nttx commited on
Commit
7c09cd7
·
verified ·
1 Parent(s): 0b3e576

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:a403061f6e9c11dc20f76f71c4e28eca715fca0efffc5519fc417d094cad3804
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8d641d8a10d1b733c72b48a776ea11d92598ec20d71e906ff75ba6fb8b451a
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87dc46cc5764f45fd7ba15c8033508855fac76a8ec60144457fd8c6c4735f59e
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13c5afe71d8ef92beaa4f604406c8753c785cb375ebd55f99c7f79fdae94fbe
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca6bf59f903c36ac7c5db8e71d6f2057fd65567c08d6589ce4e48497006af39e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698c84172e8cb39fbffd87ca0781d3c269ce7bc57bf3d84cee2d1465e4f109ef
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.12535908818244934,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.8080808080808081,
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": 12.133,
732
  "eval_steps_per_second": 6.096,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.37604737531904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1097421795129776,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.2161616161616162,
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": 12.133,
732
  "eval_steps_per_second": 6.096,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.8161616161616162,
737
+ "grad_norm": 0.16581574082374573,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.1527,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.8242424242424242,
744
+ "grad_norm": 0.16338536143302917,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.1264,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.8323232323232324,
751
+ "grad_norm": 0.1547755002975464,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.1383,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.8404040404040404,
758
+ "grad_norm": 0.16346782445907593,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.1301,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8484848484848485,
765
+ "grad_norm": 0.1595148742198944,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.1096,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.8565656565656565,
772
+ "grad_norm": 0.17755745351314545,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.1391,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.8646464646464647,
779
+ "grad_norm": 0.1880967915058136,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.1461,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.8727272727272727,
786
+ "grad_norm": 0.207597553730011,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.1356,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.8808080808080808,
793
+ "grad_norm": 0.16595274209976196,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.1171,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.8888888888888888,
800
+ "grad_norm": 0.18696972727775574,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.13,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.896969696969697,
807
+ "grad_norm": 0.1909806877374649,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.1282,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.9050505050505051,
814
+ "grad_norm": 0.21812571585178375,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.1428,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.9131313131313131,
821
+ "grad_norm": 0.22041140496730804,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.1563,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.9212121212121213,
828
+ "grad_norm": 0.23546423017978668,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.1468,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.9292929292929293,
835
+ "grad_norm": 0.20770074427127838,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.1306,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.9373737373737374,
842
+ "grad_norm": 0.19079814851284027,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.1243,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.9454545454545454,
849
+ "grad_norm": 0.18580639362335205,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.092,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.9535353535353536,
856
+ "grad_norm": 0.25704994797706604,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.1416,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.9616161616161616,
863
+ "grad_norm": 0.21285192668437958,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.1155,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.9696969696969697,
870
+ "grad_norm": 0.2817244231700897,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.0983,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.9777777777777777,
877
+ "grad_norm": 0.13769255578517914,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.1115,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.9858585858585859,
884
+ "grad_norm": 0.15998609364032745,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.1204,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.9939393939393939,
891
+ "grad_norm": 0.21727117896080017,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.1498,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.006060606060606,
898
+ "grad_norm": 0.3903018832206726,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.1544,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.0141414141414142,
905
+ "grad_norm": 0.11540907621383667,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.0935,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.0222222222222221,
912
+ "grad_norm": 0.14367812871932983,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.105,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.0303030303030303,
919
+ "grad_norm": 0.14474540948867798,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.1237,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.0383838383838384,
926
+ "grad_norm": 0.15209715068340302,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.1191,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.0464646464646465,
933
+ "grad_norm": 0.1337515115737915,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.1016,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.0545454545454545,
940
+ "grad_norm": 0.1540132761001587,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.1276,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.0626262626262626,
947
+ "grad_norm": 0.14906255900859833,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.1124,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.0707070707070707,
954
+ "grad_norm": 0.1601407527923584,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.1183,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.0787878787878789,
961
+ "grad_norm": 0.15859104692935944,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.0856,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.0868686868686868,
968
+ "grad_norm": 0.1468411684036255,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.1008,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.094949494949495,
975
+ "grad_norm": 0.1662897914648056,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.1176,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.103030303030303,
982
+ "grad_norm": 0.1451275497674942,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.0865,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.1111111111111112,
989
+ "grad_norm": 0.14780522882938385,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.0869,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.1191919191919193,
996
+ "grad_norm": 0.1837635636329651,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.118,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.1272727272727272,
1003
+ "grad_norm": 0.1539749652147293,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.1039,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.1353535353535353,
1010
+ "grad_norm": 0.17489545047283173,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.1032,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.1434343434343435,
1017
+ "grad_norm": 0.18241524696350098,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.1115,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.1515151515151516,
1024
+ "grad_norm": 0.1702713817358017,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.0934,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.1595959595959595,
1031
+ "grad_norm": 0.17830723524093628,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.0862,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.1676767676767676,
1038
+ "grad_norm": 0.17552687227725983,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.0881,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.1757575757575758,
1045
+ "grad_norm": 0.1744166612625122,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.095,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.183838383838384,
1052
+ "grad_norm": 0.18836869299411774,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.1105,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.1919191919191918,
1059
+ "grad_norm": 0.16465550661087036,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.0664,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.2,
1066
+ "grad_norm": 0.19188475608825684,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.0996,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.208080808080808,
1073
+ "grad_norm": 0.1971476525068283,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.0924,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.2161616161616162,
1080
+ "grad_norm": 0.1862366497516632,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.0757,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.2161616161616162,
1087
+ "eval_loss": 0.1097421795129776,
1088
+ "eval_runtime": 17.3569,
1089
+ "eval_samples_per_second": 12.041,
1090
+ "eval_steps_per_second": 6.049,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.05902443446272e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null