adammandic87 commited on
Commit
929cecb
·
verified ·
1 Parent(s): 9217219

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 sha256:72cabe2e50e47855b731f0b59856370478fdef3d918034c6210d60d4582ad692
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb024c15a7553c9000020231a7cec1cd8bffb5ddfdf61368baa8efa85f70b5c8
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3408330e006c0fc4057b7efb470b7caf087333ffec2cf54fa773c94478d5eb71
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f11ffbb6b1be04e1d893c75bb30bad865cd6cb3ea9e1851a5b4654d086d6a4c
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfe54cf7ac438aee0473d5efd8220205ccbf506fefb5b1843674ee2910182d68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2fb8dc2a85d0cc09b3d729bf71a8da974bf095341dbe298d83978634de38d32
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": 0.06754474839581223,
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": 269.593,
732
  "eval_steps_per_second": 134.797,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 16405915238400.0,
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": 0.10131712259371833,
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": 269.593,
732
  "eval_steps_per_second": 134.797,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06822019587977035,
737
+ "grad_norm": 0.11731832474470139,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 10.6064,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06889564336372847,
744
+ "grad_norm": 0.1060105562210083,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 10.6059,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06957109084768659,
751
+ "grad_norm": 0.12271567434072495,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 10.6046,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.07024653833164471,
758
+ "grad_norm": 0.1422068178653717,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 10.6122,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07092198581560284,
765
+ "grad_norm": 0.123976930975914,
766
+ "learning_rate": 0.0001,
767
+ "loss": 10.6086,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07159743329956096,
772
+ "grad_norm": 0.11725173145532608,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 10.6312,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07227288078351908,
779
+ "grad_norm": 0.13431864976882935,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 10.6129,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0729483282674772,
786
+ "grad_norm": 0.10811913758516312,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 10.6102,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07362377575143532,
793
+ "grad_norm": 0.1448288857936859,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 10.6097,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07429922323539345,
800
+ "grad_norm": 0.14231544733047485,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 10.6149,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07497467071935157,
807
+ "grad_norm": 0.11350355297327042,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 10.6123,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07565011820330969,
814
+ "grad_norm": 0.11213658004999161,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 10.6059,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07632556568726781,
821
+ "grad_norm": 0.12278730422258377,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 10.6049,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07700101317122594,
828
+ "grad_norm": 0.15146122872829437,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 10.6104,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07767646065518406,
835
+ "grad_norm": 0.11578516662120819,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 10.6276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07835190813914218,
842
+ "grad_norm": 0.13298995792865753,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 10.6115,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0790273556231003,
849
+ "grad_norm": 0.13557101786136627,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 10.6083,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07970280310705842,
856
+ "grad_norm": 0.12159471958875656,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 10.6037,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08037825059101655,
863
+ "grad_norm": 0.12765274941921234,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 10.6016,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08105369807497467,
870
+ "grad_norm": 0.11235444992780685,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 10.6065,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.08172914555893279,
877
+ "grad_norm": 0.14903466403484344,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 10.5995,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.08240459304289091,
884
+ "grad_norm": 0.10130941867828369,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 10.6095,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08308004052684904,
891
+ "grad_norm": 0.1442113071680069,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 10.6024,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.08375548801080716,
898
+ "grad_norm": 0.14047802984714508,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 10.6104,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08443093549476528,
905
+ "grad_norm": 0.1147422268986702,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 10.6125,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0851063829787234,
912
+ "grad_norm": 0.11507318913936615,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 10.6038,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08578183046268152,
919
+ "grad_norm": 0.13589414954185486,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 10.6044,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08645727794663965,
926
+ "grad_norm": 0.13625499606132507,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 10.6058,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08713272543059777,
933
+ "grad_norm": 0.12005976587533951,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 10.62,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0878081729145559,
940
+ "grad_norm": 0.11311294883489609,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 10.6092,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08848362039851401,
947
+ "grad_norm": 0.13194864988327026,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 10.5994,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08915906788247213,
954
+ "grad_norm": 0.12505017220973969,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 10.6069,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08983451536643026,
961
+ "grad_norm": 0.13057582080364227,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 10.5994,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.09050996285038838,
968
+ "grad_norm": 0.17442747950553894,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 10.6025,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0911854103343465,
975
+ "grad_norm": 0.12355850636959076,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 10.6065,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.09186085781830462,
982
+ "grad_norm": 0.13733559846878052,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 10.5974,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.09253630530226276,
989
+ "grad_norm": 0.14686278998851776,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 10.5941,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09321175278622088,
996
+ "grad_norm": 0.13458283245563507,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 10.5959,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.093887200270179,
1003
+ "grad_norm": 0.1384890228509903,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 10.6081,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09456264775413711,
1010
+ "grad_norm": 0.15113620460033417,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 10.6194,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09523809523809523,
1017
+ "grad_norm": 0.14613160490989685,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 10.6113,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09591354272205337,
1024
+ "grad_norm": 0.12903277575969696,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 10.6009,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09658899020601149,
1031
+ "grad_norm": 0.15327778458595276,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 10.5978,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0972644376899696,
1038
+ "grad_norm": 0.14414553344249725,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 10.5922,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09793988517392772,
1045
+ "grad_norm": 0.15006524324417114,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 10.6253,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09861533265788584,
1052
+ "grad_norm": 0.14634265005588531,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 10.6011,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09929078014184398,
1059
+ "grad_norm": 0.14320406317710876,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 10.5892,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0999662276258021,
1066
+ "grad_norm": 0.14602705836296082,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 10.5927,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.10064167510976021,
1073
+ "grad_norm": 0.14189378917217255,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 10.5985,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.10131712259371833,
1080
+ "grad_norm": 0.15539740025997162,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 10.5968,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.10131712259371833,
1087
+ "eval_loss": 10.599814414978027,
1088
+ "eval_runtime": 2.2579,
1089
+ "eval_samples_per_second": 276.357,
1090
+ "eval_steps_per_second": 138.179,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 24608872857600.0,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null