Hugging Face's logo

lesso05
/
1ddc9cb3-5687-42f7-972f-9d905f7cc732

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso05 commited on
Commit
3bfccd8
·
verified ·
1 Parent(s): e6e412e

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 sha256:55556b9360233dc159d601dfa1acfa34b0253a7e6f4330a52ba6636d211ab434
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c53ba2c78c7fcaeb53336a67a1a08083d32bea1bf7a4c0033d9f9795377b468e
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f377313668bebd864741703aaba0decc7b42b2a3b21e110ccbaf6b276dc104
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d365ca527cb3d8dc8d7ae0abb2a8bacf9acc57d5db4929590f1013cb700543e
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:cad57760029cf28563e59df0d6afdcc3b95ff86cb77fe0cab8e460b3d873d363
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58b155e5123c7f1976665fc15d0993b62f2994fac0848287641211bae5ae5bc
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": 0.0859106529209622,
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": 1.1236,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.53458201903104e+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": 0.12886597938144329,
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": 1.1236,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.08762886597938144,
411
+ "grad_norm": 0.6229404807090759,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.0744,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.08934707903780069,
418
+ "grad_norm": 0.6649324297904968,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.2195,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.09106529209621993,
425
+ "grad_norm": 0.6774650812149048,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.1679,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.09278350515463918,
432
+ "grad_norm": 0.7095744013786316,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.108,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.09278350515463918,
439
+ "eval_loss": 0.5606745481491089,
440
+ "eval_runtime": 90.1119,
441
+ "eval_samples_per_second": 5.438,
442
+ "eval_steps_per_second": 0.688,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.09450171821305842,
447
+ "grad_norm": 0.6476197838783264,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.1153,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.09621993127147767,
454
+ "grad_norm": 0.6215334534645081,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.0411,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0979381443298969,
461
+ "grad_norm": 0.6149742603302002,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.065,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.09965635738831616,
468
+ "grad_norm": 0.6694630980491638,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.1175,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.1013745704467354,
475
+ "grad_norm": 0.651583731174469,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.0373,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.10309278350515463,
482
+ "grad_norm": 0.7086051106452942,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.1749,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.10481099656357389,
489
+ "grad_norm": 0.6843875050544739,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.1709,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.10652920962199312,
496
+ "grad_norm": 0.6379663944244385,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.0606,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.10824742268041238,
503
+ "grad_norm": 0.6318539381027222,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.0532,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.10824742268041238,
510
+ "eval_loss": 0.5513098835945129,
511
+ "eval_runtime": 90.0773,
512
+ "eval_samples_per_second": 5.44,
513
+ "eval_steps_per_second": 0.688,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.10996563573883161,
518
+ "grad_norm": 0.6428488492965698,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.1226,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.11168384879725086,
525
+ "grad_norm": 0.645643413066864,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.0735,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.1134020618556701,
532
+ "grad_norm": 0.6907498836517334,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.1535,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.11512027491408934,
539
+ "grad_norm": 0.694670557975769,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.1467,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.11683848797250859,
546
+ "grad_norm": 0.6445086598396301,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.203,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.11855670103092783,
553
+ "grad_norm": 0.6669037342071533,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.1215,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.12027491408934708,
560
+ "grad_norm": 0.6564927697181702,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.0801,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.12199312714776632,
567
+ "grad_norm": 0.6863424181938171,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.0468,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.12371134020618557,
574
+ "grad_norm": 0.6587359309196472,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.1093,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.12371134020618557,
581
+ "eval_loss": 0.545613706111908,
582
+ "eval_runtime": 90.0987,
583
+ "eval_samples_per_second": 5.438,
584
+ "eval_steps_per_second": 0.688,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.1254295532646048,
589
+ "grad_norm": 0.6815155148506165,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.1796,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.12714776632302405,
596
+ "grad_norm": 0.6789014339447021,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.09,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.12886597938144329,
603
+ "grad_norm": 0.5994151830673218,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.0405,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.80187302854656e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null