prxy5608 commited on
Commit
3abd7a6
·
verified ·
1 Parent(s): 5af5d06

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 sha256:6a9a18abddce34657a19cb3ad5636d0558c30e86a8b1af08e95e795b119cbb3d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9025540ad2b3582ad70feae2840eb810a99114aae26e575e8cdbf44cf6a0868d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:888c121345f302826fbf147c201788f7e4d4f17870521c9e8e56f27a2f9fb798
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8b8251f629599301bf03fb70978967c097994e989f8f951fcda718ac097c79
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20f95e3ccc57127f25c87a8e4f3be3f8282d19322205084cc5f371fb09b24a94
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0efdbd0290c3bec2e18fc5b8e392511da6bd8857c2828ed0b57ea5b0bb5e49e
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": 1.097873330116272,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3129890453834116,
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": 10.596,
732
  "eval_steps_per_second": 2.654,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430998008987648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9583534002304077,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.4694835680751174,
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": 10.596,
732
  "eval_steps_per_second": 2.654,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3161189358372457,
737
+ "grad_norm": 17.200475692749023,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.0628,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3192488262910798,
744
+ "grad_norm": 16.55729103088379,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.6174,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.3223787167449139,
751
+ "grad_norm": 13.40699577331543,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 4.4485,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.325508607198748,
758
+ "grad_norm": 16.179691314697266,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.4267,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3286384976525822,
765
+ "grad_norm": 12.13221263885498,
766
+ "learning_rate": 5e-05,
767
+ "loss": 4.5886,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3317683881064163,
772
+ "grad_norm": 13.112076759338379,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.8863,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3348982785602504,
779
+ "grad_norm": 12.681835174560547,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.1724,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3380281690140845,
786
+ "grad_norm": 16.578872680664062,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.2564,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.3411580594679186,
793
+ "grad_norm": 16.367685317993164,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.6577,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3442879499217527,
800
+ "grad_norm": 13.197063446044922,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.7398,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.3474178403755869,
807
+ "grad_norm": 12.449812889099121,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 4.2059,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.350547730829421,
814
+ "grad_norm": 17.642208099365234,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.4826,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3536776212832551,
821
+ "grad_norm": 13.99929141998291,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.7785,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3568075117370892,
828
+ "grad_norm": 14.53055477142334,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.5251,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.3599374021909233,
835
+ "grad_norm": 11.492012023925781,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.3418,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.36306729264475746,
842
+ "grad_norm": 13.30124568939209,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.9226,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.36619718309859156,
849
+ "grad_norm": 16.955896377563477,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.6735,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.36932707355242567,
856
+ "grad_norm": 10.842327117919922,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.5142,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.37245696400625977,
863
+ "grad_norm": 12.223581314086914,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.324,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.3755868544600939,
870
+ "grad_norm": 19.217103958129883,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.5136,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.37871674491392804,
877
+ "grad_norm": 13.311538696289062,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.8219,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.38184663536776214,
884
+ "grad_norm": 13.755578994750977,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.2884,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.38497652582159625,
891
+ "grad_norm": 17.464670181274414,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.1701,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.38810641627543035,
898
+ "grad_norm": 12.010941505432129,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.8741,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.39123630672926446,
905
+ "grad_norm": 11.247178077697754,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.7416,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.39436619718309857,
912
+ "grad_norm": 14.176021575927734,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.4903,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.3974960876369327,
919
+ "grad_norm": 15.087220191955566,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.4811,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.40062597809076683,
926
+ "grad_norm": 11.732949256896973,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.8604,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.40375586854460094,
933
+ "grad_norm": 16.730178833007812,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.6548,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.40688575899843504,
940
+ "grad_norm": 17.501941680908203,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 6.8638,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.41001564945226915,
947
+ "grad_norm": 19.133256912231445,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.0677,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4131455399061033,
954
+ "grad_norm": 15.215507507324219,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.336,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4162754303599374,
961
+ "grad_norm": 11.798393249511719,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.5207,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.4194053208137715,
968
+ "grad_norm": 16.98396873474121,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.4974,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4225352112676056,
975
+ "grad_norm": 15.462417602539062,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.5462,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.42566510172143973,
982
+ "grad_norm": 14.0867919921875,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.0519,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4287949921752739,
989
+ "grad_norm": 16.403470993041992,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.5506,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.431924882629108,
996
+ "grad_norm": 14.880640983581543,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.3063,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.4350547730829421,
1003
+ "grad_norm": 15.50600528717041,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.7444,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.4381846635367762,
1010
+ "grad_norm": 12.847511291503906,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.386,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4413145539906103,
1017
+ "grad_norm": 12.983108520507812,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.3244,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4444444444444444,
1024
+ "grad_norm": 12.264243125915527,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.1835,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4475743348982786,
1031
+ "grad_norm": 15.786096572875977,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.2445,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4507042253521127,
1038
+ "grad_norm": 15.613906860351562,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.4688,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.4538341158059468,
1045
+ "grad_norm": 15.737792015075684,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.7568,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.4569640062597809,
1052
+ "grad_norm": 13.866209983825684,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.1838,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.460093896713615,
1059
+ "grad_norm": 13.762788772583008,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.3406,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.46322378716744916,
1066
+ "grad_norm": 11.111533164978027,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.917,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.46635367762128327,
1073
+ "grad_norm": 15.114660263061523,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 4.7809,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.4694835680751174,
1080
+ "grad_norm": 13.22601318359375,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.0232,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.4694835680751174,
1087
+ "eval_loss": 0.9583534002304077,
1088
+ "eval_runtime": 50.874,
1089
+ "eval_samples_per_second": 10.595,
1090
+ "eval_steps_per_second": 2.654,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146497013481472e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null