0x1202 commited on
Commit
b874161
·
verified ·
1 Parent(s): 6f446c0

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 sha256:7d6d046de4ff6b0fd32bee203830af543cc8635c555c0bbbf72ac6e20e85fa7c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbfd44c0ffc617387492813b075c12e15a5a3010836e6f9d5d0c734e6532fbcc
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8374457a69b35808d34e1c4f021923d1cf8d8d196f9303ff5410adbb0ea756dd
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2b223b93e37306a5dd1b68379d83e0e2ee82421a5f6f7ec8493586094821c67
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68d4a279032806da36d9826e577f4932af193d3891ec3782a5b4aba1c2d60ee9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f00f208ec460fd9844caad242b2be97b1321847b2935fa80ac1b2033e50276
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": 1.3847177028656006,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.016208112160136148,
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": 10.091,
732
  "eval_steps_per_second": 2.523,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.8226703675424768e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.313240647315979,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.024312168240204223,
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": 10.091,
732
  "eval_steps_per_second": 2.523,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01637019328173751,
737
+ "grad_norm": 4.2005791664123535,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.9015,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.016532274403338872,
744
+ "grad_norm": 3.48933744430542,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.3167,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01669435552494023,
751
+ "grad_norm": 3.365427255630493,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.4929,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.016856436646541594,
758
+ "grad_norm": 3.3781585693359375,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.9119,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.017018517768142956,
765
+ "grad_norm": 3.499401807785034,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.0897,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.017180598889744318,
772
+ "grad_norm": 3.4389567375183105,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.0629,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.017342680011345677,
779
+ "grad_norm": 3.493772029876709,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.9737,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01750476113294704,
786
+ "grad_norm": 3.5260846614837646,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.9115,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.017666842254548402,
793
+ "grad_norm": 3.542769193649292,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.0926,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.017828923376149764,
800
+ "grad_norm": 3.4510931968688965,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.1305,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.017991004497751123,
807
+ "grad_norm": 3.4425296783447266,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.0381,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.018153085619352485,
814
+ "grad_norm": 3.593886137008667,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.0233,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.018315166740953848,
821
+ "grad_norm": 3.619311809539795,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.9667,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01847724786255521,
828
+ "grad_norm": 3.6048331260681152,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.0864,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01863932898415657,
835
+ "grad_norm": 3.5712852478027344,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.9163,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01880141010575793,
842
+ "grad_norm": 4.003663539886475,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.2713,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.018963491227359294,
849
+ "grad_norm": 3.878546953201294,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.9272,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.019125572348960656,
856
+ "grad_norm": 3.715549945831299,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.9297,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019287653470562015,
863
+ "grad_norm": 3.861307144165039,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.0783,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.019449734592163377,
870
+ "grad_norm": 3.8011298179626465,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.9478,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01961181571376474,
877
+ "grad_norm": 3.8588430881500244,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.0608,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.019773896835366102,
884
+ "grad_norm": 4.052944660186768,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.1274,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.01993597795696746,
891
+ "grad_norm": 3.9233617782592773,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.0635,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.020098059078568823,
898
+ "grad_norm": 3.8510828018188477,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.0339,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020260140200170185,
905
+ "grad_norm": 4.156836032867432,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.1914,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020422221321771548,
912
+ "grad_norm": 4.0888471603393555,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.4011,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.020584302443372907,
919
+ "grad_norm": 4.1924028396606445,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.1957,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02074638356497427,
926
+ "grad_norm": 4.259236812591553,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.1416,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.02090846468657563,
933
+ "grad_norm": 4.339385509490967,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.3724,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.021070545808176994,
940
+ "grad_norm": 4.363649845123291,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.3802,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.021232626929778353,
947
+ "grad_norm": 4.244985103607178,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.8814,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.021394708051379715,
954
+ "grad_norm": 4.618222713470459,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.4262,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.021556789172981077,
961
+ "grad_norm": 4.758816242218018,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.2982,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02171887029458244,
968
+ "grad_norm": 4.659364223480225,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.2061,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0218809514161838,
975
+ "grad_norm": 4.976042747497559,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.2508,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02204303253778516,
982
+ "grad_norm": 4.979991912841797,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.3716,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.022205113659386523,
989
+ "grad_norm": 4.848566055297852,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.3942,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.022367194780987885,
996
+ "grad_norm": 5.319351673126221,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.2437,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022529275902589244,
1003
+ "grad_norm": 5.115017890930176,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.4039,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.022691357024190607,
1010
+ "grad_norm": 5.578060626983643,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.2967,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02285343814579197,
1017
+ "grad_norm": 5.800137042999268,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.972,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02301551926739333,
1024
+ "grad_norm": 6.258816242218018,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 6.232,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02317760038899469,
1031
+ "grad_norm": 6.430749893188477,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.7707,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.023339681510596053,
1038
+ "grad_norm": 6.416401386260986,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.7204,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.023501762632197415,
1045
+ "grad_norm": 7.269473075866699,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 6.021,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.023663843753798777,
1052
+ "grad_norm": 7.365699768066406,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.6886,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.023825924875400136,
1059
+ "grad_norm": 7.84915828704834,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.7911,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0239880059970015,
1066
+ "grad_norm": 9.239398956298828,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 6.2228,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02415008711860286,
1073
+ "grad_norm": 10.24454402923584,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.6922,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.024312168240204223,
1080
+ "grad_norm": 14.783937454223633,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.2486,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.024312168240204223,
1087
+ "eval_loss": 1.313240647315979,
1088
+ "eval_runtime": 1031.1636,
1089
+ "eval_samples_per_second": 10.078,
1090
+ "eval_steps_per_second": 2.519,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.7394194236925542e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null