aleegis09 commited on
Commit
01d4639
·
verified ·
1 Parent(s): e71d31f

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 sha256:500ef376f2deb682811316db03e667ef24083975f7f50d62d77f62070af3e1a3
3
  size 377538512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43a40f019c95f25c9c1983f62f20689fe8dda19085b62df82e68939655343a1
3
  size 377538512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f85bfc473add60ccd12b383300eecd18304c04aa3a1370f5af81b88ad7b872a4
3
  size 192144596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e25511e18572bd2d81305b78816b7cf0c8ebbae03aed7dcefd7a2b112e36b4a
3
  size 192144596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e5cd16290db2bb0b98c6ce0d298625aee4b740f8ad76460a497e1e9edfa3fc0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e764aedd8b9c13f90658d271fddebd975714b2530a45a8a63f22d4174f76524
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": 2.9756832122802734,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.09704027171276079,
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": 10.506,
374
  "eval_steps_per_second": 2.626,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 5.3929253535744e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0220495462417603,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.19408054342552158,
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": 10.506,
374
  "eval_steps_per_second": 2.626,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.09898107714701601,
379
+ "grad_norm": 71.17930603027344,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 5.2893,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.10092188258127123,
386
+ "grad_norm": 52.50294876098633,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.4814,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.10286268801552645,
393
+ "grad_norm": 26.074068069458008,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.5954,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.10480349344978165,
400
+ "grad_norm": 7.427390098571777,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.8787,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.10674429888403687,
407
+ "grad_norm": 3.58815860748291,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6604,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.10868510431829209,
414
+ "grad_norm": 2.99554443359375,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.5315,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.11062590975254731,
421
+ "grad_norm": 2.7059144973754883,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.5737,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.11256671518680253,
428
+ "grad_norm": 1.8956794738769531,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5386,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.11450752062105773,
435
+ "grad_norm": 2.838517189025879,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.5438,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.11644832605531295,
442
+ "grad_norm": 2.675584316253662,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6574,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.11838913148956817,
449
+ "grad_norm": 2.1755335330963135,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.5774,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.12032993692382339,
456
+ "grad_norm": 2.3560686111450195,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5783,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.1222707423580786,
463
+ "grad_norm": 1.8677828311920166,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5582,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.12421154779233382,
470
+ "grad_norm": 2.1840298175811768,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.645,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.12615235322658905,
477
+ "grad_norm": 2.2143750190734863,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5533,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.12809315866084425,
484
+ "grad_norm": 2.0592188835144043,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6437,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.13003396409509946,
491
+ "grad_norm": 2.2719454765319824,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.6332,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1319747695293547,
498
+ "grad_norm": 2.2744674682617188,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5922,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1339155749636099,
505
+ "grad_norm": 2.8700437545776367,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6904,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.1358563803978651,
512
+ "grad_norm": 2.6853842735290527,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.6535,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.13779718583212033,
519
+ "grad_norm": 3.1052772998809814,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7032,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.13973799126637554,
526
+ "grad_norm": 2.2774715423583984,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7064,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.14167879670063077,
533
+ "grad_norm": 3.7868194580078125,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.6476,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.14361960213488598,
540
+ "grad_norm": 2.482116460800171,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.577,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.14556040756914118,
547
+ "grad_norm": 3.1218602657318115,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.8259,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.14750121300339641,
554
+ "grad_norm": 4.078639030456543,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.8581,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.14944201843765162,
561
+ "grad_norm": 4.382765769958496,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.8175,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.15138282387190685,
568
+ "grad_norm": 3.7048816680908203,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.808,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.15332362930616206,
575
+ "grad_norm": 4.033629417419434,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.7593,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.15526443474041726,
582
+ "grad_norm": 4.56980037689209,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.672,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1572052401746725,
589
+ "grad_norm": 4.158092975616455,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.6214,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1591460456089277,
596
+ "grad_norm": 4.216987133026123,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.6047,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.16108685104318293,
603
+ "grad_norm": 3.5317301750183105,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6012,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.16302765647743814,
610
+ "grad_norm": 12.014446258544922,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.9439,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.16496846191169334,
617
+ "grad_norm": 22.006229400634766,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.583,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.16690926734594858,
624
+ "grad_norm": 37.996788024902344,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.3416,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.16885007278020378,
631
+ "grad_norm": 20.80458641052246,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.9229,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.170790878214459,
638
+ "grad_norm": 20.84687042236328,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.8207,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.17273168364871422,
645
+ "grad_norm": 17.68490982055664,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6995,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.17467248908296942,
652
+ "grad_norm": 25.93991470336914,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.5536,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.17661329451722466,
659
+ "grad_norm": 16.228805541992188,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.2994,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.17855409995147986,
666
+ "grad_norm": 8.50417423248291,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.1472,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.1804949053857351,
673
+ "grad_norm": 11.803483009338379,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.1267,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1824357108199903,
680
+ "grad_norm": 6.2093424797058105,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0646,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1843765162542455,
687
+ "grad_norm": 17.27790069580078,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.07,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.18631732168850074,
694
+ "grad_norm": 6.931070804595947,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.1174,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.18825812712275594,
701
+ "grad_norm": 10.341382026672363,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0852,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.19019893255701115,
708
+ "grad_norm": 6.310524940490723,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.053,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.19213973799126638,
715
+ "grad_norm": 3.348977565765381,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0262,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.19408054342552158,
722
+ "grad_norm": 4.910148620605469,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0362,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.19408054342552158,
729
+ "eval_loss": 1.0220495462417603,
730
+ "eval_runtime": 82.6786,
731
+ "eval_samples_per_second": 10.498,
732
+ "eval_steps_per_second": 2.625,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.07858507071488e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null