prxy5604 commited on
Commit
afd7681
·
verified ·
1 Parent(s): 812fb17

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 sha256:936c1b8bc0bdaae8f4d526d2713f0d9f1455592e31863a3f95d931e5c8ae076e
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22804bc48592a43dc26fa27add30cef17ccbf990d19cbf0b21385c529042f1c0
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:512548d909c01161977d33749de906d270283b8671a35bcc9711e71e977b6ab3
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb923c8656b0ed68b12856cfa5860ef1804382d4f94c7fb77cec5d7d5befde1
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d2282d3b55291d9e7d0729a73f1123803802e8d9f90fc14744e7d8232ec1fdb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e55f98c131138cc5d8e20cffd7cdf5789806aa23f8f933e1658c03052c7655b
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": 0.409039705991745,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.16611295681063123,
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": 7.525,
732
  "eval_steps_per_second": 1.885,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.46948355375104e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3880166709423065,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.24916943521594684,
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": 7.525,
732
  "eval_steps_per_second": 1.885,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.16777408637873753,
737
+ "grad_norm": 0.1708502620458603,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.2821,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.16943521594684385,
744
+ "grad_norm": 0.1842401623725891,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.2969,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.17109634551495018,
751
+ "grad_norm": 0.15198273956775665,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2685,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.17275747508305647,
758
+ "grad_norm": 0.14956019818782806,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2899,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1744186046511628,
765
+ "grad_norm": 0.1505981981754303,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2836,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1760797342192691,
772
+ "grad_norm": 0.15199552476406097,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.2911,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1777408637873754,
779
+ "grad_norm": 0.15069696307182312,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.2961,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.17940199335548174,
786
+ "grad_norm": 0.14875832200050354,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.287,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.18106312292358803,
793
+ "grad_norm": 0.1654970794916153,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.3096,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.18272425249169436,
800
+ "grad_norm": 0.14778447151184082,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.2612,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.18438538205980065,
807
+ "grad_norm": 0.14741088449954987,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.2852,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.18604651162790697,
814
+ "grad_norm": 0.1445004642009735,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2849,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1877076411960133,
821
+ "grad_norm": 0.16333213448524475,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.2977,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1893687707641196,
828
+ "grad_norm": 0.1434721201658249,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2925,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.19102990033222592,
835
+ "grad_norm": 0.13791555166244507,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.2619,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.19269102990033224,
842
+ "grad_norm": 0.14811094105243683,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2951,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.19435215946843853,
849
+ "grad_norm": 0.13586348295211792,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.2758,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.19601328903654486,
856
+ "grad_norm": 0.15308637917041779,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.2889,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.19767441860465115,
863
+ "grad_norm": 0.1554800420999527,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2985,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.19933554817275748,
870
+ "grad_norm": 0.1462528556585312,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.293,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2009966777408638,
877
+ "grad_norm": 0.15194445848464966,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3062,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.2026578073089701,
884
+ "grad_norm": 0.15283334255218506,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3033,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.20431893687707642,
891
+ "grad_norm": 0.1533212512731552,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3403,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2059800664451827,
898
+ "grad_norm": 0.17399577796459198,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.415,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.20764119601328904,
905
+ "grad_norm": 0.1844712793827057,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.4619,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.20930232558139536,
912
+ "grad_norm": 0.18232126533985138,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.4879,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.21096345514950166,
919
+ "grad_norm": 0.17209911346435547,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.4918,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.21262458471760798,
926
+ "grad_norm": 0.15540632605552673,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.4778,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.21428571428571427,
933
+ "grad_norm": 0.14485326409339905,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.498,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.2159468438538206,
940
+ "grad_norm": 0.1500222533941269,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.4784,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.21760797342192692,
947
+ "grad_norm": 0.1539774239063263,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.4763,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.21926910299003322,
954
+ "grad_norm": 0.1498161256313324,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.4736,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.22093023255813954,
961
+ "grad_norm": 0.15067896246910095,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.4791,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.22259136212624583,
968
+ "grad_norm": 0.1555660367012024,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.5062,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.22425249169435216,
975
+ "grad_norm": 0.15103194117546082,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4651,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.22591362126245848,
982
+ "grad_norm": 0.15316762030124664,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.4843,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.22757475083056478,
989
+ "grad_norm": 0.15561173856258392,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.5106,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2292358803986711,
996
+ "grad_norm": 0.15198399126529694,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4786,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.23089700996677742,
1003
+ "grad_norm": 0.15727408230304718,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.4604,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.23255813953488372,
1010
+ "grad_norm": 0.15432614088058472,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.4822,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.23421926910299004,
1017
+ "grad_norm": 0.14581052958965302,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.4861,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.23588039867109634,
1024
+ "grad_norm": 0.14340969920158386,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.4584,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.23754152823920266,
1031
+ "grad_norm": 0.15534572303295135,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.4786,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.23920265780730898,
1038
+ "grad_norm": 0.1554005742073059,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.5156,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.24086378737541528,
1045
+ "grad_norm": 0.15117494761943817,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.5163,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2425249169435216,
1052
+ "grad_norm": 0.1590317040681839,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.5077,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2441860465116279,
1059
+ "grad_norm": 0.15675310790538788,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.485,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.24584717607973422,
1066
+ "grad_norm": 0.16706211864948273,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.5485,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.24750830564784054,
1073
+ "grad_norm": 0.18405000865459442,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.568,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.24916943521594684,
1080
+ "grad_norm": 0.232390895485878,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.6994,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.24916943521594684,
1087
+ "eval_loss": 0.3880166709423065,
1088
+ "eval_runtime": 135.2855,
1089
+ "eval_samples_per_second": 7.495,
1090
+ "eval_steps_per_second": 1.878,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.69076765458432e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null