blood34 commited on
Commit
2df1d87
·
verified ·
1 Parent(s): ab9ada4

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:ef05a3cacb9e140de1d62aa62c89a289736ce8a73a5e034c40f9f97e9e7b5836
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649efce0b0f9aed4b27dfff4e21197e6a667bf9cfa9d07869e4854b340d0d7fd
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c63b4340f3c0d6bc13fdd18111c2170dbcef0e9e7ce0c5bbd36b6cb28ab43c8
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373b3a4b4ebe2ad2276132913411d5f9bf5d008ffc74c8974d26c6d7f2dcc831
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e7bd38afa90c7b2ff704302889dc7bebc024d0c576b2234ebd6066017d891b5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f04d91fca0ec88fc6895597b4854c05f2aeec913e8db950c59864b16e4e0ad
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": 2.1340065002441406,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02730561813093044,
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": 8.839,
732
  "eval_steps_per_second": 2.21,
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": 2.0223450660705566,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.040958427196395655,
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": 8.839,
732
  "eval_steps_per_second": 2.21,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.027578674312239742,
737
+ "grad_norm": 18.07147789001465,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 6.5228,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.027851730493549047,
744
+ "grad_norm": 20.77764892578125,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 7.8123,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.028124786674858352,
751
+ "grad_norm": 20.727760314941406,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 8.3957,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.028397842856167657,
758
+ "grad_norm": 16.201143264770508,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 7.7034,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.028670899037476962,
765
+ "grad_norm": 14.143803596496582,
766
+ "learning_rate": 5e-05,
767
+ "loss": 7.5807,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.028943955218786264,
772
+ "grad_norm": 16.559654235839844,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 7.6732,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.02921701140009557,
779
+ "grad_norm": 15.340529441833496,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 7.8505,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.029490067581404874,
786
+ "grad_norm": 17.633358001708984,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 8.5092,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.02976312376271418,
793
+ "grad_norm": 16.75809097290039,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.4787,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.030036179944023484,
800
+ "grad_norm": 16.6685848236084,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 7.757,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.030309236125332786,
807
+ "grad_norm": 16.05257225036621,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 8.5722,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03058229230664209,
814
+ "grad_norm": 15.737967491149902,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 8.13,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.030855348487951396,
821
+ "grad_norm": 18.064294815063477,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 8.5067,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0311284046692607,
828
+ "grad_norm": 23.488189697265625,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 8.6982,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03140146085057,
835
+ "grad_norm": 17.5887508392334,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 8.8168,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03167451703187931,
842
+ "grad_norm": 14.242671966552734,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 6.7286,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03194757321318861,
849
+ "grad_norm": 14.122462272644043,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 8.5156,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03222062939449792,
856
+ "grad_norm": 15.14977741241455,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 7.9296,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03249368557580722,
863
+ "grad_norm": 17.33123779296875,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 8.8162,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.032766741757116524,
870
+ "grad_norm": 14.457858085632324,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 8.0185,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03303979793842583,
877
+ "grad_norm": 15.224176406860352,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 8.4122,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.033312854119735134,
884
+ "grad_norm": 17.36722755432129,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 7.9025,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03358591030104444,
891
+ "grad_norm": 15.94758415222168,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 8.2387,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.033858966482353745,
898
+ "grad_norm": 18.829530715942383,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 8.4182,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.034132022663663046,
905
+ "grad_norm": 18.859539031982422,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 8.3133,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.034405078844972355,
912
+ "grad_norm": 15.820075035095215,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 7.9701,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.034678135026281656,
919
+ "grad_norm": 18.90699577331543,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.6803,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.034951191207590965,
926
+ "grad_norm": 16.5141658782959,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 7.4541,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.035224247388900266,
933
+ "grad_norm": 18.62548828125,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 7.9896,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03549730357020957,
940
+ "grad_norm": 19.355186462402344,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 8.5288,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.035770359751518876,
947
+ "grad_norm": 21.866207122802734,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 8.3981,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03604341593282818,
954
+ "grad_norm": 17.40390396118164,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 8.2206,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03631647211413749,
961
+ "grad_norm": 16.635597229003906,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 6.883,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03658952829544679,
968
+ "grad_norm": 16.17715072631836,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 7.0958,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03686258447675609,
975
+ "grad_norm": 19.20148468017578,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 8.0087,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0371356406580654,
982
+ "grad_norm": 16.3226318359375,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 6.7139,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0374086968393747,
989
+ "grad_norm": 22.199859619140625,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 8.521,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03768175302068401,
996
+ "grad_norm": 25.420183181762695,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 7.8769,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03795480920199331,
1003
+ "grad_norm": 17.60880470275879,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 7.6496,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03822786538330261,
1010
+ "grad_norm": 19.348995208740234,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 8.1288,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03850092156461192,
1017
+ "grad_norm": 19.610876083374023,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 8.0972,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03877397774592122,
1024
+ "grad_norm": 33.40858840942383,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.7113,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03904703392723053,
1031
+ "grad_norm": 22.39961051940918,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 8.1275,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03932009010853983,
1038
+ "grad_norm": 24.164146423339844,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 8.4301,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.039593146289849133,
1045
+ "grad_norm": 28.657455444335938,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 7.9669,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03986620247115844,
1052
+ "grad_norm": 30.79471206665039,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 8.4107,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.040139258652467744,
1059
+ "grad_norm": 35.513553619384766,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 8.0686,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04041231483377705,
1066
+ "grad_norm": 20.78765106201172,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 7.3615,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.040685371015086354,
1073
+ "grad_norm": 27.29558563232422,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 7.879,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.040958427196395655,
1080
+ "grad_norm": 46.89344024658203,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.8891,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.040958427196395655,
1087
+ "eval_loss": 2.0223450660705566,
1088
+ "eval_runtime": 698.0638,
1089
+ "eval_samples_per_second": 8.836,
1090
+ "eval_steps_per_second": 2.209,
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