prxy5605 commited on
Commit
d0eabdc
·
verified ·
1 Parent(s): 958f819

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 sha256:49ec199b5c98b48873360b6790b211a33ae3e9fd392389a01b4e6a8bc761109f
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8674c4857d86cff24cba072c2b541b830bc871f68c3dfa393082fecd1816b215
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcc87b9121428faa450989724a959f52cf5e8dcd5ea46ff647e000bd90e6ac8b
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e9cb9ba608f95f54ae254d2f2110070fd2b10f727b39af981b94ccab5dc3d4
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad7b75e73364c3cd9101bf05d417fd520f6d5501bee44305c4ca9026cb0e7817
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f561c8f873ea0b5dfb5639d1c4834359f395f862f04c10d1f68400083b0bed5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.40419265627861023,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06312135079690705,
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": 11.083,
732
  "eval_steps_per_second": 5.541,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5919852849987584e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3925303518772125,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09468202619536058,
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": 11.083,
732
  "eval_steps_per_second": 5.541,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06375256430487612,
737
+ "grad_norm": 1.128631830215454,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.9465,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0643837778128452,
744
+ "grad_norm": 1.3276664018630981,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 1.3996,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06501499132081427,
751
+ "grad_norm": 1.2908798456192017,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 1.2058,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06564620482878333,
758
+ "grad_norm": 1.2702507972717285,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 1.3292,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06627741833675241,
765
+ "grad_norm": 1.4327809810638428,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 1.7259,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06690863184472148,
772
+ "grad_norm": 1.3425438404083252,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 1.4477,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06753984535269054,
779
+ "grad_norm": 1.397606611251831,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 1.4911,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06817105886065962,
786
+ "grad_norm": 1.3934853076934814,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 1.3199,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0688022723686287,
793
+ "grad_norm": 1.4510592222213745,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 1.6421,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06943348587659776,
800
+ "grad_norm": 1.425351619720459,
801
+ "learning_rate": 5e-05,
802
+ "loss": 1.5701,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07006469938456683,
807
+ "grad_norm": 1.503740906715393,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 1.4684,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0706959128925359,
814
+ "grad_norm": 1.4400185346603394,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 1.423,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07132712640050497,
821
+ "grad_norm": 1.5304445028305054,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 1.6053,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07195833990847404,
828
+ "grad_norm": 1.4800596237182617,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 1.6218,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07258955341644312,
835
+ "grad_norm": 1.630185604095459,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 1.8255,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07322076692441218,
842
+ "grad_norm": 1.5210514068603516,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 1.5067,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07385198043238125,
849
+ "grad_norm": 1.559752345085144,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 1.5384,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07448319394035033,
856
+ "grad_norm": 1.586678147315979,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.5304,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07511440744831939,
863
+ "grad_norm": 1.4632230997085571,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 1.5951,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07574562095628846,
870
+ "grad_norm": 1.5816446542739868,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 1.7446,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07637683446425754,
877
+ "grad_norm": 1.559669852256775,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 1.5426,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0770080479722266,
884
+ "grad_norm": 1.6283562183380127,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.8152,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07763926148019568,
891
+ "grad_norm": 1.5507304668426514,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.5015,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07827047498816475,
898
+ "grad_norm": 1.5461734533309937,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 1.5926,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07890168849613381,
905
+ "grad_norm": 1.6004427671432495,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 1.5735,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07953290200410289,
912
+ "grad_norm": 1.6594659090042114,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 1.6118,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08016411551207196,
919
+ "grad_norm": 1.65187406539917,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 1.6812,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08079532902004102,
926
+ "grad_norm": 1.6164668798446655,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.6003,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0814265425280101,
933
+ "grad_norm": 1.607835054397583,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 1.526,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08205775603597917,
940
+ "grad_norm": 1.707564353942871,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.7708,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08268896954394823,
947
+ "grad_norm": 1.6170071363449097,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 1.702,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08332018305191731,
954
+ "grad_norm": 1.6684552431106567,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 1.5426,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08395139655988638,
961
+ "grad_norm": 1.6673823595046997,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 1.6907,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08458261006785545,
968
+ "grad_norm": 1.6971157789230347,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 1.6752,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08521382357582452,
975
+ "grad_norm": 1.725826382637024,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.6407,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0858450370837936,
982
+ "grad_norm": 1.7856934070587158,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.6094,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08647625059176266,
989
+ "grad_norm": 1.669678807258606,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.6688,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08710746409973173,
996
+ "grad_norm": 1.6383804082870483,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.4347,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08773867760770081,
1003
+ "grad_norm": 1.760483741760254,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.6037,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.08836989111566987,
1010
+ "grad_norm": 1.814774513244629,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.8616,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08900110462363894,
1017
+ "grad_norm": 1.8109049797058105,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 1.6744,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.08963231813160802,
1024
+ "grad_norm": 1.82987380027771,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 1.7784,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0902635316395771,
1031
+ "grad_norm": 1.7920920848846436,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 1.701,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09089474514754615,
1038
+ "grad_norm": 1.8180540800094604,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.5727,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09152595865551523,
1045
+ "grad_norm": 1.8675249814987183,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 1.4887,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0921571721634843,
1052
+ "grad_norm": 2.0394644737243652,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 1.6597,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09278838567145337,
1059
+ "grad_norm": 1.9944242238998413,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 1.6877,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09341959917942244,
1066
+ "grad_norm": 1.9664406776428223,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 1.3912,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09405081268739152,
1073
+ "grad_norm": 2.1415047645568848,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.4632,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09468202619536058,
1080
+ "grad_norm": 2.2631072998046875,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 1.3699,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09468202619536058,
1087
+ "eval_loss": 0.3925303518772125,
1088
+ "eval_runtime": 240.523,
1089
+ "eval_samples_per_second": 11.092,
1090
+ "eval_steps_per_second": 5.546,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3933441700318413e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null