batrider32 commited on
Commit
72b4a1b
·
verified ·
1 Parent(s): e0c5bb2

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:d1de8bbf7cdc1db2ace225f6e5a3b45279cee34099b82df02f88d1924322a923
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b2f21c9edc3110f3391fa7bae346840058fe20e15341afc51b33c47ae216c0
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edfbc959d31f9b360b622ac02e1fb94a1cd6a67a3aef3a19cafe33a8a1001b5b
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238549d2a856a3f7d93d0cfa642492aaa780b65da6adc22c3809b491dc8a74bb
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:301a385331199a47e4f15faf79e0e300f872b64a4b27ae2dfd4f69d1e25eaf6e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ec587357ca5e663fb07d8f9c015192d6c7eace3b8dd2e47ddd205754fc5ef1
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": 1.4245853424072266,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.29673590504451036,
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": 15.933,
732
  "eval_steps_per_second": 3.983,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.73309481648128e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3904298543930054,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.44510385756676557,
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": 15.933,
732
  "eval_steps_per_second": 3.983,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.2997032640949555,
737
+ "grad_norm": 0.7217458486557007,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.4569,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3026706231454006,
744
+ "grad_norm": 0.7270596027374268,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.4766,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.3056379821958457,
751
+ "grad_norm": 0.6617496013641357,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5208,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3086053412462908,
758
+ "grad_norm": 0.6653552055358887,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3984,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3115727002967359,
765
+ "grad_norm": 0.5785252451896667,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.3608,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.314540059347181,
772
+ "grad_norm": 0.5672193765640259,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.3808,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.31750741839762614,
779
+ "grad_norm": 0.5402122735977173,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.3914,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.32047477744807124,
786
+ "grad_norm": 0.5698200464248657,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.3551,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.32344213649851633,
793
+ "grad_norm": 0.5605568885803223,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4337,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3264094955489614,
800
+ "grad_norm": 0.5771113634109497,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4192,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.3293768545994065,
807
+ "grad_norm": 0.5909971594810486,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.3785,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3323442136498516,
814
+ "grad_norm": 0.6007561683654785,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4542,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3353115727002967,
821
+ "grad_norm": 0.5695105195045471,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.336,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.33827893175074186,
828
+ "grad_norm": 0.5950984358787537,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.3729,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.34124629080118696,
835
+ "grad_norm": 0.6076891422271729,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3499,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.34421364985163205,
842
+ "grad_norm": 0.5678555965423584,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.4291,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.34718100890207715,
849
+ "grad_norm": 0.6131122708320618,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.4546,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.35014836795252224,
856
+ "grad_norm": 0.5945773124694824,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.3873,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.35311572700296734,
863
+ "grad_norm": 0.6098718047142029,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.268,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.3560830860534125,
870
+ "grad_norm": 0.6084814071655273,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.343,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.3590504451038576,
877
+ "grad_norm": 0.614021897315979,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.2607,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.3620178041543027,
884
+ "grad_norm": 0.6363130807876587,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.3795,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.3649851632047478,
891
+ "grad_norm": 0.6323707699775696,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3594,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.36795252225519287,
898
+ "grad_norm": 0.618251621723175,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.3814,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.37091988130563797,
905
+ "grad_norm": 0.6312515139579773,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.4107,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.37388724035608306,
912
+ "grad_norm": 0.6177896857261658,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.3998,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.3768545994065282,
919
+ "grad_norm": 0.6288518905639648,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.4556,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.3798219584569733,
926
+ "grad_norm": 0.6145934462547302,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.3746,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.3827893175074184,
933
+ "grad_norm": 0.6307049989700317,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.3405,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.3857566765578635,
940
+ "grad_norm": 0.6375620365142822,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.3608,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.3887240356083086,
947
+ "grad_norm": 0.632927417755127,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.3775,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3916913946587537,
954
+ "grad_norm": 0.6326116919517517,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3603,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.39465875370919884,
961
+ "grad_norm": 0.6409311294555664,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.3208,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.39762611275964393,
968
+ "grad_norm": 0.6683651804924011,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4976,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.40059347181008903,
975
+ "grad_norm": 0.6670704483985901,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.4857,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4035608308605341,
982
+ "grad_norm": 0.6627656817436218,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.4692,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4065281899109792,
989
+ "grad_norm": 0.6916190981864929,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.437,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4094955489614243,
996
+ "grad_norm": 0.6492981314659119,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3968,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.4124629080118694,
1003
+ "grad_norm": 0.6712226867675781,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3644,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.41543026706231456,
1010
+ "grad_norm": 0.637305736541748,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.332,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.41839762611275966,
1017
+ "grad_norm": 0.6960006952285767,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.3365,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.42136498516320475,
1024
+ "grad_norm": 0.6958258152008057,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.3504,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.42433234421364985,
1031
+ "grad_norm": 0.6706694960594177,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.3494,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.42729970326409494,
1038
+ "grad_norm": 0.7032877802848816,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.4288,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.43026706231454004,
1045
+ "grad_norm": 0.69391930103302,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.3836,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.4332344213649852,
1052
+ "grad_norm": 0.728171169757843,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.4764,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4362017804154303,
1059
+ "grad_norm": 0.7183287739753723,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.4355,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.4391691394658754,
1066
+ "grad_norm": 0.7382689118385315,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.4289,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.4421364985163205,
1073
+ "grad_norm": 0.7642919421195984,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.3995,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.44510385756676557,
1080
+ "grad_norm": 0.907598078250885,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.4087,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.44510385756676557,
1087
+ "eval_loss": 1.3904298543930054,
1088
+ "eval_runtime": 35.6332,
1089
+ "eval_samples_per_second": 15.94,
1090
+ "eval_steps_per_second": 3.985,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.59964222472192e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null