prxy5605 commited on
Commit
915f48c
·
verified ·
1 Parent(s): 382fcb2

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 sha256:731b99a12b28b57c92cf00dfe1a4fe2ea2fbd8eca74956074af9015f7cd9004f
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645ecff5e067905d5ac5224bd843a267f4a25a3df221379cf1e1e04e6d35dc84
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abb07f57228d10ae3e0b8db77da5f1ba9bf54954e587c1f8b6cca3c73d1aa95a
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02a9e87c6d1677a6bcc7fdbb67140b0d39604c689b9e94e93f73b67d137b6c2
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9cf3db04dce357ca795ad42c76fa0ca88d94725018be0988ed61cb167d1561e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46a1fdc702a552b56c0900b9f25dcca336e326ddd7ff322efe181f6c540c762
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": 0.9981662631034851,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.018976232269082974,
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": 32.029,
732
  "eval_steps_per_second": 8.007,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.3421305059475456e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9701759219169617,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02846434840362446,
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": 32.029,
732
  "eval_steps_per_second": 8.007,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.019165994591773802,
737
+ "grad_norm": 0.1871665120124817,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9838,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.019355756914464634,
744
+ "grad_norm": 0.21412956714630127,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.9434,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.019545519237155463,
751
+ "grad_norm": 0.20799927413463593,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9957,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01973528155984629,
758
+ "grad_norm": 0.20693427324295044,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.9414,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.019925043882537123,
765
+ "grad_norm": 0.19739599525928497,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.925,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.02011480620522795,
772
+ "grad_norm": 0.194368377327919,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9672,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.02030456852791878,
779
+ "grad_norm": 0.198219433426857,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.9094,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.020494330850609612,
786
+ "grad_norm": 0.18252170085906982,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9321,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.02068409317330044,
793
+ "grad_norm": 0.18987925350666046,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9764,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.020873855495991273,
800
+ "grad_norm": 0.18091386556625366,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9794,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0210636178186821,
807
+ "grad_norm": 0.18169650435447693,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0014,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02125338014137293,
814
+ "grad_norm": 0.19523243606090546,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.9512,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.02144314246406376,
821
+ "grad_norm": 0.20139889419078827,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9744,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.02163290478675459,
828
+ "grad_norm": 0.18810676038265228,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9548,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02182266710944542,
835
+ "grad_norm": 0.2029637098312378,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8991,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02201242943213625,
842
+ "grad_norm": 0.20979595184326172,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0381,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02220219175482708,
849
+ "grad_norm": 0.20881718397140503,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9862,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.022391954077517907,
856
+ "grad_norm": 0.20691141486167908,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9603,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02258171640020874,
863
+ "grad_norm": 0.21193382143974304,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0092,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.022771478722899568,
870
+ "grad_norm": 0.19551590085029602,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.89,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.022961241045590396,
877
+ "grad_norm": 0.20724761486053467,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9521,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02315100336828123,
884
+ "grad_norm": 0.21067377924919128,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9714,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.023340765690972057,
891
+ "grad_norm": 0.22233997285366058,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.0466,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02353052801366289,
898
+ "grad_norm": 0.2184775173664093,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.0076,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.023720290336353717,
905
+ "grad_norm": 0.21032242476940155,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9897,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.023910052659044546,
912
+ "grad_norm": 0.22417564690113068,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.0463,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.024099814981735378,
919
+ "grad_norm": 0.21387426555156708,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.9584,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.024289577304426206,
926
+ "grad_norm": 0.2128717303276062,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.9954,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.024479339627117035,
933
+ "grad_norm": 0.2258055955171585,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.9482,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.024669101949807867,
940
+ "grad_norm": 0.21299861371517181,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.9147,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.024858864272498695,
947
+ "grad_norm": 0.2303430736064911,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9663,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.025048626595189524,
954
+ "grad_norm": 0.22739309072494507,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9808,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.025238388917880356,
961
+ "grad_norm": 0.2431771159172058,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1092,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.025428151240571184,
968
+ "grad_norm": 0.24554990231990814,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.012,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.025617913563262016,
975
+ "grad_norm": 0.24237067997455597,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.0044,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.025807675885952844,
982
+ "grad_norm": 0.24016183614730835,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0184,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.025997438208643673,
989
+ "grad_norm": 0.24562525749206543,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9808,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.026187200531334505,
996
+ "grad_norm": 0.2517540156841278,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.96,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.026376962854025333,
1003
+ "grad_norm": 0.24588365852832794,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0525,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.026566725176716162,
1010
+ "grad_norm": 0.25156688690185547,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0025,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.026756487499406994,
1017
+ "grad_norm": 0.2560715079307556,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.0106,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.026946249822097822,
1024
+ "grad_norm": 0.2707711458206177,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.938,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02713601214478865,
1031
+ "grad_norm": 0.2656857371330261,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9412,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.027325774467479483,
1038
+ "grad_norm": 0.27317842841148376,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.9181,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.02751553679017031,
1045
+ "grad_norm": 0.27799221873283386,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.044,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.02770529911286114,
1052
+ "grad_norm": 0.2845875024795532,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0191,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02789506143555197,
1059
+ "grad_norm": 0.2962326109409332,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0425,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0280848237582428,
1066
+ "grad_norm": 0.31925490498542786,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.9788,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.028274586080933632,
1073
+ "grad_norm": 0.32261669635772705,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9128,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02846434840362446,
1080
+ "grad_norm": 0.3913915157318115,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.0025,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02846434840362446,
1087
+ "eval_loss": 0.9701759219169617,
1088
+ "eval_runtime": 277.0435,
1089
+ "eval_samples_per_second": 32.038,
1090
+ "eval_steps_per_second": 8.01,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.004923158659072e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null