dimasik87 commited on
Commit
6f33b12
·
verified ·
1 Parent(s): b76dd55

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 sha256:1d943ab670d2ec02491e4ebe4f1f2ed01bfa629f3da4219180d49a36fa32e8b2
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab027d881e26b357a9ca5309b8f0bd72dc5192e93518940c83ce76e729a2a3c
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90df2dd65c3d8592c96c2fd7951235ae235e6e1012c064ef1d64e770c929963d
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b8d4505a1180617ff42550d7d27adb81045ba20f7c43033474d7be6848d596
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a271bbcc82508aea764d98d0927295201f535afc9927e075a565c461e2f8b86
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c3f3a4004f97f7a1c245516adf7d14c992d3236b73f7f1bff9c3b60cc13c71
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": 1.6530330181121826,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01025010250102501,
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": 19.225,
732
  "eval_steps_per_second": 4.806,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.572495321923584e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6176789999008179,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.015375153751537515,
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": 19.225,
732
  "eval_steps_per_second": 4.806,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01035260352603526,
737
+ "grad_norm": 0.74406498670578,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 2.0527,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.010455104551045511,
744
+ "grad_norm": 0.8070314526557922,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 1.6314,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01055760557605576,
751
+ "grad_norm": 0.8939439058303833,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 1.8166,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01066010660106601,
758
+ "grad_norm": 0.9275736808776855,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 1.7837,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01076260762607626,
765
+ "grad_norm": 1.0159188508987427,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 1.8655,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.010865108651086511,
772
+ "grad_norm": 0.9382534027099609,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 1.634,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.010967609676096762,
779
+ "grad_norm": 0.8507430553436279,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 1.6201,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01107011070110701,
786
+ "grad_norm": 0.9986007809638977,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 1.7325,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01117261172611726,
793
+ "grad_norm": 0.955406904220581,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 1.6368,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.011275112751127511,
800
+ "grad_norm": 0.9369739294052124,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 1.5455,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.011377613776137762,
807
+ "grad_norm": 1.0813074111938477,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 1.6737,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.011480114801148012,
814
+ "grad_norm": 1.034050703048706,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 1.5688,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01158261582615826,
821
+ "grad_norm": 1.0678492784500122,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 1.6165,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.011685116851168511,
828
+ "grad_norm": 1.0256990194320679,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 1.3301,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.011787617876178762,
835
+ "grad_norm": 1.0190774202346802,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 1.6662,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.011890118901189012,
842
+ "grad_norm": 1.0290199518203735,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 1.5645,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.011992619926199263,
849
+ "grad_norm": 1.0103486776351929,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 1.2945,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.012095120951209511,
856
+ "grad_norm": 1.2646342515945435,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 1.735,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.012197621976219762,
863
+ "grad_norm": 1.2448196411132812,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 1.5587,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.012300123001230012,
870
+ "grad_norm": 1.3261544704437256,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 1.7949,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.012402624026240263,
877
+ "grad_norm": 1.2770674228668213,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 1.4959,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.012505125051250513,
884
+ "grad_norm": 1.4941719770431519,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 1.5308,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.012607626076260762,
891
+ "grad_norm": 1.2907934188842773,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 1.7877,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.012710127101271012,
898
+ "grad_norm": 1.3961200714111328,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 1.7712,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.012812628126281263,
905
+ "grad_norm": 1.4105072021484375,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 1.6403,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.012915129151291513,
912
+ "grad_norm": 1.323488473892212,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 1.5076,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.013017630176301764,
919
+ "grad_norm": 1.4488778114318848,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 1.655,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.013120131201312012,
926
+ "grad_norm": 1.50008225440979,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 1.7404,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.013222632226322263,
933
+ "grad_norm": 1.4806251525878906,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 1.4379,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.013325133251332513,
940
+ "grad_norm": 1.5019195079803467,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 1.5715,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.013427634276342764,
947
+ "grad_norm": 1.620043158531189,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 1.0703,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.013530135301353014,
954
+ "grad_norm": 1.8016197681427002,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 1.3446,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.013632636326363263,
961
+ "grad_norm": 2.6074109077453613,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 1.3707,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.013735137351373513,
968
+ "grad_norm": 2.0289924144744873,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 1.836,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.013837638376383764,
975
+ "grad_norm": 2.613877058029175,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 1.9227,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.013940139401394014,
982
+ "grad_norm": 2.5930979251861572,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 1.5137,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.014042640426404265,
989
+ "grad_norm": 2.3788273334503174,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 1.5968,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.014145141451414513,
996
+ "grad_norm": 2.544044256210327,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 1.8297,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.014247642476424764,
1003
+ "grad_norm": 1.9537235498428345,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 1.19,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.014350143501435014,
1010
+ "grad_norm": 2.7683722972869873,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 1.753,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.014452644526445265,
1017
+ "grad_norm": 2.9598679542541504,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 1.6878,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.014555145551455515,
1024
+ "grad_norm": 2.162545919418335,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 1.0099,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.014657646576465764,
1031
+ "grad_norm": 2.538316249847412,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 1.57,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.014760147601476014,
1038
+ "grad_norm": 2.4566807746887207,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 1.2957,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.014862648626486265,
1045
+ "grad_norm": 2.836510181427002,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 1.7585,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.014965149651496515,
1052
+ "grad_norm": 2.739304780960083,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 1.0675,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.015067650676506766,
1059
+ "grad_norm": 3.267035484313965,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 1.3077,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.015170151701517014,
1066
+ "grad_norm": 3.737492084503174,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 1.5623,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.015272652726527265,
1073
+ "grad_norm": 3.9221222400665283,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 1.4467,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.015375153751537515,
1080
+ "grad_norm": 9.252695083618164,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 2.2941,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.015375153751537515,
1087
+ "eval_loss": 1.6176789999008179,
1088
+ "eval_runtime": 213.9116,
1089
+ "eval_samples_per_second": 19.204,
1090
+ "eval_steps_per_second": 4.801,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.349856178601984e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null