prxy5607 commited on
Commit
b91976a
·
verified ·
1 Parent(s): e66de6f

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 sha256:76653409a120684ef890f505ef9e7bc0c3fa98f186cc74a0526c767745cc51ff
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a2857c680e8d6c519c0b935a36bace07c5466f1104148b58c5a444d67484de
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a3c078115927e2760bdb97c7967fa3c12a9654b1af7002afbaab11f67dd5cb8
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cce1ecb9fcd658424cebe1b3291071f4ab2671b2d52af1eebaafecb08b262f9
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fe416ab31f7fb740718cb7b6fb195baea1c90e6d1111d0e5ccc89106252052d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369666c64e1dd843499afbd3085b17a119ba3d21c8bdf864464f64df94b73ff0
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": 1.7929612398147583,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.009448446911538916,
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": 30.661,
732
  "eval_steps_per_second": 7.666,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.986788419272704e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7651623487472534,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.014172670367308373,
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": 30.661,
732
  "eval_steps_per_second": 7.666,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009542931380654304,
737
+ "grad_norm": 1.1900925636291504,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.0002,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009637415849769694,
744
+ "grad_norm": 1.246945858001709,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.9059,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009731900318885083,
751
+ "grad_norm": 1.3612993955612183,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.0033,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009826384788000473,
758
+ "grad_norm": 1.561272144317627,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.0228,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009920869257115862,
765
+ "grad_norm": 0.9032238721847534,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.6668,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01001535372623125,
772
+ "grad_norm": 1.0913615226745605,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.8146,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01010983819534664,
779
+ "grad_norm": 0.936185359954834,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.8548,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.010204322664462029,
786
+ "grad_norm": 0.9609870910644531,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.6464,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.010298807133577418,
793
+ "grad_norm": 0.899878978729248,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7359,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.010393291602692808,
800
+ "grad_norm": 0.9809157848358154,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.6935,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.010487776071808197,
807
+ "grad_norm": 0.9736418724060059,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.6766,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010582260540923585,
814
+ "grad_norm": 0.9102429747581482,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.704,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.010676745010038974,
821
+ "grad_norm": 0.9363366365432739,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.6961,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010771229479154364,
828
+ "grad_norm": 0.9577345848083496,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.72,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.010865713948269753,
835
+ "grad_norm": 1.033258318901062,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.6714,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.010960198417385143,
842
+ "grad_norm": 0.9051771759986877,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7117,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01105468288650053,
849
+ "grad_norm": 0.996087908744812,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7179,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.01114916735561592,
856
+ "grad_norm": 0.9880028367042542,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.6529,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.01124365182473131,
863
+ "grad_norm": 1.0762004852294922,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7738,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.011338136293846699,
870
+ "grad_norm": 1.1333122253417969,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6419,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.011432620762962089,
877
+ "grad_norm": 0.9502783417701721,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.5949,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.011527105232077478,
884
+ "grad_norm": 1.1124191284179688,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.8083,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.011621589701192866,
891
+ "grad_norm": 1.213707447052002,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.7856,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011716074170308255,
898
+ "grad_norm": 1.2123509645462036,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.7704,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011810558639423645,
905
+ "grad_norm": 1.1718707084655762,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.6658,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011905043108539034,
912
+ "grad_norm": 1.242866039276123,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6367,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.011999527577654424,
919
+ "grad_norm": 1.2593830823898315,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6954,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.012094012046769811,
926
+ "grad_norm": 1.1635302305221558,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.6607,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.012188496515885201,
933
+ "grad_norm": 1.2189949750900269,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.7548,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.01228298098500059,
940
+ "grad_norm": 1.4098221063613892,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.7796,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01237746545411598,
947
+ "grad_norm": 1.4896501302719116,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.8862,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01247194992323137,
954
+ "grad_norm": 1.426547884941101,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.9333,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.012566434392346759,
961
+ "grad_norm": 1.343456506729126,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.7487,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012660918861462147,
968
+ "grad_norm": 1.5635097026824951,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.8904,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.012755403330577536,
975
+ "grad_norm": 1.3845025300979614,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.6632,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.012849887799692926,
982
+ "grad_norm": 1.3566688299179077,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.7332,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012944372268808315,
989
+ "grad_norm": 1.3113293647766113,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.7121,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.013038856737923704,
996
+ "grad_norm": 1.3649717569351196,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.6727,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.013133341207039092,
1003
+ "grad_norm": 1.6140693426132202,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.7886,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.013227825676154482,
1010
+ "grad_norm": 1.4083361625671387,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.8824,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.013322310145269871,
1017
+ "grad_norm": 1.4232109785079956,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.8112,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01341679461438526,
1024
+ "grad_norm": 1.5610580444335938,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.686,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.01351127908350065,
1031
+ "grad_norm": 1.460500955581665,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6369,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.013605763552616038,
1038
+ "grad_norm": 1.4880610704421997,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.8207,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013700248021731427,
1045
+ "grad_norm": 1.4838835000991821,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.8259,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.013794732490846817,
1052
+ "grad_norm": 1.3945232629776,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.6692,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.013889216959962206,
1059
+ "grad_norm": 1.4665021896362305,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.8147,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.013983701429077596,
1066
+ "grad_norm": 1.4989385604858398,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.7704,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.014078185898192985,
1073
+ "grad_norm": 1.4875540733337402,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.6716,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.014172670367308373,
1080
+ "grad_norm": 1.9659397602081299,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.8831,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.014172670367308373,
1087
+ "eval_loss": 1.7651623487472534,
1088
+ "eval_runtime": 581.394,
1089
+ "eval_samples_per_second": 30.661,
1090
+ "eval_steps_per_second": 7.666,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.469977201508352e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null