dimasik87 commited on
Commit
6a09216
·
verified ·
1 Parent(s): aa64e60

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 sha256:98c6e105fbfcce98d87f563d001246c7a64a658c6e27133cbccfd826371987c3
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ad7dd5dab93baff8ab4200fee597bb9ba9de30f07968210705bdbc3353f2f2
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb7f94c7dff78b1b297888f15bbae78681bfd58928897bb34a7d67e0323df315
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404bf3aee8ccf09a689ca20f6656d263a3e16de1fcb9505a3db63b676675008a
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6ed9ebb7297ee2e0f818b649d564c25c55944ce776d4f6fb15d80ba0ede6b9d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7577594cb2e923f0986dcd66099d06bc38653ca89937b5665a0cf443b5a214d8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a1533051e4bee653afc683a4359c329f95831c0354ae8442616cabf80d0caa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5160658359527588,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0859106529209622,
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": 20.318,
732
  "eval_steps_per_second": 5.1,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.9943329193984e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4959875345230103,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.12886597938144329,
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": 20.318,
732
  "eval_steps_per_second": 5.1,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08676975945017182,
737
+ "grad_norm": 0.48756492137908936,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 1.4015,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08762886597938144,
744
+ "grad_norm": 0.42037105560302734,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 1.4429,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08848797250859107,
751
+ "grad_norm": 0.4923235774040222,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 1.4581,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08934707903780069,
758
+ "grad_norm": 0.41760286688804626,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 1.1997,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.09020618556701031,
765
+ "grad_norm": 0.4583994746208191,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 1.4086,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.09106529209621993,
772
+ "grad_norm": 0.458413302898407,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 1.5256,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09192439862542956,
779
+ "grad_norm": 0.4747663140296936,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 1.3945,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09278350515463918,
786
+ "grad_norm": 0.4569973647594452,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 1.4371,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0936426116838488,
793
+ "grad_norm": 0.4393562972545624,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 1.4525,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09450171821305842,
800
+ "grad_norm": 0.4615718424320221,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 1.578,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09536082474226804,
807
+ "grad_norm": 0.44367459416389465,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 1.4314,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09621993127147767,
814
+ "grad_norm": 0.4110322594642639,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 1.4254,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09707903780068729,
821
+ "grad_norm": 0.4521294832229614,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 1.5936,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0979381443298969,
828
+ "grad_norm": 0.4364003837108612,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 1.5987,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09879725085910653,
835
+ "grad_norm": 0.4320337772369385,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 1.5928,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09965635738831616,
842
+ "grad_norm": 0.47091159224510193,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 1.5915,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.10051546391752578,
849
+ "grad_norm": 0.4349591135978699,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 1.4902,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1013745704467354,
856
+ "grad_norm": 0.4385061264038086,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 1.6705,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10223367697594501,
863
+ "grad_norm": 0.4168137311935425,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 1.5591,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10309278350515463,
870
+ "grad_norm": 0.42430955171585083,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 1.4457,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10395189003436427,
877
+ "grad_norm": 0.4482705295085907,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 1.6385,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10481099656357389,
884
+ "grad_norm": 0.4236373007297516,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 1.5653,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1056701030927835,
891
+ "grad_norm": 0.4247753620147705,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 1.4705,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10652920962199312,
898
+ "grad_norm": 0.4102475345134735,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 1.387,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10738831615120274,
905
+ "grad_norm": 0.4251536428928375,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 1.5281,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.10824742268041238,
912
+ "grad_norm": 0.41173189878463745,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 1.5701,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.109106529209622,
919
+ "grad_norm": 0.4324643015861511,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 1.4983,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10996563573883161,
926
+ "grad_norm": 0.3974796235561371,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 1.4384,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.11082474226804123,
933
+ "grad_norm": 0.43069207668304443,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 1.5198,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11168384879725086,
940
+ "grad_norm": 0.4067608416080475,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 1.4449,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11254295532646048,
947
+ "grad_norm": 0.38891565799713135,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 1.3167,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1134020618556701,
954
+ "grad_norm": 0.41567280888557434,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 1.4248,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11426116838487972,
961
+ "grad_norm": 0.44299566745758057,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 1.5865,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11512027491408934,
968
+ "grad_norm": 0.3968340754508972,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 1.5147,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11597938144329897,
975
+ "grad_norm": 0.40769246220588684,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 1.5635,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11683848797250859,
982
+ "grad_norm": 0.4221096336841583,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 1.447,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11769759450171821,
989
+ "grad_norm": 0.38482198119163513,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 1.3877,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11855670103092783,
996
+ "grad_norm": 0.4175458550453186,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 1.5137,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11941580756013746,
1003
+ "grad_norm": 0.4658557176589966,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 1.366,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.12027491408934708,
1010
+ "grad_norm": 0.4771043658256531,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 1.4614,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1211340206185567,
1017
+ "grad_norm": 0.42562994360923767,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 1.1766,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12199312714776632,
1024
+ "grad_norm": 0.45292311906814575,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 1.3532,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12285223367697594,
1031
+ "grad_norm": 0.5051841735839844,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 1.501,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.12371134020618557,
1038
+ "grad_norm": 0.525606095790863,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 1.4933,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12457044673539519,
1045
+ "grad_norm": 0.500237762928009,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 1.2868,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1254295532646048,
1052
+ "grad_norm": 0.5657179355621338,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 1.5876,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12628865979381443,
1059
+ "grad_norm": 0.5619215369224548,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 1.4058,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12714776632302405,
1066
+ "grad_norm": 0.5765167474746704,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 1.6314,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12800687285223367,
1073
+ "grad_norm": 0.77131587266922,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 1.9087,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.12886597938144329,
1080
+ "grad_norm": 0.7527775168418884,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 1.4388,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.12886597938144329,
1087
+ "eval_loss": 1.4959875345230103,
1088
+ "eval_runtime": 24.189,
1089
+ "eval_samples_per_second": 20.257,
1090
+ "eval_steps_per_second": 5.085,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.4914993790976e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null