0x1202 commited on
Commit
59bf446
·
verified ·
1 Parent(s): 29f7e67

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 sha256:4bec2bc64b43de0faff3b835c5bf83b031d573b08ea28ab2bbb3a183f431f0d3
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c56c7f2935b491eb0926309417fb9ca46e99bdce7417d79251bff2f2e0f009
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9caffc0f18bf9eca7fd3e757c4e0031bbea1eb8487f7e92a5c7fa5fbb0f05cf6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74950b626114b776eb2adf04bc2948c15ec870fe344b35e2ad4c8d481561832e
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:ed955d209c4ae3cabe88b3aacb8d1e6c1a1d2b90241e1e928ad7a23d584a1087
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8c5dbb432fe619f0e82b22f672366837aa9c9b7855e46a05c933524b8fb4f3
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": 0.7096530795097351,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07791195948578107,
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": 13.096,
732
  "eval_steps_per_second": 3.277,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5122848626927206e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6910772919654846,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1168679392286716,
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": 13.096,
732
  "eval_steps_per_second": 3.277,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07869107908063888,
737
+ "grad_norm": 0.6954978704452515,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.744,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07947019867549669,
744
+ "grad_norm": 0.6375919580459595,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.6658,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0802493182703545,
751
+ "grad_norm": 0.5256960391998291,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.453,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08102843786521231,
758
+ "grad_norm": 0.5784470438957214,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.4609,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08180755746007012,
765
+ "grad_norm": 0.7667689919471741,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.5884,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08258667705492793,
772
+ "grad_norm": 0.7474583983421326,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.5678,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08336579664978574,
779
+ "grad_norm": 0.606269896030426,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.4151,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08414491624464356,
786
+ "grad_norm": 1.0019197463989258,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.6818,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08492403583950137,
793
+ "grad_norm": 1.0073875188827515,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.6309,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08570315543435918,
800
+ "grad_norm": 0.8935511112213135,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.6305,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08648227502921699,
807
+ "grad_norm": 0.7624496221542358,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.4602,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0872613946240748,
814
+ "grad_norm": 1.4252090454101562,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8574,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08804051421893261,
821
+ "grad_norm": 0.9349772334098816,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.5872,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08881963381379042,
828
+ "grad_norm": 0.7691337466239929,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4455,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08959875340864823,
835
+ "grad_norm": 0.8447167873382568,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.6966,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09037787300350604,
842
+ "grad_norm": 0.8726719617843628,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.4893,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09115699259836385,
849
+ "grad_norm": 0.8984177112579346,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.5922,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09193611219322166,
856
+ "grad_norm": 1.1984186172485352,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7462,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09271523178807947,
863
+ "grad_norm": 0.906705915927887,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.5035,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09349435138293728,
870
+ "grad_norm": 1.0962584018707275,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7058,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09427347097779509,
877
+ "grad_norm": 1.3912545442581177,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8249,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0950525905726529,
884
+ "grad_norm": 1.846705436706543,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8236,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09583171016751071,
891
+ "grad_norm": 1.1177746057510376,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.6809,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09661082976236852,
898
+ "grad_norm": 1.1306052207946777,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7495,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09738994935722634,
905
+ "grad_norm": 1.2963117361068726,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7833,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09816906895208415,
912
+ "grad_norm": 1.239415168762207,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.5055,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.09894818854694196,
919
+ "grad_norm": 0.9889114499092102,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.6577,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.09972730814179977,
926
+ "grad_norm": 1.475911259651184,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.8122,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10050642773665758,
933
+ "grad_norm": 1.3534642457962036,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6979,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.10128554733151539,
940
+ "grad_norm": 0.935779333114624,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.5987,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1020646669263732,
947
+ "grad_norm": 1.366776466369629,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7755,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10284378652123101,
954
+ "grad_norm": 1.1041908264160156,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.6515,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10362290611608882,
961
+ "grad_norm": 1.0831820964813232,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7518,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10440202571094663,
968
+ "grad_norm": 1.2963292598724365,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7511,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10518114530580444,
975
+ "grad_norm": 1.1479302644729614,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.5344,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10596026490066225,
982
+ "grad_norm": 1.2546635866165161,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7483,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10673938449552006,
989
+ "grad_norm": 1.1935690641403198,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.6237,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10751850409037787,
996
+ "grad_norm": 1.1862212419509888,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4676,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10829762368523568,
1003
+ "grad_norm": 1.5882529020309448,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.6818,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1090767432800935,
1010
+ "grad_norm": 1.4618513584136963,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.8551,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1098558628749513,
1017
+ "grad_norm": 1.5193032026290894,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.8568,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11063498246980911,
1024
+ "grad_norm": 2.0033516883850098,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.9242,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11141410206466693,
1031
+ "grad_norm": 1.8691881895065308,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.8573,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11219322165952474,
1038
+ "grad_norm": 1.8360486030578613,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0104,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11297234125438255,
1045
+ "grad_norm": 1.311622142791748,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.638,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11375146084924036,
1052
+ "grad_norm": 1.7371994256973267,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.051,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11453058044409817,
1059
+ "grad_norm": 1.1233638525009155,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6505,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11530970003895598,
1066
+ "grad_norm": 1.392989993095398,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.63,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11608881963381379,
1073
+ "grad_norm": 1.106126070022583,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5245,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1168679392286716,
1080
+ "grad_norm": 1.4793016910552979,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.5887,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1168679392286716,
1087
+ "eval_loss": 0.6910772919654846,
1088
+ "eval_runtime": 165.1707,
1089
+ "eval_samples_per_second": 13.089,
1090
+ "eval_steps_per_second": 3.275,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2665416520656486e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null