ciloku commited on
Commit
0871d01
·
verified ·
1 Parent(s): 7c37b2a

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 sha256:02adea0c078b9237109f11e60cb08bb51be6204374589e6e02643a1a3f7b179f
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05aa21867173975b54c2433e2ea2e2d33b9477ac7d7330c058890afd12903750
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ea0a7e10314faf1b04ad2b5c07c7157a226207eba87f8932afb95f567984004
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3a4b1e126c0099f085d2e4a8565a1d034f0d691cbe73ac35fc1487961c814d
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:a4dfbe9f6b9a0e0944ac634d00c2eec1843aea882374d48474c5fc2a25883176
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351daf090d5da39941e428a5c5910a98049d94fdb508be4f472927f329dbcf8c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6460bb99370887d9faf3cffceb8d3101c13b7403d6f4c0b1c1e2e73b5257e4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4a786186a574bdc543ff4b4563aab7c5e0b442c74c85899bb42a25553c5d0c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0051817893981934,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.34305317324185247,
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": 13.337,
732
  "eval_steps_per_second": 3.341,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3804027338817536e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9647265076637268,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5145797598627787,
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": 13.337,
732
  "eval_steps_per_second": 3.341,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.346483704974271,
737
+ "grad_norm": 0.36224040389060974,
738
+ "learning_rate": 3.1982717529770985e-05,
739
+ "loss": 1.0916,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.34991423670668953,
744
+ "grad_norm": 0.38614827394485474,
745
+ "learning_rate": 3.148751264019667e-05,
746
+ "loss": 1.135,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.35334476843910806,
751
+ "grad_norm": 0.3652215600013733,
752
+ "learning_rate": 3.099190107951924e-05,
753
+ "loss": 1.0972,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3567753001715266,
758
+ "grad_norm": 0.3642301559448242,
759
+ "learning_rate": 3.049601834299076e-05,
760
+ "loss": 1.0843,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3602058319039451,
765
+ "grad_norm": 0.3324933350086212,
766
+ "learning_rate": 3e-05,
767
+ "loss": 1.1357,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.36363636363636365,
772
+ "grad_norm": 0.32382386922836304,
773
+ "learning_rate": 2.9503981657009246e-05,
774
+ "loss": 1.0928,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3670668953687822,
779
+ "grad_norm": 0.31067949533462524,
780
+ "learning_rate": 2.9008098920480752e-05,
781
+ "loss": 1.0738,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3704974271012007,
786
+ "grad_norm": 0.3035469055175781,
787
+ "learning_rate": 2.851248735980333e-05,
788
+ "loss": 1.0208,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.37392795883361923,
793
+ "grad_norm": 0.3173302412033081,
794
+ "learning_rate": 2.801728247022902e-05,
795
+ "loss": 1.0499,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.37735849056603776,
800
+ "grad_norm": 0.30463680624961853,
801
+ "learning_rate": 2.7522619635830034e-05,
802
+ "loss": 1.0523,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.38078902229845624,
807
+ "grad_norm": 0.3191668689250946,
808
+ "learning_rate": 2.702863409248612e-05,
809
+ "loss": 1.0131,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.38421955403087477,
814
+ "grad_norm": 0.3322906494140625,
815
+ "learning_rate": 2.6535460890912416e-05,
816
+ "loss": 0.944,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3876500857632933,
821
+ "grad_norm": 0.3359247148036957,
822
+ "learning_rate": 2.604323485973793e-05,
823
+ "loss": 0.9608,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3910806174957118,
828
+ "grad_norm": 0.32519465684890747,
829
+ "learning_rate": 2.555209056864474e-05,
830
+ "loss": 0.969,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.39451114922813035,
835
+ "grad_norm": 0.3210972547531128,
836
+ "learning_rate": 2.5062162291577978e-05,
837
+ "loss": 1.0239,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3979416809605489,
842
+ "grad_norm": 0.323660671710968,
843
+ "learning_rate": 2.4573583970036712e-05,
844
+ "loss": 1.0374,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4013722126929674,
849
+ "grad_norm": 0.3377305567264557,
850
+ "learning_rate": 2.4086489176455595e-05,
851
+ "loss": 0.9631,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.40480274442538594,
856
+ "grad_norm": 0.33635398745536804,
857
+ "learning_rate": 2.36010110776876e-05,
858
+ "loss": 1.0388,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.40823327615780447,
863
+ "grad_norm": 0.3557407259941101,
864
+ "learning_rate": 2.3117282398597456e-05,
865
+ "loss": 0.9769,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.411663807890223,
870
+ "grad_norm": 0.34973031282424927,
871
+ "learning_rate": 2.263543538577603e-05,
872
+ "loss": 1.0182,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.41509433962264153,
877
+ "grad_norm": 0.3528589606285095,
878
+ "learning_rate": 2.215560177138541e-05,
879
+ "loss": 0.9451,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.41852487135506006,
884
+ "grad_norm": 0.38225072622299194,
885
+ "learning_rate": 2.167791273714467e-05,
886
+ "loss": 0.9343,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4219554030874786,
891
+ "grad_norm": 0.41067805886268616,
892
+ "learning_rate": 2.1202498878466062e-05,
893
+ "loss": 1.0003,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.42538593481989706,
898
+ "grad_norm": 0.3684796094894409,
899
+ "learning_rate": 2.072949016875158e-05,
900
+ "loss": 0.9985,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4288164665523156,
905
+ "grad_norm": 0.40370795130729675,
906
+ "learning_rate": 2.0259015923859498e-05,
907
+ "loss": 1.0254,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4322469982847341,
912
+ "grad_norm": 0.40378862619400024,
913
+ "learning_rate": 1.979120476675071e-05,
914
+ "loss": 1.0512,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.43567753001715265,
919
+ "grad_norm": 0.40470102429389954,
920
+ "learning_rate": 1.9326184592324503e-05,
921
+ "loss": 0.9445,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.4391080617495712,
926
+ "grad_norm": 0.39239588379859924,
927
+ "learning_rate": 1.8864082532453373e-05,
928
+ "loss": 0.9897,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4425385934819897,
933
+ "grad_norm": 0.4297294318675995,
934
+ "learning_rate": 1.840502492122644e-05,
935
+ "loss": 0.948,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.44596912521440824,
940
+ "grad_norm": 0.3933764398097992,
941
+ "learning_rate": 1.7949137260410924e-05,
942
+ "loss": 0.9737,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.44939965694682676,
947
+ "grad_norm": 0.3823975920677185,
948
+ "learning_rate": 1.7496544185141295e-05,
949
+ "loss": 0.9043,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4528301886792453,
954
+ "grad_norm": 0.40711742639541626,
955
+ "learning_rate": 1.7047369429845216e-05,
956
+ "loss": 0.9259,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4562607204116638,
961
+ "grad_norm": 0.42227280139923096,
962
+ "learning_rate": 1.6601735794415806e-05,
963
+ "loss": 0.9292,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.45969125214408235,
968
+ "grad_norm": 0.41876545548439026,
969
+ "learning_rate": 1.615976511063937e-05,
970
+ "loss": 0.9579,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4631217838765009,
975
+ "grad_norm": 0.426393985748291,
976
+ "learning_rate": 1.5721578208887793e-05,
977
+ "loss": 0.9606,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4665523156089194,
982
+ "grad_norm": 0.446198046207428,
983
+ "learning_rate": 1.5287294885084766e-05,
984
+ "loss": 0.9419,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4699828473413379,
989
+ "grad_norm": 0.4536357522010803,
990
+ "learning_rate": 1.4857033867954697e-05,
991
+ "loss": 1.0326,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4734133790737564,
996
+ "grad_norm": 0.45464301109313965,
997
+ "learning_rate": 1.4430912786563554e-05,
998
+ "loss": 1.0325,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.47684391080617494,
1003
+ "grad_norm": 0.45512655377388,
1004
+ "learning_rate": 1.4009048138160195e-05,
1005
+ "loss": 0.9605,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.48027444253859347,
1010
+ "grad_norm": 0.4851442575454712,
1011
+ "learning_rate": 1.3591555256327199e-05,
1012
+ "loss": 0.9561,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.483704974271012,
1017
+ "grad_norm": 0.4672333300113678,
1018
+ "learning_rate": 1.3178548279449822e-05,
1019
+ "loss": 0.9497,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.48713550600343053,
1024
+ "grad_norm": 0.49268803000450134,
1025
+ "learning_rate": 1.2770140119511693e-05,
1026
+ "loss": 0.9491,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.49056603773584906,
1031
+ "grad_norm": 0.5017989277839661,
1032
+ "learning_rate": 1.2366442431225809e-05,
1033
+ "loss": 0.9614,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4939965694682676,
1038
+ "grad_norm": 0.5563336610794067,
1039
+ "learning_rate": 1.1967565581509248e-05,
1040
+ "loss": 0.995,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4974271012006861,
1045
+ "grad_norm": 0.5561904907226562,
1046
+ "learning_rate": 1.1573618619309965e-05,
1047
+ "loss": 1.0163,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5008576329331046,
1052
+ "grad_norm": 0.5744907855987549,
1053
+ "learning_rate": 1.1184709245793889e-05,
1054
+ "loss": 1.0965,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5042881646655232,
1059
+ "grad_norm": 0.6907095313072205,
1060
+ "learning_rate": 1.0800943784900502e-05,
1061
+ "loss": 0.9873,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5077186963979416,
1066
+ "grad_norm": 0.6119263768196106,
1067
+ "learning_rate": 1.042242715427494e-05,
1068
+ "loss": 0.9336,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5111492281303602,
1073
+ "grad_norm": 0.705530047416687,
1074
+ "learning_rate": 1.004926283658455e-05,
1075
+ "loss": 1.0054,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5145797598627787,
1080
+ "grad_norm": 1.1301898956298828,
1081
+ "learning_rate": 9.681552851227774e-06,
1082
+ "loss": 1.0328,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5145797598627787,
1087
+ "eval_loss": 0.9647265076637268,
1088
+ "eval_runtime": 37.0798,
1089
+ "eval_samples_per_second": 13.242,
1090
+ "eval_steps_per_second": 3.317,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0722672366465843e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null