lesso12 commited on
Commit
036a88f
·
verified ·
1 Parent(s): 5365aec

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:c268a968469ce5bdb163868ef7a39513f3ce100500f548076454fb362101818f
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6657a226cc0c3e14f29fa370deb9e3caa775840677e244efcc32831037a36d5a
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ff0ecbc3dd55945258109ca348b084fe566682a070abd9553684ae9db17483
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c018df9e83db2d92c241d99012be2dcc0322a1f2d180ac4b86bd9a7a2f4541b
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b17708d9648299288e0c2b2842c837451cc839482b30f36568b7b117b8a6cbe5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1f766df65bea57494f01e4f4c52272697127fbef8384c36b4d737b1bb7c772
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2ff91019f251b72cdf781986424ccdfd5ceb7ae633fedb2bccce31d3f61847
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970068ebf9c0dc6a40c93653c563bb0b2ba5296a6c46496b504a3f1343bf3a62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.47890180349349976,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.42016806722689076,
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": 1.48,
732
  "eval_steps_per_second": 0.373,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.57603212935168e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.14084061980247498,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6302521008403361,
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": 1.48,
732
  "eval_steps_per_second": 0.373,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.42436974789915966,
737
+ "grad_norm": 4.169086933135986,
738
+ "learning_rate": 5.8634982137913465e-05,
739
+ "loss": 0.5264,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.42857142857142855,
744
+ "grad_norm": 1.9985085725784302,
745
+ "learning_rate": 5.772710650702723e-05,
746
+ "loss": 0.1248,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4327731092436975,
751
+ "grad_norm": 0.057010602205991745,
752
+ "learning_rate": 5.681848531245195e-05,
753
+ "loss": 0.0331,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4369747899159664,
758
+ "grad_norm": 0.07370073348283768,
759
+ "learning_rate": 5.590936696214972e-05,
760
+ "loss": 0.0401,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4411764705882353,
765
+ "grad_norm": 0.07470442354679108,
766
+ "learning_rate": 5.5e-05,
767
+ "loss": 0.0451,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.44537815126050423,
772
+ "grad_norm": 0.07614938914775848,
773
+ "learning_rate": 5.409063303785029e-05,
774
+ "loss": 0.05,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4495798319327731,
779
+ "grad_norm": 0.07786896824836731,
780
+ "learning_rate": 5.318151468754805e-05,
781
+ "loss": 0.0505,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.453781512605042,
786
+ "grad_norm": 0.07709647715091705,
787
+ "learning_rate": 5.227289349297277e-05,
788
+ "loss": 0.0517,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4579831932773109,
793
+ "grad_norm": 0.07772062718868256,
794
+ "learning_rate": 5.136501786208654e-05,
795
+ "loss": 0.0539,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.46218487394957986,
800
+ "grad_norm": 0.07466543465852737,
801
+ "learning_rate": 5.045813599902173e-05,
802
+ "loss": 0.0563,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.46638655462184875,
807
+ "grad_norm": 0.07618583738803864,
808
+ "learning_rate": 4.955249583622455e-05,
809
+ "loss": 0.0543,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.47058823529411764,
814
+ "grad_norm": 0.0762595385313034,
815
+ "learning_rate": 4.8648344966672767e-05,
816
+ "loss": 0.0534,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.47478991596638653,
821
+ "grad_norm": 0.07716407626867294,
822
+ "learning_rate": 4.774593057618621e-05,
823
+ "loss": 0.0501,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.4789915966386555,
828
+ "grad_norm": 0.07322922348976135,
829
+ "learning_rate": 4.6845499375848686e-05,
830
+ "loss": 0.0509,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.4831932773109244,
835
+ "grad_norm": 0.0707123726606369,
836
+ "learning_rate": 4.5947297534559625e-05,
837
+ "loss": 0.0482,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.48739495798319327,
842
+ "grad_norm": 0.07027147710323334,
843
+ "learning_rate": 4.5051570611733976e-05,
844
+ "loss": 0.0489,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.49159663865546216,
849
+ "grad_norm": 0.06395595520734787,
850
+ "learning_rate": 4.415856349016859e-05,
851
+ "loss": 0.045,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4957983193277311,
856
+ "grad_norm": 0.06482091546058655,
857
+ "learning_rate": 4.326852030909393e-05,
858
+ "loss": 0.0441,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5,
863
+ "grad_norm": 0.06443566083908081,
864
+ "learning_rate": 4.238168439742867e-05,
865
+ "loss": 0.0436,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5042016806722689,
870
+ "grad_norm": 0.06711577624082565,
871
+ "learning_rate": 4.149829820725605e-05,
872
+ "loss": 0.0436,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5084033613445378,
877
+ "grad_norm": 0.05877511948347092,
878
+ "learning_rate": 4.0618603247539916e-05,
879
+ "loss": 0.0432,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5126050420168067,
884
+ "grad_norm": 0.06349120289087296,
885
+ "learning_rate": 3.9742840018098564e-05,
886
+ "loss": 0.0508,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5168067226890757,
891
+ "grad_norm": 0.05786605551838875,
892
+ "learning_rate": 3.887124794385445e-05,
893
+ "loss": 0.0459,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5210084033613446,
898
+ "grad_norm": 0.058453019708395004,
899
+ "learning_rate": 3.80040653093779e-05,
900
+ "loss": 0.0446,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5252100840336135,
905
+ "grad_norm": 0.05471871420741081,
906
+ "learning_rate": 3.714152919374241e-05,
907
+ "loss": 0.0485,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5294117647058824,
912
+ "grad_norm": 0.06058911234140396,
913
+ "learning_rate": 3.628387540570963e-05,
914
+ "loss": 0.0462,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5336134453781513,
919
+ "grad_norm": 0.05696989595890045,
920
+ "learning_rate": 3.543133841926159e-05,
921
+ "loss": 0.0513,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5378151260504201,
926
+ "grad_norm": 0.04979941248893738,
927
+ "learning_rate": 3.458415130949785e-05,
928
+ "loss": 0.0616,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.542016806722689,
933
+ "grad_norm": 0.046740416437387466,
934
+ "learning_rate": 3.374254568891514e-05,
935
+ "loss": 0.0597,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5462184873949579,
940
+ "grad_norm": 0.048966214060783386,
941
+ "learning_rate": 3.290675164408669e-05,
942
+ "loss": 0.0661,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5504201680672269,
947
+ "grad_norm": 0.05556921288371086,
948
+ "learning_rate": 3.207699767275904e-05,
949
+ "loss": 0.0771,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5546218487394958,
954
+ "grad_norm": 0.058795638382434845,
955
+ "learning_rate": 3.12535106213829e-05,
956
+ "loss": 0.0708,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5588235294117647,
961
+ "grad_norm": 0.059710677713155746,
962
+ "learning_rate": 3.0436515623095647e-05,
963
+ "loss": 0.0702,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5630252100840336,
968
+ "grad_norm": 0.06440545618534088,
969
+ "learning_rate": 2.962623603617218e-05,
970
+ "loss": 0.0857,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5672268907563025,
975
+ "grad_norm": 0.059835322201251984,
976
+ "learning_rate": 2.8822893382960955e-05,
977
+ "loss": 0.0959,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5714285714285714,
982
+ "grad_norm": 0.06194557622075081,
983
+ "learning_rate": 2.802670728932207e-05,
984
+ "loss": 0.1121,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5756302521008403,
989
+ "grad_norm": 0.06737734377384186,
990
+ "learning_rate": 2.723789542458361e-05,
991
+ "loss": 0.1135,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5798319327731093,
996
+ "grad_norm": 0.06589267402887344,
997
+ "learning_rate": 2.6456673442033183e-05,
998
+ "loss": 0.1125,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5840336134453782,
1003
+ "grad_norm": 0.07247166335582733,
1004
+ "learning_rate": 2.5683254919960356e-05,
1005
+ "loss": 0.1377,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5882352941176471,
1010
+ "grad_norm": 0.07507860660552979,
1011
+ "learning_rate": 2.4917851303266533e-05,
1012
+ "loss": 0.1326,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.592436974789916,
1017
+ "grad_norm": 0.09094900637865067,
1018
+ "learning_rate": 2.4160671845658007e-05,
1019
+ "loss": 0.1411,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5966386554621849,
1024
+ "grad_norm": 0.09972415864467621,
1025
+ "learning_rate": 2.3411923552438105e-05,
1026
+ "loss": 0.1649,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6008403361344538,
1031
+ "grad_norm": 0.10327650606632233,
1032
+ "learning_rate": 2.2671811123913983e-05,
1033
+ "loss": 0.185,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6050420168067226,
1038
+ "grad_norm": 0.13001111149787903,
1039
+ "learning_rate": 2.194053689943362e-05,
1040
+ "loss": 0.2116,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6092436974789915,
1045
+ "grad_norm": 0.10833977162837982,
1046
+ "learning_rate": 2.121830080206827e-05,
1047
+ "loss": 0.2416,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6134453781512605,
1052
+ "grad_norm": 0.1772170066833496,
1053
+ "learning_rate": 2.0505300283955464e-05,
1054
+ "loss": 0.3062,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6176470588235294,
1059
+ "grad_norm": 0.2684325873851776,
1060
+ "learning_rate": 1.9801730272317585e-05,
1061
+ "loss": 0.4366,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6218487394957983,
1066
+ "grad_norm": 0.288666307926178,
1067
+ "learning_rate": 1.910778311617072e-05,
1068
+ "loss": 0.6787,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6260504201680672,
1073
+ "grad_norm": 0.31838375329971313,
1074
+ "learning_rate": 1.8423648533738342e-05,
1075
+ "loss": 0.9365,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6302521008403361,
1080
+ "grad_norm": 0.3195730745792389,
1081
+ "learning_rate": 1.7749513560584252e-05,
1082
+ "loss": 1.051,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6302521008403361,
1087
+ "eval_loss": 0.14084061980247498,
1088
+ "eval_runtime": 247.0151,
1089
+ "eval_samples_per_second": 1.623,
1090
+ "eval_steps_per_second": 0.409,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.86404819402752e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null