bbytxt commited on
Commit
9dee3d5
·
verified ·
1 Parent(s): 3c08d47

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 sha256:8673285cb30ce5b9fadffc615f856aba8af8140d3a8875a53e1bda7913dd42f6
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00524af72925c355978706e3f58b93389758d9f046f54a15a00c3100a169838d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1be0e735eddbd6afc3dd1047e689cdaa7262a6f3594971b83d364d24c519b2b7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36971486421bd29362bf1c47e7761845fa83433861642e4e89287187635cd9fc
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:dca0b41f70ae0368efc2e01d22581d09d32c705050718ae34ed3620569ea6856
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14d1dcc42e070bd2ba045b5574706b21dd179cb9ac496d7cebbb9d24c9ae2a8
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": 0.8521695733070374,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0033863580565691113,
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": 11.37,
732
  "eval_steps_per_second": 2.843,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5313565367926784e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8154168128967285,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.005079537084853667,
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": 11.37,
732
  "eval_steps_per_second": 2.843,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0034202216371348026,
737
+ "grad_norm": 1.1458899974822998,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.8591,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0034540852177004935,
744
+ "grad_norm": 1.172037959098816,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.327,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0034879487982661848,
751
+ "grad_norm": 0.9343804717063904,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9444,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0035218123788318756,
758
+ "grad_norm": 0.7813839316368103,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0259,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.003555675959397567,
765
+ "grad_norm": 0.7565736770629883,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.041,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0035895395399632582,
772
+ "grad_norm": 0.8008309006690979,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0422,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.003623403120528949,
779
+ "grad_norm": 0.7426912784576416,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0826,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0036572667010946404,
786
+ "grad_norm": 0.936414361000061,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9141,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0036911302816603313,
793
+ "grad_norm": 0.8418607115745544,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9935,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0037249938622260226,
800
+ "grad_norm": 0.920128345489502,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8894,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0037588574427917134,
807
+ "grad_norm": 1.1256664991378784,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9296,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0037927210233574048,
814
+ "grad_norm": 0.9914236664772034,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8955,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0038265846039230956,
821
+ "grad_norm": 0.86021488904953,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1076,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.003860448184488787,
828
+ "grad_norm": 0.8354436159133911,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9834,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0038943117650544782,
835
+ "grad_norm": 0.8657628893852234,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8908,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0039281753456201695,
842
+ "grad_norm": 0.855169415473938,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8587,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00396203892618586,
849
+ "grad_norm": 0.9482845067977905,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9064,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.003995902506751551,
856
+ "grad_norm": 0.8780611753463745,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.77,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.004029766087317243,
863
+ "grad_norm": 0.843481719493866,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7907,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004063629667882934,
870
+ "grad_norm": 0.817581832408905,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7699,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004097493248448624,
877
+ "grad_norm": 0.9872439503669739,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.7838,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.004131356829014316,
884
+ "grad_norm": 0.8429522514343262,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7741,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004165220409580007,
891
+ "grad_norm": 0.8456198573112488,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8308,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.004199083990145698,
898
+ "grad_norm": 0.836810290813446,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7197,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0042329475707113895,
905
+ "grad_norm": 0.8510724306106567,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7817,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.00426681115127708,
912
+ "grad_norm": 0.9283472299575806,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.7639,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.004300674731842771,
919
+ "grad_norm": 0.9334129095077515,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7159,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.004334538312408463,
926
+ "grad_norm": 0.8882057666778564,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7146,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.004368401892974154,
933
+ "grad_norm": 1.0052096843719482,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7436,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.004402265473539844,
940
+ "grad_norm": 1.036095380783081,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.7443,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.004436129054105536,
947
+ "grad_norm": 1.1256189346313477,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7056,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.004469992634671227,
954
+ "grad_norm": 1.1841328144073486,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.7057,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.004503856215236918,
961
+ "grad_norm": 1.177301287651062,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7923,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0045377197958026095,
968
+ "grad_norm": 1.3304249048233032,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7732,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0045715833763683,
975
+ "grad_norm": 1.3118896484375,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7544,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.004605446956933991,
982
+ "grad_norm": 1.5514614582061768,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8029,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.004639310537499683,
989
+ "grad_norm": 1.2711803913116455,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.753,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.004673174118065374,
996
+ "grad_norm": 1.4091942310333252,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8104,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.004707037698631065,
1003
+ "grad_norm": 1.648789405822754,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.763,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.004740901279196756,
1010
+ "grad_norm": 1.9252206087112427,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.7113,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.004774764859762447,
1017
+ "grad_norm": 1.8625355958938599,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7801,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.004808628440328138,
1024
+ "grad_norm": 1.736893653869629,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7988,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0048424920208938295,
1031
+ "grad_norm": 1.6877861022949219,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7038,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.00487635560145952,
1038
+ "grad_norm": 2.2004785537719727,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8114,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.004910219182025211,
1045
+ "grad_norm": 2.4584996700286865,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7978,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.004944082762590903,
1052
+ "grad_norm": 2.3921878337860107,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8769,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.004977946343156594,
1059
+ "grad_norm": 2.814528465270996,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6822,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.005011809923722285,
1066
+ "grad_norm": 2.679048538208008,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7034,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.005045673504287976,
1073
+ "grad_norm": 4.924661636352539,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.4983,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005079537084853667,
1080
+ "grad_norm": 3.6667542457580566,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.5527,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005079537084853667,
1087
+ "eval_loss": 0.8154168128967285,
1088
+ "eval_runtime": 4334.8234,
1089
+ "eval_samples_per_second": 11.473,
1090
+ "eval_steps_per_second": 2.868,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.295198646272e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null