prxy5604 commited on
Commit
0ebe507
·
verified ·
1 Parent(s): 1215a77

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:dfa88c949b98ad1431afba1e62e4cdd515cb36e99b4d5d92aa0d106f8c3f1fca
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0773a762b8b99fa5d95b544493e77fa1acab1d7d6768a199a6822bc16868fe
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67b490e3109c41f066faa1e0546061b897cff410a8797a0840f2fa3daf38d2cf
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ba7ab55756715c15abf6c7f8e4524af4ebbd86d381133583933613be15a672
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fa119557e709f25237eb7de58a5e0561b78756f065a809e07702d31bbd62f20
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b223f2d23c8cf87f9d297844b9a444f538e1825d9092fa0a6877185824ba901a
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": 1.0070159435272217,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.32679738562091504,
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": 41.842,
732
  "eval_steps_per_second": 10.481,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.4637857696055296e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9922726154327393,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.49019607843137253,
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": 41.842,
732
  "eval_steps_per_second": 10.481,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3300653594771242,
737
+ "grad_norm": 0.184713214635849,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1821,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3333333333333333,
744
+ "grad_norm": 0.16883322596549988,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.1243,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.3366013071895425,
751
+ "grad_norm": 0.1671701818704605,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.0867,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.33986928104575165,
758
+ "grad_norm": 0.15528738498687744,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0852,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3431372549019608,
765
+ "grad_norm": 0.15602558851242065,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.0716,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3464052287581699,
772
+ "grad_norm": 0.13668398559093475,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0536,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.34967320261437906,
779
+ "grad_norm": 0.1294436901807785,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.9405,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.35294117647058826,
786
+ "grad_norm": 0.12812989950180054,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.0272,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.3562091503267974,
793
+ "grad_norm": 0.1318708062171936,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0285,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.35947712418300654,
800
+ "grad_norm": 0.1318873167037964,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.0436,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.3627450980392157,
807
+ "grad_norm": 0.13608375191688538,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0168,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3660130718954248,
814
+ "grad_norm": 0.13542938232421875,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0793,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.369281045751634,
821
+ "grad_norm": 0.14122723042964935,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0175,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.37254901960784315,
828
+ "grad_norm": 0.13928431272506714,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9935,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.3758169934640523,
835
+ "grad_norm": 0.14117971062660217,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9638,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3790849673202614,
842
+ "grad_norm": 0.14064086973667145,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0097,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.38235294117647056,
849
+ "grad_norm": 0.1440376192331314,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9901,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.38562091503267976,
856
+ "grad_norm": 0.13447478413581848,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.0247,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.3888888888888889,
863
+ "grad_norm": 0.1368880420923233,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0189,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.39215686274509803,
870
+ "grad_norm": 0.1322520673274994,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0052,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.3954248366013072,
877
+ "grad_norm": 0.13966742157936096,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.042,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.39869281045751637,
884
+ "grad_norm": 0.12975157797336578,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9768,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4019607843137255,
891
+ "grad_norm": 0.13822442293167114,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.0098,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.40522875816993464,
898
+ "grad_norm": 0.1365102380514145,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9441,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4084967320261438,
905
+ "grad_norm": 0.13646253943443298,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9881,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4117647058823529,
912
+ "grad_norm": 0.13747969269752502,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.056,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4150326797385621,
919
+ "grad_norm": 0.13940247893333435,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.9747,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.41830065359477125,
926
+ "grad_norm": 0.13401050865650177,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0157,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4215686274509804,
933
+ "grad_norm": 0.13685061037540436,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0059,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.42483660130718953,
940
+ "grad_norm": 0.13194219768047333,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.9569,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.42810457516339867,
947
+ "grad_norm": 0.13972924649715424,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9642,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.43137254901960786,
954
+ "grad_norm": 0.13786868751049042,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9932,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.434640522875817,
961
+ "grad_norm": 0.14051565527915955,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.9972,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.43790849673202614,
968
+ "grad_norm": 0.141611710190773,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0209,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4411764705882353,
975
+ "grad_norm": 0.1423238068819046,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.9516,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4444444444444444,
982
+ "grad_norm": 0.14845594763755798,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.9477,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4477124183006536,
989
+ "grad_norm": 0.14403949677944183,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.0214,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.45098039215686275,
996
+ "grad_norm": 0.14817410707473755,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.9928,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.4542483660130719,
1003
+ "grad_norm": 0.15064844489097595,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0206,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.45751633986928103,
1010
+ "grad_norm": 0.14492543041706085,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9473,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.46078431372549017,
1017
+ "grad_norm": 0.14751087129116058,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.8948,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.46405228758169936,
1024
+ "grad_norm": 0.14993497729301453,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.9734,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4673202614379085,
1031
+ "grad_norm": 0.1499774307012558,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9313,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.47058823529411764,
1038
+ "grad_norm": 0.159506157040596,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.9449,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4738562091503268,
1045
+ "grad_norm": 0.15356262028217316,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9332,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.477124183006536,
1052
+ "grad_norm": 0.1673261672258377,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0145,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4803921568627451,
1059
+ "grad_norm": 0.16216711699962616,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.9091,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.48366013071895425,
1066
+ "grad_norm": 0.17228259146213531,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.9386,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.4869281045751634,
1073
+ "grad_norm": 0.1875411570072174,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9501,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.49019607843137253,
1080
+ "grad_norm": 0.31840279698371887,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.8351,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.49019607843137253,
1087
+ "eval_loss": 0.9922726154327393,
1088
+ "eval_runtime": 12.3126,
1089
+ "eval_samples_per_second": 41.827,
1090
+ "eval_steps_per_second": 10.477,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.717010132933018e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null