prxy5608 commited on
Commit
f8538a9
·
verified ·
1 Parent(s): a7276b4

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:d765fa0e90e8740349e19bf17f1d2b4bbfe010bca8028a281fade3a16a1e016f
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097f6d3629c1ab8d5bb388a3febfa06ccead317facdf11ef6a354ae3e55b70ec
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccd48b1a65ca04ed0e2cc9a0ab1260ab69973eb8c2aab0e8ba187bf7d6795d10
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38145e6067d36a2f1b2515687e7d08608528a09dbc93506ac54873a34723853b
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:671512a515a39068ef19d71faed55ffe45d350fe3c1007fbe71c139337192b08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2fb391e0f541ae75ac243584642cc078a99b6113189ea9393c62f913435e42
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": 0.434915691614151,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.39408866995073893,
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": 13.347,
732
  "eval_steps_per_second": 3.337,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.127130048351437e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2746962308883667,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5911330049261084,
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": 13.347,
732
  "eval_steps_per_second": 3.337,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3980295566502463,
737
+ "grad_norm": 0.9950315952301025,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.3496,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4019704433497537,
744
+ "grad_norm": 1.4049850702285767,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.4795,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4059113300492611,
751
+ "grad_norm": 1.1271802186965942,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2861,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4098522167487685,
758
+ "grad_norm": 1.2322853803634644,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.3483,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.41379310344827586,
765
+ "grad_norm": 1.181979775428772,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2755,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.41773399014778323,
772
+ "grad_norm": 1.2165412902832031,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.3267,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.42167487684729066,
779
+ "grad_norm": 1.3426710367202759,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3285,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.42561576354679803,
786
+ "grad_norm": 1.3296332359313965,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2895,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4295566502463054,
793
+ "grad_norm": 1.6037664413452148,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4341,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.43349753694581283,
800
+ "grad_norm": 1.3613358736038208,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.2708,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4374384236453202,
807
+ "grad_norm": 1.8670945167541504,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.4552,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.4413793103448276,
814
+ "grad_norm": 1.343572974205017,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2287,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.44532019704433495,
821
+ "grad_norm": 1.9313302040100098,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.4153,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.4492610837438424,
828
+ "grad_norm": 1.4682947397232056,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.3328,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.45320197044334976,
835
+ "grad_norm": 1.764954924583435,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3722,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.45714285714285713,
842
+ "grad_norm": 1.8122596740722656,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.3311,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.46108374384236456,
849
+ "grad_norm": 1.6849801540374756,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.3091,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.46502463054187193,
856
+ "grad_norm": 0.9165311455726624,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.101,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.4689655172413793,
863
+ "grad_norm": 2.010204553604126,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3682,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.4729064039408867,
870
+ "grad_norm": 1.6442277431488037,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.2343,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4768472906403941,
877
+ "grad_norm": 1.557530164718628,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.1875,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4807881773399015,
884
+ "grad_norm": 1.488112211227417,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.1714,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.48472906403940885,
891
+ "grad_norm": 1.8102607727050781,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.1938,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4886699507389163,
898
+ "grad_norm": 1.8396623134613037,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.1607,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.49261083743842365,
905
+ "grad_norm": 2.4509646892547607,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.2625,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.496551724137931,
912
+ "grad_norm": 1.8777393102645874,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.2728,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5004926108374385,
919
+ "grad_norm": 2.6126911640167236,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2017,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5044334975369458,
926
+ "grad_norm": 2.2730720043182373,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2649,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5083743842364532,
933
+ "grad_norm": 1.7744430303573608,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1378,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5123152709359606,
940
+ "grad_norm": 2.1662611961364746,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.1538,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.516256157635468,
947
+ "grad_norm": 2.4438276290893555,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.237,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5201970443349754,
954
+ "grad_norm": 1.7531158924102783,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.1383,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5241379310344828,
961
+ "grad_norm": 2.0699450969696045,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.1534,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5280788177339901,
968
+ "grad_norm": 3.246652126312256,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2998,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5320197044334976,
975
+ "grad_norm": 6.806807518005371,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.6264,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5359605911330049,
982
+ "grad_norm": 3.666675567626953,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.4792,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5399014778325123,
989
+ "grad_norm": 2.5924410820007324,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.525,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5438423645320197,
996
+ "grad_norm": 1.7887628078460693,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.2162,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.547783251231527,
1003
+ "grad_norm": 2.560127019882202,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.4434,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5517241379310345,
1010
+ "grad_norm": 1.782257080078125,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2569,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5556650246305419,
1017
+ "grad_norm": 1.762956976890564,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.277,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5596059113300492,
1024
+ "grad_norm": 1.4035093784332275,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.167,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5635467980295567,
1031
+ "grad_norm": 1.0826499462127686,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0938,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5674876847290641,
1038
+ "grad_norm": 1.010370135307312,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2034,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5714285714285714,
1045
+ "grad_norm": 1.454880952835083,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3517,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5753694581280788,
1052
+ "grad_norm": 1.653377652168274,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.4822,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5793103448275863,
1059
+ "grad_norm": 1.2127748727798462,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2397,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5832512315270936,
1066
+ "grad_norm": 1.2672176361083984,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.3219,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.587192118226601,
1073
+ "grad_norm": 1.0319257974624634,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.2282,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5911330049261084,
1080
+ "grad_norm": 2.236492395401001,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7111,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5911330049261084,
1087
+ "eval_loss": 0.2746962308883667,
1088
+ "eval_runtime": 31.9121,
1089
+ "eval_samples_per_second": 13.412,
1090
+ "eval_steps_per_second": 3.353,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0669976671223808e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null