CocoRoF commited on
Commit
cb630d0
·
verified ·
1 Parent(s): 93b3641

Training in progress, step 55000, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "v_proj",
27
  "q_proj",
28
- "k_proj",
29
- "down_proj"
30
  ],
31
  "task_type": "SEQ_CLS",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "down_proj",
27
  "q_proj",
28
+ "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "SEQ_CLS",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2c6c1cadce7ce52b13a926bfbafa64e446b86e5b4b7ec3eba9dfd5cad410f6
3
  size 962707376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3b4fea81f3900bfa69110b0134fccc266c3f6ab24b41591a22031c6dc0bf38
3
  size 962707376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b855713affff09aec742fce2d37ecba061f0936159fdaf7e21c3bd0641619255
3
- size 61870586
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abda76448b02ed8e0515fa61dee3b896a7eb5b7a285486480cdc210629933bb2
3
+ size 61873722
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e255daa5ad5f11069df3a999246b0ccdc09247bd43432e7fdcd3a70ab5d06348
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fc40fd4217bb1769994a01649f5a56abbdb75dddc3799ff60503d0cb999b01
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fba2973ecba0f00ec98a89ba1c3d4441c0d63876f4e6205a3677f60062c512c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d537560203eb7afe3f6a8a44879b439cea0a94e1a4b8761fd98f99d53cacdea
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:995a7178a2eebf115a7587c3e6c91ed487a1801369e20d9a59c790e542ab8b74
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29e1df3583637c5354ea07c22896e12d461364bcdcfbc1cbd8878bc3c491cdf
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8acf023b229f8625b4ebc78e4ac75d24c6c079231c7dd2b05ff59df4dcb92a3f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e34e43ccaf5787f5a424c1b44fbe292f707243ea8dc15124de1140db9b0f5d4
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac3a306a2182134e3345739eaf8e920ee1bbaf2cd67b334a1c9dd75d75464588
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e9475c739c6dcbf77fbb3156414a1f7621b69f01b559ea426b746f7680f932
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4201970100402832,
3
- "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-15000",
4
- "epoch": 0.08784117144986245,
5
- "eval_steps": 5000,
6
- "global_step": 15000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -454,13 +454,1151 @@
454
  "eval_samples_per_second": 210.503,
455
  "eval_steps_per_second": 6.578,
456
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
457
  }
458
  ],
459
  "logging_steps": 250,
460
- "max_steps": 170762,
461
  "num_input_tokens_seen": 0,
462
  "num_train_epochs": 1,
463
- "save_steps": 5000,
464
  "stateful_callbacks": {
465
  "TrainerControl": {
466
  "args": {
@@ -473,7 +1611,7 @@
473
  "attributes": {}
474
  }
475
  },
476
- "total_flos": 3.8871669372931277e+18,
477
  "train_batch_size": 8,
478
  "trial_name": null,
479
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.362331748008728,
3
+ "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-55000",
4
+ "epoch": 0.32206354899391737,
5
+ "eval_steps": 55000,
6
+ "global_step": 55000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
454
  "eval_samples_per_second": 210.503,
455
  "eval_steps_per_second": 6.578,
456
  "step": 15000
457
+ },
458
+ {
459
+ "epoch": 0.0892994385846771,
460
+ "grad_norm": 10.84184455871582,
461
+ "learning_rate": 0.00019349020046898423,
462
+ "loss": 0.4211,
463
+ "step": 15250
464
+ },
465
+ {
466
+ "epoch": 0.09076336380737672,
467
+ "grad_norm": 7.9568657875061035,
468
+ "learning_rate": 0.00019317920297562402,
469
+ "loss": 0.4203,
470
+ "step": 15500
471
+ },
472
+ {
473
+ "epoch": 0.09222728903007635,
474
+ "grad_norm": 12.237702369689941,
475
+ "learning_rate": 0.00019286820548226384,
476
+ "loss": 0.4181,
477
+ "step": 15750
478
+ },
479
+ {
480
+ "epoch": 0.09369121425277596,
481
+ "grad_norm": 25.739120483398438,
482
+ "learning_rate": 0.00019255720798890363,
483
+ "loss": 0.4143,
484
+ "step": 16000
485
+ },
486
+ {
487
+ "epoch": 0.09515513947547559,
488
+ "grad_norm": 8.341870307922363,
489
+ "learning_rate": 0.00019224621049554342,
490
+ "loss": 0.4171,
491
+ "step": 16250
492
+ },
493
+ {
494
+ "epoch": 0.09661906469817522,
495
+ "grad_norm": 10.707802772521973,
496
+ "learning_rate": 0.0001919352130021832,
497
+ "loss": 0.4058,
498
+ "step": 16500
499
+ },
500
+ {
501
+ "epoch": 0.09808298992087484,
502
+ "grad_norm": 7.021149158477783,
503
+ "learning_rate": 0.00019162421550882302,
504
+ "loss": 0.4211,
505
+ "step": 16750
506
+ },
507
+ {
508
+ "epoch": 0.09954691514357447,
509
+ "grad_norm": 11.840470314025879,
510
+ "learning_rate": 0.0001913132180154628,
511
+ "loss": 0.4093,
512
+ "step": 17000
513
+ },
514
+ {
515
+ "epoch": 0.10101084036627409,
516
+ "grad_norm": 7.401727676391602,
517
+ "learning_rate": 0.0001910022205221026,
518
+ "loss": 0.4281,
519
+ "step": 17250
520
+ },
521
+ {
522
+ "epoch": 0.10247476558897371,
523
+ "grad_norm": 7.601231575012207,
524
+ "learning_rate": 0.00019069246701871584,
525
+ "loss": 0.4044,
526
+ "step": 17500
527
+ },
528
+ {
529
+ "epoch": 0.10393869081167334,
530
+ "grad_norm": 6.85632848739624,
531
+ "learning_rate": 0.00019038146952535563,
532
+ "loss": 0.4244,
533
+ "step": 17750
534
+ },
535
+ {
536
+ "epoch": 0.10540261603437297,
537
+ "grad_norm": 10.810693740844727,
538
+ "learning_rate": 0.00019007171602196887,
539
+ "loss": 0.4216,
540
+ "step": 18000
541
+ },
542
+ {
543
+ "epoch": 0.1068665412570726,
544
+ "grad_norm": 9.758743286132812,
545
+ "learning_rate": 0.00018976071852860865,
546
+ "loss": 0.417,
547
+ "step": 18250
548
+ },
549
+ {
550
+ "epoch": 0.10833046647977221,
551
+ "grad_norm": 10.75692367553711,
552
+ "learning_rate": 0.00018944972103524847,
553
+ "loss": 0.4143,
554
+ "step": 18500
555
+ },
556
+ {
557
+ "epoch": 0.10979439170247184,
558
+ "grad_norm": 10.375711441040039,
559
+ "learning_rate": 0.00018913872354188826,
560
+ "loss": 0.4075,
561
+ "step": 18750
562
+ },
563
+ {
564
+ "epoch": 0.11125831692517146,
565
+ "grad_norm": 8.414403915405273,
566
+ "learning_rate": 0.00018882772604852805,
567
+ "loss": 0.4148,
568
+ "step": 19000
569
+ },
570
+ {
571
+ "epoch": 0.11272224214787109,
572
+ "grad_norm": 9.86490249633789,
573
+ "learning_rate": 0.00018851672855516786,
574
+ "loss": 0.4074,
575
+ "step": 19250
576
+ },
577
+ {
578
+ "epoch": 0.11418616737057072,
579
+ "grad_norm": 7.522060394287109,
580
+ "learning_rate": 0.00018820573106180765,
581
+ "loss": 0.4106,
582
+ "step": 19500
583
+ },
584
+ {
585
+ "epoch": 0.11565009259327033,
586
+ "grad_norm": 7.423270225524902,
587
+ "learning_rate": 0.00018789473356844744,
588
+ "loss": 0.4034,
589
+ "step": 19750
590
+ },
591
+ {
592
+ "epoch": 0.11711401781596996,
593
+ "grad_norm": 8.761688232421875,
594
+ "learning_rate": 0.00018758373607508723,
595
+ "loss": 0.4025,
596
+ "step": 20000
597
+ },
598
+ {
599
+ "epoch": 0.11711401781596996,
600
+ "eval_accuracy": 0.8823756104911845,
601
+ "eval_loss": 0.4016551673412323,
602
+ "eval_runtime": 11547.1595,
603
+ "eval_samples_per_second": 210.336,
604
+ "eval_steps_per_second": 6.573,
605
+ "step": 20000
606
+ },
607
+ {
608
+ "epoch": 0.11857794303866959,
609
+ "grad_norm": 9.6015043258667,
610
+ "learning_rate": 0.0001872802025215677,
611
+ "loss": 0.4087,
612
+ "step": 20250
613
+ },
614
+ {
615
+ "epoch": 0.12004186826136921,
616
+ "grad_norm": 6.658656120300293,
617
+ "learning_rate": 0.00018696920502820748,
618
+ "loss": 0.408,
619
+ "step": 20500
620
+ },
621
+ {
622
+ "epoch": 0.12150579348406883,
623
+ "grad_norm": 6.935655117034912,
624
+ "learning_rate": 0.00018665820753484727,
625
+ "loss": 0.3983,
626
+ "step": 20750
627
+ },
628
+ {
629
+ "epoch": 0.12296971870676845,
630
+ "grad_norm": 7.918155193328857,
631
+ "learning_rate": 0.00018634721004148706,
632
+ "loss": 0.3994,
633
+ "step": 21000
634
+ },
635
+ {
636
+ "epoch": 0.12443364392946808,
637
+ "grad_norm": 7.246758937835693,
638
+ "learning_rate": 0.00018603621254812688,
639
+ "loss": 0.4111,
640
+ "step": 21250
641
+ },
642
+ {
643
+ "epoch": 0.1258975691521677,
644
+ "grad_norm": 8.375380516052246,
645
+ "learning_rate": 0.00018572521505476667,
646
+ "loss": 0.4006,
647
+ "step": 21500
648
+ },
649
+ {
650
+ "epoch": 0.12736149437486732,
651
+ "grad_norm": 6.993825435638428,
652
+ "learning_rate": 0.0001854154615513799,
653
+ "loss": 0.4113,
654
+ "step": 21750
655
+ },
656
+ {
657
+ "epoch": 0.12882541959756696,
658
+ "grad_norm": 8.703255653381348,
659
+ "learning_rate": 0.00018510446405801972,
660
+ "loss": 0.3977,
661
+ "step": 22000
662
+ },
663
+ {
664
+ "epoch": 0.13028934482026658,
665
+ "grad_norm": 6.940033912658691,
666
+ "learning_rate": 0.0001847934665646595,
667
+ "loss": 0.4005,
668
+ "step": 22250
669
+ },
670
+ {
671
+ "epoch": 0.1317532700429662,
672
+ "grad_norm": 6.712055683135986,
673
+ "learning_rate": 0.0001844824690712993,
674
+ "loss": 0.41,
675
+ "step": 22500
676
+ },
677
+ {
678
+ "epoch": 0.13321719526566583,
679
+ "grad_norm": 6.171209812164307,
680
+ "learning_rate": 0.0001841714715779391,
681
+ "loss": 0.3971,
682
+ "step": 22750
683
+ },
684
+ {
685
+ "epoch": 0.13468112048836545,
686
+ "grad_norm": 10.764921188354492,
687
+ "learning_rate": 0.0001838604740845789,
688
+ "loss": 0.4105,
689
+ "step": 23000
690
+ },
691
+ {
692
+ "epoch": 0.1361450457110651,
693
+ "grad_norm": 8.0676908493042,
694
+ "learning_rate": 0.0001835494765912187,
695
+ "loss": 0.3958,
696
+ "step": 23250
697
+ },
698
+ {
699
+ "epoch": 0.1376089709337647,
700
+ "grad_norm": 5.20599365234375,
701
+ "learning_rate": 0.00018323847909785848,
702
+ "loss": 0.3946,
703
+ "step": 23500
704
+ },
705
+ {
706
+ "epoch": 0.13907289615646432,
707
+ "grad_norm": 5.9439239501953125,
708
+ "learning_rate": 0.0001829274816044983,
709
+ "loss": 0.3951,
710
+ "step": 23750
711
+ },
712
+ {
713
+ "epoch": 0.14053682137916396,
714
+ "grad_norm": 9.821541786193848,
715
+ "learning_rate": 0.0001826164841111381,
716
+ "loss": 0.3906,
717
+ "step": 24000
718
+ },
719
+ {
720
+ "epoch": 0.14200074660186357,
721
+ "grad_norm": 6.659691333770752,
722
+ "learning_rate": 0.00018230673060775133,
723
+ "loss": 0.4009,
724
+ "step": 24250
725
+ },
726
+ {
727
+ "epoch": 0.1434646718245632,
728
+ "grad_norm": 6.624240398406982,
729
+ "learning_rate": 0.00018199573311439112,
730
+ "loss": 0.3975,
731
+ "step": 24500
732
+ },
733
+ {
734
+ "epoch": 0.14492859704726282,
735
+ "grad_norm": 7.993641376495361,
736
+ "learning_rate": 0.0001816847356210309,
737
+ "loss": 0.3925,
738
+ "step": 24750
739
+ },
740
+ {
741
+ "epoch": 0.14639252226996244,
742
+ "grad_norm": 6.6386613845825195,
743
+ "learning_rate": 0.0001813737381276707,
744
+ "loss": 0.3975,
745
+ "step": 25000
746
+ },
747
+ {
748
+ "epoch": 0.14785644749266208,
749
+ "grad_norm": 9.204560279846191,
750
+ "learning_rate": 0.0001810627406343105,
751
+ "loss": 0.3997,
752
+ "step": 25250
753
+ },
754
+ {
755
+ "epoch": 0.1493203727153617,
756
+ "grad_norm": 8.072566986083984,
757
+ "learning_rate": 0.0001807517431409503,
758
+ "loss": 0.4022,
759
+ "step": 25500
760
+ },
761
+ {
762
+ "epoch": 0.15078429793806133,
763
+ "grad_norm": 10.15225601196289,
764
+ "learning_rate": 0.0001804407456475901,
765
+ "loss": 0.392,
766
+ "step": 25750
767
+ },
768
+ {
769
+ "epoch": 0.15224822316076095,
770
+ "grad_norm": 7.751401901245117,
771
+ "learning_rate": 0.0001801297481542299,
772
+ "loss": 0.3946,
773
+ "step": 26000
774
+ },
775
+ {
776
+ "epoch": 0.15371214838346056,
777
+ "grad_norm": 8.481501579284668,
778
+ "learning_rate": 0.0001798187506608697,
779
+ "loss": 0.3883,
780
+ "step": 26250
781
+ },
782
+ {
783
+ "epoch": 0.1551760736061602,
784
+ "grad_norm": 9.861278533935547,
785
+ "learning_rate": 0.00017950775316750948,
786
+ "loss": 0.3824,
787
+ "step": 26500
788
+ },
789
+ {
790
+ "epoch": 0.15663999882885982,
791
+ "grad_norm": 6.405235290527344,
792
+ "learning_rate": 0.0001791967556741493,
793
+ "loss": 0.4006,
794
+ "step": 26750
795
+ },
796
+ {
797
+ "epoch": 0.15810392405155946,
798
+ "grad_norm": 9.90355110168457,
799
+ "learning_rate": 0.00017888575818078909,
800
+ "loss": 0.3881,
801
+ "step": 27000
802
+ },
803
+ {
804
+ "epoch": 0.15956784927425907,
805
+ "grad_norm": 9.354215621948242,
806
+ "learning_rate": 0.00017857476068742887,
807
+ "loss": 0.3965,
808
+ "step": 27250
809
+ },
810
+ {
811
+ "epoch": 0.16103177449695869,
812
+ "grad_norm": 9.162219047546387,
813
+ "learning_rate": 0.00017826376319406866,
814
+ "loss": 0.3933,
815
+ "step": 27500
816
+ },
817
+ {
818
+ "epoch": 0.16249569971965833,
819
+ "grad_norm": 6.755202770233154,
820
+ "learning_rate": 0.00017795276570070848,
821
+ "loss": 0.3874,
822
+ "step": 27750
823
+ },
824
+ {
825
+ "epoch": 0.16395962494235794,
826
+ "grad_norm": 8.385200500488281,
827
+ "learning_rate": 0.00017764176820734827,
828
+ "loss": 0.3873,
829
+ "step": 28000
830
+ },
831
+ {
832
+ "epoch": 0.16542355016505758,
833
+ "grad_norm": 6.508645057678223,
834
+ "learning_rate": 0.00017733077071398806,
835
+ "loss": 0.3895,
836
+ "step": 28250
837
+ },
838
+ {
839
+ "epoch": 0.1668874753877572,
840
+ "grad_norm": 8.241129875183105,
841
+ "learning_rate": 0.00017702226120057472,
842
+ "loss": 0.3912,
843
+ "step": 28500
844
+ },
845
+ {
846
+ "epoch": 0.1683514006104568,
847
+ "grad_norm": 7.879597187042236,
848
+ "learning_rate": 0.00017671126370721454,
849
+ "loss": 0.3929,
850
+ "step": 28750
851
+ },
852
+ {
853
+ "epoch": 0.16981532583315645,
854
+ "grad_norm": 12.0702486038208,
855
+ "learning_rate": 0.00017640026621385432,
856
+ "loss": 0.404,
857
+ "step": 29000
858
+ },
859
+ {
860
+ "epoch": 0.17127925105585606,
861
+ "grad_norm": 8.789772033691406,
862
+ "learning_rate": 0.0001760892687204941,
863
+ "loss": 0.3823,
864
+ "step": 29250
865
+ },
866
+ {
867
+ "epoch": 0.1727431762785557,
868
+ "grad_norm": 11.022305488586426,
869
+ "learning_rate": 0.00017577827122713393,
870
+ "loss": 0.3887,
871
+ "step": 29500
872
+ },
873
+ {
874
+ "epoch": 0.17420710150125532,
875
+ "grad_norm": 7.665167331695557,
876
+ "learning_rate": 0.00017546727373377372,
877
+ "loss": 0.394,
878
+ "step": 29750
879
+ },
880
+ {
881
+ "epoch": 0.17567102672395493,
882
+ "grad_norm": 11.05783748626709,
883
+ "learning_rate": 0.0001751562762404135,
884
+ "loss": 0.3938,
885
+ "step": 30000
886
+ },
887
+ {
888
+ "epoch": 0.17713495194665457,
889
+ "grad_norm": 8.389631271362305,
890
+ "learning_rate": 0.0001748452787470533,
891
+ "loss": 0.39,
892
+ "step": 30250
893
+ },
894
+ {
895
+ "epoch": 0.1785988771693542,
896
+ "grad_norm": 8.158947944641113,
897
+ "learning_rate": 0.0001745342812536931,
898
+ "loss": 0.3818,
899
+ "step": 30500
900
+ },
901
+ {
902
+ "epoch": 0.1800628023920538,
903
+ "grad_norm": 7.684356689453125,
904
+ "learning_rate": 0.0001742232837603329,
905
+ "loss": 0.3905,
906
+ "step": 30750
907
+ },
908
+ {
909
+ "epoch": 0.18152672761475344,
910
+ "grad_norm": 10.129668235778809,
911
+ "learning_rate": 0.00017391353025694614,
912
+ "loss": 0.3886,
913
+ "step": 31000
914
+ },
915
+ {
916
+ "epoch": 0.18299065283745305,
917
+ "grad_norm": 6.924737453460693,
918
+ "learning_rate": 0.00017360253276358593,
919
+ "loss": 0.3892,
920
+ "step": 31250
921
+ },
922
+ {
923
+ "epoch": 0.1844545780601527,
924
+ "grad_norm": 5.863354206085205,
925
+ "learning_rate": 0.00017329153527022572,
926
+ "loss": 0.3822,
927
+ "step": 31500
928
+ },
929
+ {
930
+ "epoch": 0.1859185032828523,
931
+ "grad_norm": 9.10240650177002,
932
+ "learning_rate": 0.00017298053777686553,
933
+ "loss": 0.3895,
934
+ "step": 31750
935
+ },
936
+ {
937
+ "epoch": 0.18738242850555192,
938
+ "grad_norm": 9.565494537353516,
939
+ "learning_rate": 0.00017266954028350532,
940
+ "loss": 0.383,
941
+ "step": 32000
942
+ },
943
+ {
944
+ "epoch": 0.18884635372825156,
945
+ "grad_norm": 8.238012313842773,
946
+ "learning_rate": 0.0001723585427901451,
947
+ "loss": 0.3854,
948
+ "step": 32250
949
+ },
950
+ {
951
+ "epoch": 0.19031027895095118,
952
+ "grad_norm": 9.350130081176758,
953
+ "learning_rate": 0.0001720475452967849,
954
+ "loss": 0.3922,
955
+ "step": 32500
956
+ },
957
+ {
958
+ "epoch": 0.19177420417365082,
959
+ "grad_norm": 6.337550163269043,
960
+ "learning_rate": 0.00017173654780342472,
961
+ "loss": 0.3778,
962
+ "step": 32750
963
+ },
964
+ {
965
+ "epoch": 0.19323812939635043,
966
+ "grad_norm": 8.421921730041504,
967
+ "learning_rate": 0.00017142679430003793,
968
+ "loss": 0.3929,
969
+ "step": 33000
970
+ },
971
+ {
972
+ "epoch": 0.19470205461905005,
973
+ "grad_norm": 8.888238906860352,
974
+ "learning_rate": 0.00017111579680667774,
975
+ "loss": 0.3844,
976
+ "step": 33250
977
+ },
978
+ {
979
+ "epoch": 0.1961659798417497,
980
+ "grad_norm": 10.774327278137207,
981
+ "learning_rate": 0.00017080479931331753,
982
+ "loss": 0.3804,
983
+ "step": 33500
984
+ },
985
+ {
986
+ "epoch": 0.1976299050644493,
987
+ "grad_norm": 7.07879114151001,
988
+ "learning_rate": 0.00017049380181995732,
989
+ "loss": 0.3954,
990
+ "step": 33750
991
+ },
992
+ {
993
+ "epoch": 0.19909383028714894,
994
+ "grad_norm": 7.102870941162109,
995
+ "learning_rate": 0.00017018280432659714,
996
+ "loss": 0.3815,
997
+ "step": 34000
998
+ },
999
+ {
1000
+ "epoch": 0.20055775550984856,
1001
+ "grad_norm": 5.815110206604004,
1002
+ "learning_rate": 0.00016987180683323693,
1003
+ "loss": 0.3907,
1004
+ "step": 34250
1005
+ },
1006
+ {
1007
+ "epoch": 0.20202168073254817,
1008
+ "grad_norm": 7.749156475067139,
1009
+ "learning_rate": 0.00016956080933987672,
1010
+ "loss": 0.3798,
1011
+ "step": 34500
1012
+ },
1013
+ {
1014
+ "epoch": 0.2034856059552478,
1015
+ "grad_norm": 7.0530476570129395,
1016
+ "learning_rate": 0.0001692498118465165,
1017
+ "loss": 0.3947,
1018
+ "step": 34750
1019
+ },
1020
+ {
1021
+ "epoch": 0.20494953117794742,
1022
+ "grad_norm": 6.623088836669922,
1023
+ "learning_rate": 0.00016893881435315632,
1024
+ "loss": 0.3816,
1025
+ "step": 35000
1026
+ },
1027
+ {
1028
+ "epoch": 0.20641345640064707,
1029
+ "grad_norm": 8.431561470031738,
1030
+ "learning_rate": 0.0001686278168597961,
1031
+ "loss": 0.3815,
1032
+ "step": 35250
1033
+ },
1034
+ {
1035
+ "epoch": 0.20787738162334668,
1036
+ "grad_norm": 11.600255012512207,
1037
+ "learning_rate": 0.00016831806335640935,
1038
+ "loss": 0.3782,
1039
+ "step": 35500
1040
+ },
1041
+ {
1042
+ "epoch": 0.2093413068460463,
1043
+ "grad_norm": 5.186095237731934,
1044
+ "learning_rate": 0.00016800706586304914,
1045
+ "loss": 0.3828,
1046
+ "step": 35750
1047
+ },
1048
+ {
1049
+ "epoch": 0.21080523206874593,
1050
+ "grad_norm": 12.819711685180664,
1051
+ "learning_rate": 0.00016769606836968895,
1052
+ "loss": 0.3902,
1053
+ "step": 36000
1054
+ },
1055
+ {
1056
+ "epoch": 0.21226915729144555,
1057
+ "grad_norm": 7.843264579772949,
1058
+ "learning_rate": 0.00016738507087632874,
1059
+ "loss": 0.3716,
1060
+ "step": 36250
1061
+ },
1062
+ {
1063
+ "epoch": 0.2137330825141452,
1064
+ "grad_norm": 8.602349281311035,
1065
+ "learning_rate": 0.00016707407338296853,
1066
+ "loss": 0.3791,
1067
+ "step": 36500
1068
+ },
1069
+ {
1070
+ "epoch": 0.2151970077368448,
1071
+ "grad_norm": 7.939485549926758,
1072
+ "learning_rate": 0.00016676307588960832,
1073
+ "loss": 0.3752,
1074
+ "step": 36750
1075
+ },
1076
+ {
1077
+ "epoch": 0.21666093295954442,
1078
+ "grad_norm": 6.328729629516602,
1079
+ "learning_rate": 0.00016645207839624814,
1080
+ "loss": 0.3761,
1081
+ "step": 37000
1082
+ },
1083
+ {
1084
+ "epoch": 0.21812485818224406,
1085
+ "grad_norm": 6.196065902709961,
1086
+ "learning_rate": 0.00016614108090288793,
1087
+ "loss": 0.3817,
1088
+ "step": 37250
1089
+ },
1090
+ {
1091
+ "epoch": 0.21958878340494367,
1092
+ "grad_norm": 10.096115112304688,
1093
+ "learning_rate": 0.00016583008340952771,
1094
+ "loss": 0.3828,
1095
+ "step": 37500
1096
+ },
1097
+ {
1098
+ "epoch": 0.2210527086276433,
1099
+ "grad_norm": 6.120075702667236,
1100
+ "learning_rate": 0.0001655190859161675,
1101
+ "loss": 0.3774,
1102
+ "step": 37750
1103
+ },
1104
+ {
1105
+ "epoch": 0.22251663385034293,
1106
+ "grad_norm": 6.575611114501953,
1107
+ "learning_rate": 0.00016520808842280732,
1108
+ "loss": 0.3823,
1109
+ "step": 38000
1110
+ },
1111
+ {
1112
+ "epoch": 0.22398055907304254,
1113
+ "grad_norm": 7.636918067932129,
1114
+ "learning_rate": 0.0001648970909294471,
1115
+ "loss": 0.3846,
1116
+ "step": 38250
1117
+ },
1118
+ {
1119
+ "epoch": 0.22544448429574218,
1120
+ "grad_norm": 15.759072303771973,
1121
+ "learning_rate": 0.00016458733742606037,
1122
+ "loss": 0.3842,
1123
+ "step": 38500
1124
+ },
1125
+ {
1126
+ "epoch": 0.2269084095184418,
1127
+ "grad_norm": 10.398168563842773,
1128
+ "learning_rate": 0.0001642775839226736,
1129
+ "loss": 0.3794,
1130
+ "step": 38750
1131
+ },
1132
+ {
1133
+ "epoch": 0.22837233474114144,
1134
+ "grad_norm": 6.939914703369141,
1135
+ "learning_rate": 0.0001639665864293134,
1136
+ "loss": 0.3763,
1137
+ "step": 39000
1138
+ },
1139
+ {
1140
+ "epoch": 0.22983625996384105,
1141
+ "grad_norm": 11.021454811096191,
1142
+ "learning_rate": 0.0001636555889359532,
1143
+ "loss": 0.368,
1144
+ "step": 39250
1145
+ },
1146
+ {
1147
+ "epoch": 0.23130018518654066,
1148
+ "grad_norm": 7.381429195404053,
1149
+ "learning_rate": 0.00016334459144259298,
1150
+ "loss": 0.3783,
1151
+ "step": 39500
1152
+ },
1153
+ {
1154
+ "epoch": 0.2327641104092403,
1155
+ "grad_norm": 9.803789138793945,
1156
+ "learning_rate": 0.0001630335939492328,
1157
+ "loss": 0.3828,
1158
+ "step": 39750
1159
+ },
1160
+ {
1161
+ "epoch": 0.23422803563193992,
1162
+ "grad_norm": 7.722465991973877,
1163
+ "learning_rate": 0.00016272259645587259,
1164
+ "loss": 0.3764,
1165
+ "step": 40000
1166
+ },
1167
+ {
1168
+ "epoch": 0.23569196085463953,
1169
+ "grad_norm": 8.471487998962402,
1170
+ "learning_rate": 0.00016241159896251237,
1171
+ "loss": 0.3879,
1172
+ "step": 40250
1173
+ },
1174
+ {
1175
+ "epoch": 0.23715588607733917,
1176
+ "grad_norm": 9.46483039855957,
1177
+ "learning_rate": 0.00016210060146915216,
1178
+ "loss": 0.3772,
1179
+ "step": 40500
1180
+ },
1181
+ {
1182
+ "epoch": 0.2386198113000388,
1183
+ "grad_norm": 11.850425720214844,
1184
+ "learning_rate": 0.00016178960397579198,
1185
+ "loss": 0.3688,
1186
+ "step": 40750
1187
+ },
1188
+ {
1189
+ "epoch": 0.24008373652273843,
1190
+ "grad_norm": 7.718139171600342,
1191
+ "learning_rate": 0.00016147860648243177,
1192
+ "loss": 0.3728,
1193
+ "step": 41000
1194
+ },
1195
+ {
1196
+ "epoch": 0.24154766174543804,
1197
+ "grad_norm": 7.039102077484131,
1198
+ "learning_rate": 0.00016116760898907156,
1199
+ "loss": 0.3718,
1200
+ "step": 41250
1201
+ },
1202
+ {
1203
+ "epoch": 0.24301158696813766,
1204
+ "grad_norm": 6.891547679901123,
1205
+ "learning_rate": 0.00016085661149571137,
1206
+ "loss": 0.3713,
1207
+ "step": 41500
1208
+ },
1209
+ {
1210
+ "epoch": 0.2444755121908373,
1211
+ "grad_norm": 8.54554271697998,
1212
+ "learning_rate": 0.00016054561400235116,
1213
+ "loss": 0.3818,
1214
+ "step": 41750
1215
+ },
1216
+ {
1217
+ "epoch": 0.2459394374135369,
1218
+ "grad_norm": 6.554268836975098,
1219
+ "learning_rate": 0.00016023461650899095,
1220
+ "loss": 0.3706,
1221
+ "step": 42000
1222
+ },
1223
+ {
1224
+ "epoch": 0.24740336263623655,
1225
+ "grad_norm": 6.389885902404785,
1226
+ "learning_rate": 0.00015992361901563074,
1227
+ "loss": 0.3577,
1228
+ "step": 42250
1229
+ },
1230
+ {
1231
+ "epoch": 0.24886728785893616,
1232
+ "grad_norm": 6.833805561065674,
1233
+ "learning_rate": 0.00015961262152227056,
1234
+ "loss": 0.3722,
1235
+ "step": 42500
1236
+ },
1237
+ {
1238
+ "epoch": 0.2503312130816358,
1239
+ "grad_norm": 9.135841369628906,
1240
+ "learning_rate": 0.00015930162402891034,
1241
+ "loss": 0.3747,
1242
+ "step": 42750
1243
+ },
1244
+ {
1245
+ "epoch": 0.2517951383043354,
1246
+ "grad_norm": 7.466910362243652,
1247
+ "learning_rate": 0.00015899187052552358,
1248
+ "loss": 0.378,
1249
+ "step": 43000
1250
+ },
1251
+ {
1252
+ "epoch": 0.25325906352703503,
1253
+ "grad_norm": 14.597432136535645,
1254
+ "learning_rate": 0.00015868087303216337,
1255
+ "loss": 0.3743,
1256
+ "step": 43250
1257
+ },
1258
+ {
1259
+ "epoch": 0.25472298874973465,
1260
+ "grad_norm": 6.523279190063477,
1261
+ "learning_rate": 0.00015836987553880316,
1262
+ "loss": 0.3728,
1263
+ "step": 43500
1264
+ },
1265
+ {
1266
+ "epoch": 0.25618691397243426,
1267
+ "grad_norm": 5.352029800415039,
1268
+ "learning_rate": 0.00015805887804544298,
1269
+ "loss": 0.367,
1270
+ "step": 43750
1271
+ },
1272
+ {
1273
+ "epoch": 0.25765083919513393,
1274
+ "grad_norm": 8.408788681030273,
1275
+ "learning_rate": 0.00015774788055208277,
1276
+ "loss": 0.3694,
1277
+ "step": 44000
1278
+ },
1279
+ {
1280
+ "epoch": 0.25911476441783354,
1281
+ "grad_norm": 7.64408016204834,
1282
+ "learning_rate": 0.00015743688305872256,
1283
+ "loss": 0.3664,
1284
+ "step": 44250
1285
+ },
1286
+ {
1287
+ "epoch": 0.26057868964053316,
1288
+ "grad_norm": 4.888110637664795,
1289
+ "learning_rate": 0.00015712588556536234,
1290
+ "loss": 0.3637,
1291
+ "step": 44500
1292
+ },
1293
+ {
1294
+ "epoch": 0.26204261486323277,
1295
+ "grad_norm": 5.068843841552734,
1296
+ "learning_rate": 0.00015681488807200216,
1297
+ "loss": 0.369,
1298
+ "step": 44750
1299
+ },
1300
+ {
1301
+ "epoch": 0.2635065400859324,
1302
+ "grad_norm": 6.427637577056885,
1303
+ "learning_rate": 0.00015650389057864195,
1304
+ "loss": 0.3788,
1305
+ "step": 45000
1306
+ },
1307
+ {
1308
+ "epoch": 0.26497046530863205,
1309
+ "grad_norm": 8.00766658782959,
1310
+ "learning_rate": 0.00015619289308528174,
1311
+ "loss": 0.3638,
1312
+ "step": 45250
1313
+ },
1314
+ {
1315
+ "epoch": 0.26643439053133167,
1316
+ "grad_norm": 8.729680061340332,
1317
+ "learning_rate": 0.00015588189559192155,
1318
+ "loss": 0.3736,
1319
+ "step": 45500
1320
+ },
1321
+ {
1322
+ "epoch": 0.2678983157540313,
1323
+ "grad_norm": 10.317773818969727,
1324
+ "learning_rate": 0.00015557089809856134,
1325
+ "loss": 0.3618,
1326
+ "step": 45750
1327
+ },
1328
+ {
1329
+ "epoch": 0.2693622409767309,
1330
+ "grad_norm": 7.715869903564453,
1331
+ "learning_rate": 0.00015525990060520113,
1332
+ "loss": 0.3741,
1333
+ "step": 46000
1334
+ },
1335
+ {
1336
+ "epoch": 0.2708261661994305,
1337
+ "grad_norm": 5.711330890655518,
1338
+ "learning_rate": 0.00015494890311184092,
1339
+ "loss": 0.3745,
1340
+ "step": 46250
1341
+ },
1342
+ {
1343
+ "epoch": 0.2722900914221302,
1344
+ "grad_norm": 9.835432052612305,
1345
+ "learning_rate": 0.00015463790561848074,
1346
+ "loss": 0.3693,
1347
+ "step": 46500
1348
+ },
1349
+ {
1350
+ "epoch": 0.2737540166448298,
1351
+ "grad_norm": 6.019217014312744,
1352
+ "learning_rate": 0.00015432815211509395,
1353
+ "loss": 0.3674,
1354
+ "step": 46750
1355
+ },
1356
+ {
1357
+ "epoch": 0.2752179418675294,
1358
+ "grad_norm": 7.813283443450928,
1359
+ "learning_rate": 0.00015401715462173376,
1360
+ "loss": 0.3674,
1361
+ "step": 47000
1362
+ },
1363
+ {
1364
+ "epoch": 0.276681867090229,
1365
+ "grad_norm": 7.319979190826416,
1366
+ "learning_rate": 0.00015370615712837355,
1367
+ "loss": 0.3675,
1368
+ "step": 47250
1369
+ },
1370
+ {
1371
+ "epoch": 0.27814579231292863,
1372
+ "grad_norm": 8.74886703491211,
1373
+ "learning_rate": 0.00015339515963501334,
1374
+ "loss": 0.3633,
1375
+ "step": 47500
1376
+ },
1377
+ {
1378
+ "epoch": 0.2796097175356283,
1379
+ "grad_norm": 9.456360816955566,
1380
+ "learning_rate": 0.00015308416214165316,
1381
+ "loss": 0.379,
1382
+ "step": 47750
1383
+ },
1384
+ {
1385
+ "epoch": 0.2810736427583279,
1386
+ "grad_norm": 10.024221420288086,
1387
+ "learning_rate": 0.00015277316464829295,
1388
+ "loss": 0.375,
1389
+ "step": 48000
1390
+ },
1391
+ {
1392
+ "epoch": 0.2825375679810275,
1393
+ "grad_norm": 6.477073669433594,
1394
+ "learning_rate": 0.00015246216715493274,
1395
+ "loss": 0.3634,
1396
+ "step": 48250
1397
+ },
1398
+ {
1399
+ "epoch": 0.28400149320372714,
1400
+ "grad_norm": 8.587589263916016,
1401
+ "learning_rate": 0.00015215116966157255,
1402
+ "loss": 0.3693,
1403
+ "step": 48500
1404
+ },
1405
+ {
1406
+ "epoch": 0.28546541842642675,
1407
+ "grad_norm": 10.675822257995605,
1408
+ "learning_rate": 0.00015184017216821234,
1409
+ "loss": 0.3668,
1410
+ "step": 48750
1411
+ },
1412
+ {
1413
+ "epoch": 0.2869293436491264,
1414
+ "grad_norm": 10.77786636352539,
1415
+ "learning_rate": 0.00015153041866482558,
1416
+ "loss": 0.3711,
1417
+ "step": 49000
1418
+ },
1419
+ {
1420
+ "epoch": 0.28839326887182604,
1421
+ "grad_norm": 7.768797874450684,
1422
+ "learning_rate": 0.00015121942117146537,
1423
+ "loss": 0.3692,
1424
+ "step": 49250
1425
+ },
1426
+ {
1427
+ "epoch": 0.28985719409452565,
1428
+ "grad_norm": 6.11573600769043,
1429
+ "learning_rate": 0.00015090842367810516,
1430
+ "loss": 0.3618,
1431
+ "step": 49500
1432
+ },
1433
+ {
1434
+ "epoch": 0.29132111931722526,
1435
+ "grad_norm": 7.369346618652344,
1436
+ "learning_rate": 0.00015059742618474495,
1437
+ "loss": 0.365,
1438
+ "step": 49750
1439
+ },
1440
+ {
1441
+ "epoch": 0.2927850445399249,
1442
+ "grad_norm": 10.559876441955566,
1443
+ "learning_rate": 0.00015028642869138476,
1444
+ "loss": 0.369,
1445
+ "step": 50000
1446
+ },
1447
+ {
1448
+ "epoch": 0.29424896976262455,
1449
+ "grad_norm": 6.763681888580322,
1450
+ "learning_rate": 0.00014997543119802455,
1451
+ "loss": 0.3723,
1452
+ "step": 50250
1453
+ },
1454
+ {
1455
+ "epoch": 0.29571289498532416,
1456
+ "grad_norm": 14.075911521911621,
1457
+ "learning_rate": 0.00014966443370466434,
1458
+ "loss": 0.3656,
1459
+ "step": 50500
1460
+ },
1461
+ {
1462
+ "epoch": 0.2971768202080238,
1463
+ "grad_norm": 7.817617893218994,
1464
+ "learning_rate": 0.00014935343621130416,
1465
+ "loss": 0.3745,
1466
+ "step": 50750
1467
+ },
1468
+ {
1469
+ "epoch": 0.2986407454307234,
1470
+ "grad_norm": 5.018287181854248,
1471
+ "learning_rate": 0.00014904243871794395,
1472
+ "loss": 0.3664,
1473
+ "step": 51000
1474
+ },
1475
+ {
1476
+ "epoch": 0.300104670653423,
1477
+ "grad_norm": 9.846301078796387,
1478
+ "learning_rate": 0.00014873144122458373,
1479
+ "loss": 0.3644,
1480
+ "step": 51250
1481
+ },
1482
+ {
1483
+ "epoch": 0.30156859587612267,
1484
+ "grad_norm": 8.65786361694336,
1485
+ "learning_rate": 0.00014842044373122352,
1486
+ "loss": 0.3698,
1487
+ "step": 51500
1488
+ },
1489
+ {
1490
+ "epoch": 0.3030325210988223,
1491
+ "grad_norm": 6.303979873657227,
1492
+ "learning_rate": 0.00014810944623786334,
1493
+ "loss": 0.3707,
1494
+ "step": 51750
1495
+ },
1496
+ {
1497
+ "epoch": 0.3044964463215219,
1498
+ "grad_norm": 39.32520294189453,
1499
+ "learning_rate": 0.00014779844874450313,
1500
+ "loss": 0.3617,
1501
+ "step": 52000
1502
+ },
1503
+ {
1504
+ "epoch": 0.3059603715442215,
1505
+ "grad_norm": 6.535865306854248,
1506
+ "learning_rate": 0.00014748869524111637,
1507
+ "loss": 0.3642,
1508
+ "step": 52250
1509
+ },
1510
+ {
1511
+ "epoch": 0.3074242967669211,
1512
+ "grad_norm": 6.031300067901611,
1513
+ "learning_rate": 0.00014717769774775616,
1514
+ "loss": 0.363,
1515
+ "step": 52500
1516
+ },
1517
+ {
1518
+ "epoch": 0.3088882219896208,
1519
+ "grad_norm": 7.255093097686768,
1520
+ "learning_rate": 0.00014686670025439595,
1521
+ "loss": 0.3594,
1522
+ "step": 52750
1523
+ },
1524
+ {
1525
+ "epoch": 0.3103521472123204,
1526
+ "grad_norm": 7.491271018981934,
1527
+ "learning_rate": 0.00014655570276103576,
1528
+ "loss": 0.3697,
1529
+ "step": 53000
1530
+ },
1531
+ {
1532
+ "epoch": 0.31181607243502,
1533
+ "grad_norm": 8.154767036437988,
1534
+ "learning_rate": 0.00014624470526767555,
1535
+ "loss": 0.3667,
1536
+ "step": 53250
1537
+ },
1538
+ {
1539
+ "epoch": 0.31327999765771963,
1540
+ "grad_norm": 7.7836384773254395,
1541
+ "learning_rate": 0.00014593370777431534,
1542
+ "loss": 0.3756,
1543
+ "step": 53500
1544
+ },
1545
+ {
1546
+ "epoch": 0.31474392288041925,
1547
+ "grad_norm": 7.439420223236084,
1548
+ "learning_rate": 0.00014562271028095513,
1549
+ "loss": 0.3734,
1550
+ "step": 53750
1551
+ },
1552
+ {
1553
+ "epoch": 0.3162078481031189,
1554
+ "grad_norm": 7.654810428619385,
1555
+ "learning_rate": 0.00014531171278759494,
1556
+ "loss": 0.3689,
1557
+ "step": 54000
1558
+ },
1559
+ {
1560
+ "epoch": 0.31767177332581853,
1561
+ "grad_norm": 4.918389320373535,
1562
+ "learning_rate": 0.00014500195928420816,
1563
+ "loss": 0.3688,
1564
+ "step": 54250
1565
+ },
1566
+ {
1567
+ "epoch": 0.31913569854851814,
1568
+ "grad_norm": 6.2310895919799805,
1569
+ "learning_rate": 0.00014469096179084797,
1570
+ "loss": 0.3711,
1571
+ "step": 54500
1572
+ },
1573
+ {
1574
+ "epoch": 0.32059962377121776,
1575
+ "grad_norm": 7.458713054656982,
1576
+ "learning_rate": 0.00014437996429748776,
1577
+ "loss": 0.3614,
1578
+ "step": 54750
1579
+ },
1580
+ {
1581
+ "epoch": 0.32206354899391737,
1582
+ "grad_norm": 6.790125370025635,
1583
+ "learning_rate": 0.00014406896680412755,
1584
+ "loss": 0.3635,
1585
+ "step": 55000
1586
+ },
1587
+ {
1588
+ "epoch": 0.32206354899391737,
1589
+ "eval_accuracy": 0.8905084935576763,
1590
+ "eval_loss": 0.362331748008728,
1591
+ "eval_runtime": 11551.2138,
1592
+ "eval_samples_per_second": 210.262,
1593
+ "eval_steps_per_second": 6.571,
1594
+ "step": 55000
1595
  }
1596
  ],
1597
  "logging_steps": 250,
1598
+ "max_steps": 170773,
1599
  "num_input_tokens_seen": 0,
1600
  "num_train_epochs": 1,
1601
+ "save_steps": 55000,
1602
  "stateful_callbacks": {
1603
  "TrainerControl": {
1604
  "args": {
 
1611
  "attributes": {}
1612
  }
1613
  },
1614
+ "total_flos": 1.4252945436741468e+19,
1615
  "train_batch_size": 8,
1616
  "trial_name": null,
1617
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b372e5851cc47aa9329b7a66ec8513f97b45313a34745bdcd97dbb6b7cc5d
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ab149dc9de59a03b51e35c756efbb0c41468f20a9ae957e4c4f7f49a5059ed
3
  size 5304