prxy5604 commited on
Commit
720bf25
·
verified ·
1 Parent(s): a52c3f6

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 sha256:6afb43221df3e4361d024069416b03aa5e6f137c283cc929d3f96eb7db013205
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccb8d71491a38ea0a5fe85f43ed37754b346b0412ddaefdc342328af620db55
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b693844dfb7001d154079ee1a99b2e554a784c55a728273850e6ab80aac1e0
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa3606bd7edc250a9043afe1a6e2ec1a1b3ac209d00eef7772f6893ec840687
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": 0.6699920892715454,
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": 7.208,
732
  "eval_steps_per_second": 3.606,
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": 0.6293469667434692,
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": 7.208,
732
  "eval_steps_per_second": 3.606,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07098928132138464,
737
+ "grad_norm": 0.31048935651779175,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.3279,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0716921454928835,
744
+ "grad_norm": 0.23303721845149994,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.2911,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07239500966438236,
751
+ "grad_norm": 0.16442705690860748,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.2268,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07309787383588122,
758
+ "grad_norm": 0.12565502524375916,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.245,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07380073800738007,
765
+ "grad_norm": 0.17081908881664276,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.3868,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07450360217887893,
772
+ "grad_norm": 0.1710432767868042,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.3924,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0752064663503778,
779
+ "grad_norm": 0.16267825663089752,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.3854,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07590933052187665,
786
+ "grad_norm": 0.16099761426448822,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.3856,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0766121946933755,
793
+ "grad_norm": 0.17963358759880066,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.509,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07731505886487436,
800
+ "grad_norm": 0.20281143486499786,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.5468,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07801792303637323,
807
+ "grad_norm": 0.226894810795784,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.6794,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07872078720787208,
814
+ "grad_norm": 0.21442313492298126,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.6481,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07942365137937094,
821
+ "grad_norm": 0.2053515762090683,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.576,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08012651555086979,
828
+ "grad_norm": 0.21976761519908905,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.6167,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08082937972236866,
835
+ "grad_norm": 0.21342608332633972,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.6261,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08153224389386751,
842
+ "grad_norm": 0.21594056487083435,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.6295,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08223510806536637,
849
+ "grad_norm": 0.21840204298496246,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.6031,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08293797223686522,
856
+ "grad_norm": 0.19876247644424438,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.5297,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08364083640836409,
863
+ "grad_norm": 0.2141687124967575,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.5889,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08434370057986294,
870
+ "grad_norm": 0.22303129732608795,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.58,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0850465647513618,
877
+ "grad_norm": 0.2441388964653015,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.6225,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.08574942892286065,
884
+ "grad_norm": 0.24580511450767517,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.6232,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08645229309435952,
891
+ "grad_norm": 0.24386319518089294,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.6931,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08715515726585837,
898
+ "grad_norm": 0.24831323325634003,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.7371,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08785802143735723,
905
+ "grad_norm": 0.24015425145626068,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.7962,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08856088560885608,
912
+ "grad_norm": 0.26282528042793274,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.81,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08926374978035495,
919
+ "grad_norm": 0.24072156846523285,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.7402,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0899666139518538,
926
+ "grad_norm": 0.2517646849155426,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.7933,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.09066947812335266,
933
+ "grad_norm": 0.25127989053726196,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.7506,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09137234229485151,
940
+ "grad_norm": 0.2872861325740814,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.7521,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09207520646635038,
947
+ "grad_norm": 0.2886121869087219,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.818,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.09277807063784924,
954
+ "grad_norm": 0.30951032042503357,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.8753,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.09348093480934809,
961
+ "grad_norm": 0.3464934527873993,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.8002,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.09418379898084694,
968
+ "grad_norm": 0.3084924817085266,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.7794,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.09488666315234581,
975
+ "grad_norm": 0.3726934790611267,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.8027,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.09558952732384467,
982
+ "grad_norm": 0.3362215459346771,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.7978,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.09629239149534352,
989
+ "grad_norm": 0.3757701814174652,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.831,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09699525566684239,
996
+ "grad_norm": 0.3992413282394409,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.8456,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09769811983834124,
1003
+ "grad_norm": 0.33233338594436646,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.7549,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0984009840098401,
1010
+ "grad_norm": 0.29152634739875793,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.798,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09910384818133895,
1017
+ "grad_norm": 0.27916690707206726,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.8472,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09980671235283782,
1024
+ "grad_norm": 0.28885746002197266,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.8525,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.10050957652433667,
1031
+ "grad_norm": 0.29643693566322327,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.816,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10121244069583553,
1038
+ "grad_norm": 0.3148972690105438,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.8217,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.10191530486733438,
1045
+ "grad_norm": 0.32868483662605286,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.7778,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.10261816903883325,
1052
+ "grad_norm": 0.36426761746406555,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.785,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1033210332103321,
1059
+ "grad_norm": 0.36612796783447266,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.8406,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.10402389738183096,
1066
+ "grad_norm": 0.39215895533561707,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.8605,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.10472676155332981,
1073
+ "grad_norm": 0.40241187810897827,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.9149,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.10542962572482868,
1080
+ "grad_norm": 0.5203744769096375,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.9079,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.10542962572482868,
1087
+ "eval_loss": 0.6293469667434692,
1088
+ "eval_runtime": 332.3797,
1089
+ "eval_samples_per_second": 7.212,
1090
+ "eval_steps_per_second": 3.607,
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