nttx commited on
Commit
3e59682
·
verified ·
1 Parent(s): 3e0d0bb

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 sha256:90e1ecd5ae1796a40c42cc53e2b8baa6ae9e576fdaf8002f53d5fc55ab6bbe2f
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e315aa30715289722f8e8dc7716b46e18e1b1e0f04e9814106e3943eb2db1dac
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b74f45887eb2bf8a4c01583be5dd4fbec0a4170f7a4e1472ab36942385358ca4
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2bc22981a68d97f566ec50919e0e3397327c4ca7fa2b40792534e0c318d0bd
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f46da81ba631b64de591d5d73e697ebef2af8b3cb47a5eff2c98fdadd25e3f5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e265ffe25496d13bbe5b8c2f6d7b807b2f860b2c181e6285464675ef97b62a7b
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": 0.02691887505352497,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.033715441672285906,
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": 12.28,
732
  "eval_steps_per_second": 6.141,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.438154617698386e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.012810143642127514,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05057316250842886,
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": 12.28,
732
  "eval_steps_per_second": 6.141,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03405259608900876,
737
+ "grad_norm": 4.755925178527832,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.059,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.03438975050573163,
744
+ "grad_norm": 2.4394125938415527,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.0369,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.034726904922454484,
751
+ "grad_norm": 3.223604440689087,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.0616,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03506405933917734,
758
+ "grad_norm": 2.9902310371398926,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.0542,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.035401213755900204,
765
+ "grad_norm": 6.737509250640869,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.0767,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03573836817262306,
772
+ "grad_norm": 3.23425030708313,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.1023,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03607552258934592,
779
+ "grad_norm": 5.8453369140625,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.1004,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03641267700606878,
786
+ "grad_norm": 2.000162124633789,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.0292,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03674983142279164,
793
+ "grad_norm": 5.187445640563965,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.1003,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.037086985839514496,
800
+ "grad_norm": 0.8303626179695129,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.0142,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03742414025623736,
807
+ "grad_norm": 4.555915832519531,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.0523,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.037761294672960216,
814
+ "grad_norm": 1.806445837020874,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.0349,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03809844908968307,
821
+ "grad_norm": 1.471052885055542,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.0226,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03843560350640594,
828
+ "grad_norm": 2.268584966659546,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.0347,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.038772757923128794,
835
+ "grad_norm": 2.2255048751831055,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.0276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03910991233985165,
842
+ "grad_norm": 2.3270277976989746,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.0507,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.039447066756574514,
849
+ "grad_norm": 0.9853026270866394,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.0067,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03978422117329737,
856
+ "grad_norm": 2.494917392730713,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.0284,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.04012137559002023,
863
+ "grad_norm": 1.041441559791565,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.0078,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04045853000674309,
870
+ "grad_norm": 3.8731324672698975,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.0814,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04079568442346595,
877
+ "grad_norm": 3.1091275215148926,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.0392,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.041132838840188805,
884
+ "grad_norm": 2.3696067333221436,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.0401,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04146999325691166,
891
+ "grad_norm": 2.993685245513916,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.1073,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041807147673634526,
898
+ "grad_norm": 3.7679295539855957,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.097,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04214430209035738,
905
+ "grad_norm": 3.30842661857605,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.0337,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.04248145650708024,
912
+ "grad_norm": 1.5507580041885376,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.0749,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0428186109238031,
919
+ "grad_norm": 8.317049026489258,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.081,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04315576534052596,
926
+ "grad_norm": 4.408754825592041,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.0907,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04349291975724882,
933
+ "grad_norm": 3.775179147720337,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.0575,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04383007417397168,
940
+ "grad_norm": 7.735755443572998,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.1781,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04416722859069454,
947
+ "grad_norm": 1.943678379058838,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.0128,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.044504383007417395,
954
+ "grad_norm": 3.540893793106079,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.0932,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04484153742414026,
961
+ "grad_norm": 4.737628936767578,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.0265,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.045178691840863115,
968
+ "grad_norm": 1.0604182481765747,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.0195,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04551584625758597,
975
+ "grad_norm": 1.3365453481674194,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.0325,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.045853000674308836,
982
+ "grad_norm": 1.242696762084961,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.0211,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04619015509103169,
989
+ "grad_norm": 4.375517845153809,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.1008,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04652730950775455,
996
+ "grad_norm": 3.7607028484344482,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.1257,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04686446392447741,
1003
+ "grad_norm": 5.041885852813721,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.1199,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.04720161834120027,
1010
+ "grad_norm": 4.754733085632324,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.0584,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04753877275792313,
1017
+ "grad_norm": 1.6650151014328003,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.0149,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04787592717464599,
1024
+ "grad_norm": 4.360198497772217,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.1853,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04821308159136885,
1031
+ "grad_norm": 4.324887752532959,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.0979,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.048550236008091704,
1038
+ "grad_norm": 2.8787121772766113,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.0385,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04888739042481457,
1045
+ "grad_norm": 2.155133008956909,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.0243,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.049224544841537425,
1052
+ "grad_norm": 3.4507551193237305,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.0961,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04956169925826028,
1059
+ "grad_norm": 2.0871427059173584,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.0321,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.049898853674983146,
1066
+ "grad_norm": 3.9840118885040283,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.0725,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.050236008091706,
1073
+ "grad_norm": 1.3192414045333862,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.0148,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05057316250842886,
1080
+ "grad_norm": 3.3443753719329834,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.0527,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05057316250842886,
1087
+ "eval_loss": 0.012810143642127514,
1088
+ "eval_runtime": 406.1644,
1089
+ "eval_samples_per_second": 12.298,
1090
+ "eval_steps_per_second": 6.15,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.157231926547579e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null