aleegis10 commited on
Commit
3f2c199
·
verified ·
1 Parent(s): b619918

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:f87d844ad917148c13e6551d34615d7b041581fe1cab9272dcefb2f2bb9da31d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef0bb2dceeecf903090b542801e1b96f298db2f1291c050ab1dee879002952e
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaf34dcf06c28195928e27eed1a4d84d9278f053b4fc884e10a01f077e97fef8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246c31f5c8d8dc7eafbf10c64ac87472f86a855fdfbd3aad10d7c39c3ca4c934
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90807a1d83bd82a08797b4429c1802f437d69b9284001fef57bdbb720f809a96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dcd4452a69608e938a5009c34a959206e72d5053189e310cef8d05b8fc3e23e
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": 1.8262602090835571,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07544322897019992,
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": 13.185,
732
  "eval_steps_per_second": 3.301,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5880422592163086,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11316484345529988,
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": 13.185,
732
  "eval_steps_per_second": 3.301,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07619766125990192,
737
+ "grad_norm": 1.596497654914856,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.9814,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07695209354960392,
744
+ "grad_norm": 1.8237228393554688,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.2038,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07770652583930593,
751
+ "grad_norm": 1.6423615217208862,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.0431,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07846095812900793,
758
+ "grad_norm": 1.4647657871246338,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.0032,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07921539041870992,
765
+ "grad_norm": 1.2502529621124268,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0455,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07996982270841192,
772
+ "grad_norm": 1.076562762260437,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.9707,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08072425499811392,
779
+ "grad_norm": 0.8226836919784546,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.7367,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08147868728781592,
786
+ "grad_norm": 0.8313952684402466,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.9226,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08223311957751792,
793
+ "grad_norm": 0.9033826589584351,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7792,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08298755186721991,
800
+ "grad_norm": 0.9052550196647644,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.8617,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08374198415692191,
807
+ "grad_norm": 0.9986050128936768,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.782,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08449641644662391,
814
+ "grad_norm": 0.8404749035835266,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.8473,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08525084873632592,
821
+ "grad_norm": 0.8716220259666443,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.8361,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08600528102602792,
828
+ "grad_norm": 0.8941475749015808,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.6842,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08675971331572992,
835
+ "grad_norm": 0.8960546851158142,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.8462,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08751414560543191,
842
+ "grad_norm": 0.9606665372848511,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.6934,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08826857789513391,
849
+ "grad_norm": 0.8806241154670715,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.5693,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08902301018483591,
856
+ "grad_norm": 0.8808760643005371,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.5308,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08977744247453791,
863
+ "grad_norm": 0.8981679677963257,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7348,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0905318747642399,
870
+ "grad_norm": 1.0557870864868164,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.8061,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0912863070539419,
877
+ "grad_norm": 0.9026768803596497,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6813,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0920407393436439,
884
+ "grad_norm": 0.9068759083747864,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.7559,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09279517163334591,
891
+ "grad_norm": 0.8655785322189331,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.643,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09354960392304791,
898
+ "grad_norm": 0.8876742124557495,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6204,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09430403621274991,
905
+ "grad_norm": 0.8887796401977539,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7183,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0950584685024519,
912
+ "grad_norm": 0.9163860082626343,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6476,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0958129007921539,
919
+ "grad_norm": 0.8868651986122131,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.7739,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0965673330818559,
926
+ "grad_norm": 1.086626648902893,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.6641,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0973217653715579,
933
+ "grad_norm": 0.9153982996940613,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.8573,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0980761976612599,
940
+ "grad_norm": 0.9019652009010315,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.7614,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0988306299509619,
947
+ "grad_norm": 0.8990781903266907,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.7265,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0995850622406639,
954
+ "grad_norm": 0.998482882976532,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.7286,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1003394945303659,
961
+ "grad_norm": 0.8682374358177185,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5439,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1010939268200679,
968
+ "grad_norm": 0.946426510810852,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4326,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1018483591097699,
975
+ "grad_norm": 0.8491016626358032,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.4449,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1026027913994719,
982
+ "grad_norm": 0.8618675470352173,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.5693,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1033572236891739,
989
+ "grad_norm": 0.893403947353363,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5326,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1041116559788759,
996
+ "grad_norm": 0.8355165719985962,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.367,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10486608826857789,
1003
+ "grad_norm": 0.8898566961288452,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3839,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.10562052055827989,
1010
+ "grad_norm": 0.9898171424865723,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.6544,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10637495284798189,
1017
+ "grad_norm": 0.9910078644752502,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.3499,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1071293851376839,
1024
+ "grad_norm": 0.949513852596283,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.4267,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1078838174273859,
1031
+ "grad_norm": 1.091713786125183,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.4309,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1086382497170879,
1038
+ "grad_norm": 1.0707581043243408,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.5613,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1093926820067899,
1045
+ "grad_norm": 1.1106162071228027,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.3316,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11014711429649189,
1052
+ "grad_norm": 1.1206798553466797,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.399,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11090154658619389,
1059
+ "grad_norm": 1.160050868988037,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.2398,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11165597887589589,
1066
+ "grad_norm": 1.1449685096740723,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7707,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11241041116559788,
1073
+ "grad_norm": 1.1998111009597778,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.7566,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11316484345529988,
1080
+ "grad_norm": 1.456712007522583,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7632,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11316484345529988,
1087
+ "eval_loss": 1.5880422592163086,
1088
+ "eval_runtime": 169.1427,
1089
+ "eval_samples_per_second": 13.202,
1090
+ "eval_steps_per_second": 3.305,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null