prxy5605 commited on
Commit
b16569b
·
verified ·
1 Parent(s): feaacee

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 sha256:4d6d025c38202d7987ee426151328b7612425c438c05ca9732083d682444a78d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06dd4a8ad0b1d30ba6740d0925be9d80ca6c2a9a7eae7dc04bca1abcaddf15ee
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bce81c1d83fa2e10d0a288ac0ce4a34d1786db0c43d6da813d17aa3d07319346
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86c174f1431d3a36b8db2dfd355307771f2aeca7f648a4d66a65dfce14f2e23
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:095a5dbc60995a1f237ab3f197cce7aef4d06809ef2d17a6c3188fde144e0eb9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ef399be744db3c6c85f5e78e06088fae0e5d9ba90a3ef3cce3ff3c79eba66d
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": 1.2719783782958984,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.45300113250283125,
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": 13.235,
732
  "eval_steps_per_second": 3.309,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0218840837478638,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6795016987542469,
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": 13.235,
732
  "eval_steps_per_second": 3.309,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4575311438278596,
737
+ "grad_norm": 2.714219570159912,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.0719,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.46206115515288787,
744
+ "grad_norm": 1.833893060684204,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8059,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4665911664779162,
751
+ "grad_norm": 1.7362415790557861,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.8914,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4711211778029445,
758
+ "grad_norm": 1.587952971458435,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0055,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.47565118912797283,
765
+ "grad_norm": 1.382871389389038,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.853,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4801812004530011,
772
+ "grad_norm": 1.427045226097107,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9621,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.48471121177802945,
779
+ "grad_norm": 1.2589244842529297,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8243,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.48924122310305773,
786
+ "grad_norm": 1.1731473207473755,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8862,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.49377123442808607,
793
+ "grad_norm": 1.2672301530838013,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8736,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4983012457531144,
800
+ "grad_norm": 1.1130244731903076,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8778,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5028312570781427,
807
+ "grad_norm": 1.2738019227981567,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0309,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.507361268403171,
814
+ "grad_norm": 1.1945719718933105,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.9288,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5118912797281994,
821
+ "grad_norm": 1.153830885887146,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.997,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5164212910532276,
828
+ "grad_norm": 1.128495693206787,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.862,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5209513023782559,
835
+ "grad_norm": 1.2062228918075562,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0172,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5254813137032842,
842
+ "grad_norm": 1.1854007244110107,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9473,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5300113250283126,
849
+ "grad_norm": 1.105261206626892,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.8747,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5345413363533409,
856
+ "grad_norm": 1.1203992366790771,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7881,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5390713476783692,
863
+ "grad_norm": 1.1720339059829712,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9116,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5436013590033975,
870
+ "grad_norm": 1.220534086227417,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7269,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5481313703284258,
877
+ "grad_norm": 1.1943268775939941,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9006,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5526613816534541,
884
+ "grad_norm": 1.1528831720352173,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8354,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5571913929784824,
891
+ "grad_norm": 1.2273133993148804,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8162,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5617214043035108,
898
+ "grad_norm": 1.2099953889846802,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.8402,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5662514156285391,
905
+ "grad_norm": 1.1575597524642944,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9024,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5707814269535674,
912
+ "grad_norm": 1.4714939594268799,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.0202,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5753114382785957,
919
+ "grad_norm": 1.4315725564956665,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0502,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.579841449603624,
926
+ "grad_norm": 1.5543477535247803,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.1694,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5843714609286523,
933
+ "grad_norm": 1.3127039670944214,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.9434,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5889014722536806,
940
+ "grad_norm": 1.568535327911377,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1988,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5934314835787089,
947
+ "grad_norm": 1.353140950202942,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.8726,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5979614949037373,
954
+ "grad_norm": 1.4939686059951782,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.2155,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6024915062287656,
961
+ "grad_norm": 1.489733099937439,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.923,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6070215175537939,
968
+ "grad_norm": 1.6046398878097534,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.1015,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6115515288788222,
975
+ "grad_norm": 1.578744888305664,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2103,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6160815402038505,
982
+ "grad_norm": 1.431128740310669,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8943,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6206115515288788,
989
+ "grad_norm": 1.9715696573257446,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3989,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6251415628539071,
996
+ "grad_norm": 1.8589072227478027,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.5329,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6296715741789355,
1003
+ "grad_norm": 1.8302171230316162,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.1766,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6342015855039638,
1010
+ "grad_norm": 2.0135345458984375,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.4761,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.638731596828992,
1017
+ "grad_norm": 1.8871492147445679,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.9438,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6432616081540203,
1024
+ "grad_norm": 2.027357578277588,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1982,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6477916194790487,
1031
+ "grad_norm": 2.037635564804077,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1497,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.652321630804077,
1038
+ "grad_norm": 1.9788384437561035,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.3363,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6568516421291053,
1045
+ "grad_norm": 1.8388274908065796,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2891,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6613816534541337,
1052
+ "grad_norm": 1.6475542783737183,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0235,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.665911664779162,
1059
+ "grad_norm": 2.038667917251587,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1535,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6704416761041903,
1066
+ "grad_norm": 2.430046796798706,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.3292,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6749716874292185,
1073
+ "grad_norm": 2.0234296321868896,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.3348,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6795016987542469,
1080
+ "grad_norm": 2.2200522422790527,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.3524,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6795016987542469,
1087
+ "eval_loss": 1.0218840837478638,
1088
+ "eval_runtime": 28.1145,
1089
+ "eval_samples_per_second": 13.232,
1090
+ "eval_steps_per_second": 3.308,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null