brixeus commited on
Commit
a3661a2
·
verified ·
1 Parent(s): 97380ef

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 sha256:3a1b26be33253ad0a66ee5d25b8f9a2d25786b2b02e44283b3f4858c74918498
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513d1d001e44abbb11bad16b9d54f3736bb27c4130e0788ca51fd9c10438e975
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34b6e58541ad0d0a61f2edc7efde332154dc6f3545e03394635737552df4fecb
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7521782a5874a8c21ae024658e0c02f59d66f7eb9a3acad546da3fddd692a3
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8366215dffbd63174077be1231ee70e87f021ffca8910618e93d26b5e4c45c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd02c6bfecd03b67f7114f8aadb9346cf17a57d8ec1cb14f3f019d44fd417cd5
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": 1.2262212038040161,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.13582342954159593,
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": 16.349,
732
  "eval_steps_per_second": 4.087,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.054998217156198e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1833840608596802,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.2037351443123939,
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": 16.349,
732
  "eval_steps_per_second": 4.087,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.13718166383701189,
737
+ "grad_norm": 0.5559870600700378,
738
+ "learning_rate": 8.715724127386972e-05,
739
+ "loss": 1.2997,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.13853989813242784,
744
+ "grad_norm": 0.4555906057357788,
745
+ "learning_rate": 8.688653405904652e-05,
746
+ "loss": 1.301,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1398981324278438,
751
+ "grad_norm": 0.31413426995277405,
752
+ "learning_rate": 8.661343332988869e-05,
753
+ "loss": 1.2188,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.14125636672325975,
758
+ "grad_norm": 0.2615854740142822,
759
+ "learning_rate": 8.633795680751116e-05,
760
+ "loss": 1.1284,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.14261460101867574,
765
+ "grad_norm": 0.2208709567785263,
766
+ "learning_rate": 8.606012236719073e-05,
767
+ "loss": 1.2063,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1439728353140917,
772
+ "grad_norm": 0.20494621992111206,
773
+ "learning_rate": 8.577994803720606e-05,
774
+ "loss": 1.2157,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.14533106960950765,
779
+ "grad_norm": 0.2158403843641281,
780
+ "learning_rate": 8.549745199766792e-05,
781
+ "loss": 1.1396,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1466893039049236,
786
+ "grad_norm": 0.22656506299972534,
787
+ "learning_rate": 8.521265257933948e-05,
788
+ "loss": 1.1591,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.14804753820033956,
793
+ "grad_norm": 0.23627708852291107,
794
+ "learning_rate": 8.492556826244687e-05,
795
+ "loss": 1.1998,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1494057724957555,
800
+ "grad_norm": 0.23139552772045135,
801
+ "learning_rate": 8.463621767547998e-05,
802
+ "loss": 1.2165,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.15076400679117147,
807
+ "grad_norm": 0.237015500664711,
808
+ "learning_rate": 8.434461959398376e-05,
809
+ "loss": 1.1609,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.15212224108658742,
814
+ "grad_norm": 0.2324032187461853,
815
+ "learning_rate": 8.405079293933986e-05,
816
+ "loss": 1.2107,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1534804753820034,
821
+ "grad_norm": 0.22056780755519867,
822
+ "learning_rate": 8.375475677753881e-05,
823
+ "loss": 1.1398,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.15483870967741936,
828
+ "grad_norm": 0.21998582780361176,
829
+ "learning_rate": 8.345653031794292e-05,
830
+ "loss": 1.1788,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.15619694397283532,
835
+ "grad_norm": 0.220359206199646,
836
+ "learning_rate": 8.315613291203976e-05,
837
+ "loss": 1.2086,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.15755517826825127,
842
+ "grad_norm": 0.2111772894859314,
843
+ "learning_rate": 8.285358405218655e-05,
844
+ "loss": 1.1961,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.15891341256366723,
849
+ "grad_norm": 0.21595050394535065,
850
+ "learning_rate": 8.25489033703452e-05,
851
+ "loss": 1.2173,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.16027164685908318,
856
+ "grad_norm": 0.22538748383522034,
857
+ "learning_rate": 8.224211063680853e-05,
858
+ "loss": 1.1223,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.16162988115449914,
863
+ "grad_norm": 0.22196736931800842,
864
+ "learning_rate": 8.19332257589174e-05,
865
+ "loss": 1.1796,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.16298811544991512,
870
+ "grad_norm": 0.22292838990688324,
871
+ "learning_rate": 8.162226877976887e-05,
872
+ "loss": 1.1198,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.16434634974533108,
877
+ "grad_norm": 0.22580811381340027,
878
+ "learning_rate": 8.130925987691569e-05,
879
+ "loss": 1.1997,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.16570458404074703,
884
+ "grad_norm": 0.22446706891059875,
885
+ "learning_rate": 8.099421936105702e-05,
886
+ "loss": 1.0938,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.167062818336163,
891
+ "grad_norm": 0.24063196778297424,
892
+ "learning_rate": 8.067716767472045e-05,
893
+ "loss": 1.272,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.16842105263157894,
898
+ "grad_norm": 0.2342248260974884,
899
+ "learning_rate": 8.035812539093557e-05,
900
+ "loss": 1.1282,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1697792869269949,
905
+ "grad_norm": 0.23322924971580505,
906
+ "learning_rate": 8.003711321189895e-05,
907
+ "loss": 1.1774,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.17113752122241085,
912
+ "grad_norm": 0.227143794298172,
913
+ "learning_rate": 7.971415196763088e-05,
914
+ "loss": 1.1614,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.17249575551782684,
919
+ "grad_norm": 0.2375260442495346,
920
+ "learning_rate": 7.938926261462366e-05,
921
+ "loss": 1.0878,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1738539898132428,
926
+ "grad_norm": 0.23172912001609802,
927
+ "learning_rate": 7.906246623448183e-05,
928
+ "loss": 1.114,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.17521222410865875,
933
+ "grad_norm": 0.2283349484205246,
934
+ "learning_rate": 7.873378403255419e-05,
935
+ "loss": 1.1243,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1765704584040747,
940
+ "grad_norm": 0.22897659242153168,
941
+ "learning_rate": 7.840323733655778e-05,
942
+ "loss": 1.1494,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.17792869269949066,
947
+ "grad_norm": 0.2336939573287964,
948
+ "learning_rate": 7.807084759519405e-05,
949
+ "loss": 1.2519,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.17928692699490661,
954
+ "grad_norm": 0.23826266825199127,
955
+ "learning_rate": 7.773663637675694e-05,
956
+ "loss": 1.1086,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.18064516129032257,
961
+ "grad_norm": 0.2425377517938614,
962
+ "learning_rate": 7.740062536773352e-05,
963
+ "loss": 1.1654,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.18200339558573855,
968
+ "grad_norm": 0.2372315227985382,
969
+ "learning_rate": 7.706283637139658e-05,
970
+ "loss": 1.1962,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1833616298811545,
975
+ "grad_norm": 0.24342741072177887,
976
+ "learning_rate": 7.672329130639005e-05,
977
+ "loss": 1.1181,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.18471986417657046,
982
+ "grad_norm": 0.2434910535812378,
983
+ "learning_rate": 7.638201220530665e-05,
984
+ "loss": 1.2285,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.18607809847198642,
989
+ "grad_norm": 0.24890004098415375,
990
+ "learning_rate": 7.603902121325813e-05,
991
+ "loss": 1.1714,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.18743633276740237,
996
+ "grad_norm": 0.25163108110427856,
997
+ "learning_rate": 7.569434058643844e-05,
998
+ "loss": 1.1956,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.18879456706281833,
1003
+ "grad_norm": 0.24931834638118744,
1004
+ "learning_rate": 7.534799269067953e-05,
1005
+ "loss": 1.1483,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.19015280135823429,
1010
+ "grad_norm": 0.25025516748428345,
1011
+ "learning_rate": 7.500000000000001e-05,
1012
+ "loss": 1.2085,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.19151103565365024,
1017
+ "grad_norm": 0.2583712339401245,
1018
+ "learning_rate": 7.465038509514688e-05,
1019
+ "loss": 1.2139,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.19286926994906622,
1024
+ "grad_norm": 0.26586151123046875,
1025
+ "learning_rate": 7.42991706621303e-05,
1026
+ "loss": 1.2006,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.19422750424448218,
1031
+ "grad_norm": 0.2643159031867981,
1032
+ "learning_rate": 7.394637949075154e-05,
1033
+ "loss": 1.1739,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.19558573853989814,
1038
+ "grad_norm": 0.2751873731613159,
1039
+ "learning_rate": 7.35920344731241e-05,
1040
+ "loss": 1.2109,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.1969439728353141,
1045
+ "grad_norm": 0.2727619707584381,
1046
+ "learning_rate": 7.323615860218843e-05,
1047
+ "loss": 1.1851,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.19830220713073005,
1052
+ "grad_norm": 0.2831723690032959,
1053
+ "learning_rate": 7.287877497021978e-05,
1054
+ "loss": 1.1864,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.199660441426146,
1059
+ "grad_norm": 0.28427502512931824,
1060
+ "learning_rate": 7.251990676732984e-05,
1061
+ "loss": 1.1347,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.20101867572156196,
1066
+ "grad_norm": 0.2935657203197479,
1067
+ "learning_rate": 7.215957727996207e-05,
1068
+ "loss": 1.1435,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.20237691001697794,
1073
+ "grad_norm": 0.3436415195465088,
1074
+ "learning_rate": 7.179780988938051e-05,
1075
+ "loss": 1.182,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2037351443123939,
1080
+ "grad_norm": 0.41627824306488037,
1081
+ "learning_rate": 7.143462807015271e-05,
1082
+ "loss": 1.2069,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2037351443123939,
1087
+ "eval_loss": 1.1833840608596802,
1088
+ "eval_runtime": 75.9037,
1089
+ "eval_samples_per_second": 16.336,
1090
+ "eval_steps_per_second": 4.084,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2025166377569485e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null