aleegis10 commited on
Commit
5f331b5
·
verified ·
1 Parent(s): 9f219de

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 sha256:2dc4e17a91f20c94446595346fb4432ca8b424fd117f4728327d8058784b561b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98157d60b88b0eb9c01808fcb40f0d01c1d62aaddc743efcae67d54759b81b1b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cfda97d5176677b6cd58b1a00d3b9ebb91e6515ab39f3f53a6e5857a067d221
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0140ad6d499d0dfb056f2842b0e57edd722db829315a07782af8a8bb489257d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0372a767b1e9eb3858edd1a414bd1df06b0bad95b855bd2bf5be8f2cabd5f36
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d2eeaa65ec1cf376b185932acb238ac83c3599176c917521de47571527cea2
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": 1.419034719467163,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06480881399870382,
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": 7.066,
732
  "eval_steps_per_second": 1.767,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.717763934177198e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3218529224395752,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09721322099805574,
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": 7.066,
732
  "eval_steps_per_second": 1.767,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06545690213869086,
737
+ "grad_norm": 4.814598560333252,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.9494,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0661049902786779,
744
+ "grad_norm": 4.578697204589844,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.5302,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06675307841866494,
751
+ "grad_norm": 5.0061421394348145,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.5884,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06740116655865197,
758
+ "grad_norm": 5.34958553314209,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.775,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06804925469863901,
765
+ "grad_norm": 5.827226161956787,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.9442,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06869734283862605,
772
+ "grad_norm": 5.971827030181885,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.573,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06934543097861309,
779
+ "grad_norm": 6.491287708282471,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.302,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06999351911860013,
786
+ "grad_norm": 7.205959796905518,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.6267,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07064160725858717,
793
+ "grad_norm": 7.4618330001831055,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.4974,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0712896953985742,
800
+ "grad_norm": 7.016729831695557,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.6011,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07193778353856124,
807
+ "grad_norm": 7.163577079772949,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.402,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07258587167854828,
814
+ "grad_norm": 6.554802894592285,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.0592,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07323395981853532,
821
+ "grad_norm": 7.247341156005859,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.3753,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07388204795852236,
828
+ "grad_norm": 7.453572750091553,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.6571,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07453013609850939,
835
+ "grad_norm": 7.110829830169678,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.1858,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07517822423849643,
842
+ "grad_norm": 7.949575424194336,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.8766,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07582631237848347,
849
+ "grad_norm": 8.235194206237793,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.2648,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07647440051847051,
856
+ "grad_norm": 7.894912242889404,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.6548,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07712248865845756,
863
+ "grad_norm": 7.492299556732178,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.0731,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07777057679844458,
870
+ "grad_norm": 7.998632431030273,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.5284,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07841866493843162,
877
+ "grad_norm": 8.506697654724121,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.0284,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07906675307841866,
884
+ "grad_norm": 8.809338569641113,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.5977,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0797148412184057,
891
+ "grad_norm": 8.432890892028809,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.4425,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08036292935839275,
898
+ "grad_norm": 8.092004776000977,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.1623,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08101101749837979,
905
+ "grad_norm": 8.064069747924805,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.67,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08165910563836681,
912
+ "grad_norm": 9.591204643249512,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.3424,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08230719377835385,
919
+ "grad_norm": 8.736778259277344,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.6868,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0829552819183409,
926
+ "grad_norm": 9.050400733947754,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.7636,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08360337005832794,
933
+ "grad_norm": 8.817517280578613,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.2625,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08425145819831498,
940
+ "grad_norm": 9.457335472106934,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.4587,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.084899546338302,
947
+ "grad_norm": 8.814817428588867,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.1092,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08554763447828904,
954
+ "grad_norm": 9.131630897521973,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.4849,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08619572261827609,
961
+ "grad_norm": 10.105237007141113,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.6843,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08684381075826313,
968
+ "grad_norm": 8.991281509399414,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.762,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08749189889825017,
975
+ "grad_norm": 9.899235725402832,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.2467,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0881399870382372,
982
+ "grad_norm": 10.578429222106934,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.4836,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08878807517822424,
989
+ "grad_norm": 11.909724235534668,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.7676,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08943616331821128,
996
+ "grad_norm": 10.881829261779785,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.7597,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09008425145819832,
1003
+ "grad_norm": 10.840633392333984,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.5822,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09073233959818536,
1010
+ "grad_norm": 12.91557502746582,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.6312,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09138042773817238,
1017
+ "grad_norm": 16.27786636352539,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 6.1149,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09202851587815943,
1024
+ "grad_norm": 13.686140060424805,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.5252,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09267660401814647,
1031
+ "grad_norm": 20.249967575073242,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 7.0736,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09332469215813351,
1038
+ "grad_norm": 11.816630363464355,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.1945,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09397278029812055,
1045
+ "grad_norm": 9.47885799407959,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.6706,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09462086843810759,
1052
+ "grad_norm": 7.617250919342041,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.5462,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09526895657809462,
1059
+ "grad_norm": 7.987148761749268,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.8455,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09591704471808166,
1066
+ "grad_norm": 7.913012981414795,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.5029,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0965651328580687,
1073
+ "grad_norm": 7.453940391540527,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.257,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09721322099805574,
1080
+ "grad_norm": 8.691618919372559,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.9776,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09721322099805574,
1087
+ "eval_loss": 1.3218529224395752,
1088
+ "eval_runtime": 368.0191,
1089
+ "eval_samples_per_second": 7.062,
1090
+ "eval_steps_per_second": 1.766,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.078450525392077e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null