Hugging Face's logo

lesso01
/
b890da7f-865b-4f11-80c0-9395d138e88e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
81769e4
·
verified ·
1 Parent(s): 0e33e8e

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 sha256:9e4d068ad2bbd99801d9d0e72e16357ea266ba29b0e535e1b98d3182b72aaf95
3
  size 13587864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fcfc3ee95215c0c20d581f3f1423d9ecaa76f00b70e323ee8e10885047a79b8
3
  size 13587864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e2ffa5b4b5275e6845c2490878407779da9efd61d29a52a19a1d88fdd747841
3
  size 27273018
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f015b0dd6ff9416a388857a4fb06c33f225dbedd7fd8ec088e600654f70a063
3
  size 27273018
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239232cf7c5031833b038c630b77e099bb2bf58f2bd57a48368600792c74cee2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf907df125d736a55f06d03d9cdedce0bb4c3f9baece6cc712d35b7fc7e8fd7
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": 0.07451564828614009,
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": 0.3541,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 694187930419200.0,
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": 0.11177347242921014,
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": 0.3541,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.07600596125186289,
411
+ "grad_norm": 0.8720141053199768,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.3429,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.07749627421758569,
418
+ "grad_norm": 1.314767599105835,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.2712,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.07898658718330849,
425
+ "grad_norm": 1.2060467004776,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.3906,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.08047690014903129,
432
+ "grad_norm": 1.077643871307373,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.2892,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.08047690014903129,
439
+ "eval_loss": 0.35677972435951233,
440
+ "eval_runtime": 2.708,
441
+ "eval_samples_per_second": 208.641,
442
+ "eval_steps_per_second": 26.219,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.08196721311475409,
447
+ "grad_norm": 1.2945141792297363,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.3159,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.08345752608047691,
454
+ "grad_norm": 1.3156005144119263,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.3413,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.08494783904619971,
461
+ "grad_norm": 1.6275720596313477,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.3478,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.08643815201192251,
468
+ "grad_norm": 1.8152949810028076,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.3269,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.08792846497764531,
475
+ "grad_norm": 1.127657413482666,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.339,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.08941877794336811,
482
+ "grad_norm": 1.2930176258087158,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.4244,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.09090909090909091,
489
+ "grad_norm": 1.3748923540115356,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.2725,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.09239940387481371,
496
+ "grad_norm": 1.7203524112701416,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.3573,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.09388971684053651,
503
+ "grad_norm": 0.811051607131958,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.2246,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.09388971684053651,
510
+ "eval_loss": 0.3099740743637085,
511
+ "eval_runtime": 2.7369,
512
+ "eval_samples_per_second": 206.441,
513
+ "eval_steps_per_second": 25.942,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.09538002980625931,
518
+ "grad_norm": 1.456381916999817,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.2353,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.09687034277198212,
525
+ "grad_norm": 0.758620023727417,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.2168,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.09836065573770492,
532
+ "grad_norm": 1.1172595024108887,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.2702,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.09985096870342772,
539
+ "grad_norm": 0.9833356738090515,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.3002,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.10134128166915052,
546
+ "grad_norm": 1.0243797302246094,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.2407,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.10283159463487332,
553
+ "grad_norm": 0.6949136853218079,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.2043,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.10432190760059612,
560
+ "grad_norm": 1.4197059869766235,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.2862,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.10581222056631892,
567
+ "grad_norm": 0.7830525636672974,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.2069,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.10730253353204174,
574
+ "grad_norm": 1.1061123609542847,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.2021,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.10730253353204174,
581
+ "eval_loss": 0.2788161039352417,
582
+ "eval_runtime": 2.6609,
583
+ "eval_samples_per_second": 212.333,
584
+ "eval_steps_per_second": 26.683,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.10879284649776454,
589
+ "grad_norm": 0.7569260001182556,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.2181,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.11028315946348734,
596
+ "grad_norm": 0.9492326974868774,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.3657,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.11177347242921014,
603
+ "grad_norm": 0.8849908709526062,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.2092,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 1041281895628800.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null