Hugging Face's logo

lesso01
/
8286b448-364a-42aa-81cd-dd63f301c534

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso01 commited on
Commit
c3e510c
•
1 Parent(s): 3002064

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 sha256:81305f3c73dad6d3182e0486da55de2ab5f24272675d4793f32ca8c10cfe1c7d
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e41d5b25d1f36ffbdea09b38462e006ce7c5ed26575f862915901dbd7526ceab
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85dae8d46d4d06a33f10d7ca71e52cb6d2452e4f02e229c6db767f7005f54d49
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3643d9c4c1a11119b58d60b076147de885b538737cf28c787bc0d1f8e2d4ee3
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b0f4f9d935debe1754d2bcdf6836577fd7f75677fdbebc826454f63e3fb737
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074e8690a8d61dba7a66649463fc8a03dc8e3c47ce5a5c77b759d178ed3f5ec7
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": 0.352112676056338,
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": 1.4195,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 3.26732322177024e+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": 0.528169014084507,
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": 1.4195,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.3591549295774648,
411
+ "grad_norm": 2.0427401065826416,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.6343,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.36619718309859156,
418
+ "grad_norm": 3.6951797008514404,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.7408,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.3732394366197183,
425
+ "grad_norm": 3.672791004180908,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.524,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.38028169014084506,
432
+ "grad_norm": 4.061415672302246,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.5609,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.38028169014084506,
439
+ "eval_loss": 0.7512367963790894,
440
+ "eval_runtime": 5.2814,
441
+ "eval_samples_per_second": 22.721,
442
+ "eval_steps_per_second": 2.84,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.3873239436619718,
447
+ "grad_norm": 2.5772194862365723,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.4108,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.39436619718309857,
454
+ "grad_norm": 1.6014587879180908,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.365,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.4014084507042254,
461
+ "grad_norm": 2.9118096828460693,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.7301,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.4084507042253521,
468
+ "grad_norm": 4.28907585144043,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.7773,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.4154929577464789,
475
+ "grad_norm": 3.053123712539673,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.6367,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.4225352112676056,
482
+ "grad_norm": 3.9312641620635986,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.5563,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.4295774647887324,
489
+ "grad_norm": 4.716941833496094,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.5059,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.43661971830985913,
496
+ "grad_norm": 1.2284787893295288,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.3866,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.44366197183098594,
503
+ "grad_norm": 1.6609184741973877,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.3671,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.44366197183098594,
510
+ "eval_loss": 0.7309496402740479,
511
+ "eval_runtime": 5.2546,
512
+ "eval_samples_per_second": 22.837,
513
+ "eval_steps_per_second": 2.855,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.4507042253521127,
518
+ "grad_norm": 2.3474254608154297,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.6455,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.45774647887323944,
525
+ "grad_norm": 3.384629726409912,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.5113,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.4647887323943662,
532
+ "grad_norm": 2.769561290740967,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 2.0072,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.47183098591549294,
539
+ "grad_norm": 1.6377378702163696,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.378,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.4788732394366197,
546
+ "grad_norm": 2.9717202186584473,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.9511,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.4859154929577465,
553
+ "grad_norm": 1.5930095911026,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.6474,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.49295774647887325,
560
+ "grad_norm": 2.147733688354492,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.5024,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.5,
567
+ "grad_norm": 2.3971445560455322,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.4185,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.5070422535211268,
574
+ "grad_norm": 2.334181308746338,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.4944,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.5070422535211268,
581
+ "eval_loss": 0.7280327677726746,
582
+ "eval_runtime": 5.2593,
583
+ "eval_samples_per_second": 22.817,
584
+ "eval_steps_per_second": 2.852,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.5140845070422535,
589
+ "grad_norm": 2.140132427215576,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.4209,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.5211267605633803,
596
+ "grad_norm": 1.595037817955017,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.6229,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.528169014084507,
603
+ "grad_norm": 3.3290388584136963,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.4053,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 4.90098483265536e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null