lesso commited on
Commit
31b26db
·
verified ·
1 Parent(s): 8d147e5

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 sha256:51bda91e3c7e83bdd5ec060e8c8b53a011be6565c476c602a5f732325657c660
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ef959bc49972065f0eb1579922e75b24031ac84581f34f6439470ee3fb8110
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48a83b0a99f0f095c3c632878deef6b3d7118417a2017e999d52fd7ecee5a75a
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b77d913691758bd3f549babcdbd405bb3da28e97e97463214db348578b489911
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba95427e7241c1dfd47297f17101d1daf28730b332855a47bb55cb5da7c6641
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2e0d4afaeb4f4fc1a329ad0ad6d1305abfdebb4c656a7d8d60d6b12b349036
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c41bb450efe89fd65fecb2593939b817f9b2794a5d87a632ad90e5ebc9b592b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a1533051e4bee653afc683a4359c329f95831c0354ae8442616cabf80d0caa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4087783396244049,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0010475152937232883,
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": 34.46,
732
  "eval_steps_per_second": 8.615,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1941781210988544.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3863369822502136,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0015712729405849325,
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": 34.46,
732
  "eval_steps_per_second": 8.615,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0010579904466605213,
737
+ "grad_norm": 1.2196251153945923,
738
+ "learning_rate": 5.2157368421052626e-05,
739
+ "loss": 0.3787,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.001068465599597754,
744
+ "grad_norm": 1.1273436546325684,
745
+ "learning_rate": 5.163052631578947e-05,
746
+ "loss": 0.4126,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.001078940752534987,
751
+ "grad_norm": 1.3024041652679443,
752
+ "learning_rate": 5.110368421052632e-05,
753
+ "loss": 0.4315,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0010894159054722198,
758
+ "grad_norm": 0.8069114089012146,
759
+ "learning_rate": 5.057684210526316e-05,
760
+ "loss": 0.3689,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0010998910584094528,
765
+ "grad_norm": 1.1076774597167969,
766
+ "learning_rate": 5.005e-05,
767
+ "loss": 0.3951,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0011103662113466856,
772
+ "grad_norm": 1.0082478523254395,
773
+ "learning_rate": 4.9523157894736836e-05,
774
+ "loss": 0.3647,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0011208413642839186,
779
+ "grad_norm": 1.247436761856079,
780
+ "learning_rate": 4.899631578947368e-05,
781
+ "loss": 0.428,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0011313165172211514,
786
+ "grad_norm": 0.9683943390846252,
787
+ "learning_rate": 4.846947368421052e-05,
788
+ "loss": 0.3885,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0011417916701583844,
793
+ "grad_norm": 1.249470591545105,
794
+ "learning_rate": 4.794263157894737e-05,
795
+ "loss": 0.4012,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0011522668230956172,
800
+ "grad_norm": 1.2975919246673584,
801
+ "learning_rate": 4.7415789473684206e-05,
802
+ "loss": 0.4242,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0011627419760328501,
807
+ "grad_norm": 1.357737421989441,
808
+ "learning_rate": 4.688894736842105e-05,
809
+ "loss": 0.4239,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.001173217128970083,
814
+ "grad_norm": 0.9484228491783142,
815
+ "learning_rate": 4.636210526315789e-05,
816
+ "loss": 0.398,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.001183692281907316,
821
+ "grad_norm": 1.8374979496002197,
822
+ "learning_rate": 4.583526315789473e-05,
823
+ "loss": 0.4023,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0011941674348445487,
828
+ "grad_norm": 0.8284303545951843,
829
+ "learning_rate": 4.530842105263158e-05,
830
+ "loss": 0.3575,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0012046425877817817,
835
+ "grad_norm": 1.5431602001190186,
836
+ "learning_rate": 4.4781578947368416e-05,
837
+ "loss": 0.4184,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0012151177407190145,
842
+ "grad_norm": 2.5418710708618164,
843
+ "learning_rate": 4.425473684210526e-05,
844
+ "loss": 0.3906,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0012255928936562475,
849
+ "grad_norm": 1.1935153007507324,
850
+ "learning_rate": 4.372789473684211e-05,
851
+ "loss": 0.4312,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0012360680465934803,
856
+ "grad_norm": 1.3094145059585571,
857
+ "learning_rate": 4.320105263157895e-05,
858
+ "loss": 0.4287,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.001246543199530713,
863
+ "grad_norm": 1.5560877323150635,
864
+ "learning_rate": 4.2674210526315786e-05,
865
+ "loss": 0.3867,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.001257018352467946,
870
+ "grad_norm": 1.892146348953247,
871
+ "learning_rate": 4.2147368421052626e-05,
872
+ "loss": 0.4283,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0012674935054051788,
877
+ "grad_norm": 1.1117372512817383,
878
+ "learning_rate": 4.162052631578947e-05,
879
+ "loss": 0.4011,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0012779686583424118,
884
+ "grad_norm": 0.887161374092102,
885
+ "learning_rate": 4.109368421052631e-05,
886
+ "loss": 0.3982,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0012884438112796446,
891
+ "grad_norm": 2.119391441345215,
892
+ "learning_rate": 4.056684210526316e-05,
893
+ "loss": 0.4202,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0012989189642168776,
898
+ "grad_norm": 1.4735006093978882,
899
+ "learning_rate": 4.004e-05,
900
+ "loss": 0.4131,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0013093941171541104,
905
+ "grad_norm": 1.1728277206420898,
906
+ "learning_rate": 3.951315789473684e-05,
907
+ "loss": 0.4078,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0013198692700913434,
912
+ "grad_norm": 0.7051212787628174,
913
+ "learning_rate": 3.898631578947368e-05,
914
+ "loss": 0.3675,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0013303444230285762,
919
+ "grad_norm": 1.1503040790557861,
920
+ "learning_rate": 3.845947368421052e-05,
921
+ "loss": 0.377,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0013408195759658092,
926
+ "grad_norm": 0.9245353937149048,
927
+ "learning_rate": 3.7932631578947367e-05,
928
+ "loss": 0.4042,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.001351294728903042,
933
+ "grad_norm": 0.8474845290184021,
934
+ "learning_rate": 3.7405789473684206e-05,
935
+ "loss": 0.388,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.001361769881840275,
940
+ "grad_norm": 1.3868615627288818,
941
+ "learning_rate": 3.6878947368421045e-05,
942
+ "loss": 0.4165,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0013722450347775077,
947
+ "grad_norm": 0.7195939421653748,
948
+ "learning_rate": 3.635210526315789e-05,
949
+ "loss": 0.3945,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0013827201877147407,
954
+ "grad_norm": 0.6076641082763672,
955
+ "learning_rate": 3.582526315789474e-05,
956
+ "loss": 0.3685,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0013931953406519735,
961
+ "grad_norm": 1.5683972835540771,
962
+ "learning_rate": 3.5298421052631576e-05,
963
+ "loss": 0.4105,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0014036704935892065,
968
+ "grad_norm": 1.4858858585357666,
969
+ "learning_rate": 3.477157894736842e-05,
970
+ "loss": 0.4079,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0014141456465264393,
975
+ "grad_norm": 0.8402929306030273,
976
+ "learning_rate": 3.424473684210526e-05,
977
+ "loss": 0.3853,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0014246207994636723,
982
+ "grad_norm": 1.1739568710327148,
983
+ "learning_rate": 3.37178947368421e-05,
984
+ "loss": 0.4135,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.001435095952400905,
989
+ "grad_norm": 0.8241525888442993,
990
+ "learning_rate": 3.319105263157894e-05,
991
+ "loss": 0.3691,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.0014455711053381378,
996
+ "grad_norm": 1.062759518623352,
997
+ "learning_rate": 3.2664210526315786e-05,
998
+ "loss": 0.3906,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.0014560462582753708,
1003
+ "grad_norm": 1.0611199140548706,
1004
+ "learning_rate": 3.213736842105263e-05,
1005
+ "loss": 0.388,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0014665214112126036,
1010
+ "grad_norm": 1.0666338205337524,
1011
+ "learning_rate": 3.161052631578947e-05,
1012
+ "loss": 0.3855,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0014769965641498366,
1017
+ "grad_norm": 1.0595502853393555,
1018
+ "learning_rate": 3.108368421052632e-05,
1019
+ "loss": 0.3878,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0014874717170870694,
1024
+ "grad_norm": 1.0443916320800781,
1025
+ "learning_rate": 3.0556842105263156e-05,
1026
+ "loss": 0.3801,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0014979468700243024,
1031
+ "grad_norm": 1.820534586906433,
1032
+ "learning_rate": 3.0029999999999995e-05,
1033
+ "loss": 0.4207,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0015084220229615352,
1038
+ "grad_norm": 1.2642821073532104,
1039
+ "learning_rate": 2.9503157894736838e-05,
1040
+ "loss": 0.3682,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0015188971758987682,
1045
+ "grad_norm": 0.946820855140686,
1046
+ "learning_rate": 2.8976315789473684e-05,
1047
+ "loss": 0.3733,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.001529372328836001,
1052
+ "grad_norm": 0.8744164109230042,
1053
+ "learning_rate": 2.8449473684210523e-05,
1054
+ "loss": 0.3617,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.001539847481773234,
1059
+ "grad_norm": 0.8865841031074524,
1060
+ "learning_rate": 2.7922631578947366e-05,
1061
+ "loss": 0.3892,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0015503226347104667,
1066
+ "grad_norm": 1.0649254322052002,
1067
+ "learning_rate": 2.7395789473684212e-05,
1068
+ "loss": 0.3874,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0015607977876476997,
1073
+ "grad_norm": 0.8309904336929321,
1074
+ "learning_rate": 2.686894736842105e-05,
1075
+ "loss": 0.3948,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0015712729405849325,
1080
+ "grad_norm": 1.3515825271606445,
1081
+ "learning_rate": 2.634210526315789e-05,
1082
+ "loss": 0.3902,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0015712729405849325,
1087
+ "eval_loss": 0.3863369822502136,
1088
+ "eval_runtime": 1164.8786,
1089
+ "eval_samples_per_second": 34.507,
1090
+ "eval_steps_per_second": 8.627,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2907841514962944.0,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null