cimol commited on
Commit
70dfbdd
·
verified ·
1 Parent(s): ca9e51f

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 sha256:12b46729d5b4e925c6bdd7c136b0ca024012703ee4f228985b74c05cc5c390b9
3
  size 114073120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3513ffe155ec1d6590114258e93cc23ecc4843001412b25e3dfeea9e23952031
3
  size 114073120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15bcfbb720807adae55580f430a4e13f19609ae96834a14ec67d7919025e77ff
3
  size 58250916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f360c04b2224240fd83acc1b0b45aa6334932a1e9b3aee82a8743167e8e146
3
  size 58250916
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cab6f0072f5d43484fb9489051799f2181884aa2c73a6d2f9596844086049306
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7b9a9a8d43c66f545ccfac7be7fabfbcdf96dd0714e72cbfccf0ac64785bd8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26348e70deb5f7d6cee52f5eb084c0e6829440001a3c6d0128b93cd074af8c2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.344313144683838,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.47337278106508873,
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": 78.968,
732
  "eval_steps_per_second": 19.742,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7324035528523776.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.168163537979126,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.7100591715976331,
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": 78.968,
732
  "eval_steps_per_second": 19.742,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.47810650887573963,
737
+ "grad_norm": 6.659903049468994,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 9.4537,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.48284023668639053,
744
+ "grad_norm": 9.363694190979004,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 6.9591,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.48757396449704143,
751
+ "grad_norm": 7.893527507781982,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 8.0727,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.49230769230769234,
758
+ "grad_norm": 4.582357406616211,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 9.4672,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4970414201183432,
765
+ "grad_norm": 4.138848781585693,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 9.7494,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5017751479289941,
772
+ "grad_norm": 3.278074264526367,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 9.7498,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.506508875739645,
779
+ "grad_norm": 2.7417900562286377,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 9.8849,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5112426035502958,
786
+ "grad_norm": 2.2889347076416016,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 9.1304,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5159763313609468,
793
+ "grad_norm": 2.015984296798706,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 9.534,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5207100591715976,
800
+ "grad_norm": 1.9426658153533936,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 9.2463,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5254437869822485,
807
+ "grad_norm": 1.877349615097046,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 9.1375,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5301775147928994,
814
+ "grad_norm": 1.7960454225540161,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 9.5241,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5349112426035503,
821
+ "grad_norm": 1.7549121379852295,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 9.2105,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5396449704142012,
828
+ "grad_norm": 1.845401406288147,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 9.1138,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5443786982248521,
835
+ "grad_norm": 1.8168048858642578,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 9.168,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5491124260355029,
842
+ "grad_norm": 1.7769105434417725,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 8.604,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5538461538461539,
849
+ "grad_norm": 1.9021414518356323,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 9.1297,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5585798816568047,
856
+ "grad_norm": 2.2273471355438232,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 8.2981,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5633136094674556,
863
+ "grad_norm": 2.5367212295532227,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 8.1807,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5680473372781065,
870
+ "grad_norm": 2.3623132705688477,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 8.1484,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5727810650887574,
877
+ "grad_norm": 2.8582258224487305,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 8.3255,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5775147928994083,
884
+ "grad_norm": 2.4786276817321777,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 8.6349,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5822485207100592,
891
+ "grad_norm": 2.775315046310425,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 8.3631,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.58698224852071,
898
+ "grad_norm": 4.248892784118652,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 8.025,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.591715976331361,
905
+ "grad_norm": 4.944392681121826,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 6.5133,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5964497041420118,
912
+ "grad_norm": 4.233840465545654,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 6.8379,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6011834319526628,
919
+ "grad_norm": 4.832763671875,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 6.2868,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6059171597633136,
926
+ "grad_norm": 4.202553749084473,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 9.0585,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6106508875739645,
933
+ "grad_norm": 4.346737861633301,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 7.6753,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6153846153846154,
940
+ "grad_norm": 5.097937107086182,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 7.9764,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6201183431952663,
947
+ "grad_norm": 4.751710891723633,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 8.1434,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6248520710059171,
954
+ "grad_norm": 4.927725315093994,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 7.8983,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6295857988165681,
961
+ "grad_norm": 4.509367942810059,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 8.6726,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6343195266272189,
968
+ "grad_norm": 5.069119453430176,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 9.9922,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6390532544378699,
975
+ "grad_norm": 5.712182521820068,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 8.8338,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6437869822485207,
982
+ "grad_norm": 6.012514114379883,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 9.8681,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6485207100591716,
989
+ "grad_norm": 10.424877166748047,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 9.6439,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6532544378698225,
996
+ "grad_norm": 16.737018585205078,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 11.2645,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6579881656804734,
1003
+ "grad_norm": 21.493574142456055,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 12.6379,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6627218934911243,
1010
+ "grad_norm": 22.50312042236328,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 11.9446,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6674556213017752,
1017
+ "grad_norm": 17.180870056152344,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 11.4304,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.672189349112426,
1024
+ "grad_norm": 20.37939453125,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 9.6147,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.676923076923077,
1031
+ "grad_norm": 15.90661907196045,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 10.0453,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6816568047337278,
1038
+ "grad_norm": 15.373900413513184,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 9.0296,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6863905325443787,
1045
+ "grad_norm": 14.838103294372559,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 9.7712,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6911242603550296,
1052
+ "grad_norm": 18.918119430541992,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 11.0932,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6958579881656805,
1059
+ "grad_norm": 16.040857315063477,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 9.4681,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7005917159763314,
1066
+ "grad_norm": 15.517600059509277,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 9.5907,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.7053254437869823,
1073
+ "grad_norm": 16.77145767211914,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 10.3682,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.7100591715976331,
1080
+ "grad_norm": 26.573543548583984,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 12.3598,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.7100591715976331,
1087
+ "eval_loss": 2.168163537979126,
1088
+ "eval_runtime": 4.5428,
1089
+ "eval_samples_per_second": 78.365,
1090
+ "eval_steps_per_second": 19.591,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0994209234354176e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null