aleegis10 commited on
Commit
f8e7a3f
·
verified ·
1 Parent(s): eff569c

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 sha256:7e5de2140baf6f620427dc1d8842ffb9c0c189930283c13dea8371617bb0a6e6
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d86d3258681638a4515c9722c833bbfccb3c3d30b51b1a98178b851608df75
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e79ceabe181945fcd1f42dc8cc25109cc259d2c7b58843018d5166f218966efd
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4839fac77c05adc0ad1a359d9e737cd439fa03ddf72c41b6eb4847a04fe9ed
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:e544fa26e926e21e61c55ab734352ac990eb3e409ab96102d967c4788d6ba03b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debdffd3fb03aa00d21d8b6aa1a28278d4a890aa417da8280a477de1e03bc77f
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": 1.2086118459701538,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006492347145801886,
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": 13.061,
732
  "eval_steps_per_second": 3.265,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5160561466395853e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1435943841934204,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009738520718702829,
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": 13.061,
732
  "eval_steps_per_second": 3.265,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.006557270617259905,
737
+ "grad_norm": 0.7666314244270325,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1916,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006622194088717924,
744
+ "grad_norm": 0.7668541073799133,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.2555,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006687117560175942,
751
+ "grad_norm": 0.6754006147384644,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.439,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006752041031633961,
758
+ "grad_norm": 0.6046998500823975,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3285,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00681696450309198,
765
+ "grad_norm": 0.5599321722984314,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.095,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0068818879745499995,
772
+ "grad_norm": 0.5471016764640808,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2777,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006946811446008018,
779
+ "grad_norm": 0.49177172780036926,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.1703,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.007011734917466037,
786
+ "grad_norm": 0.5032525658607483,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1511,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007076658388924056,
793
+ "grad_norm": 0.5286602973937988,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.115,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007141581860382075,
800
+ "grad_norm": 0.5137684941291809,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.147,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.007206505331840094,
807
+ "grad_norm": 0.5753626823425293,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2481,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007271428803298112,
814
+ "grad_norm": 0.5408186316490173,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.2194,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.007336352274756131,
821
+ "grad_norm": 0.5109596252441406,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1028,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.00740127574621415,
828
+ "grad_norm": 0.5321526527404785,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1843,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007466199217672169,
835
+ "grad_norm": 0.6054028868675232,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3398,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007531122689130188,
842
+ "grad_norm": 0.5974127650260925,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.1662,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007596046160588206,
849
+ "grad_norm": 0.6349529027938843,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1256,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007660969632046225,
856
+ "grad_norm": 0.6932494640350342,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.1376,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007725893103504244,
863
+ "grad_norm": 0.6950923800468445,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3131,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0077908165749622635,
870
+ "grad_norm": 0.6611078381538391,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1848,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007855740046420282,
877
+ "grad_norm": 0.6949260830879211,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.1571,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0079206635178783,
884
+ "grad_norm": 0.7227311134338379,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.235,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.00798558698933632,
891
+ "grad_norm": 0.7589835524559021,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2022,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008050510460794339,
898
+ "grad_norm": 0.9023049473762512,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1878,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008115433932252357,
905
+ "grad_norm": 0.779160737991333,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.136,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008180357403710377,
912
+ "grad_norm": 0.8739699125289917,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.1297,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.008245280875168395,
919
+ "grad_norm": 1.034454107284546,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.3353,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008310204346626415,
926
+ "grad_norm": 0.9376235604286194,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.1614,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008375127818084433,
933
+ "grad_norm": 0.8876826763153076,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1918,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008440051289542451,
940
+ "grad_norm": 1.2257558107376099,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.029,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008504974761000471,
947
+ "grad_norm": 0.9673946499824524,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.0787,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.00856989823245849,
954
+ "grad_norm": 1.084344506263733,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.2127,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.00863482170391651,
961
+ "grad_norm": 1.0751358270645142,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.0577,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.008699745175374527,
968
+ "grad_norm": 1.241531252861023,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.0526,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008764668646832546,
975
+ "grad_norm": 1.5708144903182983,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1888,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.008829592118290566,
982
+ "grad_norm": 1.5015288591384888,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.1294,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008894515589748584,
989
+ "grad_norm": 1.4662539958953857,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.0714,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.008959439061206602,
996
+ "grad_norm": 1.8017679452896118,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.2173,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.009024362532664622,
1003
+ "grad_norm": 1.651761770248413,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.9604,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.00908928600412264,
1010
+ "grad_norm": 2.246441125869751,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0027,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00915420947558066,
1017
+ "grad_norm": 2.0347628593444824,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.9599,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.009219132947038678,
1024
+ "grad_norm": 2.0897066593170166,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0067,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.009284056418496696,
1031
+ "grad_norm": 4.240103244781494,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.0535,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009348979889954716,
1038
+ "grad_norm": 2.844397783279419,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0563,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.009413903361412734,
1045
+ "grad_norm": 2.234746217727661,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9805,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.009478826832870754,
1052
+ "grad_norm": 2.4138054847717285,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9855,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009543750304328772,
1059
+ "grad_norm": 2.2872800827026367,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.9283,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.00960867377578679,
1066
+ "grad_norm": 2.9530155658721924,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.4646,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.00967359724724481,
1073
+ "grad_norm": 3.5457417964935303,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1648,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009738520718702829,
1080
+ "grad_norm": 4.596130847930908,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.5164,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009738520718702829,
1087
+ "eval_loss": 1.1435943841934204,
1088
+ "eval_runtime": 1987.4184,
1089
+ "eval_samples_per_second": 13.053,
1090
+ "eval_steps_per_second": 3.264,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.274084219959378e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null