arcwarden46 commited on
Commit
9f93785
·
verified ·
1 Parent(s): 59e7c13

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:b891797876220ccdbcb44810208e98022965b68b40e086c344b5de7f6cc6487d
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44724e2d4a89f5955b389dc74f202a1c863731eef26d020703090613c6c2280
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f428067e505d06d5e704bc119f456c513e0a0857d70c5c68e8d621d88835d7
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7d4d885cb0314a46dc9a8bee947aa8bca2532cc4b55ff2a1ac732e63f9246c
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c258c46613a0a1b7bfc77bb59bab07d92cddda90d5d4bcbfbd14dbaca6100db
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f269f88e6c3f8ca85570234591bbe63ac5bf86a81f11be0d6edb49cb9f818d31
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": 1.363740086555481,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.010311670232785956,
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": 32.228,
732
  "eval_steps_per_second": 8.058,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.433129108832256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3284672498703003,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.015467505349178933,
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": 32.228,
732
  "eval_steps_per_second": 8.058,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.010414786935113815,
737
+ "grad_norm": 0.14795686304569244,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9004,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.010517903637441674,
744
+ "grad_norm": 0.17717111110687256,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0257,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.010621020339769534,
751
+ "grad_norm": 0.18498282134532928,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.0396,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.010724137042097393,
758
+ "grad_norm": 0.19741852581501007,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.1009,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.010827253744425253,
765
+ "grad_norm": 0.20189106464385986,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.0569,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.010930370446753114,
772
+ "grad_norm": 0.20939910411834717,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0656,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.011033487149080973,
779
+ "grad_norm": 0.2105722278356552,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0898,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.011136603851408832,
786
+ "grad_norm": 0.19876085221767426,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9473,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.011239720553736692,
793
+ "grad_norm": 0.20182077586650848,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0884,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.011342837256064551,
800
+ "grad_norm": 0.18769417703151703,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9572,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01144595395839241,
807
+ "grad_norm": 0.18182441592216492,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0277,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01154907066072027,
814
+ "grad_norm": 0.1890416145324707,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.9458,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01165218736304813,
821
+ "grad_norm": 0.1826457679271698,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.042,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.011755304065375989,
828
+ "grad_norm": 0.21521930396556854,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.0792,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.011858420767703848,
835
+ "grad_norm": 0.2592601776123047,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.2465,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01196153747003171,
842
+ "grad_norm": 0.351700097322464,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.4669,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.012064654172359569,
849
+ "grad_norm": 0.4038744568824768,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.4436,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.012167770874687428,
856
+ "grad_norm": 0.3753279745578766,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.4066,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.012270887577015287,
863
+ "grad_norm": 0.33974844217300415,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3319,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.012374004279343147,
870
+ "grad_norm": 0.3477650284767151,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.4443,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.012477120981671006,
877
+ "grad_norm": 0.40520280599594116,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.5132,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.012580237683998866,
884
+ "grad_norm": 0.3967605233192444,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.4972,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.012683354386326725,
891
+ "grad_norm": 0.4460206627845764,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6543,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.012786471088654584,
898
+ "grad_norm": 0.4313359558582306,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.7027,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.012889587790982444,
905
+ "grad_norm": 0.38823527097702026,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.5328,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.012992704493310303,
912
+ "grad_norm": 0.4104168713092804,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4856,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.013095821195638164,
919
+ "grad_norm": 0.44358229637145996,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.5431,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.013198937897966024,
926
+ "grad_norm": 0.419261634349823,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.5564,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.013302054600293883,
933
+ "grad_norm": 0.468816876411438,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.5998,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.013405171302621742,
940
+ "grad_norm": 0.40720266103744507,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.6278,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.013508288004949602,
947
+ "grad_norm": 0.37988948822021484,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4482,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.013611404707277461,
954
+ "grad_norm": 0.41549137234687805,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.4159,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01371452140960532,
961
+ "grad_norm": 0.4578942656517029,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.7196,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.01381763811193318,
968
+ "grad_norm": 0.37664926052093506,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4267,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01392075481426104,
975
+ "grad_norm": 0.4693012833595276,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.5935,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.014023871516588899,
982
+ "grad_norm": 0.38475286960601807,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.3708,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.01412698821891676,
989
+ "grad_norm": 0.45392167568206787,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1787,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01423010492124462,
996
+ "grad_norm": 0.49088478088378906,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3393,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.014333221623572479,
1003
+ "grad_norm": 0.5570761561393738,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.4169,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.014436338325900338,
1010
+ "grad_norm": 0.5477977991104126,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.3538,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.014539455028228197,
1017
+ "grad_norm": 0.5661804676055908,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2375,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.014642571730556057,
1024
+ "grad_norm": 0.5767088532447815,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.2619,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.014745688432883916,
1031
+ "grad_norm": 0.6942093968391418,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.4754,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.014848805135211775,
1038
+ "grad_norm": 0.6901765465736389,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.485,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.014951921837539635,
1045
+ "grad_norm": 0.7722551822662354,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.4824,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.015055038539867494,
1052
+ "grad_norm": 0.7323166131973267,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.3823,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.015158155242195355,
1059
+ "grad_norm": 0.7713239192962646,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.421,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.015261271944523215,
1066
+ "grad_norm": 0.9180830121040344,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.4636,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.015364388646851074,
1073
+ "grad_norm": 0.8078856468200684,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4319,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.015467505349178933,
1080
+ "grad_norm": 1.2015869617462158,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.7577,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.015467505349178933,
1087
+ "eval_loss": 1.3284672498703003,
1088
+ "eval_runtime": 506.7409,
1089
+ "eval_samples_per_second": 32.233,
1090
+ "eval_steps_per_second": 8.059,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.145557363117261e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null