nttx commited on
Commit
f586223
·
verified ·
1 Parent(s): 0045a20

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:fc217f99753422f193caf9c6b8a568e82b5b9ce788123275737f2588de20e4ca
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453c1d5cf47fb4e3921e12014c1829ebb1eb709f2b6e1d36a97378a35d8f12b6
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c45ef18a02ae4bf5432f680e94514eafdf470f6a8616411fa90e00ed04b9479a
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3f280d6c7741c2b9b8aecfd959bb1e36d0f2e1f9256824b2ea2305104151e16
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d40015f9b0060360be0dbdeaab42222ac37ca1d65e73bfdbacc136d49a439e80
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e56946399aabee448fd3c422a118df88cf2bc9a4a8936d73afb8a779bd8edd2
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": 0.6700912117958069,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07028641714988579,
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": 7.244,
732
  "eval_steps_per_second": 3.623,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.43583936364544e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6301707029342651,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.10542962572482868,
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": 7.244,
732
  "eval_steps_per_second": 3.623,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07098928132138464,
737
+ "grad_norm": 0.33022674918174744,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.3285,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0716921454928835,
744
+ "grad_norm": 0.23496587574481964,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.291,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07239500966438236,
751
+ "grad_norm": 0.1598483771085739,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.2264,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07309787383588122,
758
+ "grad_norm": 0.1260489821434021,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.2455,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07380073800738007,
765
+ "grad_norm": 0.17387931048870087,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.3873,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07450360217887893,
772
+ "grad_norm": 0.17388597130775452,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.3936,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0752064663503778,
779
+ "grad_norm": 0.1646834909915924,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.3863,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07590933052187665,
786
+ "grad_norm": 0.15986335277557373,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.3856,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0766121946933755,
793
+ "grad_norm": 0.18033923208713531,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.5094,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07731505886487436,
800
+ "grad_norm": 0.1951182335615158,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.5479,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07801792303637323,
807
+ "grad_norm": 0.2278830111026764,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.6816,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07872078720787208,
814
+ "grad_norm": 0.21481981873512268,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.6485,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07942365137937094,
821
+ "grad_norm": 0.20478928089141846,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.5773,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08012651555086979,
828
+ "grad_norm": 0.20480093359947205,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.6184,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08082937972236866,
835
+ "grad_norm": 0.21362999081611633,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.6276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08153224389386751,
842
+ "grad_norm": 0.21587170660495758,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.6309,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08223510806536637,
849
+ "grad_norm": 0.21990324556827545,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.605,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08293797223686522,
856
+ "grad_norm": 0.1980743706226349,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.531,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08364083640836409,
863
+ "grad_norm": 0.2157222479581833,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.5889,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08434370057986294,
870
+ "grad_norm": 0.2280951738357544,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.5798,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0850465647513618,
877
+ "grad_norm": 0.24583876132965088,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.6229,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.08574942892286065,
884
+ "grad_norm": 0.2399996966123581,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.6234,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08645229309435952,
891
+ "grad_norm": 0.24560829997062683,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.6934,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08715515726585837,
898
+ "grad_norm": 0.2501152455806732,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.7375,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08785802143735723,
905
+ "grad_norm": 0.24112533032894135,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.7972,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08856088560885608,
912
+ "grad_norm": 0.25931692123413086,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.81,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08926374978035495,
919
+ "grad_norm": 0.24223147332668304,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.7402,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0899666139518538,
926
+ "grad_norm": 0.252523809671402,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.7944,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.09066947812335266,
933
+ "grad_norm": 0.24921025335788727,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.7511,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09137234229485151,
940
+ "grad_norm": 0.28853365778923035,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.7525,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09207520646635038,
947
+ "grad_norm": 0.287954717874527,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.8199,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.09277807063784924,
954
+ "grad_norm": 0.3075440227985382,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.8766,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.09348093480934809,
961
+ "grad_norm": 0.3455755114555359,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.8013,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.09418379898084694,
968
+ "grad_norm": 0.30856016278266907,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.7784,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.09488666315234581,
975
+ "grad_norm": 0.37127408385276794,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.8032,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.09558952732384467,
982
+ "grad_norm": 0.3385152816772461,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.7991,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.09629239149534352,
989
+ "grad_norm": 0.37487202882766724,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.8295,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09699525566684239,
996
+ "grad_norm": 0.4049539566040039,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.8476,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09769811983834124,
1003
+ "grad_norm": 0.3347541093826294,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.7553,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0984009840098401,
1010
+ "grad_norm": 0.2915925085544586,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.7991,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09910384818133895,
1017
+ "grad_norm": 0.2804563641548157,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.849,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09980671235283782,
1024
+ "grad_norm": 0.29074734449386597,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.8534,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.10050957652433667,
1031
+ "grad_norm": 0.3367944657802582,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.8162,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10121244069583553,
1038
+ "grad_norm": 0.30872201919555664,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.8223,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.10191530486733438,
1045
+ "grad_norm": 0.32860398292541504,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.7783,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.10261816903883325,
1052
+ "grad_norm": 0.36504289507865906,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.7863,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1033210332103321,
1059
+ "grad_norm": 0.36676210165023804,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.8424,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.10402389738183096,
1066
+ "grad_norm": 0.3919408917427063,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.8613,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.10472676155332981,
1073
+ "grad_norm": 0.39226704835891724,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.9161,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.10542962572482868,
1080
+ "grad_norm": 0.5209399461746216,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.9089,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.10542962572482868,
1087
+ "eval_loss": 0.6301707029342651,
1088
+ "eval_runtime": 331.001,
1089
+ "eval_samples_per_second": 7.242,
1090
+ "eval_steps_per_second": 3.622,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.63693695041536e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null