aleegis10 commited on
Commit
8dfd4ea
·
verified ·
1 Parent(s): 87a3b3b

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 sha256:1cd82664da094b599f7c71bb53bd899f41bdb2554328ad728d1a43a771708b76
3
  size 226532664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec55e2325a949c900f2bc2e61c0229ed58a1a174de694c440b8a90945f68bf7b
3
  size 226532664
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a90f28d8577454ddb581f1a433d9097398034f38525cd48169339047b57f2f
3
  size 115354708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30f6c946d4833af0dddcb16e0e1146cff712add7c3223c237b61b248abe4aa1
3
  size 115354708
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6035d9004af696ae5e1bc35c8e65c34b607c4e5264ea65faf6547ecb4c87e31
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd12b7bc2f7eac4a210114f4aeeed6a891c704f0abe888a0d1560a91a281b7d2
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": 2.2455861568450928,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07855459544383346,
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": 51.139,
732
  "eval_steps_per_second": 12.785,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.48753499930624e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1957271099090576,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1178318931657502,
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": 51.139,
732
  "eval_steps_per_second": 12.785,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0793401413982718,
737
+ "grad_norm": 12.604543685913086,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 10.5349,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08012568735271014,
744
+ "grad_norm": 12.975698471069336,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 9.552,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08091123330714847,
751
+ "grad_norm": 11.618823051452637,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 10.1759,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0816967792615868,
758
+ "grad_norm": 10.762922286987305,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 9.4778,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08248232521602514,
765
+ "grad_norm": 10.559846878051758,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.1414,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08326787117046347,
772
+ "grad_norm": 8.871981620788574,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 8.8772,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0840534171249018,
779
+ "grad_norm": 8.570491790771484,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 9.0475,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08483896307934014,
786
+ "grad_norm": 8.62580680847168,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 9.0189,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08562450903377848,
793
+ "grad_norm": 7.929637432098389,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.6152,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08641005498821681,
800
+ "grad_norm": 8.455918312072754,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 9.1007,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08719560094265515,
807
+ "grad_norm": 8.789467811584473,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 9.1613,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08798114689709348,
814
+ "grad_norm": 7.669537544250488,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 9.366,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08876669285153181,
821
+ "grad_norm": 10.022933959960938,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 8.7371,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08955223880597014,
828
+ "grad_norm": 6.977982044219971,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 8.3784,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09033778476040849,
835
+ "grad_norm": 7.774967193603516,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 8.1028,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09112333071484682,
842
+ "grad_norm": 7.518317699432373,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 8.1503,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09190887666928516,
849
+ "grad_norm": 8.686746597290039,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 8.4072,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09269442262372349,
856
+ "grad_norm": 7.320336818695068,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 8.7316,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09347996857816182,
863
+ "grad_norm": 8.401020050048828,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 8.3795,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09426551453260015,
870
+ "grad_norm": 8.351461410522461,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 8.3938,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09505106048703849,
877
+ "grad_norm": 7.415112495422363,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 7.8384,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09583660644147683,
884
+ "grad_norm": 8.294906616210938,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 8.9706,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09662215239591516,
891
+ "grad_norm": 8.841975212097168,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 8.7504,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0974076983503535,
898
+ "grad_norm": 8.693595886230469,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 9.6779,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09819324430479183,
905
+ "grad_norm": 7.786905765533447,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 8.1271,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09897879025923016,
912
+ "grad_norm": 7.634393692016602,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 8.7359,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0997643362136685,
919
+ "grad_norm": 7.668099403381348,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.6546,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10054988216810684,
926
+ "grad_norm": 7.765418529510498,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 8.2512,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10133542812254517,
933
+ "grad_norm": 7.825764179229736,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 8.7348,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1021209740769835,
940
+ "grad_norm": 8.585892677307129,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 8.8134,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.10290652003142184,
947
+ "grad_norm": 8.444032669067383,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 9.2033,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10369206598586017,
954
+ "grad_norm": 8.120606422424316,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 8.6813,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1044776119402985,
961
+ "grad_norm": 8.226983070373535,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 8.4219,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10526315789473684,
968
+ "grad_norm": 8.079105377197266,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.4639,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10604870384917518,
975
+ "grad_norm": 8.742115020751953,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 8.774,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10683424980361352,
982
+ "grad_norm": 8.329201698303223,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.012,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10761979575805185,
989
+ "grad_norm": 7.8153862953186035,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 8.3099,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10840534171249018,
996
+ "grad_norm": 7.9953508377075195,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 7.9009,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10919088766692851,
1003
+ "grad_norm": 7.998071193695068,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 8.482,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.10997643362136685,
1010
+ "grad_norm": 7.762322902679443,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 8.4567,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11076197957580518,
1017
+ "grad_norm": 8.578129768371582,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 7.8857,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11154752553024352,
1024
+ "grad_norm": 17.240890502929688,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 8.4809,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11233307148468186,
1031
+ "grad_norm": 8.905219078063965,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 8.438,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11311861743912019,
1038
+ "grad_norm": 8.852285385131836,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 8.6253,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11390416339355852,
1045
+ "grad_norm": 10.754981994628906,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 10.1772,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11468970934799685,
1052
+ "grad_norm": 10.300592422485352,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 8.7962,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11547525530243519,
1059
+ "grad_norm": 9.20134449005127,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 9.0638,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11626080125687353,
1066
+ "grad_norm": 9.793197631835938,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 8.5398,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11704634721131187,
1073
+ "grad_norm": 12.644885063171387,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.7453,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1178318931657502,
1080
+ "grad_norm": 13.801067352294922,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 10.1863,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1178318931657502,
1087
+ "eval_loss": 2.1957271099090576,
1088
+ "eval_runtime": 41.9278,
1089
+ "eval_samples_per_second": 51.136,
1090
+ "eval_steps_per_second": 12.784,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.73130249895936e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null