prxy5606 commited on
Commit
cdfff77
·
verified ·
1 Parent(s): 5eb194e

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:bad84c7fca2cfeeb1f76902a2789cf0b93fd45d4e8f727c6a6906ba69fb4ea01
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe73852f202235061d607e9fca310786233a8a17c9bf22c2644657f8c2b2dc7
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38c1876c9cf4f250cf3e35c6d23e2f4a083b28ce93d8552299de6b6d9f559859
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328fdf46c77da053bc8d4cc6eb0a142f10c704f7a54502a9895b469cbdd402a4
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6032ff9f11490ba171d2818e08694831a9d5f1d9085352e52d616758448e61fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db56496494aa4378a5c9781d654feb8d33932c80d7850a9d17ce5609a75bbea
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": 0.025695189833641052,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.008985129610494632,
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": 20.675,
732
  "eval_steps_per_second": 5.17,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7.55390862065664e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.017778942361474037,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.013477694415741948,
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": 20.675,
732
  "eval_steps_per_second": 5.17,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009074980906599578,
737
+ "grad_norm": 0.3603351414203644,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.0495,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009164832202704525,
744
+ "grad_norm": 0.14788700640201569,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.0081,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.00925468349880947,
751
+ "grad_norm": 0.3788295090198517,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.0845,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009344534794914417,
758
+ "grad_norm": 0.541358232498169,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0861,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009434386091019363,
765
+ "grad_norm": 0.06525766104459763,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.0023,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.00952423738712431,
772
+ "grad_norm": 7.902554512023926,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.0945,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.009614088683229256,
779
+ "grad_norm": 0.060054849833250046,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0042,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.009703939979334202,
786
+ "grad_norm": 0.8934226632118225,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2003,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.009793791275439149,
793
+ "grad_norm": 0.48377078771591187,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.0312,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.009883642571544095,
800
+ "grad_norm": 0.11235053092241287,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0052,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.009973493867649041,
807
+ "grad_norm": 0.15674369037151337,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.0065,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010063345163753987,
814
+ "grad_norm": 0.13642801344394684,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.0073,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.010153196459858934,
821
+ "grad_norm": 1.1502249240875244,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.0665,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01024304775596388,
828
+ "grad_norm": 0.4164653420448303,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.0166,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.010332899052068826,
835
+ "grad_norm": 0.29311686754226685,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.026,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.010422750348173773,
842
+ "grad_norm": 1.3062735795974731,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.091,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.010512601644278719,
849
+ "grad_norm": 0.3029405474662781,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.053,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.010602452940383665,
856
+ "grad_norm": 0.08126576244831085,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.0032,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.010692304236488611,
863
+ "grad_norm": 2.6398396492004395,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.0262,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.010782155532593558,
870
+ "grad_norm": 1.9561644792556763,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.0381,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.010872006828698504,
877
+ "grad_norm": 0.723412036895752,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.0563,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01096185812480345,
884
+ "grad_norm": 1.8104438781738281,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.1271,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.011051709420908397,
891
+ "grad_norm": 0.12050595879554749,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.0046,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011141560717013343,
898
+ "grad_norm": 0.18473798036575317,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.0068,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011231412013118289,
905
+ "grad_norm": 1.3061293363571167,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.0727,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011321263309223235,
912
+ "grad_norm": 0.827674150466919,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.1182,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.011411114605328182,
919
+ "grad_norm": 1.8033653497695923,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.0416,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.011500965901433128,
926
+ "grad_norm": 0.8880636096000671,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.015,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.011590817197538074,
933
+ "grad_norm": 0.27589327096939087,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.0695,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.01168066849364302,
940
+ "grad_norm": 0.7286954522132874,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.0176,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.011770519789747967,
947
+ "grad_norm": 0.5940603017807007,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.0625,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.011860371085852913,
954
+ "grad_norm": 0.3715779781341553,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.0726,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01195022238195786,
961
+ "grad_norm": 0.1934714913368225,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.0079,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012040073678062806,
968
+ "grad_norm": 0.5433386564254761,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0224,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.012129924974167752,
975
+ "grad_norm": 0.09182822704315186,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.0046,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.012219776270272698,
982
+ "grad_norm": 0.15049512684345245,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.0077,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.012309627566377645,
989
+ "grad_norm": 0.7672333717346191,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.0116,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01239947886248259,
996
+ "grad_norm": 2.007136821746826,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.031,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.012489330158587537,
1003
+ "grad_norm": 0.1672549694776535,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.0081,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.012579181454692483,
1010
+ "grad_norm": 1.327528715133667,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.1087,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01266903275079743,
1017
+ "grad_norm": 0.04769575595855713,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0029,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.012758884046902376,
1024
+ "grad_norm": 6.449910640716553,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3223,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.012848735343007322,
1031
+ "grad_norm": 0.5963060855865479,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.024,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.012938586639112269,
1038
+ "grad_norm": 0.7222399115562439,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0116,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013028437935217215,
1045
+ "grad_norm": 1.6211422681808472,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.1589,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.013118289231322161,
1052
+ "grad_norm": 6.503261089324951,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.1503,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.013208140527427107,
1059
+ "grad_norm": 4.7277655601501465,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3816,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.013297991823532054,
1066
+ "grad_norm": 2.368058204650879,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.1548,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.013387843119637,
1073
+ "grad_norm": 2.8131978511810303,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.1363,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.013477694415741948,
1080
+ "grad_norm": 8.33768081665039,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.509,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.013477694415741948,
1087
+ "eval_loss": 0.017778942361474037,
1088
+ "eval_runtime": 906.674,
1089
+ "eval_samples_per_second": 20.674,
1090
+ "eval_steps_per_second": 5.169,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.133086293098496e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null