prxy5608 commited on
Commit
d75e43f
·
verified ·
1 Parent(s): ae7db3f

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 sha256:7680f5e46bb620e536c38d3acabd0169a76cb25320b02b9f940d3276e61bd028
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c642e79889f349e58a2f5dfab81f7af2428b270d406a84ad66a35122cb7c7b96
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:793eb1079425437da1600f12060f4850db4ba077af2f7c374d8ae7c44cb25d20
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b31bf2dc068da2825b1d1e89366f39d8a90ea101656a1c7feee8063dfd638a
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2473c96820a707f3cbdaa4179ad47f586a2842fee2a14455cb080b8f7c46e89
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aea95250d4565145f320a6c8868a36d6081ef50ac749e15b78a12847b9b9d6a
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": 1.48580801486969,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01204202667308908,
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": 8.604,
732
  "eval_steps_per_second": 2.151,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.250246901821604e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4118815660476685,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.018063040009633623,
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": 8.604,
732
  "eval_steps_per_second": 2.151,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.012162446939819972,
737
+ "grad_norm": 16.177490234375,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.4763,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.012282867206550863,
744
+ "grad_norm": 16.521148681640625,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.9816,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.012403287473281753,
751
+ "grad_norm": 14.81554126739502,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.6084,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.012523707740012643,
758
+ "grad_norm": 13.736647605895996,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.2882,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.012644128006743536,
765
+ "grad_norm": 18.304468154907227,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.8812,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.012764548273474426,
772
+ "grad_norm": 18.765226364135742,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 5.8377,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.012884968540205316,
779
+ "grad_norm": 15.608325958251953,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.9864,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013005388806936207,
786
+ "grad_norm": 14.807425498962402,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.8354,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.013125809073667099,
793
+ "grad_norm": 17.752962112426758,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 6.3213,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01324622934039799,
800
+ "grad_norm": 16.0859432220459,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 6.3305,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01336664960712888,
807
+ "grad_norm": 17.609752655029297,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 6.2805,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01348706987385977,
814
+ "grad_norm": 18.305526733398438,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 6.1058,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.013607490140590662,
821
+ "grad_norm": 15.66598129272461,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 6.2276,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.013727910407321553,
828
+ "grad_norm": 18.535301208496094,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 6.6646,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.013848330674052443,
835
+ "grad_norm": 20.5335693359375,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 6.6563,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.013968750940783333,
842
+ "grad_norm": 18.792814254760742,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 6.7214,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.014089171207514224,
849
+ "grad_norm": 18.318065643310547,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 6.6231,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.014209591474245116,
856
+ "grad_norm": 15.907029151916504,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 6.3682,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.014330011740976006,
863
+ "grad_norm": 17.899784088134766,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 6.7449,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.014450432007706897,
870
+ "grad_norm": 20.180458068847656,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 7.5801,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.014570852274437787,
877
+ "grad_norm": 30.31849479675293,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 7.2028,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01469127254116868,
884
+ "grad_norm": 21.378841400146484,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 7.0255,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.01481169280789957,
891
+ "grad_norm": 18.160831451416016,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 7.235,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.01493211307463046,
898
+ "grad_norm": 19.299564361572266,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 6.5939,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.01505253334136135,
905
+ "grad_norm": 22.814464569091797,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 7.6817,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.015172953608092243,
912
+ "grad_norm": 19.72553253173828,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 7.2951,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.015293373874823133,
919
+ "grad_norm": 27.33616828918457,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.9711,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.015413794141554023,
926
+ "grad_norm": 17.395479202270508,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.0004,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.015534214408284914,
933
+ "grad_norm": 23.039718627929688,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.8222,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.015654634675015804,
940
+ "grad_norm": 18.903642654418945,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.7666,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.015775054941746695,
947
+ "grad_norm": 17.474811553955078,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.5946,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.015895475208477585,
954
+ "grad_norm": 15.69929027557373,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.485,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01601589547520848,
961
+ "grad_norm": 14.750075340270996,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.3102,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.01613631574193937,
968
+ "grad_norm": 14.924285888671875,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.0332,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01625673600867026,
975
+ "grad_norm": 18.159025192260742,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.2681,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01637715627540115,
982
+ "grad_norm": 17.145938873291016,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.6567,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.01649757654213204,
989
+ "grad_norm": 18.082134246826172,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.8821,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01661799680886293,
996
+ "grad_norm": 16.63163185119629,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.1819,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01673841707559382,
1003
+ "grad_norm": 13.199299812316895,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.443,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.016858837342324712,
1010
+ "grad_norm": 12.945577621459961,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.4436,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.016979257609055606,
1017
+ "grad_norm": 14.055652618408203,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.9036,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.017099677875786496,
1024
+ "grad_norm": 14.148738861083984,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.2584,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.017220098142517386,
1031
+ "grad_norm": 15.948631286621094,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.9077,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.017340518409248277,
1038
+ "grad_norm": 14.8971586227417,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.1003,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.017460938675979167,
1045
+ "grad_norm": 17.40970802307129,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.8937,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.017581358942710058,
1052
+ "grad_norm": 14.42086410522461,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.09,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.017701779209440948,
1059
+ "grad_norm": 13.88598346710205,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.2703,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.01782219947617184,
1066
+ "grad_norm": 17.1777286529541,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.753,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.01794261974290273,
1073
+ "grad_norm": 22.961992263793945,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.3804,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.018063040009633623,
1080
+ "grad_norm": 20.709712982177734,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.3321,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.018063040009633623,
1087
+ "eval_loss": 1.4118815660476685,
1088
+ "eval_runtime": 1624.7275,
1089
+ "eval_samples_per_second": 8.609,
1090
+ "eval_steps_per_second": 2.152,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.3556941079629005e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null