lesso commited on
Commit
203e759
·
verified ·
1 Parent(s): 7a153ef

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 sha256:255df5aa95dc1f24c0d5f3749369e6dd2a66ea53c364913338d2c7118d174b15
3
  size 985240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab379f924f6e6931391a70461452fe6811e9fb95c9dcc371c9d0447c1d35feb
3
  size 985240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf890291771828e1fbf015f60915b31c6143529dfbefedd50690ce800f2a900e
3
  size 520860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f8160ea8629dd885b8a9b742d0b6ae07d6830e832a5442e6b44bb013945ec1
3
  size 520860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b05b2939fc14180e93724fd602f256c68fb8f47d6aa464c5fd7d8b07ac299313
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:281c1b8e19a7534ec4ecb60ce483c526a1015f200a9ffcb2c3ad12d2c598bab1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ba1abeedc944b50dfc9c3bffbf774b90111e900acad34ff55445cc0c42e5cd9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940eaf31ac549488b8de7c1e32bcee52e66762875735ca6474507071594055dc
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 8.80693531036377,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0859106529209622,
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": 122.703,
732
  "eval_steps_per_second": 30.801,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4105646899200.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 8.79317569732666,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.12886597938144329,
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": 122.703,
732
  "eval_steps_per_second": 30.801,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08676975945017182,
737
+ "grad_norm": 1.7509822845458984,
738
+ "learning_rate": 5.220947368421052e-05,
739
+ "loss": 17.6602,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08762886597938144,
744
+ "grad_norm": 1.7642613649368286,
745
+ "learning_rate": 5.1682105263157895e-05,
746
+ "loss": 17.6406,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08848797250859107,
751
+ "grad_norm": 1.9808465242385864,
752
+ "learning_rate": 5.115473684210527e-05,
753
+ "loss": 17.8926,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08934707903780069,
758
+ "grad_norm": 1.885969877243042,
759
+ "learning_rate": 5.062736842105263e-05,
760
+ "loss": 17.7344,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.09020618556701031,
765
+ "grad_norm": 1.6802561283111572,
766
+ "learning_rate": 5.01e-05,
767
+ "loss": 17.5977,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.09106529209621993,
772
+ "grad_norm": 1.6616181135177612,
773
+ "learning_rate": 4.9572631578947363e-05,
774
+ "loss": 17.5918,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09192439862542956,
779
+ "grad_norm": 1.3513654470443726,
780
+ "learning_rate": 4.9045263157894736e-05,
781
+ "loss": 17.6426,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09278350515463918,
786
+ "grad_norm": 1.3804975748062134,
787
+ "learning_rate": 4.85178947368421e-05,
788
+ "loss": 17.6445,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0936426116838488,
793
+ "grad_norm": 1.1714085340499878,
794
+ "learning_rate": 4.799052631578947e-05,
795
+ "loss": 17.6777,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09450171821305842,
800
+ "grad_norm": 1.0673766136169434,
801
+ "learning_rate": 4.746315789473684e-05,
802
+ "loss": 17.8066,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09536082474226804,
807
+ "grad_norm": 1.5452264547348022,
808
+ "learning_rate": 4.693578947368421e-05,
809
+ "loss": 17.8184,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09621993127147767,
814
+ "grad_norm": 1.5296186208724976,
815
+ "learning_rate": 4.6408421052631576e-05,
816
+ "loss": 17.6094,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09707903780068729,
821
+ "grad_norm": 1.5229887962341309,
822
+ "learning_rate": 4.588105263157894e-05,
823
+ "loss": 17.8379,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0979381443298969,
828
+ "grad_norm": 2.274534225463867,
829
+ "learning_rate": 4.5353684210526314e-05,
830
+ "loss": 17.7578,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09879725085910653,
835
+ "grad_norm": 1.2260631322860718,
836
+ "learning_rate": 4.482631578947368e-05,
837
+ "loss": 17.5723,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09965635738831616,
842
+ "grad_norm": 1.5958672761917114,
843
+ "learning_rate": 4.429894736842105e-05,
844
+ "loss": 17.5117,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.10051546391752578,
849
+ "grad_norm": 1.4200704097747803,
850
+ "learning_rate": 4.3771578947368424e-05,
851
+ "loss": 17.7402,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1013745704467354,
856
+ "grad_norm": 1.4764938354492188,
857
+ "learning_rate": 4.324421052631579e-05,
858
+ "loss": 17.3945,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10223367697594501,
863
+ "grad_norm": 1.3718637228012085,
864
+ "learning_rate": 4.2716842105263155e-05,
865
+ "loss": 17.3906,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10309278350515463,
870
+ "grad_norm": 1.2205734252929688,
871
+ "learning_rate": 4.218947368421052e-05,
872
+ "loss": 17.6113,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10395189003436427,
877
+ "grad_norm": 0.978182315826416,
878
+ "learning_rate": 4.166210526315789e-05,
879
+ "loss": 17.4883,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10481099656357389,
884
+ "grad_norm": 1.3435237407684326,
885
+ "learning_rate": 4.1134736842105265e-05,
886
+ "loss": 17.709,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1056701030927835,
891
+ "grad_norm": 0.6833091378211975,
892
+ "learning_rate": 4.060736842105263e-05,
893
+ "loss": 17.4863,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10652920962199312,
898
+ "grad_norm": 0.5739802718162537,
899
+ "learning_rate": 4.008e-05,
900
+ "loss": 17.4883,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10738831615120274,
905
+ "grad_norm": 0.7817716598510742,
906
+ "learning_rate": 3.955263157894737e-05,
907
+ "loss": 17.373,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.10824742268041238,
912
+ "grad_norm": 0.555398166179657,
913
+ "learning_rate": 3.9025263157894733e-05,
914
+ "loss": 17.4824,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.109106529209622,
919
+ "grad_norm": 0.7074904441833496,
920
+ "learning_rate": 3.84978947368421e-05,
921
+ "loss": 17.5977,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10996563573883161,
926
+ "grad_norm": 0.8045018315315247,
927
+ "learning_rate": 3.797052631578947e-05,
928
+ "loss": 17.5996,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.11082474226804123,
933
+ "grad_norm": 0.5356755256652832,
934
+ "learning_rate": 3.744315789473684e-05,
935
+ "loss": 17.4863,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11168384879725086,
940
+ "grad_norm": 1.1794716119766235,
941
+ "learning_rate": 3.691578947368421e-05,
942
+ "loss": 17.7051,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11254295532646048,
947
+ "grad_norm": 0.8735027313232422,
948
+ "learning_rate": 3.638842105263158e-05,
949
+ "loss": 17.377,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1134020618556701,
954
+ "grad_norm": 0.7275944352149963,
955
+ "learning_rate": 3.5861052631578946e-05,
956
+ "loss": 17.5977,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11426116838487972,
961
+ "grad_norm": 0.8777956962585449,
962
+ "learning_rate": 3.533368421052631e-05,
963
+ "loss": 17.3789,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11512027491408934,
968
+ "grad_norm": 1.0887410640716553,
969
+ "learning_rate": 3.4806315789473684e-05,
970
+ "loss": 17.7051,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11597938144329897,
975
+ "grad_norm": 0.860932469367981,
976
+ "learning_rate": 3.427894736842105e-05,
977
+ "loss": 17.377,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11683848797250859,
982
+ "grad_norm": 1.0373424291610718,
983
+ "learning_rate": 3.375157894736842e-05,
984
+ "loss": 17.707,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11769759450171821,
989
+ "grad_norm": 0.5653349757194519,
990
+ "learning_rate": 3.322421052631579e-05,
991
+ "loss": 17.4824,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11855670103092783,
996
+ "grad_norm": 0.899078369140625,
997
+ "learning_rate": 3.269684210526316e-05,
998
+ "loss": 17.3848,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11941580756013746,
1003
+ "grad_norm": 0.8551767468452454,
1004
+ "learning_rate": 3.2169473684210525e-05,
1005
+ "loss": 17.3789,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.12027491408934708,
1010
+ "grad_norm": 0.8607640862464905,
1011
+ "learning_rate": 3.164210526315789e-05,
1012
+ "loss": 17.3809,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1211340206185567,
1017
+ "grad_norm": 0.7621393799781799,
1018
+ "learning_rate": 3.111473684210526e-05,
1019
+ "loss": 17.375,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12199312714776632,
1024
+ "grad_norm": 0.44112229347229004,
1025
+ "learning_rate": 3.058736842105263e-05,
1026
+ "loss": 17.4883,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12285223367697594,
1031
+ "grad_norm": 0.5754379630088806,
1032
+ "learning_rate": 3.0059999999999997e-05,
1033
+ "loss": 17.5938,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.12371134020618557,
1038
+ "grad_norm": 1.126187801361084,
1039
+ "learning_rate": 2.9532631578947366e-05,
1040
+ "loss": 17.707,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12457044673539519,
1045
+ "grad_norm": 0.7772193551063538,
1046
+ "learning_rate": 2.9005263157894738e-05,
1047
+ "loss": 17.5938,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1254295532646048,
1052
+ "grad_norm": 0.5117862224578857,
1053
+ "learning_rate": 2.8477894736842103e-05,
1054
+ "loss": 17.4863,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12628865979381443,
1059
+ "grad_norm": 1.2148230075836182,
1060
+ "learning_rate": 2.7950526315789472e-05,
1061
+ "loss": 17.7031,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12714776632302405,
1066
+ "grad_norm": 0.8688849806785583,
1067
+ "learning_rate": 2.7423157894736844e-05,
1068
+ "loss": 17.5938,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12800687285223367,
1073
+ "grad_norm": 2.2169699668884277,
1074
+ "learning_rate": 2.689578947368421e-05,
1075
+ "loss": 17.9238,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.12886597938144329,
1080
+ "grad_norm": 3.289537191390991,
1081
+ "learning_rate": 2.6368421052631575e-05,
1082
+ "loss": 18.1348,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.12886597938144329,
1087
+ "eval_loss": 8.79317569732666,
1088
+ "eval_runtime": 3.9208,
1089
+ "eval_samples_per_second": 124.975,
1090
+ "eval_steps_per_second": 31.371,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6106216660992.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null