aleegis12 commited on
Commit
836fdab
·
verified ·
1 Parent(s): 1e65158

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 sha256:36e53edd075cd161d8de745d78eeec19547d29c9da3a44ad1f11fb0d260b940d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5dea04d13af60a9cd803e09badeb4dc66336e43fa1c48f9395694ae377184a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:107c9afca397321eba53a1f9b71f7d5e17df566dd96385f8a5abeda94b8b09f8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b32d483d98f2eff9c2c25676ba9b7c085738621edd3f09cd5028f30cb465f1
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:ce3f194643b4dd69f77fc4a51955be921f1a2045bc4f988e1958582626652d3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32f633b78872fda3ace9d9f1ed0368bf2c9d041bfed354af2e87a357abbd0b7
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": 0.810309112071991,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.054945054945054944,
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": 12.347,
732
  "eval_steps_per_second": 3.089,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.46892713361408e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7657567262649536,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08241758241758242,
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": 12.347,
732
  "eval_steps_per_second": 3.089,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05549450549450549,
737
+ "grad_norm": 2.7428088188171387,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.8487,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.056043956043956046,
744
+ "grad_norm": 4.557298183441162,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.7637,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.056593406593406594,
751
+ "grad_norm": 3.209634780883789,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.8463,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.05714285714285714,
758
+ "grad_norm": 5.7075276374816895,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7269,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.057692307692307696,
765
+ "grad_norm": 3.590937376022339,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9204,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.05824175824175824,
772
+ "grad_norm": 3.8173980712890625,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9498,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.05879120879120879,
779
+ "grad_norm": 3.6682701110839844,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.846,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.05934065934065934,
786
+ "grad_norm": 3.0619313716888428,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7405,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.05989010989010989,
793
+ "grad_norm": 3.3937807083129883,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8557,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06043956043956044,
800
+ "grad_norm": 3.5738933086395264,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.8423,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06098901098901099,
807
+ "grad_norm": 3.2693288326263428,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.7375,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06153846153846154,
814
+ "grad_norm": 3.017500638961792,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7283,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06208791208791209,
821
+ "grad_norm": 3.3882884979248047,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.949,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06263736263736264,
828
+ "grad_norm": 3.357642650604248,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9024,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06318681318681318,
835
+ "grad_norm": 3.2038471698760986,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7567,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06373626373626373,
842
+ "grad_norm": 3.5930140018463135,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.847,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06428571428571428,
849
+ "grad_norm": 3.030806303024292,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.817,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06483516483516484,
856
+ "grad_norm": 3.528214693069458,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8314,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06538461538461539,
863
+ "grad_norm": 3.717010736465454,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.8658,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.06593406593406594,
870
+ "grad_norm": 3.4061574935913086,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7038,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.06648351648351648,
877
+ "grad_norm": 2.5591681003570557,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.7427,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06703296703296703,
884
+ "grad_norm": 3.146589756011963,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.724,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.06758241758241758,
891
+ "grad_norm": 3.002185344696045,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.6943,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.06813186813186813,
898
+ "grad_norm": 3.108757257461548,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.8639,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.06868131868131869,
905
+ "grad_norm": 3.310210704803467,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9398,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.06923076923076923,
912
+ "grad_norm": 3.308823347091675,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.788,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.06978021978021978,
919
+ "grad_norm": 3.1850717067718506,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7686,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07032967032967033,
926
+ "grad_norm": 3.594505786895752,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7049,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07087912087912088,
933
+ "grad_norm": 3.527811288833618,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.9086,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07142857142857142,
940
+ "grad_norm": 3.708664894104004,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.8532,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07197802197802197,
947
+ "grad_norm": 3.2360305786132812,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.6813,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07252747252747253,
954
+ "grad_norm": 4.264449596405029,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.958,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.07307692307692308,
961
+ "grad_norm": 2.919825315475464,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7465,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07362637362637363,
968
+ "grad_norm": 3.232802629470825,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7196,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07417582417582418,
975
+ "grad_norm": 3.242577314376831,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.71,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07472527472527472,
982
+ "grad_norm": 3.7792561054229736,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8448,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.07527472527472527,
989
+ "grad_norm": 3.8947784900665283,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9169,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.07582417582417582,
996
+ "grad_norm": 3.439913749694824,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.7157,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.07637362637362638,
1003
+ "grad_norm": 2.68253231048584,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.6558,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.07692307692307693,
1010
+ "grad_norm": 4.011876583099365,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9641,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.07747252747252747,
1017
+ "grad_norm": 4.138200759887695,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7938,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.07802197802197802,
1024
+ "grad_norm": 4.425159454345703,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.9208,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.07857142857142857,
1031
+ "grad_norm": 3.966238498687744,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.8659,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.07912087912087912,
1038
+ "grad_norm": 4.205827236175537,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8532,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.07967032967032966,
1045
+ "grad_norm": 3.454686403274536,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7116,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08021978021978023,
1052
+ "grad_norm": 3.6158885955810547,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8404,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08076923076923077,
1059
+ "grad_norm": 4.816569805145264,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0318,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08131868131868132,
1066
+ "grad_norm": 4.617947101593018,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7545,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08186813186813187,
1073
+ "grad_norm": 2.717759132385254,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5016,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08241758241758242,
1080
+ "grad_norm": 3.2810633182525635,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.6501,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08241758241758242,
1087
+ "eval_loss": 0.7657567262649536,
1088
+ "eval_runtime": 248.2901,
1089
+ "eval_samples_per_second": 12.348,
1090
+ "eval_steps_per_second": 3.089,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.20339070042112e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null