aleegis12 commited on
Commit
26d441f
·
verified ·
1 Parent(s): 79ac5f7

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 sha256:13e1fe7753925243e54249c512465c6a1d807db998d1c556ae40ce415032d078
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fddeede094d5a76b21ff3403abb00610870573acdcb6607c9c34dbaffb1824c9
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec270ac845d8f884a790caba31790768a045360535cc8a7bb5513086927d04a
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874bb4983ada2b70c0d4429c411c0caab765530fd6f53e87cbc952885998f117
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87b41b0d79577d3f8aa699ebcf8f462a22c0681d69865b3de5e4c593914b7e65
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2e37b7341b7a67ca3efd108b12e515bfbeffd35af09ae35d091a2591734428
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": 2.5514986515045166,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9501187648456056,
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": 80.781,
732
  "eval_steps_per_second": 20.422,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7693382549766144.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5159730911254883,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.4251781472684084,
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": 80.781,
732
  "eval_steps_per_second": 20.422,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.9596199524940617,
737
+ "grad_norm": 119.67656707763672,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.156,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.9691211401425178,
744
+ "grad_norm": 96.49195098876953,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.5515,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.9786223277909739,
751
+ "grad_norm": 113.34687042236328,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.5258,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9881235154394299,
758
+ "grad_norm": 153.2520751953125,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.5513,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.997624703087886,
765
+ "grad_norm": 95.41917419433594,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.7464,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.007125890736342,
772
+ "grad_norm": 132.74461364746094,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.098,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.0166270783847982,
779
+ "grad_norm": 57.19962692260742,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 10.9078,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.0261282660332542,
786
+ "grad_norm": 83.69065856933594,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 10.2019,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.03562945368171,
793
+ "grad_norm": 71.2281265258789,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 10.0873,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.0451306413301662,
800
+ "grad_norm": 81.04923248291016,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 10.5363,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.0546318289786223,
807
+ "grad_norm": 81.03862762451172,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 10.4283,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.0641330166270784,
814
+ "grad_norm": 75.69035339355469,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 9.5565,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.0736342042755345,
821
+ "grad_norm": 85.27928924560547,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 9.4412,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.0831353919239906,
828
+ "grad_norm": 79.6570816040039,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 9.5959,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.0926365795724466,
835
+ "grad_norm": 75.83023834228516,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 9.5345,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.1021377672209025,
842
+ "grad_norm": 97.34774017333984,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 9.6553,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.1116389548693586,
849
+ "grad_norm": 80.85506439208984,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.6712,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1211401425178147,
856
+ "grad_norm": 72.7548599243164,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 9.0978,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.1306413301662708,
863
+ "grad_norm": 154.8693389892578,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 9.2004,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.1401425178147269,
870
+ "grad_norm": 107.32441711425781,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.7621,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.149643705463183,
877
+ "grad_norm": 132.4986572265625,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 10.3251,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.159144893111639,
884
+ "grad_norm": 118.84049987792969,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 10.1513,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.168646080760095,
891
+ "grad_norm": 143.0657958984375,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 10.1979,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.178147268408551,
898
+ "grad_norm": 97.22129821777344,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 10.2347,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.187648456057007,
905
+ "grad_norm": 94.11260986328125,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 10.5843,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.1971496437054632,
912
+ "grad_norm": 135.90623474121094,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 10.5021,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.2066508313539193,
919
+ "grad_norm": 101.69560241699219,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 10.8865,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.2161520190023754,
926
+ "grad_norm": 110.10270690917969,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 10.4683,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.2256532066508314,
933
+ "grad_norm": 87.06689453125,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.0287,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.2351543942992875,
940
+ "grad_norm": 96.41451263427734,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.7243,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.2446555819477434,
947
+ "grad_norm": 257.0499267578125,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.351,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.2541567695961995,
954
+ "grad_norm": 65.98271179199219,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 10.5907,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.2636579572446556,
961
+ "grad_norm": 53.33887481689453,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 10.3695,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.2731591448931117,
968
+ "grad_norm": 55.912235260009766,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 10.1185,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.2826603325415677,
975
+ "grad_norm": 77.50757598876953,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 10.3438,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.2921615201900236,
982
+ "grad_norm": 56.65907287597656,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.9854,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.3016627078384797,
989
+ "grad_norm": 55.6379508972168,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 9.9772,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.3111638954869358,
996
+ "grad_norm": 97.31382751464844,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.5288,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.3206650831353919,
1003
+ "grad_norm": 66.84870147705078,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 9.0591,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.330166270783848,
1010
+ "grad_norm": 64.66853332519531,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.5168,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.339667458432304,
1017
+ "grad_norm": 66.04855346679688,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 9.3083,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.3491686460807601,
1024
+ "grad_norm": 77.19223022460938,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.5059,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.3586698337292162,
1031
+ "grad_norm": 92.79340362548828,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.479,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.3681710213776723,
1038
+ "grad_norm": 64.79487609863281,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 9.0669,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.3776722090261282,
1045
+ "grad_norm": 73.25862884521484,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.504,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.3871733966745843,
1052
+ "grad_norm": 74.61793518066406,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 9.475,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.3966745843230404,
1059
+ "grad_norm": 134.77496337890625,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 10.5703,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.4061757719714965,
1066
+ "grad_norm": 116.8616943359375,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.4287,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.4156769596199525,
1073
+ "grad_norm": 83.34971618652344,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.9763,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.4251781472684084,
1080
+ "grad_norm": 99.0321044921875,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 10.2022,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.4251781472684084,
1087
+ "eval_loss": 2.5159730911254883,
1088
+ "eval_runtime": 2.2,
1089
+ "eval_samples_per_second": 80.909,
1090
+ "eval_steps_per_second": 20.454,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.1540073824649216e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null