abaddon182 commited on
Commit
fe68da1
·
verified ·
1 Parent(s): 74404f3

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:eceda081eedf38618e4698dc7f486f85225e4bc6668dddfc20deca2cc6ea4d6b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d8f8e700ee2f3f96ccc4592ed19db08422907d2455fdff727dfa4c130efb04
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e25757156d8e02297fc3e6ecc2b5e8c99339c0d8cbef974121454b0977acd7e6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bac2772349751df27dc676baadc0f13d5d9a53b5c0edab58be38c7775452bc2
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:f66fb4c25287efcd562f1cd952fe2acec5050f537751e06ba78f7930e53db878
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21e0dbc07229d3b7a7c386447e6efb1d0e77588599235bf588bab9234dbd6017
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": 0.24134224653244019,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.016149218781541443,
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": 13.555,
732
  "eval_steps_per_second": 3.39,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2087429314851761,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.024223828172312164,
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": 13.555,
732
  "eval_steps_per_second": 3.39,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.016310710969356858,
737
+ "grad_norm": 4.9987311363220215,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.6489,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.016472203157172273,
744
+ "grad_norm": 4.759182929992676,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.6947,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.016633695344987685,
751
+ "grad_norm": 3.8671958446502686,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.6864,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0167951875328031,
758
+ "grad_norm": 4.098058700561523,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7082,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.016956679720618515,
765
+ "grad_norm": 6.332775592803955,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9335,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01711817190843393,
772
+ "grad_norm": 5.647943019866943,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0795,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.017279664096249345,
779
+ "grad_norm": 6.842463970184326,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.8744,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.017441156284064757,
786
+ "grad_norm": 3.7888684272766113,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9048,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.017602648471880172,
793
+ "grad_norm": 4.186934471130371,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9536,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.017764140659695588,
800
+ "grad_norm": 3.675734758377075,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.7804,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.017925632847511003,
807
+ "grad_norm": 10.108420372009277,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2615,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.018087125035326414,
814
+ "grad_norm": 4.677420139312744,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7271,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01824861722314183,
821
+ "grad_norm": 6.296616077423096,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.4184,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.018410109410957245,
828
+ "grad_norm": 3.8865997791290283,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.6349,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01857160159877266,
835
+ "grad_norm": 4.712935447692871,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8963,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.018733093786588075,
842
+ "grad_norm": 4.991330146789551,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8648,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.018894585974403487,
849
+ "grad_norm": 4.175543308258057,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.7846,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.019056078162218902,
856
+ "grad_norm": 3.322171926498413,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7698,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019217570350034317,
863
+ "grad_norm": 3.053602457046509,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.6644,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.019379062537849732,
870
+ "grad_norm": 4.954108715057373,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1093,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.019540554725665148,
877
+ "grad_norm": 3.911067485809326,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.6895,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01970204691348056,
884
+ "grad_norm": 5.648387432098389,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2158,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.019863539101295975,
891
+ "grad_norm": 4.296334266662598,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7483,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02002503128911139,
898
+ "grad_norm": 4.768459320068359,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.9063,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020186523476926805,
905
+ "grad_norm": 4.852877616882324,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.6464,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020348015664742217,
912
+ "grad_norm": 3.614675521850586,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.714,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.020509507852557632,
919
+ "grad_norm": 3.900026798248291,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7799,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.020671000040373047,
926
+ "grad_norm": 4.189906120300293,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7379,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.020832492228188462,
933
+ "grad_norm": 3.848201274871826,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6732,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.020993984416003877,
940
+ "grad_norm": 5.243552207946777,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.8563,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02115547660381929,
947
+ "grad_norm": 5.969999313354492,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.2854,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.021316968791634704,
954
+ "grad_norm": 5.380910873413086,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.0254,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02147846097945012,
961
+ "grad_norm": 4.808969974517822,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.0162,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.021639953167265535,
968
+ "grad_norm": 4.541471481323242,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.1123,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.021801445355080946,
975
+ "grad_norm": 3.330897331237793,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.6584,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02196293754289636,
982
+ "grad_norm": 3.167905807495117,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.618,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.022124429730711777,
989
+ "grad_norm": 6.538463115692139,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.2219,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.022285921918527192,
996
+ "grad_norm": 3.817915678024292,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.7884,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022447414106342607,
1003
+ "grad_norm": 3.567233085632324,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.6219,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02260890629415802,
1010
+ "grad_norm": 7.849123001098633,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.7381,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.022770398481973434,
1017
+ "grad_norm": 4.571730136871338,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7234,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02293189066978885,
1024
+ "grad_norm": 4.714327335357666,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.56,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.023093382857604264,
1031
+ "grad_norm": 3.729198455810547,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7249,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.023254875045419676,
1038
+ "grad_norm": 3.5794527530670166,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.6373,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.02341636723323509,
1045
+ "grad_norm": 7.21630859375,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9469,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.023577859421050507,
1052
+ "grad_norm": 5.132265090942383,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8685,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.023739351608865922,
1059
+ "grad_norm": 6.083048343658447,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.8698,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.023900843796681337,
1066
+ "grad_norm": 4.920403003692627,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7564,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02406233598449675,
1073
+ "grad_norm": 10.307737350463867,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1976,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.024223828172312164,
1080
+ "grad_norm": 9.064608573913574,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.8906,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.024223828172312164,
1087
+ "eval_loss": 0.2087429314851761,
1088
+ "eval_runtime": 769.5887,
1089
+ "eval_samples_per_second": 13.551,
1090
+ "eval_steps_per_second": 3.389,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146499429400576e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null