bbytxt commited on
Commit
60869f2
·
verified ·
1 Parent(s): ec3f03d

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 sha256:01e5886c701b592ffbe8ffbbb2857042e7e5251ee15a6559f5ef1b071fd4d7d1
3
  size 1163996488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49cd1df38e3b867d0f6179efc8ff5b8e2259954570bcb5ede36b73f8fc00810
3
  size 1163996488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:289f8cd84b023e7b8d7b298de7203a789ddf22f04662b0d0d75c56dec758a2eb
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6dc122f7461c14714e3bb795e67c455d2396e3a3d5cc54b08219a3f5705f8a3
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2275c91757d31577450d039735611baaffa5ab54ceb0d90c9668f0d41713225c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25d7bd1393453292cb28bb1da31e93070548d594957a6c536f4670e1797a153
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.46107152104377747,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10357327809425168,
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": 12.265,
732
  "eval_steps_per_second": 6.133,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.330496579567616e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3055230975151062,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15535991714137753,
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": 12.265,
732
  "eval_steps_per_second": 6.133,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1046090108751942,
737
+ "grad_norm": 0.9650932550430298,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.6433,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10564474365613671,
744
+ "grad_norm": 1.0569595098495483,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.6046,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10668047643707923,
751
+ "grad_norm": 1.3118841648101807,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.6978,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10771620921802175,
758
+ "grad_norm": 0.9649919867515564,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.5771,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10875194199896426,
765
+ "grad_norm": 0.8630145788192749,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.4207,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10978767477990678,
772
+ "grad_norm": 0.8723099231719971,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.4919,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1108234075608493,
779
+ "grad_norm": 1.1895697116851807,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.5618,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.11185914034179181,
786
+ "grad_norm": 1.1931686401367188,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.4773,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.11289487312273433,
793
+ "grad_norm": 1.6731840372085571,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.4266,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11393060590367685,
800
+ "grad_norm": 1.227846622467041,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.5589,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11496633868461936,
807
+ "grad_norm": 1.0807693004608154,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.4194,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11600207146556188,
814
+ "grad_norm": 0.823137104511261,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.623,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1170378042465044,
821
+ "grad_norm": 0.9013914465904236,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.4202,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11807353702744691,
828
+ "grad_norm": 0.896589457988739,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.4487,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11910926980838944,
835
+ "grad_norm": 0.7383155226707458,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.3712,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.12014500258933196,
842
+ "grad_norm": 1.5368659496307373,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.3895,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.12118073537027448,
849
+ "grad_norm": 0.825655996799469,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.3584,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.12221646815121699,
856
+ "grad_norm": 0.7657477855682373,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.3234,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12325220093215951,
863
+ "grad_norm": 0.7747549414634705,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.363,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12428793371310203,
870
+ "grad_norm": 1.066019892692566,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.4481,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12532366649404453,
877
+ "grad_norm": 0.8845261931419373,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.2096,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12635939927498704,
884
+ "grad_norm": 0.969825267791748,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.3525,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12739513205592956,
891
+ "grad_norm": 0.9056379199028015,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.3636,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12843086483687208,
898
+ "grad_norm": 0.8290777206420898,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.2886,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1294665976178146,
905
+ "grad_norm": 0.8031933903694153,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.336,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1305023303987571,
912
+ "grad_norm": 1.104204773902893,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.3722,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.13153806317969963,
919
+ "grad_norm": 0.9014912247657776,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.3251,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.13257379596064214,
926
+ "grad_norm": 0.5569969415664673,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.2197,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13360952874158466,
933
+ "grad_norm": 0.5489453077316284,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.157,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13464526152252718,
940
+ "grad_norm": 0.700421929359436,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.2833,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1356809943034697,
947
+ "grad_norm": 0.8463655114173889,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.3084,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1367167270844122,
954
+ "grad_norm": 1.074282169342041,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.2022,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.13775245986535473,
961
+ "grad_norm": 0.7204672694206238,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.1456,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13878819264629724,
968
+ "grad_norm": 1.4383536577224731,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.2751,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.13982392542723976,
975
+ "grad_norm": 0.6281360387802124,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.0874,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.14085965820818228,
982
+ "grad_norm": 0.6139625906944275,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.1965,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1418953909891248,
989
+ "grad_norm": 1.241881012916565,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.2662,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.14293112377006734,
996
+ "grad_norm": 0.6423341631889343,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.1051,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14396685655100985,
1003
+ "grad_norm": 1.093138337135315,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.2853,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14500258933195237,
1010
+ "grad_norm": 1.1384899616241455,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.3369,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.14603832211289489,
1017
+ "grad_norm": 0.7722360491752625,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.2649,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1470740548938374,
1024
+ "grad_norm": 1.1144746541976929,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.2119,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14810978767477992,
1031
+ "grad_norm": 0.6660451292991638,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.1605,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14914552045572244,
1038
+ "grad_norm": 0.6069556474685669,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.1004,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.15018125323666495,
1045
+ "grad_norm": 0.9130787253379822,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.1797,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.15121698601760747,
1052
+ "grad_norm": 0.6856268644332886,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.1913,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.15225271879854999,
1059
+ "grad_norm": 1.281296730041504,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.4095,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1532884515794925,
1066
+ "grad_norm": 1.5272610187530518,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.5091,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.15432418436043502,
1073
+ "grad_norm": 1.2128320932388306,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.3015,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15535991714137753,
1080
+ "grad_norm": 0.903167724609375,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.3632,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15535991714137753,
1087
+ "eval_loss": 0.3055230975151062,
1088
+ "eval_runtime": 132.6347,
1089
+ "eval_samples_per_second": 12.259,
1090
+ "eval_steps_per_second": 6.13,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.995744869351424e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null