aleegis09 commited on
Commit
0128b98
·
verified ·
1 Parent(s): 3898503

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:f227b623f8a075672ea79225413b2b2fce2241f30b0954a96eb8fd65f4d00290
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1504bd2201aad5bbce1a62b8f63a1c55a70b1d7ea94041e88892187fd4315d
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bfad403a0ebb39bced1a367b6fa9b54cab41bd0ff1239c233fd2904d5d33994
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170a6eefc3cef6d5f4a62914bf0496acf04d8b75d71758167459e32f60b315cf
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2950f6dac83ac119a24d49f55b4575671ea046ff6d1f4c7213cca3c8b1c0efa7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903af28b8a06393992435b870841df7b43b1c49c2651c379a64b2f35e53107fb
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": 0.7207558155059814,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.005101520253035404,
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": 23.024,
732
  "eval_steps_per_second": 5.756,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.769028955635712e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6727603077888489,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.007652280379553107,
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": 23.024,
732
  "eval_steps_per_second": 5.756,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0051525354555657585,
737
+ "grad_norm": 1.8114409446716309,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.4519,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.005203550658096113,
744
+ "grad_norm": 1.3645156621932983,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.9355,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.005254565860626467,
751
+ "grad_norm": 1.6342055797576904,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.1483,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.005305581063156821,
758
+ "grad_norm": 1.4563757181167603,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0416,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0053565962656871744,
765
+ "grad_norm": 1.3042280673980713,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9037,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.005407611468217529,
772
+ "grad_norm": 1.167454481124878,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8422,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.005458626670747883,
779
+ "grad_norm": 1.5215885639190674,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8697,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.005509641873278237,
786
+ "grad_norm": 1.1718409061431885,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8225,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.005560657075808591,
793
+ "grad_norm": 1.1947486400604248,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9246,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.005611672278338945,
800
+ "grad_norm": 1.2682052850723267,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8374,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.005662687480869299,
807
+ "grad_norm": 1.0839130878448486,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.8509,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.005713702683399653,
814
+ "grad_norm": 1.0443567037582397,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8311,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.005764717885930007,
821
+ "grad_norm": 0.9204378724098206,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.6479,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0058157330884603614,
828
+ "grad_norm": 1.0801767110824585,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.6897,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.005866748290990716,
835
+ "grad_norm": 0.9096378684043884,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.6534,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.005917763493521069,
842
+ "grad_norm": 0.9231741428375244,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.6428,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.005968778696051423,
849
+ "grad_norm": 1.1641801595687866,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.8048,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.006019793898581777,
856
+ "grad_norm": 0.9723463654518127,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.6917,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.006070809101112132,
863
+ "grad_norm": 0.8771831393241882,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.6006,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.006121824303642486,
870
+ "grad_norm": 0.9439581036567688,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.6236,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.006172839506172839,
877
+ "grad_norm": 0.8829584717750549,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.5982,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.006223854708703193,
884
+ "grad_norm": 0.9171614050865173,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.5895,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.006274869911233548,
891
+ "grad_norm": 0.8911136984825134,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.5654,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.006325885113763902,
898
+ "grad_norm": 0.8596011996269226,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6283,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.006376900316294256,
905
+ "grad_norm": 0.9068416357040405,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.6281,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.006427915518824609,
912
+ "grad_norm": 0.9677693247795105,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.6103,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0064789307213549635,
919
+ "grad_norm": 0.8677883744239807,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.55,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.006529945923885318,
926
+ "grad_norm": 1.0917985439300537,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.6188,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.006580961126415672,
933
+ "grad_norm": 0.8520172834396362,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.5346,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.006631976328946026,
940
+ "grad_norm": 1.0461883544921875,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.6786,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.00668299153147638,
947
+ "grad_norm": 1.1208341121673584,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.6343,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.006734006734006734,
954
+ "grad_norm": 0.9349234700202942,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.501,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.006785021936537088,
961
+ "grad_norm": 1.0781103372573853,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7478,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.006836037139067442,
968
+ "grad_norm": 0.9444073438644409,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.5975,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.006887052341597796,
975
+ "grad_norm": 1.1122676134109497,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7441,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0069380675441281505,
982
+ "grad_norm": 0.890365481376648,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.5508,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.006989082746658504,
989
+ "grad_norm": 1.0402615070343018,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.62,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.007040097949188858,
996
+ "grad_norm": 0.8860926628112793,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.5367,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.007091113151719212,
1003
+ "grad_norm": 1.0476042032241821,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.5839,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0071421283542495665,
1010
+ "grad_norm": 0.866302490234375,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.5287,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.007193143556779921,
1017
+ "grad_norm": 1.0551623106002808,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.5768,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.007244158759310274,
1024
+ "grad_norm": 1.14937162399292,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.6421,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.007295173961840628,
1031
+ "grad_norm": 0.9636757373809814,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.6001,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0073461891643709825,
1038
+ "grad_norm": 0.8499124646186829,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.525,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.007397204366901337,
1045
+ "grad_norm": 1.1190030574798584,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6799,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.007448219569431691,
1052
+ "grad_norm": 1.0400668382644653,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.5394,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.007499234771962045,
1059
+ "grad_norm": 1.0704658031463623,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.4973,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.007550249974492398,
1066
+ "grad_norm": 0.9756684303283691,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5394,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.007601265177022753,
1073
+ "grad_norm": 1.161603569984436,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5637,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.007652280379553107,
1080
+ "grad_norm": 1.4681497812271118,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.5215,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.007652280379553107,
1087
+ "eval_loss": 0.6727603077888489,
1088
+ "eval_runtime": 1432.5915,
1089
+ "eval_samples_per_second": 23.045,
1090
+ "eval_steps_per_second": 5.762,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0153543433453568e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null