ciloku commited on
Commit
e8523c9
·
verified ·
1 Parent(s): cf24288

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 sha256:6b3982984e79b8b7922238bd1ab511d456b7e89ceaa580d921a55b335bff7386
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c027dfb2dbfd104e7a1c9635b43a433f2c3324f5993a92a3d8df8ab0750434e
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62094d54b4d19a001d9e20941fd6b5a1735ea5c39fd4d9f3bea7188b3df97b50
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc257ec324b14a41034c9d2596eda899ccae8d6d603d9bf9cee562e02a582807
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a84448d1dc78f778cc017796a82c332223307c3b57ed7cc73ca32d5dd5d42276
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fec91de91e5f57becbf1d6a75e5476fb68ea566628ed5fa952fa2ebe50e8eb6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b6460bb99370887d9faf3cffceb8d3101c13b7403d6f4c0b1c1e2e73b5257e4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4a786186a574bdc543ff4b4563aab7c5e0b442c74c85899bb42a25553c5d0c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.16816693544387817,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.7662835249042146,
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": 64.541,
732
  "eval_steps_per_second": 16.135,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3572294385401856.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.16181236505508423,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.1513409961685823,
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": 64.541,
732
  "eval_steps_per_second": 16.135,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.7739463601532567,
737
+ "grad_norm": 0.14441469311714172,
738
+ "learning_rate": 3.1982717529770985e-05,
739
+ "loss": 0.4444,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.7816091954022989,
744
+ "grad_norm": 0.11869792640209198,
745
+ "learning_rate": 3.148751264019667e-05,
746
+ "loss": 0.313,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.789272030651341,
751
+ "grad_norm": 0.09966205805540085,
752
+ "learning_rate": 3.099190107951924e-05,
753
+ "loss": 0.2333,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.7969348659003831,
758
+ "grad_norm": 0.12245635688304901,
759
+ "learning_rate": 3.049601834299076e-05,
760
+ "loss": 0.1806,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8045977011494253,
765
+ "grad_norm": 0.12711887061595917,
766
+ "learning_rate": 3e-05,
767
+ "loss": 0.2199,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.8122605363984674,
772
+ "grad_norm": 0.12456270307302475,
773
+ "learning_rate": 2.9503981657009246e-05,
774
+ "loss": 0.0923,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.8199233716475096,
779
+ "grad_norm": 0.11281975358724594,
780
+ "learning_rate": 2.9008098920480752e-05,
781
+ "loss": 0.1066,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.8275862068965517,
786
+ "grad_norm": 0.07618711143732071,
787
+ "learning_rate": 2.851248735980333e-05,
788
+ "loss": 0.074,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.8352490421455939,
793
+ "grad_norm": 0.10129279643297195,
794
+ "learning_rate": 2.801728247022902e-05,
795
+ "loss": 0.0754,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.842911877394636,
800
+ "grad_norm": 0.09363987296819687,
801
+ "learning_rate": 2.7522619635830034e-05,
802
+ "loss": 0.0853,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.8505747126436781,
807
+ "grad_norm": 0.08725081384181976,
808
+ "learning_rate": 2.702863409248612e-05,
809
+ "loss": 0.2004,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.8582375478927203,
814
+ "grad_norm": 0.0783943384885788,
815
+ "learning_rate": 2.6535460890912416e-05,
816
+ "loss": 0.1047,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.8659003831417624,
821
+ "grad_norm": 0.10503990948200226,
822
+ "learning_rate": 2.604323485973793e-05,
823
+ "loss": 0.1262,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.8735632183908046,
828
+ "grad_norm": 0.09686201065778732,
829
+ "learning_rate": 2.555209056864474e-05,
830
+ "loss": 0.0969,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.8812260536398467,
835
+ "grad_norm": 0.0980193242430687,
836
+ "learning_rate": 2.5062162291577978e-05,
837
+ "loss": 0.1034,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.8888888888888888,
842
+ "grad_norm": 0.08893204480409622,
843
+ "learning_rate": 2.4573583970036712e-05,
844
+ "loss": 0.0968,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.896551724137931,
849
+ "grad_norm": 0.12043558061122894,
850
+ "learning_rate": 2.4086489176455595e-05,
851
+ "loss": 0.0911,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.9042145593869731,
856
+ "grad_norm": 0.09192109853029251,
857
+ "learning_rate": 2.36010110776876e-05,
858
+ "loss": 0.0937,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.9118773946360154,
863
+ "grad_norm": 0.08706682920455933,
864
+ "learning_rate": 2.3117282398597456e-05,
865
+ "loss": 0.1428,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.9195402298850575,
870
+ "grad_norm": 0.11525483429431915,
871
+ "learning_rate": 2.263543538577603e-05,
872
+ "loss": 0.1219,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.9272030651340997,
877
+ "grad_norm": 0.09489944577217102,
878
+ "learning_rate": 2.215560177138541e-05,
879
+ "loss": 0.1083,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.9348659003831418,
884
+ "grad_norm": 0.10396278649568558,
885
+ "learning_rate": 2.167791273714467e-05,
886
+ "loss": 0.1037,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.9425287356321839,
891
+ "grad_norm": 0.12295960634946823,
892
+ "learning_rate": 2.1202498878466062e-05,
893
+ "loss": 0.1395,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.9501915708812261,
898
+ "grad_norm": 0.15319755673408508,
899
+ "learning_rate": 2.072949016875158e-05,
900
+ "loss": 0.1663,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.9578544061302682,
905
+ "grad_norm": 0.1255790889263153,
906
+ "learning_rate": 2.0259015923859498e-05,
907
+ "loss": 0.1011,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.9655172413793104,
912
+ "grad_norm": 0.17556820809841156,
913
+ "learning_rate": 1.979120476675071e-05,
914
+ "loss": 0.2089,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.9731800766283525,
919
+ "grad_norm": 0.15263380110263824,
920
+ "learning_rate": 1.9326184592324503e-05,
921
+ "loss": 0.1327,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.9808429118773946,
926
+ "grad_norm": 0.29129284620285034,
927
+ "learning_rate": 1.8864082532453373e-05,
928
+ "loss": 0.2664,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.9885057471264368,
933
+ "grad_norm": 0.07602576911449432,
934
+ "learning_rate": 1.840502492122644e-05,
935
+ "loss": 0.1506,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.9961685823754789,
940
+ "grad_norm": 0.07331366091966629,
941
+ "learning_rate": 1.7949137260410924e-05,
942
+ "loss": 0.0866,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.0057471264367817,
947
+ "grad_norm": 0.3374364674091339,
948
+ "learning_rate": 1.7496544185141295e-05,
949
+ "loss": 0.4057,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.0134099616858236,
954
+ "grad_norm": 0.10590671747922897,
955
+ "learning_rate": 1.7047369429845216e-05,
956
+ "loss": 0.1654,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.0210727969348659,
961
+ "grad_norm": 0.12875299155712128,
962
+ "learning_rate": 1.6601735794415806e-05,
963
+ "loss": 0.2853,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.028735632183908,
968
+ "grad_norm": 0.13337695598602295,
969
+ "learning_rate": 1.615976511063937e-05,
970
+ "loss": 0.3602,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.0363984674329503,
975
+ "grad_norm": 0.175828754901886,
976
+ "learning_rate": 1.5721578208887793e-05,
977
+ "loss": 0.4249,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.0440613026819923,
982
+ "grad_norm": 0.1130770593881607,
983
+ "learning_rate": 1.5287294885084766e-05,
984
+ "loss": 0.2504,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.0517241379310345,
989
+ "grad_norm": 0.09660311043262482,
990
+ "learning_rate": 1.4857033867954697e-05,
991
+ "loss": 0.1961,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.0593869731800767,
996
+ "grad_norm": 0.0801113024353981,
997
+ "learning_rate": 1.4430912786563554e-05,
998
+ "loss": 0.1567,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.0670498084291187,
1003
+ "grad_norm": 0.09412167966365814,
1004
+ "learning_rate": 1.4009048138160195e-05,
1005
+ "loss": 0.1346,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.0747126436781609,
1010
+ "grad_norm": 0.09223540127277374,
1011
+ "learning_rate": 1.3591555256327199e-05,
1012
+ "loss": 0.0735,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.082375478927203,
1017
+ "grad_norm": 0.06864771246910095,
1018
+ "learning_rate": 1.3178548279449822e-05,
1019
+ "loss": 0.0827,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.0900383141762453,
1024
+ "grad_norm": 0.09543950110673904,
1025
+ "learning_rate": 1.2770140119511693e-05,
1026
+ "loss": 0.0824,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.0977011494252873,
1031
+ "grad_norm": 0.07598932087421417,
1032
+ "learning_rate": 1.2366442431225809e-05,
1033
+ "loss": 0.0992,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.1053639846743295,
1038
+ "grad_norm": 0.090644970536232,
1039
+ "learning_rate": 1.1967565581509248e-05,
1040
+ "loss": 0.0885,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.1130268199233717,
1045
+ "grad_norm": 0.06884025782346725,
1046
+ "learning_rate": 1.1573618619309965e-05,
1047
+ "loss": 0.0793,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.1206896551724137,
1052
+ "grad_norm": 0.09408024698495865,
1053
+ "learning_rate": 1.1184709245793889e-05,
1054
+ "loss": 0.1176,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.128352490421456,
1059
+ "grad_norm": 0.07865190505981445,
1060
+ "learning_rate": 1.0800943784900502e-05,
1061
+ "loss": 0.1063,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.1360153256704981,
1066
+ "grad_norm": 0.07905281335115433,
1067
+ "learning_rate": 1.042242715427494e-05,
1068
+ "loss": 0.1115,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.1436781609195403,
1073
+ "grad_norm": 0.10434318333864212,
1074
+ "learning_rate": 1.004926283658455e-05,
1075
+ "loss": 0.0815,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.1513409961685823,
1080
+ "grad_norm": 0.08591567724943161,
1081
+ "learning_rate": 9.681552851227774e-06,
1082
+ "loss": 0.0945,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.1513409961685823,
1087
+ "eval_loss": 0.16181236505508423,
1088
+ "eval_runtime": 3.4216,
1089
+ "eval_samples_per_second": 64.297,
1090
+ "eval_steps_per_second": 16.074,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5420245979234304.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null