lesso commited on
Commit
6064c8b
·
verified ·
1 Parent(s): add0620

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 sha256:8a390ab90c983b502232f6dd978c1d10bd073cbd71369a7a0c14a61fba37ebca
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a671110c1409a67987e3cc6f6badddbd1a79e37f43258e913645e31fd2f9f98b
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4b3bc4c954ea220c7ba8aecc83e5b5ceea33371e9415d87cb5ab5603a4f2566
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dc121e5785116a9e4eab21d5734b169aab51b84bc921fca000c9108f5e1685
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b25b5f3b462fb3e29221ae0588e7591e3e9adfa54f981e07b5869f484f6b0ecc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd42d77a0d1deb56b88fea8a242532a0d5da06db4f00129a68e2f2d9e34bc44a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab3d2b0401484126213dd055d9044edf00d7b06db4fe9dbad6027ee8b5d34b1
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123ecf29cfd4fe3b008c987ce1ef9f63c2ad00365e06a3691aa36827aaded381
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7575440406799316,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.004644681839294009,
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": 55.766,
732
  "eval_steps_per_second": 13.944,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6106135727702016.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7381066679954529,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.006967022758941012,
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": 55.766,
732
  "eval_steps_per_second": 13.944,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0046911286576869484,
737
+ "grad_norm": 1.547819972038269,
738
+ "learning_rate": 5.3043157894736836e-05,
739
+ "loss": 0.7768,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.004737575476079888,
744
+ "grad_norm": 2.0550365447998047,
745
+ "learning_rate": 5.2507368421052635e-05,
746
+ "loss": 0.8542,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004784022294472829,
751
+ "grad_norm": 1.7644928693771362,
752
+ "learning_rate": 5.197157894736842e-05,
753
+ "loss": 0.8406,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004830469112865768,
758
+ "grad_norm": 2.784821033477783,
759
+ "learning_rate": 5.143578947368421e-05,
760
+ "loss": 1.0809,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.004876915931258709,
765
+ "grad_norm": 2.643968105316162,
766
+ "learning_rate": 5.09e-05,
767
+ "loss": 1.1358,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004923362749651649,
772
+ "grad_norm": 2.6479332447052,
773
+ "learning_rate": 5.036421052631578e-05,
774
+ "loss": 0.9534,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004969809568044589,
779
+ "grad_norm": 1.5139284133911133,
780
+ "learning_rate": 4.982842105263158e-05,
781
+ "loss": 0.6037,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.005016256386437529,
786
+ "grad_norm": 2.2001686096191406,
787
+ "learning_rate": 4.9292631578947366e-05,
788
+ "loss": 1.0875,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.005062703204830469,
793
+ "grad_norm": 1.906663417816162,
794
+ "learning_rate": 4.875684210526315e-05,
795
+ "loss": 0.8251,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.005109150023223409,
800
+ "grad_norm": 1.6133707761764526,
801
+ "learning_rate": 4.822105263157894e-05,
802
+ "loss": 0.7804,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.00515559684161635,
807
+ "grad_norm": 1.6872289180755615,
808
+ "learning_rate": 4.7685263157894735e-05,
809
+ "loss": 0.5731,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.005202043660009289,
814
+ "grad_norm": 1.2829549312591553,
815
+ "learning_rate": 4.714947368421052e-05,
816
+ "loss": 0.4865,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.005248490478402229,
821
+ "grad_norm": 1.8299009799957275,
822
+ "learning_rate": 4.661368421052631e-05,
823
+ "loss": 0.7806,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.00529493729679517,
828
+ "grad_norm": 1.3792545795440674,
829
+ "learning_rate": 4.6077894736842104e-05,
830
+ "loss": 0.5824,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.005341384115188109,
835
+ "grad_norm": 1.554002046585083,
836
+ "learning_rate": 4.554210526315789e-05,
837
+ "loss": 0.7399,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.00538783093358105,
842
+ "grad_norm": 1.8911974430084229,
843
+ "learning_rate": 4.500631578947368e-05,
844
+ "loss": 0.8756,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0054342777519739895,
849
+ "grad_norm": 2.071706771850586,
850
+ "learning_rate": 4.447052631578947e-05,
851
+ "loss": 0.8007,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.00548072457036693,
856
+ "grad_norm": 2.202437162399292,
857
+ "learning_rate": 4.393473684210526e-05,
858
+ "loss": 0.8207,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.00552717138875987,
863
+ "grad_norm": 1.33773672580719,
864
+ "learning_rate": 4.339894736842105e-05,
865
+ "loss": 0.5947,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.00557361820715281,
870
+ "grad_norm": 1.8306225538253784,
871
+ "learning_rate": 4.2863157894736835e-05,
872
+ "loss": 0.7513,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00562006502554575,
877
+ "grad_norm": 1.6813061237335205,
878
+ "learning_rate": 4.2327368421052634e-05,
879
+ "loss": 0.6929,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.005666511843938691,
884
+ "grad_norm": 1.5658451318740845,
885
+ "learning_rate": 4.179157894736842e-05,
886
+ "loss": 0.5594,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.00571295866233163,
891
+ "grad_norm": 1.4536268711090088,
892
+ "learning_rate": 4.1255789473684204e-05,
893
+ "loss": 0.6208,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00575940548072457,
898
+ "grad_norm": 1.9043149948120117,
899
+ "learning_rate": 4.072e-05,
900
+ "loss": 0.6332,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0058058522991175105,
905
+ "grad_norm": 2.0733814239501953,
906
+ "learning_rate": 4.018421052631579e-05,
907
+ "loss": 0.6764,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.00585229911751045,
912
+ "grad_norm": 1.7627897262573242,
913
+ "learning_rate": 3.9648421052631573e-05,
914
+ "loss": 0.7384,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.005898745935903391,
919
+ "grad_norm": 1.6006054878234863,
920
+ "learning_rate": 3.9112631578947365e-05,
921
+ "loss": 0.6752,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0059451927542963304,
926
+ "grad_norm": 1.4541168212890625,
927
+ "learning_rate": 3.857684210526316e-05,
928
+ "loss": 0.6692,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.005991639572689271,
933
+ "grad_norm": 1.3292078971862793,
934
+ "learning_rate": 3.804105263157894e-05,
935
+ "loss": 0.5353,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.006038086391082211,
940
+ "grad_norm": 1.6884562969207764,
941
+ "learning_rate": 3.7505263157894734e-05,
942
+ "loss": 0.7562,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.006084533209475151,
947
+ "grad_norm": 1.0477324724197388,
948
+ "learning_rate": 3.6969473684210526e-05,
949
+ "loss": 0.3243,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.006130980027868091,
954
+ "grad_norm": 1.4753937721252441,
955
+ "learning_rate": 3.643368421052631e-05,
956
+ "loss": 0.5291,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0061774268462610315,
961
+ "grad_norm": 1.7509891986846924,
962
+ "learning_rate": 3.5897894736842103e-05,
963
+ "loss": 0.6364,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.006223873664653971,
968
+ "grad_norm": 2.055713653564453,
969
+ "learning_rate": 3.5362105263157895e-05,
970
+ "loss": 0.782,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.006270320483046911,
975
+ "grad_norm": 2.0711967945098877,
976
+ "learning_rate": 3.482631578947368e-05,
977
+ "loss": 0.7677,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.006316767301439851,
982
+ "grad_norm": 1.3271763324737549,
983
+ "learning_rate": 3.429052631578947e-05,
984
+ "loss": 0.5314,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.006363214119832791,
989
+ "grad_norm": 1.7668476104736328,
990
+ "learning_rate": 3.375473684210526e-05,
991
+ "loss": 0.8441,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.006409660938225732,
996
+ "grad_norm": 1.773807168006897,
997
+ "learning_rate": 3.321894736842105e-05,
998
+ "loss": 0.7551,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.006456107756618671,
1003
+ "grad_norm": 1.6312812566757202,
1004
+ "learning_rate": 3.268315789473684e-05,
1005
+ "loss": 0.8111,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.006502554575011612,
1010
+ "grad_norm": 1.6187984943389893,
1011
+ "learning_rate": 3.2147368421052627e-05,
1012
+ "loss": 0.6781,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.006549001393404552,
1017
+ "grad_norm": 1.6448986530303955,
1018
+ "learning_rate": 3.161157894736842e-05,
1019
+ "loss": 0.5815,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.006595448211797492,
1024
+ "grad_norm": 1.9651342630386353,
1025
+ "learning_rate": 3.107578947368421e-05,
1026
+ "loss": 0.7199,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.006641895030190432,
1031
+ "grad_norm": 2.4397366046905518,
1032
+ "learning_rate": 3.0539999999999996e-05,
1033
+ "loss": 0.7959,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.006688341848583372,
1038
+ "grad_norm": 1.7463246583938599,
1039
+ "learning_rate": 3.0004210526315784e-05,
1040
+ "loss": 0.7066,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.006734788666976312,
1045
+ "grad_norm": 1.6383179426193237,
1046
+ "learning_rate": 2.946842105263158e-05,
1047
+ "loss": 0.5844,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.006781235485369252,
1052
+ "grad_norm": 2.03802752494812,
1053
+ "learning_rate": 2.8932631578947368e-05,
1054
+ "loss": 0.7851,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.006827682303762192,
1059
+ "grad_norm": 1.5965886116027832,
1060
+ "learning_rate": 2.8396842105263153e-05,
1061
+ "loss": 0.7421,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.006874129122155132,
1066
+ "grad_norm": 1.6589584350585938,
1067
+ "learning_rate": 2.786105263157895e-05,
1068
+ "loss": 0.7362,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.006920575940548073,
1073
+ "grad_norm": 1.904215693473816,
1074
+ "learning_rate": 2.7325263157894737e-05,
1075
+ "loss": 0.842,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.006967022758941012,
1080
+ "grad_norm": 1.954518437385559,
1081
+ "learning_rate": 2.6789473684210522e-05,
1082
+ "loss": 0.8687,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.006967022758941012,
1087
+ "eval_loss": 0.7381066679954529,
1088
+ "eval_runtime": 163.587,
1089
+ "eval_samples_per_second": 55.42,
1090
+ "eval_steps_per_second": 13.858,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9119207069319168.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null