prxy5605 commited on
Commit
96427cc
·
verified ·
1 Parent(s): ba7f8f8

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:f265d20d146f4e7fa4c6f76f80c9c73b1f36dc7254474f156ce6ff3d91b9d486
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07af564a71981bf730807a43c8394efa43e041b7260e866ebc9ce49175cd1f9c
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24182bdb9dd2b3d82b2ed9df6d90296d1464ebb2f1bda4c8022639f4e152b661
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39bd73db840a6e6c1eec5d6b767cfdd40057a09694dad4b8e1d1806fa4afe648
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23497d4d502105d9b958588fefb577aec8f2e43ebd8ab4f9c721b0a4560d33f0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c3fc278cf9acad581569e351f3981a9a35447df0340a9abed7401defcf1e0d
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": 0.008957763202488422,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.011198521795123043,
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": 13.919,
732
  "eval_steps_per_second": 3.48,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3371612024589517e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.007711287587881088,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.016797782692684567,
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": 13.919,
732
  "eval_steps_per_second": 3.48,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.011310507013074273,
737
+ "grad_norm": 0.08506631851196289,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0124,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.011422492231025505,
744
+ "grad_norm": 0.03572741150856018,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0088,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.011534477448976736,
751
+ "grad_norm": 0.028119171038269997,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0056,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.011646462666927966,
758
+ "grad_norm": 0.030382081866264343,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0051,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.011758447884879196,
765
+ "grad_norm": 0.03446408733725548,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0068,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.011870433102830426,
772
+ "grad_norm": 0.03344714641571045,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0051,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.011982418320781656,
779
+ "grad_norm": 0.05783190205693245,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0084,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.012094403538732887,
786
+ "grad_norm": 0.04610677435994148,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0055,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.012206388756684118,
793
+ "grad_norm": 0.04884983226656914,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0043,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.012318373974635349,
800
+ "grad_norm": 0.03212964907288551,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0059,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.012430359192586579,
807
+ "grad_norm": 0.09940595179796219,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0049,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.012542344410537809,
814
+ "grad_norm": 0.029751066118478775,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0022,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01265432962848904,
821
+ "grad_norm": 0.04463963583111763,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0072,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01276631484644027,
828
+ "grad_norm": 0.029815711081027985,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0032,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0128783000643915,
835
+ "grad_norm": 0.04161587730050087,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0126,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.012990285282342732,
842
+ "grad_norm": 0.02149057202041149,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.002,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.013102270500293962,
849
+ "grad_norm": 0.04231660068035126,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0057,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.013214255718245192,
856
+ "grad_norm": 0.08881816267967224,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.005,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.013326240936196422,
863
+ "grad_norm": 0.025332478806376457,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.004,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.013438226154147652,
870
+ "grad_norm": 0.02778369002044201,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0034,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.013550211372098882,
877
+ "grad_norm": 0.04420655220746994,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0071,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.013662196590050113,
884
+ "grad_norm": 0.0295578446239233,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.003,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.013774181808001345,
891
+ "grad_norm": 0.02409888431429863,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0032,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.013886167025952575,
898
+ "grad_norm": 0.022894464433193207,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0024,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.013998152243903805,
905
+ "grad_norm": 0.03507612273097038,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0073,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.014110137461855035,
912
+ "grad_norm": 0.06821553409099579,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0121,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.014222122679806265,
919
+ "grad_norm": 0.055723853409290314,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0103,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.014334107897757496,
926
+ "grad_norm": 0.025588707998394966,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0066,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.014446093115708726,
933
+ "grad_norm": 0.05048364773392677,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0052,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.014558078333659958,
940
+ "grad_norm": 0.03552013263106346,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0095,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.014670063551611188,
947
+ "grad_norm": 0.0784396305680275,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.014,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.014782048769562418,
954
+ "grad_norm": 0.08521043509244919,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0208,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.014894033987513648,
961
+ "grad_norm": 0.0778452605009079,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0096,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.015006019205464878,
968
+ "grad_norm": 0.33984890580177307,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.008,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.015118004423416109,
975
+ "grad_norm": 0.09499168395996094,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0119,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.015229989641367339,
982
+ "grad_norm": 0.14601409435272217,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0145,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.01534197485931857,
989
+ "grad_norm": 0.1081615462899208,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0108,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.015453960077269801,
996
+ "grad_norm": 0.11429034918546677,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0239,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.015565945295221031,
1003
+ "grad_norm": 0.04111011326313019,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0084,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01567793051317226,
1010
+ "grad_norm": 0.04043128341436386,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0083,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.015789915731123493,
1017
+ "grad_norm": 0.05154617875814438,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0052,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01590190094907472,
1024
+ "grad_norm": 0.08990739285945892,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0066,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.016013886167025954,
1031
+ "grad_norm": 0.04778852313756943,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0058,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.016125871384977182,
1038
+ "grad_norm": 0.028067700564861298,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0028,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.016237856602928414,
1045
+ "grad_norm": 0.08328656852245331,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.0133,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.016349841820879642,
1052
+ "grad_norm": 0.043928563594818115,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0079,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.016461827038830874,
1059
+ "grad_norm": 0.051368650048971176,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.006,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.016573812256782106,
1066
+ "grad_norm": 0.03745152801275253,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0047,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.016685797474733335,
1073
+ "grad_norm": 0.07638669013977051,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.0094,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.016797782692684567,
1080
+ "grad_norm": 0.20319393277168274,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.0327,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.016797782692684567,
1087
+ "eval_loss": 0.007711287587881088,
1088
+ "eval_runtime": 1079.213,
1089
+ "eval_samples_per_second": 13.936,
1090
+ "eval_steps_per_second": 3.484,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0057418036884275e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null