ancient41 commited on
Commit
f3666e2
·
verified ·
1 Parent(s): 6980d7b

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:c787b24bd44024109d98f8aa2676ee56e0943e69cb98bfad922603d0a98efff0
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcee6941a4cbcedd63d2b1cecf8b041fd000e0cabfe6654f9f091fc95acea05d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acd91ecc945c8019ccf633e240736cea161c3be8b97177861276864b9d9c4411
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690eecbb213ac3477d709c239c591e4ec4d7c126640ac2473796a283299dca4d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0969d39b6a03726473076e368e61af462cb30662f72d9029993a14099772069b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff025f2514b82a5e8352948d5a1aaeb460dc591874e4bdca4eb70ad37d10a7d
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": 0.8677875995635986,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3780718336483932,
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": 13.571,
732
  "eval_steps_per_second": 3.408,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8182804584503174,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5671077504725898,
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": 13.571,
732
  "eval_steps_per_second": 3.408,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3818525519848771,
737
+ "grad_norm": 9.579238891601562,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.5538,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3856332703213611,
744
+ "grad_norm": 9.08609390258789,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.6579,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.389413988657845,
751
+ "grad_norm": 8.470030784606934,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.5472,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3931947069943289,
758
+ "grad_norm": 7.983551502227783,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.126,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.39697542533081287,
765
+ "grad_norm": 8.211849212646484,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.2246,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4007561436672968,
772
+ "grad_norm": 7.689363479614258,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.3606,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4045368620037807,
779
+ "grad_norm": 7.449761390686035,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.4443,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.40831758034026466,
786
+ "grad_norm": 7.9302778244018555,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.3722,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4120982986767486,
793
+ "grad_norm": 8.147639274597168,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.4303,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4158790170132325,
800
+ "grad_norm": 7.9510498046875,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.3212,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.41965973534971646,
807
+ "grad_norm": 7.70236349105835,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.3949,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.42344045368620037,
814
+ "grad_norm": 7.634131908416748,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.0981,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.42722117202268434,
821
+ "grad_norm": 7.487667083740234,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.2295,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.43100189035916825,
828
+ "grad_norm": 8.120771408081055,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.1201,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.43478260869565216,
835
+ "grad_norm": 9.001714706420898,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.4735,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.43856332703213613,
842
+ "grad_norm": 7.907503604888916,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.2468,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.44234404536862004,
849
+ "grad_norm": 8.025362014770508,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.4063,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.44612476370510395,
856
+ "grad_norm": 7.450461387634277,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.9818,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.4499054820415879,
863
+ "grad_norm": 8.391257286071777,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.1225,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.45368620037807184,
870
+ "grad_norm": 8.543011665344238,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.2363,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.45746691871455575,
877
+ "grad_norm": 7.939721584320068,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.267,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4612476370510397,
884
+ "grad_norm": 9.583046913146973,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.4252,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.46502835538752363,
891
+ "grad_norm": 8.423657417297363,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.1331,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.46880907372400754,
898
+ "grad_norm": 8.184349060058594,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.0419,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4725897920604915,
905
+ "grad_norm": 10.645812034606934,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.1175,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4763705103969754,
912
+ "grad_norm": 8.734024047851562,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.1994,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.48015122873345933,
919
+ "grad_norm": 8.907480239868164,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.3357,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.4839319470699433,
926
+ "grad_norm": 9.246767044067383,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.1285,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4877126654064272,
933
+ "grad_norm": 9.020038604736328,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.3502,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.4914933837429111,
940
+ "grad_norm": 9.485525131225586,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.4852,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.4952741020793951,
947
+ "grad_norm": 9.426743507385254,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.4174,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.499054820415879,
954
+ "grad_norm": 8.460476875305176,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.1284,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.502835538752363,
961
+ "grad_norm": 11.027420997619629,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.3026,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5066162570888468,
968
+ "grad_norm": 8.760469436645508,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.3057,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5103969754253308,
975
+ "grad_norm": 8.567980766296387,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.0398,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5141776937618148,
982
+ "grad_norm": 8.330060005187988,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.8685,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5179584120982986,
989
+ "grad_norm": 9.437362670898438,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.0373,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5217391304347826,
996
+ "grad_norm": 7.858784198760986,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.936,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5255198487712666,
1003
+ "grad_norm": 9.211569786071777,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.3076,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5293005671077504,
1010
+ "grad_norm": 8.228165626525879,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.0484,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5330812854442344,
1017
+ "grad_norm": 8.578217506408691,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.1356,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5368620037807184,
1024
+ "grad_norm": 8.754902839660645,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.8195,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5406427221172023,
1031
+ "grad_norm": 9.32534408569336,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.5471,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5444234404536862,
1038
+ "grad_norm": 8.705456733703613,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.9405,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5482041587901701,
1045
+ "grad_norm": 11.633933067321777,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.3586,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5519848771266541,
1052
+ "grad_norm": 10.78929615020752,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.1784,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.555765595463138,
1059
+ "grad_norm": 9.891103744506836,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.952,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5595463137996219,
1066
+ "grad_norm": 12.48646354675293,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.1926,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5633270321361059,
1073
+ "grad_norm": 10.62431812286377,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.9827,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5671077504725898,
1080
+ "grad_norm": 10.362546920776367,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.9446,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5671077504725898,
1087
+ "eval_loss": 0.8182804584503174,
1088
+ "eval_runtime": 32.8641,
1089
+ "eval_samples_per_second": 13.571,
1090
+ "eval_steps_per_second": 3.408,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146499429400576e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null