aleegis10 commited on
Commit
e956f5b
·
verified ·
1 Parent(s): 0b02c5c

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 sha256:6c2f3061b3c413b56d53191a39470ceaa4fd7f44916cd4fa558097a6eb3548b8
3
  size 60576160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6968753c08dd31ca04f27904ffdd26f1813168cd7e5870214bf998275811e6d1
3
  size 60576160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9989f6c86c76325a6d2358718ef7cc8b9fb53521ced99ddb00a35d40d5a01b3
3
  size 30895994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e62bb4620d62fe7db3fc348e91973281e1dfa25f15c84b09ef71161e7b158a00
3
  size 30895994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d02ad52e069286506931a6ca76e52cb67d9a01677d29e8cea8e12133ca11bbbb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8536f02cf475aac34fb8584019d66d4ff1b723ed30f6822d6aa31827ba19a5b0
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": 7.954951286315918,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11768167107972934,
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": 197.29,
732
  "eval_steps_per_second": 49.322,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4553958790004736.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 7.795602321624756,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.176522506619594,
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": 197.29,
732
  "eval_steps_per_second": 49.322,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11885848779052663,
737
+ "grad_norm": 0.6639958024024963,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 8.1624,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.12003530450132392,
744
+ "grad_norm": 0.5775700211524963,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 8.116,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.12121212121212122,
751
+ "grad_norm": 0.5763347148895264,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 8.0847,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.12238893792291851,
758
+ "grad_norm": 0.49246466159820557,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 8.0074,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1235657546337158,
765
+ "grad_norm": 0.5222952961921692,
766
+ "learning_rate": 5e-05,
767
+ "loss": 8.0499,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1247425713445131,
772
+ "grad_norm": 0.44529324769973755,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 8.0989,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1259193880553104,
779
+ "grad_norm": 0.41857656836509705,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 8.0144,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12709620476610767,
786
+ "grad_norm": 0.4567342698574066,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 7.9979,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12827302147690497,
793
+ "grad_norm": 0.4231415092945099,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.0324,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12944983818770225,
800
+ "grad_norm": 0.3888261616230011,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 7.988,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.13062665489849956,
807
+ "grad_norm": 0.3901044428348541,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 7.957,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.13180347160929684,
814
+ "grad_norm": 0.3741337060928345,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 7.9095,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.13298028832009415,
821
+ "grad_norm": 0.39858943223953247,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 7.9726,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.13415710503089143,
828
+ "grad_norm": 0.36172357201576233,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 7.9589,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.13533392174168873,
835
+ "grad_norm": 0.43459007143974304,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 7.9276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.136510738452486,
842
+ "grad_norm": 0.37559008598327637,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 7.9352,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13768755516328332,
849
+ "grad_norm": 0.40874215960502625,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 7.9079,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1388643718740806,
856
+ "grad_norm": 0.4839819669723511,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 8.0152,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1400411885848779,
863
+ "grad_norm": 0.43564435839653015,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 7.9073,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1412180052956752,
870
+ "grad_norm": 0.3991973102092743,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 7.9814,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1423948220064725,
877
+ "grad_norm": 0.39016836881637573,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 7.9041,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.14357163871726977,
884
+ "grad_norm": 0.37603044509887695,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 7.9082,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.14474845542806708,
891
+ "grad_norm": 0.4174538254737854,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 7.8501,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.14592527213886436,
898
+ "grad_norm": 0.40257492661476135,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 7.8427,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.14710208884966167,
905
+ "grad_norm": 0.47855108976364136,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 7.8776,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14827890556045895,
912
+ "grad_norm": 0.42736008763313293,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 7.833,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.14945572227125625,
919
+ "grad_norm": 0.4283291697502136,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 7.8327,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.15063253898205353,
926
+ "grad_norm": 0.45647186040878296,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 7.8408,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.15180935569285084,
933
+ "grad_norm": 0.45476916432380676,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 7.8581,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.15298617240364812,
940
+ "grad_norm": 0.4499008357524872,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 7.7825,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.15416298911444543,
947
+ "grad_norm": 0.48252078890800476,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 7.8309,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1553398058252427,
954
+ "grad_norm": 0.44942083954811096,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 7.8633,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.15651662253604,
961
+ "grad_norm": 0.4168689548969269,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 7.831,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1576934392468373,
968
+ "grad_norm": 0.4632453918457031,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 7.842,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1588702559576346,
975
+ "grad_norm": 0.48195233941078186,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 7.7602,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1600470726684319,
982
+ "grad_norm": 0.6227768063545227,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 7.8154,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.16122388937922918,
989
+ "grad_norm": 0.5569599866867065,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 7.7372,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1624007060900265,
996
+ "grad_norm": 0.5394451022148132,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 7.7624,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.16357752280082377,
1003
+ "grad_norm": 0.48696470260620117,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 7.7025,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.16475433951162108,
1010
+ "grad_norm": 0.5099177956581116,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 7.693,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.16593115622241836,
1017
+ "grad_norm": 0.5277547836303711,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 7.776,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.16710797293321566,
1024
+ "grad_norm": 0.6294848322868347,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 7.8503,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.16828478964401294,
1031
+ "grad_norm": 0.6027495861053467,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 7.7101,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16946160635481025,
1038
+ "grad_norm": 0.5793259739875793,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 7.6827,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.17063842306560753,
1045
+ "grad_norm": 0.7114255428314209,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 7.8202,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.17181523977640484,
1052
+ "grad_norm": 0.5538662672042847,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 7.6738,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.17299205648720212,
1059
+ "grad_norm": 0.560323178768158,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 7.7736,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.17416887319799942,
1066
+ "grad_norm": 0.6842308044433594,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 7.7109,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1753456899087967,
1073
+ "grad_norm": 0.6988137364387512,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 7.6467,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.176522506619594,
1080
+ "grad_norm": 0.945829451084137,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 7.6427,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.176522506619594,
1087
+ "eval_loss": 7.795602321624756,
1088
+ "eval_runtime": 7.2614,
1089
+ "eval_samples_per_second": 197.207,
1090
+ "eval_steps_per_second": 49.302,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6830938185007104.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null