lesso commited on
Commit
90951eb
·
verified ·
1 Parent(s): ae08943

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:b3864acfd1014d1a0df8fa27f82cfce48218ec637e63876f792c3bed4c0f1a5e
3
  size 406863720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dad9abbf8bc0bc85d7a6855eef266e8316865f25cbf437b81052bd71bb0925d
3
  size 406863720
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a211302c27b69a338500ec852ad9e883d840459d8a2d3446d7d8c14b02d137fa
3
  size 207013892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d93587f99744a48f80040138f37c810fedc14962defd778baf99b1b370e8b66
3
  size 207013892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e1aa6e4674a8b4ab54dbebd0dd5739511029a591dcd8c88101728092c1e72f7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4573b1446910d3d1f9cc5fe520213739360e4bb421639354996d7d0e468220ce
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3388093bd4c4d331382d0016aa94fd7868af3fa4dd50305298d21879ce809e93
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16a9a2b8856e8f64eb7194578c6fcbc8625033d1caa318cc7b80ad824088880
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.1450011283159256,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.2544529262086514,
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": 16.324,
732
  "eval_steps_per_second": 4.13,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.6838380486656e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1360974758863449,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3816793893129771,
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": 16.324,
732
  "eval_steps_per_second": 4.13,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.25699745547073793,
737
+ "grad_norm": 0.9659016728401184,
738
+ "learning_rate": 5.219384210526315e-05,
739
+ "loss": 0.2955,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2595419847328244,
744
+ "grad_norm": 0.5893524885177612,
745
+ "learning_rate": 5.1666631578947374e-05,
746
+ "loss": 0.158,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.26208651399491095,
751
+ "grad_norm": 0.561215877532959,
752
+ "learning_rate": 5.113942105263158e-05,
753
+ "loss": 0.1543,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.26463104325699743,
758
+ "grad_norm": 0.5634675621986389,
759
+ "learning_rate": 5.061221052631579e-05,
760
+ "loss": 0.1578,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.26717557251908397,
765
+ "grad_norm": 0.7371407747268677,
766
+ "learning_rate": 5.0085e-05,
767
+ "loss": 0.1396,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.2697201017811705,
772
+ "grad_norm": 0.62689608335495,
773
+ "learning_rate": 4.955778947368421e-05,
774
+ "loss": 0.1542,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.272264631043257,
779
+ "grad_norm": 0.5553103685379028,
780
+ "learning_rate": 4.903057894736842e-05,
781
+ "loss": 0.0909,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2748091603053435,
786
+ "grad_norm": 0.5198187828063965,
787
+ "learning_rate": 4.850336842105263e-05,
788
+ "loss": 0.0785,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.27735368956743,
793
+ "grad_norm": 0.7179524898529053,
794
+ "learning_rate": 4.797615789473684e-05,
795
+ "loss": 0.1036,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.27989821882951654,
800
+ "grad_norm": 0.44508594274520874,
801
+ "learning_rate": 4.744894736842105e-05,
802
+ "loss": 0.1104,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.2824427480916031,
807
+ "grad_norm": 0.7336511015892029,
808
+ "learning_rate": 4.692173684210526e-05,
809
+ "loss": 0.1067,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.28498727735368956,
814
+ "grad_norm": 0.9355735778808594,
815
+ "learning_rate": 4.639452631578947e-05,
816
+ "loss": 0.1675,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.2875318066157761,
821
+ "grad_norm": 0.46843382716178894,
822
+ "learning_rate": 4.586731578947368e-05,
823
+ "loss": 0.0723,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.2900763358778626,
828
+ "grad_norm": 0.5565648078918457,
829
+ "learning_rate": 4.5340105263157894e-05,
830
+ "loss": 0.0579,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2926208651399491,
835
+ "grad_norm": 0.35323649644851685,
836
+ "learning_rate": 4.48128947368421e-05,
837
+ "loss": 0.0532,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2951653944020356,
842
+ "grad_norm": 0.41509339213371277,
843
+ "learning_rate": 4.428568421052632e-05,
844
+ "loss": 0.0788,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.29770992366412213,
849
+ "grad_norm": 0.4781738817691803,
850
+ "learning_rate": 4.3758473684210525e-05,
851
+ "loss": 0.0939,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.30025445292620867,
856
+ "grad_norm": 0.5751485824584961,
857
+ "learning_rate": 4.323126315789474e-05,
858
+ "loss": 0.0883,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.30279898218829515,
863
+ "grad_norm": 0.2596683204174042,
864
+ "learning_rate": 4.270405263157895e-05,
865
+ "loss": 0.0365,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.3053435114503817,
870
+ "grad_norm": 0.572528600692749,
871
+ "learning_rate": 4.217684210526316e-05,
872
+ "loss": 0.0871,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.30788804071246817,
877
+ "grad_norm": 0.5119253396987915,
878
+ "learning_rate": 4.164963157894737e-05,
879
+ "loss": 0.0973,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.3104325699745547,
884
+ "grad_norm": 0.5054477453231812,
885
+ "learning_rate": 4.112242105263158e-05,
886
+ "loss": 0.0494,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.31297709923664124,
891
+ "grad_norm": 0.3897090256214142,
892
+ "learning_rate": 4.059521052631579e-05,
893
+ "loss": 0.0333,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.3155216284987277,
898
+ "grad_norm": 0.2573760747909546,
899
+ "learning_rate": 4.0068e-05,
900
+ "loss": 0.0229,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.31806615776081426,
905
+ "grad_norm": 0.28332197666168213,
906
+ "learning_rate": 3.954078947368421e-05,
907
+ "loss": 0.0257,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.32061068702290074,
912
+ "grad_norm": 0.446418434381485,
913
+ "learning_rate": 3.901357894736842e-05,
914
+ "loss": 0.0825,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.3231552162849873,
919
+ "grad_norm": 0.29756420850753784,
920
+ "learning_rate": 3.848636842105263e-05,
921
+ "loss": 0.0242,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.3256997455470738,
926
+ "grad_norm": 0.5935866236686707,
927
+ "learning_rate": 3.795915789473684e-05,
928
+ "loss": 0.0925,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.3282442748091603,
933
+ "grad_norm": 0.2986157536506653,
934
+ "learning_rate": 3.743194736842105e-05,
935
+ "loss": 0.0154,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.33078880407124683,
940
+ "grad_norm": 0.03564433753490448,
941
+ "learning_rate": 3.690473684210526e-05,
942
+ "loss": 0.0024,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.3333333333333333,
947
+ "grad_norm": 0.021472949534654617,
948
+ "learning_rate": 3.6377526315789475e-05,
949
+ "loss": 0.0011,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.33587786259541985,
954
+ "grad_norm": 1.2343424558639526,
955
+ "learning_rate": 3.585031578947368e-05,
956
+ "loss": 0.3226,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.3384223918575064,
961
+ "grad_norm": 1.3323383331298828,
962
+ "learning_rate": 3.532310526315789e-05,
963
+ "loss": 0.2967,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.34096692111959287,
968
+ "grad_norm": 1.58578360080719,
969
+ "learning_rate": 3.4795894736842106e-05,
970
+ "loss": 0.2687,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.3435114503816794,
975
+ "grad_norm": 1.3783105611801147,
976
+ "learning_rate": 3.4268684210526314e-05,
977
+ "loss": 0.2798,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.3460559796437659,
982
+ "grad_norm": 1.470922827720642,
983
+ "learning_rate": 3.374147368421052e-05,
984
+ "loss": 0.3177,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.3486005089058524,
989
+ "grad_norm": 1.449453592300415,
990
+ "learning_rate": 3.321426315789473e-05,
991
+ "loss": 0.1875,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.3511450381679389,
996
+ "grad_norm": 1.273271083831787,
997
+ "learning_rate": 3.2687052631578946e-05,
998
+ "loss": 0.2517,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.35368956743002544,
1003
+ "grad_norm": 1.2989132404327393,
1004
+ "learning_rate": 3.2159842105263154e-05,
1005
+ "loss": 0.1741,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.356234096692112,
1010
+ "grad_norm": 1.1349838972091675,
1011
+ "learning_rate": 3.163263157894737e-05,
1012
+ "loss": 0.2073,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.35877862595419846,
1017
+ "grad_norm": 1.2873899936676025,
1018
+ "learning_rate": 3.110542105263158e-05,
1019
+ "loss": 0.1692,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.361323155216285,
1024
+ "grad_norm": 1.297892689704895,
1025
+ "learning_rate": 3.057821052631579e-05,
1026
+ "loss": 0.1529,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.3638676844783715,
1031
+ "grad_norm": 1.0262969732284546,
1032
+ "learning_rate": 3.0050999999999997e-05,
1033
+ "loss": 0.1269,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.366412213740458,
1038
+ "grad_norm": 1.489499807357788,
1039
+ "learning_rate": 2.9523789473684206e-05,
1040
+ "loss": 0.2182,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.36895674300254455,
1045
+ "grad_norm": 2.6656413078308105,
1046
+ "learning_rate": 2.899657894736842e-05,
1047
+ "loss": 0.1811,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.37150127226463103,
1052
+ "grad_norm": 1.5800155401229858,
1053
+ "learning_rate": 2.846936842105263e-05,
1054
+ "loss": 0.1364,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.37404580152671757,
1059
+ "grad_norm": 0.6563022136688232,
1060
+ "learning_rate": 2.794215789473684e-05,
1061
+ "loss": 0.0965,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.37659033078880405,
1066
+ "grad_norm": 1.1012194156646729,
1067
+ "learning_rate": 2.7414947368421056e-05,
1068
+ "loss": 0.097,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3791348600508906,
1073
+ "grad_norm": 1.3474540710449219,
1074
+ "learning_rate": 2.6887736842105264e-05,
1075
+ "loss": 0.1278,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3816793893129771,
1080
+ "grad_norm": 1.2162439823150635,
1081
+ "learning_rate": 2.6360526315789472e-05,
1082
+ "loss": 0.1464,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3816793893129771,
1087
+ "eval_loss": 0.1360974758863449,
1088
+ "eval_runtime": 10.1762,
1089
+ "eval_samples_per_second": 16.313,
1090
+ "eval_steps_per_second": 4.127,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.5257570729984e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null