Hugging Face's logo

lesso03
/
998e1fd2-a943-4493-bc98-73dc14446ec1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso03 commited on
Commit
2f920e5
•
1 Parent(s): 68f7a1f

Training in progress, step 75, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +202 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ed387312e4ab13ce826929c3b5ac79ffa3938f0c9e370b6ee1a900b00a482b1
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddbea23fc692ada10a7c4a1dadd0ca03fc7f0c32566afb386439f690a6767c79
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3d0ed265880e9be7e651888cec931e6bf8da7f67ebdfbdcb7b78a14e6443d7
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:994b544f5220ea4864750175b2ca55b2d26dcadeaccb7af24dc7f2f613306f5a
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f4135fa923d57e4f9ed28ea9ccde5fda0158043555149715cb9e0082935bee9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7ac41c92e00e6961fbf45d5a99d8298611815320bdf80a5f802ea50a5c3fc4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.017614937466971993,
5
  "eval_steps": 9,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -405,6 +405,205 @@
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 0.1761,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 7.307589743070413e+16,
428
  "train_batch_size": 8,
429
  "trial_name": null,
430
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02642240620045799,
5
  "eval_steps": 9,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 0.1761,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.01796723621631143,
411
+ "grad_norm": 0.46626943349838257,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.1848,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.018319534965650874,
418
+ "grad_norm": 0.34437844157218933,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.1926,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.018671833714990312,
425
+ "grad_norm": 0.3511681854724884,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.1794,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.01902413246432975,
432
+ "grad_norm": 0.33112460374832153,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.2026,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.01902413246432975,
439
+ "eval_loss": 0.17996886372566223,
440
+ "eval_runtime": 513.899,
441
+ "eval_samples_per_second": 4.653,
442
+ "eval_steps_per_second": 0.582,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.019376431213669193,
447
+ "grad_norm": 0.2823706269264221,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.1775,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.01972872996300863,
454
+ "grad_norm": 0.25659382343292236,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.1604,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.02008102871234807,
461
+ "grad_norm": 0.29731568694114685,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.1615,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.020433327461687512,
468
+ "grad_norm": 0.2573408782482147,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.1774,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.02078562621102695,
475
+ "grad_norm": 0.22935473918914795,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.1729,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.02113792496036639,
482
+ "grad_norm": 0.29212892055511475,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.1824,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.02149022370970583,
489
+ "grad_norm": 0.25081226229667664,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.1566,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.02184252245904527,
496
+ "grad_norm": 0.27154645323753357,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.1992,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.02219482120838471,
503
+ "grad_norm": 0.29524990916252136,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.1807,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.02219482120838471,
510
+ "eval_loss": 0.17594482004642487,
511
+ "eval_runtime": 513.854,
512
+ "eval_samples_per_second": 4.653,
513
+ "eval_steps_per_second": 0.582,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.02254711995772415,
518
+ "grad_norm": 0.2617270350456238,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.1494,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.02289941870706359,
525
+ "grad_norm": 0.3561565577983856,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.2031,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.023251717456403028,
532
+ "grad_norm": 0.3045690357685089,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.1668,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.02360401620574247,
539
+ "grad_norm": 0.2725241184234619,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.1494,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.02395631495508191,
546
+ "grad_norm": 0.2796728312969208,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.1703,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.02430861370442135,
553
+ "grad_norm": 0.26963382959365845,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.1611,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.02466091245376079,
560
+ "grad_norm": 0.24480478465557098,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.1655,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.025013211203100228,
567
+ "grad_norm": 0.2573697865009308,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.1594,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.02536550995243967,
574
+ "grad_norm": 0.2376534342765808,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.1667,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.02536550995243967,
581
+ "eval_loss": 0.17308475077152252,
582
+ "eval_runtime": 513.9743,
583
+ "eval_samples_per_second": 4.652,
584
+ "eval_steps_per_second": 0.582,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.02571780870177911,
589
+ "grad_norm": 0.24161791801452637,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.1814,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.026070107451118547,
596
+ "grad_norm": 0.21853087842464447,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.1654,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.02642240620045799,
603
+ "grad_norm": 0.31905707716941833,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.1668,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1.083155433998254e+17,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null