prxy5607 commited on
Commit
60e2385
·
verified ·
1 Parent(s): f510493

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:d4afe94a99101c0ef1e8328a92221d48c4dd1f4b9e05d13bd9a0fa0e7133706d
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e11cab38f0d3fa83bff0752d348bf40c16bb8f5edb130f14b7064f41e2de4c
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b789cbf94346c0f934bb43bda36fe8c3c9e2aff8ef075eeb90551542b2bc7e4
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788d6cf19a3bbc1228bbab794b00d2624e699bd97cc5944abf0d70ccfa0b1503
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95bf27e4c54eae74106423ad909d78cd68ecd3141cff730f14635eff50f0d401
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6f2b27d067cf7a828eba7aa0e0ddc05c20fe0060bf3ca66b5508fb7a2732b6
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": 0.9980463981628418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6410256410256411,
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": 9.311,
732
  "eval_steps_per_second": 2.337,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.32091006533632e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.955227792263031,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9615384615384616,
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": 9.311,
732
  "eval_steps_per_second": 2.337,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6474358974358975,
737
+ "grad_norm": 3.6587297916412354,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.918,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6538461538461539,
744
+ "grad_norm": 3.831242084503174,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.7586,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6602564102564102,
751
+ "grad_norm": 3.78513503074646,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.5943,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6666666666666666,
758
+ "grad_norm": 3.6787242889404297,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.4123,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6730769230769231,
765
+ "grad_norm": 3.7676947116851807,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.1584,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6794871794871795,
772
+ "grad_norm": 4.073101043701172,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.45,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6858974358974359,
779
+ "grad_norm": 4.140744209289551,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.5452,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.6923076923076923,
786
+ "grad_norm": 4.776129722595215,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.7265,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.6987179487179487,
793
+ "grad_norm": 4.0117506980896,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.2593,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7051282051282052,
800
+ "grad_norm": 4.677291393280029,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.1475,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7115384615384616,
807
+ "grad_norm": 5.10119104385376,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.3635,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.717948717948718,
814
+ "grad_norm": 5.42010498046875,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.0145,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7243589743589743,
821
+ "grad_norm": 5.240736484527588,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.2514,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7307692307692307,
828
+ "grad_norm": 7.772806167602539,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.5696,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7371794871794872,
835
+ "grad_norm": 8.802128791809082,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.8478,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7435897435897436,
842
+ "grad_norm": 7.847908020019531,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.0477,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.75,
849
+ "grad_norm": 7.966437816619873,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.0813,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7564102564102564,
856
+ "grad_norm": 8.309389114379883,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.3415,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.7628205128205128,
863
+ "grad_norm": 6.793262958526611,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.9559,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.7692307692307693,
870
+ "grad_norm": 6.368189334869385,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.708,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.7756410256410257,
877
+ "grad_norm": 4.444794654846191,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.6569,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.782051282051282,
884
+ "grad_norm": 5.020304203033447,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.4671,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.7884615384615384,
891
+ "grad_norm": 4.116661071777344,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.1168,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.7948717948717948,
898
+ "grad_norm": 3.835765838623047,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.2167,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8012820512820513,
905
+ "grad_norm": 3.623770236968994,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.1236,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8076923076923077,
912
+ "grad_norm": 3.4973554611206055,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.2815,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8141025641025641,
919
+ "grad_norm": 3.046509027481079,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.2196,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8205128205128205,
926
+ "grad_norm": 2.9827661514282227,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.0768,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8269230769230769,
933
+ "grad_norm": 2.907933235168457,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.9771,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.8333333333333334,
940
+ "grad_norm": 3.1948816776275635,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 4.0728,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8397435897435898,
947
+ "grad_norm": 3.368992805480957,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.0119,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8461538461538461,
954
+ "grad_norm": 3.3085951805114746,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.6765,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8525641025641025,
961
+ "grad_norm": 3.207343816757202,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.6675,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8589743589743589,
968
+ "grad_norm": 3.4521420001983643,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.7139,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.8653846153846154,
975
+ "grad_norm": 3.430363655090332,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.9139,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8717948717948718,
982
+ "grad_norm": 3.638237237930298,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.9763,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.8782051282051282,
989
+ "grad_norm": 3.6488420963287354,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.6282,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.8846153846153846,
996
+ "grad_norm": 3.8091797828674316,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.75,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.8910256410256411,
1003
+ "grad_norm": 4.3403706550598145,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.7878,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.8974358974358975,
1010
+ "grad_norm": 3.413701295852661,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.7514,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9038461538461539,
1017
+ "grad_norm": 3.869084596633911,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.8538,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9102564102564102,
1024
+ "grad_norm": 3.5061874389648438,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.4699,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9166666666666666,
1031
+ "grad_norm": 3.533756971359253,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.6468,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9230769230769231,
1038
+ "grad_norm": 3.7761576175689697,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.6921,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9294871794871795,
1045
+ "grad_norm": 3.948042154312134,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.6487,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.9358974358974359,
1052
+ "grad_norm": 3.8867499828338623,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.178,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.9423076923076923,
1059
+ "grad_norm": 4.0144782066345215,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.2615,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9487179487179487,
1066
+ "grad_norm": 3.983966112136841,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.024,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9551282051282052,
1073
+ "grad_norm": 4.11751651763916,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.3496,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9615384615384616,
1080
+ "grad_norm": 4.289830207824707,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.9751,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9615384615384616,
1087
+ "eval_loss": 0.955227792263031,
1088
+ "eval_runtime": 28.2085,
1089
+ "eval_samples_per_second": 9.323,
1090
+ "eval_steps_per_second": 2.34,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.48136509800448e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null