aleegis11 commited on
Commit
d6b344b
·
verified ·
1 Parent(s): a7e9f33

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:e6e497ed7b748a2c2d831b7ceea1ba9fbf645ad9c119f46f66af4cb4a7435847
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352170402d722fe61612011ed3297e6a1528a67e55890a956dc67a41f7e0b900
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bd18a84bd78db49ff0f1cc456b22daaa6ab2501fc7c3d85d12797243fe35ccc
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2f446efbaa8a0fd8aef5ed8880ec24bd6247ad6e020c69769b0862b26756af
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f538e6bfc63454df55e972f81e639c32fe9c65e0f107036d7c2df1fb79cf6d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973760da6dbdc4a4f531a4c29c09bcac9719bb7b8a0ae028144609a80c36eff1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.4882469177246094,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9501187648456056,
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": 81.54,
732
  "eval_steps_per_second": 20.614,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7693382549766144.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.4354910850524902,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.4251781472684084,
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": 81.54,
732
  "eval_steps_per_second": 20.614,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.9596199524940617,
737
+ "grad_norm": 60.58907699584961,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 10.7966,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.9691211401425178,
744
+ "grad_norm": 72.10790252685547,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.0507,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.9786223277909739,
751
+ "grad_norm": 81.67748260498047,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.0962,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9881235154394299,
758
+ "grad_norm": 96.13243865966797,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 10.8405,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.997624703087886,
765
+ "grad_norm": 45.95366287231445,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.4617,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.007125890736342,
772
+ "grad_norm": 74.89264678955078,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 10.7786,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.0166270783847982,
779
+ "grad_norm": 34.36727523803711,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 10.6115,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.0261282660332542,
786
+ "grad_norm": 34.2283935546875,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 9.8407,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.03562945368171,
793
+ "grad_norm": 33.08857345581055,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 9.727,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.0451306413301662,
800
+ "grad_norm": 36.63699722290039,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 10.1565,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.0546318289786223,
807
+ "grad_norm": 39.32516098022461,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 10.0876,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.0641330166270784,
814
+ "grad_norm": 51.5899658203125,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 9.2029,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.0736342042755345,
821
+ "grad_norm": 43.274932861328125,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 9.0035,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.0831353919239906,
828
+ "grad_norm": 42.604061126708984,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 9.1692,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.0926365795724466,
835
+ "grad_norm": 41.310462951660156,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 9.1696,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.1021377672209025,
842
+ "grad_norm": 43.11902618408203,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 9.2453,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.1116389548693586,
849
+ "grad_norm": 39.28797912597656,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.2359,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1211401425178147,
856
+ "grad_norm": 39.07838439941406,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 8.8084,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.1306413301662708,
863
+ "grad_norm": 42.56367111206055,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 8.8215,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.1401425178147269,
870
+ "grad_norm": 52.60874938964844,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.3862,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.149643705463183,
877
+ "grad_norm": 59.03802490234375,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 10.0051,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.159144893111639,
884
+ "grad_norm": 53.51556396484375,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 9.7166,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.168646080760095,
891
+ "grad_norm": 61.38289260864258,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 9.8521,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.178147268408551,
898
+ "grad_norm": 59.38209533691406,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 9.8615,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.187648456057007,
905
+ "grad_norm": 69.93914031982422,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 10.217,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.1971496437054632,
912
+ "grad_norm": 53.72102737426758,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 10.1848,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.2066508313539193,
919
+ "grad_norm": 54.664764404296875,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 10.483,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.2161520190023754,
926
+ "grad_norm": 60.76587677001953,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 10.0884,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.2256532066508314,
933
+ "grad_norm": 67.71343994140625,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 10.7442,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.2351543942992875,
940
+ "grad_norm": 69.5775375366211,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.2854,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.2446555819477434,
947
+ "grad_norm": 88.2365951538086,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 10.9993,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.2541567695961995,
954
+ "grad_norm": 40.71464538574219,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 10.1865,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.2636579572446556,
961
+ "grad_norm": 27.133167266845703,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 10.0801,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.2731591448931117,
968
+ "grad_norm": 27.42853355407715,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.7753,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.2826603325415677,
975
+ "grad_norm": 29.747236251831055,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 9.9648,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.2921615201900236,
982
+ "grad_norm": 28.10453224182129,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.6276,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.3016627078384797,
989
+ "grad_norm": 32.8948860168457,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 9.6534,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.3111638954869358,
996
+ "grad_norm": 36.85212707519531,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.1545,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.3206650831353919,
1003
+ "grad_norm": 42.10161590576172,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 8.7032,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.330166270783848,
1010
+ "grad_norm": 33.20311737060547,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.1932,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.339667458432304,
1017
+ "grad_norm": 40.20091247558594,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 8.9803,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.3491686460807601,
1024
+ "grad_norm": 52.291587829589844,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.1159,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.3586698337292162,
1031
+ "grad_norm": 43.315677642822266,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.0998,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.3681710213776723,
1038
+ "grad_norm": 33.63870620727539,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 8.7301,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.3776722090261282,
1045
+ "grad_norm": 43.19037628173828,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.222,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.3871733966745843,
1052
+ "grad_norm": 49.447837829589844,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 9.0844,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.3966745843230404,
1059
+ "grad_norm": 52.0371208190918,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 10.1305,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.4061757719714965,
1066
+ "grad_norm": 40.418521881103516,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.1222,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.4156769596199525,
1073
+ "grad_norm": 56.46171188354492,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.7529,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.4251781472684084,
1080
+ "grad_norm": 39.67538833618164,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.8505,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.4251781472684084,
1087
+ "eval_loss": 2.4354910850524902,
1088
+ "eval_runtime": 2.1805,
1089
+ "eval_samples_per_second": 81.632,
1090
+ "eval_steps_per_second": 20.637,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1540073824649216e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null