aleegis11 commited on
Commit
1c597e5
·
verified ·
1 Parent(s): f366d1d

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:b93d17e7a352c90cb2dba135c2f9aeded2d47ce2c0adfbdfde70cdbf5eeef59f
3
  size 54285928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c50d66b0565a14c67c92a88eaf0f5e6e7eda185fd78127743c4de4ce56716d
3
  size 54285928
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64a206df4c1fb3b202814e9a4591fa2be1c89cea6c9e396504cef50019f53b14
3
  size 27753594
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a8bc1715ea8869d84c709be0ccb19fcd7ddb0efe5d2606f34ec06b57f381f4f
3
  size 27753594
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e5baae50274f42dfb92f246aa1f9b40128b9af5eed85ca8330cefdde1f549ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6907c392381755bc101825888b977ebce798bc3a058179dfd07f06dd17df8a1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 5.082364082336426,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006414676780473724,
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": 149.203,
732
  "eval_steps_per_second": 37.301,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2976789823488000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.5528883934021,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009622015170710586,
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": 149.203,
732
  "eval_steps_per_second": 37.301,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.006478823548278461,
737
+ "grad_norm": 14.663159370422363,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 5.0622,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006542970316083198,
744
+ "grad_norm": 16.544841766357422,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 5.3057,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006607117083887936,
751
+ "grad_norm": 15.879215240478516,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 5.1625,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006671263851692673,
758
+ "grad_norm": 14.463156700134277,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 5.1542,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.00673541061949741,
765
+ "grad_norm": 13.046357154846191,
766
+ "learning_rate": 5e-05,
767
+ "loss": 4.8398,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.006799557387302147,
772
+ "grad_norm": 11.176506042480469,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.6716,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006863704155106885,
779
+ "grad_norm": 8.23073673248291,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 4.6304,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.006927850922911621,
786
+ "grad_norm": 6.0302734375,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 4.451,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006991997690716359,
793
+ "grad_norm": 3.8446044921875,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.3728,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007056144458521096,
800
+ "grad_norm": 1.688712239265442,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 4.2718,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.007120291226325834,
807
+ "grad_norm": 0.8822144865989685,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 4.3909,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0071844379941305705,
814
+ "grad_norm": 0.9888668656349182,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 4.3215,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.007248584761935308,
821
+ "grad_norm": 1.142039179801941,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 4.2201,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0073127315297400455,
828
+ "grad_norm": 1.1784989833831787,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.3019,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007376878297544782,
835
+ "grad_norm": 1.1900745630264282,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.2193,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.00744102506534952,
842
+ "grad_norm": 1.2521610260009766,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 4.1634,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007505171833154257,
849
+ "grad_norm": 1.2006127834320068,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.2993,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007569318600958995,
856
+ "grad_norm": 1.3783690929412842,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.3544,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007633465368763731,
863
+ "grad_norm": 1.1826130151748657,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.2801,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007697612136568469,
870
+ "grad_norm": 1.212864637374878,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.4208,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007761758904373206,
877
+ "grad_norm": 1.213317632675171,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.4495,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007825905672177943,
884
+ "grad_norm": 1.2609578371047974,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.4031,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.00789005243998268,
891
+ "grad_norm": 1.1333434581756592,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 4.3654,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.007954199207787418,
898
+ "grad_norm": 1.1164824962615967,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.4081,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008018345975592155,
905
+ "grad_norm": 1.0088897943496704,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.4174,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008082492743396893,
912
+ "grad_norm": 1.0312213897705078,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.5553,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.008146639511201629,
919
+ "grad_norm": 0.9682738780975342,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.3147,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008210786279006366,
926
+ "grad_norm": 1.0135595798492432,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.5083,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008274933046811104,
933
+ "grad_norm": 1.106201171875,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.3359,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008339079814615841,
940
+ "grad_norm": 1.158813238143921,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 4.4816,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008403226582420579,
947
+ "grad_norm": 1.0801420211791992,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.4342,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008467373350225316,
954
+ "grad_norm": 1.1284626722335815,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.5528,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008531520118030054,
961
+ "grad_norm": 1.1629167795181274,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.3737,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00859566688583479,
968
+ "grad_norm": 1.3331410884857178,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.3553,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008659813653639527,
975
+ "grad_norm": 1.1465953588485718,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.37,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.008723960421444264,
982
+ "grad_norm": 1.135396122932434,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.474,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008788107189249002,
989
+ "grad_norm": 1.2194247245788574,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.3128,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.00885225395705374,
996
+ "grad_norm": 1.1395728588104248,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 4.4183,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.008916400724858477,
1003
+ "grad_norm": 1.2786668539047241,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.5955,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.008980547492663214,
1010
+ "grad_norm": 1.2455207109451294,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.3468,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00904469426046795,
1017
+ "grad_norm": 1.4937551021575928,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.4906,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.009108841028272687,
1024
+ "grad_norm": 1.473012089729309,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.696,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.009172987796077425,
1031
+ "grad_norm": 1.81377112865448,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.734,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009237134563882162,
1038
+ "grad_norm": 1.8109852075576782,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 4.6593,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.0093012813316869,
1045
+ "grad_norm": 1.8153804540634155,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.6856,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.009365428099491637,
1052
+ "grad_norm": 2.1597044467926025,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.4313,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009429574867296375,
1059
+ "grad_norm": 2.92808198928833,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.9218,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.00949372163510111,
1066
+ "grad_norm": 3.4155867099761963,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.177,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.009557868402905848,
1073
+ "grad_norm": 3.7774338722229004,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.1557,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009622015170710586,
1080
+ "grad_norm": 5.2052226066589355,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.3052,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009622015170710586,
1087
+ "eval_loss": 4.5528883934021,
1088
+ "eval_runtime": 175.8332,
1089
+ "eval_samples_per_second": 149.323,
1090
+ "eval_steps_per_second": 37.331,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4465184735232000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null