ancient41 commited on
Commit
b2a2ac9
·
verified ·
1 Parent(s): 1284183

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 sha256:3b1fce025ae40bb48be118a6a39b91b92208e6d8dedbd7ca73ba38e4978f186d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9123b84056f479a3b4c365896e2d5d429ea67a51cc82096e22e49c8c78f4b5
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a212b7a35f4a8a122b23920eb3ab6bd0d3c279c6b159c1e3c4a4853fc66e368
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c2ba11a11205954406630b7649453fa6002c8012ba4c810921dd5b88b6c6ac
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fcbb89cff8d545d232a39a627552ae588bc38721303ea3f075e44656e3bbf36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818435ae6ff2143433f350712d14b85dfe9acd23933adb08dfb99ad159fe688a
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": 0.35311567783355713,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.061330880098129405,
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": 12.45,
732
  "eval_steps_per_second": 3.115,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5877105416300134e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.34416279196739197,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09199632014719411,
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": 12.45,
732
  "eval_steps_per_second": 3.115,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0619441888991107,
737
+ "grad_norm": 0.14297135174274445,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.186,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.062557497700092,
744
+ "grad_norm": 0.16984869539737701,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.2433,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06317080650107329,
751
+ "grad_norm": 0.18036068975925446,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2517,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06378411530205458,
758
+ "grad_norm": 0.203562930226326,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.3014,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06439742410303588,
765
+ "grad_norm": 0.21880516409873962,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.3114,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06501073290401717,
772
+ "grad_norm": 0.19703908264636993,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.2727,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06562404170499847,
779
+ "grad_norm": 0.20121800899505615,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3128,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06623735050597976,
786
+ "grad_norm": 0.22021602094173431,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2977,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06685065930696106,
793
+ "grad_norm": 0.21838457882404327,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3013,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06746396810794235,
800
+ "grad_norm": 0.2020447850227356,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3006,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06807727690892364,
807
+ "grad_norm": 0.22435148060321808,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.3614,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06869058570990494,
814
+ "grad_norm": 0.21225163340568542,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.3358,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06930389451088623,
821
+ "grad_norm": 0.22227871417999268,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3429,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06991720331186753,
828
+ "grad_norm": 0.2170470952987671,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.3194,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07053051211284882,
835
+ "grad_norm": 0.24869808554649353,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3856,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07114382091383012,
842
+ "grad_norm": 0.2273949682712555,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.3327,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07175712971481141,
849
+ "grad_norm": 0.24974454939365387,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.3648,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0723704385157927,
856
+ "grad_norm": 0.2473083883523941,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.361,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.072983747316774,
863
+ "grad_norm": 0.2563985586166382,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3799,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07359705611775529,
870
+ "grad_norm": 0.2372652292251587,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3455,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07421036491873659,
877
+ "grad_norm": 0.25966471433639526,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3722,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07482367371971788,
884
+ "grad_norm": 0.27156397700309753,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3817,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07543698252069918,
891
+ "grad_norm": 0.25948086380958557,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3441,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07605029132168047,
898
+ "grad_norm": 0.25913044810295105,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.3715,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07666360012266175,
905
+ "grad_norm": 0.2692747414112091,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.36,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07727690892364306,
912
+ "grad_norm": 0.26968130469322205,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3845,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07789021772462434,
919
+ "grad_norm": 0.27973347902297974,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3591,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07850352652560565,
926
+ "grad_norm": 0.2643369138240814,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.3567,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07911683532658693,
933
+ "grad_norm": 0.27118900418281555,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.3541,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07973014412756824,
940
+ "grad_norm": 0.2777666449546814,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3584,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08034345292854952,
947
+ "grad_norm": 0.28747764229774475,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.3621,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08095676172953081,
954
+ "grad_norm": 0.2967444956302643,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3819,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08157007053051211,
961
+ "grad_norm": 0.2715611159801483,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.3645,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0821833793314934,
968
+ "grad_norm": 0.2922961711883545,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.4103,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0827966881324747,
975
+ "grad_norm": 0.2891833484172821,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.3837,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.083409996933456,
982
+ "grad_norm": 0.3045870363712311,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3726,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0840233057344373,
989
+ "grad_norm": 0.3037290871143341,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.3861,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08463661453541858,
996
+ "grad_norm": 0.3093765079975128,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3951,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08524992333639987,
1003
+ "grad_norm": 0.32258591055870056,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.403,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.08586323213738117,
1010
+ "grad_norm": 0.3109833300113678,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3595,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08647654093836246,
1017
+ "grad_norm": 0.31597959995269775,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4016,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.08708984973934376,
1024
+ "grad_norm": 0.3226120173931122,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3938,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08770315854032505,
1031
+ "grad_norm": 0.33344128727912903,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3938,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08831646734130635,
1038
+ "grad_norm": 0.3264431059360504,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3881,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08892977614228764,
1045
+ "grad_norm": 0.35919469594955444,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3961,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08954308494326893,
1052
+ "grad_norm": 0.3426930010318756,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3803,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09015639374425023,
1059
+ "grad_norm": 0.35507500171661377,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.4,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09076970254523152,
1066
+ "grad_norm": 0.39351052045822144,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4207,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09138301134621282,
1073
+ "grad_norm": 0.38654205203056335,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.4047,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09199632014719411,
1080
+ "grad_norm": 0.4969562292098999,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4101,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09199632014719411,
1087
+ "eval_loss": 0.34416279196739197,
1088
+ "eval_runtime": 219.9752,
1089
+ "eval_samples_per_second": 12.483,
1090
+ "eval_steps_per_second": 3.123,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3759088865247232e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null