lesso commited on
Commit
aba3955
·
verified ·
1 Parent(s): b49a44a

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:ab556da0acb6965bb1d916e54bee52c8a41548054c6377c1250046e996774fed
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a594294ad85b1a65161a277299c6adce2edcef0026c9d3c1662b831824255867
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653e3901adf2f35e7f482587490b658f24346c49b398781812d396eb817c38c7
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eebd3fc450ecfb30813438bca73c9198e7d2295086b711c59c4a1f1b94ef6f9b
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d4f82194923c4e839c5b924f9c84d17ba32c8dc232adb7a3f482821b860cb9e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4516ce3b22c94085368cebacdccc1b800c7c499b843c80d9eda4fcde1256d71
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a1533051e4bee653afc683a4359c329f95831c0354ae8442616cabf80d0caa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6352062821388245,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10085728693898134,
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": 4.115,
732
  "eval_steps_per_second": 1.034,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.648580773235917e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6004343032836914,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15128593040847202,
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": 4.115,
732
  "eval_steps_per_second": 1.034,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10186585980837115,
737
+ "grad_norm": 0.6869097352027893,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 0.6356,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10287443267776097,
744
+ "grad_norm": 0.6879076957702637,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 0.6521,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10388300554715078,
751
+ "grad_norm": 0.66792893409729,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 0.6565,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10489157841654059,
758
+ "grad_norm": 0.6843271851539612,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 0.5228,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1059001512859304,
765
+ "grad_norm": 0.6975498795509338,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 0.6419,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10690872415532023,
772
+ "grad_norm": 0.6737810969352722,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 0.6125,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10791729702471003,
779
+ "grad_norm": 0.6993482112884521,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 0.562,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10892586989409984,
786
+ "grad_norm": 0.8742977976799011,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 0.5416,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10993444276348967,
793
+ "grad_norm": 0.583231508731842,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 0.51,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11094301563287948,
800
+ "grad_norm": 0.588787317276001,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 0.5598,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11195158850226929,
807
+ "grad_norm": 0.6221970915794373,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 0.4689,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1129601613716591,
814
+ "grad_norm": 0.8723281621932983,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 0.6268,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11396873424104892,
821
+ "grad_norm": 0.6584269404411316,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 0.5304,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11497730711043873,
828
+ "grad_norm": 0.6377540826797485,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 0.5684,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11598587997982854,
835
+ "grad_norm": 0.6488873362541199,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 0.665,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11699445284921836,
842
+ "grad_norm": 0.6601778268814087,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 0.5466,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11800302571860817,
849
+ "grad_norm": 0.7301647067070007,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 0.6203,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11901159858799798,
856
+ "grad_norm": 0.6224742531776428,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 0.6334,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1200201714573878,
863
+ "grad_norm": 0.7299985885620117,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 0.6082,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12102874432677761,
870
+ "grad_norm": 0.6680064797401428,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 0.5914,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12203731719616742,
877
+ "grad_norm": 0.7570561170578003,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 0.6341,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12304589006555723,
884
+ "grad_norm": 0.7060465216636658,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 0.608,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12405446293494705,
891
+ "grad_norm": 0.7083133459091187,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 0.6731,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12506303580433686,
898
+ "grad_norm": 0.6821840405464172,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 0.5981,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1260716086737267,
905
+ "grad_norm": 0.8325244784355164,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 0.6842,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12708018154311648,
912
+ "grad_norm": 0.7018126845359802,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 0.5196,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1280887544125063,
919
+ "grad_norm": 0.6488572359085083,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 0.5191,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12909732728189613,
926
+ "grad_norm": 0.7428427338600159,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 0.6441,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13010590015128592,
933
+ "grad_norm": 0.795226514339447,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 0.5661,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13111447302067575,
940
+ "grad_norm": 0.6325244903564453,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 0.5422,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13212304589006554,
947
+ "grad_norm": 0.7234381437301636,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 0.5709,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13313161875945537,
954
+ "grad_norm": 0.7622341513633728,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 0.4704,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1341401916288452,
961
+ "grad_norm": 0.707838237285614,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 0.6442,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13514876449823499,
968
+ "grad_norm": 0.7565646767616272,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 0.7482,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1361573373676248,
975
+ "grad_norm": 0.7385073304176331,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 0.6644,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13716591023701463,
982
+ "grad_norm": 0.6985095143318176,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 0.5484,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13817448310640443,
989
+ "grad_norm": 0.7134766578674316,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 0.542,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.13918305597579425,
996
+ "grad_norm": 0.7676419019699097,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 0.6308,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14019162884518407,
1003
+ "grad_norm": 0.8243915438652039,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 0.6686,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14120020171457387,
1010
+ "grad_norm": 0.7785696387290955,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 0.6185,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1422087745839637,
1017
+ "grad_norm": 0.8271362781524658,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 0.6464,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14321734745335352,
1024
+ "grad_norm": 1.1796181201934814,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 0.6272,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1442259203227433,
1031
+ "grad_norm": 0.7917830348014832,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 0.614,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14523449319213314,
1038
+ "grad_norm": 0.8672283887863159,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 0.6808,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14624306606152296,
1045
+ "grad_norm": 1.00629723072052,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 0.8009,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14725163893091275,
1052
+ "grad_norm": 0.9548422694206238,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 0.715,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14826021180030258,
1059
+ "grad_norm": 0.9227573871612549,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 0.73,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14926878466969237,
1066
+ "grad_norm": 0.9087833762168884,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 0.6576,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1502773575390822,
1073
+ "grad_norm": 0.9994284510612488,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 0.7382,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15128593040847202,
1080
+ "grad_norm": 1.1259467601776123,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 0.7146,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15128593040847202,
1087
+ "eval_loss": 0.6004343032836914,
1088
+ "eval_runtime": 101.5492,
1089
+ "eval_samples_per_second": 4.116,
1090
+ "eval_steps_per_second": 1.034,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2972871159853875e+17,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null