bbytxt commited on
Commit
a8a1834
·
verified ·
1 Parent(s): 55ae532

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 sha256:8d0162b96c7a11c09d459e33bb9ed62215ec36b680e5b961b5a5a2e85a87bc64
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f81ce954f71987253c0437b959a46d53e28fdcdab0e32f7db19c31b5412c634
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3080a36b2a27c988b5463399add0db6201ea81b76abd5200d90e1a67c2edff3
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d5ea444bb895258a0cfa2f66975c324842ae5bdf09e69b5535c9ccdd3756c1
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0739e9865e7e2d8c7807df590f380af43aebea4e2bdf47bdfde4d2870cf88c2c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bc442b6b248e17db6c605a743ccd4e619e6dcb577dbb3c6b32580312fa965a
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": 11.540384292602539,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.29806259314456035,
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": 100.63,
732
  "eval_steps_per_second": 25.291,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 110179123200000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.503910064697266,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.44709388971684055,
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": 100.63,
732
  "eval_steps_per_second": 25.291,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.30104321907600595,
737
+ "grad_norm": 0.5054342150688171,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.5431,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.30402384500745155,
744
+ "grad_norm": 0.27865058183670044,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.5917,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.30700447093889716,
751
+ "grad_norm": 0.2700931429862976,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.5851,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.30998509687034276,
758
+ "grad_norm": 0.22124922275543213,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.5659,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.31296572280178836,
765
+ "grad_norm": 0.21236014366149902,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.529,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.31594634873323396,
772
+ "grad_norm": 0.1851605325937271,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.56,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.31892697466467956,
779
+ "grad_norm": 0.24979141354560852,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.565,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.32190760059612517,
786
+ "grad_norm": 0.1909526288509369,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.5583,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.32488822652757077,
793
+ "grad_norm": 0.19361820816993713,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.5451,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.32786885245901637,
800
+ "grad_norm": 0.21884016692638397,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.543,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.33084947839046197,
807
+ "grad_norm": 0.1892264038324356,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.5483,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.33383010432190763,
814
+ "grad_norm": 0.1816645711660385,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.5348,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.33681073025335323,
821
+ "grad_norm": 0.15595115721225739,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.5297,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.33979135618479883,
828
+ "grad_norm": 0.14673824608325958,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.5318,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.34277198211624443,
835
+ "grad_norm": 0.15732240676879883,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.5463,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.34575260804769004,
842
+ "grad_norm": 0.19519706070423126,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.5438,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.34873323397913564,
849
+ "grad_norm": 0.15034478902816772,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.5321,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.35171385991058124,
856
+ "grad_norm": 0.21822240948677063,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.5061,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.35469448584202684,
863
+ "grad_norm": 0.14199988543987274,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.5451,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.35767511177347244,
870
+ "grad_norm": 0.1756989061832428,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.522,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.36065573770491804,
877
+ "grad_norm": 0.17190110683441162,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.5216,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.36363636363636365,
884
+ "grad_norm": 0.14261436462402344,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.5245,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.36661698956780925,
891
+ "grad_norm": 0.1700989305973053,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.5033,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.36959761549925485,
898
+ "grad_norm": 0.14692789316177368,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.5126,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.37257824143070045,
905
+ "grad_norm": 0.14157594740390778,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.5113,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.37555886736214605,
912
+ "grad_norm": 0.14132097363471985,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.5042,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.37853949329359166,
919
+ "grad_norm": 0.1447451114654541,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.5097,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.38152011922503726,
926
+ "grad_norm": 0.13442525267601013,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.507,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.38450074515648286,
933
+ "grad_norm": 0.13315923511981964,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.4993,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.38748137108792846,
940
+ "grad_norm": 0.13803797960281372,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.4959,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.39046199701937406,
947
+ "grad_norm": 0.17156541347503662,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.5019,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.39344262295081966,
954
+ "grad_norm": 0.15189988911151886,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.5115,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.39642324888226527,
961
+ "grad_norm": 0.14400018751621246,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.5088,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.39940387481371087,
968
+ "grad_norm": 0.16279402375221252,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.5146,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.40238450074515647,
975
+ "grad_norm": 0.1359529346227646,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.4951,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.40536512667660207,
982
+ "grad_norm": 0.1630541831254959,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.4992,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4083457526080477,
989
+ "grad_norm": 0.14012819528579712,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.5079,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4113263785394933,
996
+ "grad_norm": 0.16439418494701385,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.496,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.4143070044709389,
1003
+ "grad_norm": 0.13019785284996033,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.5034,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.4172876304023845,
1010
+ "grad_norm": 0.1702735871076584,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.4945,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4202682563338301,
1017
+ "grad_norm": 0.16818252205848694,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.4981,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4232488822652757,
1024
+ "grad_norm": 0.13469691574573517,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.5004,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4262295081967213,
1031
+ "grad_norm": 0.15116199851036072,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.506,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.42921013412816694,
1038
+ "grad_norm": 0.1493290662765503,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.5033,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.43219076005961254,
1045
+ "grad_norm": 0.147053524851799,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.4964,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.43517138599105815,
1052
+ "grad_norm": 0.19523854553699493,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.4983,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.43815201192250375,
1059
+ "grad_norm": 0.18568909168243408,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.4926,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.44113263785394935,
1066
+ "grad_norm": 0.16512249410152435,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.4944,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.44411326378539495,
1073
+ "grad_norm": 0.1522430181503296,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.4959,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.44709388971684055,
1080
+ "grad_norm": 0.1610044687986374,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.4846,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.44709388971684055,
1087
+ "eval_loss": 11.503910064697266,
1088
+ "eval_runtime": 5.8673,
1089
+ "eval_samples_per_second": 96.296,
1090
+ "eval_steps_per_second": 24.202,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 165268684800000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null