0x1202 commited on
Commit
6cbb986
·
verified ·
1 Parent(s): db2a99f

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 sha256:845cfc5103088c62947713e2e3e1696ee12da7f252f0bc690d1e4f092e7bb3ff
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37b67c638c582f28bc96f9c0a1843c225fce3b6b3062c23c55fbcfcf251f0f6
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b2e8cb8b031771932d4f9c1c0318c77bd3df95effed6941f2d0866ffdef78fa
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d247e0830328988b1c961f51dd72490a06c874aaca880d9bc4a9e0e8c49c42
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f79ec975af03d49aef893109bb5446991d9cda402083ae1c26d76e66484a5f6e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae534e30853c95ddd17cf23489454a02f8d58d36e531c470d855504baf4f898
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": 11.832171440124512,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06763611768684477,
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": 92.835,
732
  "eval_steps_per_second": 23.227,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 125604200448000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.815106391906738,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.10145417653026716,
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": 92.835,
732
  "eval_steps_per_second": 23.227,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06831247886371322,
737
+ "grad_norm": 0.12027816474437714,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.854,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06898884004058167,
744
+ "grad_norm": 0.20657968521118164,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.8513,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06966520121745012,
751
+ "grad_norm": 0.14324679970741272,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.8409,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07034156239431856,
758
+ "grad_norm": 0.1667536497116089,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.8408,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07101792357118701,
765
+ "grad_norm": 0.13742108643054962,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.8433,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07169428474805546,
772
+ "grad_norm": 0.13735030591487885,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.8319,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07237064592492391,
779
+ "grad_norm": 0.09163592010736465,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.8332,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07304700710179236,
786
+ "grad_norm": 0.1583622843027115,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.8349,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0737233682786608,
793
+ "grad_norm": 0.10508851706981659,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.8363,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07439972945552925,
800
+ "grad_norm": 0.15417686104774475,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.8359,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0750760906323977,
807
+ "grad_norm": 0.10372468829154968,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.83,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07575245180926615,
814
+ "grad_norm": 0.09224109351634979,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.8275,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07642881298613459,
821
+ "grad_norm": 0.1201566830277443,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.8301,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07710517416300304,
828
+ "grad_norm": 0.09112562984228134,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.8321,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07778153533987149,
835
+ "grad_norm": 0.10148422420024872,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.8325,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07845789651673994,
842
+ "grad_norm": 0.1041034460067749,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.8289,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07913425769360839,
849
+ "grad_norm": 0.11524149775505066,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.8273,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07981061887047683,
856
+ "grad_norm": 0.1229957789182663,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.826,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08048698004734528,
863
+ "grad_norm": 0.09767038375139236,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.8268,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08116334122421373,
870
+ "grad_norm": 0.10564996302127838,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.8219,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.08183970240108218,
877
+ "grad_norm": 0.11788948625326157,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.8174,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.08251606357795063,
884
+ "grad_norm": 0.0964515283703804,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.8217,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08319242475481907,
891
+ "grad_norm": 0.09519102424383163,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.8193,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08386878593168752,
898
+ "grad_norm": 0.10091554373502731,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.8243,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08454514710855597,
905
+ "grad_norm": 0.12377063930034637,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.8191,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08522150828542442,
912
+ "grad_norm": 0.09319707006216049,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.8191,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08589786946229286,
919
+ "grad_norm": 0.0966852530837059,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.8229,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08657423063916131,
926
+ "grad_norm": 0.09921374171972275,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.8186,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08725059181602976,
933
+ "grad_norm": 0.08391332626342773,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.8265,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08792695299289821,
940
+ "grad_norm": 0.10751412808895111,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.816,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08860331416976666,
947
+ "grad_norm": 0.11316145211458206,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.8241,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0892796753466351,
954
+ "grad_norm": 0.09601719677448273,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.8176,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08995603652350355,
961
+ "grad_norm": 0.11552033573389053,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.8153,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.090632397700372,
968
+ "grad_norm": 0.09254191070795059,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.8124,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.09130875887724045,
975
+ "grad_norm": 0.10105631500482559,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.8104,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.09198512005410889,
982
+ "grad_norm": 0.09207307547330856,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.8158,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.09266148123097734,
989
+ "grad_norm": 0.11376768350601196,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.8165,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09333784240784579,
996
+ "grad_norm": 0.11263630539178848,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.8093,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09401420358471424,
1003
+ "grad_norm": 0.11241159588098526,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.8116,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09469056476158269,
1010
+ "grad_norm": 0.09340821206569672,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.8168,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09536692593845113,
1017
+ "grad_norm": 0.09616852551698685,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.8109,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09604328711531958,
1024
+ "grad_norm": 0.10595780611038208,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.8105,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09671964829218803,
1031
+ "grad_norm": 0.12038301676511765,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.8137,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09739600946905648,
1038
+ "grad_norm": 0.08127898722887039,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.8064,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09807237064592493,
1045
+ "grad_norm": 0.09854679554700851,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.8088,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09874873182279337,
1052
+ "grad_norm": 0.12643414735794067,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.8133,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09942509299966182,
1059
+ "grad_norm": 0.11658405512571335,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.8071,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.10010145417653027,
1066
+ "grad_norm": 0.14468736946582794,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.7987,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.10077781535339872,
1073
+ "grad_norm": 0.14392907917499542,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.8163,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.10145417653026716,
1080
+ "grad_norm": 0.1634630709886551,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.808,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.10145417653026716,
1087
+ "eval_loss": 11.815106391906738,
1088
+ "eval_runtime": 26.7353,
1089
+ "eval_samples_per_second": 93.135,
1090
+ "eval_steps_per_second": 23.303,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 188406300672000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null