ancient41 commited on
Commit
5ff013e
·
verified ·
1 Parent(s): a158b1b

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 sha256:7b2c5d629481b018f17da6aaa530859dd84823bf447d9e31b7c96ad205c2f11d
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9141840414d45cb948d4057575ea874c3e36f848f36e02d6e45df596f29610
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a8ed22524d003781b3c10588038f67040bb9c7a1960c090591f532a8ecad0bc
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fd65aca21692f96450d83c8fb15966998976734ef89ea47e64d6edbcd44f64
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83e1dc17e7a3bfc808fd81f6d6f871582b3248596002b5607726dd2bf9b91cac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6773f3d251bbab0f7556ba82a064c4ff273e334de6184cb829d95825a11dee
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": 1.0559614896774292,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01408649105507818,
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": 49.722,
732
  "eval_steps_per_second": 12.434,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.1438135917346816e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9419289827346802,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02112973658261727,
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": 49.722,
732
  "eval_steps_per_second": 12.434,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.014227355965628961,
737
+ "grad_norm": 2.887002468109131,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.8021,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.014368220876179744,
744
+ "grad_norm": 2.8153011798858643,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.0186,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.014509085786730526,
751
+ "grad_norm": 2.0159571170806885,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.8548,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.014649950697281307,
758
+ "grad_norm": 1.593695044517517,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.6752,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.014790815607832089,
765
+ "grad_norm": 1.177317500114441,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.6363,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01493168051838287,
772
+ "grad_norm": 1.0343564748764038,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.6538,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.015072545428933652,
779
+ "grad_norm": 1.4447541236877441,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6313,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.015213410339484434,
786
+ "grad_norm": 1.1493356227874756,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5003,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.015354275250035217,
793
+ "grad_norm": 1.1778674125671387,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.581,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.015495140160585999,
800
+ "grad_norm": 1.0966111421585083,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4677,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01563600507113678,
807
+ "grad_norm": 0.9785053730010986,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.5391,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.01577686998168756,
814
+ "grad_norm": 1.2195751667022705,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.5638,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.015917734892238345,
821
+ "grad_norm": 1.2555761337280273,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3653,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.016058599802789127,
828
+ "grad_norm": 1.09703528881073,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1986,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.016199464713339908,
835
+ "grad_norm": 1.1482305526733398,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9653,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.01634032962389069,
842
+ "grad_norm": 1.1685477495193481,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8309,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01648119453444147,
849
+ "grad_norm": 1.2618950605392456,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.7785,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.016622059444992253,
856
+ "grad_norm": 1.070701241493225,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.7443,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.016762924355543034,
863
+ "grad_norm": 1.0922602415084839,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7625,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.016903789266093816,
870
+ "grad_norm": 1.0013766288757324,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.6861,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.017044654176644598,
877
+ "grad_norm": 0.8868520259857178,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.5199,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01718551908719538,
884
+ "grad_norm": 1.3038041591644287,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7734,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.01732638399774616,
891
+ "grad_norm": 0.9778259992599487,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.3785,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.017467248908296942,
898
+ "grad_norm": 1.215434193611145,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6427,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.017608113818847724,
905
+ "grad_norm": 1.095554232597351,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.681,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.017748978729398505,
912
+ "grad_norm": 0.9972038865089417,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.5964,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.017889843639949287,
919
+ "grad_norm": 1.1521289348602295,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.635,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.018030708550500072,
926
+ "grad_norm": 1.0549938678741455,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.5407,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.018171573461050854,
933
+ "grad_norm": 1.1805520057678223,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.5329,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.018312438371601635,
940
+ "grad_norm": 0.9551267027854919,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.5759,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.018453303282152417,
947
+ "grad_norm": 1.0043541193008423,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.4533,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0185941681927032,
954
+ "grad_norm": 1.1569894552230835,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.5385,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01873503310325398,
961
+ "grad_norm": 1.168152928352356,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.5891,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.01887589801380476,
968
+ "grad_norm": 1.546726107597351,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.5819,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.019016762924355543,
975
+ "grad_norm": 1.0554989576339722,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4015,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.019157627834906325,
982
+ "grad_norm": 1.2026422023773193,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.5737,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.019298492745457106,
989
+ "grad_norm": 1.1748453378677368,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.4456,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.019439357656007888,
996
+ "grad_norm": 1.128390908241272,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.4957,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01958022256655867,
1003
+ "grad_norm": 1.0329426527023315,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.4172,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01972108747710945,
1010
+ "grad_norm": 1.3100541830062866,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.6806,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.019861952387660232,
1017
+ "grad_norm": 1.3865808248519897,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.6796,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.020002817298211014,
1024
+ "grad_norm": 1.2001882791519165,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.6636,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0201436822087618,
1031
+ "grad_norm": 1.2058801651000977,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.4662,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.02028454711931258,
1038
+ "grad_norm": 1.5428941249847412,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.7921,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.020425412029863362,
1045
+ "grad_norm": 1.979830265045166,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.0626,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.020566276940414144,
1052
+ "grad_norm": 1.9408612251281738,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2731,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.020707141850964925,
1059
+ "grad_norm": 2.5928618907928467,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.6249,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.020848006761515707,
1066
+ "grad_norm": 3.2012157440185547,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.8548,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02098887167206649,
1073
+ "grad_norm": 3.9775068759918213,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.2191,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02112973658261727,
1080
+ "grad_norm": 4.948117256164551,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.9147,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02112973658261727,
1087
+ "eval_loss": 0.9419289827346802,
1088
+ "eval_runtime": 240.6256,
1089
+ "eval_samples_per_second": 49.691,
1090
+ "eval_steps_per_second": 12.426,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.2157203876020224e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null