prxy5606 commited on
Commit
d7700e2
·
verified ·
1 Parent(s): 5c2b533

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:bf353d0f5fbdf0b7a35dba376a79334e5a994b5398c9b5af4d89a571bcfa7a46
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73cb3f7e767cffabdc6df3c5d82c84756414f491e15647141f3ab35ac79119f
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36e6fca42432e3c8f63687516347d08a39f6f44949579e5b65813a16f04e9379
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7eab0b04b8694966ad08c491c58a18201d489d5a67fee877dd9a1cd0df9cde3
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bf9ba1abf6b0348288bd583475285e81d89893da9d49c4bdbde4c077bc7277e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8532c41a24f0ea71c2034161462b2f0a6c70aba8a176d5ef2b01abb9963d3848
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": 0.46243494749069214,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9174311926605505,
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": 32.641,
732
  "eval_steps_per_second": 8.16,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.30904010489856e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4371192753314972,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.3761467889908257,
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": 32.641,
732
  "eval_steps_per_second": 8.16,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.926605504587156,
737
+ "grad_norm": 0.3079433739185333,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.5249,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.9357798165137615,
744
+ "grad_norm": 0.2792729139328003,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.4466,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.944954128440367,
751
+ "grad_norm": 0.3364558219909668,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.5365,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9541284403669725,
758
+ "grad_norm": 0.3221740126609802,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.496,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.963302752293578,
765
+ "grad_norm": 0.3582867980003357,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.5445,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.9724770642201835,
772
+ "grad_norm": 0.44838571548461914,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.6834,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.981651376146789,
779
+ "grad_norm": 0.39783820509910583,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.4235,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.9908256880733946,
786
+ "grad_norm": 0.8808133602142334,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.985,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.0,
793
+ "grad_norm": 0.2551686763763428,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.528,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.0091743119266054,
800
+ "grad_norm": 0.1278965026140213,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.1972,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.018348623853211,
807
+ "grad_norm": 0.141044482588768,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2327,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.0275229357798166,
814
+ "grad_norm": 0.13628904521465302,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.1995,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.036697247706422,
821
+ "grad_norm": 0.18226638436317444,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3852,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.0458715596330275,
828
+ "grad_norm": 0.22630174458026886,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.463,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.0550458715596331,
835
+ "grad_norm": 0.18771854043006897,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.2828,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.0642201834862386,
842
+ "grad_norm": 0.21680407226085663,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.4297,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.073394495412844,
849
+ "grad_norm": 0.17024627327919006,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.2751,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.0825688073394495,
856
+ "grad_norm": 0.21628738939762115,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.3745,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.091743119266055,
863
+ "grad_norm": 0.24735943973064423,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.4844,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.1009174311926606,
870
+ "grad_norm": 0.21772918105125427,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.2957,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.110091743119266,
877
+ "grad_norm": 0.2418142408132553,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.2949,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.1192660550458715,
884
+ "grad_norm": 0.25259315967559814,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.4492,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.1284403669724772,
891
+ "grad_norm": 0.3049667477607727,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.4814,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.1376146788990826,
898
+ "grad_norm": 0.30187371373176575,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.5876,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.146788990825688,
905
+ "grad_norm": 0.31283828616142273,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.5676,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.1559633027522935,
912
+ "grad_norm": 0.2810775637626648,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.4347,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.165137614678899,
919
+ "grad_norm": 0.23284779489040375,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3206,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.1743119266055047,
926
+ "grad_norm": 0.29070916771888733,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.4457,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.18348623853211,
933
+ "grad_norm": 0.3149646818637848,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.4184,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.1926605504587156,
940
+ "grad_norm": 0.33116212487220764,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.4638,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.2018348623853212,
947
+ "grad_norm": 0.33836284279823303,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.472,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.2110091743119267,
954
+ "grad_norm": 0.3052822947502136,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.4088,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.2201834862385321,
961
+ "grad_norm": 0.3751441240310669,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.5534,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.2293577981651376,
968
+ "grad_norm": 0.4007648527622223,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.522,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.238532110091743,
975
+ "grad_norm": 0.4260527193546295,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.3983,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.2477064220183487,
982
+ "grad_norm": 0.5929573178291321,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.5811,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.2568807339449541,
989
+ "grad_norm": 0.1770479828119278,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.4312,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.2660550458715596,
996
+ "grad_norm": 0.182498037815094,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3243,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.2752293577981653,
1003
+ "grad_norm": 0.21625658869743347,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3693,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.2844036697247707,
1010
+ "grad_norm": 0.19629067182540894,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3357,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.2935779816513762,
1017
+ "grad_norm": 0.23945830762386322,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4062,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.3027522935779816,
1024
+ "grad_norm": 0.21827231347560883,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.2891,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.311926605504587,
1031
+ "grad_norm": 0.21502086520195007,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2466,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.3211009174311927,
1038
+ "grad_norm": 0.28084877133369446,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.4362,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.3302752293577982,
1045
+ "grad_norm": 0.2033384144306183,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.232,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.3394495412844036,
1052
+ "grad_norm": 0.28219449520111084,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.423,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.3486238532110093,
1059
+ "grad_norm": 0.24117745459079742,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3882,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.3577981651376148,
1066
+ "grad_norm": 0.35435786843299866,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5143,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.3669724770642202,
1073
+ "grad_norm": 0.2955686151981354,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.4645,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.3761467889908257,
1080
+ "grad_norm": 0.29498574137687683,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4583,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.3761467889908257,
1087
+ "eval_loss": 0.4371192753314972,
1088
+ "eval_runtime": 5.6365,
1089
+ "eval_samples_per_second": 32.645,
1090
+ "eval_steps_per_second": 8.161,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.96356015734784e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null