prxy5608 commited on
Commit
4a430d7
·
verified ·
1 Parent(s): 9afb86a

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:e26386d4b1437a7349f1be6d6ce938994eba6aa23f4234e4bd02a46fe4eb5282
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f359a8647ac3636a3e7e2f7d7876e117bc2ad3b30067092402bca1fc434b15b0
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa829aa043269b7f4ee0862e3e27bfea95acf1cf2aa8b478c75fe4d2c75677d9
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c740947cbee89bc06bf8ac49b8c5f367e0c7a5f2aa356769c6e1ac4e22eb7c4
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef06e63c0956f1f73682a2d5ef0f790770958786b166f8bb09c5effb8a386c7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d22f45fb109a2f511bbed34b0303d6a02c71e08295131f5863bb11633923df7
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": 0.8251528143882751,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.16835016835016836,
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": 57.974,
732
  "eval_steps_per_second": 14.537,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.762880802154541,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.25252525252525254,
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": 57.974,
732
  "eval_steps_per_second": 14.537,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.17003367003367004,
737
+ "grad_norm": 2.0755367279052734,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9672,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.1717171717171717,
744
+ "grad_norm": 2.0217695236206055,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.9535,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1734006734006734,
751
+ "grad_norm": 1.9532135725021362,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9503,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1750841750841751,
758
+ "grad_norm": 1.8931111097335815,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8849,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.17676767676767677,
765
+ "grad_norm": 1.6922742128372192,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8469,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.17845117845117844,
772
+ "grad_norm": 1.7153887748718262,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8565,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.18013468013468015,
779
+ "grad_norm": 1.6420055627822876,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8784,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.18181818181818182,
786
+ "grad_norm": 1.5930083990097046,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8256,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.1835016835016835,
793
+ "grad_norm": 1.415897011756897,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8017,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.18518518518518517,
800
+ "grad_norm": 1.426174283027649,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8197,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.18686868686868688,
807
+ "grad_norm": 1.4900239706039429,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.7042,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.18855218855218855,
814
+ "grad_norm": 1.5487056970596313,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8758,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.19023569023569023,
821
+ "grad_norm": 1.4241440296173096,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.7972,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1919191919191919,
828
+ "grad_norm": 1.5170420408248901,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8287,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1936026936026936,
835
+ "grad_norm": 1.4301002025604248,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7282,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.19528619528619529,
842
+ "grad_norm": 1.4963473081588745,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.7553,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.19696969696969696,
849
+ "grad_norm": 1.3359309434890747,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.697,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.19865319865319866,
856
+ "grad_norm": 1.4342330694198608,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7276,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.20033670033670034,
863
+ "grad_norm": 1.4613280296325684,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.6979,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.20202020202020202,
870
+ "grad_norm": 1.3762140274047852,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.6833,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2037037037037037,
877
+ "grad_norm": 1.4406741857528687,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.7792,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.2053872053872054,
884
+ "grad_norm": 1.4419723749160767,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7243,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.20707070707070707,
891
+ "grad_norm": 1.439305067062378,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7154,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.20875420875420875,
898
+ "grad_norm": 1.4699344635009766,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7628,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.21043771043771045,
905
+ "grad_norm": 1.4562989473342896,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7785,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.21212121212121213,
912
+ "grad_norm": 1.3667465448379517,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.6523,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2138047138047138,
919
+ "grad_norm": 1.4240037202835083,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7409,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.21548821548821548,
926
+ "grad_norm": 1.5213513374328613,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7481,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.21717171717171718,
933
+ "grad_norm": 1.4982272386550903,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7974,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.21885521885521886,
940
+ "grad_norm": 1.4482314586639404,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.6998,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.22053872053872053,
947
+ "grad_norm": 1.4862515926361084,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.6552,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.2222222222222222,
954
+ "grad_norm": 1.431307315826416,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.6858,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2239057239057239,
961
+ "grad_norm": 1.466747760772705,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.6499,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2255892255892256,
968
+ "grad_norm": 1.5380254983901978,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.788,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.22727272727272727,
975
+ "grad_norm": 1.5833460092544556,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7462,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.22895622895622897,
982
+ "grad_norm": 1.5846306085586548,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7795,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.23063973063973064,
989
+ "grad_norm": 1.4377760887145996,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.6324,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.23232323232323232,
996
+ "grad_norm": 1.5191439390182495,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.6281,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.234006734006734,
1003
+ "grad_norm": 1.4722684621810913,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.6257,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2356902356902357,
1010
+ "grad_norm": 1.5686328411102295,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6873,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.23737373737373738,
1017
+ "grad_norm": 1.4807740449905396,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.5796,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.23905723905723905,
1024
+ "grad_norm": 1.4003280401229858,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.6285,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.24074074074074073,
1031
+ "grad_norm": 1.5255802869796753,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7166,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.24242424242424243,
1038
+ "grad_norm": 1.6983699798583984,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.732,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2441077441077441,
1045
+ "grad_norm": 1.538061261177063,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6466,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.24579124579124578,
1052
+ "grad_norm": 1.6083265542984009,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.668,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2474747474747475,
1059
+ "grad_norm": 1.7365162372589111,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6049,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.24915824915824916,
1066
+ "grad_norm": 1.8119126558303833,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.6753,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.25084175084175087,
1073
+ "grad_norm": 1.7427568435668945,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5982,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.25252525252525254,
1080
+ "grad_norm": 2.1858670711517334,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.6981,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.25252525252525254,
1087
+ "eval_loss": 0.762880802154541,
1088
+ "eval_runtime": 17.251,
1089
+ "eval_samples_per_second": 58.026,
1090
+ "eval_steps_per_second": 14.55,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null