prxy5605 commited on
Commit
dea83ef
·
verified ·
1 Parent(s): 1d6dd1e

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 sha256:97efde25644ce733034b4eb47814f39b31f4de0df69051a60d92636f50451312
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6960406493dc43e08dc486675d7bc0de7d041d59c89dfd9fbb07ef59b64e44
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef7ec2ad0192a041371aa1964a96d6270dcecf67aed6e4fb9a23d19a23b90b36
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415651bc677fa8a43504e8690766b4b40f04c3199e690c34de970c9a833c77bf
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a416455331f137495054250517b3069fa88696bc8153f10063ef17ad6e64d86a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6817e6a4d659fca10ea9e56af8f37365a6cf5da2f5b3a3c564e42db42bd60e
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": 1.3684649467468262,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0435777317790609,
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": 12.153,
732
  "eval_steps_per_second": 6.078,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4307262039955866e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3558998107910156,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.06536659766859135,
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": 12.153,
732
  "eval_steps_per_second": 6.078,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.04401350909685151,
737
+ "grad_norm": 0.6644337177276611,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 1.43,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.04444928641464212,
744
+ "grad_norm": 0.6406741142272949,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.4389,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.04488506373243273,
751
+ "grad_norm": 0.6088762283325195,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.3575,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.04532084105022333,
758
+ "grad_norm": 0.5756306052207947,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.2714,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.045756618368013945,
765
+ "grad_norm": 0.5706756711006165,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.3047,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.046192395685804556,
772
+ "grad_norm": 0.6538943648338318,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.4369,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.04662817300359516,
779
+ "grad_norm": 0.6861059665679932,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.386,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04706395032138577,
786
+ "grad_norm": 0.667604386806488,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.3972,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.047499727639176384,
793
+ "grad_norm": 0.5741658210754395,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.3382,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04793550495696699,
800
+ "grad_norm": 0.6127682328224182,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.3597,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0483712822747576,
807
+ "grad_norm": 0.6162969470024109,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.3884,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.048807059592548205,
814
+ "grad_norm": 0.6853535771369934,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.5718,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.049242836910338816,
821
+ "grad_norm": 0.6162100434303284,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.4271,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.04967861422812943,
828
+ "grad_norm": 0.5969780087471008,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.3138,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.05011439154592003,
835
+ "grad_norm": 0.563022792339325,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.2623,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.050550168863710644,
842
+ "grad_norm": 0.658589780330658,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.4113,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.050985946181501256,
849
+ "grad_norm": 0.6488298773765564,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.4764,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.05142172349929186,
856
+ "grad_norm": 0.6470029950141907,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.3366,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.05185750081708247,
863
+ "grad_norm": 0.6214532852172852,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.3507,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.05229327813487308,
870
+ "grad_norm": 0.6346096396446228,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.36,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.05272905545266369,
877
+ "grad_norm": 0.6477368474006653,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.4248,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0531648327704543,
884
+ "grad_norm": 0.6995759606361389,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.2993,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.053600610088244904,
891
+ "grad_norm": 0.6448193788528442,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.4006,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.054036387406035516,
898
+ "grad_norm": 0.5889584422111511,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.3996,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.05447216472382613,
905
+ "grad_norm": 0.6430240869522095,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.3608,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.05490794204161673,
912
+ "grad_norm": 0.6376746296882629,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.3421,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.055343719359407344,
919
+ "grad_norm": 0.6999002695083618,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.4008,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.055779496677197955,
926
+ "grad_norm": 0.622456431388855,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.3804,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.05621527399498856,
933
+ "grad_norm": 0.6279011368751526,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.3072,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.05665105131277917,
940
+ "grad_norm": 0.612434446811676,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.2956,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.057086828630569776,
947
+ "grad_norm": 0.6098705530166626,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.3117,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.05752260594836039,
954
+ "grad_norm": 0.6360723376274109,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.279,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.057958383266151,
961
+ "grad_norm": 0.6856507062911987,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.3226,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.058394160583941604,
968
+ "grad_norm": 0.6899363994598389,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.3294,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.058829937901732215,
975
+ "grad_norm": 0.6617586016654968,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.4432,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.05926571521952283,
982
+ "grad_norm": 0.712164580821991,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.4219,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05970149253731343,
989
+ "grad_norm": 0.6878612637519836,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.3542,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.06013726985510404,
996
+ "grad_norm": 0.690792977809906,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.319,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.06057304717289465,
1003
+ "grad_norm": 0.7101471424102783,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.3666,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.06100882449068526,
1010
+ "grad_norm": 0.7041705250740051,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.3118,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.06144460180847587,
1017
+ "grad_norm": 0.6758811473846436,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.2953,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.061880379126266476,
1024
+ "grad_norm": 0.7130976319313049,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.3082,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.06231615644405709,
1031
+ "grad_norm": 0.6844936013221741,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.2318,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.06275193376184769,
1038
+ "grad_norm": 0.7062429785728455,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.2312,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0631877110796383,
1045
+ "grad_norm": 0.6911125779151917,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.288,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.06362348839742892,
1052
+ "grad_norm": 0.6440110802650452,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.2698,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.06405926571521953,
1059
+ "grad_norm": 0.6771082878112793,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.2934,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.06449504303301014,
1066
+ "grad_norm": 0.6761582493782043,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.189,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.06493082035080074,
1073
+ "grad_norm": 0.722388505935669,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.3512,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.06536659766859135,
1080
+ "grad_norm": 0.7161824107170105,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.3205,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.06536659766859135,
1087
+ "eval_loss": 1.3558998107910156,
1088
+ "eval_runtime": 318.2564,
1089
+ "eval_samples_per_second": 12.144,
1090
+ "eval_steps_per_second": 6.074,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.1443053581080986e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null