nttx commited on
Commit
a662248
·
verified ·
1 Parent(s): f33150f

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 sha256:527c620c8f76060997d8d29add6d54e8a4bbb01302f4e972970f642d422e0ffe
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aa5b9082738c47aa82582e18b6a0d3db14e1ca62110782d67d35f7651d6bb4
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2720e34bc517dd05a8866fc0c4ef6b9ca36077ba43f1ade1844d7dfd2415f058
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a544f5a11ebb57eab41dadfea8761d7b143f0abe46d540bc6aebe615be1d3e
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d8b8836f43a546956a1bc8471fcdba26d9404b35197da2230ed9e0902488491
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c8687d9cf0e416074c6cb6a0f12d990c5bc1a3a2c1d07d702c17cf6cd21e47
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": 0.5659072399139404,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1502065339842283,
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": 33.694,
732
  "eval_steps_per_second": 8.439,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.3173127051608064e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.44630166888237,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.22530980097634248,
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": 33.694,
732
  "eval_steps_per_second": 8.439,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1517085993240706,
737
+ "grad_norm": 2.895529270172119,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7982,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.1532106646639129,
744
+ "grad_norm": 1.8724274635314941,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.6634,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.15471273000375516,
751
+ "grad_norm": 0.6110711097717285,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.5691,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.15621479534359745,
758
+ "grad_norm": 0.33346492052078247,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.5415,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.15771686068343974,
765
+ "grad_norm": 0.3243321180343628,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.535,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.15921892602328203,
772
+ "grad_norm": 0.30207017064094543,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.5076,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1607209913631243,
779
+ "grad_norm": 0.2547878921031952,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.5209,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.16222305670296658,
786
+ "grad_norm": 0.2538004219532013,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.5153,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.16372512204280887,
793
+ "grad_norm": 0.310922235250473,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.5151,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.16522718738265116,
800
+ "grad_norm": 0.2497279793024063,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.496,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.16672925272249342,
807
+ "grad_norm": 0.2196495532989502,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.4956,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1682313180623357,
814
+ "grad_norm": 0.24011313915252686,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.5075,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.169733383402178,
821
+ "grad_norm": 0.2906111776828766,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.5019,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1712354487420203,
828
+ "grad_norm": 0.250466525554657,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.5044,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.17273751408186255,
835
+ "grad_norm": 0.2569282352924347,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.4807,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.17423957942170484,
842
+ "grad_norm": 0.21970154345035553,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.475,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.17574164476154713,
849
+ "grad_norm": 0.27862656116485596,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.4507,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.17724371010138942,
856
+ "grad_norm": 0.2613980174064636,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.4843,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.17874577544123169,
863
+ "grad_norm": 0.2648200988769531,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.4803,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.18024784078107398,
870
+ "grad_norm": 0.21359142661094666,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.4547,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.18174990612091627,
877
+ "grad_norm": 0.3049919605255127,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.4756,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.18325197146075856,
884
+ "grad_norm": 0.2409057766199112,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.4482,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.18475403680060082,
891
+ "grad_norm": 0.2844046652317047,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.4584,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1862561021404431,
898
+ "grad_norm": 0.25576141476631165,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.4534,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1877581674802854,
905
+ "grad_norm": 0.2949036657810211,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.4317,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1892602328201277,
912
+ "grad_norm": 0.26583975553512573,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.4551,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.19076229815996995,
919
+ "grad_norm": 0.23787036538124084,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.4281,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.19226436349981224,
926
+ "grad_norm": 0.2489592432975769,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.4411,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.19376642883965453,
933
+ "grad_norm": 0.24158670008182526,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.426,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.19526849417949682,
940
+ "grad_norm": 0.26309508085250854,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.4176,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.19677055951933908,
947
+ "grad_norm": 0.30277812480926514,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.4447,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.19827262485918137,
954
+ "grad_norm": 0.2779122292995453,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.4184,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.19977469019902366,
961
+ "grad_norm": 0.27596765756607056,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.4194,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.20127675553886595,
968
+ "grad_norm": 0.29626959562301636,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.4133,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.20277882087870822,
975
+ "grad_norm": 0.28480854630470276,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4135,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2042808862185505,
982
+ "grad_norm": 0.25113052129745483,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.4278,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.2057829515583928,
989
+ "grad_norm": 0.2552507519721985,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.4119,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.20728501689823509,
996
+ "grad_norm": 0.30283552408218384,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4133,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.20878708223807735,
1003
+ "grad_norm": 0.2749648988246918,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3889,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.21028914757791964,
1010
+ "grad_norm": 0.2759481370449066,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.4072,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.21179121291776193,
1017
+ "grad_norm": 0.30377233028411865,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.414,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.21329327825760422,
1024
+ "grad_norm": 0.28212490677833557,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.4027,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.21479534359744648,
1031
+ "grad_norm": 0.2726624608039856,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.4062,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.21629740893728877,
1038
+ "grad_norm": 0.3503369987010956,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.4023,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.21779947427713106,
1045
+ "grad_norm": 0.3181203603744507,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.4119,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.21930153961697335,
1052
+ "grad_norm": 0.28087958693504333,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3891,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2208036049568156,
1059
+ "grad_norm": 0.3313179910182953,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.4068,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2223056702966579,
1066
+ "grad_norm": 0.3119460940361023,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4139,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2238077356365002,
1073
+ "grad_norm": 0.3136446177959442,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3918,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.22530980097634248,
1080
+ "grad_norm": 0.4063158333301544,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.3947,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.22530980097634248,
1087
+ "eval_loss": 0.44630166888237,
1088
+ "eval_runtime": 33.3195,
1089
+ "eval_samples_per_second": 33.674,
1090
+ "eval_steps_per_second": 8.433,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.980105357872333e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null