prxy5607 commited on
Commit
4fc37fd
·
verified ·
1 Parent(s): 261ba55

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 sha256:14b2384f88b7ecfaa7d3c58157bdfa35162643397671d65445743372cba7cc51
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54e9495d965261b0f9feeb2d442c43e468e7547984658b8ce91909065409ee0
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f47ed66dadc89eb660d0fa705d9514572f7fc42d264e9b6e08256211bccc3bcb
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd88294d5e76bff603028285d1fbc87c9fabba4023a6701f1a2ae9e787ebf9c
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93868955788f316d8972e8cf811bd441e7d0fd237f4aae2e249bff92db8e0125
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f6e6c8a4bd3a551e728331c704bf76947e7b4596973fc6cc5a0a45a365d8ad
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": 0.5433698296546936,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10590415673815197,
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": 23.55,
732
  "eval_steps_per_second": 5.895,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.7353521946624e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5023760199546814,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15885623510722796,
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": 23.55,
732
  "eval_steps_per_second": 5.895,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1069631983055335,
737
+ "grad_norm": 2.4498658180236816,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0951,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10802223987291501,
744
+ "grad_norm": 3.297206163406372,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5397,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10908128144029654,
751
+ "grad_norm": 6.535586833953857,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.7827,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.11014032300767805,
758
+ "grad_norm": 5.509376525878906,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.388,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.11119936457505956,
765
+ "grad_norm": 14.902447700500488,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.4545,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.11225840614244109,
772
+ "grad_norm": 9.136420249938965,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.3523,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1133174477098226,
779
+ "grad_norm": 4.453599452972412,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.4496,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.11437648927720413,
786
+ "grad_norm": 2.747684955596924,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2555,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.11543553084458565,
793
+ "grad_norm": 1.1514734029769897,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3649,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11649457241196717,
800
+ "grad_norm": 1.0662457942962646,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3119,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11755361397934869,
807
+ "grad_norm": 1.0363942384719849,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2564,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11861265554673021,
814
+ "grad_norm": 0.991450846195221,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2594,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11967169711411173,
821
+ "grad_norm": 0.8109326362609863,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.2614,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.12073073868149325,
828
+ "grad_norm": 0.8643113374710083,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2497,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.12178978024887477,
835
+ "grad_norm": 0.7588681578636169,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.1104,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.12284882181625628,
842
+ "grad_norm": 0.4470180571079254,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.1131,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.12390786338363781,
849
+ "grad_norm": 0.740826427936554,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.218,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.12496690495101932,
856
+ "grad_norm": 0.6321307420730591,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.1568,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12602594651840085,
863
+ "grad_norm": 0.39843466877937317,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0865,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12708498808578236,
870
+ "grad_norm": 0.5428439974784851,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.1524,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12814402965316388,
877
+ "grad_norm": 0.7778955101966858,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.2212,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12920307122054542,
884
+ "grad_norm": 0.6086372137069702,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.2027,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.13026211278792693,
891
+ "grad_norm": 1.1050877571105957,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3415,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.13132115435530844,
898
+ "grad_norm": 0.786582350730896,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.232,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.13238019592268996,
905
+ "grad_norm": 0.8695224523544312,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.291,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.13343923749007147,
912
+ "grad_norm": 1.0951405763626099,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3707,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.134498279057453,
919
+ "grad_norm": 1.0619536638259888,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.4561,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.13555732062483453,
926
+ "grad_norm": 0.7016887664794922,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.3002,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13661636219221604,
933
+ "grad_norm": 0.8689793944358826,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.2976,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13767540375959755,
940
+ "grad_norm": 1.246698260307312,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3429,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1387344453269791,
947
+ "grad_norm": 0.7733801007270813,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.2483,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1397934868943606,
954
+ "grad_norm": 0.6558393836021423,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.1775,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.14085252846174212,
961
+ "grad_norm": 0.8950910568237305,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2029,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.14191157002912363,
968
+ "grad_norm": 0.8760111331939697,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.3004,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.14297061159650518,
975
+ "grad_norm": 0.7885894179344177,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.2863,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1440296531638867,
982
+ "grad_norm": 0.8052722811698914,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.2165,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1450886947312682,
989
+ "grad_norm": 0.5998448729515076,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.1542,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.14614773629864972,
996
+ "grad_norm": 0.563927173614502,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.1687,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14720677786603123,
1003
+ "grad_norm": 0.5400364995002747,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.1221,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14826581943341277,
1010
+ "grad_norm": 0.7391272783279419,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2194,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.14932486100079428,
1017
+ "grad_norm": 0.5647990703582764,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.1527,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1503839025681758,
1024
+ "grad_norm": 0.5798601508140564,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.1829,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1514429441355573,
1031
+ "grad_norm": 0.7401353120803833,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2007,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.15250198570293885,
1038
+ "grad_norm": 0.6129791736602783,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.1875,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.15356102727032037,
1045
+ "grad_norm": 0.46040213108062744,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.1631,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.15462006883770188,
1052
+ "grad_norm": 0.5951967239379883,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.1146,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1556791104050834,
1059
+ "grad_norm": 0.863836407661438,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.1582,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1567381519724649,
1066
+ "grad_norm": 0.8844537138938904,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.1491,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.15779719353984645,
1073
+ "grad_norm": 0.5204589366912842,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.1124,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15885623510722796,
1080
+ "grad_norm": 0.6919870972633362,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0894,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15885623510722796,
1087
+ "eval_loss": 0.5023760199546814,
1088
+ "eval_runtime": 67.4833,
1089
+ "eval_samples_per_second": 23.561,
1090
+ "eval_steps_per_second": 5.898,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.01030282919936e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null