prxy5606 commited on
Commit
7a32637
·
verified ·
1 Parent(s): ef22ffb

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:d74e790a17fa8ab81db18409815e367f89964ccaa3ea830093d1d5fa4538379f
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdca459544d8a76993f4be48c9193e1bcef7149077c6dc69f40dcb934c25a354
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7020db2288dc30d5c2f8210a561b8c7cc067ec478c214097afb099cddad42f4c
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7444c2d56d3c7f5b8fc8776c4e990d3c71bdffa9a972b7d8c08309ed6e0b72c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80eca96ca022fed76831f59c0941b67503bf26655fc8a190514e5d44bfcef2c2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940cf77bd02daddb88b010d9817e6f797ea17df5693286fe569e62708c7d9aa8
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": 0.9282410144805908,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.23446658851113716,
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": 13.356,
732
  "eval_steps_per_second": 3.348,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.438154617698386e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8359604477882385,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3516998827667057,
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": 13.356,
732
  "eval_steps_per_second": 3.348,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.23681125439624853,
737
+ "grad_norm": 13.492389678955078,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.208,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2391559202813599,
744
+ "grad_norm": 11.557668685913086,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.7059,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.24150058616647127,
751
+ "grad_norm": 7.9621806144714355,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.8156,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.24384525205158264,
758
+ "grad_norm": 6.837264537811279,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.1534,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.246189917936694,
765
+ "grad_norm": 6.286181449890137,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.4996,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.2485345838218054,
772
+ "grad_norm": 7.520151615142822,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.0659,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2508792497069168,
779
+ "grad_norm": 7.174684524536133,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.6981,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2532239155920281,
786
+ "grad_norm": 5.834714889526367,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.3225,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.2555685814771395,
793
+ "grad_norm": 6.822752475738525,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.6656,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.25791324736225085,
800
+ "grad_norm": 7.0578227043151855,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.5365,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.26025791324736225,
807
+ "grad_norm": 6.7616424560546875,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.4461,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.26260257913247365,
814
+ "grad_norm": 6.884385585784912,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.5808,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.264947245017585,
821
+ "grad_norm": 7.327887058258057,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.027,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.2672919109026964,
828
+ "grad_norm": 7.241699695587158,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.6953,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2696365767878077,
835
+ "grad_norm": 6.595090866088867,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.1933,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2719812426729191,
842
+ "grad_norm": 6.4801483154296875,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.3897,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.27432590855803046,
849
+ "grad_norm": 6.858499050140381,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.2126,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.27667057444314186,
856
+ "grad_norm": 6.374567985534668,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.1547,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2790152403282532,
863
+ "grad_norm": 6.215252876281738,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.3142,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2813599062133646,
870
+ "grad_norm": 6.304596424102783,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.1328,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.283704572098476,
877
+ "grad_norm": 6.3406524658203125,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.1292,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.28604923798358733,
884
+ "grad_norm": 7.53887414932251,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.6153,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.28839390386869873,
891
+ "grad_norm": 6.54124641418457,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.32,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.29073856975381007,
898
+ "grad_norm": 6.543540000915527,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.9915,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.29308323563892147,
905
+ "grad_norm": 7.439838886260986,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.8839,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2954279015240328,
912
+ "grad_norm": 6.743582248687744,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.8826,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2977725674091442,
919
+ "grad_norm": 6.0309014320373535,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.6459,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.30011723329425555,
926
+ "grad_norm": 7.520136833190918,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.8574,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.30246189917936694,
933
+ "grad_norm": 6.969455242156982,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.3561,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.3048065650644783,
940
+ "grad_norm": 6.428686618804932,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.8129,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.3071512309495897,
947
+ "grad_norm": 6.685698986053467,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.1487,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.3094958968347011,
954
+ "grad_norm": 6.508021354675293,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.1696,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.3118405627198124,
961
+ "grad_norm": 6.594387531280518,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.6793,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.3141852286049238,
968
+ "grad_norm": 5.8391337394714355,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.4195,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.31652989449003516,
975
+ "grad_norm": 7.751064300537109,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.9144,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.31887456037514655,
982
+ "grad_norm": 6.841287612915039,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.771,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.3212192262602579,
989
+ "grad_norm": 6.453044414520264,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.8674,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.3235638921453693,
996
+ "grad_norm": 7.089900970458984,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.7596,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.32590855803048063,
1003
+ "grad_norm": 7.597554683685303,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.0539,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.32825322391559203,
1010
+ "grad_norm": 7.377899646759033,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.7922,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.3305978898007034,
1017
+ "grad_norm": 7.7280192375183105,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.266,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.33294255568581477,
1024
+ "grad_norm": 7.4540324211120605,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.7233,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.33528722157092616,
1031
+ "grad_norm": 7.697388648986816,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.783,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.3376318874560375,
1038
+ "grad_norm": 7.493178844451904,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.6292,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.3399765533411489,
1045
+ "grad_norm": 6.404391765594482,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.3068,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.34232121922626024,
1052
+ "grad_norm": 8.373858451843262,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.8398,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.34466588511137164,
1059
+ "grad_norm": 6.972586631774902,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.2926,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.347010550996483,
1066
+ "grad_norm": 7.07899808883667,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.3815,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3493552168815944,
1073
+ "grad_norm": 7.6493144035339355,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.4759,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3516998827667057,
1080
+ "grad_norm": 7.906857490539551,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.5526,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3516998827667057,
1087
+ "eval_loss": 0.8359604477882385,
1088
+ "eval_runtime": 53.7652,
1089
+ "eval_samples_per_second": 13.354,
1090
+ "eval_steps_per_second": 3.348,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.157231926547579e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null