Hugging Face's logo

lesso07
/
4c61c612-f68a-4a61-b1db-226144634c97

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso07 commited on
Commit
f276922
•
1 Parent(s): 1ab3345

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 sha256:8c14e0f7f1581c43792fae127f5dc2aa2db5c7ffc154e7dbcab5002dc205a311
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56f81a19f2d7a89a5c39d51efa7df5b4faee2f8b3f08a9b5f67ccbe2186988d
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:876c50bdb3058a027b1dcee26ff89f782f3e533f497522d4be3e9d3bb838f3dc
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ffc98cff462c6dc8e65046118fe70eee96408089cbc3da62ace8f123f907ec
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:817c0c920c38e6b732b0d266b0e56dd34ec41f28c179a9e2af0befa47dc64c9c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c860416f4a35753c0891786622a3db7fb5c0f226f4b67e9e410abef8cbd1aca
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": 0.001053230257198829,
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": 10.3733,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 2824332115968.0,
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": 0.0015798453857982433,
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": 10.3733,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0010742948623428054,
411
+ "grad_norm": 0.05248018354177475,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 10.375,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0010953594674867819,
418
+ "grad_norm": 0.05726935714483261,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 10.3719,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0011164240726307586,
425
+ "grad_norm": 0.06659786403179169,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 10.3712,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.001137488677774735,
432
+ "grad_norm": 0.07157450169324875,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 10.3746,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.001137488677774735,
439
+ "eval_loss": 10.372406005859375,
440
+ "eval_runtime": 325.9982,
441
+ "eval_samples_per_second": 122.633,
442
+ "eval_steps_per_second": 15.331,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0011585532829187118,
447
+ "grad_norm": 0.07614810019731522,
448
+ "learning_rate": 5e-05,
449
+ "loss": 10.3737,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0011796178880626883,
454
+ "grad_norm": 0.0629672184586525,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 10.3721,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0012006824932066648,
461
+ "grad_norm": 0.06121913716197014,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 10.3733,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.0012217470983506415,
468
+ "grad_norm": 0.07098937779664993,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 10.3714,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.001242811703494618,
475
+ "grad_norm": 0.07375166565179825,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 10.373,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0012638763086385946,
482
+ "grad_norm": 0.07011041790246964,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 10.3747,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0012849409137825711,
489
+ "grad_norm": 0.07801834493875504,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 10.3708,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.0013060055189265476,
496
+ "grad_norm": 0.06852724403142929,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 10.3679,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.0013270701240705243,
503
+ "grad_norm": 0.08574629575014114,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 10.371,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.0013270701240705243,
510
+ "eval_loss": 10.371370315551758,
511
+ "eval_runtime": 326.3428,
512
+ "eval_samples_per_second": 122.503,
513
+ "eval_steps_per_second": 15.315,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.0013481347292145008,
518
+ "grad_norm": 0.07531008124351501,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 10.3716,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.0013691993343584775,
525
+ "grad_norm": 0.07393725961446762,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 10.3698,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.001390263939502454,
532
+ "grad_norm": 0.06109638884663582,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 10.3713,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0014113285446464307,
539
+ "grad_norm": 0.06804902851581573,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 10.3729,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0014323931497904072,
546
+ "grad_norm": 0.06823346018791199,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 10.3726,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0014534577549343837,
553
+ "grad_norm": 0.08150950819253922,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 10.3709,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.0014745223600783604,
560
+ "grad_norm": 0.0740344300866127,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 10.3701,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0014955869652223369,
567
+ "grad_norm": 0.07693792879581451,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 10.3696,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.0015166515703663136,
574
+ "grad_norm": 0.07825221121311188,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 10.371,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.0015166515703663136,
581
+ "eval_loss": 10.370597839355469,
582
+ "eval_runtime": 326.4253,
583
+ "eval_samples_per_second": 122.472,
584
+ "eval_steps_per_second": 15.311,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.00153771617551029,
589
+ "grad_norm": 0.07389895617961884,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 10.3719,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.0015587807806542666,
596
+ "grad_norm": 0.07960311323404312,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 10.3719,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.0015798453857982433,
603
+ "grad_norm": 0.07482942938804626,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 10.3725,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 4210346950656.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null