arcwarden46 commited on
Commit
68506e9
·
verified ·
1 Parent(s): 13e9a67

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 sha256:4ab1fb74c1a072631df8fab6b5cf607c99d22804f04432d50e4c2f36471f0e11
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624ac9978d14c5ce04acf072ffb67bf490fd657640ae30d5988d112c2d9690ec
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3da34e137448eb15eb6405d323a74d2814ebc7ea1f26c70c2cdb681c68865f16
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d8686460d134f40cc41d930518290b3a9f71e0e9fe705fe264f51f1cbec099
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9477fa0e4be4cf50bb75d29e2e86e534c2df5a3cfd904bd36cd74856e9a18ba
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe219f32f5e7052b1967f488ab8ab0774f62ec5954f28d52ad467cc1799534da
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": 0.32512158155441284,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.7130124777183601,
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": 13.114,
732
  "eval_steps_per_second": 3.278,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.11750635504722595,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.0695187165775402,
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": 13.114,
732
  "eval_steps_per_second": 3.278,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.7201426024955436,
737
+ "grad_norm": 4.077305316925049,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.2662,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.7272727272727273,
744
+ "grad_norm": 4.493444919586182,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.2757,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.7344028520499108,
751
+ "grad_norm": 1.2807857990264893,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.1086,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.7415329768270945,
758
+ "grad_norm": 1.7022565603256226,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2093,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.7486631016042781,
765
+ "grad_norm": 3.4729650020599365,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.4945,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.7557932263814616,
772
+ "grad_norm": 9.623605728149414,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8191,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7629233511586453,
779
+ "grad_norm": 6.82785177230835,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.6385,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7700534759358288,
786
+ "grad_norm": 3.6015989780426025,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.509,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7771836007130125,
793
+ "grad_norm": 4.353756904602051,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4556,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7843137254901961,
800
+ "grad_norm": 4.157517433166504,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3514,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7914438502673797,
807
+ "grad_norm": 1.487565040588379,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2651,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7985739750445633,
814
+ "grad_norm": 1.8361451625823975,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.214,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.8057040998217468,
821
+ "grad_norm": 2.8729050159454346,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.1751,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.8128342245989305,
828
+ "grad_norm": 2.9342260360717773,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.1975,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.8199643493761141,
835
+ "grad_norm": 1.1883810758590698,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.1764,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.8270944741532977,
842
+ "grad_norm": 2.3309926986694336,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2418,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.8342245989304813,
849
+ "grad_norm": 2.0552427768707275,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.1506,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.8413547237076648,
856
+ "grad_norm": 1.2462787628173828,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.1211,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.8484848484848485,
863
+ "grad_norm": 1.4371592998504639,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2315,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.8556149732620321,
870
+ "grad_norm": 1.6682649850845337,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.211,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8627450980392157,
877
+ "grad_norm": 2.4928805828094482,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.1682,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.8698752228163993,
884
+ "grad_norm": 1.7620739936828613,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.1171,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8770053475935828,
891
+ "grad_norm": 1.4409494400024414,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.2122,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.8841354723707665,
898
+ "grad_norm": 3.6312010288238525,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.1687,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8912655971479501,
905
+ "grad_norm": 1.3037965297698975,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.1059,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8983957219251337,
912
+ "grad_norm": 1.5927499532699585,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.1325,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.9055258467023173,
919
+ "grad_norm": 1.1492993831634521,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0601,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.9126559714795008,
926
+ "grad_norm": 1.1006429195404053,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.1772,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.9197860962566845,
933
+ "grad_norm": 2.085655927658081,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1353,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.9269162210338681,
940
+ "grad_norm": 3.305060625076294,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.2093,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.9340463458110517,
947
+ "grad_norm": 1.5962597131729126,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.1222,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.9411764705882353,
954
+ "grad_norm": 1.1807433366775513,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.1408,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.948306595365419,
961
+ "grad_norm": 1.820581316947937,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2907,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.9554367201426025,
968
+ "grad_norm": 2.320713758468628,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.1864,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.9625668449197861,
975
+ "grad_norm": 2.3209404945373535,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.3219,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.9696969696969697,
982
+ "grad_norm": 2.7532081604003906,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3793,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.9768270944741533,
989
+ "grad_norm": 1.9822131395339966,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.1778,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.983957219251337,
996
+ "grad_norm": 1.895337700843811,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.2372,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9910873440285205,
1003
+ "grad_norm": 1.6673623323440552,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.1409,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9982174688057041,
1010
+ "grad_norm": 2.0436630249023438,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3324,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.0053475935828877,
1017
+ "grad_norm": 5.202945232391357,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.6321,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.0124777183600713,
1024
+ "grad_norm": 1.9828206300735474,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.2057,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.0196078431372548,
1031
+ "grad_norm": 1.4824261665344238,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2002,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.0267379679144386,
1038
+ "grad_norm": 1.8293224573135376,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2948,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.0338680926916222,
1045
+ "grad_norm": 1.3274524211883545,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2465,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.0409982174688057,
1052
+ "grad_norm": 2.0107944011688232,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3174,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.0481283422459893,
1059
+ "grad_norm": 2.3455100059509277,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2253,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.0552584670231728,
1066
+ "grad_norm": 2.172856569290161,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.1358,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.0623885918003566,
1073
+ "grad_norm": 1.3267221450805664,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0817,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.0695187165775402,
1080
+ "grad_norm": 0.9412680268287659,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0696,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.0695187165775402,
1087
+ "eval_loss": 0.11750635504722595,
1088
+ "eval_runtime": 17.9532,
1089
+ "eval_samples_per_second": 13.145,
1090
+ "eval_steps_per_second": 3.286,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2608847261453517e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null