Hugging Face's logo

lesso05
/
b3be65aa-c29d-43b1-9b69-163f0950e5d6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso05 commited on
Commit
6948b26
·
verified ·
1 Parent(s): ccbaaa8

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 sha256:20a1f4fc48191511ee8238751e45fb455f07a343e925ced4436966b25802b33a
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9c9988eb95110d6bbb0f40f363f8865bdec434ba073f7b14685ea49654fb07
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03d216b8ef66614dd2b0e7d65dfa1ea3d313c0bf0c28a85f740da026263d3990
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc8eb602935fd30627db4a815df8a8d74c2b36e2716d6edd4a65010321fe2a4
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:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
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": 10.3559,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 2615122329600.0,
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": 0.528169014084507,
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": 10.3559,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.3591549295774648,
411
+ "grad_norm": 0.33691930770874023,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 10.3518,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.36619718309859156,
418
+ "grad_norm": 0.4393768608570099,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 10.3666,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.3732394366197183,
425
+ "grad_norm": 0.42232954502105713,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 10.3746,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.38028169014084506,
432
+ "grad_norm": 0.43516579270362854,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 10.3505,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.38028169014084506,
439
+ "eval_loss": 10.360475540161133,
440
+ "eval_runtime": 0.4151,
441
+ "eval_samples_per_second": 289.056,
442
+ "eval_steps_per_second": 36.132,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.3873239436619718,
447
+ "grad_norm": 0.3640041947364807,
448
+ "learning_rate": 5e-05,
449
+ "loss": 10.3532,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.39436619718309857,
454
+ "grad_norm": 0.4502539336681366,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 10.3388,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.4014084507042254,
461
+ "grad_norm": 0.40651506185531616,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 10.3417,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.4084507042253521,
468
+ "grad_norm": 0.3992672860622406,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 10.3183,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.4154929577464789,
475
+ "grad_norm": 0.4093829095363617,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 10.3617,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.4225352112676056,
482
+ "grad_norm": 0.4767419397830963,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 10.3806,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.4295774647887324,
489
+ "grad_norm": 0.463030606508255,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 10.3756,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.43661971830985913,
496
+ "grad_norm": 0.49670639634132385,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 10.3488,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.44366197183098594,
503
+ "grad_norm": 0.4131371080875397,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 10.3594,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.44366197183098594,
510
+ "eval_loss": 10.352477073669434,
511
+ "eval_runtime": 0.4055,
512
+ "eval_samples_per_second": 295.956,
513
+ "eval_steps_per_second": 36.994,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.4507042253521127,
518
+ "grad_norm": 0.37016379833221436,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 10.3651,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.45774647887323944,
525
+ "grad_norm": 0.4693770408630371,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 10.3473,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.4647887323943662,
532
+ "grad_norm": 0.34537220001220703,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 10.3488,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.47183098591549294,
539
+ "grad_norm": 0.48998722434043884,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 10.3422,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.4788732394366197,
546
+ "grad_norm": 0.3674013912677765,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 10.34,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.4859154929577465,
553
+ "grad_norm": 0.38952964544296265,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 10.3635,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.49295774647887325,
560
+ "grad_norm": 0.4728361666202545,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 10.3293,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.5,
567
+ "grad_norm": 0.4525172710418701,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 10.3354,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.5070422535211268,
574
+ "grad_norm": 0.4703201353549957,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 10.3275,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.5070422535211268,
581
+ "eval_loss": 10.34687328338623,
582
+ "eval_runtime": 0.4256,
583
+ "eval_samples_per_second": 281.966,
584
+ "eval_steps_per_second": 35.246,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.5140845070422535,
589
+ "grad_norm": 0.4370110332965851,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 10.3539,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.5211267605633803,
596
+ "grad_norm": 0.4113081693649292,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 10.3532,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.528169014084507,
603
+ "grad_norm": 0.4943798780441284,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 10.3506,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 3922683494400.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null