nttx commited on
Commit
d8bcd72
·
verified ·
1 Parent(s): 209499e

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:cf797c333eb83dd3c95c9a67d5f407a3ddf1ccd3e64ea4763f3efa60b026e464
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646286d7b4ac468f622c856ba141a9b4d5fb1685f0b5f62c1c8cab315120ced8
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9962a1eae61aa19823efd2e4513be41d88f831e888e15eda82f4a6a81ae288f3
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0e8ad4f31bfd16a51a2b8c4bbef5e7090efea35ff4ba25f49dc76c4766436e
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5669b004ba2c674bf9781c8f43916606e8ebd1ca3dc5903b3816ebbf24f436cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aeec98de2a543bc4b433146bd590a4898fabeb53c61c1909eb8b961873d4ab0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8527500629425049,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.12907389480477574,
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": 12.298,
732
  "eval_steps_per_second": 6.154,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7135263681411743,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1936108422071636,
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": 12.298,
732
  "eval_steps_per_second": 6.154,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.13036463375282348,
737
+ "grad_norm": 2.645070791244507,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 1.5433,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.13165537270087124,
744
+ "grad_norm": 3.2914302349090576,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 1.7588,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.132946111648919,
751
+ "grad_norm": 2.8321797847747803,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 1.6911,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.13423685059696677,
758
+ "grad_norm": 2.6913323402404785,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 1.5505,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1355275895450145,
765
+ "grad_norm": 2.40425443649292,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 1.6987,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.13681832849306227,
772
+ "grad_norm": 2.166919231414795,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 1.8477,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.13810906744111004,
779
+ "grad_norm": 2.1085963249206543,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 1.3727,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1393998063891578,
786
+ "grad_norm": 2.3301165103912354,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 1.6837,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.14069054533720554,
793
+ "grad_norm": 2.3991880416870117,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 1.742,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1419812842852533,
800
+ "grad_norm": 2.073758363723755,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 1.501,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.14327202323330107,
807
+ "grad_norm": 2.043945550918579,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 1.5306,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1445627621813488,
814
+ "grad_norm": 2.3612983226776123,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 1.2722,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.14585350112939657,
821
+ "grad_norm": 2.2310869693756104,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 1.6452,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.14714424007744434,
828
+ "grad_norm": 2.3419902324676514,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 1.5262,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1484349790254921,
835
+ "grad_norm": 2.4059255123138428,
836
+ "learning_rate": 5e-05,
837
+ "loss": 1.4984,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.14972571797353984,
842
+ "grad_norm": 2.149911642074585,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 1.708,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1510164569215876,
849
+ "grad_norm": 2.24536395072937,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 1.8139,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.15230719586963537,
856
+ "grad_norm": 2.1570913791656494,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 1.4399,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.15359793481768313,
863
+ "grad_norm": 2.671151876449585,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 1.5718,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.15488867376573087,
870
+ "grad_norm": 2.0248093605041504,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 1.6957,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.15617941271377864,
877
+ "grad_norm": 2.008172035217285,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 1.4275,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1574701516618264,
884
+ "grad_norm": 2.3770668506622314,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 1.7451,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.15876089060987417,
891
+ "grad_norm": 2.311845541000366,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 1.6255,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1600516295579219,
898
+ "grad_norm": 2.1279056072235107,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 1.647,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.16134236850596967,
905
+ "grad_norm": 2.579422950744629,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 1.6169,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.16263310745401743,
912
+ "grad_norm": 2.14923357963562,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 1.5497,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.16392384640206517,
919
+ "grad_norm": 2.577373504638672,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 1.7964,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.16521458535011294,
926
+ "grad_norm": 2.1733500957489014,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 1.6157,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1665053242981607,
933
+ "grad_norm": 2.469484329223633,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 1.6811,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.16779606324620847,
940
+ "grad_norm": 2.4052541255950928,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.3892,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1690868021942562,
947
+ "grad_norm": 2.5126283168792725,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 1.5076,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.17037754114230397,
954
+ "grad_norm": 2.3482887744903564,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 1.4998,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.17166828009035173,
961
+ "grad_norm": 2.716629981994629,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 1.8134,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1729590190383995,
968
+ "grad_norm": 2.555504560470581,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 1.6125,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.17424975798644723,
975
+ "grad_norm": 2.7541518211364746,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 1.7103,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.175540496934495,
982
+ "grad_norm": 2.813023090362549,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 1.8416,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.17683123588254276,
989
+ "grad_norm": 3.048743963241577,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 1.7248,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1781219748305905,
996
+ "grad_norm": 2.53549861907959,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 1.971,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.17941271377863827,
1003
+ "grad_norm": 2.9249329566955566,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 1.8153,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.18070345272668603,
1010
+ "grad_norm": 2.572925090789795,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 1.56,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1819941916747338,
1017
+ "grad_norm": 2.91241455078125,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.7049,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.18328493062278153,
1024
+ "grad_norm": 2.950890064239502,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 1.9443,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1845756695708293,
1031
+ "grad_norm": 2.7503061294555664,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 1.7713,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.18586640851887706,
1038
+ "grad_norm": 3.214904546737671,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.7367,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.18715714746692483,
1045
+ "grad_norm": 2.8951315879821777,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 2.0016,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.18844788641497257,
1052
+ "grad_norm": 3.1537482738494873,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 1.8615,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.18973862536302033,
1059
+ "grad_norm": 4.895639896392822,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 1.5843,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.1910293643110681,
1066
+ "grad_norm": 3.6234192848205566,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 2.0226,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.19232010325911583,
1073
+ "grad_norm": 3.944408893585205,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 2.3779,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1936108422071636,
1080
+ "grad_norm": 5.268966197967529,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 2.7319,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1936108422071636,
1087
+ "eval_loss": 1.7135263681411743,
1088
+ "eval_runtime": 106.2082,
1089
+ "eval_samples_per_second": 12.287,
1090
+ "eval_steps_per_second": 6.148,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null