0x1202 commited on
Commit
3c9335a
·
verified ·
1 Parent(s): 5be8bb2

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:a8d6ef069186b9cbee782ee703d6c07dc9ab02a7a62985f77b5150a054fd2248
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9533e8c57da63a45a6d94ea1c33843ed77e35db2a092e2624b219512798e96
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b727f02e98ee6cfbab0afbe340584aba7f1fdc4eb6bb9f189add5f38949b801
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd8256eb5553e69258941e3e77265322212eea1fb073efc4d7617f2d2d7bb2d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0de8cba1572a321bd775311cc96cb7c3e964b41002f420e840929f3d9fd6c3d2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1f55850bd5adc639f39496b6f333728a24cc6fa8b3cf719b15ec4078b5715f
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": 2.377595901489258,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.39331366764995085,
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": 10.117,
732
  "eval_steps_per_second": 2.529,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.903227351953572e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.344693660736084,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5899705014749262,
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": 10.117,
732
  "eval_steps_per_second": 2.529,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3972468043264503,
737
+ "grad_norm": 3.08909273147583,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 9.9756,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.40117994100294985,
744
+ "grad_norm": 2.7837369441986084,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 9.6044,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4051130776794494,
751
+ "grad_norm": 2.4905002117156982,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 9.6984,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.40904621435594885,
758
+ "grad_norm": 2.5934627056121826,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 9.5509,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.41297935103244837,
765
+ "grad_norm": 2.774919271469116,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.095,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4169124877089479,
772
+ "grad_norm": 2.2922799587249756,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 8.5538,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.42084562438544737,
779
+ "grad_norm": 2.2252211570739746,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 8.5763,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4247787610619469,
786
+ "grad_norm": 2.1300716400146484,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 9.19,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4287118977384464,
793
+ "grad_norm": 2.0938432216644287,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.579,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4326450344149459,
800
+ "grad_norm": 2.029053211212158,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 9.235,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4365781710914454,
807
+ "grad_norm": 2.1520063877105713,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 10.1329,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.44051130776794495,
814
+ "grad_norm": 2.1671314239501953,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 10.1986,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.4444444444444444,
821
+ "grad_norm": 2.1574721336364746,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 9.854,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.44837758112094395,
828
+ "grad_norm": 2.193593978881836,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 10.1098,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.4523107177974435,
835
+ "grad_norm": 2.2297420501708984,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 10.3231,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.45624385447394294,
842
+ "grad_norm": 2.1912527084350586,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 10.0058,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.46017699115044247,
849
+ "grad_norm": 2.048713207244873,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.4333,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.464110127826942,
856
+ "grad_norm": 2.169332265853882,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 9.9015,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.46804326450344147,
863
+ "grad_norm": 2.181147575378418,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 9.4366,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.471976401179941,
870
+ "grad_norm": 2.2025153636932373,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.1722,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4759095378564405,
877
+ "grad_norm": 2.1340596675872803,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 8.992,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.47984267453294,
884
+ "grad_norm": 2.2811179161071777,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 9.445,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4837758112094395,
891
+ "grad_norm": 2.3786089420318604,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 9.4312,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.48770894788593905,
898
+ "grad_norm": 2.277052879333496,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 9.0085,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4916420845624385,
905
+ "grad_norm": 2.360323667526245,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 9.1277,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.49557522123893805,
912
+ "grad_norm": 2.438770055770874,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 9.3701,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4995083579154376,
919
+ "grad_norm": 2.3755929470062256,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 9.2335,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5034414945919371,
926
+ "grad_norm": 2.406074285507202,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 9.279,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5073746312684366,
933
+ "grad_norm": 2.4719107151031494,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 8.8831,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.511307767944936,
940
+ "grad_norm": 2.44181227684021,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 8.8951,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5152409046214356,
947
+ "grad_norm": 2.5877556800842285,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 9.553,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5191740412979351,
954
+ "grad_norm": 2.557809591293335,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 9.6316,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5231071779744346,
961
+ "grad_norm": 2.610058546066284,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 9.5595,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5270403146509341,
968
+ "grad_norm": 2.6222903728485107,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.2895,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5309734513274337,
975
+ "grad_norm": 2.859793186187744,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 9.684,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5349065880039331,
982
+ "grad_norm": 2.576481342315674,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.0351,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5388397246804326,
989
+ "grad_norm": 2.724790573120117,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 8.9841,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5427728613569321,
996
+ "grad_norm": 2.8321926593780518,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.5174,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5467059980334317,
1003
+ "grad_norm": 2.817160129547119,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 9.3392,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5506391347099312,
1010
+ "grad_norm": 2.91648268699646,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.3903,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5545722713864307,
1017
+ "grad_norm": 3.1426236629486084,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 9.8369,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5585054080629301,
1024
+ "grad_norm": 3.0239462852478027,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.397,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5624385447394297,
1031
+ "grad_norm": 3.1258440017700195,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.5766,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5663716814159292,
1038
+ "grad_norm": 3.3126816749572754,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 9.2543,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5703048180924287,
1045
+ "grad_norm": 3.448613166809082,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.8778,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5742379547689282,
1052
+ "grad_norm": 3.536125421524048,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 9.6228,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5781710914454278,
1059
+ "grad_norm": 3.59429669380188,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 9.3941,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5821042281219272,
1066
+ "grad_norm": 3.537135601043701,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 8.9489,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5860373647984267,
1073
+ "grad_norm": 3.9991540908813477,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.7437,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5899705014749262,
1080
+ "grad_norm": 4.636314868927002,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 10.0317,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5899705014749262,
1087
+ "eval_loss": 2.344693660736084,
1088
+ "eval_runtime": 42.3118,
1089
+ "eval_samples_per_second": 10.115,
1090
+ "eval_steps_per_second": 2.529,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.858418522952827e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null