cilooor commited on
Commit
b89a607
·
verified ·
1 Parent(s): 1da1fa0

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 sha256:515948f9892eb56522995af4e7447e14a1ce77ab48040cabb3e69bd864966d61
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f69deae36ef8aa746649ec8b264ab9a3f74cd624439f1c5e53aae8fc35fc992
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c353dec8a42af643633c760a6b4a39c29024ea6e35a17d7000c75db4efd93084
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8811b62237e53486bc6dd7cd69eabae5f9c362fd15881519db72cb2ee8336544
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:eabd323f96aa88f0a0c8cc7cb371e7b584d6f9b8cd6ddec15dc9da6604213a40
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a25a85d9419a9776d89ea0a82a145e70152151f37246f54358709a882afc75
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b0f0591a54513981f9045153a7608f989005ce4fb6ed2c798b085bae23c1094
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed88ff7cbe02e7c054abfce3510882248a01917e1eb8cf2c358f612dd7312357
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.423828125,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0784313725490196,
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": 12.478,
732
  "eval_steps_per_second": 3.119,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.513282097727406e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.37640249729156494,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11764705882352941,
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": 12.478,
732
  "eval_steps_per_second": 3.119,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0792156862745098,
737
+ "grad_norm": 6.207220077514648,
738
+ "learning_rate": 4.797407629465648e-05,
739
+ "loss": 3.1864,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08,
744
+ "grad_norm": 4.361649990081787,
745
+ "learning_rate": 4.7231268960295003e-05,
746
+ "loss": 2.0343,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08078431372549019,
751
+ "grad_norm": 3.420992851257324,
752
+ "learning_rate": 4.648785161927887e-05,
753
+ "loss": 1.307,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0815686274509804,
758
+ "grad_norm": 2.5062878131866455,
759
+ "learning_rate": 4.574402751448614e-05,
760
+ "loss": 1.256,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08235294117647059,
765
+ "grad_norm": 2.8243720531463623,
766
+ "learning_rate": 4.5e-05,
767
+ "loss": 1.6743,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08313725490196078,
772
+ "grad_norm": 2.8885185718536377,
773
+ "learning_rate": 4.425597248551387e-05,
774
+ "loss": 1.2425,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08392156862745098,
779
+ "grad_norm": 3.3675057888031006,
780
+ "learning_rate": 4.3512148380721134e-05,
781
+ "loss": 1.2662,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08470588235294117,
786
+ "grad_norm": 3.927375316619873,
787
+ "learning_rate": 4.2768731039704995e-05,
788
+ "loss": 1.5353,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08549019607843138,
793
+ "grad_norm": 3.4482688903808594,
794
+ "learning_rate": 4.202592370534353e-05,
795
+ "loss": 1.5533,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08627450980392157,
800
+ "grad_norm": 4.18345832824707,
801
+ "learning_rate": 4.128392945374505e-05,
802
+ "loss": 1.1801,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08705882352941176,
807
+ "grad_norm": 3.1618025302886963,
808
+ "learning_rate": 4.0542951138729184e-05,
809
+ "loss": 1.1809,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08784313725490196,
814
+ "grad_norm": 3.343364953994751,
815
+ "learning_rate": 3.980319133636863e-05,
816
+ "loss": 1.3565,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08862745098039215,
821
+ "grad_norm": 3.7614049911499023,
822
+ "learning_rate": 3.9064852289606895e-05,
823
+ "loss": 1.2552,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08941176470588236,
828
+ "grad_norm": 3.514059066772461,
829
+ "learning_rate": 3.832813585296711e-05,
830
+ "loss": 1.2708,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09019607843137255,
835
+ "grad_norm": 3.6900923252105713,
836
+ "learning_rate": 3.759324343736697e-05,
837
+ "loss": 1.1696,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09098039215686274,
842
+ "grad_norm": 3.7292330265045166,
843
+ "learning_rate": 3.686037595505507e-05,
844
+ "loss": 1.4199,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09176470588235294,
849
+ "grad_norm": 4.216084957122803,
850
+ "learning_rate": 3.612973376468339e-05,
851
+ "loss": 1.2863,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09254901960784313,
856
+ "grad_norm": 4.107268810272217,
857
+ "learning_rate": 3.54015166165314e-05,
858
+ "loss": 1.1495,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09333333333333334,
863
+ "grad_norm": 5.08326530456543,
864
+ "learning_rate": 3.4675923597896184e-05,
865
+ "loss": 1.4167,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09411764705882353,
870
+ "grad_norm": 4.708593368530273,
871
+ "learning_rate": 3.395315307866404e-05,
872
+ "loss": 1.3636,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09490196078431372,
877
+ "grad_norm": 4.576901912689209,
878
+ "learning_rate": 3.3233402657078116e-05,
879
+ "loss": 1.3424,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09568627450980392,
884
+ "grad_norm": 4.741860866546631,
885
+ "learning_rate": 3.2516869105717005e-05,
886
+ "loss": 1.2734,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09647058823529411,
891
+ "grad_norm": 4.217694282531738,
892
+ "learning_rate": 3.1803748317699093e-05,
893
+ "loss": 0.9932,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09725490196078432,
898
+ "grad_norm": 5.4652419090271,
899
+ "learning_rate": 3.1094235253127374e-05,
900
+ "loss": 1.1499,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09803921568627451,
905
+ "grad_norm": 5.599730014801025,
906
+ "learning_rate": 3.038852388578925e-05,
907
+ "loss": 1.2061,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0988235294117647,
912
+ "grad_norm": 5.845987319946289,
913
+ "learning_rate": 2.9686807150126064e-05,
914
+ "loss": 0.9805,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0996078431372549,
919
+ "grad_norm": 5.0457258224487305,
920
+ "learning_rate": 2.8989276888486755e-05,
921
+ "loss": 0.9718,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1003921568627451,
926
+ "grad_norm": 6.9256744384765625,
927
+ "learning_rate": 2.829612379868006e-05,
928
+ "loss": 1.0395,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1011764705882353,
933
+ "grad_norm": 5.739282131195068,
934
+ "learning_rate": 2.760753738183966e-05,
935
+ "loss": 1.2639,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.10196078431372549,
940
+ "grad_norm": 5.214005947113037,
941
+ "learning_rate": 2.6923705890616385e-05,
942
+ "loss": 1.1527,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1027450980392157,
947
+ "grad_norm": 6.843442916870117,
948
+ "learning_rate": 2.6244816277711943e-05,
949
+ "loss": 1.446,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10352941176470588,
954
+ "grad_norm": 5.266831398010254,
955
+ "learning_rate": 2.5571054144767825e-05,
956
+ "loss": 1.0564,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10431372549019607,
961
+ "grad_norm": 7.751642227172852,
962
+ "learning_rate": 2.4902603691623712e-05,
963
+ "loss": 1.1319,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10509803921568628,
968
+ "grad_norm": 5.268066883087158,
969
+ "learning_rate": 2.4239647665959058e-05,
970
+ "loss": 0.9805,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10588235294117647,
975
+ "grad_norm": 6.458575248718262,
976
+ "learning_rate": 2.358236731333169e-05,
977
+ "loss": 1.1729,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10666666666666667,
982
+ "grad_norm": 7.804651260375977,
983
+ "learning_rate": 2.293094232762715e-05,
984
+ "loss": 1.919,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10745098039215686,
989
+ "grad_norm": 7.9424052238464355,
990
+ "learning_rate": 2.2285550801932047e-05,
991
+ "loss": 1.468,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10823529411764705,
996
+ "grad_norm": 6.931085109710693,
997
+ "learning_rate": 2.164636917984533e-05,
998
+ "loss": 1.5243,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10901960784313726,
1003
+ "grad_norm": 8.593782424926758,
1004
+ "learning_rate": 2.1013572207240293e-05,
1005
+ "loss": 1.4203,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.10980392156862745,
1010
+ "grad_norm": 7.546792984008789,
1011
+ "learning_rate": 2.03873328844908e-05,
1012
+ "loss": 1.4472,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11058823529411765,
1017
+ "grad_norm": 9.1332426071167,
1018
+ "learning_rate": 1.9767822419174733e-05,
1019
+ "loss": 1.5902,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11137254901960784,
1024
+ "grad_norm": 10.055811882019043,
1025
+ "learning_rate": 1.915521017926754e-05,
1026
+ "loss": 2.183,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11215686274509803,
1031
+ "grad_norm": 9.171233177185059,
1032
+ "learning_rate": 1.8549663646838714e-05,
1033
+ "loss": 1.7493,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11294117647058824,
1038
+ "grad_norm": 7.260237693786621,
1039
+ "learning_rate": 1.7951348372263872e-05,
1040
+ "loss": 1.3346,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11372549019607843,
1045
+ "grad_norm": 12.887181282043457,
1046
+ "learning_rate": 1.7360427928964948e-05,
1047
+ "loss": 2.0163,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11450980392156863,
1052
+ "grad_norm": 9.76959228515625,
1053
+ "learning_rate": 1.6777063868690835e-05,
1054
+ "loss": 1.9468,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11529411764705882,
1059
+ "grad_norm": 12.850676536560059,
1060
+ "learning_rate": 1.6201415677350752e-05,
1061
+ "loss": 2.0807,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11607843137254902,
1066
+ "grad_norm": 11.191648483276367,
1067
+ "learning_rate": 1.563364073141241e-05,
1068
+ "loss": 1.9254,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11686274509803922,
1073
+ "grad_norm": 16.186717987060547,
1074
+ "learning_rate": 1.5073894254876825e-05,
1075
+ "loss": 2.6053,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11764705882352941,
1080
+ "grad_norm": 24.65969467163086,
1081
+ "learning_rate": 1.452232927684166e-05,
1082
+ "loss": 2.2168,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11764705882352941,
1087
+ "eval_loss": 0.37640249729156494,
1088
+ "eval_runtime": 171.5386,
1089
+ "eval_samples_per_second": 12.522,
1090
+ "eval_steps_per_second": 3.13,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2717118961156096e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null