0x1202 commited on
Commit
54b472f
·
verified ·
1 Parent(s): 96ebce7

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 sha256:869ce6ac6a7601a520215cac180b1a852c87902943d000ccc61055ca67733791
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6d046de4ff6b0fd32bee203830af543cc8635c555c0bbbf72ac6e20e85fa7c
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1a3cb0b82f277097e40df46f7afa1a6ec43a8c9c5862e5b1b34531275f68011
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8374457a69b35808d34e1c4f021923d1cf8d8d196f9303ff5410adbb0ea756dd
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:246d82cbd807b20c1b01ea00cff231f876ebaa1bfa2849a1809a6e46c4a92fc1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d4a279032806da36d9826e577f4932af193d3891ec3782a5b4aba1c2d60ee9
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": 1.5559238195419312,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008104056080068074,
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": 10.078,
374
  "eval_steps_per_second": 2.52,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9.095305596449587e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3847177028656006,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.016208112160136148,
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": 10.078,
374
  "eval_steps_per_second": 2.52,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008266137201669436,
379
+ "grad_norm": 8.963892936706543,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.6975,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008428218323270797,
386
+ "grad_norm": 5.794774055480957,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 6.5483,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008590299444872159,
393
+ "grad_norm": 4.353773593902588,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 6.2493,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.00875238056647352,
400
+ "grad_norm": 4.177701950073242,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 5.725,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008914461688074882,
407
+ "grad_norm": 3.7573206424713135,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 5.5812,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009076542809676243,
414
+ "grad_norm": 4.3062591552734375,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 5.6443,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009238623931277605,
421
+ "grad_norm": 3.8506991863250732,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 5.6099,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009400705052878966,
428
+ "grad_norm": 3.8697073459625244,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 5.0964,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009562786174480328,
435
+ "grad_norm": 3.971761465072632,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 5.5613,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009724867296081689,
442
+ "grad_norm": 3.820019245147705,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 5.6731,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009886948417683051,
449
+ "grad_norm": 4.112672805786133,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 5.4865,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.010049029539284412,
456
+ "grad_norm": 3.847612142562866,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.548,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010211110660885774,
463
+ "grad_norm": 3.959521770477295,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 5.6983,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010373191782487134,
470
+ "grad_norm": 3.779252052307129,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.1694,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010535272904088497,
477
+ "grad_norm": 3.9358041286468506,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 5.6322,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010697354025689857,
484
+ "grad_norm": 3.8914718627929688,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 4.9709,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01085943514729122,
491
+ "grad_norm": 4.115433216094971,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.2434,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01102151626889258,
498
+ "grad_norm": 4.220749855041504,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 5.4555,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011183597390493943,
505
+ "grad_norm": 4.126224040985107,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.3821,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.011345678512095303,
512
+ "grad_norm": 4.412211894989014,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 5.6406,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011507759633696666,
519
+ "grad_norm": 3.9712724685668945,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 5.4385,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011669840755298026,
526
+ "grad_norm": 4.128697395324707,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 5.7166,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011831921876899389,
533
+ "grad_norm": 4.208035945892334,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 5.5222,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01199400299850075,
540
+ "grad_norm": 4.283714294433594,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.4174,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012156084120102112,
547
+ "grad_norm": 4.24643087387085,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.5042,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012318165241703472,
554
+ "grad_norm": 4.205446720123291,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.0924,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012480246363304835,
561
+ "grad_norm": 4.379979133605957,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.3984,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012642327484906195,
568
+ "grad_norm": 4.69776725769043,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.6712,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012804408606507557,
575
+ "grad_norm": 4.539688587188721,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.2928,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012966489728108918,
582
+ "grad_norm": 4.4620490074157715,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.2381,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01312857084971028,
589
+ "grad_norm": 4.704196929931641,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 5.2825,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013290651971311641,
596
+ "grad_norm": 4.632774829864502,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 5.4664,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013452733092913003,
603
+ "grad_norm": 4.884334087371826,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 5.3945,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013614814214514364,
610
+ "grad_norm": 4.739119529724121,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 5.7381,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013776895336115726,
617
+ "grad_norm": 5.047530174255371,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 5.7925,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.013938976457717087,
624
+ "grad_norm": 5.00535249710083,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 5.4451,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01410105757931845,
631
+ "grad_norm": 5.174424171447754,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 5.6002,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.01426313870091981,
638
+ "grad_norm": 5.37460470199585,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 5.7764,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014425219822521172,
645
+ "grad_norm": 5.565922260284424,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 6.0238,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014587300944122533,
652
+ "grad_norm": 5.54338264465332,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 5.8409,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014749382065723895,
659
+ "grad_norm": 5.88922119140625,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 5.8109,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014911463187325256,
666
+ "grad_norm": 6.442539691925049,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 5.9126,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015073544308926618,
673
+ "grad_norm": 6.439504146575928,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 5.8973,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015235625430527979,
680
+ "grad_norm": 6.778526306152344,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 5.9212,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015397706552129341,
687
+ "grad_norm": 7.527666091918945,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 6.1104,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015559787673730702,
694
+ "grad_norm": 8.4906644821167,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 6.6445,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015721868795332064,
701
+ "grad_norm": 8.908556938171387,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 6.2731,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015883949916933426,
708
+ "grad_norm": 10.14052963256836,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 6.0604,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.016046031038534785,
715
+ "grad_norm": 12.570101737976074,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 6.3531,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016208112160136148,
722
+ "grad_norm": 14.668326377868652,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 6.2624,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016208112160136148,
729
+ "eval_loss": 1.3847177028656006,
730
+ "eval_runtime": 1029.8455,
731
+ "eval_samples_per_second": 10.091,
732
+ "eval_steps_per_second": 2.523,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.8226703675424768e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null