0x1202 commited on
Commit
1314b8d
·
verified ·
1 Parent(s): 7cf980b

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:f264cb59cd780fa28956a9ca7270e8aab073ab69f3a1f2218fd8c791321acbce
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcdc77e691ebc355908e9667b4cbd7c7c85785799b2b0e55f8bf181e4c844a09
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:256ce5c390aa39144eae9cac3d09e672ce5618cc384e2d3b3ff201b84ffefb7c
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cda67a8c3d8fcebc569c259b0d32f6c5f1ea3ea10abf325c01bcce81aeed86
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cddb5b592d53e899d7d2e0acba41d9eb20923335f8f874ce4055ba10187bbb89
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04caaef13525a396cc9d35e70563f264d75bb0e4937ab39918b270f68e01a11
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": 2.0762710571289062,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.014283673760891302,
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": 14.208,
732
  "eval_steps_per_second": 3.552,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.42188868534272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0154037475585938,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02142551064133695,
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": 14.208,
732
  "eval_steps_per_second": 3.552,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.014426510498500215,
737
+ "grad_norm": 0.9230821132659912,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.9822,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.014569347236109127,
744
+ "grad_norm": 0.927600085735321,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.2515,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01471218397371804,
751
+ "grad_norm": 0.8468804955482483,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.4639,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.014855020711326954,
758
+ "grad_norm": 0.8162264227867126,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.3332,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.014997857448935866,
765
+ "grad_norm": 0.5949187874794006,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.0985,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01514069418654478,
772
+ "grad_norm": 0.6014756560325623,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.4103,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.015283530924153693,
779
+ "grad_norm": 0.535846471786499,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.2027,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.015426367661762605,
786
+ "grad_norm": 0.5490545630455017,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.2776,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.015569204399371518,
793
+ "grad_norm": 0.5120407938957214,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.0491,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01571204113698043,
800
+ "grad_norm": 0.5499867796897888,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.9542,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.015854877874589345,
807
+ "grad_norm": 0.5313657522201538,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.1666,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.015997714612198257,
814
+ "grad_norm": 0.5323649048805237,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.0331,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01614055134980717,
821
+ "grad_norm": 0.5379316806793213,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.1669,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.016283388087416084,
828
+ "grad_norm": 0.5692285895347595,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.1202,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.016426224825024996,
835
+ "grad_norm": 0.5327719449996948,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.1069,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.016569061562633908,
842
+ "grad_norm": 0.5937054753303528,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.2263,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.016711898300242823,
849
+ "grad_norm": 0.7458532452583313,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.1605,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.016854735037851735,
856
+ "grad_norm": 0.5572732090950012,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.0539,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.01699757177546065,
863
+ "grad_norm": 0.5822060704231262,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.2946,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.017140408513069562,
870
+ "grad_norm": 0.5658606886863708,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.9808,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.017283245250678474,
877
+ "grad_norm": 0.6279320120811462,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.958,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01742608198828739,
884
+ "grad_norm": 0.6270695924758911,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.0164,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0175689187258963,
891
+ "grad_norm": 0.6223905682563782,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.2622,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.017711755463505213,
898
+ "grad_norm": 0.5716925859451294,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.8439,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.017854592201114128,
905
+ "grad_norm": 0.5686030983924866,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.9191,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.01799742893872304,
912
+ "grad_norm": 0.6836259961128235,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.1853,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.01814026567633195,
919
+ "grad_norm": 0.6107368469238281,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.049,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.018283102413940867,
926
+ "grad_norm": 0.6420040726661682,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.1299,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01842593915154978,
933
+ "grad_norm": 0.6745955944061279,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.1502,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.01856877588915869,
940
+ "grad_norm": 0.5770037770271301,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.853,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.018711612626767606,
947
+ "grad_norm": 0.6133952140808105,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.9472,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.018854449364376517,
954
+ "grad_norm": 0.6142903566360474,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.6797,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01899728610198543,
961
+ "grad_norm": 0.7279035449028015,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.1774,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.019140122839594344,
968
+ "grad_norm": 0.7295705676078796,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.255,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.019282959577203256,
975
+ "grad_norm": 0.8287146687507629,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.193,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.019425796314812168,
982
+ "grad_norm": 0.7983558773994446,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.0274,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.019568633052421083,
989
+ "grad_norm": 0.9305437803268433,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.237,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.019711469790029995,
996
+ "grad_norm": 0.8844069242477417,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.0594,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01985430652763891,
1003
+ "grad_norm": 0.8477354049682617,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.0616,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.019997143265247822,
1010
+ "grad_norm": 0.8395882844924927,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.0588,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.020139980002856734,
1017
+ "grad_norm": 0.8531187176704407,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.8994,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02028281674046565,
1024
+ "grad_norm": 0.8506578207015991,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.618,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02042565347807456,
1031
+ "grad_norm": 0.8401762247085571,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.5319,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.020568490215683473,
1038
+ "grad_norm": 0.9789445400238037,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.9447,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.020711326953292388,
1045
+ "grad_norm": 0.9492172598838806,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5791,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0208541636909013,
1052
+ "grad_norm": 1.1460164785385132,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7931,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.02099700042851021,
1059
+ "grad_norm": 0.9129149317741394,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.5159,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.021139837166119127,
1066
+ "grad_norm": 1.139918327331543,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.875,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02128267390372804,
1073
+ "grad_norm": 1.1506749391555786,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.0811,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02142551064133695,
1080
+ "grad_norm": 1.2690898180007935,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.2944,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02142551064133695,
1087
+ "eval_loss": 2.0154037475585938,
1088
+ "eval_runtime": 830.098,
1089
+ "eval_samples_per_second": 14.204,
1090
+ "eval_steps_per_second": 3.551,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.13283302801408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null