Hugging Face's logo

lesso03
/
e6bdfa97-5090-445b-9017-ba45d2da0a32

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso03 commited on
Commit
efd17dc
·
verified ·
1 Parent(s): 0376fd0

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 sha256:9a4458e0bf4a61acc42dbf5111a62e09e99c43ff78e29ddcb01f706ba34c6ade
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f93a300e3f3b5f25803b84c9e7de73b41cf01a0974beaf422f399d9400a6f20
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:892da1a8ef8e351cf1cafb0d1cf2522c8e347f7e4c0fffa1601e5cf8bfe769b2
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a42b541feb92b363bc38c6e7755d5fcd38ab8cd52678647d74c5e2f7ef4dc75
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:530487a5edf6ba65c7204040f421229570d7408fe24ffdeb3f7f121ae6e97780
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d974693f1b73d24c115a391c91cb48722102d864f187f886474234f46a38e9
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": 0.01300221037576388,
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": 10.3791,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 2850483339264.0,
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": 0.01950331556364582,
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": 10.3791,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.013262254583279157,
411
+ "grad_norm": 0.03601168096065521,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 10.3785,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.013522298790794435,
418
+ "grad_norm": 0.0392109639942646,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 10.3772,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.013782342998309712,
425
+ "grad_norm": 0.038347356021404266,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 10.3782,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.01404238720582499,
432
+ "grad_norm": 0.05170854181051254,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 10.3791,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.01404238720582499,
439
+ "eval_loss": 10.378482818603516,
440
+ "eval_runtime": 25.1756,
441
+ "eval_samples_per_second": 128.657,
442
+ "eval_steps_per_second": 16.087,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.014302431413340267,
447
+ "grad_norm": 0.0428142324090004,
448
+ "learning_rate": 5e-05,
449
+ "loss": 10.3794,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.014562475620855546,
454
+ "grad_norm": 0.037890929728746414,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 10.3741,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.014822519828370823,
461
+ "grad_norm": 0.03927186131477356,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 10.3771,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.015082564035886101,
468
+ "grad_norm": 0.03995467722415924,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 10.3758,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.015342608243401378,
475
+ "grad_norm": 0.04345840960741043,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 10.3802,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.015602652450916656,
482
+ "grad_norm": 0.03900769725441933,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 10.3786,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.015862696658431933,
489
+ "grad_norm": 0.04522537812590599,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 10.3794,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.01612274086594721,
496
+ "grad_norm": 0.04456991329789162,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 10.38,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.01638278507346249,
503
+ "grad_norm": 0.04366768151521683,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 10.38,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.01638278507346249,
510
+ "eval_loss": 10.377856254577637,
511
+ "eval_runtime": 25.6986,
512
+ "eval_samples_per_second": 126.038,
513
+ "eval_steps_per_second": 15.76,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.016642829280977767,
518
+ "grad_norm": 0.037021130323410034,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 10.3788,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.016902873488493043,
525
+ "grad_norm": 0.05037117004394531,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 10.3793,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.01716291769600832,
532
+ "grad_norm": 0.04364752769470215,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 10.3806,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0174229619035236,
539
+ "grad_norm": 0.0497322604060173,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 10.3793,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.017683006111038877,
546
+ "grad_norm": 0.0477624237537384,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 10.3787,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.017943050318554154,
553
+ "grad_norm": 0.04558240994811058,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 10.3801,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.01820309452606943,
560
+ "grad_norm": 0.03950976952910423,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 10.3733,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.01846313873358471,
567
+ "grad_norm": 0.04475395381450653,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 10.3772,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.018723182941099988,
574
+ "grad_norm": 0.058802977204322815,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 10.3766,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.018723182941099988,
581
+ "eval_loss": 10.377392768859863,
582
+ "eval_runtime": 25.9933,
583
+ "eval_samples_per_second": 124.609,
584
+ "eval_steps_per_second": 15.581,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.018983227148615264,
589
+ "grad_norm": 0.04606263339519501,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 10.3784,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.01924327135613054,
596
+ "grad_norm": 0.044724252074956894,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 10.3761,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.01950331556364582,
603
+ "grad_norm": 0.04722006618976593,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 10.3747,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 4288800620544.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null