adammandic87 commited on
Commit
01c6af9
·
verified ·
1 Parent(s): 92a0eb3

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 sha256:5baaa3e55613e98b43f99d3fbbf46bb4df7aff5930c32a4aa176a54b268528ff
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc93d1f13a2a8f1f8245507fcd8ae394247e580c6c16202925f7c687618353f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ddb6206168f55daf70cc2a5467f9a509e509b5e2c0c34e4ebcbb3506640848c
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01f81e1868393f25da4f8e8af72b4bc3a18d778bfb7e2c18ea0c612eeebb645
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e38b43bb216852b411c1d270f1be8fb468fb40b1ffedbc6087e027f8c704135f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04e377c8bc5e1c0c621fd1ae7bf7a34353c940aacfa57010c4d302185068e55c
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": 0.14732965009208104,
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": 30.367,
732
  "eval_steps_per_second": 15.183,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 1.6368929882505216e+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": 0.22099447513812154,
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": 30.367,
732
  "eval_steps_per_second": 15.183,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.14880294659300183,
737
+ "grad_norm": 7.7546186447143555,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 7.1284,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.15027624309392265,
744
+ "grad_norm": 8.040283203125,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 7.7712,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.15174953959484347,
751
+ "grad_norm": 5.6713547706604,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 5.3149,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.15322283609576426,
758
+ "grad_norm": 7.573396682739258,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 8.7858,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.15469613259668508,
765
+ "grad_norm": 9.673140525817871,
766
+ "learning_rate": 0.0001,
767
+ "loss": 7.4904,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1561694290976059,
772
+ "grad_norm": 13.609859466552734,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 9.5067,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1576427255985267,
779
+ "grad_norm": 9.656366348266602,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 10.8401,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1591160220994475,
786
+ "grad_norm": 12.622513771057129,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 7.4235,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.16058931860036832,
793
+ "grad_norm": 6.947592258453369,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 8.8876,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.16206261510128914,
800
+ "grad_norm": 7.011374473571777,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 5.4014,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.16353591160220995,
807
+ "grad_norm": 4.517526626586914,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 5.814,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.16500920810313074,
814
+ "grad_norm": 6.089804172515869,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 6.8508,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.16648250460405156,
821
+ "grad_norm": 10.510293006896973,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 9.7658,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.16795580110497238,
828
+ "grad_norm": 9.174927711486816,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 7.1456,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1694290976058932,
835
+ "grad_norm": 7.33340311050415,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 6.902,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.170902394106814,
842
+ "grad_norm": 6.4531779289245605,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 6.6226,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1723756906077348,
849
+ "grad_norm": 9.962913513183594,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 9.6444,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.17384898710865562,
856
+ "grad_norm": 5.590907573699951,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 7.2986,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.17532228360957644,
863
+ "grad_norm": 10.6129150390625,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 7.5536,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.17679558011049723,
870
+ "grad_norm": 14.160097122192383,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 12.2425,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.17826887661141805,
877
+ "grad_norm": 10.54971694946289,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 6.7272,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.17974217311233887,
884
+ "grad_norm": 6.65580415725708,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 6.8475,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.18121546961325966,
891
+ "grad_norm": 10.194478034973145,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 8.6189,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.18268876611418047,
898
+ "grad_norm": 11.780241012573242,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 8.392,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1841620626151013,
905
+ "grad_norm": 6.544031143188477,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 7.9356,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1856353591160221,
912
+ "grad_norm": 5.778688430786133,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 4.8296,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1871086556169429,
919
+ "grad_norm": 13.133682250976562,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 8.4469,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.18858195211786372,
926
+ "grad_norm": 5.862144947052002,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 5.7135,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.19005524861878453,
933
+ "grad_norm": 5.824400901794434,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 7.4102,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.19152854511970535,
940
+ "grad_norm": 7.972049713134766,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 7.9903,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.19300184162062614,
947
+ "grad_norm": 7.148801803588867,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 4.9407,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.19447513812154696,
954
+ "grad_norm": 4.160274028778076,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 7.0311,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.19594843462246778,
961
+ "grad_norm": 4.829346656799316,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 5.5874,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1974217311233886,
968
+ "grad_norm": 8.297733306884766,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 6.3769,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.19889502762430938,
975
+ "grad_norm": 5.839636325836182,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 6.8749,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2003683241252302,
982
+ "grad_norm": 7.078559398651123,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 6.4378,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.20184162062615102,
989
+ "grad_norm": 5.329637050628662,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 6.1027,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.20331491712707184,
996
+ "grad_norm": 10.604938507080078,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 9.6319,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.20478821362799263,
1003
+ "grad_norm": 10.23065185546875,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 10.1313,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.20626151012891344,
1010
+ "grad_norm": 14.528596878051758,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 8.1347,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.20773480662983426,
1017
+ "grad_norm": 5.988021373748779,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 8.9566,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.20920810313075505,
1024
+ "grad_norm": 13.86946964263916,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 7.2571,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.21068139963167587,
1031
+ "grad_norm": 8.190982818603516,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 6.508,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2121546961325967,
1038
+ "grad_norm": 8.50158405303955,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 5.1829,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2136279926335175,
1045
+ "grad_norm": 9.470782279968262,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 6.3869,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2151012891344383,
1052
+ "grad_norm": 9.785574913024902,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 7.6541,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2165745856353591,
1059
+ "grad_norm": 5.911442756652832,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 5.7766,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.21804788213627993,
1066
+ "grad_norm": 5.854257583618164,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 4.5367,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.21952117863720075,
1073
+ "grad_norm": 12.969705581665039,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 8.9383,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.22099447513812154,
1080
+ "grad_norm": 9.376482963562012,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 9.8813,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.22099447513812154,
1087
+ "eval_loss": 1.8338268995285034,
1088
+ "eval_runtime": 9.4611,
1089
+ "eval_samples_per_second": 30.229,
1090
+ "eval_steps_per_second": 15.115,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 2.463483228585984e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null