aleegis09 commited on
Commit
c05ab97
·
verified ·
1 Parent(s): eb91ab9

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 sha256:82f5c8dc140b24bae63ef0d36ffeae84bdb32c727dcab89b4d7e6121e7ea6828
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46edc1ec92691fe61dea39e7a416696a9f8913581742b2212e106d72b37d7f56
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecfa7c6e29fb78dd53377800cd121776a86e9e659b66a180205537ffe478c7ba
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685507dedf6111a598e3016e9a69bb0410a56b5ef58ad29fe399440577cd8016
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547212ff5093756d6f7c74d5e6347951b86f5e392a4912233dafd205a955a5d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c81bc38fb2c4b4545ac6ddefe2d599097088dea54f660088f685d30c77f0d9a
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": 0.01937755011022091,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3872216844143272,
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": 14.028,
732
  "eval_steps_per_second": 3.515,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.330508659163136e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.017788490280508995,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5808325266214908,
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": 14.028,
732
  "eval_steps_per_second": 3.515,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3910939012584705,
737
+ "grad_norm": 0.05301031470298767,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0234,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.39496611810261373,
744
+ "grad_norm": 0.06627804785966873,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0187,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.398838334946757,
751
+ "grad_norm": 0.05236673355102539,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0171,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4027105517909003,
758
+ "grad_norm": 0.04712076112627983,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0195,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.40658276863504356,
765
+ "grad_norm": 0.046172890812158585,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0168,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.41045498547918685,
772
+ "grad_norm": 0.05620027333498001,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0156,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4143272023233301,
779
+ "grad_norm": 0.06328780949115753,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0203,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4181994191674734,
786
+ "grad_norm": 0.0666506290435791,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0267,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4220716360116166,
793
+ "grad_norm": 0.042762067168951035,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0156,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4259438528557599,
800
+ "grad_norm": 0.05910148099064827,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0196,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4298160696999032,
807
+ "grad_norm": 0.046227678656578064,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0193,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.43368828654404645,
814
+ "grad_norm": 0.051421985030174255,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0183,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.43756050338818975,
821
+ "grad_norm": 0.03285564109683037,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0148,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.441432720232333,
828
+ "grad_norm": 0.035902880132198334,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0151,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.4453049370764763,
835
+ "grad_norm": 0.04394988343119621,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0187,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.4491771539206196,
842
+ "grad_norm": 0.04423746466636658,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0172,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4530493707647628,
849
+ "grad_norm": 0.05456831306219101,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.023,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4569215876089061,
856
+ "grad_norm": 0.05230424925684929,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.019,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.46079380445304935,
863
+ "grad_norm": 0.04211042821407318,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0174,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.46466602129719264,
870
+ "grad_norm": 0.04608823359012604,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0239,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.46853823814133594,
877
+ "grad_norm": 0.07439879328012466,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.018,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4724104549854792,
884
+ "grad_norm": 0.049552951008081436,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0146,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4762826718296225,
891
+ "grad_norm": 0.051944442093372345,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0223,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4801548886737657,
898
+ "grad_norm": 0.03937254101037979,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0135,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.484027105517909,
905
+ "grad_norm": 0.07220064103603363,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.017,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4878993223620523,
912
+ "grad_norm": 0.039477597922086716,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0158,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.49177153920619554,
919
+ "grad_norm": 0.04569016396999359,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0124,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.49564375605033884,
926
+ "grad_norm": 0.051465414464473724,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0174,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4995159728944821,
933
+ "grad_norm": 0.06285690516233444,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0181,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5033881897386253,
940
+ "grad_norm": 0.03760867938399315,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0161,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5072604065827686,
947
+ "grad_norm": 0.0777566134929657,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0352,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5111326234269119,
954
+ "grad_norm": 0.04282362014055252,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0144,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5150048402710552,
961
+ "grad_norm": 0.04963918775320053,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0162,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5188770571151985,
968
+ "grad_norm": 0.050760362297296524,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0173,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5227492739593417,
975
+ "grad_norm": 0.055553846061229706,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0197,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.526621490803485,
982
+ "grad_norm": 0.06745583564043045,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.021,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5304937076476283,
989
+ "grad_norm": 0.061450064182281494,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0211,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5343659244917716,
996
+ "grad_norm": 0.06228160485625267,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0228,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5382381413359149,
1003
+ "grad_norm": 0.055065497756004333,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0145,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.542110358180058,
1010
+ "grad_norm": 0.041081007570028305,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0155,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5459825750242013,
1017
+ "grad_norm": 0.06930065900087357,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0167,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5498547918683446,
1024
+ "grad_norm": 0.056641146540641785,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0173,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5537270087124879,
1031
+ "grad_norm": 0.04107319563627243,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0168,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5575992255566312,
1038
+ "grad_norm": 0.05168822407722473,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0144,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5614714424007744,
1045
+ "grad_norm": 0.03349588066339493,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0125,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5653436592449177,
1052
+ "grad_norm": 0.0859992504119873,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0287,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.569215876089061,
1059
+ "grad_norm": 0.044449854642152786,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.0121,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5730880929332043,
1066
+ "grad_norm": 0.044262442737817764,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0108,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5769603097773476,
1073
+ "grad_norm": 0.06609819829463959,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0202,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5808325266214908,
1080
+ "grad_norm": 0.08649075031280518,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0131,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5808325266214908,
1087
+ "eval_loss": 0.017788490280508995,
1088
+ "eval_runtime": 31.0247,
1089
+ "eval_samples_per_second": 14.021,
1090
+ "eval_steps_per_second": 3.513,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.995762988744704e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null