nttx commited on
Commit
3ddecdc
·
verified ·
1 Parent(s): 404f11e

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 sha256:6c0bb592bda9cb2c46ec6da47b5adaa66da41732ec2d8c60e8de12a37566ae6b
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513125d507301ccd00d74712fa253a23b6ed2f53eff6f6c47ba4fe010afb37d0
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58801b3879ea9659a1361e631e085c6f40564719c65895b21096db37795b2113
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfd037edccc7631ccce3679e1cbaee3f1dfb658b02d0207e3e6d8d43c9fce6e
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8a50273e2c0884ecb0d7fb1230a0b527160c52eb1c35e2c19daa1b836d36278
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c498c7e1a5790569ac49106fdd6e068692119d9b1573def4630da7946c81c8b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6734322309494019,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.004620431548306611,
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": 38.367,
732
  "eval_steps_per_second": 19.184,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6971912733327360.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6421379446983337,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.006930647322459918,
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": 38.367,
732
  "eval_steps_per_second": 19.184,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.004666635863789678,
737
+ "grad_norm": 0.2588423788547516,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.7065,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0047128401792727445,
744
+ "grad_norm": 0.21197082102298737,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.2932,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004759044494755811,
751
+ "grad_norm": 0.22588442265987396,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.3405,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004805248810238877,
758
+ "grad_norm": 0.25069916248321533,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.4191,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.004851453125721943,
765
+ "grad_norm": 0.24258778989315033,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.355,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004897657441205009,
772
+ "grad_norm": 0.20508873462677002,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.3554,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004943861756688075,
779
+ "grad_norm": 0.2670445442199707,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.5443,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.004990066072171141,
786
+ "grad_norm": 0.24584536254405975,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.4639,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.005036270387654207,
793
+ "grad_norm": 0.2456938475370407,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.4195,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.005082474703137273,
800
+ "grad_norm": 0.25109416246414185,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.487,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.005128679018620339,
807
+ "grad_norm": 0.1877359002828598,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.4365,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0051748833341034054,
814
+ "grad_norm": 0.19817650318145752,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.327,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0052210876495864715,
821
+ "grad_norm": 0.198269784450531,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.4454,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.005267291965069538,
828
+ "grad_norm": 0.22586289048194885,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.4795,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.005313496280552604,
835
+ "grad_norm": 0.2628689706325531,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.4899,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.00535970059603567,
842
+ "grad_norm": 0.2354358434677124,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.4658,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.005405904911518736,
849
+ "grad_norm": 0.23226183652877808,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.5188,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.005452109227001802,
856
+ "grad_norm": 0.25832581520080566,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.482,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.005498313542484868,
863
+ "grad_norm": 0.21811699867248535,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.4764,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.005544517857967934,
870
+ "grad_norm": 0.19816286861896515,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.4253,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.005590722173451,
877
+ "grad_norm": 0.3619321286678314,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.5297,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.005636926488934066,
884
+ "grad_norm": 0.31721270084381104,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.5815,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0056831308044171325,
891
+ "grad_norm": 0.2503688633441925,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.5621,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.005729335119900199,
898
+ "grad_norm": 0.25126245617866516,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.3979,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.005775539435383265,
905
+ "grad_norm": 0.24463218450546265,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.5177,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.005821743750866331,
912
+ "grad_norm": 0.33323267102241516,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.5103,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.005867948066349397,
919
+ "grad_norm": 0.2861713171005249,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.5381,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.005914152381832463,
926
+ "grad_norm": 0.3225221037864685,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.6206,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.005960356697315529,
933
+ "grad_norm": 0.23997412621974945,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.4345,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.006006561012798595,
940
+ "grad_norm": 0.22723270952701569,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.5091,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.006052765328281661,
947
+ "grad_norm": 0.31986862421035767,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.5041,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.006098969643764727,
954
+ "grad_norm": 0.4289882481098175,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.6675,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0061451739592477935,
961
+ "grad_norm": 0.24950823187828064,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.5478,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00619137827473086,
968
+ "grad_norm": 0.292449027299881,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.5382,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.006237582590213926,
975
+ "grad_norm": 0.27559009194374084,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.5363,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.006283786905696992,
982
+ "grad_norm": 0.27184924483299255,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.6343,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.006329991221180058,
989
+ "grad_norm": 0.26460501551628113,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.5129,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.006376195536663124,
996
+ "grad_norm": 0.31789299845695496,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.5976,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.00642239985214619,
1003
+ "grad_norm": 0.3732602000236511,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.6542,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.006468604167629256,
1010
+ "grad_norm": 0.4154840111732483,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.6341,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.006514808483112323,
1017
+ "grad_norm": 0.43639206886291504,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.6507,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.006561012798595389,
1024
+ "grad_norm": 0.2488391399383545,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.5045,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.006607217114078455,
1031
+ "grad_norm": 0.2505655586719513,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.539,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.006653421429561521,
1038
+ "grad_norm": 0.3137003779411316,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.741,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0066996257450445875,
1045
+ "grad_norm": 0.4721606969833374,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.8028,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.006745830060527654,
1052
+ "grad_norm": 0.325411856174469,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.6541,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.00679203437601072,
1059
+ "grad_norm": 0.434574693441391,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.8358,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.006838238691493786,
1066
+ "grad_norm": 0.299848735332489,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.6771,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.006884443006976852,
1073
+ "grad_norm": 0.3632323741912842,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.8139,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.006930647322459918,
1080
+ "grad_norm": 0.3702452778816223,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.7374,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.006930647322459918,
1087
+ "eval_loss": 0.6421379446983337,
1088
+ "eval_runtime": 951.4779,
1089
+ "eval_samples_per_second": 38.31,
1090
+ "eval_steps_per_second": 19.155,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.045786909999104e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null