aleegis11 commited on
Commit
7f9e23b
·
verified ·
1 Parent(s): 1532081

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 sha256:4300c24a4fc7349ee026753e8fcc0bdd76cdbf8af41e0660e5cfcfdc49eca24e
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf7b32247e3c0bf2781cea338cfb2a209b3f0fdcae96fc43b22bad3da48036b
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c3db81cc2353742152faf297413204fca42511d4c48613b8bfa9470aa2b7433
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7453bc0e138bf37d1f8c334918d6825cffbe283f18f796005afb2fe7e13224fc
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f84d44f8b30748ad7616fa9b9557c9ae059a938575ee5d987410cbf693aba249
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab6b1fa3d19ef80a8b6a3ee155408e858b9b550f44bfb07b20708201055bcf3
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": 3.5297350883483887,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.012370496366166692,
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": 60.394,
732
  "eval_steps_per_second": 15.1,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.487229824066162,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.01855574454925004,
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": 60.394,
732
  "eval_steps_per_second": 15.1,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.012494201329828359,
737
+ "grad_norm": 0.4453275799751282,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.2384,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.012617906293490026,
744
+ "grad_norm": 0.5066372752189636,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.3263,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.012741611257151694,
751
+ "grad_norm": 0.27735647559165955,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3094,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01286531622081336,
758
+ "grad_norm": 0.2043253630399704,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5011,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.012989021184475027,
765
+ "grad_norm": 0.18582770228385925,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.6609,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.013112726148136694,
772
+ "grad_norm": 0.18918775022029877,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.6867,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01323643111179836,
779
+ "grad_norm": 0.22034385800361633,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.9582,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013360136075460027,
786
+ "grad_norm": 0.22781382501125336,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8897,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.013483841039121695,
793
+ "grad_norm": 0.2723545730113983,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.0569,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.013607546002783362,
800
+ "grad_norm": 0.24561963975429535,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.1398,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.013731250966445029,
807
+ "grad_norm": 0.23813565075397491,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.3282,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.013854955930106695,
814
+ "grad_norm": 0.2500579357147217,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.3831,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.013978660893768362,
821
+ "grad_norm": 0.26784828305244446,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.3787,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01410236585743003,
828
+ "grad_norm": 0.2763846814632416,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.7042,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.014226070821091697,
835
+ "grad_norm": 0.2663004696369171,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.3558,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.014349775784753363,
842
+ "grad_norm": 0.28943297266960144,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.9233,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01447348074841503,
849
+ "grad_norm": 0.258836567401886,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.5686,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.014597185712076697,
856
+ "grad_norm": 0.33632829785346985,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.4671,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.014720890675738363,
863
+ "grad_norm": 0.311443567276001,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.0168,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.014844595639400032,
870
+ "grad_norm": 0.3112979531288147,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.2336,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.014968300603061698,
877
+ "grad_norm": 0.3561400771141052,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.4632,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.015092005566723365,
884
+ "grad_norm": 0.3534078896045685,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.4256,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.015215710530385031,
891
+ "grad_norm": 0.3245716094970703,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.2542,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.015339415494046698,
898
+ "grad_norm": 0.3680708706378937,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.763,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.015463120457708366,
905
+ "grad_norm": 0.35930800437927246,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.7993,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.015586825421370033,
912
+ "grad_norm": 0.3474310338497162,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.6859,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.015710530385031698,
919
+ "grad_norm": 0.4066416621208191,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.2552,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.015834235348693368,
926
+ "grad_norm": 0.38194552063941956,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.1787,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.015957940312355035,
933
+ "grad_norm": 0.3861883580684662,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.1073,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0160816452760167,
940
+ "grad_norm": 0.4550367593765259,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 4.0508,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.016205350239678368,
947
+ "grad_norm": 0.4556775987148285,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.2837,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.016329055203340034,
954
+ "grad_norm": 0.41627028584480286,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.2839,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0164527601670017,
961
+ "grad_norm": 0.4195609986782074,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.3206,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.016576465130663368,
968
+ "grad_norm": 0.4351290166378021,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.5282,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.016700170094325034,
975
+ "grad_norm": 0.45207464694976807,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.5273,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0168238750579867,
982
+ "grad_norm": 0.4965157210826874,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.3781,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.016947580021648367,
989
+ "grad_norm": 0.4925777316093445,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.4784,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.017071284985310034,
996
+ "grad_norm": 0.48698151111602783,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.7109,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.017194989948971704,
1003
+ "grad_norm": 0.5326199531555176,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.7638,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01731869491263337,
1010
+ "grad_norm": 0.5045056939125061,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.7973,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.017442399876295037,
1017
+ "grad_norm": 0.48011139035224915,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.5411,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.017566104839956704,
1024
+ "grad_norm": 0.6269281506538391,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.6874,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.01768980980361837,
1031
+ "grad_norm": 0.5466679930686951,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.6733,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.017813514767280037,
1038
+ "grad_norm": 0.5804339051246643,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.6588,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.017937219730941704,
1045
+ "grad_norm": 0.6334162950515747,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 5.0589,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.01806092469460337,
1052
+ "grad_norm": 0.6198123097419739,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.9944,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.018184629658265037,
1059
+ "grad_norm": 0.6776898503303528,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.1355,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.018308334621926704,
1066
+ "grad_norm": 0.6639952063560486,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.3923,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.01843203958558837,
1073
+ "grad_norm": 0.8215330839157104,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.2146,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.01855574454925004,
1080
+ "grad_norm": 0.8143311738967896,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.5062,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.01855574454925004,
1087
+ "eval_loss": 3.487229824066162,
1088
+ "eval_runtime": 225.7115,
1089
+ "eval_samples_per_second": 60.32,
1090
+ "eval_steps_per_second": 15.081,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.032049150918656e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null