prxy5607 commited on
Commit
c787637
·
verified ·
1 Parent(s): a7001fd

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:ba40b2d2bd00af252b49b7c4f0110943554c3bba25fda95cb734a7b5c78af0b7
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e2d3e599ceccb51131143c3535a8bf1fea1f8fb7090f2e42512e31a7c5f29d
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:229b18585a8a12905cd1ad8b003396a838b9f821a7e46cd31fa95b7eed34f5ea
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:586995f97ab94b839676b5fdccfb670e75e5b09c5f1602bb7e1893c1d33964b0
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaf573cda31eda0b648e5f2f96ce6788009eede16eb2285431fff2395fdecba0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be13dfc437ebaf22fe1c460077f957a008e3b4eec1919313f3b5733f42e57f8b
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": 3.437983512878418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01597125174685566,
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": 28.699,
732
  "eval_steps_per_second": 7.177,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.060902527179162e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.3761205673217773,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02395687762028349,
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": 28.699,
732
  "eval_steps_per_second": 7.177,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.016130964264324216,
737
+ "grad_norm": 2.563222646713257,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.1601,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.016290676781792773,
744
+ "grad_norm": 2.3833115100860596,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.2734,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01645038929926133,
751
+ "grad_norm": 2.2120771408081055,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.3793,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.016610101816729887,
758
+ "grad_norm": 1.8844492435455322,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.2532,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.016769814334198444,
765
+ "grad_norm": 1.4038431644439697,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.2878,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.016929526851667,
772
+ "grad_norm": 1.0654053688049316,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.2445,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.017089239369135555,
779
+ "grad_norm": 0.8803927302360535,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.3826,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01724895188660411,
786
+ "grad_norm": 0.8809193968772888,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.3263,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01740866440407267,
793
+ "grad_norm": 0.9295204281806946,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.3115,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.017568376921541225,
800
+ "grad_norm": 0.9930161833763123,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.2609,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.017728089439009782,
807
+ "grad_norm": 1.0246449708938599,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.3752,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01788780195647834,
814
+ "grad_norm": 0.9885937571525574,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.3546,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.018047514473946896,
821
+ "grad_norm": 0.934032142162323,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.4028,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.018207226991415453,
828
+ "grad_norm": 0.9788658618927002,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.3554,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01836693950888401,
835
+ "grad_norm": 0.9676387310028076,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.3169,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.018526652026352567,
842
+ "grad_norm": 1.0396462678909302,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.2757,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01868636454382112,
849
+ "grad_norm": 1.0794548988342285,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.327,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.018846077061289677,
856
+ "grad_norm": 1.0206615924835205,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.225,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019005789578758234,
863
+ "grad_norm": 0.9828562140464783,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.3342,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01916550209622679,
870
+ "grad_norm": 1.2915130853652954,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.3889,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01932521461369535,
877
+ "grad_norm": 1.0610451698303223,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.3425,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.019484927131163905,
884
+ "grad_norm": 1.0585017204284668,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.3319,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.019644639648632462,
891
+ "grad_norm": 1.0622979402542114,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.527,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.01980435216610102,
898
+ "grad_norm": 1.0423346757888794,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.3608,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.019964064683569576,
905
+ "grad_norm": 1.0512298345565796,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.4576,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020123777201038133,
912
+ "grad_norm": 1.050781011581421,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.429,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.020283489718506686,
919
+ "grad_norm": 1.0709890127182007,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.4985,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.020443202235975243,
926
+ "grad_norm": 1.146832823753357,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.4954,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0206029147534438,
933
+ "grad_norm": 1.070890188217163,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.3281,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.020762627270912357,
940
+ "grad_norm": 1.0944342613220215,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.4404,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.020922339788380914,
947
+ "grad_norm": 1.1096227169036865,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.4476,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02108205230584947,
954
+ "grad_norm": 1.2392953634262085,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.4012,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.021241764823318028,
961
+ "grad_norm": 1.1994134187698364,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.3475,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.021401477340786585,
968
+ "grad_norm": 1.1271154880523682,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.1871,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.021561189858255142,
975
+ "grad_norm": 1.1170655488967896,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.2844,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0217209023757237,
982
+ "grad_norm": 1.148924469947815,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.5097,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.021880614893192252,
989
+ "grad_norm": 1.1717835664749146,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.5366,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02204032741066081,
996
+ "grad_norm": 1.1314111948013306,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.2612,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022200039928129366,
1003
+ "grad_norm": 1.1890403032302856,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.4438,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.022359752445597923,
1010
+ "grad_norm": 1.1819334030151367,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.4172,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02251946496306648,
1017
+ "grad_norm": 1.2623519897460938,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.4651,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.022679177480535037,
1024
+ "grad_norm": 1.2643638849258423,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.4054,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.022838889998003594,
1031
+ "grad_norm": 1.3270361423492432,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.5708,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.02299860251547215,
1038
+ "grad_norm": 1.2927286624908447,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.5297,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.023158315032940708,
1045
+ "grad_norm": 1.3989403247833252,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.3454,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.023318027550409265,
1052
+ "grad_norm": 1.3746222257614136,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.3294,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02347774006787782,
1059
+ "grad_norm": 1.6690480709075928,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.4948,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.023637452585346375,
1066
+ "grad_norm": 1.5143362283706665,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.5697,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.023797165102814932,
1073
+ "grad_norm": 1.5836552381515503,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.5201,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02395687762028349,
1080
+ "grad_norm": 1.9442321062088013,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.5552,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02395687762028349,
1087
+ "eval_loss": 3.3761205673217773,
1088
+ "eval_runtime": 367.4841,
1089
+ "eval_samples_per_second": 28.695,
1090
+ "eval_steps_per_second": 7.176,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.086290321283482e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null