auxyus commited on
Commit
c937396
·
verified ·
1 Parent(s): 9251521

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:a5ce9388ff5c0d016e84e5463befac62b67968957fff89127716a439a91513cd
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f28640da8513710a1c6d192f40a3d8ea241cac90e8ec45be09547591b6d8ea5
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125c09852ff0efdf055c0b05d8491ab176667896b227314f13bcf828c1716814
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d71f325631eea82c7034d459bcfa13ca9eed69dce270daecb1cab022f919b54
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73802fadfe7a3f3281ac6f7349f29b843350a9fb51f5dee1bb39ff24037f453b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc5eb50fa4b443481656b87ad994502e0c2c1a75908d934112745ae78e8728d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4002ee03f4202a6a410bde3375cd186d152ce129e8a177eb112bee1f18b1e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8155827522277832,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06341154090044387,
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": 8.92,
732
  "eval_steps_per_second": 2.23,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.3383168908263424e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8000059723854065,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09511731135066583,
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": 8.92,
732
  "eval_steps_per_second": 2.23,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06404565630944832,
737
+ "grad_norm": 1.5373103618621826,
738
+ "learning_rate": 8.715724127386972e-05,
739
+ "loss": 3.477,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06467977171845275,
744
+ "grad_norm": 1.278006911277771,
745
+ "learning_rate": 8.688653405904652e-05,
746
+ "loss": 3.476,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0653138871274572,
751
+ "grad_norm": 1.0467379093170166,
752
+ "learning_rate": 8.661343332988869e-05,
753
+ "loss": 3.3155,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06594800253646163,
758
+ "grad_norm": 1.3283839225769043,
759
+ "learning_rate": 8.633795680751116e-05,
760
+ "loss": 3.4751,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06658211794546608,
765
+ "grad_norm": 1.1208345890045166,
766
+ "learning_rate": 8.606012236719073e-05,
767
+ "loss": 3.228,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06721623335447051,
772
+ "grad_norm": 1.0446490049362183,
773
+ "learning_rate": 8.577994803720606e-05,
774
+ "loss": 3.3327,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06785034876347495,
779
+ "grad_norm": 1.0248538255691528,
780
+ "learning_rate": 8.549745199766792e-05,
781
+ "loss": 3.348,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06848446417247939,
786
+ "grad_norm": 1.1333471536636353,
787
+ "learning_rate": 8.521265257933948e-05,
788
+ "loss": 3.3869,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06911857958148383,
793
+ "grad_norm": 1.1693687438964844,
794
+ "learning_rate": 8.492556826244687e-05,
795
+ "loss": 3.326,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06975269499048826,
800
+ "grad_norm": 1.0264679193496704,
801
+ "learning_rate": 8.463621767547998e-05,
802
+ "loss": 3.2675,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07038681039949271,
807
+ "grad_norm": 1.103921890258789,
808
+ "learning_rate": 8.434461959398376e-05,
809
+ "loss": 3.354,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07102092580849714,
814
+ "grad_norm": 1.0422513484954834,
815
+ "learning_rate": 8.405079293933986e-05,
816
+ "loss": 3.2956,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07165504121750159,
821
+ "grad_norm": 1.0689914226531982,
822
+ "learning_rate": 8.375475677753881e-05,
823
+ "loss": 3.3304,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07228915662650602,
828
+ "grad_norm": 1.0220685005187988,
829
+ "learning_rate": 8.345653031794292e-05,
830
+ "loss": 3.3593,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07292327203551047,
835
+ "grad_norm": 1.1142345666885376,
836
+ "learning_rate": 8.315613291203976e-05,
837
+ "loss": 3.295,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0735573874445149,
842
+ "grad_norm": 1.048160433769226,
843
+ "learning_rate": 8.285358405218655e-05,
844
+ "loss": 3.2746,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07419150285351934,
849
+ "grad_norm": 1.0649545192718506,
850
+ "learning_rate": 8.25489033703452e-05,
851
+ "loss": 3.3655,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07482561826252378,
856
+ "grad_norm": 1.0890159606933594,
857
+ "learning_rate": 8.224211063680853e-05,
858
+ "loss": 3.3308,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07545973367152822,
863
+ "grad_norm": 1.0687116384506226,
864
+ "learning_rate": 8.19332257589174e-05,
865
+ "loss": 3.1868,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07609384908053266,
870
+ "grad_norm": 1.1016745567321777,
871
+ "learning_rate": 8.162226877976887e-05,
872
+ "loss": 3.2142,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0767279644895371,
877
+ "grad_norm": 1.051974892616272,
878
+ "learning_rate": 8.130925987691569e-05,
879
+ "loss": 3.3221,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07736207989854153,
884
+ "grad_norm": 1.0410847663879395,
885
+ "learning_rate": 8.099421936105702e-05,
886
+ "loss": 3.1397,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07799619530754598,
891
+ "grad_norm": 1.072290301322937,
892
+ "learning_rate": 8.067716767472045e-05,
893
+ "loss": 3.3434,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07863031071655041,
898
+ "grad_norm": 1.0379129648208618,
899
+ "learning_rate": 8.035812539093557e-05,
900
+ "loss": 3.25,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07926442612555486,
905
+ "grad_norm": 1.0454907417297363,
906
+ "learning_rate": 8.003711321189895e-05,
907
+ "loss": 3.2054,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07989854153455929,
912
+ "grad_norm": 1.0810647010803223,
913
+ "learning_rate": 7.971415196763088e-05,
914
+ "loss": 3.1932,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08053265694356374,
919
+ "grad_norm": 1.0763037204742432,
920
+ "learning_rate": 7.938926261462366e-05,
921
+ "loss": 3.2082,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08116677235256817,
926
+ "grad_norm": 1.1298437118530273,
927
+ "learning_rate": 7.906246623448183e-05,
928
+ "loss": 3.1894,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0818008877615726,
933
+ "grad_norm": 1.0926628112792969,
934
+ "learning_rate": 7.873378403255419e-05,
935
+ "loss": 3.1941,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08243500317057705,
940
+ "grad_norm": 1.0685158967971802,
941
+ "learning_rate": 7.840323733655778e-05,
942
+ "loss": 3.169,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08306911857958148,
947
+ "grad_norm": 1.0912131071090698,
948
+ "learning_rate": 7.807084759519405e-05,
949
+ "loss": 3.1239,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08370323398858592,
954
+ "grad_norm": 1.1438196897506714,
955
+ "learning_rate": 7.773663637675694e-05,
956
+ "loss": 3.273,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08433734939759036,
961
+ "grad_norm": 1.1781691312789917,
962
+ "learning_rate": 7.740062536773352e-05,
963
+ "loss": 3.3073,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0849714648065948,
968
+ "grad_norm": 1.149361252784729,
969
+ "learning_rate": 7.706283637139658e-05,
970
+ "loss": 3.2185,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08560558021559923,
975
+ "grad_norm": 1.1654759645462036,
976
+ "learning_rate": 7.672329130639005e-05,
977
+ "loss": 3.1729,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08623969562460368,
982
+ "grad_norm": 1.3615312576293945,
983
+ "learning_rate": 7.638201220530665e-05,
984
+ "loss": 3.1193,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08687381103360811,
989
+ "grad_norm": 1.0837875604629517,
990
+ "learning_rate": 7.603902121325813e-05,
991
+ "loss": 3.1017,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08750792644261256,
996
+ "grad_norm": 1.105128526687622,
997
+ "learning_rate": 7.569434058643844e-05,
998
+ "loss": 3.1515,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08814204185161699,
1003
+ "grad_norm": 1.0796869993209839,
1004
+ "learning_rate": 7.534799269067953e-05,
1005
+ "loss": 3.1271,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.08877615726062144,
1010
+ "grad_norm": 1.2005115747451782,
1011
+ "learning_rate": 7.500000000000001e-05,
1012
+ "loss": 3.131,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08941027266962587,
1017
+ "grad_norm": 1.122515082359314,
1018
+ "learning_rate": 7.465038509514688e-05,
1019
+ "loss": 3.1134,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09004438807863031,
1024
+ "grad_norm": 1.1972311735153198,
1025
+ "learning_rate": 7.42991706621303e-05,
1026
+ "loss": 3.0486,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09067850348763475,
1031
+ "grad_norm": 1.140086054801941,
1032
+ "learning_rate": 7.394637949075154e-05,
1033
+ "loss": 2.9324,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09131261889663919,
1038
+ "grad_norm": 1.3415659666061401,
1039
+ "learning_rate": 7.35920344731241e-05,
1040
+ "loss": 3.0243,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09194673430564362,
1045
+ "grad_norm": 1.196213722229004,
1046
+ "learning_rate": 7.323615860218843e-05,
1047
+ "loss": 3.0405,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09258084971464807,
1052
+ "grad_norm": 1.3614180088043213,
1053
+ "learning_rate": 7.287877497021978e-05,
1054
+ "loss": 2.8349,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0932149651236525,
1059
+ "grad_norm": 1.288540244102478,
1060
+ "learning_rate": 7.251990676732984e-05,
1061
+ "loss": 2.7361,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09384908053265695,
1066
+ "grad_norm": 1.2313977479934692,
1067
+ "learning_rate": 7.215957727996207e-05,
1068
+ "loss": 2.8024,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09448319594166138,
1073
+ "grad_norm": 1.2483394145965576,
1074
+ "learning_rate": 7.179780988938051e-05,
1075
+ "loss": 2.5696,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09511731135066583,
1080
+ "grad_norm": 1.4693834781646729,
1081
+ "learning_rate": 7.143462807015271e-05,
1082
+ "loss": 2.6114,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09511731135066583,
1087
+ "eval_loss": 0.8000059723854065,
1088
+ "eval_runtime": 299.1522,
1089
+ "eval_samples_per_second": 8.878,
1090
+ "eval_steps_per_second": 2.22,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.510376473821184e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null