nttx commited on
Commit
a2f574e
·
verified ·
1 Parent(s): ecccf83

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 sha256:99af7d2c9dc9f265213cbcae76c63bacba96310e774df711021253e43c1f2602
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c20b12d70ee5100b8376be29fe9ec43e6c022c72cec53196f8ca6e3b2f3c3ed
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f78c64050b21331e1eef06b68c9d8cc601600f097357cf4da622d5a05133e8d9
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644802706ffd9cafe29a13877727438a055a91ae33168908b2deab0631bf7b58
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e00c2432e112b2a78fc53a975e4d07def6405b474829a71147248edfdfb03b6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b11f03ae21d39be3f1f941e5510af2aa8839c66c87f19317481335b391cdbef
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": 0.047212474048137665,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6745362563237775,
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": 59.982,
732
  "eval_steps_per_second": 15.116,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6868879540224000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0355226956307888,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.0118043844856661,
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": 59.982,
732
  "eval_steps_per_second": 15.116,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6812816188870152,
737
+ "grad_norm": 0.17502517998218536,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0105,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.688026981450253,
744
+ "grad_norm": 0.09536734968423843,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0182,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6947723440134908,
751
+ "grad_norm": 0.18720607459545135,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0244,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.7015177065767285,
758
+ "grad_norm": 0.10460835695266724,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0161,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.7082630691399663,
765
+ "grad_norm": 0.04144510254263878,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0021,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.715008431703204,
772
+ "grad_norm": 0.27221187949180603,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0207,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.7217537942664418,
779
+ "grad_norm": 0.07747731357812881,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0038,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.7284991568296796,
786
+ "grad_norm": 0.2026963233947754,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0358,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.7352445193929174,
793
+ "grad_norm": 0.10932726413011551,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0203,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7419898819561551,
800
+ "grad_norm": 0.07752896845340729,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0033,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7487352445193929,
807
+ "grad_norm": 0.5522063970565796,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.1557,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7554806070826307,
814
+ "grad_norm": 0.8922995924949646,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.4962,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7622259696458684,
821
+ "grad_norm": 0.747218668460846,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.2185,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7689713322091062,
828
+ "grad_norm": 0.19041088223457336,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0152,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.7757166947723441,
835
+ "grad_norm": 0.4229462444782257,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.0618,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7824620573355818,
842
+ "grad_norm": 0.30456361174583435,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.0824,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7892074198988196,
849
+ "grad_norm": 0.2638731300830841,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.0391,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7959527824620574,
856
+ "grad_norm": 0.12386748194694519,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0198,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.8026981450252951,
863
+ "grad_norm": 0.13967956602573395,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0204,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.8094435075885329,
870
+ "grad_norm": 0.13475240767002106,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0054,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.8161888701517707,
877
+ "grad_norm": 0.21277835965156555,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0224,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.8229342327150084,
884
+ "grad_norm": 0.21421295404434204,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.0088,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.8296795952782462,
891
+ "grad_norm": 0.22496074438095093,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0233,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.836424957841484,
898
+ "grad_norm": 0.24452394247055054,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0363,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.8431703204047217,
905
+ "grad_norm": 0.1874397248029709,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0108,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.8499156829679595,
912
+ "grad_norm": 0.09923595935106277,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.0044,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8566610455311973,
919
+ "grad_norm": 0.08702019602060318,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0038,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.863406408094435,
926
+ "grad_norm": 0.1192399188876152,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.0059,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.8701517706576728,
933
+ "grad_norm": 0.055553749203681946,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0026,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.8768971332209107,
940
+ "grad_norm": 0.055112626403570175,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0025,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8836424957841484,
947
+ "grad_norm": 0.032335035502910614,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0014,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8903878583473862,
954
+ "grad_norm": 0.14078502357006073,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0137,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.897133220910624,
961
+ "grad_norm": 0.04515624791383743,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0028,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.9038785834738617,
968
+ "grad_norm": 0.06440647691488266,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0059,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.9106239460370995,
975
+ "grad_norm": 0.24568696320056915,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0066,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.9173693086003373,
982
+ "grad_norm": 0.03420849144458771,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0017,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.924114671163575,
989
+ "grad_norm": 0.03081429935991764,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0013,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.9308600337268128,
996
+ "grad_norm": 0.017709970474243164,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0008,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.9376053962900506,
1003
+ "grad_norm": 0.036176182329654694,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0016,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.9443507588532883,
1010
+ "grad_norm": 0.024693654850125313,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.0012,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.9510961214165261,
1017
+ "grad_norm": 0.17358708381652832,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0156,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9578414839797639,
1024
+ "grad_norm": 0.1224161759018898,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.0162,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.9645868465430016,
1031
+ "grad_norm": 0.10097432136535645,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.0128,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9713322091062394,
1038
+ "grad_norm": 0.1563689410686493,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0154,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9780775716694773,
1045
+ "grad_norm": 0.34062257409095764,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.049,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.984822934232715,
1052
+ "grad_norm": 0.11708389222621918,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0171,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.9915682967959528,
1059
+ "grad_norm": 0.131124809384346,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.0188,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9983136593591906,
1066
+ "grad_norm": 0.48198604583740234,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0995,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.0050590219224282,
1073
+ "grad_norm": 0.4684287905693054,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.2564,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.0118043844856661,
1080
+ "grad_norm": 0.6373432874679565,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.2716,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.0118043844856661,
1087
+ "eval_loss": 0.0355226956307888,
1088
+ "eval_runtime": 4.1722,
1089
+ "eval_samples_per_second": 59.921,
1090
+ "eval_steps_per_second": 15.1,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.030117278547968e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null