aleegis09 commited on
Commit
21aaf94
·
verified ·
1 Parent(s): 80a521b

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:c2c832c7c338c089953b13edd4ec20f50223d6934fefe9d6c6edd2ab5fd24df2
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd440f61b1b934b3a8b6e2afde1f6cf03193be8ef01bccd37d5d9448b4bb2895
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb953eaf4f751e42cc97306c715a5ead14c96170e39faa3fb4b64eb2c7fcede
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430130a4a956f21ea863d1b6908c14ce55f6d16c585bae313bdfcc6efb5f89cd
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1755d42c60e50ff7c04ecac5c6e1061394aa2f05c7189115068dc63454405dd5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fedbca1d43cc0179665b5ce0a8fbd1ee0b4f1453a3eb449449832d9bb81d619a
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": 2.2260937690734863,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.009306870797366156,
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": 59.412,
732
  "eval_steps_per_second": 14.855,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.195554733276367,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.013960306196049233,
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": 59.412,
732
  "eval_steps_per_second": 14.855,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009399939505339816,
737
+ "grad_norm": 0.885202169418335,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.0273,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009493008213313479,
744
+ "grad_norm": 0.8084040284156799,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.861,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009586076921287141,
751
+ "grad_norm": 0.827190637588501,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.7483,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009679145629260802,
758
+ "grad_norm": 0.8935898542404175,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.6683,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009772214337234464,
765
+ "grad_norm": 0.9296590089797974,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.4647,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.009865283045208124,
772
+ "grad_norm": 0.765300452709198,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.9411,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.009958351753181787,
779
+ "grad_norm": 0.7055776715278625,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.5806,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.010051420461155447,
786
+ "grad_norm": 0.7580770254135132,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.1138,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01014448916912911,
793
+ "grad_norm": 0.7041999101638794,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.9105,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.010237557877102772,
800
+ "grad_norm": 0.8343727588653564,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.0693,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.010330626585076432,
807
+ "grad_norm": 0.8094717860221863,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.0537,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010423695293050095,
814
+ "grad_norm": 0.8005990386009216,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.0875,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.010516764001023755,
821
+ "grad_norm": 0.8130223751068115,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.3609,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010609832708997418,
828
+ "grad_norm": 0.7583662271499634,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.7585,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.010702901416971078,
835
+ "grad_norm": 0.8314856290817261,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.198,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01079597012494474,
842
+ "grad_norm": 0.6716787219047546,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.85,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.010889038832918403,
849
+ "grad_norm": 0.7772634625434875,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.1143,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.010982107540892063,
856
+ "grad_norm": 0.8054991960525513,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.269,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.011075176248865726,
863
+ "grad_norm": 0.959876537322998,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.3457,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.011168244956839386,
870
+ "grad_norm": 1.0733617544174194,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.4271,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.011261313664813049,
877
+ "grad_norm": 0.7122442722320557,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.098,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01135438237278671,
884
+ "grad_norm": 0.8017372488975525,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.1153,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.011447451080760371,
891
+ "grad_norm": 0.8121442794799805,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.4195,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011540519788734034,
898
+ "grad_norm": 0.789205014705658,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.1837,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011633588496707694,
905
+ "grad_norm": 0.6309551000595093,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.4381,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011726657204681357,
912
+ "grad_norm": 0.8947659730911255,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.3491,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.011819725912655017,
919
+ "grad_norm": 0.6499992609024048,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.8383,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01191279462062868,
926
+ "grad_norm": 0.7750574946403503,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.0827,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01200586332860234,
933
+ "grad_norm": 0.8053340911865234,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.9525,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.012098932036576002,
940
+ "grad_norm": 0.8092412352561951,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.1892,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.012192000744549663,
947
+ "grad_norm": 0.7703909873962402,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.0859,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.012285069452523325,
954
+ "grad_norm": 0.7653037309646606,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.2152,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.012378138160496988,
961
+ "grad_norm": 0.8823392391204834,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.3267,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012471206868470648,
968
+ "grad_norm": 0.8371039032936096,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.5191,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01256427557644431,
975
+ "grad_norm": 0.7754389643669128,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.0445,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.012657344284417971,
982
+ "grad_norm": 0.7838861346244812,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.2573,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012750412992391633,
989
+ "grad_norm": 0.7995550036430359,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.3577,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.012843481700365294,
996
+ "grad_norm": 0.9165576100349426,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.6747,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.012936550408338956,
1003
+ "grad_norm": 0.8664534091949463,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.4664,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.013029619116312618,
1010
+ "grad_norm": 0.7616163492202759,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.9131,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.013122687824286279,
1017
+ "grad_norm": 0.836466372013092,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.4565,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.013215756532259941,
1024
+ "grad_norm": 0.8205718398094177,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.319,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.013308825240233602,
1031
+ "grad_norm": 0.8233223557472229,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.1568,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.013401893948207264,
1038
+ "grad_norm": 0.8584922552108765,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.0534,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013494962656180925,
1045
+ "grad_norm": 1.0535118579864502,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.8399,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.013588031364154587,
1052
+ "grad_norm": 0.7697364687919617,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.2599,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.01368110007212825,
1059
+ "grad_norm": 0.8693205714225769,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.314,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.01377416878010191,
1066
+ "grad_norm": 0.8806237578392029,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.8067,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.013867237488075572,
1073
+ "grad_norm": 0.9994990229606628,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.3948,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.013960306196049233,
1080
+ "grad_norm": 1.1815805435180664,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.335,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.013960306196049233,
1087
+ "eval_loss": 2.195554733276367,
1088
+ "eval_runtime": 304.583,
1089
+ "eval_samples_per_second": 59.416,
1090
+ "eval_steps_per_second": 14.856,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.032049150918656e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null