bbytxt commited on
Commit
4f9eb20
·
verified ·
1 Parent(s): 8a6f12b

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 sha256:13d542e9735e9e1d453ebc11024950ae1156977d367cb2289b5900934e071806
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e519a7136fde9969561b3dfded5654d507721e3f9f1e856385f745f609c8993
3
  size 134235712
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ab12b447a4488b8d63d3cc705b08953c713824dfe9b2f382a00f117cddfafb3
3
  size 68309690
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120c5e4fd2ee8204f779d86b76a70c47e596675f80b79e3f08b93b917ad5f1c8
3
  size 68309690
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96ff6a0fb624a37fd2d534e54db98b1101ecb020f3f94bf91855ace2dfaf24e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a5b667d90db08dc0492dc3d96e47b490b50f1f3ba593428656c569cba0a3f5
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": 1.3124672174453735,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01798156889188582,
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": 63.406,
732
  "eval_steps_per_second": 15.853,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.130563221684224e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.266676902770996,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.026972353337828724,
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": 63.406,
732
  "eval_steps_per_second": 15.853,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.018161384580804674,
737
+ "grad_norm": 3.0927953720092773,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 4.7219,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.018341200269723534,
744
+ "grad_norm": 2.4117701053619385,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.0346,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.018521015958642393,
751
+ "grad_norm": 1.944919228553772,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 4.0665,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01870083164756125,
758
+ "grad_norm": 1.6473654508590698,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.3962,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.018880647336480108,
765
+ "grad_norm": 6.872864723205566,
766
+ "learning_rate": 5e-05,
767
+ "loss": 5.5185,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.019060463025398967,
772
+ "grad_norm": 8.84312915802002,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.8907,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.019240278714317823,
779
+ "grad_norm": 23.499691009521484,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 14.5035,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.019420094403236682,
786
+ "grad_norm": 1.1414278745651245,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.1426,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.019599910092155542,
793
+ "grad_norm": 1.1366653442382812,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.1498,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.019779725781074398,
800
+ "grad_norm": 1.1586591005325317,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 4.38,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.019959541469993257,
807
+ "grad_norm": 1.1299108266830444,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 4.2907,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.020139357158912116,
814
+ "grad_norm": 1.0422109365463257,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.0555,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.020319172847830972,
821
+ "grad_norm": 1.182247281074524,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.5219,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.02049898853674983,
828
+ "grad_norm": 1.2507672309875488,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.2076,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02067880422566869,
835
+ "grad_norm": 1.490870475769043,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.5297,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.020858619914587546,
842
+ "grad_norm": 1.6921954154968262,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.0783,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.021038435603506406,
849
+ "grad_norm": 1.7724065780639648,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.7452,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.021218251292425265,
856
+ "grad_norm": 1.983605146408081,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.8282,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02139806698134412,
863
+ "grad_norm": 2.102980613708496,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.8787,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02157788267026298,
870
+ "grad_norm": 2.0234570503234863,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.9748,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02175769835918184,
877
+ "grad_norm": 2.22562313079834,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.9043,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.021937514048100695,
884
+ "grad_norm": 2.026779890060425,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.8919,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.022117329737019555,
891
+ "grad_norm": 2.259678840637207,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.7569,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.022297145425938414,
898
+ "grad_norm": 2.704587697982788,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.255,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.02247696111485727,
905
+ "grad_norm": 2.4990928173065186,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.1142,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.02265677680377613,
912
+ "grad_norm": 2.6718528270721436,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.0288,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02283659249269499,
919
+ "grad_norm": 2.499281406402588,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.8267,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.023016408181613844,
926
+ "grad_norm": 2.7516565322875977,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.151,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.023196223870532703,
933
+ "grad_norm": 2.75677752494812,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 5.2269,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.023376039559451563,
940
+ "grad_norm": 3.0223629474639893,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.1285,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.023555855248370422,
947
+ "grad_norm": 3.013000726699829,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.475,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.023735670937289278,
954
+ "grad_norm": 3.157944440841675,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.4984,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.023915486626208137,
961
+ "grad_norm": 2.9882850646972656,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.155,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.024095302315126996,
968
+ "grad_norm": 3.0872802734375,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.3129,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.024275118004045852,
975
+ "grad_norm": 3.3222086429595947,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.6433,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02445493369296471,
982
+ "grad_norm": 3.2879323959350586,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.1644,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02463474938188357,
989
+ "grad_norm": 4.245479583740234,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.8712,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.024814565070802427,
996
+ "grad_norm": 3.6900298595428467,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.7443,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.024994380759721286,
1003
+ "grad_norm": 3.6398282051086426,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.1735,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.025174196448640145,
1010
+ "grad_norm": 3.6330318450927734,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.701,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.025354012137559,
1017
+ "grad_norm": 3.6759214401245117,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.3478,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02553382782647786,
1024
+ "grad_norm": 4.149223327636719,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.922,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02571364351539672,
1031
+ "grad_norm": 4.057140350341797,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.8168,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.025893459204315575,
1038
+ "grad_norm": 3.7229368686676025,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.0563,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.026073274893234435,
1045
+ "grad_norm": 3.859713315963745,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.6961,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.026253090582153294,
1052
+ "grad_norm": 4.604867935180664,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.0718,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02643290627107215,
1059
+ "grad_norm": 4.342564582824707,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.7592,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02661272195999101,
1066
+ "grad_norm": 4.944156646728516,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.2069,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02679253764890987,
1073
+ "grad_norm": 6.3663811683654785,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.2485,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.026972353337828724,
1080
+ "grad_norm": 8.032842636108398,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 6.4474,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.026972353337828724,
1087
+ "eval_loss": 1.266676902770996,
1088
+ "eval_runtime": 147.67,
1089
+ "eval_samples_per_second": 63.432,
1090
+ "eval_steps_per_second": 15.86,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.1912131733487616e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null