0x1202 commited on
Commit
ea2f07e
·
verified ·
1 Parent(s): aa75191

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 sha256:8d9fa2ff246ac17497e2a8ec383e3f5b8b3409950d836c8ebf74fcfdae773ed5
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a1d19127ac018695f61fc731664be5cb528d41cf54b7e3f06f33a063587250
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c77e5f4d02461c36f61863d91a7fdd3df17b83219e120b23befcf385c38e70b3
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aaf8089ce4e14f9702a0307921a8e5e89a4bf9d7265d155842879f45ae3d46f
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f05dc69ef0bffac0c7dad05d40261f8cc7fadec7a2b18286685c393506d06c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c727cd747bba7311ffc1f8fd4959b9f91c3e817caa148a63ad928eff25b7cf
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": 0.09879136830568314,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.084010840108401,
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": 42.258,
732
  "eval_steps_per_second": 10.565,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.634257793024e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.08209174126386642,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.6260162601626016,
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": 42.258,
732
  "eval_steps_per_second": 10.565,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.094850948509485,
737
+ "grad_norm": 0.4146367907524109,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0374,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1056910569105691,
744
+ "grad_norm": 0.36523959040641785,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.035,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1165311653116532,
751
+ "grad_norm": 0.3721497356891632,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0389,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.127371273712737,
758
+ "grad_norm": 0.2500871419906616,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0333,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.1382113821138211,
765
+ "grad_norm": 0.5672609210014343,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0445,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.1490514905149052,
772
+ "grad_norm": 0.5433923006057739,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0574,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.1598915989159893,
779
+ "grad_norm": 0.43868547677993774,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0306,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.170731707317073,
786
+ "grad_norm": 0.43001192808151245,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0389,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.1815718157181572,
793
+ "grad_norm": 0.18207843601703644,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0123,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.1924119241192412,
800
+ "grad_norm": 0.4550378620624542,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0243,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.203252032520325,
807
+ "grad_norm": 0.27300575375556946,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0098,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2140921409214092,
814
+ "grad_norm": 0.17592142522335052,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0104,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2249322493224932,
821
+ "grad_norm": 0.48420414328575134,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0202,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.2357723577235773,
828
+ "grad_norm": 1.371536135673523,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.1445,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.2466124661246614,
835
+ "grad_norm": 0.7464447617530823,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0311,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.2574525745257452,
842
+ "grad_norm": 1.5276039838790894,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.1417,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.2682926829268293,
849
+ "grad_norm": 0.26058825850486755,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0589,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.2791327913279134,
856
+ "grad_norm": 0.3222558796405792,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0245,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.2899728997289972,
863
+ "grad_norm": 0.44456252455711365,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0413,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.3008130081300813,
870
+ "grad_norm": 0.27726078033447266,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0523,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.3116531165311653,
877
+ "grad_norm": 0.5933356285095215,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0652,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.3224932249322494,
884
+ "grad_norm": 0.6122859120368958,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0435,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.3333333333333333,
891
+ "grad_norm": 0.8560364842414856,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0874,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.3441734417344173,
898
+ "grad_norm": 0.20532087981700897,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0102,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.3550135501355014,
905
+ "grad_norm": 0.7897826433181763,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0957,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.3658536585365852,
912
+ "grad_norm": 0.41313865780830383,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0335,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.3766937669376693,
919
+ "grad_norm": 0.2979642152786255,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0426,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.3875338753387534,
926
+ "grad_norm": 0.3756512701511383,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0628,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.3983739837398375,
933
+ "grad_norm": 0.5913124084472656,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.057,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.4092140921409215,
940
+ "grad_norm": 0.5157326459884644,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0371,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.4200542005420054,
947
+ "grad_norm": 0.39981499314308167,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0232,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.4308943089430894,
954
+ "grad_norm": 0.2877366244792938,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.015,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.4417344173441735,
961
+ "grad_norm": 0.16340596973896027,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0079,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.4525745257452574,
968
+ "grad_norm": 0.2619611322879791,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0171,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.4634146341463414,
975
+ "grad_norm": 1.1646555662155151,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0712,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.4742547425474255,
982
+ "grad_norm": 0.5431463122367859,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0385,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.4850948509485096,
989
+ "grad_norm": 0.19880428910255432,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0091,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.4959349593495934,
996
+ "grad_norm": 0.32186517119407654,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0166,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.5067750677506775,
1003
+ "grad_norm": 0.30488982796669006,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0523,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.5176151761517616,
1010
+ "grad_norm": 0.48191314935684204,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0501,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5284552845528454,
1017
+ "grad_norm": 0.45830032229423523,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0759,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.5392953929539295,
1024
+ "grad_norm": 0.2845216393470764,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0503,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.5501355013550135,
1031
+ "grad_norm": 0.3950357437133789,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.041,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.5609756097560976,
1038
+ "grad_norm": 0.27710777521133423,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0405,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.5718157181571817,
1045
+ "grad_norm": 0.14560440182685852,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0065,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.5826558265582655,
1052
+ "grad_norm": 0.6007800102233887,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0633,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.5934959349593496,
1059
+ "grad_norm": 0.3015676736831665,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.04,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.6043360433604335,
1066
+ "grad_norm": 0.39085838198661804,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0315,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.6151761517615175,
1073
+ "grad_norm": 0.47567927837371826,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.068,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.6260162601626016,
1080
+ "grad_norm": 0.25586554408073425,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0149,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.6260162601626016,
1087
+ "eval_loss": 0.08209174126386642,
1088
+ "eval_runtime": 3.6946,
1089
+ "eval_samples_per_second": 42.224,
1090
+ "eval_steps_per_second": 10.556,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.951386689536e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null