bbytxt commited on
Commit
84d47d8
·
verified ·
1 Parent(s): a072dfd

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 sha256:39c96e9cf6e2b3120bc0eab28ef2904c066bb6558ec88d64b40b1aa88ab94d95
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ccd82755ad2d2945eff4ca8f43e02b448b77ef9311657f270ec43a58060c0c
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e86d90101d2ebba69b9851ae781925ee77a2fce774b5eca84e0b2a3cea57241d
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fce541339fa5050de00caa960fd8d61ca21a43eca63d5718201fbfa2577f17
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5655b941a7f159665e5079bacde9cede7325b8416a425aa8bad17b596c7a1752
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d9bdfc2ba6154d61cd7260dd620e1f349213d69be6799af284de5a68d050df
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": 3.154662609100342,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.03716090672612412,
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": 87.032,
732
  "eval_steps_per_second": 21.758,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7469846010789888.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.0939109325408936,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.055741360089186176,
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": 87.032,
732
  "eval_steps_per_second": 21.758,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03753251579338536,
737
+ "grad_norm": 28.16967010498047,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 12.9067,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0379041248606466,
744
+ "grad_norm": 30.37758445739746,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 12.7569,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03827573392790784,
751
+ "grad_norm": 24.201208114624023,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 12.8335,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03864734299516908,
758
+ "grad_norm": 23.62079429626465,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 12.2592,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03901895206243032,
765
+ "grad_norm": 22.814987182617188,
766
+ "learning_rate": 5e-05,
767
+ "loss": 12.4559,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03939056112969157,
772
+ "grad_norm": 21.530044555664062,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 12.5896,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03976217019695281,
779
+ "grad_norm": 23.73486328125,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 12.3527,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.04013377926421405,
786
+ "grad_norm": 21.59313201904297,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 12.1843,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.04050538833147529,
793
+ "grad_norm": 23.252063751220703,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 12.442,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.04087699739873653,
800
+ "grad_norm": 23.04511833190918,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 12.0954,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.04124860646599777,
807
+ "grad_norm": 21.15141487121582,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 12.3417,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.04162021553325901,
814
+ "grad_norm": 22.450578689575195,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 12.1134,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.041991824600520256,
821
+ "grad_norm": 23.66915512084961,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 12.4642,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.042363433667781496,
828
+ "grad_norm": 24.237220764160156,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 12.2302,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.042735042735042736,
835
+ "grad_norm": 22.29314422607422,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 12.2421,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.043106651802303976,
842
+ "grad_norm": 25.172727584838867,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 12.1878,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.043478260869565216,
849
+ "grad_norm": 26.602157592773438,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 12.2879,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.043849869936826456,
856
+ "grad_norm": 24.090085983276367,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 12.4924,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.044221479004087696,
863
+ "grad_norm": 26.16728973388672,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 12.145,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.044593088071348944,
870
+ "grad_norm": 27.40218734741211,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.8146,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.044964697138610184,
877
+ "grad_norm": 24.844179153442383,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 12.1576,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.045336306205871424,
884
+ "grad_norm": 25.813631057739258,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 12.2498,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.045707915273132664,
891
+ "grad_norm": 27.253564834594727,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 13.0846,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.046079524340393904,
898
+ "grad_norm": 30.898393630981445,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 12.5038,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.046451133407655144,
905
+ "grad_norm": 28.49885368347168,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 12.0529,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.046822742474916385,
912
+ "grad_norm": 33.739097595214844,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 12.4644,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04719435154217763,
919
+ "grad_norm": 27.413183212280273,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.8988,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04756596060943887,
926
+ "grad_norm": 28.41815757751465,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 12.3175,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04793756967670011,
933
+ "grad_norm": 24.673856735229492,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.0224,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04830917874396135,
940
+ "grad_norm": 29.299766540527344,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 12.2135,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04868078781122259,
947
+ "grad_norm": 26.782230377197266,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 12.197,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04905239687848383,
954
+ "grad_norm": 40.575321197509766,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 12.0718,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04942400594574508,
961
+ "grad_norm": 24.29773712158203,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 12.2244,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04979561501300632,
968
+ "grad_norm": 25.015186309814453,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 12.3849,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.05016722408026756,
975
+ "grad_norm": 36.70491409301758,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.7532,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0505388331475288,
982
+ "grad_norm": 29.158506393432617,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 12.1616,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.05091044221479004,
989
+ "grad_norm": 25.96609115600586,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 12.0101,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.05128205128205128,
996
+ "grad_norm": 32.55073547363281,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 12.3175,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.05165366034931252,
1003
+ "grad_norm": 28.77853775024414,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 12.2389,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.05202526941657377,
1010
+ "grad_norm": 29.920581817626953,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.7101,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.05239687848383501,
1017
+ "grad_norm": 30.31206512451172,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 12.373,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.05276848755109625,
1024
+ "grad_norm": 34.891883850097656,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 12.0662,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.05314009661835749,
1031
+ "grad_norm": 40.02173614501953,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 12.6474,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.05351170568561873,
1038
+ "grad_norm": 36.588050842285156,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 13.1617,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.05388331475287997,
1045
+ "grad_norm": 34.155696868896484,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 12.7202,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.05425492382014121,
1052
+ "grad_norm": 33.35672378540039,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.7438,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.054626532887402456,
1059
+ "grad_norm": 34.478858947753906,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 13.309,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.054998141954663696,
1066
+ "grad_norm": 42.10382843017578,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 13.2585,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.055369751021924936,
1073
+ "grad_norm": 32.687721252441406,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 15.1013,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.055741360089186176,
1080
+ "grad_norm": 35.498931884765625,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 15.1974,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.055741360089186176,
1087
+ "eval_loss": 3.0939109325408936,
1088
+ "eval_runtime": 52.034,
1089
+ "eval_samples_per_second": 87.097,
1090
+ "eval_steps_per_second": 21.774,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1195454993727488e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null