bbytxt commited on
Commit
8f7dae5
·
verified ·
1 Parent(s): 914dbc9

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 sha256:91db19a4d1886e3d0a8dba988e8c4aefb6380137a1722f5877e0f039f09de765
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6166490909151867201e4a4dba2d4e34a3ff6b26a21c6ed0dce63ad3b53e81a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:485c9b189313663c9724f45337f87319abb2c41ca36b1108f95ae33d5605f881
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1f2f7973eedbf6d679ec83fb7a1f1e1ac8765257a3663b18614c9ed3686223
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6d462da0494e11688d71f8b57287cef6ce233aaa1d77af7d51d4af692ff1fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9876e664d71a439355ae26b7d143f5ca467a9adfbfdf19e514bbda7bae110d1c
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": 0.4530438780784607,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.23121387283236994,
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": 13.151,
732
  "eval_steps_per_second": 3.301,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5122848626927206e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3980286419391632,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3468208092485549,
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": 13.151,
732
  "eval_steps_per_second": 3.301,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.23352601156069364,
737
+ "grad_norm": 0.2852354049682617,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.4976,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.23583815028901733,
744
+ "grad_norm": 0.35582005977630615,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5344,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.23815028901734103,
751
+ "grad_norm": 0.4306597411632538,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.5123,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.24046242774566473,
758
+ "grad_norm": 0.4623056948184967,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.4795,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.24277456647398843,
765
+ "grad_norm": 0.45900461077690125,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.4629,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.24508670520231213,
772
+ "grad_norm": 0.3884137272834778,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.4861,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.24739884393063583,
779
+ "grad_norm": 0.38582172989845276,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.4635,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.24971098265895952,
786
+ "grad_norm": 0.36394259333610535,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.4533,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.2520231213872832,
793
+ "grad_norm": 0.3826720416545868,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4762,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.2543352601156069,
800
+ "grad_norm": 0.4032803177833557,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.4543,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.2566473988439306,
807
+ "grad_norm": 0.4062879979610443,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.4138,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2589595375722543,
814
+ "grad_norm": 0.40897321701049805,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.437,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.261271676300578,
821
+ "grad_norm": 0.38823291659355164,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.4179,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.2635838150289017,
828
+ "grad_norm": 0.4021931290626526,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4432,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2658959537572254,
835
+ "grad_norm": 0.38717618584632874,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.4293,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2682080924855491,
842
+ "grad_norm": 0.37913429737091064,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.4331,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.2705202312138728,
849
+ "grad_norm": 0.37779611349105835,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.4313,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.2728323699421965,
856
+ "grad_norm": 0.3787301182746887,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.4174,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2751445086705202,
863
+ "grad_norm": 0.37400850653648376,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3715,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2774566473988439,
870
+ "grad_norm": 0.4016834795475006,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3909,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.27976878612716766,
877
+ "grad_norm": 0.41165751218795776,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3953,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.28208092485549136,
884
+ "grad_norm": 0.397403359413147,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3943,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.28439306358381505,
891
+ "grad_norm": 0.42636638879776,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.4129,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.28670520231213875,
898
+ "grad_norm": 0.40113964676856995,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.4056,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.28901734104046245,
905
+ "grad_norm": 0.397616446018219,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.3683,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.29132947976878615,
912
+ "grad_norm": 0.40275707840919495,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3787,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.29364161849710985,
919
+ "grad_norm": 0.44181469082832336,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3794,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.29595375722543354,
926
+ "grad_norm": 0.4472711682319641,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.3897,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.29826589595375724,
933
+ "grad_norm": 0.42659565806388855,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.3889,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.30057803468208094,
940
+ "grad_norm": 0.4072771370410919,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3523,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.30289017341040464,
947
+ "grad_norm": 0.3996623456478119,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.3353,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.30520231213872834,
954
+ "grad_norm": 0.3975715637207031,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.3361,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.30751445086705204,
961
+ "grad_norm": 0.4468100368976593,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.3838,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.30982658959537573,
968
+ "grad_norm": 0.42215695977211,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.3393,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.31213872832369943,
975
+ "grad_norm": 0.4449115991592407,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4239,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.31445086705202313,
982
+ "grad_norm": 0.4244880676269531,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3593,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.31676300578034683,
989
+ "grad_norm": 0.43322813510894775,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.3543,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.3190751445086705,
996
+ "grad_norm": 0.43968623876571655,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3778,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.3213872832369942,
1003
+ "grad_norm": 0.44799986481666565,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3564,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.3236994219653179,
1010
+ "grad_norm": 0.4537672996520996,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3249,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.3260115606936416,
1017
+ "grad_norm": 0.44438549876213074,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.369,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.3283236994219653,
1024
+ "grad_norm": 0.47159919142723083,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3804,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.330635838150289,
1031
+ "grad_norm": 0.45272132754325867,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.3509,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.3329479768786127,
1038
+ "grad_norm": 0.4658597409725189,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3796,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.3352601156069364,
1045
+ "grad_norm": 0.4488268196582794,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3464,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.3375722543352601,
1052
+ "grad_norm": 0.4805041253566742,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3794,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.3398843930635838,
1059
+ "grad_norm": 0.5441201329231262,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3796,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.3421965317919075,
1066
+ "grad_norm": 0.7714905142784119,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4142,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3445086705202312,
1073
+ "grad_norm": 0.5890783071517944,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3823,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3468208092485549,
1080
+ "grad_norm": 0.6957663893699646,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.3374,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3468208092485549,
1087
+ "eval_loss": 0.3980286419391632,
1088
+ "eval_runtime": 55.4876,
1089
+ "eval_samples_per_second": 13.138,
1090
+ "eval_steps_per_second": 3.298,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2665416520656486e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null