alchemist69 commited on
Commit
49deeaa
·
verified ·
1 Parent(s): 024fefe

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 sha256:0fa357a20d7f21536fdb924d7a8104744ae3aee8d918bbda7f6c079795e79970
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45e45ca7d3a0f636bf3dcd079bd8012583ff5ba425684c719d0cd170ac9bad4
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5880e75a3383c95d1ab9688b6c1cca8a9e2d09d9591027b87fc7dc36c9ba23
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928b8c417a8549c93ed46f003dd606e142a5afedc04b9d1bcec926fe2307ce3
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98a0d604872530d20701175f67aa0ece715763dd6f253e1b27685008bcabe078
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8f252c3d1c7f6c7ab7b35283e66950e759e3a6a4f9298b96cf8f2eb0c0e25f
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": 2.5357449054718018,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.004321567864821357,
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": 55.899,
732
  "eval_steps_per_second": 13.976,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7960336904749056.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2222373485565186,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0064823517972320355,
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": 55.899,
732
  "eval_steps_per_second": 13.976,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.004364783543469571,
737
+ "grad_norm": 2.230421543121338,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.5381,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.004407999222117784,
744
+ "grad_norm": 2.6643025875091553,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.7262,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004451214900765998,
751
+ "grad_norm": 1.3600833415985107,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.336,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004494430579414212,
758
+ "grad_norm": 1.4324188232421875,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.4007,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.004537646258062425,
765
+ "grad_norm": 1.2632137537002563,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.4797,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004580861936710639,
772
+ "grad_norm": 1.0838202238082886,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.5874,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004624077615358852,
779
+ "grad_norm": 0.8901143670082092,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.5016,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0046672932940070655,
786
+ "grad_norm": 0.7791396379470825,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.2775,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.00471050897265528,
793
+ "grad_norm": 0.83558189868927,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.551,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.004753724651303493,
800
+ "grad_norm": 0.9123079180717468,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.809,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.004796940329951706,
807
+ "grad_norm": 0.7764745354652405,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.3993,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.00484015600859992,
814
+ "grad_norm": 0.914115846157074,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.7408,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0048833716872481335,
821
+ "grad_norm": 0.9541878700256348,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.9164,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.004926587365896348,
828
+ "grad_norm": 0.9033474922180176,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.8551,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.004969803044544561,
835
+ "grad_norm": 0.9788798093795776,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.9718,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.005013018723192774,
842
+ "grad_norm": 0.9812341928482056,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.0141,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.005056234401840988,
849
+ "grad_norm": 1.0843638181686401,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.2219,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.005099450080489201,
856
+ "grad_norm": 1.1995590925216675,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.0114,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.005142665759137415,
863
+ "grad_norm": 1.1657427549362183,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.3271,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.005185881437785629,
870
+ "grad_norm": 1.1515438556671143,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.4316,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.005229097116433842,
877
+ "grad_norm": 1.143696904182434,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.0873,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.005272312795082056,
884
+ "grad_norm": 1.1540189981460571,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.1561,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.005315528473730269,
891
+ "grad_norm": 1.1534439325332642,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.1773,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.005358744152378483,
898
+ "grad_norm": 1.2039779424667358,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.3618,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.005401959831026697,
905
+ "grad_norm": 1.3046797513961792,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.2247,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.00544517550967491,
912
+ "grad_norm": 1.2940418720245361,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.3937,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.005488391188323124,
919
+ "grad_norm": 1.277789831161499,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.1374,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.005531606866971337,
926
+ "grad_norm": 1.410267949104309,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.0059,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0055748225456195505,
933
+ "grad_norm": 1.4004080295562744,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.2198,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.005618038224267765,
940
+ "grad_norm": 1.5924218893051147,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.1304,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.005661253902915978,
947
+ "grad_norm": 1.45093834400177,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.2004,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.005704469581564191,
954
+ "grad_norm": 1.613592505455017,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.1924,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.005747685260212405,
961
+ "grad_norm": 1.7190560102462769,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.3621,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0057909009388606185,
968
+ "grad_norm": 1.7284499406814575,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.369,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0058341166175088326,
975
+ "grad_norm": 2.0238022804260254,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.3721,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.005877332296157046,
982
+ "grad_norm": 2.1432666778564453,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.5473,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.005920547974805259,
989
+ "grad_norm": 2.3544888496398926,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.3199,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.005963763653453473,
996
+ "grad_norm": 2.298560619354248,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.387,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.006006979332101686,
1003
+ "grad_norm": 2.356074810028076,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.3223,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0060501950107499,
1010
+ "grad_norm": 2.7027668952941895,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.5456,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.006093410689398114,
1017
+ "grad_norm": 2.9178318977355957,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.592,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.006136626368046327,
1024
+ "grad_norm": 3.6187164783477783,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.8921,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.006179842046694541,
1031
+ "grad_norm": 4.825345993041992,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.1484,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.006223057725342754,
1038
+ "grad_norm": 5.179505825042725,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.0456,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.006266273403990968,
1045
+ "grad_norm": 5.007200241088867,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.8785,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.006309489082639182,
1052
+ "grad_norm": 8.197183609008789,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.4507,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.006352704761287395,
1059
+ "grad_norm": 10.905704498291016,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.9406,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.006395920439935609,
1066
+ "grad_norm": 11.057151794433594,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.9861,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.006439136118583822,
1073
+ "grad_norm": 12.691493034362793,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.4541,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0064823517972320355,
1080
+ "grad_norm": 15.140165328979492,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.7136,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0064823517972320355,
1087
+ "eval_loss": 2.2222373485565186,
1088
+ "eval_runtime": 697.9194,
1089
+ "eval_samples_per_second": 55.842,
1090
+ "eval_steps_per_second": 13.961,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1921184151044096e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null