adammandic87 commited on
Commit
f2ee645
·
verified ·
1 Parent(s): 264d703

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 sha256:27181cf1af8cd6ab09bdd6e86509935d6815cf8e2ba87b51987b3b929dbbf15e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6681d845f3a09d6f17e582f96874a62d69fa36b0b53228148aa76617f669989
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31903c9e1781861fe55c4c0d1bc48a981e34b9e68b3cb04073e11d1775cfbb59
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e944b6e69003fd29708f276d6bc4fb36d70410cd1c9f00dfbaf3f8f8292ee59
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:355e76fc8598e2798497bc3f2005a10b27ba180fd974991d896736ff11192f57
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092bbf7dba62c9c6523393b0e9e7df3c1352ee6dd4eae5bc37aac4bda7c5fc71
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.030557677616501147,
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": 31.58,
732
  "eval_steps_per_second": 15.79,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 1.895803354349568e+16,
754
  "train_batch_size": 2,
755
  "trial_name": null,
756
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04583651642475172,
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": 31.58,
732
  "eval_steps_per_second": 15.79,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.030863254392666156,
737
+ "grad_norm": 1.059015154838562,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 2.2306,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.03116883116883117,
744
+ "grad_norm": 1.7741599082946777,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 3.5765,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03147440794499618,
751
+ "grad_norm": 2.162186622619629,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 3.4345,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.03177998472116119,
758
+ "grad_norm": 2.5586822032928467,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 2.9903,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03208556149732621,
765
+ "grad_norm": 2.0206334590911865,
766
+ "learning_rate": 0.0001,
767
+ "loss": 2.1015,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.032391138273491216,
772
+ "grad_norm": 1.485046148300171,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 3.0347,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.032696715049656225,
779
+ "grad_norm": 1.54109787940979,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 3.4548,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03300229182582124,
786
+ "grad_norm": 2.197310209274292,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 3.259,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03330786860198625,
793
+ "grad_norm": 1.7704206705093384,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 3.6315,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03361344537815126,
800
+ "grad_norm": 1.5361251831054688,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 3.565,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.033919022154316275,
807
+ "grad_norm": 1.6352933645248413,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 4.2866,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.034224598930481284,
814
+ "grad_norm": 1.5935004949569702,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 1.9851,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03453017570664629,
821
+ "grad_norm": 1.665504813194275,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 2.6306,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03483575248281131,
828
+ "grad_norm": 1.937706470489502,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 3.863,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03514132925897632,
835
+ "grad_norm": 1.2224433422088623,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 2.8868,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03544690603514133,
842
+ "grad_norm": 1.5066522359848022,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 2.3325,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.035752482811306344,
849
+ "grad_norm": 1.7514053583145142,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 3.0919,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03605805958747135,
856
+ "grad_norm": 2.9330379962921143,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 3.5218,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03636363636363636,
863
+ "grad_norm": 1.7792319059371948,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 2.6203,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03666921313980138,
870
+ "grad_norm": 1.3247697353363037,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 3.0596,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03697478991596639,
877
+ "grad_norm": 1.2648736238479614,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 1.8237,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.037280366692131396,
884
+ "grad_norm": 1.992238163948059,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 3.7792,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03758594346829641,
891
+ "grad_norm": 4.09771203994751,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 2.6822,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03789152024446142,
898
+ "grad_norm": 1.820434331893921,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 2.6724,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03819709702062643,
905
+ "grad_norm": 1.6424354314804077,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 3.4209,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.038502673796791446,
912
+ "grad_norm": 2.45306134223938,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 3.502,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.038808250572956456,
919
+ "grad_norm": 1.5133211612701416,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 2.9659,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.039113827349121465,
926
+ "grad_norm": 2.0427510738372803,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 4.4254,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03941940412528648,
933
+ "grad_norm": 1.8973280191421509,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 2.7392,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03972498090145149,
940
+ "grad_norm": 1.3709115982055664,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 1.846,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0400305576776165,
947
+ "grad_norm": 0.9821792244911194,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 2.6255,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.040336134453781515,
954
+ "grad_norm": 1.0302985906600952,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 1.7235,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.040641711229946524,
961
+ "grad_norm": 1.5651659965515137,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 3.025,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04094728800611153,
968
+ "grad_norm": 1.6474765539169312,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 2.6187,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.04125286478227655,
975
+ "grad_norm": 1.3223847150802612,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 2.7047,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04155844155844156,
982
+ "grad_norm": 1.139236569404602,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 1.2376,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04186401833460657,
989
+ "grad_norm": 1.7920728921890259,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 3.7943,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.042169595110771584,
996
+ "grad_norm": 1.287239909172058,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 3.2348,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04247517188693659,
1003
+ "grad_norm": 1.7391269207000732,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 4.3926,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0427807486631016,
1010
+ "grad_norm": 1.4766433238983154,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 1.1949,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04308632543926662,
1017
+ "grad_norm": 2.0691680908203125,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 2.6009,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04339190221543163,
1024
+ "grad_norm": 2.074167490005493,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 2.3074,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.043697478991596636,
1031
+ "grad_norm": 1.3897058963775635,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 3.5031,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04400305576776165,
1038
+ "grad_norm": 1.8366340398788452,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 3.5897,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04430863254392666,
1045
+ "grad_norm": 1.4808062314987183,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 3.3973,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04461420932009167,
1052
+ "grad_norm": 1.730080485343933,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 3.0046,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.044919786096256686,
1059
+ "grad_norm": 1.9429744482040405,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 3.086,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.045225362872421696,
1066
+ "grad_norm": 1.349107265472412,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 3.3598,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.045530939648586705,
1073
+ "grad_norm": 1.0275979042053223,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 1.5396,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04583651642475172,
1080
+ "grad_norm": 1.412550449371338,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 1.6656,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04583651642475172,
1087
+ "eval_loss": 3.142651081085205,
1088
+ "eval_runtime": 43.5899,
1089
+ "eval_samples_per_second": 31.613,
1090
+ "eval_steps_per_second": 15.806,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 2.8344572102836224e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null