prxy5608 commited on
Commit
b0adc47
·
verified ·
1 Parent(s): d81ebc8

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 sha256:4ae7fb951efd40cadaa8d4e798d0cef3405d7a5673bfcb19a035d884c3dc6082
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b85cb199d584852c732661fe7546cfc3382cc0ee93424e5c840a077dad13c5
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77c3dde79ccc95908ca3a863b0d6964aa6670a111f700bc75a562beeb6714cce
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fbc0a1b5a3b11a80140901ce3ef27947bebb076c2a4e270d68a9b666c8c5f93
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3170e57bfd77a0c009b8af0846cfe2fcb3a26c6d685b057a397bd5371972bbfa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af86edf94b5fa41684eb2bae9d031531ac295295c655e73da175b29cc6ea22a8
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": 1.6982988119125366,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06927606511950121,
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": 13.173,
732
  "eval_steps_per_second": 3.295,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5660514831542969,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.10391409767925182,
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": 13.173,
732
  "eval_steps_per_second": 3.295,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06996882577069623,
737
+ "grad_norm": 0.808838963508606,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.2906,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07066158642189124,
744
+ "grad_norm": 0.8714607954025269,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.5006,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07135434707308624,
751
+ "grad_norm": 0.7841171026229858,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5611,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07204710772428126,
758
+ "grad_norm": 0.6819593906402588,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.6411,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07273986837547627,
765
+ "grad_norm": 0.5991967916488647,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.5971,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07343262902667129,
772
+ "grad_norm": 0.6412804126739502,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.622,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07412538967786629,
779
+ "grad_norm": 0.5765404105186462,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6142,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0748181503290613,
786
+ "grad_norm": 0.6134495139122009,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.6143,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07551091098025632,
793
+ "grad_norm": 0.5833260416984558,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4422,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07620367163145134,
800
+ "grad_norm": 0.6028990745544434,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4908,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07689643228264635,
807
+ "grad_norm": 0.6026722192764282,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.5221,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07758919293384135,
814
+ "grad_norm": 0.5972195267677307,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4751,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07828195358503637,
821
+ "grad_norm": 0.5974715948104858,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.5023,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07897471423623138,
828
+ "grad_norm": 0.6070694923400879,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.4872,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0796674748874264,
835
+ "grad_norm": 0.615339994430542,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.5426,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0803602355386214,
842
+ "grad_norm": 0.5781705975532532,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.3618,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08105299618981641,
849
+ "grad_norm": 0.6544880867004395,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.5149,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08174575684101143,
856
+ "grad_norm": 0.657573938369751,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.5114,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08243851749220645,
863
+ "grad_norm": 0.6392859220504761,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.5861,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08313127814340146,
870
+ "grad_norm": 0.6606055498123169,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.5429,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.08382403879459646,
877
+ "grad_norm": 0.7363746166229248,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.7137,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.08451679944579148,
884
+ "grad_norm": 0.685859203338623,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.5803,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08520956009698649,
891
+ "grad_norm": 0.745258629322052,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.5613,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08590232074818151,
898
+ "grad_norm": 0.7659652233123779,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6056,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08659508139937652,
905
+ "grad_norm": 0.7633351683616638,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7241,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08728784205057152,
912
+ "grad_norm": 0.7845526337623596,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4687,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08798060270176654,
919
+ "grad_norm": 0.819581925868988,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6291,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08867336335296155,
926
+ "grad_norm": 0.8217785954475403,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.5233,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08936612400415657,
933
+ "grad_norm": 0.8633366823196411,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.5922,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09005888465535157,
940
+ "grad_norm": 0.8733365535736084,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.6332,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09075164530654659,
947
+ "grad_norm": 0.9523481726646423,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.5584,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0914444059577416,
954
+ "grad_norm": 1.0276700258255005,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.4192,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.09213716660893662,
961
+ "grad_norm": 1.0592403411865234,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.8051,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.09282992726013163,
968
+ "grad_norm": 1.0674453973770142,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.5308,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.09352268791132663,
975
+ "grad_norm": 1.1967990398406982,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.6214,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.09421544856252165,
982
+ "grad_norm": 1.3590198755264282,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.8485,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.09490820921371666,
989
+ "grad_norm": 1.393479585647583,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5188,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09560096986491168,
996
+ "grad_norm": 1.4235612154006958,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.579,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09629373051610668,
1003
+ "grad_norm": 1.5139780044555664,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5479,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0969864911673017,
1010
+ "grad_norm": 1.5156546831130981,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.6592,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09767925181849671,
1017
+ "grad_norm": 1.5736416578292847,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7471,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09837201246969172,
1024
+ "grad_norm": 1.863377332687378,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.6134,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09906477312088674,
1031
+ "grad_norm": 2.1274333000183105,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.8196,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09975753377208174,
1038
+ "grad_norm": 1.9414417743682861,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.7024,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.10045029442327676,
1045
+ "grad_norm": 2.2269279956817627,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.7322,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.10114305507447177,
1052
+ "grad_norm": 2.3395190238952637,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.749,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.10183581572566679,
1059
+ "grad_norm": 2.3803727626800537,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.6153,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.10252857637686179,
1066
+ "grad_norm": 2.970226287841797,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.0335,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1032213370280568,
1073
+ "grad_norm": 3.3703672885894775,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.8923,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.10391409767925182,
1080
+ "grad_norm": 4.29112434387207,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.552,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.10391409767925182,
1087
+ "eval_loss": 1.5660514831542969,
1088
+ "eval_runtime": 184.5174,
1089
+ "eval_samples_per_second": 13.175,
1090
+ "eval_steps_per_second": 3.295,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null