prxy5606 commited on
Commit
d5e3f3b
·
verified ·
1 Parent(s): 23be600

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:d444568afb8b626cbf640791babdf50a210eb3389a3824652c5ffe0ee00f4781
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56663602219e7992952a2eb901691dcbf21a2adc16f4d8d6b51de262f71dc51b
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:215f4967e3876fdfd54872eedd10a5eee0c805c0694e021a9bc3d9b080304dd8
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1eaa360784105ecafa74f3b273c2b40862b9c49103c3415e101beda7e75da1
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae4dd329e4b1720c9761fa6025878a14c9f34b696abdf822cdb2369cee5e3ef7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1695eb6f1d475e1b1778c22f07d3e0e8abc42e71ea75baff0420201f04b674f6
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": 0.4823625683784485,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06424670735624799,
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": 73.213,
374
  "eval_steps_per_second": 18.317,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1266990223196160.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.43862655758857727,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.12849341471249598,
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": 73.213,
374
  "eval_steps_per_second": 18.317,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06553164150337296,
379
+ "grad_norm": 0.41886407136917114,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.3765,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.06681657565049791,
386
+ "grad_norm": 0.3565922975540161,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.3995,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.06810150979762288,
393
+ "grad_norm": 0.3009561598300934,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.4963,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.06938644394474783,
400
+ "grad_norm": 0.30226537585258484,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3823,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0706713780918728,
407
+ "grad_norm": 0.24455474317073822,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.3055,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07195631223899775,
414
+ "grad_norm": 0.18948034942150116,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.4758,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07324124638612271,
421
+ "grad_norm": 0.20388995110988617,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.5025,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07452618053324767,
428
+ "grad_norm": 0.16348803043365479,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3856,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.07581111468037263,
435
+ "grad_norm": 0.1716645210981369,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.5104,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.07709604882749758,
442
+ "grad_norm": 0.18084391951560974,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.4021,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.07838098297462255,
449
+ "grad_norm": 0.18903827667236328,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.5257,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0796659171217475,
456
+ "grad_norm": 0.17917057871818542,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.405,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08095085126887247,
463
+ "grad_norm": 0.13263970613479614,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.3336,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.08223578541599744,
470
+ "grad_norm": 0.19856888055801392,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4876,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08352071956312239,
477
+ "grad_norm": 0.17072618007659912,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.4405,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08480565371024736,
484
+ "grad_norm": 0.17208395898342133,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.4741,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.08609058785737231,
491
+ "grad_norm": 0.1645234227180481,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.3383,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.08737552200449727,
498
+ "grad_norm": 0.16286449134349823,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.413,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.08866045615162223,
505
+ "grad_norm": 0.1754399538040161,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5182,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0899453902987472,
512
+ "grad_norm": 0.1368543952703476,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.3331,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09123032444587215,
519
+ "grad_norm": 0.13811126351356506,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3799,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09251525859299711,
526
+ "grad_norm": 0.1286497414112091,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.2911,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.09380019274012207,
533
+ "grad_norm": 0.16766689717769623,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4131,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.09508512688724703,
540
+ "grad_norm": 0.15062600374221802,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.3549,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.09637006103437198,
547
+ "grad_norm": 0.17661640048027039,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4628,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.09765499518149695,
554
+ "grad_norm": 0.18976455926895142,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.447,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0989399293286219,
561
+ "grad_norm": 0.17289698123931885,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.4547,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10022486347574687,
568
+ "grad_norm": 0.1608312577009201,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4095,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.10150979762287182,
575
+ "grad_norm": 0.16891804337501526,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4182,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.10279473176999679,
582
+ "grad_norm": 0.19559670984745026,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.4894,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.10407966591712174,
589
+ "grad_norm": 0.16868546605110168,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3961,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.10536460006424671,
596
+ "grad_norm": 0.1829994171857834,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.446,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.10664953421137166,
603
+ "grad_norm": 0.1991136521100998,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.4248,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.10793446835849663,
610
+ "grad_norm": 0.22807911038398743,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.5467,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1092194025056216,
617
+ "grad_norm": 0.1949082463979721,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.4612,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.11050433665274655,
624
+ "grad_norm": 0.22015252709388733,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.4521,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.11178927079987151,
631
+ "grad_norm": 0.19183842837810516,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.4972,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.11307420494699646,
638
+ "grad_norm": 0.19982464611530304,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.4231,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.11435913909412143,
645
+ "grad_norm": 0.19909873604774475,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.3886,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.11564407324124638,
652
+ "grad_norm": 0.2026892900466919,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4575,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.11692900738837135,
659
+ "grad_norm": 0.23532840609550476,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.5401,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1182139415354963,
666
+ "grad_norm": 0.23304833471775055,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4831,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.11949887568262127,
673
+ "grad_norm": 0.24611881375312805,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.6095,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12078380982974622,
680
+ "grad_norm": 0.2635016441345215,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4649,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.12206874397687119,
687
+ "grad_norm": 0.24433648586273193,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.3904,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.12335367812399614,
694
+ "grad_norm": 0.2562096118927002,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4316,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.12463861227112111,
701
+ "grad_norm": 0.26686418056488037,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4104,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.12592354641824607,
708
+ "grad_norm": 0.2688847482204437,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4729,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.127208480565371,
715
+ "grad_norm": 0.31322845816612244,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.5112,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.12849341471249598,
722
+ "grad_norm": 0.4091756343841553,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.7067,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.12849341471249598,
729
+ "eval_loss": 0.43862655758857727,
730
+ "eval_runtime": 17.9241,
731
+ "eval_samples_per_second": 73.142,
732
+ "eval_steps_per_second": 18.299,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2533980446392320.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null