alchemist69 commited on
Commit
937f827
·
verified ·
1 Parent(s): d4cf133

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:f7955cd385df47f00bb23a4aafb46576dc7c405f3c515294e6f57ba4976a6b0e
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f670ac63a6e6cb8380604e7990e8807931075b80df6307ed6d27dee744ca0fa
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ced0fed4d3acc4ce51d89ee5663d1d48a6c63e656ee631e655a88e507618d62f
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0171647034896bdc2e219e48e3a59144d1d0ae45ce8740b549e873ea3556119b
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:578c9034391114abb274096907986a3fe624faa6a3bf1f52fd7205d69f9ea173
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2736acb6a2ef10df364cdc191b1326a76b7de282097399abed6b111c5628d51b
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": 1.3750338554382324,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.005614901949774702,
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": 60.149,
732
  "eval_steps_per_second": 15.038,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6868879540224000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3391810655593872,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.008422352924662053,
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": 60.149,
732
  "eval_steps_per_second": 15.038,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.005671050969272449,
737
+ "grad_norm": 0.5887877941131592,
738
+ "learning_rate": 8.715724127386972e-05,
739
+ "loss": 1.4701,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0057271999887701965,
744
+ "grad_norm": 0.533300518989563,
745
+ "learning_rate": 8.688653405904652e-05,
746
+ "loss": 1.4185,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.005783349008267943,
751
+ "grad_norm": 0.47831276059150696,
752
+ "learning_rate": 8.661343332988869e-05,
753
+ "loss": 1.4503,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.00583949802776569,
758
+ "grad_norm": 0.44194933772087097,
759
+ "learning_rate": 8.633795680751116e-05,
760
+ "loss": 1.4504,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0058956470472634375,
765
+ "grad_norm": 0.37259674072265625,
766
+ "learning_rate": 8.606012236719073e-05,
767
+ "loss": 1.3562,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.005951796066761184,
772
+ "grad_norm": 0.3651125431060791,
773
+ "learning_rate": 8.577994803720606e-05,
774
+ "loss": 1.363,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006007945086258931,
779
+ "grad_norm": 0.3322165608406067,
780
+ "learning_rate": 8.549745199766792e-05,
781
+ "loss": 1.3722,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0060640941057566785,
786
+ "grad_norm": 0.31796780228614807,
787
+ "learning_rate": 8.521265257933948e-05,
788
+ "loss": 1.3725,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006120243125254425,
793
+ "grad_norm": 0.3114439845085144,
794
+ "learning_rate": 8.492556826244687e-05,
795
+ "loss": 1.3041,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006176392144752172,
800
+ "grad_norm": 0.33855172991752625,
801
+ "learning_rate": 8.463621767547998e-05,
802
+ "loss": 1.3537,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0062325411642499195,
807
+ "grad_norm": 0.34555360674858093,
808
+ "learning_rate": 8.434461959398376e-05,
809
+ "loss": 1.4027,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.006288690183747666,
814
+ "grad_norm": 0.3324665129184723,
815
+ "learning_rate": 8.405079293933986e-05,
816
+ "loss": 1.4327,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.006344839203245413,
821
+ "grad_norm": 0.3820353150367737,
822
+ "learning_rate": 8.375475677753881e-05,
823
+ "loss": 1.4021,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0064009882227431605,
828
+ "grad_norm": 0.34804096817970276,
829
+ "learning_rate": 8.345653031794292e-05,
830
+ "loss": 1.3878,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.006457137242240907,
835
+ "grad_norm": 0.36230865120887756,
836
+ "learning_rate": 8.315613291203976e-05,
837
+ "loss": 1.4082,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.006513286261738654,
842
+ "grad_norm": 0.3718462884426117,
843
+ "learning_rate": 8.285358405218655e-05,
844
+ "loss": 1.3452,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0065694352812364016,
849
+ "grad_norm": 0.33835625648498535,
850
+ "learning_rate": 8.25489033703452e-05,
851
+ "loss": 1.3261,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.006625584300734149,
856
+ "grad_norm": 0.32900914549827576,
857
+ "learning_rate": 8.224211063680853e-05,
858
+ "loss": 1.2985,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.006681733320231895,
863
+ "grad_norm": 0.33768901228904724,
864
+ "learning_rate": 8.19332257589174e-05,
865
+ "loss": 1.3194,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.006737882339729643,
870
+ "grad_norm": 0.3272550106048584,
871
+ "learning_rate": 8.162226877976887e-05,
872
+ "loss": 1.2992,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00679403135922739,
877
+ "grad_norm": 0.3214387893676758,
878
+ "learning_rate": 8.130925987691569e-05,
879
+ "loss": 1.2775,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.006850180378725136,
884
+ "grad_norm": 0.3233121335506439,
885
+ "learning_rate": 8.099421936105702e-05,
886
+ "loss": 1.3604,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.006906329398222884,
891
+ "grad_norm": 0.3374609351158142,
892
+ "learning_rate": 8.067716767472045e-05,
893
+ "loss": 1.3658,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.006962478417720631,
898
+ "grad_norm": 0.32785022258758545,
899
+ "learning_rate": 8.035812539093557e-05,
900
+ "loss": 1.2985,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.007018627437218377,
905
+ "grad_norm": 0.3212898075580597,
906
+ "learning_rate": 8.003711321189895e-05,
907
+ "loss": 1.285,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007074776456716125,
912
+ "grad_norm": 0.34439992904663086,
913
+ "learning_rate": 7.971415196763088e-05,
914
+ "loss": 1.4653,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.007130925476213872,
919
+ "grad_norm": 0.34514302015304565,
920
+ "learning_rate": 7.938926261462366e-05,
921
+ "loss": 1.3337,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.007187074495711618,
926
+ "grad_norm": 0.38126933574676514,
927
+ "learning_rate": 7.906246623448183e-05,
928
+ "loss": 1.3511,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.007243223515209366,
933
+ "grad_norm": 0.34479570388793945,
934
+ "learning_rate": 7.873378403255419e-05,
935
+ "loss": 1.329,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.007299372534707113,
940
+ "grad_norm": 0.34173834323883057,
941
+ "learning_rate": 7.840323733655778e-05,
942
+ "loss": 1.3119,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.007355521554204859,
947
+ "grad_norm": 0.35819727182388306,
948
+ "learning_rate": 7.807084759519405e-05,
949
+ "loss": 1.3358,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.007411670573702607,
954
+ "grad_norm": 0.35329777002334595,
955
+ "learning_rate": 7.773663637675694e-05,
956
+ "loss": 1.3238,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.007467819593200354,
961
+ "grad_norm": 0.36197683215141296,
962
+ "learning_rate": 7.740062536773352e-05,
963
+ "loss": 1.2516,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0075239686126981,
968
+ "grad_norm": 0.36278480291366577,
969
+ "learning_rate": 7.706283637139658e-05,
970
+ "loss": 1.2106,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.007580117632195848,
975
+ "grad_norm": 0.36338376998901367,
976
+ "learning_rate": 7.672329130639005e-05,
977
+ "loss": 1.2502,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.007636266651693595,
982
+ "grad_norm": 0.369215190410614,
983
+ "learning_rate": 7.638201220530665e-05,
984
+ "loss": 1.3322,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.007692415671191341,
989
+ "grad_norm": 0.3735330104827881,
990
+ "learning_rate": 7.603902121325813e-05,
991
+ "loss": 1.2302,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.007748564690689089,
996
+ "grad_norm": 0.3798264265060425,
997
+ "learning_rate": 7.569434058643844e-05,
998
+ "loss": 1.4184,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.007804713710186836,
1003
+ "grad_norm": 0.3851505517959595,
1004
+ "learning_rate": 7.534799269067953e-05,
1005
+ "loss": 1.3757,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.007860862729684583,
1010
+ "grad_norm": 0.3895701467990875,
1011
+ "learning_rate": 7.500000000000001e-05,
1012
+ "loss": 1.2911,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00791701174918233,
1017
+ "grad_norm": 0.3997504711151123,
1018
+ "learning_rate": 7.465038509514688e-05,
1019
+ "loss": 1.3938,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.007973160768680076,
1024
+ "grad_norm": 0.3898596465587616,
1025
+ "learning_rate": 7.42991706621303e-05,
1026
+ "loss": 1.2683,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.008029309788177823,
1031
+ "grad_norm": 0.42272382974624634,
1032
+ "learning_rate": 7.394637949075154e-05,
1033
+ "loss": 1.3499,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.00808545880767557,
1038
+ "grad_norm": 0.3854672610759735,
1039
+ "learning_rate": 7.35920344731241e-05,
1040
+ "loss": 1.2151,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.008141607827173318,
1045
+ "grad_norm": 0.39451897144317627,
1046
+ "learning_rate": 7.323615860218843e-05,
1047
+ "loss": 1.2315,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.008197756846671065,
1052
+ "grad_norm": 0.4249548614025116,
1053
+ "learning_rate": 7.287877497021978e-05,
1054
+ "loss": 1.1785,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.008253905866168813,
1059
+ "grad_norm": 0.43391963839530945,
1060
+ "learning_rate": 7.251990676732984e-05,
1061
+ "loss": 1.1203,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.008310054885666558,
1066
+ "grad_norm": 0.45870715379714966,
1067
+ "learning_rate": 7.215957727996207e-05,
1068
+ "loss": 1.1546,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.008366203905164305,
1073
+ "grad_norm": 0.4571928083896637,
1074
+ "learning_rate": 7.179780988938051e-05,
1075
+ "loss": 1.1424,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.008422352924662053,
1080
+ "grad_norm": 0.5306082963943481,
1081
+ "learning_rate": 7.143462807015271e-05,
1082
+ "loss": 0.979,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.008422352924662053,
1087
+ "eval_loss": 1.3391810655593872,
1088
+ "eval_runtime": 499.3755,
1089
+ "eval_samples_per_second": 60.065,
1090
+ "eval_steps_per_second": 15.017,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0303319310336e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null