Hugging Face's logo

lesso05
/
005fb086-9df9-41ae-8326-ff27d8d22bc4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso05 commited on
Commit
b8fe86b
·
verified ·
1 Parent(s): a1e044d

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 sha256:63e0cc77edea88572543764b6c951757beee7f485322db5cec447e8beb8eccc7
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce6cd20e681f98c2734c015985c305bd4186b6e971f6865b92d0459cd678488
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a664b930e1bddf7987b31444e4cbdf4987a7205d1a58550b98f9370ac0bad05b
3
  size 1601338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3d74f37abd9193ac7105ef99460da0265fc91c8bfe894a1e42cb085a18679f
3
  size 1601338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561c96a9de2039e2fc252d4f61038d8c0e79bafac8eb8ddb35ced95407e0d204
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20bd7f9e98977739901deb4ac065306087d350d274dcb68e6b2fdb27bdb7adc
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": 0.0749063670411985,
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": 4.3734,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 13574760038400.0,
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": 0.11235955056179775,
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": 4.3734,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.07640449438202247,
411
+ "grad_norm": 2.5853934288024902,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 4.313,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.07790262172284644,
418
+ "grad_norm": 2.9297568798065186,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 4.6197,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.07940074906367041,
425
+ "grad_norm": 2.545381546020508,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 4.0591,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.08089887640449438,
432
+ "grad_norm": 2.857722520828247,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 4.5878,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.08089887640449438,
439
+ "eval_loss": 4.307217597961426,
440
+ "eval_runtime": 5.1062,
441
+ "eval_samples_per_second": 110.061,
442
+ "eval_steps_per_second": 13.905,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.08239700374531835,
447
+ "grad_norm": 2.407810688018799,
448
+ "learning_rate": 5e-05,
449
+ "loss": 4.3392,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.08389513108614233,
454
+ "grad_norm": 2.570552110671997,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 4.4584,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0853932584269663,
461
+ "grad_norm": 2.6279847621917725,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 4.425,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.08689138576779026,
468
+ "grad_norm": 3.007448434829712,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 4.5935,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.08838951310861423,
475
+ "grad_norm": 2.377514123916626,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 3.9613,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0898876404494382,
482
+ "grad_norm": 2.6137871742248535,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 4.1664,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.09138576779026217,
489
+ "grad_norm": 2.346526861190796,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 4.3429,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.09288389513108614,
496
+ "grad_norm": 2.3919084072113037,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 4.3198,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.09438202247191012,
503
+ "grad_norm": 2.6010396480560303,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 4.4285,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.09438202247191012,
510
+ "eval_loss": 4.148770809173584,
511
+ "eval_runtime": 5.0464,
512
+ "eval_samples_per_second": 111.367,
513
+ "eval_steps_per_second": 14.07,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.09588014981273409,
518
+ "grad_norm": 2.1853432655334473,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 4.0948,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.09737827715355805,
525
+ "grad_norm": 2.2798073291778564,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 4.1717,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.09887640449438202,
532
+ "grad_norm": 2.386640787124634,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 3.9134,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.10037453183520599,
539
+ "grad_norm": 2.6383981704711914,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 4.3411,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.10187265917602996,
546
+ "grad_norm": 2.1975576877593994,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 4.1277,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.10337078651685393,
553
+ "grad_norm": 2.150082588195801,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 4.0219,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.10486891385767791,
560
+ "grad_norm": 2.762874126434326,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 4.2591,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.10636704119850188,
567
+ "grad_norm": 1.973354458808899,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 3.8811,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.10786516853932585,
574
+ "grad_norm": 2.2953357696533203,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 4.0632,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.10786516853932585,
581
+ "eval_loss": 4.0451812744140625,
582
+ "eval_runtime": 5.0459,
583
+ "eval_samples_per_second": 111.377,
584
+ "eval_steps_per_second": 14.071,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.10936329588014981,
589
+ "grad_norm": 2.3707635402679443,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 4.1333,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.11086142322097378,
596
+ "grad_norm": 2.294806480407715,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 4.0764,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.11235955056179775,
603
+ "grad_norm": 2.1599864959716797,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 3.7799,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 20362140057600.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null