cilooor commited on
Commit
09be760
·
verified ·
1 Parent(s): 24f8671

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 sha256:8ac6c4baaf5a4dedccbb5d0ee3c4a935b07164bdab13c76c0b17af75fcf9edcf
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f9c561d26913b0d45756fcfafa8863a23122c66e0dbe7dbc82ffcc042b2537
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f4824398b19798b4ce658c79f89b1b5319d088d9a43ae16e9918eec8e6747b3
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9973fa49dd1818e61fab7b962848c47b97ec0a22af70fe2755a32ce360687c55
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30063c1786bea61bdde622638c6279790e0239b563d5fa59c5ecff53192b48b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741b188532d5ed7f83ef7d58a413d797deb4f38779f0427ddda8341b9145f402
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b0f0591a54513981f9045153a7608f989005ce4fb6ed2c798b085bae23c1094
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed88ff7cbe02e7c054abfce3510882248a01917e1eb8cf2c358f612dd7312357
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.833295226097107,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0019212480427285566,
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": 22.8,
732
  "eval_steps_per_second": 5.7,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.933753135058125e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8138833045959473,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0028818720640928345,
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": 22.8,
732
  "eval_steps_per_second": 5.7,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.001940460523155842,
737
+ "grad_norm": 0.38725751638412476,
738
+ "learning_rate": 4.797407629465648e-05,
739
+ "loss": 2.036,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0019596730035831276,
744
+ "grad_norm": 0.4056459665298462,
745
+ "learning_rate": 4.7231268960295003e-05,
746
+ "loss": 2.2175,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.001978885484010413,
751
+ "grad_norm": 0.6771987676620483,
752
+ "learning_rate": 4.648785161927887e-05,
753
+ "loss": 1.6623,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.001998097964437699,
758
+ "grad_norm": 1.075822353363037,
759
+ "learning_rate": 4.574402751448614e-05,
760
+ "loss": 1.1344,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0020173104448649843,
765
+ "grad_norm": 1.1966012716293335,
766
+ "learning_rate": 4.5e-05,
767
+ "loss": 1.2106,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0020365229252922697,
772
+ "grad_norm": 0.6514367461204529,
773
+ "learning_rate": 4.425597248551387e-05,
774
+ "loss": 2.4871,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0020557354057195555,
779
+ "grad_norm": 1.3281652927398682,
780
+ "learning_rate": 4.3512148380721134e-05,
781
+ "loss": 2.1116,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.002074947886146841,
786
+ "grad_norm": 1.0242716073989868,
787
+ "learning_rate": 4.2768731039704995e-05,
788
+ "loss": 1.9819,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0020941603665741264,
793
+ "grad_norm": 0.9406623840332031,
794
+ "learning_rate": 4.202592370534353e-05,
795
+ "loss": 2.2307,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0021133728470014122,
800
+ "grad_norm": 1.036744475364685,
801
+ "learning_rate": 4.128392945374505e-05,
802
+ "loss": 1.3772,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0021325853274286976,
807
+ "grad_norm": 1.084477186203003,
808
+ "learning_rate": 4.0542951138729184e-05,
809
+ "loss": 1.8637,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.002151797807855983,
814
+ "grad_norm": 1.1325368881225586,
815
+ "learning_rate": 3.980319133636863e-05,
816
+ "loss": 1.0554,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.002171010288283269,
821
+ "grad_norm": 1.1569682359695435,
822
+ "learning_rate": 3.9064852289606895e-05,
823
+ "loss": 1.6565,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0021902227687105543,
828
+ "grad_norm": 1.3950432538986206,
829
+ "learning_rate": 3.832813585296711e-05,
830
+ "loss": 0.3665,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0022094352491378397,
835
+ "grad_norm": 1.0858311653137207,
836
+ "learning_rate": 3.759324343736697e-05,
837
+ "loss": 1.1037,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0022286477295651256,
842
+ "grad_norm": 1.3634651899337769,
843
+ "learning_rate": 3.686037595505507e-05,
844
+ "loss": 1.5144,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.002247860209992411,
849
+ "grad_norm": 1.4642441272735596,
850
+ "learning_rate": 3.612973376468339e-05,
851
+ "loss": 1.4407,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0022670726904196964,
856
+ "grad_norm": 1.508213758468628,
857
+ "learning_rate": 3.54015166165314e-05,
858
+ "loss": 1.2446,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0022862851708469823,
863
+ "grad_norm": 1.3166296482086182,
864
+ "learning_rate": 3.4675923597896184e-05,
865
+ "loss": 1.8091,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0023054976512742677,
870
+ "grad_norm": 1.141366958618164,
871
+ "learning_rate": 3.395315307866404e-05,
872
+ "loss": 1.2671,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0023247101317015535,
877
+ "grad_norm": 1.3715970516204834,
878
+ "learning_rate": 3.3233402657078116e-05,
879
+ "loss": 1.0325,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.002343922612128839,
884
+ "grad_norm": 0.9950500130653381,
885
+ "learning_rate": 3.2516869105717005e-05,
886
+ "loss": 1.4616,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0023631350925561244,
891
+ "grad_norm": 1.3959550857543945,
892
+ "learning_rate": 3.1803748317699093e-05,
893
+ "loss": 1.3512,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0023823475729834102,
898
+ "grad_norm": 1.3552947044372559,
899
+ "learning_rate": 3.1094235253127374e-05,
900
+ "loss": 0.9966,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0024015600534106956,
905
+ "grad_norm": 1.4716287851333618,
906
+ "learning_rate": 3.038852388578925e-05,
907
+ "loss": 1.2362,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.002420772533837981,
912
+ "grad_norm": 1.1937332153320312,
913
+ "learning_rate": 2.9686807150126064e-05,
914
+ "loss": 1.6868,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.002439985014265267,
919
+ "grad_norm": 1.4279030561447144,
920
+ "learning_rate": 2.8989276888486755e-05,
921
+ "loss": 1.3592,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0024591974946925523,
926
+ "grad_norm": 1.4244630336761475,
927
+ "learning_rate": 2.829612379868006e-05,
928
+ "loss": 1.6008,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0024784099751198377,
933
+ "grad_norm": 1.6446768045425415,
934
+ "learning_rate": 2.760753738183966e-05,
935
+ "loss": 1.1883,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0024976224555471236,
940
+ "grad_norm": 1.3861147165298462,
941
+ "learning_rate": 2.6923705890616385e-05,
942
+ "loss": 1.2918,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.002516834935974409,
947
+ "grad_norm": 1.2332127094268799,
948
+ "learning_rate": 2.6244816277711943e-05,
949
+ "loss": 1.2566,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0025360474164016944,
954
+ "grad_norm": 1.2724624872207642,
955
+ "learning_rate": 2.5571054144767825e-05,
956
+ "loss": 0.9582,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0025552598968289803,
961
+ "grad_norm": 1.575805425643921,
962
+ "learning_rate": 2.4902603691623712e-05,
963
+ "loss": 1.3997,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0025744723772562657,
968
+ "grad_norm": 1.768161654472351,
969
+ "learning_rate": 2.4239647665959058e-05,
970
+ "loss": 1.0172,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.002593684857683551,
975
+ "grad_norm": 1.6644028425216675,
976
+ "learning_rate": 2.358236731333169e-05,
977
+ "loss": 1.5184,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.002612897338110837,
982
+ "grad_norm": 2.4780852794647217,
983
+ "learning_rate": 2.293094232762715e-05,
984
+ "loss": 1.5998,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0026321098185381224,
989
+ "grad_norm": 1.552331566810608,
990
+ "learning_rate": 2.2285550801932047e-05,
991
+ "loss": 0.9399,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.0026513222989654078,
996
+ "grad_norm": 1.4867897033691406,
997
+ "learning_rate": 2.164636917984533e-05,
998
+ "loss": 1.0078,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.0026705347793926936,
1003
+ "grad_norm": 2.0035929679870605,
1004
+ "learning_rate": 2.1013572207240293e-05,
1005
+ "loss": 1.6794,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.002689747259819979,
1010
+ "grad_norm": 1.5320886373519897,
1011
+ "learning_rate": 2.03873328844908e-05,
1012
+ "loss": 1.4663,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0027089597402472645,
1017
+ "grad_norm": 2.784316301345825,
1018
+ "learning_rate": 1.9767822419174733e-05,
1019
+ "loss": 1.6031,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0027281722206745503,
1024
+ "grad_norm": 1.9862154722213745,
1025
+ "learning_rate": 1.915521017926754e-05,
1026
+ "loss": 1.4249,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0027473847011018357,
1031
+ "grad_norm": 2.684689998626709,
1032
+ "learning_rate": 1.8549663646838714e-05,
1033
+ "loss": 1.3566,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.002766597181529121,
1038
+ "grad_norm": 2.400099277496338,
1039
+ "learning_rate": 1.7951348372263872e-05,
1040
+ "loss": 1.6717,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.002785809661956407,
1045
+ "grad_norm": 2.823960304260254,
1046
+ "learning_rate": 1.7360427928964948e-05,
1047
+ "loss": 2.1536,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0028050221423836924,
1052
+ "grad_norm": 2.5241665840148926,
1053
+ "learning_rate": 1.6777063868690835e-05,
1054
+ "loss": 2.198,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.002824234622810978,
1059
+ "grad_norm": 4.04758358001709,
1060
+ "learning_rate": 1.6201415677350752e-05,
1061
+ "loss": 2.2812,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0028434471032382637,
1066
+ "grad_norm": 3.2880547046661377,
1067
+ "learning_rate": 1.563364073141241e-05,
1068
+ "loss": 2.3492,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.002862659583665549,
1073
+ "grad_norm": 3.0113375186920166,
1074
+ "learning_rate": 1.5073894254876825e-05,
1075
+ "loss": 2.4835,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0028818720640928345,
1080
+ "grad_norm": 4.216464519500732,
1081
+ "learning_rate": 1.452232927684166e-05,
1082
+ "loss": 3.0384,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0028818720640928345,
1087
+ "eval_loss": 1.8138833045959473,
1088
+ "eval_runtime": 3841.3252,
1089
+ "eval_samples_per_second": 22.821,
1090
+ "eval_steps_per_second": 5.705,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.900629702587187e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null