adammandic87 commited on
Commit
43ded2a
·
verified ·
1 Parent(s): 2d9e45b

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 sha256:0e3b25918b1260c2aac96f1111a7039c4e4d35245b6757794cbad45e17026a06
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2429be1c822029d64617c25305cdd96ef6b8fbf7bd2618035453cc3adf0a235
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b7dd35136c3ebc23453776e63fa0b50647e50ead8c2ed63aacdeea0e79a7723
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f2ec2fb492a17ed821f9a3b357da327814f5969ee72662788990cebe7dabf2
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:b7a0834f50a582035cd09b2a274dabb427c787de931d9ea2c7f3f40fc712e263
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967f26a21846d34647d4361804017e0a4a711430068ed13a0161edd6f4da826e
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": 0.14519056261343014,
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": 30.656,
732
  "eval_steps_per_second": 15.328,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 1.84956424814592e+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": 0.2177858439201452,
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": 30.656,
732
  "eval_steps_per_second": 15.328,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.14664246823956442,
737
+ "grad_norm": 5.348310470581055,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 2.9461,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.14809437386569874,
744
+ "grad_norm": 5.192211627960205,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 3.4127,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.14954627949183302,
751
+ "grad_norm": 6.189526081085205,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 4.1548,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.15099818511796734,
758
+ "grad_norm": 6.250619888305664,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 2.3115,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.15245009074410162,
765
+ "grad_norm": 6.426736354827881,
766
+ "learning_rate": 0.0001,
767
+ "loss": 3.7167,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.15390199637023594,
772
+ "grad_norm": 5.75291633605957,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 3.3103,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.15535390199637023,
779
+ "grad_norm": 7.253111362457275,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 4.6042,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.15680580762250454,
786
+ "grad_norm": 5.568508148193359,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 5.0946,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.15825771324863883,
793
+ "grad_norm": 6.753984451293945,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 4.3953,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.15970961887477314,
800
+ "grad_norm": 6.216484546661377,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 5.5118,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.16116152450090745,
807
+ "grad_norm": 5.957434177398682,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 4.6331,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.16261343012704174,
814
+ "grad_norm": 6.5958099365234375,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 4.002,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.16406533575317606,
821
+ "grad_norm": 6.027259349822998,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 3.4588,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.16551724137931034,
828
+ "grad_norm": 5.432747840881348,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 1.8244,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.16696914700544466,
835
+ "grad_norm": 5.895387649536133,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 1.848,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.16842105263157894,
842
+ "grad_norm": 6.68657922744751,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 4.273,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.16987295825771326,
849
+ "grad_norm": 6.267836093902588,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 4.0085,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.17132486388384754,
856
+ "grad_norm": 5.793243408203125,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 2.6966,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.17277676950998186,
863
+ "grad_norm": 6.046859264373779,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 2.7905,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.17422867513611615,
870
+ "grad_norm": 6.670989990234375,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 4.2815,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.17568058076225046,
877
+ "grad_norm": 6.77061653137207,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 1.7735,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.17713248638838475,
884
+ "grad_norm": 6.429769992828369,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 3.4541,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.17858439201451906,
891
+ "grad_norm": 5.392553329467773,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 1.5246,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.18003629764065335,
898
+ "grad_norm": 8.095450401306152,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 4.5834,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.18148820326678766,
905
+ "grad_norm": 8.309353828430176,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 4.316,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.18294010889292195,
912
+ "grad_norm": 4.959926605224609,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 1.4555,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.18439201451905626,
919
+ "grad_norm": 7.317534923553467,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 3.3059,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.18584392014519055,
926
+ "grad_norm": 7.211315155029297,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 4.0826,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.18729582577132486,
933
+ "grad_norm": 5.193168640136719,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 1.0949,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.18874773139745918,
940
+ "grad_norm": 5.57371711730957,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 2.0219,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.19019963702359347,
947
+ "grad_norm": 6.150767803192139,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 2.8859,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.19165154264972778,
954
+ "grad_norm": 6.404767990112305,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 1.7771,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.19310344827586207,
961
+ "grad_norm": 7.142930507659912,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 2.5359,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.19455535390199638,
968
+ "grad_norm": 7.44117546081543,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 2.2002,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.19600725952813067,
975
+ "grad_norm": 7.635119438171387,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 2.4039,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.19745916515426498,
982
+ "grad_norm": 10.386938095092773,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 2.7951,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.19891107078039927,
989
+ "grad_norm": 8.819989204406738,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 3.6493,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.20036297640653358,
996
+ "grad_norm": 9.565943717956543,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 3.5784,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.20181488203266787,
1003
+ "grad_norm": 7.251652717590332,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 3.5906,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.20326678765880218,
1010
+ "grad_norm": 6.240248203277588,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 2.4813,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.20471869328493647,
1017
+ "grad_norm": 8.464350700378418,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 2.9515,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.20617059891107078,
1024
+ "grad_norm": 5.84903621673584,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 1.6964,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.20762250453720507,
1031
+ "grad_norm": 4.5005059242248535,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 1.3032,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.20907441016333939,
1038
+ "grad_norm": 9.735710144042969,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 3.9053,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.21052631578947367,
1045
+ "grad_norm": 8.019299507141113,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 3.5871,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.211978221415608,
1052
+ "grad_norm": 7.978186130523682,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 2.0637,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.21343012704174227,
1059
+ "grad_norm": 8.015654563903809,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 4.5913,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2148820326678766,
1066
+ "grad_norm": 9.128483772277832,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 2.6751,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2163339382940109,
1073
+ "grad_norm": 9.646977424621582,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 3.4304,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.2177858439201452,
1080
+ "grad_norm": 7.943133354187012,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 3.3976,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.2177858439201452,
1087
+ "eval_loss": 2.125631093978882,
1088
+ "eval_runtime": 9.4544,
1089
+ "eval_samples_per_second": 30.674,
1090
+ "eval_steps_per_second": 15.337,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 2.77434637221888e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null