Hugging Face's logo

lesso07
/
cc4279ba-065d-4168-9ca5-f4c0e00d9900

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso07 commited on
Commit
8d57094
•
1 Parent(s): bf842fe

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:d6b8822e8ef13b78beed5989b208438e1a1f33b59ac7dd433ff16bf57cc0d67a
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb886e0757b0b17db9f1b9cd42abca1d7bf251e97a38643dafcc6b18ce18d88
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d394331cc8c7eea3ffbfe6d4f1cf19ac151294efb9b345dbccaa20dfa317c02
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:800fcfb385190dfa3fe5491c22f7add14bb199b150ed5764967663a04ea59671
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90cdb72911d38e9202f3334751018a6c79ad3b2006b03921a34979cf1abce5c7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:831cb014d734d1a236f43ff0ae6d2fae9843b9526271b8c069d0c080cd61d6bb
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": 0.2506265664160401,
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": 1.3792,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 5.946469637318246e+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": 0.37593984962406013,
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": 1.3792,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.2556390977443609,
411
+ "grad_norm": 1.3042017221450806,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.3079,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.2606516290726817,
418
+ "grad_norm": 2.5631418228149414,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.2139,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.2656641604010025,
425
+ "grad_norm": 1.2268803119659424,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.2679,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.2706766917293233,
432
+ "grad_norm": 2.560192584991455,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.3228,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.2706766917293233,
439
+ "eval_loss": 0.734089195728302,
440
+ "eval_runtime": 28.3315,
441
+ "eval_samples_per_second": 5.93,
442
+ "eval_steps_per_second": 0.741,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.2756892230576441,
447
+ "grad_norm": 1.112692952156067,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.1927,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.2807017543859649,
454
+ "grad_norm": 3.5040154457092285,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.6805,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.2857142857142857,
461
+ "grad_norm": 1.8913439512252808,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.2348,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.2907268170426065,
468
+ "grad_norm": 3.6960103511810303,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.7078,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.2957393483709273,
475
+ "grad_norm": 3.0150368213653564,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.5443,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.3007518796992481,
482
+ "grad_norm": 2.5609323978424072,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.4539,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.3057644110275689,
489
+ "grad_norm": 2.451897382736206,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.5173,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.3107769423558897,
496
+ "grad_norm": 2.140015125274658,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.4675,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.3157894736842105,
503
+ "grad_norm": 2.0622689723968506,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.345,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.3157894736842105,
510
+ "eval_loss": 0.6988301873207092,
511
+ "eval_runtime": 28.3304,
512
+ "eval_samples_per_second": 5.93,
513
+ "eval_steps_per_second": 0.741,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.3208020050125313,
518
+ "grad_norm": 3.642866373062134,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.4744,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.3258145363408521,
525
+ "grad_norm": 1.6694496870040894,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.445,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.3308270676691729,
532
+ "grad_norm": 2.037517547607422,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.4296,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.3358395989974937,
539
+ "grad_norm": 1.9167176485061646,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.3653,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.3408521303258145,
546
+ "grad_norm": 1.5640507936477661,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.3799,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.3458646616541353,
553
+ "grad_norm": 1.5936436653137207,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.3459,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.3508771929824561,
560
+ "grad_norm": 1.5570849180221558,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.3129,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.3558897243107769,
567
+ "grad_norm": 1.6648975610733032,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.2919,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.3609022556390977,
574
+ "grad_norm": 1.4776012897491455,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.4474,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.3609022556390977,
581
+ "eval_loss": 0.689708411693573,
582
+ "eval_runtime": 28.3408,
583
+ "eval_samples_per_second": 5.928,
584
+ "eval_steps_per_second": 0.741,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.3659147869674185,
589
+ "grad_norm": 9.771589279174805,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.7794,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.37092731829573933,
596
+ "grad_norm": 2.208794355392456,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.4788,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.37593984962406013,
603
+ "grad_norm": 2.5760669708251953,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.5225,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 8.887031545882214e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null