lesso04 commited on
Commit
26f634f
·
verified ·
1 Parent(s): 8cd9c90

Training in progress, step 100, 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:d92fef256f0ccb44632f028174b79c4315aa97622865b0e73b1b8abfecdb548c
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638c5572eb628bd4bf871d03cc3300c61230a0475c060578bec70c69dc72a3a9
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:511d94acc69926051e08f559753504805cfefd1cfb406179bff346ea4a5c7f00
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b65ec0ed9ad56733f57ed5986c36e9f804ebe182dc1709834335e42297f0a9
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c56631f999197208b15fc6f972734a62266efd1a3eb9ca3e6ed3b0125411c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98b95fe5d318df2cb4b3adbf31158694d511584491e88097c6284b36b77ac9a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
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": 0.0021892057561516682,
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,
@@ -604,6 +604,205 @@
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 2.0434,
606
  "step": 75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
607
  }
608
  ],
609
  "logging_steps": 1,
@@ -618,12 +817,12 @@
618
  "should_evaluate": false,
619
  "should_log": false,
620
  "should_save": true,
621
- "should_training_stop": false
622
  },
623
  "attributes": {}
624
  }
625
  },
626
- "total_flos": 1.1108631969792e+17,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002918941008202224,
5
  "eval_steps": 9,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
604
  "learning_rate": 1.7860619515673033e-05,
605
  "loss": 2.0434,
606
  "step": 75
607
+ },
608
+ {
609
+ "epoch": 0.0022183951662336906,
610
+ "grad_norm": 5.061326503753662,
611
+ "learning_rate": 1.6543469682057106e-05,
612
+ "loss": 2.2139,
613
+ "step": 76
614
+ },
615
+ {
616
+ "epoch": 0.0022475845763157126,
617
+ "grad_norm": 4.171151638031006,
618
+ "learning_rate": 1.526708147705013e-05,
619
+ "loss": 2.5195,
620
+ "step": 77
621
+ },
622
+ {
623
+ "epoch": 0.002276773986397735,
624
+ "grad_norm": 4.396327972412109,
625
+ "learning_rate": 1.4033009983067452e-05,
626
+ "loss": 1.9265,
627
+ "step": 78
628
+ },
629
+ {
630
+ "epoch": 0.0023059633964797573,
631
+ "grad_norm": 4.16161584854126,
632
+ "learning_rate": 1.2842758726130283e-05,
633
+ "loss": 2.0707,
634
+ "step": 79
635
+ },
636
+ {
637
+ "epoch": 0.0023351528065617792,
638
+ "grad_norm": 4.6011834144592285,
639
+ "learning_rate": 1.1697777844051105e-05,
640
+ "loss": 2.2528,
641
+ "step": 80
642
+ },
643
+ {
644
+ "epoch": 0.0023643422166438016,
645
+ "grad_norm": 3.9297537803649902,
646
+ "learning_rate": 1.0599462319663905e-05,
647
+ "loss": 2.0247,
648
+ "step": 81
649
+ },
650
+ {
651
+ "epoch": 0.0023643422166438016,
652
+ "eval_loss": 1.1290487051010132,
653
+ "eval_runtime": 5167.8842,
654
+ "eval_samples_per_second": 5.583,
655
+ "eval_steps_per_second": 0.698,
656
+ "step": 81
657
+ },
658
+ {
659
+ "epoch": 0.002393531626725824,
660
+ "grad_norm": 5.19559907913208,
661
+ "learning_rate": 9.549150281252633e-06,
662
+ "loss": 2.6874,
663
+ "step": 82
664
+ },
665
+ {
666
+ "epoch": 0.002422721036807846,
667
+ "grad_norm": 3.3443710803985596,
668
+ "learning_rate": 8.548121372247918e-06,
669
+ "loss": 1.908,
670
+ "step": 83
671
+ },
672
+ {
673
+ "epoch": 0.0024519104468898683,
674
+ "grad_norm": 4.5716872215271,
675
+ "learning_rate": 7.597595192178702e-06,
676
+ "loss": 2.3403,
677
+ "step": 84
678
+ },
679
+ {
680
+ "epoch": 0.0024810998569718907,
681
+ "grad_norm": 5.666961669921875,
682
+ "learning_rate": 6.698729810778065e-06,
683
+ "loss": 1.8948,
684
+ "step": 85
685
+ },
686
+ {
687
+ "epoch": 0.002510289267053913,
688
+ "grad_norm": 3.6606452465057373,
689
+ "learning_rate": 5.852620357053651e-06,
690
+ "loss": 1.7972,
691
+ "step": 86
692
+ },
693
+ {
694
+ "epoch": 0.002539478677135935,
695
+ "grad_norm": 3.9051780700683594,
696
+ "learning_rate": 5.060297685041659e-06,
697
+ "loss": 2.2984,
698
+ "step": 87
699
+ },
700
+ {
701
+ "epoch": 0.0025686680872179573,
702
+ "grad_norm": 3.8334949016571045,
703
+ "learning_rate": 4.322727117869951e-06,
704
+ "loss": 1.8084,
705
+ "step": 88
706
+ },
707
+ {
708
+ "epoch": 0.0025978574972999797,
709
+ "grad_norm": 3.7805323600769043,
710
+ "learning_rate": 3.6408072716606346e-06,
711
+ "loss": 1.8582,
712
+ "step": 89
713
+ },
714
+ {
715
+ "epoch": 0.0026270469073820016,
716
+ "grad_norm": 4.389084815979004,
717
+ "learning_rate": 3.0153689607045845e-06,
718
+ "loss": 2.6724,
719
+ "step": 90
720
+ },
721
+ {
722
+ "epoch": 0.0026270469073820016,
723
+ "eval_loss": 1.1242789030075073,
724
+ "eval_runtime": 5177.0735,
725
+ "eval_samples_per_second": 5.573,
726
+ "eval_steps_per_second": 0.697,
727
+ "step": 90
728
+ },
729
+ {
730
+ "epoch": 0.002656236317464024,
731
+ "grad_norm": 3.7023391723632812,
732
+ "learning_rate": 2.4471741852423237e-06,
733
+ "loss": 2.2794,
734
+ "step": 91
735
+ },
736
+ {
737
+ "epoch": 0.0026854257275460464,
738
+ "grad_norm": 4.1875224113464355,
739
+ "learning_rate": 1.9369152030840556e-06,
740
+ "loss": 2.2988,
741
+ "step": 92
742
+ },
743
+ {
744
+ "epoch": 0.0027146151376280687,
745
+ "grad_norm": 3.8059375286102295,
746
+ "learning_rate": 1.4852136862001764e-06,
747
+ "loss": 2.0377,
748
+ "step": 93
749
+ },
750
+ {
751
+ "epoch": 0.0027438045477100907,
752
+ "grad_norm": 3.355520009994507,
753
+ "learning_rate": 1.0926199633097157e-06,
754
+ "loss": 1.7596,
755
+ "step": 94
756
+ },
757
+ {
758
+ "epoch": 0.002772993957792113,
759
+ "grad_norm": 3.7353641986846924,
760
+ "learning_rate": 7.596123493895991e-07,
761
+ "loss": 2.2464,
762
+ "step": 95
763
+ },
764
+ {
765
+ "epoch": 0.0028021833678741354,
766
+ "grad_norm": 4.7744011878967285,
767
+ "learning_rate": 4.865965629214819e-07,
768
+ "loss": 2.2035,
769
+ "step": 96
770
+ },
771
+ {
772
+ "epoch": 0.0028313727779561574,
773
+ "grad_norm": 4.310746669769287,
774
+ "learning_rate": 2.7390523158633554e-07,
775
+ "loss": 2.7079,
776
+ "step": 97
777
+ },
778
+ {
779
+ "epoch": 0.0028605621880381797,
780
+ "grad_norm": 4.090019702911377,
781
+ "learning_rate": 1.2179748700879012e-07,
782
+ "loss": 1.9389,
783
+ "step": 98
784
+ },
785
+ {
786
+ "epoch": 0.002889751598120202,
787
+ "grad_norm": 3.6498568058013916,
788
+ "learning_rate": 3.04586490452119e-08,
789
+ "loss": 1.9602,
790
+ "step": 99
791
+ },
792
+ {
793
+ "epoch": 0.002889751598120202,
794
+ "eval_loss": 1.12322998046875,
795
+ "eval_runtime": 5172.741,
796
+ "eval_samples_per_second": 5.577,
797
+ "eval_steps_per_second": 0.697,
798
+ "step": 99
799
+ },
800
+ {
801
+ "epoch": 0.002918941008202224,
802
+ "grad_norm": 3.8397557735443115,
803
+ "learning_rate": 0.0,
804
+ "loss": 1.8497,
805
+ "step": 100
806
  }
807
  ],
808
  "logging_steps": 1,
 
817
  "should_evaluate": false,
818
  "should_log": false,
819
  "should_save": true,
820
+ "should_training_stop": true
821
  },
822
  "attributes": {}
823
  }
824
  },
825
+ "total_flos": 1.485382789103616e+17,
826
  "train_batch_size": 8,
827
  "trial_name": null,
828
  "trial_params": null