adammandic87 commited on
Commit
a4a198d
·
verified ·
1 Parent(s): 12d7c7a

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 sha256:67fb7cf3f03225341f706810efc14dc0275b281834e7280fd701b66271ef466b
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe0258f51cba9473425f5af36cbc1e58dfc7f320b17c7343e9d9db1d0d2636e
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20af0204ba26215eeae779f5c296c8c25c39f674a67417809b0243c2f5da778f
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7cc924d2ad84a864c450c1a0fb17974279afe42a38df73fa8c5a110a6e8e94
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be5afc39674e7e298ab83def8baadc99e8bd4d16cc9154de0ed8e193aa716642
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd9f9263dbc26372a7918f84d2f4dd14b1a917732ead01427739fe885cff62d
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": 0.016526194017517766,
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": 61.576,
732
  "eval_steps_per_second": 30.788,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 2641052175433728.0,
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": 0.02478929102627665,
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": 61.576,
732
  "eval_steps_per_second": 30.788,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.016691455957692943,
737
+ "grad_norm": 0.5702753663063049,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 1.553,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.01685671789786812,
744
+ "grad_norm": 0.5369312167167664,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 1.5788,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.017021979838043298,
751
+ "grad_norm": 0.4222307801246643,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 1.5621,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.017187241778218475,
758
+ "grad_norm": 0.5532189607620239,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 1.4918,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.017352503718393655,
765
+ "grad_norm": 0.7070478796958923,
766
+ "learning_rate": 0.0001,
767
+ "loss": 1.623,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.017517765658568833,
772
+ "grad_norm": 0.6058260202407837,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 1.5853,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.01768302759874401,
779
+ "grad_norm": 0.3898620009422302,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 1.5686,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.017848289538919187,
786
+ "grad_norm": 0.5478883385658264,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 1.5867,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.018013551479094364,
793
+ "grad_norm": 0.47779756784439087,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 1.4921,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01817881341926954,
800
+ "grad_norm": 0.8399332165718079,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 1.6164,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01834407535944472,
807
+ "grad_norm": 0.5388432145118713,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 1.6265,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0185093372996199,
814
+ "grad_norm": 0.5579386949539185,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 1.3753,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.018674599239795076,
821
+ "grad_norm": 0.40802866220474243,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 1.3763,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.018839861179970253,
828
+ "grad_norm": 0.552657425403595,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 1.3575,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01900512312014543,
835
+ "grad_norm": 0.8166072964668274,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 1.6855,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.019170385060320608,
842
+ "grad_norm": 0.8131512999534607,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 1.8306,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.019335647000495785,
849
+ "grad_norm": 0.42067432403564453,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 1.5663,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.019500908940670962,
856
+ "grad_norm": 0.5358683466911316,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 1.7055,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019666170880846143,
863
+ "grad_norm": 0.6525923013687134,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 1.3311,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01983143282102132,
870
+ "grad_norm": 0.6140702962875366,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 1.7929,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.019996694761196497,
877
+ "grad_norm": 0.6280947923660278,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 1.7175,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.020161956701371674,
884
+ "grad_norm": 0.686147153377533,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 1.6716,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.02032721864154685,
891
+ "grad_norm": 0.5507709383964539,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 1.3555,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02049248058172203,
898
+ "grad_norm": 0.5885040163993835,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 1.3161,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020657742521897206,
905
+ "grad_norm": 0.4891628623008728,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 1.4675,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020823004462072386,
912
+ "grad_norm": 0.8562346696853638,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 1.5319,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.020988266402247564,
919
+ "grad_norm": 0.676142156124115,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 1.4428,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02115352834242274,
926
+ "grad_norm": 0.5416271686553955,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 1.4903,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.021318790282597918,
933
+ "grad_norm": 0.4796253442764282,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 1.4259,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.021484052222773095,
940
+ "grad_norm": 0.4909597635269165,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 1.3397,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.021649314162948272,
947
+ "grad_norm": 0.5054872035980225,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 1.6404,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02181457610312345,
954
+ "grad_norm": 0.6180214285850525,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 1.782,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.021979838043298627,
961
+ "grad_norm": 0.657794177532196,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 1.5387,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.022145099983473807,
968
+ "grad_norm": 0.5247397422790527,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 1.4955,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.022310361923648984,
975
+ "grad_norm": 0.5147126913070679,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 1.4354,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02247562386382416,
982
+ "grad_norm": 0.4486481249332428,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 1.3835,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02264088580399934,
989
+ "grad_norm": 0.4644688367843628,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 1.5637,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.022806147744174516,
996
+ "grad_norm": 0.7985265254974365,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 1.4771,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022971409684349693,
1003
+ "grad_norm": 0.43993720412254333,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 1.4761,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02313667162452487,
1010
+ "grad_norm": 0.597682535648346,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 1.5009,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02330193356470005,
1017
+ "grad_norm": 0.46359845995903015,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 1.4938,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.023467195504875228,
1024
+ "grad_norm": 0.5101354718208313,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 1.4861,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.023632457445050405,
1031
+ "grad_norm": 0.5093466639518738,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 1.4807,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.023797719385225583,
1038
+ "grad_norm": 0.5195640325546265,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 1.61,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.02396298132540076,
1045
+ "grad_norm": 0.500438392162323,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 1.4983,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.024128243265575937,
1052
+ "grad_norm": 0.4799457788467407,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 1.3141,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.024293505205751114,
1059
+ "grad_norm": 0.5169847011566162,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 1.7889,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.024458767145926295,
1066
+ "grad_norm": 0.49090850353240967,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 1.6389,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.024624029086101472,
1073
+ "grad_norm": 0.6075248122215271,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 1.5403,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02478929102627665,
1080
+ "grad_norm": 0.5191071033477783,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 1.3608,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02478929102627665,
1087
+ "eval_loss": 1.5432822704315186,
1088
+ "eval_runtime": 41.6111,
1089
+ "eval_samples_per_second": 61.234,
1090
+ "eval_steps_per_second": 30.617,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 3945591264509952.0,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null