infogeo commited on
Commit
421e92a
·
verified ·
1 Parent(s): f76d084

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 sha256:8c7db96197ac9bf4b04b14e2d97921abf2bfa1955f72c4347a6fa294934c6b87
3
  size 985240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7428134e07270fc4d17fd544f229da577d041985891e0d4d88e317401b0bcd21
3
  size 985240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c84ccb8f52db7053ea35e5b1bef3d1d4991e25744c14da6b28def6bfb36d9f5
3
  size 520860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6236b53ff3ee4f39ccef16baf9cb96b97ab3fec5f7981c004f529d24b746bf
3
  size 520860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc4d3e43e57936d5e788699cc8026d15748e5a3653d1e84f052a2ef2a1ca7f8b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520ed0f0305e51b9eba187b564a25f613b36cf1399f5af5141d8672ac8c7a0ad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.57370376586914,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.011292417141889222,
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": 123.603,
732
  "eval_steps_per_second": 30.926,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3000854642688.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.512722969055176,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.016938625712833832,
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": 123.603,
732
  "eval_steps_per_second": 30.926,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.011405341313308113,
737
+ "grad_norm": 1.898417353630066,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 21.5383,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.011518265484727007,
744
+ "grad_norm": 1.7448859214782715,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 21.5164,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.011631189656145898,
751
+ "grad_norm": 2.15998911857605,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 21.4158,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01174411382756479,
758
+ "grad_norm": 1.7991974353790283,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 21.544,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.011857037998983683,
765
+ "grad_norm": 1.6782306432724,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 21.4899,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.011969962170402575,
772
+ "grad_norm": 1.6934300661087036,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 21.4828,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.012082886341821466,
779
+ "grad_norm": 1.7622517347335815,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 21.5518,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01219581051324036,
786
+ "grad_norm": 2.0620055198669434,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 21.4972,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.012308734684659251,
793
+ "grad_norm": 1.7865617275238037,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 21.1913,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.012421658856078143,
800
+ "grad_norm": 1.6678588390350342,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 21.33,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.012534583027497036,
807
+ "grad_norm": 1.5663342475891113,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 21.2791,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.012647507198915928,
814
+ "grad_norm": 1.3401545286178589,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 21.2329,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.012760431370334821,
821
+ "grad_norm": 1.5291308164596558,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 21.0561,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.012873355541753713,
828
+ "grad_norm": 1.5034675598144531,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 21.0625,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.012986279713172604,
835
+ "grad_norm": 1.502207636833191,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 20.9603,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.013099203884591498,
842
+ "grad_norm": 1.3683857917785645,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 21.2751,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.013212128056010389,
849
+ "grad_norm": 1.3831427097320557,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 21.2536,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.01332505222742928,
856
+ "grad_norm": 1.7075899839401245,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 20.9327,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.013437976398848174,
863
+ "grad_norm": 1.4572417736053467,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 21.0398,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.013550900570267066,
870
+ "grad_norm": 1.8132352828979492,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 20.8115,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.013663824741685957,
877
+ "grad_norm": 1.7252711057662964,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 20.8063,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01377674891310485,
884
+ "grad_norm": 1.995081901550293,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 20.6842,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.013889673084523742,
891
+ "grad_norm": 1.5869985818862915,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 21.1246,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.014002597255942634,
898
+ "grad_norm": 1.448175072669983,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 21.1664,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.014115521427361527,
905
+ "grad_norm": 1.4581042528152466,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 21.1033,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.014228445598780419,
912
+ "grad_norm": 1.358923077583313,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 21.054,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.014341369770199312,
919
+ "grad_norm": 1.5759377479553223,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 21.0667,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.014454293941618204,
926
+ "grad_norm": 1.616433024406433,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 20.9253,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.014567218113037095,
933
+ "grad_norm": 1.6013528108596802,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 21.0409,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.014680142284455988,
940
+ "grad_norm": 1.7452136278152466,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 21.2808,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01479306645587488,
947
+ "grad_norm": 1.6038225889205933,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 21.1862,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.014905990627293772,
954
+ "grad_norm": 1.6077948808670044,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 20.9297,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.015018914798712665,
961
+ "grad_norm": 1.8298345804214478,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 20.9612,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.015131838970131557,
968
+ "grad_norm": 1.5444914102554321,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 21.0415,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.015244763141550448,
975
+ "grad_norm": 1.6737421751022339,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 21.0475,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.015357687312969341,
982
+ "grad_norm": 2.06323504447937,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 20.9078,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.015470611484388233,
989
+ "grad_norm": 1.7106398344039917,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 20.9534,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.015583535655807125,
996
+ "grad_norm": 1.7233997583389282,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 20.9764,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.015696459827226016,
1003
+ "grad_norm": 1.6839755773544312,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 20.7462,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01580938399864491,
1010
+ "grad_norm": 1.747623085975647,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 20.7554,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.015922308170063803,
1017
+ "grad_norm": 1.651952862739563,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 21.0266,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.016035232341482693,
1024
+ "grad_norm": 1.6088999509811401,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 21.1224,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.016148156512901586,
1031
+ "grad_norm": 1.762588620185852,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 20.9005,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01626108068432048,
1038
+ "grad_norm": 1.566470742225647,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 21.1413,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.01637400485573937,
1045
+ "grad_norm": 1.6514183282852173,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 20.8771,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.016486929027158263,
1052
+ "grad_norm": 1.7934764623641968,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 20.9009,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.016599853198577156,
1059
+ "grad_norm": 1.6794406175613403,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 20.9681,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.01671277736999605,
1066
+ "grad_norm": 1.6893374919891357,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 21.0311,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.01682570154141494,
1073
+ "grad_norm": 1.7404531240463257,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 20.9912,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.016938625712833832,
1080
+ "grad_norm": 1.9118671417236328,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 21.0618,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.016938625712833832,
1087
+ "eval_loss": 10.512722969055176,
1088
+ "eval_runtime": 30.1193,
1089
+ "eval_samples_per_second": 123.808,
1090
+ "eval_steps_per_second": 30.977,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4493817151488.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null