aleegis09 commited on
Commit
9028144
·
verified ·
1 Parent(s): 54e2419

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 sha256:1cdb938f94d59810542bfbd9c77671ae4ca0dc2450991fe2f478234eaa9649aa
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e50c1c801c9f4adcf1aadd51c7a30e0cb821ef7285afa2dd53a5fdc31eb73b1
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4c879b46379c9eb4001f789c1f8421cf6e3aff373bf9e82a5ea0f5af3cb23c6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0805cccf51704f9d2122782325fd954962912cf86c0eb2878d4237d2958e94
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a63b2e6cfa8e7c53a6078d8f283572bcc328e7348f57fcb91b3a529da9fcee4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec5da4e685b4cd075a6f0601cf5a6be35ae2fa90278badd4d104bd38853327b
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": 0.8006256818771362,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.13314447592068,
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": 13.039,
732
  "eval_steps_per_second": 3.325,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.519356020093092e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7515243291854858,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.6997167138810199,
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": 13.039,
732
  "eval_steps_per_second": 3.325,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.1444759206798867,
737
+ "grad_norm": 0.31149691343307495,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.6993,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.1558073654390935,
744
+ "grad_norm": 0.31584376096725464,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.7272,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.1671388101983002,
751
+ "grad_norm": 0.33238154649734497,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.7262,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.178470254957507,
758
+ "grad_norm": 0.34204113483428955,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7337,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.1898016997167138,
765
+ "grad_norm": 0.3630761504173279,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.748,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.2011331444759206,
772
+ "grad_norm": 0.3507816791534424,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.6793,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.2124645892351276,
779
+ "grad_norm": 0.40318283438682556,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.7535,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.2237960339943343,
786
+ "grad_norm": 0.4211021065711975,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7193,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.2351274787535411,
793
+ "grad_norm": 0.4252460300922394,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.7051,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.246458923512748,
800
+ "grad_norm": 0.6195134520530701,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.6238,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.2577903682719547,
807
+ "grad_norm": 0.3660491704940796,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.5634,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.2691218130311614,
814
+ "grad_norm": 0.46309658885002136,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7133,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.2804532577903682,
821
+ "grad_norm": 0.39401277899742126,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.716,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.291784702549575,
828
+ "grad_norm": 0.37151670455932617,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.7727,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.3031161473087818,
835
+ "grad_norm": 0.3559165596961975,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7659,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.3144475920679888,
842
+ "grad_norm": 0.3626144230365753,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.7037,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.3257790368271953,
849
+ "grad_norm": 0.3644079566001892,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.6993,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.3371104815864023,
856
+ "grad_norm": 0.37085551023483276,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7115,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.348441926345609,
863
+ "grad_norm": 0.3566945195198059,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7249,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.3597733711048159,
870
+ "grad_norm": 0.3588652014732361,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7622,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.3711048158640227,
877
+ "grad_norm": 0.34322044253349304,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.677,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.3824362606232294,
884
+ "grad_norm": 0.35693424940109253,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7196,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.3937677053824362,
891
+ "grad_norm": 0.3655772805213928,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7097,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.405099150141643,
898
+ "grad_norm": 0.3697783052921295,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.7266,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.41643059490085,
905
+ "grad_norm": 0.355410635471344,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.676,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.4277620396600565,
912
+ "grad_norm": 0.3988121449947357,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.7216,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.4390934844192635,
919
+ "grad_norm": 0.4042431116104126,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.6971,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.4504249291784703,
926
+ "grad_norm": 0.3926319181919098,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.6643,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.461756373937677,
933
+ "grad_norm": 0.4321343004703522,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6273,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.4730878186968839,
940
+ "grad_norm": 0.48049649596214294,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.5886,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.4844192634560907,
947
+ "grad_norm": 0.4928465783596039,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.5801,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.4957507082152974,
954
+ "grad_norm": 0.7852864265441895,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.4474,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.5070821529745042,
961
+ "grad_norm": 0.3517076075077057,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.5221,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.5184135977337112,
968
+ "grad_norm": 0.43520981073379517,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.6602,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.5297450424929178,
975
+ "grad_norm": 0.5653157234191895,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7331,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.5410764872521248,
982
+ "grad_norm": 0.45808669924736023,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.692,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.5524079320113313,
989
+ "grad_norm": 0.3955627977848053,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.6531,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.5637393767705383,
996
+ "grad_norm": 0.40485164523124695,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.6694,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.575070821529745,
1003
+ "grad_norm": 0.40561431646347046,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7055,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.5864022662889519,
1010
+ "grad_norm": 0.3729764223098755,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6782,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.5977337110481586,
1017
+ "grad_norm": 0.38850530982017517,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7543,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.6090651558073654,
1024
+ "grad_norm": 0.37639227509498596,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.6859,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.6203966005665722,
1031
+ "grad_norm": 0.3915426731109619,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.6985,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.631728045325779,
1038
+ "grad_norm": 0.3907557725906372,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.6392,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.643059490084986,
1045
+ "grad_norm": 0.37761691212654114,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6814,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.6543909348441925,
1052
+ "grad_norm": 0.38431620597839355,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.6704,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.6657223796033995,
1059
+ "grad_norm": 0.38361120223999023,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6842,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.677053824362606,
1066
+ "grad_norm": 0.39874064922332764,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.6795,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.688385269121813,
1073
+ "grad_norm": 0.40643274784088135,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.6898,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.6997167138810199,
1080
+ "grad_norm": 0.4098912179470062,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.6418,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.6997167138810199,
1087
+ "eval_loss": 0.7515243291854858,
1088
+ "eval_runtime": 11.4029,
1089
+ "eval_samples_per_second": 13.067,
1090
+ "eval_steps_per_second": 3.332,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.27361280946602e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null