arcwarden46 commited on
Commit
f93d778
·
verified ·
1 Parent(s): 5ec339e

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 sha256:73a327840041c5e7f13b68febe1404afbdae0a8414835aa8b57e5cb162911778
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d094a881ded9c78d1fba75863f5462bababd81859013d2e41874f970a11428
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14e5a43ce8ddf7cbcd015679d22f3b1b35906ede53546e80360ea858db5c4643
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ae857031525c8e71317e07af7a22f6016ac2cd6dc17acdf762a54ae3a31add
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0664582359f99320cf3ef366e7c6afff3e12ad91b8e191e816f63cc9e498ed67
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844eaf46bc220302fea9fbecdc4be2a8dad6024a220ef352813547cff4438fbc
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": 10.304642677307129,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.023633677991137372,
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": 505.759,
732
  "eval_steps_per_second": 126.458,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 21695727403008.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.302956581115723,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03545051698670606,
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": 505.759,
732
  "eval_steps_per_second": 126.458,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.023870014771048744,
737
+ "grad_norm": 0.6042443513870239,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 41.2659,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.02410635155096012,
744
+ "grad_norm": 0.6423136591911316,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 41.2584,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02434268833087149,
751
+ "grad_norm": 0.8272608518600464,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 41.264,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.024579025110782866,
758
+ "grad_norm": 0.5923576951026917,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 41.2572,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.024815361890694238,
765
+ "grad_norm": 0.5755631327629089,
766
+ "learning_rate": 5e-05,
767
+ "loss": 41.2527,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.025051698670605613,
772
+ "grad_norm": 0.8759294152259827,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 41.231,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.025288035450516985,
779
+ "grad_norm": 0.7109207510948181,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 41.2625,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02552437223042836,
786
+ "grad_norm": 0.9061951637268066,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 41.2426,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.025760709010339736,
793
+ "grad_norm": 0.5387170910835266,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 41.2334,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.025997045790251107,
800
+ "grad_norm": 0.6056496500968933,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 41.222,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.026233382570162483,
807
+ "grad_norm": 0.5027456283569336,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 41.229,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.026469719350073855,
814
+ "grad_norm": 0.4441814422607422,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 41.2496,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.02670605612998523,
821
+ "grad_norm": 0.5234106183052063,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 41.1787,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0269423929098966,
828
+ "grad_norm": 0.6285588145256042,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 41.2019,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.027178729689807977,
835
+ "grad_norm": 0.7189363837242126,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 41.2289,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02741506646971935,
842
+ "grad_norm": 0.4671284854412079,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 41.2176,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.027651403249630724,
849
+ "grad_norm": 0.7947689294815063,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 41.2367,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0278877400295421,
856
+ "grad_norm": 0.7902439832687378,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 41.2048,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02812407680945347,
863
+ "grad_norm": 0.4855709969997406,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 41.2063,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.028360413589364846,
870
+ "grad_norm": 0.5833091139793396,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 41.2372,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.028596750369276218,
877
+ "grad_norm": 0.7160181999206543,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 41.2106,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.028833087149187593,
884
+ "grad_norm": 0.6571805477142334,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 41.2137,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.029069423929098965,
891
+ "grad_norm": 0.5013795495033264,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 41.1875,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02930576070901034,
898
+ "grad_norm": 0.5372549295425415,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 41.197,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.029542097488921712,
905
+ "grad_norm": 0.3943471908569336,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 41.2067,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.029778434268833087,
912
+ "grad_norm": 0.5975308418273926,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 41.2444,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.030014771048744462,
919
+ "grad_norm": 0.5731347799301147,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 41.2314,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.030251107828655834,
926
+ "grad_norm": 0.67473304271698,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 41.2306,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03048744460856721,
933
+ "grad_norm": 0.5370274782180786,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 41.1631,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03072378138847858,
940
+ "grad_norm": 0.5157413482666016,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 41.1876,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.030960118168389957,
947
+ "grad_norm": 0.4812129735946655,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 41.2219,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03119645494830133,
954
+ "grad_norm": 0.7001417875289917,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 41.2037,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0314327917282127,
961
+ "grad_norm": 0.5039445161819458,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 41.2263,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.031669128508124075,
968
+ "grad_norm": 0.5022205114364624,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 41.2047,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03190546528803545,
975
+ "grad_norm": 0.4550672173500061,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 41.2202,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.032141802067946826,
982
+ "grad_norm": 0.5127445459365845,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 41.212,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0323781388478582,
989
+ "grad_norm": 0.43551337718963623,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 41.2019,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03261447562776957,
996
+ "grad_norm": 0.5555402636528015,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 41.1991,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.032850812407680945,
1003
+ "grad_norm": 0.5227714776992798,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 41.2078,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03308714918759232,
1010
+ "grad_norm": 0.46548959612846375,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 41.2231,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.033323485967503695,
1017
+ "grad_norm": 0.4519064426422119,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 41.2182,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03355982274741506,
1024
+ "grad_norm": 0.5990817546844482,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 41.1755,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03379615952732644,
1031
+ "grad_norm": 0.43311795592308044,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 41.2137,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.034032496307237814,
1038
+ "grad_norm": 0.44968536496162415,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 41.2196,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03426883308714919,
1045
+ "grad_norm": 0.5897616147994995,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 41.2188,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.034505169867060564,
1052
+ "grad_norm": 0.5212418437004089,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 41.2309,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03474150664697193,
1059
+ "grad_norm": 0.5393649339675903,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 41.217,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03497784342688331,
1066
+ "grad_norm": 0.5517672300338745,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 41.1982,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03521418020679468,
1073
+ "grad_norm": 0.7273964285850525,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 41.1897,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03545051698670606,
1080
+ "grad_norm": 1.0823817253112793,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 41.1503,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03545051698670606,
1087
+ "eval_loss": 10.302956581115723,
1088
+ "eval_runtime": 14.0592,
1089
+ "eval_samples_per_second": 506.928,
1090
+ "eval_steps_per_second": 126.75,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 32597293400064.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null