aleegis09 commited on
Commit
27a6318
·
verified ·
1 Parent(s): ca43fb4

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:e9284e29dd5f1339cd5776a2ea0a7c260f0c96887265bf105bb3b6f72a14a42e
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b595ff55dbb615a469cb2930ea86a52ee2277b869e96277abd3ee28c2eb2a98
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db04599d6aa75b9f0324e9a96d66c3acb5e3342433921b060e6e57a53597f7e9
3
  size 243802484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d953f5b09b6b0c3d8a761a01b44f07940ca74f76fe02ea784795718a1c5b1c72
3
  size 243802484
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e8978bbe4f4eafc5bee61cc0d0a78bf0cbcc0a412014359850b883439620548
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76968e7138d3f360b78ccd4b3bb0bd7aab81a417cf1d6a49cb9d204ccdc0a4a
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": 0.5233702063560486,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.021422450728363324,
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": 18.319,
374
  "eval_steps_per_second": 4.581,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3.2153214086283264e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5112596750259399,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.04284490145672665,
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": 18.319,
374
  "eval_steps_per_second": 4.581,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.021850899742930592,
379
+ "grad_norm": 0.15064652264118195,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.4372,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.022279348757497857,
386
+ "grad_norm": 0.20386983454227448,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.5498,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.022707797772065125,
393
+ "grad_norm": 2.4847986698150635,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.4945,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.02313624678663239,
400
+ "grad_norm": 0.20311777293682098,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.5348,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.02356469580119966,
407
+ "grad_norm": 0.2357204109430313,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.5865,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.023993144815766924,
414
+ "grad_norm": 0.2169618010520935,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.5453,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02442159383033419,
421
+ "grad_norm": 0.18748903274536133,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.4958,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.024850042844901457,
428
+ "grad_norm": 0.19831594824790955,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5572,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.025278491859468722,
435
+ "grad_norm": 0.1811814159154892,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.5235,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02570694087403599,
442
+ "grad_norm": 0.19561834633350372,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.4957,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.026135389888603255,
449
+ "grad_norm": 0.2204512506723404,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.5922,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.026563838903170524,
456
+ "grad_norm": 0.17718099057674408,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.4556,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02699228791773779,
463
+ "grad_norm": 0.2117452174425125,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5375,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.027420736932305057,
470
+ "grad_norm": 0.2319151908159256,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5579,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.027849185946872322,
477
+ "grad_norm": 0.19332152605056763,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5133,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.028277634961439587,
484
+ "grad_norm": 0.21406444907188416,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5307,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.028706083976006855,
491
+ "grad_norm": 0.23117361962795258,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.54,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02913453299057412,
498
+ "grad_norm": 0.21088655292987823,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5812,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02956298200514139,
505
+ "grad_norm": 0.20900338888168335,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5061,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.029991431019708654,
512
+ "grad_norm": 0.22404471039772034,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5556,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.030419880034275922,
519
+ "grad_norm": 0.20459339022636414,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5004,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.030848329048843187,
526
+ "grad_norm": 0.2245027720928192,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5351,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.031276778063410456,
533
+ "grad_norm": 0.18311403691768646,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4642,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.031705227077977724,
540
+ "grad_norm": 0.21955837309360504,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5077,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.032133676092544985,
547
+ "grad_norm": 0.2084721326828003,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5319,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.032562125107112254,
554
+ "grad_norm": 0.21330246329307556,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5585,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03299057412167952,
561
+ "grad_norm": 0.24155814945697784,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.54,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.033419023136246784,
568
+ "grad_norm": 0.2249860167503357,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.553,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03384747215081405,
575
+ "grad_norm": 0.2181163728237152,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.5347,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03427592116538132,
582
+ "grad_norm": 0.20594443380832672,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5072,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03470437017994859,
589
+ "grad_norm": 0.20609448850154877,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.4803,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03513281919451585,
596
+ "grad_norm": 0.22857272624969482,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5394,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03556126820908312,
603
+ "grad_norm": 0.21896202862262726,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5107,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03598971722365039,
610
+ "grad_norm": 0.23790735006332397,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.5915,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03641816623821765,
617
+ "grad_norm": 0.2318210005760193,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5167,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03684661525278492,
624
+ "grad_norm": 0.2057870477437973,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.47,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.037275064267352186,
631
+ "grad_norm": 0.2366434782743454,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.5018,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.037703513281919454,
638
+ "grad_norm": 0.2103012651205063,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.5134,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.038131962296486716,
645
+ "grad_norm": 0.21713051199913025,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.4617,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.038560411311053984,
652
+ "grad_norm": 0.21644674241542816,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4271,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03898886032562125,
659
+ "grad_norm": 0.2307886928319931,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.5383,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03941730934018852,
666
+ "grad_norm": 0.24658828973770142,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4651,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03984575835475578,
673
+ "grad_norm": 0.24504642188549042,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5077,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.04027420736932305,
680
+ "grad_norm": 0.22446109354496002,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4376,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04070265638389032,
687
+ "grad_norm": 0.2468467354774475,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.4683,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04113110539845758,
694
+ "grad_norm": 0.25989946722984314,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4697,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.04155955441302485,
701
+ "grad_norm": 0.25286898016929626,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4461,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04198800342759212,
708
+ "grad_norm": 0.3009304702281952,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4282,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.042416452442159386,
715
+ "grad_norm": 0.2842262387275696,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.4702,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.04284490145672665,
722
+ "grad_norm": 0.30349037051200867,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4609,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.04284490145672665,
729
+ "eval_loss": 0.5112596750259399,
730
+ "eval_runtime": 214.5352,
731
+ "eval_samples_per_second": 18.323,
732
+ "eval_steps_per_second": 4.582,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6.459096989014426e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null