lesso commited on
Commit
b034e98
·
verified ·
1 Parent(s): e1a9610

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 sha256:81828e3e61b4387228ad3c68a9ba9231d8672c73c1b05769197c2d6000a5a10c
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240e719bcd4fd491c2237e23258c8e39bca047342b7cc8bc8fdd9f49df12bdb3
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5303af86a139a579e4e2c61f6de3133b66ded50e50fd29e4c9abf77182aacbe0
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b87cc3ac8b401765f602819af990d8bdfece651b5596734d6d6a8600928caf
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d914f88fd473c9ee149cb520f3e290d828f1c3cc7e21304f6d037422c1b59399
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a46691699b106230eff0c0cf4e82d75bf9752a9bea064a69a0f7866220b32ab
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9085a964616f2d2af1a309022ca2f10b583138a852293c2266e9df64914089
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191b4f74b8892fe464b31b446bc6f50032359ce22cb38236d5fdccf47f27920e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.635071337223053,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10085728693898134,
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": 8.882,
732
  "eval_steps_per_second": 2.231,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.648580773235917e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6001591086387634,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15128593040847202,
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": 8.882,
732
  "eval_steps_per_second": 2.231,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10186585980837115,
737
+ "grad_norm": 0.7055741548538208,
738
+ "learning_rate": 5.2199052631578945e-05,
739
+ "loss": 0.6355,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10287443267776097,
744
+ "grad_norm": 0.7601715922355652,
745
+ "learning_rate": 5.167178947368422e-05,
746
+ "loss": 0.6535,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10388300554715078,
751
+ "grad_norm": 0.6638849973678589,
752
+ "learning_rate": 5.114452631578948e-05,
753
+ "loss": 0.6594,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10489157841654059,
758
+ "grad_norm": 0.5764726996421814,
759
+ "learning_rate": 5.061726315789474e-05,
760
+ "loss": 0.5227,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1059001512859304,
765
+ "grad_norm": 0.7011322975158691,
766
+ "learning_rate": 5.009e-05,
767
+ "loss": 0.6485,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10690872415532023,
772
+ "grad_norm": 0.6385596394538879,
773
+ "learning_rate": 4.9562736842105266e-05,
774
+ "loss": 0.617,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10791729702471003,
779
+ "grad_norm": 0.613409161567688,
780
+ "learning_rate": 4.903547368421053e-05,
781
+ "loss": 0.5565,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10892586989409984,
786
+ "grad_norm": 0.5934216976165771,
787
+ "learning_rate": 4.850821052631579e-05,
788
+ "loss": 0.5369,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10993444276348967,
793
+ "grad_norm": 0.5698984265327454,
794
+ "learning_rate": 4.7980947368421055e-05,
795
+ "loss": 0.5095,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11094301563287948,
800
+ "grad_norm": 0.6158843636512756,
801
+ "learning_rate": 4.745368421052632e-05,
802
+ "loss": 0.5607,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11195158850226929,
807
+ "grad_norm": 0.6479724645614624,
808
+ "learning_rate": 4.692642105263158e-05,
809
+ "loss": 0.4708,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1129601613716591,
814
+ "grad_norm": 0.7158260345458984,
815
+ "learning_rate": 4.6399157894736844e-05,
816
+ "loss": 0.6306,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11396873424104892,
821
+ "grad_norm": 0.6772667169570923,
822
+ "learning_rate": 4.5871894736842107e-05,
823
+ "loss": 0.5333,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11497730711043873,
828
+ "grad_norm": 0.6242232322692871,
829
+ "learning_rate": 4.5344631578947376e-05,
830
+ "loss": 0.5704,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11598587997982854,
835
+ "grad_norm": 0.6591203212738037,
836
+ "learning_rate": 4.481736842105263e-05,
837
+ "loss": 0.665,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11699445284921836,
842
+ "grad_norm": 0.6875463128089905,
843
+ "learning_rate": 4.4290105263157895e-05,
844
+ "loss": 0.546,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11800302571860817,
849
+ "grad_norm": 0.7117153406143188,
850
+ "learning_rate": 4.3762842105263165e-05,
851
+ "loss": 0.6204,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11901159858799798,
856
+ "grad_norm": 0.6039959192276001,
857
+ "learning_rate": 4.323557894736843e-05,
858
+ "loss": 0.635,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1200201714573878,
863
+ "grad_norm": 0.7009987235069275,
864
+ "learning_rate": 4.2708315789473684e-05,
865
+ "loss": 0.608,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12102874432677761,
870
+ "grad_norm": 0.6250441074371338,
871
+ "learning_rate": 4.218105263157895e-05,
872
+ "loss": 0.5882,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12203731719616742,
877
+ "grad_norm": 0.7398062944412231,
878
+ "learning_rate": 4.1653789473684217e-05,
879
+ "loss": 0.6349,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12304589006555723,
884
+ "grad_norm": 0.7030249834060669,
885
+ "learning_rate": 4.112652631578948e-05,
886
+ "loss": 0.6066,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12405446293494705,
891
+ "grad_norm": 0.7045819163322449,
892
+ "learning_rate": 4.0599263157894736e-05,
893
+ "loss": 0.6708,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12506303580433686,
898
+ "grad_norm": 0.6833453178405762,
899
+ "learning_rate": 4.0072000000000005e-05,
900
+ "loss": 0.6002,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1260716086737267,
905
+ "grad_norm": 0.8382267951965332,
906
+ "learning_rate": 3.954473684210527e-05,
907
+ "loss": 0.6854,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12708018154311648,
912
+ "grad_norm": 0.8998156189918518,
913
+ "learning_rate": 3.901747368421053e-05,
914
+ "loss": 0.5236,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1280887544125063,
919
+ "grad_norm": 0.6268869638442993,
920
+ "learning_rate": 3.849021052631579e-05,
921
+ "loss": 0.5159,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12909732728189613,
926
+ "grad_norm": 0.7306240797042847,
927
+ "learning_rate": 3.796294736842106e-05,
928
+ "loss": 0.6468,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13010590015128592,
933
+ "grad_norm": 0.696013331413269,
934
+ "learning_rate": 3.743568421052632e-05,
935
+ "loss": 0.5668,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13111447302067575,
940
+ "grad_norm": 0.6369208693504333,
941
+ "learning_rate": 3.6908421052631576e-05,
942
+ "loss": 0.5423,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13212304589006554,
947
+ "grad_norm": 0.711659848690033,
948
+ "learning_rate": 3.6381157894736846e-05,
949
+ "loss": 0.5699,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13313161875945537,
954
+ "grad_norm": 0.6578086614608765,
955
+ "learning_rate": 3.585389473684211e-05,
956
+ "loss": 0.4694,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1341401916288452,
961
+ "grad_norm": 0.7941672205924988,
962
+ "learning_rate": 3.532663157894737e-05,
963
+ "loss": 0.6442,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13514876449823499,
968
+ "grad_norm": 0.7573974132537842,
969
+ "learning_rate": 3.4799368421052634e-05,
970
+ "loss": 0.7441,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1361573373676248,
975
+ "grad_norm": 0.7425283789634705,
976
+ "learning_rate": 3.42721052631579e-05,
977
+ "loss": 0.6675,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13716591023701463,
982
+ "grad_norm": 0.6818085312843323,
983
+ "learning_rate": 3.374484210526316e-05,
984
+ "loss": 0.5508,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13817448310640443,
989
+ "grad_norm": 0.729345440864563,
990
+ "learning_rate": 3.321757894736842e-05,
991
+ "loss": 0.5426,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.13918305597579425,
996
+ "grad_norm": 0.6872043013572693,
997
+ "learning_rate": 3.2690315789473686e-05,
998
+ "loss": 0.6318,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14019162884518407,
1003
+ "grad_norm": 0.8204219937324524,
1004
+ "learning_rate": 3.216305263157895e-05,
1005
+ "loss": 0.6653,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14120020171457387,
1010
+ "grad_norm": 0.788364827632904,
1011
+ "learning_rate": 3.163578947368421e-05,
1012
+ "loss": 0.6192,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1422087745839637,
1017
+ "grad_norm": 0.7906739115715027,
1018
+ "learning_rate": 3.1108526315789475e-05,
1019
+ "loss": 0.6494,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14321734745335352,
1024
+ "grad_norm": 0.8248524069786072,
1025
+ "learning_rate": 3.058126315789474e-05,
1026
+ "loss": 0.6254,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1442259203227433,
1031
+ "grad_norm": 0.7894427180290222,
1032
+ "learning_rate": 3.0054e-05,
1033
+ "loss": 0.6097,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14523449319213314,
1038
+ "grad_norm": 0.8506288528442383,
1039
+ "learning_rate": 2.9526736842105263e-05,
1040
+ "loss": 0.6809,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14624306606152296,
1045
+ "grad_norm": 1.004377841949463,
1046
+ "learning_rate": 2.899947368421053e-05,
1047
+ "loss": 0.7994,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14725163893091275,
1052
+ "grad_norm": 0.9447079300880432,
1053
+ "learning_rate": 2.847221052631579e-05,
1054
+ "loss": 0.7159,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14826021180030258,
1059
+ "grad_norm": 0.9489012360572815,
1060
+ "learning_rate": 2.7944947368421052e-05,
1061
+ "loss": 0.7263,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14926878466969237,
1066
+ "grad_norm": 0.9614557027816772,
1067
+ "learning_rate": 2.741768421052632e-05,
1068
+ "loss": 0.6547,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1502773575390822,
1073
+ "grad_norm": 0.98894202709198,
1074
+ "learning_rate": 2.689042105263158e-05,
1075
+ "loss": 0.7373,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15128593040847202,
1080
+ "grad_norm": 1.164485216140747,
1081
+ "learning_rate": 2.636315789473684e-05,
1082
+ "loss": 0.7158,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15128593040847202,
1087
+ "eval_loss": 0.6001591086387634,
1088
+ "eval_runtime": 47.5174,
1089
+ "eval_samples_per_second": 8.797,
1090
+ "eval_steps_per_second": 2.21,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2972871159853875e+17,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null