aleegis09 commited on
Commit
1a5bc1f
·
verified ·
1 Parent(s): 8bc0704

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 sha256:1d8aa6438f5f2fdb970f6879b0bd748a26558054579397495f19c998d5838445
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0918bf551b48fe95e4e8d929589b0471642f808871300fc9dcbdb1db0b453c5
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f49b9b3c38ca46e33e77dbd0f7031afa38f9521d933b3cfab8a766fdda6d3f9a
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e111c9964dbff41e79d3d7f3639f77138eea0a484c65af8caa895a410a4224
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:f6b7e05755e9ef667ed9928c12ef91d072c131d60dfc3a926c203ffaf359fc37
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50728167a311d6f74a3ddfca5ceecef52b621a3aeb34b4e3d4b5ec49be7874cb
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": 1.291818380355835,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.60790273556231,
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": 8.799,
732
  "eval_steps_per_second": 2.223,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.4249355778339635e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2594267129898071,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9118541033434651,
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": 8.799,
732
  "eval_steps_per_second": 2.223,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.6139817629179332,
737
+ "grad_norm": 1.443122148513794,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.4089,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6200607902735562,
744
+ "grad_norm": 1.6079407930374146,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.4846,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6261398176291794,
751
+ "grad_norm": 1.2146152257919312,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.2541,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6322188449848024,
758
+ "grad_norm": 1.0780636072158813,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.155,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6382978723404256,
765
+ "grad_norm": 1.0256733894348145,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2241,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6443768996960486,
772
+ "grad_norm": 1.025854468345642,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.2551,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6504559270516718,
779
+ "grad_norm": 0.9595382809638977,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.1257,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.6565349544072948,
786
+ "grad_norm": 1.0922917127609253,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.1945,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.662613981762918,
793
+ "grad_norm": 1.0498374700546265,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.1911,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.668693009118541,
800
+ "grad_norm": 1.0221478939056396,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.1414,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.6747720364741642,
807
+ "grad_norm": 1.0440903902053833,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2226,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.6808510638297872,
814
+ "grad_norm": 1.2824653387069702,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1579,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.6869300911854104,
821
+ "grad_norm": 1.0503424406051636,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.2229,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.6930091185410334,
828
+ "grad_norm": 0.9603865146636963,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1739,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.6990881458966566,
835
+ "grad_norm": 1.053389549255371,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0727,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7051671732522796,
842
+ "grad_norm": 0.9794132709503174,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.1693,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7112462006079028,
849
+ "grad_norm": 1.194525957107544,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1384,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7173252279635258,
856
+ "grad_norm": 1.0075552463531494,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.1697,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.723404255319149,
863
+ "grad_norm": 1.3113508224487305,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0993,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.729483282674772,
870
+ "grad_norm": 1.0296517610549927,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.2017,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.7355623100303952,
877
+ "grad_norm": 1.151802897453308,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.2173,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.7416413373860182,
884
+ "grad_norm": 1.101464033126831,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2155,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.7477203647416414,
891
+ "grad_norm": 1.2130014896392822,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2716,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.7537993920972644,
898
+ "grad_norm": 0.8958890438079834,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.3998,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.7598784194528876,
905
+ "grad_norm": 1.0223948955535889,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3954,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.7659574468085106,
912
+ "grad_norm": 1.014959692955017,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4315,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.7720364741641338,
919
+ "grad_norm": 1.0947637557983398,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.4246,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.7781155015197568,
926
+ "grad_norm": 0.9514850974082947,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2555,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.78419452887538,
933
+ "grad_norm": 1.2168844938278198,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4294,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.790273556231003,
940
+ "grad_norm": 1.093896746635437,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2719,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.7963525835866262,
947
+ "grad_norm": 2.7117221355438232,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.5384,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8024316109422492,
954
+ "grad_norm": 1.3037480115890503,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.3691,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8085106382978723,
961
+ "grad_norm": 1.3540011644363403,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.4782,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8145896656534954,
968
+ "grad_norm": 1.2777421474456787,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3177,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.8206686930091185,
975
+ "grad_norm": 1.3406814336776733,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1462,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8267477203647416,
982
+ "grad_norm": 1.2267261743545532,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.465,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.8328267477203647,
989
+ "grad_norm": 1.4003666639328003,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.2814,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.8389057750759878,
996
+ "grad_norm": 1.2393686771392822,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.2385,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.8449848024316109,
1003
+ "grad_norm": 1.312151312828064,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2368,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.851063829787234,
1010
+ "grad_norm": 1.6161844730377197,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.2925,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.8571428571428571,
1017
+ "grad_norm": 1.444501280784607,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.3931,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.8632218844984803,
1024
+ "grad_norm": 1.3983210325241089,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.3165,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.8693009118541033,
1031
+ "grad_norm": 1.3116635084152222,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.3285,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.8753799392097265,
1038
+ "grad_norm": 1.119754433631897,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2094,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.8814589665653495,
1045
+ "grad_norm": 1.1628637313842773,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.0616,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.8875379939209727,
1052
+ "grad_norm": 1.0161055326461792,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.1605,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.8936170212765957,
1059
+ "grad_norm": 1.0418037176132202,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1572,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.8996960486322189,
1066
+ "grad_norm": 0.9632786512374878,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.0861,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9057750759878419,
1073
+ "grad_norm": 1.1108787059783936,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.2152,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9118541033434651,
1080
+ "grad_norm": 0.9935660362243652,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.2279,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9118541033434651,
1087
+ "eval_loss": 1.2594267129898071,
1088
+ "eval_runtime": 31.213,
1089
+ "eval_samples_per_second": 8.875,
1090
+ "eval_steps_per_second": 2.243,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.5261504903184384e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null