Hugging Face's logo

lesso07
/
58532653-71b1-4e20-b6af-81243e8976d0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso07 commited on
Commit
ee8b73e
·
verified ·
1 Parent(s): 01a6477

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:a510fe165aae28915849ab21b4a2389f97dc68f0eba51edf2e9d89e0c442733f
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f1bef8c07cc222a092b0f5a1871431eab788ec7e2f37b2fd32870591f9f174
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3c0e3814cb8f46e5ec8a340aba015af3097aa3b8dc5286e92c993179f4a9c10
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8e998732b81666d3775792ac52a7376c9d2b0e7809b282ee36dc97e3d20acf
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11514b197853b462348465f3dc339beef02f4f254b0c41ac5a64915cdbed9ea0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af799fe3211e3e40d8b9706f8c3b206167d5ffb2362156a8c722bc7264a1502
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": 0.33783783783783783,
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": 2.062,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 5146843860172800.0,
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": 0.5067567567567568,
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": 2.062,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.34459459459459457,
411
+ "grad_norm": 1.1078695058822632,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 2.1678,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.35135135135135137,
418
+ "grad_norm": 0.9430006742477417,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.8513,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.3581081081081081,
425
+ "grad_norm": 0.9669394493103027,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.8486,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.36486486486486486,
432
+ "grad_norm": 0.9533030390739441,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.8129,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.36486486486486486,
439
+ "eval_loss": 1.7548061609268188,
440
+ "eval_runtime": 3.5366,
441
+ "eval_samples_per_second": 35.345,
442
+ "eval_steps_per_second": 4.524,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.3716216216216216,
447
+ "grad_norm": 0.8269166350364685,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.6914,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.3783783783783784,
454
+ "grad_norm": 0.9480825662612915,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.8577,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.38513513513513514,
461
+ "grad_norm": 0.9473639130592346,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.9744,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.3918918918918919,
468
+ "grad_norm": 0.9393849968910217,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.8944,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.39864864864864863,
475
+ "grad_norm": 0.848622739315033,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.619,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.40540540540540543,
482
+ "grad_norm": 0.9589544534683228,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.8031,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.41216216216216217,
489
+ "grad_norm": 0.9193155169487,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.57,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.4189189189189189,
496
+ "grad_norm": 0.8888735175132751,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.5869,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.42567567567567566,
503
+ "grad_norm": 0.9404612183570862,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.8206,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.42567567567567566,
510
+ "eval_loss": 1.7357913255691528,
511
+ "eval_runtime": 3.5129,
512
+ "eval_samples_per_second": 35.583,
513
+ "eval_steps_per_second": 4.555,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.43243243243243246,
518
+ "grad_norm": 0.8742846846580505,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.5211,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.4391891891891892,
525
+ "grad_norm": 0.9241499304771423,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 2.082,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.44594594594594594,
532
+ "grad_norm": 0.9210823774337769,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.7166,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.4527027027027027,
539
+ "grad_norm": 0.8455032706260681,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.5984,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.4594594594594595,
546
+ "grad_norm": 0.9703152775764465,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.8997,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.46621621621621623,
553
+ "grad_norm": 1.0417201519012451,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.6946,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.47297297297297297,
560
+ "grad_norm": 0.8623643517494202,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.8819,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.4797297297297297,
567
+ "grad_norm": 0.8981446027755737,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.7159,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.4864864864864865,
574
+ "grad_norm": 0.8115476965904236,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.3985,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.4864864864864865,
581
+ "eval_loss": 1.719651699066162,
582
+ "eval_runtime": 3.5221,
583
+ "eval_samples_per_second": 35.49,
584
+ "eval_steps_per_second": 4.543,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.49324324324324326,
589
+ "grad_norm": 0.8665674328804016,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.5179,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.5,
596
+ "grad_norm": 0.9210397005081177,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.7493,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.5067567567567568,
603
+ "grad_norm": 0.8442562222480774,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.8021,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7771734228860928.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null