prxy5604 commited on
Commit
2f93811
·
verified ·
1 Parent(s): 86d7e47

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:fb31e9a27fbe0b013995b1556a81ba5b33a977b1ea662af116587a298f5acc72
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8126973eea567fd09c49b47ae958dcafdbee94354e9523b355242886604ee6d1
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e66e36641e95381e4b0b93b2d4d0a90451742b9082c40b02d3365489e25916a
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b90a21951163fd5c43c931baa20dc51ca75f8b2e1c2e22d570647586a732012
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77764e2c0971744730dab5830dc21a51fe69b2aa7137e57f8f6ef34360b99abe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74c4becd71c93cbcbe352d1fedf069b5db76851fa457636618a9fea09c58dca
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": 1.3032747507095337,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0851063829787234,
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": 12.349,
732
  "eval_steps_per_second": 3.089,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.696886084193485e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2979270219802856,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1276595744680851,
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": 12.349,
732
  "eval_steps_per_second": 3.089,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08595744680851064,
737
+ "grad_norm": 0.6527327299118042,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.4381,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08680851063829788,
744
+ "grad_norm": 0.6568225622177124,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.4244,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0876595744680851,
751
+ "grad_norm": 0.6263706684112549,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3487,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08851063829787234,
758
+ "grad_norm": 0.6476358771324158,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3787,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08936170212765958,
765
+ "grad_norm": 0.6962791085243225,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.4081,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0902127659574468,
772
+ "grad_norm": 0.6745772361755371,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.4239,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09106382978723404,
779
+ "grad_norm": 0.6622292995452881,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.4127,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09191489361702128,
786
+ "grad_norm": 0.7627405524253845,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.3924,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.09276595744680852,
793
+ "grad_norm": 0.6973463296890259,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4557,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09361702127659574,
800
+ "grad_norm": 0.7011168003082275,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.3789,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09446808510638298,
807
+ "grad_norm": 0.6751556992530823,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.3525,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09531914893617022,
814
+ "grad_norm": 0.7253915667533875,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.3292,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09617021276595744,
821
+ "grad_norm": 0.7240049242973328,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3756,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09702127659574468,
828
+ "grad_norm": 0.7273006439208984,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.2924,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09787234042553192,
835
+ "grad_norm": 0.699385404586792,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3678,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09872340425531916,
842
+ "grad_norm": 0.7153459191322327,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2603,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09957446808510638,
849
+ "grad_norm": 0.7200783491134644,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.3495,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10042553191489362,
856
+ "grad_norm": 0.7112252712249756,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2678,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10127659574468086,
863
+ "grad_norm": 0.7226855158805847,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.2695,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10212765957446808,
870
+ "grad_norm": 0.7355283498764038,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.4014,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10297872340425532,
877
+ "grad_norm": 0.7358095645904541,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.2802,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10382978723404256,
884
+ "grad_norm": 0.71736079454422,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2517,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1046808510638298,
891
+ "grad_norm": 0.7413192391395569,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2643,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10553191489361702,
898
+ "grad_norm": 0.7529467344284058,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.3011,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10638297872340426,
905
+ "grad_norm": 0.7763828039169312,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3914,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1072340425531915,
912
+ "grad_norm": 0.7712790966033936,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.3272,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10808510638297872,
919
+ "grad_norm": 0.7886697053909302,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.358,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10893617021276596,
926
+ "grad_norm": 0.7689956426620483,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.3551,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1097872340425532,
933
+ "grad_norm": 0.7094907760620117,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1919,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11063829787234042,
940
+ "grad_norm": 0.7634008526802063,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2681,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11148936170212766,
947
+ "grad_norm": 0.7647489905357361,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.3139,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1123404255319149,
954
+ "grad_norm": 0.77503502368927,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3824,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11319148936170213,
961
+ "grad_norm": 0.7760922908782959,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.3273,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11404255319148936,
968
+ "grad_norm": 0.7831414341926575,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3015,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1148936170212766,
975
+ "grad_norm": 0.7792320251464844,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.321,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11574468085106383,
982
+ "grad_norm": 0.7789376974105835,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.3521,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11659574468085106,
989
+ "grad_norm": 0.7763599157333374,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.2396,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1174468085106383,
996
+ "grad_norm": 0.8315020203590393,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.2175,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11829787234042553,
1003
+ "grad_norm": 0.8341485857963562,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3048,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11914893617021277,
1010
+ "grad_norm": 0.8231856226921082,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3283,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.12,
1017
+ "grad_norm": 0.8549226522445679,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.385,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12085106382978723,
1024
+ "grad_norm": 0.8536549806594849,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.3222,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12170212765957447,
1031
+ "grad_norm": 0.7238088846206665,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1573,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1225531914893617,
1038
+ "grad_norm": 0.7287506461143494,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.1731,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12340425531914893,
1045
+ "grad_norm": 0.714331328868866,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1122,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12425531914893617,
1052
+ "grad_norm": 0.7509970664978027,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.1225,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1251063829787234,
1059
+ "grad_norm": 0.7498308420181274,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0927,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12595744680851065,
1066
+ "grad_norm": 0.7059639692306519,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.0788,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12680851063829787,
1073
+ "grad_norm": 0.7344927787780762,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1151,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1276595744680851,
1080
+ "grad_norm": 0.8907794952392578,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.1759,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1276595744680851,
1087
+ "eval_loss": 1.2979270219802856,
1088
+ "eval_runtime": 160.2387,
1089
+ "eval_samples_per_second": 12.35,
1090
+ "eval_steps_per_second": 3.089,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1591945529222758e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null