0x1202 commited on
Commit
5f30c60
·
verified ·
1 Parent(s): 5614f68

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 sha256:1fb4d7424e860ef1341503f40a83dd4cf0723f7a9885b04334effde2065a9e4c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296e31d840b91885b52b6785a4f15969a0bac4756d7ea0ec275adc8449743430
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5cd1e1479c3eccc7a87aa3366324fbb82608efadb198111bcbf65efd988f1a0
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee08ee50aaa762986314420cadc5ee0ff484a6e45dddef6369bc0bf1fa2f2e2
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:b6b81a1a637610e9cb6b2c546d5457423f80aebe5c89eb2c2cb03e186d28348b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7da9782a54720b00876117dbb0410e8af36c21e6ff40e2a2e0deaf1bb939107
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": 1.6402361392974854,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1718213058419244,
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": 2.881,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8.523101719914086e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5493346452713013,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3436426116838488,
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": 2.881,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17525773195876287,
379
+ "grad_norm": 1.2197675704956055,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.9356,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.17869415807560138,
386
+ "grad_norm": 0.8116856217384338,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.0348,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18213058419243985,
393
+ "grad_norm": 0.5514941215515137,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.9794,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18556701030927836,
400
+ "grad_norm": 0.47552359104156494,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.0041,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.18900343642611683,
407
+ "grad_norm": 0.3883759081363678,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.9981,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.19243986254295534,
414
+ "grad_norm": 0.3964765667915344,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.8896,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1958762886597938,
421
+ "grad_norm": 0.40116173028945923,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.8873,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.19931271477663232,
428
+ "grad_norm": 0.4208248555660248,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.8127,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2027491408934708,
435
+ "grad_norm": 0.4747980833053589,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.6512,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.20618556701030927,
442
+ "grad_norm": 0.4318777322769165,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.8278,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.20962199312714777,
449
+ "grad_norm": 0.5040547847747803,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.7725,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.21305841924398625,
456
+ "grad_norm": 0.48844555020332336,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6757,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21649484536082475,
463
+ "grad_norm": 0.5083892941474915,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.8451,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.21993127147766323,
470
+ "grad_norm": 0.5018050074577332,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7201,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.22336769759450173,
477
+ "grad_norm": 0.5488980412483215,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6684,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2268041237113402,
484
+ "grad_norm": 0.5470010638237,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.7186,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.23024054982817868,
491
+ "grad_norm": 0.5802435278892517,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.5814,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.23367697594501718,
498
+ "grad_norm": 0.5508120059967041,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.7299,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.23711340206185566,
505
+ "grad_norm": 0.5759636759757996,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.503,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.24054982817869416,
512
+ "grad_norm": 0.5945281982421875,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.7036,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.24398625429553264,
519
+ "grad_norm": 0.5784856081008911,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.534,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.24742268041237114,
526
+ "grad_norm": 0.6172903776168823,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.5518,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2508591065292096,
533
+ "grad_norm": 0.6575155854225159,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.5429,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2542955326460481,
540
+ "grad_norm": 0.6710128784179688,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.6403,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.25773195876288657,
547
+ "grad_norm": 0.7106481194496155,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.6003,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2611683848797251,
554
+ "grad_norm": 0.7457655072212219,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.5166,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2646048109965636,
561
+ "grad_norm": 0.8298302888870239,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.4188,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.26804123711340205,
568
+ "grad_norm": 0.7822423577308655,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.4283,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.27147766323024053,
575
+ "grad_norm": 0.7826134562492371,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.4861,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.27491408934707906,
582
+ "grad_norm": 0.7911308407783508,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.5385,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.27835051546391754,
589
+ "grad_norm": 0.8717237114906311,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.5897,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.281786941580756,
596
+ "grad_norm": 0.810140073299408,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3252,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2852233676975945,
603
+ "grad_norm": 0.9688878059387207,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.4507,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.28865979381443296,
610
+ "grad_norm": 0.9685982465744019,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.521,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2920962199312715,
617
+ "grad_norm": 0.8572627305984497,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3448,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.29553264604810997,
624
+ "grad_norm": 0.9771127104759216,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.3461,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.29896907216494845,
631
+ "grad_norm": 1.0161019563674927,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.3099,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3024054982817869,
638
+ "grad_norm": 1.0854941606521606,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.2461,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.30584192439862545,
645
+ "grad_norm": 1.0072003602981567,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.308,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.30927835051546393,
652
+ "grad_norm": 1.1473398208618164,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.1992,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3127147766323024,
659
+ "grad_norm": 1.1940810680389404,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.2966,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3161512027491409,
666
+ "grad_norm": 1.736954689025879,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.9234,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.31958762886597936,
673
+ "grad_norm": 1.2535929679870605,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.2638,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3230240549828179,
680
+ "grad_norm": 1.2844491004943848,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.224,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.32646048109965636,
687
+ "grad_norm": 1.21943199634552,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.0463,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.32989690721649484,
694
+ "grad_norm": 1.3590772151947021,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0311,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3333333333333333,
701
+ "grad_norm": 1.2511202096939087,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.8306,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.33676975945017185,
708
+ "grad_norm": 1.4306681156158447,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.9824,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3402061855670103,
715
+ "grad_norm": 1.5601223707199097,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.106,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3436426116838488,
722
+ "grad_norm": 1.7903016805648804,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.1582,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3436426116838488,
729
+ "eval_loss": 1.5493346452713013,
730
+ "eval_runtime": 42.4479,
731
+ "eval_samples_per_second": 11.544,
732
+ "eval_steps_per_second": 2.898,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.7046203439828173e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null