Hugging Face's logo

lesso03
/
313e89b5-6608-499b-94d4-d64922ba564f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso03 commited on
Commit
084929e
•
1 Parent(s): acee7b8

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:bb0d566a64518e27d8c1756f941d3a03ca417f453df046de16408a1f01e899a0
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63622b593e81d02a230cbe440c98aa3ffbee4770adb2b5badf6b0a7940fd33aa
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40e6aec5ed2559cc6e406fba4a33ba8d5d1a523fda48c4318bdd24bfc4449b72
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b49805228d17ca45e8fc83ac243816a15ef14b15e62ed43299103295aae941
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e7be9add4fd70e35b944858b1783354a7587e3ae43652236bdd5b1fe3daade7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c2aeb48c97bc17fc16027c087a1f2b9b14a3b5da40e726c4c4179d5382c495
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": 0.12269938650306748,
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": 0.0934,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.34313627444183e+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": 0.18404907975460122,
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": 0.0934,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.12515337423312883,
411
+ "grad_norm": 0.12899591028690338,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.0896,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.1276073619631902,
418
+ "grad_norm": 0.13761845231056213,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.0926,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.13006134969325153,
425
+ "grad_norm": 0.1670072227716446,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.0979,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.1325153374233129,
432
+ "grad_norm": 0.14916564524173737,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.0799,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.1325153374233129,
439
+ "eval_loss": 0.0861867144703865,
440
+ "eval_runtime": 72.1722,
441
+ "eval_samples_per_second": 4.753,
442
+ "eval_steps_per_second": 0.596,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.13496932515337423,
447
+ "grad_norm": 0.1766030490398407,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.0606,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.1374233128834356,
454
+ "grad_norm": 0.133830726146698,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.0845,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.13987730061349693,
461
+ "grad_norm": 0.17518991231918335,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.073,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.1423312883435583,
468
+ "grad_norm": 0.1533428430557251,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.0843,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.14478527607361963,
475
+ "grad_norm": 0.13991299271583557,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.0718,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.147239263803681,
482
+ "grad_norm": 0.1512841433286667,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.085,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.14969325153374233,
489
+ "grad_norm": 0.1344129890203476,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.0761,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.1521472392638037,
496
+ "grad_norm": 0.1694488674402237,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.0939,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.15460122699386503,
503
+ "grad_norm": 0.14527535438537598,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.0855,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.15460122699386503,
510
+ "eval_loss": 0.0837635025382042,
511
+ "eval_runtime": 72.198,
512
+ "eval_samples_per_second": 4.751,
513
+ "eval_steps_per_second": 0.596,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.1570552147239264,
518
+ "grad_norm": 0.11152983456850052,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.0755,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.15950920245398773,
525
+ "grad_norm": 0.14772440493106842,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.08,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.1619631901840491,
532
+ "grad_norm": 0.14314669370651245,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.0783,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.16441717791411042,
539
+ "grad_norm": 0.23815108835697174,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.1082,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.1668711656441718,
546
+ "grad_norm": 0.19166451692581177,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.0888,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.16932515337423312,
553
+ "grad_norm": 0.19325505197048187,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.1017,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.17177914110429449,
560
+ "grad_norm": 0.16106754541397095,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0922,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.17423312883435582,
567
+ "grad_norm": 0.0972488522529602,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.0567,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.17668711656441718,
574
+ "grad_norm": 0.1254057139158249,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.0602,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.17668711656441718,
581
+ "eval_loss": 0.0817757397890091,
582
+ "eval_runtime": 72.2756,
583
+ "eval_samples_per_second": 4.746,
584
+ "eval_steps_per_second": 0.595,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.17914110429447852,
589
+ "grad_norm": 0.1219269409775734,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.0836,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.18159509202453988,
596
+ "grad_norm": 0.10528916865587234,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.0572,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.18404907975460122,
603
+ "grad_norm": 0.1957486867904663,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.0593,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.57034595792978e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null