prxy5608 commited on
Commit
68caa30
·
verified ·
1 Parent(s): 8b72df4

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 sha256:826c36ca30366c7ee75ff79ce8b9bf88fcf43a79bdb8b4ee95564dd71b7afb77
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7382ef32a9877a2ed869c16707f12992838ee714c26eca051bd1ebeded79f3
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b59a1a31f25665c0627e2bb70f978205718eaf26a2c65d552282f0856cb2322a
3
  size 281824770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f971d8bf3531bb23880707a42e65ac2cc4456198ec7b101205e76b4d9b0d386
3
  size 281824770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa7b44789e269747b34fd32afff7933f1573ae1e6e1cabed2899757679411e09
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5c27c4dddcba3be65a7d345a5bc86beeb9039cb39e1ea79f8014c8e2065816a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3735841512680054,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11296243998870376,
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": 37.024,
732
  "eval_steps_per_second": 18.524,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 9544675803267072.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3262138366699219,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.16944365998305563,
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": 37.024,
732
  "eval_steps_per_second": 18.524,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11409206438859079,
737
+ "grad_norm": 1.4661117792129517,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.2823,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.11522168878847783,
744
+ "grad_norm": 1.2689025402069092,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.2338,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.11635131318836486,
751
+ "grad_norm": 0.728518009185791,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.3032,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.11748093758825191,
758
+ "grad_norm": 0.5547231435775757,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.2473,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.11861056198813895,
765
+ "grad_norm": 0.5641574263572693,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.4354,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.11974018638802598,
772
+ "grad_norm": 0.47582149505615234,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.3457,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.12086981078791302,
779
+ "grad_norm": 0.45510634779930115,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.5321,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12199943518780006,
786
+ "grad_norm": 0.4705533981323242,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.39,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12312905958768709,
793
+ "grad_norm": 0.5092720985412598,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.4614,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12425868398757413,
800
+ "grad_norm": 0.4724782705307007,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.5284,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.12538830838746118,
807
+ "grad_norm": 0.4754285216331482,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.4385,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.12651793278734821,
814
+ "grad_norm": 0.4652653932571411,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.2717,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.12764755718723525,
821
+ "grad_norm": 0.46366190910339355,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.0826,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.12877718158712229,
828
+ "grad_norm": 0.5129349827766418,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.12,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.12990680598700932,
835
+ "grad_norm": 0.5288143754005432,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.2204,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.13103643038689636,
842
+ "grad_norm": 0.48036372661590576,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.1622,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1321660547867834,
849
+ "grad_norm": 0.5082106590270996,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.1976,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.13329567918667043,
856
+ "grad_norm": 0.46712690591812134,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.1619,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.13442530358655747,
863
+ "grad_norm": 0.476954847574234,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.2585,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1355549279864445,
870
+ "grad_norm": 0.5237648487091064,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.232,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.13668455238633154,
877
+ "grad_norm": 0.5067607760429382,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.1094,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.13781417678621857,
884
+ "grad_norm": 0.49429094791412354,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.1623,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1389438011861056,
891
+ "grad_norm": 0.4955546259880066,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.3095,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.14007342558599264,
898
+ "grad_norm": 0.5102877616882324,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.3287,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1412030499858797,
905
+ "grad_norm": 0.5063963532447815,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.3784,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14233267438576674,
912
+ "grad_norm": 0.5107027292251587,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.3058,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.14346229878565378,
919
+ "grad_norm": 0.5037428140640259,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.3713,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.14459192318554082,
926
+ "grad_norm": 0.5251663327217102,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.2503,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.14572154758542785,
933
+ "grad_norm": 0.5187826156616211,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.2749,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1468511719853149,
940
+ "grad_norm": 0.5050429105758667,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.2933,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.14798079638520192,
947
+ "grad_norm": 0.5002557039260864,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.3044,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.14911042078508896,
954
+ "grad_norm": 0.5536271929740906,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.2421,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.150240045184976,
961
+ "grad_norm": 0.5174810290336609,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.3492,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.15136966958486303,
968
+ "grad_norm": 0.5379897356033325,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.2034,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.15249929398475007,
975
+ "grad_norm": 0.536281943321228,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.3215,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1536289183846371,
982
+ "grad_norm": 0.566135585308075,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.4021,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.15475854278452414,
989
+ "grad_norm": 0.5772363543510437,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.4305,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.15588816718441117,
996
+ "grad_norm": 0.5848212242126465,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.3881,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.1570177915842982,
1003
+ "grad_norm": 0.5845930576324463,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.3913,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.15814741598418525,
1010
+ "grad_norm": 0.6087456345558167,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.483,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.15927704038407228,
1017
+ "grad_norm": 0.6329395771026611,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.6086,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.16040666478395935,
1024
+ "grad_norm": 0.625912070274353,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.4864,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.16153628918384638,
1031
+ "grad_norm": 0.6695480346679688,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.5817,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16266591358373342,
1038
+ "grad_norm": 0.6978421211242676,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.4269,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16379553798362045,
1045
+ "grad_norm": 0.7641833424568176,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.6088,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1649251623835075,
1052
+ "grad_norm": 0.7974191308021545,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.6181,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.16605478678339453,
1059
+ "grad_norm": 0.8420169949531555,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.6132,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.16718441118328156,
1066
+ "grad_norm": 0.9237271547317505,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.6012,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1683140355831686,
1073
+ "grad_norm": 1.0851755142211914,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.5464,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.16944365998305563,
1080
+ "grad_norm": 1.4369741678237915,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.6628,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.16944365998305563,
1087
+ "eval_loss": 1.3262138366699219,
1088
+ "eval_runtime": 40.2556,
1089
+ "eval_samples_per_second": 37.038,
1090
+ "eval_steps_per_second": 18.532,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.429769249882112e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null