prxy5605 commited on
Commit
dad9e4a
·
verified ·
1 Parent(s): d0cca52

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 sha256:45e928888fb5cf96fafb2634b0d8a42537dce403817b5a37eecf8a003cb82182
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3580e456e02ff5f31a22519584e52996023f24307cff693f17d79949dfa4ee8d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57db4d8c24eaac41d5a0e14e0cca39936eeb60c9d8a45eb7cb8d980c347e6155
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100697963642ad4cba963ab9ea4430adc63c4a96e1f26c52896c6526992824cf
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:fccf73e344f43ead4c5faeae8f2de0e57673ce09ed2d88e5a67b5b78c8b89a97
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5878c92a5f722dcf6f7a0ec4f3726c156d8b946dde60c77ccccf5ccf613e6c
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": 1.5281273126602173,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.022746659084446973,
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": 13.01,
732
  "eval_steps_per_second": 3.252,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4924601848600986e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.427915096282959,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.034119988626670456,
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": 13.01,
732
  "eval_steps_per_second": 3.252,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.022974125675291442,
737
+ "grad_norm": 14.376147270202637,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.8557,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.023201592266135912,
744
+ "grad_norm": 18.546865463256836,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 6.5242,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02342905885698038,
751
+ "grad_norm": 22.680837631225586,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.8747,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.02365652544782485,
758
+ "grad_norm": 13.674721717834473,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.9718,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02388399203866932,
765
+ "grad_norm": 10.834354400634766,
766
+ "learning_rate": 5e-05,
767
+ "loss": 4.634,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.02411145862951379,
772
+ "grad_norm": 13.663738250732422,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.8656,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.02433892522035826,
779
+ "grad_norm": 11.865979194641113,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.7424,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02456639181120273,
786
+ "grad_norm": 10.258040428161621,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.8621,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0247938584020472,
793
+ "grad_norm": 9.784005165100098,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.4615,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.02502132499289167,
800
+ "grad_norm": 11.660787582397461,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 4.375,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02524879158373614,
807
+ "grad_norm": 9.96675968170166,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.5918,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02547625817458061,
814
+ "grad_norm": 10.535229682922363,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.9647,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.025703724765425078,
821
+ "grad_norm": 10.414861679077148,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.7578,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.025931191356269548,
828
+ "grad_norm": 10.012444496154785,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.758,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.026158657947114018,
835
+ "grad_norm": 10.83643627166748,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.0217,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.026386124537958487,
842
+ "grad_norm": 10.590777397155762,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.9621,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.026613591128802957,
849
+ "grad_norm": 10.981629371643066,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.6573,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.026841057719647426,
856
+ "grad_norm": 10.608504295349121,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.9342,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.027068524310491896,
863
+ "grad_norm": 10.594474792480469,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.2988,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.027295990901336366,
870
+ "grad_norm": 14.070845603942871,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.8005,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.027523457492180835,
877
+ "grad_norm": 11.825883865356445,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.7208,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.027750924083025305,
884
+ "grad_norm": 10.942339897155762,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.7025,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.027978390673869775,
891
+ "grad_norm": 14.623804092407227,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.4894,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.028205857264714244,
898
+ "grad_norm": 12.45561695098877,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.9834,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.028433323855558714,
905
+ "grad_norm": 14.46573257446289,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 6.5757,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.028660790446403184,
912
+ "grad_norm": 10.923254013061523,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.1281,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.028888257037247653,
919
+ "grad_norm": 13.554349899291992,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 6.6561,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.029115723628092123,
926
+ "grad_norm": 12.60084342956543,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 6.1441,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.029343190218936593,
933
+ "grad_norm": 12.465630531311035,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.3392,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.029570656809781062,
940
+ "grad_norm": 14.023859977722168,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 6.109,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.029798123400625532,
947
+ "grad_norm": 12.172150611877441,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 6.4841,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03002558999147,
954
+ "grad_norm": 11.973929405212402,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 6.5025,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03025305658231447,
961
+ "grad_norm": 12.626691818237305,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.9404,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03048052317315894,
968
+ "grad_norm": 12.803211212158203,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 6.2931,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03070798976400341,
975
+ "grad_norm": 14.181547164916992,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 6.6704,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03093545635484788,
982
+ "grad_norm": 13.545026779174805,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 6.7224,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03116292294569235,
989
+ "grad_norm": 12.032373428344727,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 6.25,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03139038953653682,
996
+ "grad_norm": 13.542147636413574,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 7.1351,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03161785612738129,
1003
+ "grad_norm": 14.927430152893066,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 6.9813,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03184532271822576,
1010
+ "grad_norm": 14.990326881408691,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 7.0015,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03207278930907023,
1017
+ "grad_norm": 14.314873695373535,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 7.53,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0323002558999147,
1024
+ "grad_norm": 16.397851943969727,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 8.4307,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03252772249075917,
1031
+ "grad_norm": 14.191055297851562,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 7.5042,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03275518908160364,
1038
+ "grad_norm": 14.179217338562012,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 7.2985,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03298265567244811,
1045
+ "grad_norm": 24.625808715820312,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 5.7651,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03321012226329258,
1052
+ "grad_norm": 14.160369873046875,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 7.54,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03343758885413705,
1059
+ "grad_norm": 16.07367515563965,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 8.1794,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.033665055444981516,
1066
+ "grad_norm": 15.326973915100098,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 7.2608,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03389252203582599,
1073
+ "grad_norm": 17.90393829345703,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 7.4912,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.034119988626670456,
1080
+ "grad_norm": 32.38639831542969,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 8.0163,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.034119988626670456,
1087
+ "eval_loss": 1.427915096282959,
1088
+ "eval_runtime": 570.6727,
1089
+ "eval_samples_per_second": 12.974,
1090
+ "eval_steps_per_second": 3.244,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.247637880316887e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null