seblaku commited on
Commit
b8abcc1
·
verified ·
1 Parent(s): e93b72e

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:129b3e52b478d7e24c5887447357af790dacfe440b7044a8ae3023a7394eb821
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bad89d55fb28d55d7d9cd158ba466f31c4a25f392871322055e15be9b574d5
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aff48842137bd019dc375504a3b176e44c76e810786e0690a98b9820a356cf67
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32c901e733a1a3fc1e09d95b045aa50f7e3ec3a528f1d35da0728881ecbb676
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dc38f07ddd17799abc0a9143cd94c582c7e4c541315bb39a28bb7952c94f7a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76e04f17b1b515e0d6d0d83fb285dc16fd1c4b8c423217ecf1723b55152fac7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2481782945fd527fd68f03d6ecc086ae38c0c705bfbe5de3172ab751f2e6c8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6405f9fabb3d2e45adcc13758e2849ef278b423e1ee939354d45ffa4e9327204
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6937828063964844,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9569377990430622,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -731,6 +731,364 @@
731
  "eval_samples_per_second": 30.551,
732
  "eval_steps_per_second": 7.767,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.78948348952576e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6925917863845825,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.4354066985645932,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
731
  "eval_samples_per_second": 30.551,
732
  "eval_steps_per_second": 7.767,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.9665071770334929,
737
+ "grad_norm": 1.0401110649108887,
738
+ "learning_rate": 4.264362337302798e-05,
739
+ "loss": 1.9696,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.9760765550239234,
744
+ "grad_norm": 1.2967274188995361,
745
+ "learning_rate": 4.1983350186928894e-05,
746
+ "loss": 2.0238,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.9856459330143541,
751
+ "grad_norm": 1.6171687841415405,
752
+ "learning_rate": 4.132253477269233e-05,
753
+ "loss": 1.7819,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9952153110047847,
758
+ "grad_norm": 2.1571907997131348,
759
+ "learning_rate": 4.0661357790654345e-05,
760
+ "loss": 1.4887,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.0047846889952152,
765
+ "grad_norm": 0.6212150454521179,
766
+ "learning_rate": 4e-05,
767
+ "loss": 2.2897,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.014354066985646,
772
+ "grad_norm": 0.2727871239185333,
773
+ "learning_rate": 3.933864220934566e-05,
774
+ "loss": 1.3308,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.0239234449760766,
779
+ "grad_norm": 0.3046855330467224,
780
+ "learning_rate": 3.8677465227307676e-05,
781
+ "loss": 1.4615,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.0334928229665072,
786
+ "grad_norm": 0.31469711661338806,
787
+ "learning_rate": 3.8016649813071106e-05,
788
+ "loss": 1.3841,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.0430622009569377,
793
+ "grad_norm": 0.32190945744514465,
794
+ "learning_rate": 3.735637662697203e-05,
795
+ "loss": 1.3789,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.0526315789473684,
800
+ "grad_norm": 0.3380140960216522,
801
+ "learning_rate": 3.669682618110671e-05,
802
+ "loss": 1.437,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.062200956937799,
807
+ "grad_norm": 0.3436225652694702,
808
+ "learning_rate": 3.6038178789981494e-05,
809
+ "loss": 1.2847,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.0717703349282297,
814
+ "grad_norm": 0.36676591634750366,
815
+ "learning_rate": 3.538061452121656e-05,
816
+ "loss": 1.297,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.0813397129186604,
821
+ "grad_norm": 0.39319589734077454,
822
+ "learning_rate": 3.472431314631724e-05,
823
+ "loss": 1.489,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.0909090909090908,
828
+ "grad_norm": 0.38813480734825134,
829
+ "learning_rate": 3.406945409152632e-05,
830
+ "loss": 1.4377,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.1004784688995215,
835
+ "grad_norm": 0.41558539867401123,
836
+ "learning_rate": 3.341621638877064e-05,
837
+ "loss": 1.4287,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.1100478468899522,
842
+ "grad_norm": 0.40909650921821594,
843
+ "learning_rate": 3.276477862671562e-05,
844
+ "loss": 1.441,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.1196172248803828,
849
+ "grad_norm": 0.45959237217903137,
850
+ "learning_rate": 3.21153189019408e-05,
851
+ "loss": 1.6774,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1291866028708135,
856
+ "grad_norm": 0.46516451239585876,
857
+ "learning_rate": 3.146801477025013e-05,
858
+ "loss": 1.4372,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.138755980861244,
863
+ "grad_norm": 0.5069877505302429,
864
+ "learning_rate": 3.082304319812994e-05,
865
+ "loss": 1.642,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.1483253588516746,
870
+ "grad_norm": 0.5341264009475708,
871
+ "learning_rate": 3.0180580514368037e-05,
872
+ "loss": 1.6585,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.1578947368421053,
877
+ "grad_norm": 0.56055748462677,
878
+ "learning_rate": 2.9540802361847212e-05,
879
+ "loss": 1.6557,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.167464114832536,
884
+ "grad_norm": 0.5781103372573853,
885
+ "learning_rate": 2.890388364952623e-05,
886
+ "loss": 1.6671,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.1770334928229664,
891
+ "grad_norm": 0.6097198724746704,
892
+ "learning_rate": 2.8269998504621416e-05,
893
+ "loss": 1.6451,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.186602870813397,
898
+ "grad_norm": 0.6518456339836121,
899
+ "learning_rate": 2.7639320225002108e-05,
900
+ "loss": 1.6557,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.1961722488038278,
905
+ "grad_norm": 0.6572650671005249,
906
+ "learning_rate": 2.7012021231812666e-05,
907
+ "loss": 1.4739,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.2057416267942584,
912
+ "grad_norm": 0.783046543598175,
913
+ "learning_rate": 2.638827302233428e-05,
914
+ "loss": 1.8914,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.215311004784689,
919
+ "grad_norm": 0.808749794960022,
920
+ "learning_rate": 2.576824612309934e-05,
921
+ "loss": 1.6836,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.2248803827751196,
926
+ "grad_norm": 0.9802379012107849,
927
+ "learning_rate": 2.5152110043271166e-05,
928
+ "loss": 1.6596,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.2344497607655502,
933
+ "grad_norm": 1.2099603414535522,
934
+ "learning_rate": 2.454003322830192e-05,
935
+ "loss": 1.5137,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.244019138755981,
940
+ "grad_norm": 1.4862251281738281,
941
+ "learning_rate": 2.393218301388123e-05,
942
+ "loss": 1.1418,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.2535885167464116,
947
+ "grad_norm": 1.0337613821029663,
948
+ "learning_rate": 2.3328725580188395e-05,
949
+ "loss": 1.2111,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.263157894736842,
954
+ "grad_norm": 0.33979716897010803,
955
+ "learning_rate": 2.272982590646029e-05,
956
+ "loss": 1.4224,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.2727272727272727,
961
+ "grad_norm": 0.37942126393318176,
962
+ "learning_rate": 2.2135647725887744e-05,
963
+ "loss": 1.4692,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.2822966507177034,
968
+ "grad_norm": 0.3820892572402954,
969
+ "learning_rate": 2.1546353480852495e-05,
970
+ "loss": 1.3997,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.291866028708134,
975
+ "grad_norm": 0.37589502334594727,
976
+ "learning_rate": 2.096210427851706e-05,
977
+ "loss": 1.44,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.3014354066985647,
982
+ "grad_norm": 0.39906907081604004,
983
+ "learning_rate": 2.038305984677969e-05,
984
+ "loss": 1.4383,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.3110047846889952,
989
+ "grad_norm": 0.3934566378593445,
990
+ "learning_rate": 1.9809378490606264e-05,
991
+ "loss": 1.3633,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.3205741626794258,
996
+ "grad_norm": 0.4008135497570038,
997
+ "learning_rate": 1.9241217048751406e-05,
998
+ "loss": 1.4147,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.3301435406698565,
1003
+ "grad_norm": 0.4096076488494873,
1004
+ "learning_rate": 1.867873085088026e-05,
1005
+ "loss": 1.3079,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.339712918660287,
1010
+ "grad_norm": 0.4406437873840332,
1011
+ "learning_rate": 1.8122073675102935e-05,
1012
+ "loss": 1.4559,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.3492822966507176,
1017
+ "grad_norm": 0.42370909452438354,
1018
+ "learning_rate": 1.75713977059331e-05,
1019
+ "loss": 1.3705,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.3588516746411483,
1024
+ "grad_norm": 0.4583252966403961,
1025
+ "learning_rate": 1.702685349268226e-05,
1026
+ "loss": 1.4909,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.368421052631579,
1031
+ "grad_norm": 0.44213107228279114,
1032
+ "learning_rate": 1.648858990830108e-05,
1033
+ "loss": 1.3054,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.3779904306220097,
1038
+ "grad_norm": 0.46722662448883057,
1039
+ "learning_rate": 1.5956754108678996e-05,
1040
+ "loss": 1.443,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.38755980861244,
1045
+ "grad_norm": 0.48926499485969543,
1046
+ "learning_rate": 1.5431491492413288e-05,
1047
+ "loss": 1.4217,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.3971291866028708,
1052
+ "grad_norm": 0.5186731219291687,
1053
+ "learning_rate": 1.491294566105852e-05,
1054
+ "loss": 1.567,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.4066985645933014,
1059
+ "grad_norm": 0.5692178010940552,
1060
+ "learning_rate": 1.4401258379867335e-05,
1061
+ "loss": 1.6171,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.4162679425837321,
1066
+ "grad_norm": 0.5609941482543945,
1067
+ "learning_rate": 1.3896569539033253e-05,
1068
+ "loss": 1.5476,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.4258373205741628,
1073
+ "grad_norm": 0.6115127801895142,
1074
+ "learning_rate": 1.3399017115446067e-05,
1075
+ "loss": 1.5292,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.4354066985645932,
1080
+ "grad_norm": 0.6445640325546265,
1081
+ "learning_rate": 1.2908737134970367e-05,
1082
+ "loss": 1.6103,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.4354066985645932,
1087
+ "eval_loss": 1.6925917863845825,
1088
+ "eval_runtime": 5.7417,
1089
+ "eval_samples_per_second": 30.827,
1090
+ "eval_steps_per_second": 7.837,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.177421616021504e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null