prxy5607 commited on
Commit
72371bb
·
verified ·
1 Parent(s): b207128

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:b5a1db31d8d708fe6091442d3662ffd25f45b7f965ebc5ac1984c99ed598260f
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7bcd85db33fb4de6dea08bf9bc9c7f931969e3390999aa88d652222a0fc4b7
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c821306125feede0cb7a8ebf2dc2c910b1bccafdd04c038d30854519bc5e53b
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5407f49c8cf2b19d2774ca5b2bf004b889c9d5b855ac04ff674830287c254b7
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac111ae5926f3e7f68c6af8f6629c531b078106918c156ed436bbdb5da375568
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3273c7252e8d7251a1b974bd9c1eb0842e643bbed0ef8080153a46b34f28b1ab
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": 2.5757181644439697,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3367003367003367,
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": 86.983,
374
  "eval_steps_per_second": 21.92,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3725608982937600.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.275372266769409,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6734006734006734,
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": 86.983,
374
  "eval_steps_per_second": 21.92,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.3434343434343434,
379
+ "grad_norm": 56.74869918823242,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 8.5832,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.3501683501683502,
386
+ "grad_norm": 120.69475555419922,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 9.0831,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3569023569023569,
393
+ "grad_norm": 90.3545913696289,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 8.7051,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.36363636363636365,
400
+ "grad_norm": 59.1437873840332,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 8.1265,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.37037037037037035,
407
+ "grad_norm": 85.22001647949219,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 8.4988,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.3771043771043771,
414
+ "grad_norm": 106.94491577148438,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 8.5023,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3838383838383838,
421
+ "grad_norm": 101.17305755615234,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 8.1557,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.39057239057239057,
428
+ "grad_norm": 126.14461517333984,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 8.039,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.39730639730639733,
435
+ "grad_norm": 152.2769317626953,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 9.834,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.40404040404040403,
442
+ "grad_norm": 119.77828216552734,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 8.9833,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.4107744107744108,
449
+ "grad_norm": 113.63468170166016,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 9.3487,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.4175084175084175,
456
+ "grad_norm": 142.9735107421875,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 8.3782,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.42424242424242425,
463
+ "grad_norm": 137.7916717529297,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 8.9443,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.43097643097643096,
470
+ "grad_norm": 231.43089294433594,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 9.1096,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.4377104377104377,
477
+ "grad_norm": 116.13423919677734,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 8.3049,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.4444444444444444,
484
+ "grad_norm": 145.97251892089844,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 9.7356,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4511784511784512,
491
+ "grad_norm": 163.04188537597656,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 10.6661,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.45791245791245794,
498
+ "grad_norm": 162.80068969726562,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 9.8382,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.46464646464646464,
505
+ "grad_norm": 146.3478240966797,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 11.777,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.4713804713804714,
512
+ "grad_norm": 195.50843811035156,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 12.0246,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4781144781144781,
519
+ "grad_norm": 328.9975280761719,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 9.7281,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.48484848484848486,
526
+ "grad_norm": 194.7329864501953,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 12.9932,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.49158249158249157,
533
+ "grad_norm": 154.91452026367188,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 10.7869,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4983164983164983,
540
+ "grad_norm": 157.42726135253906,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 14.3655,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5050505050505051,
547
+ "grad_norm": 68.41136169433594,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 9.1286,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5117845117845118,
554
+ "grad_norm": 94.79463958740234,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 9.4578,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5185185185185185,
561
+ "grad_norm": 65.79988861083984,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 9.1846,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5252525252525253,
568
+ "grad_norm": 642.8189697265625,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 8.9449,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.531986531986532,
575
+ "grad_norm": 60.4979248046875,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 9.353,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5387205387205387,
582
+ "grad_norm": 64.75019073486328,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 8.7256,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5454545454545454,
589
+ "grad_norm": 69.59507751464844,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 8.9943,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5521885521885522,
596
+ "grad_norm": 55.43488693237305,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 8.3704,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5589225589225589,
603
+ "grad_norm": 66.44117736816406,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 8.7222,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5656565656565656,
610
+ "grad_norm": 50.78106689453125,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 8.182,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5723905723905723,
617
+ "grad_norm": 81.48322296142578,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 7.8204,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5791245791245792,
624
+ "grad_norm": 94.91535186767578,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 7.6156,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5858585858585859,
631
+ "grad_norm": 65.08795928955078,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 8.135,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5925925925925926,
638
+ "grad_norm": 70.78136444091797,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 8.7126,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5993265993265994,
645
+ "grad_norm": 83.88176727294922,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 8.183,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6060606060606061,
652
+ "grad_norm": 68.87261199951172,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 8.1776,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6127946127946128,
659
+ "grad_norm": 80.12345886230469,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 9.1202,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6195286195286195,
666
+ "grad_norm": 100.9736328125,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 8.8236,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6262626262626263,
673
+ "grad_norm": 76.5873031616211,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 8.6311,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.632996632996633,
680
+ "grad_norm": 69.47529602050781,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 7.5208,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6397306397306397,
687
+ "grad_norm": 97.56402587890625,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 8.3195,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6464646464646465,
694
+ "grad_norm": 191.1015167236328,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 8.2413,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6531986531986532,
701
+ "grad_norm": 147.45555114746094,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 9.2333,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6599326599326599,
708
+ "grad_norm": 378.5626525878906,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 8.5199,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6666666666666666,
715
+ "grad_norm": 136.10995483398438,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 8.8421,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.6734006734006734,
722
+ "grad_norm": 111.9849853515625,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 8.6364,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6734006734006734,
729
+ "eval_loss": 2.275372266769409,
730
+ "eval_runtime": 2.8712,
731
+ "eval_samples_per_second": 87.072,
732
+ "eval_steps_per_second": 21.942,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7451217965875200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null