adammandic87 commited on
Commit
f849034
·
verified ·
1 Parent(s): ce91d2c

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 sha256:540b43c27ce9d45f67e5362b6b4cfcbb10e6586ca874fac5db3612514de201fd
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35df2ac04757fc2484eec897923cf09fee52fe11145e75d6daded7d6e0604f2
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58a8f70b234248e16553fb2e2efbdc0c248b9900aa542270ae5d7046f520e5b3
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7794fd3a5dcd4d47b3aa584e252d74f75d6e0e06c7dce5dba07b783b433c301f
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1587726aec1f75f737018a73e7de2d0d5713390c50e5b1386177a35ec2977d5a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d380fb8adddb94901ede23d4bcc04dd248a3fa334878c53401d03fb2209d192b
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": 0.021831677764436196,
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": 10.609,
732
  "eval_steps_per_second": 5.307,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -750,7 +1108,7 @@
750
  "attributes": {}
751
  }
752
  },
753
- "total_flos": 6.563165450010624e+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": 0.0327475166466543,
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": 10.609,
732
  "eval_steps_per_second": 5.307,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.022049994542080557,
737
+ "grad_norm": 0.21762917935848236,
738
+ "learning_rate": 0.00010660905843256994,
739
+ "loss": 0.7735,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.022268311319724923,
744
+ "grad_norm": 0.18513105809688568,
745
+ "learning_rate": 0.00010495837546732224,
746
+ "loss": 0.7981,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.022486628097369284,
751
+ "grad_norm": 0.1725614219903946,
752
+ "learning_rate": 0.00010330633693173082,
753
+ "loss": 0.66,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.022704944875013646,
758
+ "grad_norm": 0.18261019885540009,
759
+ "learning_rate": 0.00010165339447663587,
760
+ "loss": 0.8389,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.022923261652658008,
765
+ "grad_norm": 0.16905616223812103,
766
+ "learning_rate": 0.0001,
767
+ "loss": 0.5165,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.02314157843030237,
772
+ "grad_norm": 0.18981021642684937,
773
+ "learning_rate": 9.834660552336415e-05,
774
+ "loss": 0.8955,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.02335989520794673,
779
+ "grad_norm": 0.18465036153793335,
780
+ "learning_rate": 9.669366306826919e-05,
781
+ "loss": 0.6604,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.023578211985591093,
786
+ "grad_norm": 0.1783265918493271,
787
+ "learning_rate": 9.504162453267777e-05,
788
+ "loss": 0.6334,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.023796528763235455,
793
+ "grad_norm": 0.16945728659629822,
794
+ "learning_rate": 9.339094156743007e-05,
795
+ "loss": 0.5026,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.024014845540879817,
800
+ "grad_norm": 0.16877439618110657,
801
+ "learning_rate": 9.174206545276677e-05,
802
+ "loss": 0.6765,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02423316231852418,
807
+ "grad_norm": 0.18142911791801453,
808
+ "learning_rate": 9.009544697495374e-05,
809
+ "loss": 0.6832,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02445147909616854,
814
+ "grad_norm": 0.17140087485313416,
815
+ "learning_rate": 8.845153630304139e-05,
816
+ "loss": 0.6352,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.024669795873812902,
821
+ "grad_norm": 0.16582410037517548,
822
+ "learning_rate": 8.681078286579311e-05,
823
+ "loss": 0.5553,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.024888112651457264,
828
+ "grad_norm": 0.15053234994411469,
829
+ "learning_rate": 8.517363522881579e-05,
830
+ "loss": 0.5002,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.025106429429101625,
835
+ "grad_norm": 0.17048825323581696,
836
+ "learning_rate": 8.35405409719266e-05,
837
+ "loss": 0.6109,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.025324746206745987,
842
+ "grad_norm": 0.16614414751529694,
843
+ "learning_rate": 8.191194656678904e-05,
844
+ "loss": 0.6749,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02554306298439035,
849
+ "grad_norm": 0.17033010721206665,
850
+ "learning_rate": 8.028829725485199e-05,
851
+ "loss": 0.5342,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.025761379762034714,
856
+ "grad_norm": 0.18463349342346191,
857
+ "learning_rate": 7.867003692562534e-05,
858
+ "loss": 0.7151,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.025979696539679076,
863
+ "grad_norm": 0.15648098289966583,
864
+ "learning_rate": 7.705760799532485e-05,
865
+ "loss": 0.5211,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.026198013317323438,
870
+ "grad_norm": 0.16885478794574738,
871
+ "learning_rate": 7.54514512859201e-05,
872
+ "loss": 0.6123,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0264163300949678,
877
+ "grad_norm": 0.16653332114219666,
878
+ "learning_rate": 7.385200590461803e-05,
879
+ "loss": 0.6589,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02663464687261216,
884
+ "grad_norm": 0.1621529459953308,
885
+ "learning_rate": 7.225970912381556e-05,
886
+ "loss": 0.5623,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.026852963650256523,
891
+ "grad_norm": 0.17834222316741943,
892
+ "learning_rate": 7.067499626155354e-05,
893
+ "loss": 0.5837,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.027071280427900885,
898
+ "grad_norm": 0.17469386756420135,
899
+ "learning_rate": 6.909830056250527e-05,
900
+ "loss": 0.7037,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.027289597205545246,
905
+ "grad_norm": 0.16732703149318695,
906
+ "learning_rate": 6.753005307953167e-05,
907
+ "loss": 0.6519,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.027507913983189608,
912
+ "grad_norm": 0.19885458052158356,
913
+ "learning_rate": 6.59706825558357e-05,
914
+ "loss": 0.637,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02772623076083397,
919
+ "grad_norm": 0.15952806174755096,
920
+ "learning_rate": 6.442061530774834e-05,
921
+ "loss": 0.5294,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02794454753847833,
926
+ "grad_norm": 0.18024499714374542,
927
+ "learning_rate": 6.28802751081779e-05,
928
+ "loss": 0.7163,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.028162864316122693,
933
+ "grad_norm": 0.1813889443874359,
934
+ "learning_rate": 6.135008307075481e-05,
935
+ "loss": 0.8399,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.028381181093767055,
940
+ "grad_norm": 0.16543258726596832,
941
+ "learning_rate": 5.983045753470308e-05,
942
+ "loss": 0.6442,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.028599497871411417,
947
+ "grad_norm": 0.21711844205856323,
948
+ "learning_rate": 5.832181395047098e-05,
949
+ "loss": 0.9936,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.02881781464905578,
954
+ "grad_norm": 0.16442720592021942,
955
+ "learning_rate": 5.6824564766150726e-05,
956
+ "loss": 0.5848,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02903613142670014,
961
+ "grad_norm": 0.16723956167697906,
962
+ "learning_rate": 5.533911931471936e-05,
963
+ "loss": 0.6755,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.029254448204344505,
968
+ "grad_norm": 0.16711710393428802,
969
+ "learning_rate": 5.386588370213124e-05,
970
+ "loss": 0.6657,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.029472764981988867,
975
+ "grad_norm": 0.16483482718467712,
976
+ "learning_rate": 5.240526069629265e-05,
977
+ "loss": 0.6668,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02969108175963323,
982
+ "grad_norm": 0.17765454947948456,
983
+ "learning_rate": 5.095764961694922e-05,
984
+ "loss": 0.6791,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02990939853727759,
989
+ "grad_norm": 0.18251171708106995,
990
+ "learning_rate": 4.952344622651566e-05,
991
+ "loss": 0.7367,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.030127715314921952,
996
+ "grad_norm": 0.17135152220726013,
997
+ "learning_rate": 4.810304262187852e-05,
998
+ "loss": 0.6704,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.030346032092566314,
1003
+ "grad_norm": 0.194648876786232,
1004
+ "learning_rate": 4.669682712720065e-05,
1005
+ "loss": 0.9007,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.030564348870210676,
1010
+ "grad_norm": 0.14134380221366882,
1011
+ "learning_rate": 4.530518418775733e-05,
1012
+ "loss": 0.4324,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.030782665647855038,
1017
+ "grad_norm": 0.16082902252674103,
1018
+ "learning_rate": 4.392849426483274e-05,
1019
+ "loss": 0.5531,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0310009824254994,
1024
+ "grad_norm": 0.185900017619133,
1025
+ "learning_rate": 4.256713373170564e-05,
1026
+ "loss": 0.8044,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03121929920314376,
1031
+ "grad_norm": 0.16822083294391632,
1032
+ "learning_rate": 4.12214747707527e-05,
1033
+ "loss": 0.63,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.031437615980788126,
1038
+ "grad_norm": 0.1961585134267807,
1039
+ "learning_rate": 3.9891885271697496e-05,
1040
+ "loss": 0.7769,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03165593275843249,
1045
+ "grad_norm": 0.17126162350177765,
1046
+ "learning_rate": 3.857872873103322e-05,
1047
+ "loss": 0.5417,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03187424953607685,
1052
+ "grad_norm": 0.17973680794239044,
1053
+ "learning_rate": 3.7282364152646297e-05,
1054
+ "loss": 0.6837,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03209256631372121,
1059
+ "grad_norm": 0.18085865676403046,
1060
+ "learning_rate": 3.600314594966834e-05,
1061
+ "loss": 0.7359,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03231088309136557,
1066
+ "grad_norm": 0.1475389152765274,
1067
+ "learning_rate": 3.4741423847583134e-05,
1068
+ "loss": 0.4654,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.032529199869009935,
1073
+ "grad_norm": 0.1810745894908905,
1074
+ "learning_rate": 3.349754278861517e-05,
1075
+ "loss": 0.7939,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0327475166466543,
1080
+ "grad_norm": 0.18114720284938812,
1081
+ "learning_rate": 3.227184283742591e-05,
1082
+ "loss": 0.6863,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0327475166466543,
1087
+ "eval_loss": 0.6545336842536926,
1088
+ "eval_runtime": 181.8183,
1089
+ "eval_samples_per_second": 10.609,
1090
+ "eval_steps_per_second": 5.307,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1108
  "attributes": {}
1109
  }
1110
  },
1111
+ "total_flos": 9.861238540468224e+16,
1112
  "train_batch_size": 2,
1113
  "trial_name": null,
1114
  "trial_params": null