cilooor commited on
Commit
7b92fd9
·
verified ·
1 Parent(s): 03c1954

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 sha256:08eddf5d2e1789ff2f97c75af72290ccecf51a8a5190d83f884a919bd7797fbc
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913d9e0b2e7313383348dccbf7f6f5714565d54b1a37803b1cdf3976d4f765c3
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9be178ef563b2fda0549454bcba7c6bac8dc41ee555d989efeef6bbcd010fb4d
3
  size 51613348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84169d42af36cf044b6ed85deb6f5d3c1fc26a07e04df7f6eddd94111fcc9962
3
  size 51613348
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a27e81cefaa8529725105e912d37767f2af2ad487c8790d604cb2445088ea2b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0612fcda79d6048d2cad54e51b631d9ff7aecf4af2413fcfdda06d15711e1f24
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b7af7cbef1883982510fef2007cf89af07627ee7ec1378e98375ea74556514a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb0f7a710adf9e599fc08ebbb5ad60e429eaaf1eaeec204e7c52cb45e30b9cf
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8693193197250366,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.05466721333880006,
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": 32.541,
732
  "eval_steps_per_second": 8.143,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.896121962482893e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8439501523971558,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08200082000820008,
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": 32.541,
732
  "eval_steps_per_second": 8.143,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05521388547218806,
737
+ "grad_norm": 0.44926929473876953,
738
+ "learning_rate": 4.3954497215805244e-05,
739
+ "loss": 0.63,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.05576055760557606,
744
+ "grad_norm": 0.34577685594558716,
745
+ "learning_rate": 4.332773182649165e-05,
746
+ "loss": 0.6255,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.05630722973896406,
751
+ "grad_norm": 0.37551775574684143,
752
+ "learning_rate": 4.2698122524388405e-05,
753
+ "loss": 0.8668,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.05685390187235206,
758
+ "grad_norm": 0.3831069767475128,
759
+ "learning_rate": 4.206588432049535e-05,
760
+ "loss": 0.7327,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.05740057400574006,
765
+ "grad_norm": 0.368376761674881,
766
+ "learning_rate": 4.143123312357996e-05,
767
+ "loss": 0.7613,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.05794724613912806,
772
+ "grad_norm": 0.2958766222000122,
773
+ "learning_rate": 4.079438566644454e-05,
774
+ "loss": 0.8557,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.05849391827251606,
779
+ "grad_norm": 0.2869422137737274,
780
+ "learning_rate": 4.015555943191231e-05,
781
+ "loss": 0.8202,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.05904059040590406,
786
+ "grad_norm": 0.2743949890136719,
787
+ "learning_rate": 3.9514972578557114e-05,
788
+ "loss": 0.824,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.05958726253929206,
793
+ "grad_norm": 0.2857745289802551,
794
+ "learning_rate": 3.8872843866202525e-05,
795
+ "loss": 0.8618,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06013393467268006,
800
+ "grad_norm": 0.2635364532470703,
801
+ "learning_rate": 3.8229392581215565e-05,
802
+ "loss": 0.7633,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06068060680606806,
807
+ "grad_norm": 0.27216577529907227,
808
+ "learning_rate": 3.7584838461620587e-05,
809
+ "loss": 0.8427,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.061227278939456065,
814
+ "grad_norm": 0.28717127442359924,
815
+ "learning_rate": 3.693940162205895e-05,
816
+ "loss": 0.7745,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.061773951072844065,
821
+ "grad_norm": 0.2799830138683319,
822
+ "learning_rate": 3.629330247862007e-05,
823
+ "loss": 0.7972,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.062320623206232065,
828
+ "grad_norm": 0.3147888779640198,
829
+ "learning_rate": 3.564676167356954e-05,
830
+ "loss": 0.8222,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06286729533962006,
835
+ "grad_norm": 0.30850040912628174,
836
+ "learning_rate": 3.5e-05,
837
+ "loss": 0.8039,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06341396747300806,
842
+ "grad_norm": 0.3144112229347229,
843
+ "learning_rate": 3.435323832643046e-05,
844
+ "loss": 0.7823,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06396063960639606,
849
+ "grad_norm": 0.3839268088340759,
850
+ "learning_rate": 3.370669752137993e-05,
851
+ "loss": 0.9132,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06450731173978407,
856
+ "grad_norm": 0.37383535504341125,
857
+ "learning_rate": 3.306059837794105e-05,
858
+ "loss": 0.8359,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06505398387317206,
863
+ "grad_norm": 0.42678016424179077,
864
+ "learning_rate": 3.241516153837941e-05,
865
+ "loss": 0.9635,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.06560065600656007,
870
+ "grad_norm": 0.478986918926239,
871
+ "learning_rate": 3.177060741878443e-05,
872
+ "loss": 0.8426,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.06614732813994807,
877
+ "grad_norm": 0.33792608976364136,
878
+ "learning_rate": 3.1127156133797475e-05,
879
+ "loss": 0.7594,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06669400027333607,
884
+ "grad_norm": 0.401961088180542,
885
+ "learning_rate": 3.048502742144289e-05,
886
+ "loss": 0.9038,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.06724067240672407,
891
+ "grad_norm": 0.3711259067058563,
892
+ "learning_rate": 2.984444056808768e-05,
893
+ "loss": 0.8834,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.06778734454011207,
898
+ "grad_norm": 0.4284830689430237,
899
+ "learning_rate": 2.9205614333555444e-05,
900
+ "loss": 0.8564,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.06833401667350007,
905
+ "grad_norm": 0.4255787134170532,
906
+ "learning_rate": 2.856876687642003e-05,
907
+ "loss": 0.7818,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.06888068880688807,
912
+ "grad_norm": 0.4699144959449768,
913
+ "learning_rate": 2.7934115679504645e-05,
914
+ "loss": 0.8755,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.06942736094027607,
919
+ "grad_norm": 0.4922056198120117,
920
+ "learning_rate": 2.7301877475611606e-05,
921
+ "loss": 0.908,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.06997403307366407,
926
+ "grad_norm": 0.47387874126434326,
927
+ "learning_rate": 2.667226817350835e-05,
928
+ "loss": 0.9525,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07052070520705207,
933
+ "grad_norm": 0.47072669863700867,
934
+ "learning_rate": 2.604550278419475e-05,
935
+ "loss": 0.8472,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07106737734044007,
940
+ "grad_norm": 0.595217764377594,
941
+ "learning_rate": 2.54217953474771e-05,
942
+ "loss": 0.8562,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07161404947382807,
947
+ "grad_norm": 0.585902214050293,
948
+ "learning_rate": 2.4801358858873636e-05,
949
+ "loss": 0.8419,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07216072160721607,
954
+ "grad_norm": 0.6359130144119263,
955
+ "learning_rate": 2.4184405196876842e-05,
956
+ "loss": 0.8576,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.07270739374060407,
961
+ "grad_norm": 0.532152533531189,
962
+ "learning_rate": 2.3571145050597088e-05,
963
+ "loss": 0.8793,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07325406587399207,
968
+ "grad_norm": 0.6238685250282288,
969
+ "learning_rate": 2.296178784781251e-05,
970
+ "loss": 0.8179,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07380073800738007,
975
+ "grad_norm": 0.7119914889335632,
976
+ "learning_rate": 2.2356541683449646e-05,
977
+ "loss": 0.9274,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07434741014076808,
982
+ "grad_norm": 0.7729023694992065,
983
+ "learning_rate": 2.175561324851914e-05,
984
+ "loss": 1.088,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.07489408227415607,
989
+ "grad_norm": 0.7109841108322144,
990
+ "learning_rate": 2.1159207759531013e-05,
991
+ "loss": 0.9875,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.07544075440754408,
996
+ "grad_norm": 0.6977630257606506,
997
+ "learning_rate": 2.0567528888413382e-05,
998
+ "loss": 0.8897,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.07598742654093207,
1003
+ "grad_norm": 0.7141391038894653,
1004
+ "learning_rate": 1.9980778692958684e-05,
1005
+ "loss": 0.9585,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.07653409867432008,
1010
+ "grad_norm": 0.7913526296615601,
1011
+ "learning_rate": 1.9399157547821162e-05,
1012
+ "loss": 0.8552,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.07708077080770807,
1017
+ "grad_norm": 0.9253504276275635,
1018
+ "learning_rate": 1.882286407608904e-05,
1019
+ "loss": 0.88,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.07762744294109608,
1024
+ "grad_norm": 1.1985421180725098,
1025
+ "learning_rate": 1.825209508145497e-05,
1026
+ "loss": 0.9832,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.07817411507448407,
1031
+ "grad_norm": 0.9133749008178711,
1032
+ "learning_rate": 1.7687045481007746e-05,
1033
+ "loss": 0.8496,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.07872078720787208,
1038
+ "grad_norm": 1.0693060159683228,
1039
+ "learning_rate": 1.712790823866826e-05,
1040
+ "loss": 0.9679,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.07926745934126007,
1045
+ "grad_norm": 1.4201616048812866,
1046
+ "learning_rate": 1.657487429929254e-05,
1047
+ "loss": 0.9618,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.07981413147464808,
1052
+ "grad_norm": 1.446235179901123,
1053
+ "learning_rate": 1.602813252346427e-05,
1054
+ "loss": 0.9855,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08036080360803607,
1059
+ "grad_norm": 1.2012956142425537,
1060
+ "learning_rate": 1.5487869622999004e-05,
1061
+ "loss": 0.8761,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08090747574142408,
1066
+ "grad_norm": 1.4860199689865112,
1067
+ "learning_rate": 1.4954270097182317e-05,
1068
+ "loss": 0.8868,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08145414787481207,
1073
+ "grad_norm": 1.4566800594329834,
1074
+ "learning_rate": 1.4427516169763444e-05,
1075
+ "loss": 0.8158,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08200082000820008,
1080
+ "grad_norm": 2.238769769668579,
1081
+ "learning_rate": 1.3907787726726029e-05,
1082
+ "loss": 0.9074,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08200082000820008,
1087
+ "eval_loss": 0.8439501523971558,
1088
+ "eval_runtime": 94.8117,
1089
+ "eval_samples_per_second": 32.496,
1090
+ "eval_steps_per_second": 8.132,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.351996222400102e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null