dimasik2987 commited on
Commit
341f572
1 Parent(s): 957d719

Training in progress, step 75, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64d74e79aae9d1ccf5119bf5934a597572dd633b3c363863d20a6df81e31aa2
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0a1ce6d86852e9793e737e65d556d3df255e49f387bcba9992e5d9b438db81
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c4fd1c816e41aee5ea31a357b563620c35f6f7570c9840a262b78b29a65949
3
  size 313998650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47072bfd7244c6c06fe1a851f91407e928547735634d696d48a0c8599acff2f1
3
  size 313998650
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf6e2a58c61d475445667dd025fa2d042c8e1b2a88048290fc79ad802251df6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36241241c556c0422936654eb78722f0afdb8217df9491d285f074e05b26e247
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
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": 0.019112236609489224,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,189 @@
381
  "eval_samples_per_second": 9.252,
382
  "eval_steps_per_second": 4.626,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -395,12 +578,12 @@
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
- "should_training_stop": false
399
  },
400
  "attributes": {}
401
  }
402
  },
403
- "total_flos": 1.98682972520448e+16,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.028668354914233838,
5
  "eval_steps": 25,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 9.252,
382
  "eval_steps_per_second": 4.626,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.01949448134167901,
387
+ "grad_norm": 9.267752647399902,
388
+ "learning_rate": 2.500000000000001e-05,
389
+ "loss": 4.2077,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.019876726073868794,
394
+ "grad_norm": 9.39410400390625,
395
+ "learning_rate": 2.3135019582658802e-05,
396
+ "loss": 4.1575,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.02025897080605858,
401
+ "grad_norm": 8.945734977722168,
402
+ "learning_rate": 2.132117818244771e-05,
403
+ "loss": 3.9224,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.020641215538248363,
408
+ "grad_norm": 8.452441215515137,
409
+ "learning_rate": 1.9561928549563968e-05,
410
+ "loss": 3.3653,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.02102346027043815,
415
+ "grad_norm": 7.56348180770874,
416
+ "learning_rate": 1.7860619515673033e-05,
417
+ "loss": 3.7901,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.021405705002627933,
422
+ "grad_norm": 7.109958648681641,
423
+ "learning_rate": 1.622048961921699e-05,
424
+ "loss": 3.9603,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.021787949734817718,
429
+ "grad_norm": 7.252974987030029,
430
+ "learning_rate": 1.4644660940672627e-05,
431
+ "loss": 3.7393,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.022170194467007503,
436
+ "grad_norm": 6.574551105499268,
437
+ "learning_rate": 1.3136133159493802e-05,
438
+ "loss": 3.5858,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.022552439199197288,
443
+ "grad_norm": 5.8216447830200195,
444
+ "learning_rate": 1.1697777844051105e-05,
445
+ "loss": 3.341,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.02293468393138707,
450
+ "grad_norm": 5.938989162445068,
451
+ "learning_rate": 1.0332332985438248e-05,
452
+ "loss": 3.22,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.023316928663576854,
457
+ "grad_norm": 5.049765110015869,
458
+ "learning_rate": 9.042397785550405e-06,
459
+ "loss": 3.3303,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.02369917339576664,
464
+ "grad_norm": 4.824350357055664,
465
+ "learning_rate": 7.830427709355725e-06,
466
+ "loss": 3.2963,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.024081418127956424,
471
+ "grad_norm": 5.315403461456299,
472
+ "learning_rate": 6.698729810778065e-06,
473
+ "loss": 2.9856,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.02446366286014621,
478
+ "grad_norm": 4.886056900024414,
479
+ "learning_rate": 5.649458341088915e-06,
480
+ "loss": 2.9163,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.024845907592335993,
485
+ "grad_norm": 5.032073497772217,
486
+ "learning_rate": 4.684610648167503e-06,
487
+ "loss": 3.2227,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.025228152324525778,
492
+ "grad_norm": 4.646665573120117,
493
+ "learning_rate": 3.8060233744356633e-06,
494
+ "loss": 3.1442,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.025610397056715563,
499
+ "grad_norm": 4.919647216796875,
500
+ "learning_rate": 3.0153689607045845e-06,
501
+ "loss": 3.1255,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.025992641788905348,
506
+ "grad_norm": 5.229823112487793,
507
+ "learning_rate": 2.314152462588659e-06,
508
+ "loss": 2.7633,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.026374886521095132,
513
+ "grad_norm": 4.874609470367432,
514
+ "learning_rate": 1.70370868554659e-06,
515
+ "loss": 2.9428,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.026757131253284917,
520
+ "grad_norm": 4.912359714508057,
521
+ "learning_rate": 1.1851996440033319e-06,
522
+ "loss": 2.9206,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.0271393759854747,
527
+ "grad_norm": 4.882635593414307,
528
+ "learning_rate": 7.596123493895991e-07,
529
+ "loss": 2.7132,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.027521620717664484,
534
+ "grad_norm": 4.96625280380249,
535
+ "learning_rate": 4.277569313094809e-07,
536
+ "loss": 2.6065,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.02790386544985427,
541
+ "grad_norm": 5.217054843902588,
542
+ "learning_rate": 1.9026509541272275e-07,
543
+ "loss": 2.7019,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.028286110182044053,
548
+ "grad_norm": 5.2616705894470215,
549
+ "learning_rate": 4.7588920907110094e-08,
550
+ "loss": 2.5789,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.028668354914233838,
555
+ "grad_norm": 5.830911159515381,
556
+ "learning_rate": 0.0,
557
+ "loss": 3.0903,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.028668354914233838,
562
+ "eval_loss": 2.6363327503204346,
563
+ "eval_runtime": 238.1673,
564
+ "eval_samples_per_second": 9.254,
565
+ "eval_steps_per_second": 4.627,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
578
  "should_evaluate": false,
579
  "should_log": false,
580
  "should_save": true,
581
+ "should_training_stop": true
582
  },
583
  "attributes": {}
584
  }
585
  },
586
+ "total_flos": 2.98024458780672e+16,
587
  "train_batch_size": 2,
588
  "trial_name": null,
589
  "trial_params": null