aleegis10 commited on
Commit
afd63f2
·
verified ·
1 Parent(s): bf897ae

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 sha256:722f6a2666ffe7685494bafcb55c904f057a183d6a218ec570efc953ad13ea0f
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13822418c5b4c604b38e9dc6e6ad5cb1c4723f0723fa4f7b63aafb5111cb4587
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07848b7f68381bd4441add4b072694c29fb48819d25407552f117f37e2401452
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df004dc624630f32f11ef61d942133243297d8fc73ac3fad86bce974f45a41e2
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:b558afaea239203282390239f269a8f4eddf087662e4e504915be6f67107670a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b39c8edee9cb2de2bc7e6c99fede756129e4a2fe8380422ed4b22b9031c905
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": 0.30729740858078003,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005825808330905913,
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": 11.477,
374
  "eval_steps_per_second": 2.869,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8.62176300415058e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2293005883693695,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011651616661811826,
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": 11.477,
374
  "eval_steps_per_second": 2.869,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005942324497524031,
379
+ "grad_norm": 7.646812438964844,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.4163,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0060588406641421495,
386
+ "grad_norm": 6.700872898101807,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.4841,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.006175356830760268,
393
+ "grad_norm": 6.486911296844482,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.3511,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006291872997378386,
400
+ "grad_norm": 20.43660545349121,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.9787,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.006408389163996504,
407
+ "grad_norm": 7.909752368927002,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.3232,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.006524905330614623,
414
+ "grad_norm": 5.747597694396973,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.2553,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006641421497232741,
421
+ "grad_norm": 5.942625999450684,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.6,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006757937663850859,
428
+ "grad_norm": 6.343461513519287,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.6722,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.006874453830468977,
435
+ "grad_norm": 7.53312873840332,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.3428,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006990969997087096,
442
+ "grad_norm": 6.786001682281494,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.8934,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.007107486163705214,
449
+ "grad_norm": 6.07697057723999,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.5482,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.007224002330323332,
456
+ "grad_norm": 7.817957401275635,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.8168,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0073405184969414505,
463
+ "grad_norm": 10.404017448425293,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.0485,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007457034663559569,
470
+ "grad_norm": 6.8413777351379395,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5882,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.007573550830177687,
477
+ "grad_norm": 6.327642917633057,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.4513,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007690066996795805,
484
+ "grad_norm": 7.955966949462891,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5974,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007806583163413924,
491
+ "grad_norm": 7.306300163269043,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0354,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007923099330032043,
498
+ "grad_norm": 5.990658760070801,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6796,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.00803961549665016,
505
+ "grad_norm": 4.4180121421813965,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5267,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.00815613166326828,
512
+ "grad_norm": 3.890469551086426,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.46,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.008272647829886397,
519
+ "grad_norm": 4.6100239753723145,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.4944,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.008389163996504514,
526
+ "grad_norm": 5.460227966308594,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.4118,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008505680163122633,
533
+ "grad_norm": 5.597787857055664,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4636,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.00862219632974075,
540
+ "grad_norm": 4.456701755523682,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.4148,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.00873871249635887,
547
+ "grad_norm": 4.373245716094971,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4957,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008855228662976987,
554
+ "grad_norm": 6.624417781829834,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.4018,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008971744829595106,
561
+ "grad_norm": 3.571817398071289,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.4453,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.009088260996213224,
568
+ "grad_norm": 4.248070240020752,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.3584,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.009204777162831343,
575
+ "grad_norm": 9.709259033203125,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4822,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.00932129332944946,
582
+ "grad_norm": 3.1241631507873535,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.2599,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.00943780949606758,
589
+ "grad_norm": 4.64263916015625,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.4409,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009554325662685697,
596
+ "grad_norm": 4.032393455505371,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3145,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.009670841829303816,
603
+ "grad_norm": 5.52547550201416,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.64,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.009787357995921933,
610
+ "grad_norm": 3.4348347187042236,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.222,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.009903874162540053,
617
+ "grad_norm": 2.8319878578186035,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.3056,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01002039032915817,
624
+ "grad_norm": 1.929783582687378,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.1418,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01013690649577629,
631
+ "grad_norm": 5.322389602661133,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3162,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.010253422662394407,
638
+ "grad_norm": 6.367090225219727,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.2716,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.010369938829012526,
645
+ "grad_norm": 4.7843337059021,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.2803,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.010486454995630643,
652
+ "grad_norm": 3.9384782314300537,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.2986,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.010602971162248762,
659
+ "grad_norm": 3.9873108863830566,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.1867,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.01071948732886688,
666
+ "grad_norm": 5.899569511413574,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4297,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.010836003495484999,
673
+ "grad_norm": 3.702864646911621,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.3268,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010952519662103116,
680
+ "grad_norm": 3.3945624828338623,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.2245,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.011069035828721235,
687
+ "grad_norm": 3.3172385692596436,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.2557,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.011185551995339353,
694
+ "grad_norm": 3.4038662910461426,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.2956,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.011302068161957472,
701
+ "grad_norm": 3.525500535964966,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.1912,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01141858432857559,
708
+ "grad_norm": 4.306077480316162,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.3404,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.011535100495193708,
715
+ "grad_norm": 3.4483957290649414,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.1822,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011651616661811826,
722
+ "grad_norm": 3.101605176925659,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.1502,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011651616661811826,
729
+ "eval_loss": 0.2293005883693695,
730
+ "eval_runtime": 1260.8588,
731
+ "eval_samples_per_second": 11.464,
732
+ "eval_steps_per_second": 2.866,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.7100426207402394e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null