+ "grad_norm": 6.49424409866333,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.2726,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.16647127784290738,
519
+ "grad_norm": 8.221322059631348,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.0207,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.16881594372801875,
526
+ "grad_norm": 7.128183841705322,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.0073,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.17116060961313012,
533
+ "grad_norm": 7.4666619300842285,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.0837,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1735052754982415,
540
+ "grad_norm": 6.74752950668335,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.2209,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.17584994138335286,
547
+ "grad_norm": 6.79481315612793,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.1971,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.17819460726846426,
554
+ "grad_norm": 7.2510528564453125,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 3.0597,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.18053927315357562,
561
+ "grad_norm": 7.681369781494141,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.7634,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.182883939038687,
568
+ "grad_norm": 8.846420288085938,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.0827,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.18522860492379836,
575
+ "grad_norm": 8.721245765686035,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 3.1422,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.18757327080890973,
582
+ "grad_norm": 7.962874412536621,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.2284,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1899179366940211,
589
+ "grad_norm": 7.202088832855225,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.6309,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.19226260257913247,
596
+ "grad_norm": 7.756674289703369,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.0028,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.19460726846424384,
603
+ "grad_norm": 7.410325527191162,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.7875,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.1969519343493552,
610
+ "grad_norm": 7.595869064331055,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.9473,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.19929660023446658,
617
+ "grad_norm": 7.9515557289123535,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.1198,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.20164126611957797,
624
+ "grad_norm": 8.794443130493164,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.2781,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.20398593200468934,
631
+ "grad_norm": 9.458645820617676,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 3.2948,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.2063305978898007,
638
+ "grad_norm": 7.8468146324157715,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.0067,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.20867526377491208,
645
+ "grad_norm": 9.829216003417969,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.8751,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.21101992966002345,
652
+ "grad_norm": 7.089529991149902,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.7765,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.21336459554513482,
659
+ "grad_norm": 8.202539443969727,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.2057,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.21570926143024619,
666
+ "grad_norm": 8.448012351989746,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.3169,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.21805392731535755,
673
+ "grad_norm": 7.2261576652526855,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.8668,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.22039859320046892,
680
+ "grad_norm": 7.020049095153809,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.8429,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.2227432590855803,
687
+ "grad_norm": 7.415134906768799,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.5114,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.2250879249706917,
694
+ "grad_norm": 7.972723484039307,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.8023,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.22743259085580306,
701
+ "grad_norm": 8.125452995300293,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.9841,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.22977725674091443,
708
+ "grad_norm": 6.471831798553467,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.3228,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.2321219226260258,
715
+ "grad_norm": 6.832740783691406,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.2556,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.23446658851113716,
722
+ "grad_norm": 7.426825523376465,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.4321,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.23446658851113716,
729
+ "eval_loss": 0.9207891225814819,
730
+ "eval_runtime": 53.3707,
731
+ "eval_samples_per_second": 13.453,
732
+ "eval_steps_per_second": 3.373,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.438154617698386e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null