bbytxt commited on
Commit
2412e1a
·
verified ·
1 Parent(s): 259fa22

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 sha256:5e1033432107bb453250512855bb4417555fb261809e1513428bad2c18002473
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d6164534de2fe3dd76f76fab754d967c5a1cc75854a61375769f8f229a84ce
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5ae8dfb1b88d4dfc431b29329c34520fa281e9dfc7bbba64cf6fb35fc81f89b
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6282b434c8263f14c489886eb009a73c00f78873f55c72315077efd92a0e1b7
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf69b39deaf4ceca685dfbcc23736d2b58b7133cb9b3922c08857d6baece73ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b41a52b97ddb68065be69b6fe530ce0d6a484a406f1702250b019f3cdfff6d5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9608962535858154,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.017115960633290545,
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": 38.671,
732
  "eval_steps_per_second": 19.336,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3850414190493696.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.9427156448364258,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.025673940949935817,
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": 38.671,
732
  "eval_steps_per_second": 19.336,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01728712023962345,
737
+ "grad_norm": 0.12267659604549408,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 1.8221,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.017458279845956354,
744
+ "grad_norm": 0.11667729169130325,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 1.8163,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01762943945228926,
751
+ "grad_norm": 0.1297779083251953,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 1.8252,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.017800599058622166,
758
+ "grad_norm": 0.12183117121458054,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 1.79,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.01797175866495507,
765
+ "grad_norm": 0.11510883271694183,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 1.7359,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.018142918271287976,
772
+ "grad_norm": 0.11487369984388351,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 1.8322,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01831407787762088,
779
+ "grad_norm": 0.12407288700342178,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 1.9415,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01848523748395379,
786
+ "grad_norm": 0.11880673468112946,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 1.7991,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018656397090286693,
793
+ "grad_norm": 0.12787018716335297,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 1.9157,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.018827556696619598,
800
+ "grad_norm": 0.12218679487705231,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 1.843,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.018998716302952502,
807
+ "grad_norm": 0.1273295134305954,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 1.9732,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01916987590928541,
814
+ "grad_norm": 0.1331591010093689,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 1.9346,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.019341035515618315,
821
+ "grad_norm": 0.1283877044916153,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 1.9575,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.01951219512195122,
828
+ "grad_norm": 0.11732184886932373,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 1.8368,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.019683354728284124,
835
+ "grad_norm": 0.1036926805973053,
836
+ "learning_rate": 5e-05,
837
+ "loss": 1.7971,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01985451433461703,
842
+ "grad_norm": 0.12696321308612823,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 1.987,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.020025673940949937,
849
+ "grad_norm": 0.12035303562879562,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 2.05,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.02019683354728284,
856
+ "grad_norm": 0.09441588819026947,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 1.7966,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.020367993153615746,
863
+ "grad_norm": 0.1084362342953682,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 1.9896,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02053915275994865,
870
+ "grad_norm": 0.10377444326877594,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 1.9442,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02071031236628156,
877
+ "grad_norm": 0.09699568152427673,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 1.8642,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.020881471972614463,
884
+ "grad_norm": 0.10071204602718353,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 1.9961,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.021052631578947368,
891
+ "grad_norm": 0.0921294167637825,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 1.8438,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.021223791185280273,
898
+ "grad_norm": 0.10018813610076904,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 1.9538,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.02139495079161318,
905
+ "grad_norm": 0.09550834447145462,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 1.8572,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.021566110397946085,
912
+ "grad_norm": 0.1069275438785553,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 2.0335,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02173727000427899,
919
+ "grad_norm": 0.1051395982503891,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 2.0374,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.021908429610611894,
926
+ "grad_norm": 0.10209425538778305,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 1.9306,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.022079589216944803,
933
+ "grad_norm": 0.09854423254728317,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 1.9756,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.022250748823277707,
940
+ "grad_norm": 0.10003539174795151,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.9646,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.022421908429610612,
947
+ "grad_norm": 0.10941645503044128,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 2.062,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.022593068035943516,
954
+ "grad_norm": 0.1019466444849968,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 1.9037,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.022764227642276424,
961
+ "grad_norm": 0.10443319380283356,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 2.0101,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.02293538724860933,
968
+ "grad_norm": 0.10645749419927597,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 1.9192,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.023106546854942234,
975
+ "grad_norm": 0.10710829496383667,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 1.8548,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02327770646127514,
982
+ "grad_norm": 0.11624782532453537,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 1.9397,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.023448866067608043,
989
+ "grad_norm": 0.12152379751205444,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 1.971,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02362002567394095,
996
+ "grad_norm": 0.12296583503484726,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 1.8179,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.023791185280273856,
1003
+ "grad_norm": 0.1308358758687973,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 2.0566,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02396234488660676,
1010
+ "grad_norm": 0.12238892912864685,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 2.0106,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.024133504492939665,
1017
+ "grad_norm": 0.14263762533664703,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.8094,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.024304664099272573,
1024
+ "grad_norm": 0.16151531040668488,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 1.7815,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.024475823705605478,
1031
+ "grad_norm": 0.17212718725204468,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 1.977,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.024646983311938382,
1038
+ "grad_norm": 0.16314253211021423,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.8695,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.024818142918271287,
1045
+ "grad_norm": 0.1866285353899002,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 1.8092,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.024989302524604195,
1052
+ "grad_norm": 0.19816122949123383,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 1.9085,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0251604621309371,
1059
+ "grad_norm": 0.2647472023963928,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 2.0202,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.025331621737270004,
1066
+ "grad_norm": 0.37373101711273193,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 2.1299,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02550278134360291,
1073
+ "grad_norm": 0.43742233514785767,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 2.0061,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.025673940949935817,
1080
+ "grad_norm": 0.7022097110748291,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 2.3952,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.025673940949935817,
1087
+ "eval_loss": 1.9427156448364258,
1088
+ "eval_runtime": 254.3821,
1089
+ "eval_samples_per_second": 38.682,
1090
+ "eval_steps_per_second": 19.341,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5784891945910272.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null