ancient41 commited on
Commit
ab5e851
·
verified ·
1 Parent(s): 071eeaa

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 sha256:10e6406863ea1d92f1e1020cf2e8c1e12682ea930c3a8218ca094301611943fb
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb3445c9a73bff3ff5f85390b1bcd07c1d26bc07ca3969169d0c109931697ef
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a20df0bd6a04086079c627cdd5fdd7b459bf4a169391ecbd3b353b4ce0eba4a
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943eb5aa631847e9a435c6e17fb747a96875f461b42084fbedd84c65338cef3f
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8ee380e95e6e82fdc182840795b5effbdc3a1991636161dc88bdbf1fb71e418
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2477363bc463823e84454728572f636cbebb9f2564e60cb787fda6c5013d99ad
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": 0.96268630027771,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3898635477582846,
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": 22.46,
732
  "eval_steps_per_second": 5.615,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.14368026066944e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8595620393753052,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5847953216374269,
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": 22.46,
732
  "eval_steps_per_second": 5.615,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3937621832358674,
737
+ "grad_norm": 2.57578706741333,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1375,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.39766081871345027,
744
+ "grad_norm": 1.840401291847229,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0448,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4015594541910331,
751
+ "grad_norm": 1.357450008392334,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.7451,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.40545808966861596,
758
+ "grad_norm": 1.1181912422180176,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8256,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4093567251461988,
765
+ "grad_norm": 1.0798479318618774,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8896,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.41325536062378165,
772
+ "grad_norm": 0.9752025604248047,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8598,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4171539961013645,
779
+ "grad_norm": 0.8327402472496033,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.7254,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.42105263157894735,
786
+ "grad_norm": 0.9912234544754028,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7752,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4249512670565302,
793
+ "grad_norm": 0.8864346742630005,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.6974,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.42884990253411304,
800
+ "grad_norm": 0.840218186378479,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.767,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4327485380116959,
807
+ "grad_norm": 0.889740526676178,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.8652,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.43664717348927873,
814
+ "grad_norm": 0.9511635303497314,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7903,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.4405458089668616,
821
+ "grad_norm": 0.8167177438735962,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.7002,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.4444444444444444,
828
+ "grad_norm": 0.9066333174705505,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.7985,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.44834307992202727,
835
+ "grad_norm": 0.9710180163383484,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8682,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.4522417153996101,
842
+ "grad_norm": 1.026107668876648,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9463,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.45614035087719296,
849
+ "grad_norm": 1.144396424293518,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9756,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4600389863547758,
856
+ "grad_norm": 0.9720786213874817,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7923,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.46393762183235865,
863
+ "grad_norm": 0.8938807845115662,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.8101,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.4678362573099415,
870
+ "grad_norm": 1.144248127937317,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0173,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.47173489278752434,
877
+ "grad_norm": 0.9937459826469421,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8223,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4756335282651072,
884
+ "grad_norm": 0.9959102272987366,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8625,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.47953216374269003,
891
+ "grad_norm": 1.0088458061218262,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8588,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4834307992202729,
898
+ "grad_norm": 1.1958123445510864,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9693,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4873294346978557,
905
+ "grad_norm": 1.2331714630126953,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9571,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.49122807017543857,
912
+ "grad_norm": 1.2077465057373047,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.0563,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4951267056530214,
919
+ "grad_norm": 1.073055386543274,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.8451,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.49902534113060426,
926
+ "grad_norm": 1.2219706773757935,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.9929,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5029239766081871,
933
+ "grad_norm": 1.2187883853912354,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.8952,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.50682261208577,
940
+ "grad_norm": 1.0449047088623047,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.788,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5107212475633528,
947
+ "grad_norm": 1.2690509557724,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.0085,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5146198830409356,
954
+ "grad_norm": 1.0717588663101196,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.7838,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5185185185185185,
961
+ "grad_norm": 1.0692975521087646,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7223,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5224171539961013,
968
+ "grad_norm": 1.176875352859497,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7841,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5263157894736842,
975
+ "grad_norm": 1.1164765357971191,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7474,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.530214424951267,
982
+ "grad_norm": 1.1768156290054321,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7283,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5341130604288499,
989
+ "grad_norm": 1.33505117893219,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.8782,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5380116959064327,
996
+ "grad_norm": 1.3603265285491943,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8582,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5419103313840156,
1003
+ "grad_norm": 1.2987911701202393,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.8193,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5458089668615984,
1010
+ "grad_norm": 1.4902960062026978,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9436,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5497076023391813,
1017
+ "grad_norm": 1.3773430585861206,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7515,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5536062378167641,
1024
+ "grad_norm": 1.4242339134216309,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.8044,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.557504873294347,
1031
+ "grad_norm": 1.589614987373352,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.8548,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5614035087719298,
1038
+ "grad_norm": 1.4356437921524048,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8482,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5653021442495126,
1045
+ "grad_norm": 1.3600770235061646,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6998,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5692007797270955,
1052
+ "grad_norm": 1.4260246753692627,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.683,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5730994152046783,
1059
+ "grad_norm": 1.6639034748077393,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.8587,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5769980506822612,
1066
+ "grad_norm": 1.7599772214889526,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.8492,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.580896686159844,
1073
+ "grad_norm": 2.006871461868286,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1456,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5847953216374269,
1080
+ "grad_norm": 2.1173348426818848,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.0789,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5847953216374269,
1087
+ "eval_loss": 0.8595620393753052,
1088
+ "eval_runtime": 19.2515,
1089
+ "eval_samples_per_second": 22.44,
1090
+ "eval_steps_per_second": 5.61,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.21552039100416e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null