aleegis12 commited on
Commit
a5fe4a5
·
verified ·
1 Parent(s): c36c2c6

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:dc6847b30ee8a41554b68fb3b0a49838bf829f3971bb4b4d7158bf10a4a148f9
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe5e78a93ee6cbd97a3fa345351df4f30d4c023362e804f82099d1266680ca1
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c142a41f043c0c0bde3bda5434efd7f73920093505f509a8446260a66c086f22
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97705a19032181b15fc9516bfee8c3d27cbdaa97a0ab50454fa48eb8929be44f
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0664582359f99320cf3ef366e7c6afff3e12ad91b8e191e816f63cc9e498ed67
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844eaf46bc220302fea9fbecdc4be2a8dad6024a220ef352813547cff4438fbc
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": 10.304475784301758,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.023633677991137372,
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": 501.569,
732
  "eval_steps_per_second": 125.41,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 21695727403008.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.302660942077637,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03545051698670606,
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": 501.569,
732
  "eval_steps_per_second": 125.41,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.023870014771048744,
737
+ "grad_norm": 0.5683258175849915,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 41.2639,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.02410635155096012,
744
+ "grad_norm": 0.6116344332695007,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 41.2569,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02434268833087149,
751
+ "grad_norm": 0.7886593341827393,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 41.2623,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.024579025110782866,
758
+ "grad_norm": 0.5637018084526062,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 41.2561,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.024815361890694238,
765
+ "grad_norm": 0.5537078976631165,
766
+ "learning_rate": 5e-05,
767
+ "loss": 41.2528,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.025051698670605613,
772
+ "grad_norm": 0.8540703654289246,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 41.2307,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.025288035450516985,
779
+ "grad_norm": 0.6901519298553467,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 41.2618,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02552437223042836,
786
+ "grad_norm": 0.8774058818817139,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 41.2425,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.025760709010339736,
793
+ "grad_norm": 0.5206881165504456,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 41.2331,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.025997045790251107,
800
+ "grad_norm": 0.5892984867095947,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 41.2217,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.026233382570162483,
807
+ "grad_norm": 0.4885897636413574,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 41.2286,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.026469719350073855,
814
+ "grad_norm": 0.4280990660190582,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 41.249,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.02670605612998523,
821
+ "grad_norm": 0.511814534664154,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 41.1789,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0269423929098966,
828
+ "grad_norm": 0.6043238639831543,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 41.2006,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.027178729689807977,
835
+ "grad_norm": 0.6983438730239868,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 41.2285,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02741506646971935,
842
+ "grad_norm": 0.4473256468772888,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 41.2161,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.027651403249630724,
849
+ "grad_norm": 0.7691261172294617,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 41.235,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0278877400295421,
856
+ "grad_norm": 0.7613927721977234,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 41.2039,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02812407680945347,
863
+ "grad_norm": 0.4714309275150299,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 41.2043,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.028360413589364846,
870
+ "grad_norm": 0.5756589770317078,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 41.236,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.028596750369276218,
877
+ "grad_norm": 0.6995598077774048,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 41.2093,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.028833087149187593,
884
+ "grad_norm": 0.6448226571083069,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 41.212,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.029069423929098965,
891
+ "grad_norm": 0.4924877882003784,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 41.1863,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02930576070901034,
898
+ "grad_norm": 0.5269948840141296,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 41.1971,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.029542097488921712,
905
+ "grad_norm": 0.39500701427459717,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 41.2065,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.029778434268833087,
912
+ "grad_norm": 0.5846647620201111,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 41.2433,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.030014771048744462,
919
+ "grad_norm": 0.5672599077224731,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 41.2302,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.030251107828655834,
926
+ "grad_norm": 0.666126549243927,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 41.23,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03048744460856721,
933
+ "grad_norm": 0.5294464230537415,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 41.1618,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03072378138847858,
940
+ "grad_norm": 0.5049988031387329,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 41.1871,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.030960118168389957,
947
+ "grad_norm": 0.4904077649116516,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 41.221,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03119645494830133,
954
+ "grad_norm": 0.690887987613678,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 41.2017,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0314327917282127,
961
+ "grad_norm": 0.5043950080871582,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 41.2255,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.031669128508124075,
968
+ "grad_norm": 0.5043528079986572,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 41.2038,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03190546528803545,
975
+ "grad_norm": 0.45125049352645874,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 41.2188,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.032141802067946826,
982
+ "grad_norm": 0.5066573023796082,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 41.2102,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0323781388478582,
989
+ "grad_norm": 0.43378594517707825,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 41.2007,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03261447562776957,
996
+ "grad_norm": 0.5496785640716553,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 41.1984,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.032850812407680945,
1003
+ "grad_norm": 0.5256023406982422,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 41.2067,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03308714918759232,
1010
+ "grad_norm": 0.4560036361217499,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 41.2223,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.033323485967503695,
1017
+ "grad_norm": 0.45323535799980164,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 41.2171,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03355982274741506,
1024
+ "grad_norm": 0.5921773314476013,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 41.1751,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03379615952732644,
1031
+ "grad_norm": 0.4303775131702423,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 41.2136,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.034032496307237814,
1038
+ "grad_norm": 0.4436986446380615,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 41.2185,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03426883308714919,
1045
+ "grad_norm": 0.5888164043426514,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 41.2181,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.034505169867060564,
1052
+ "grad_norm": 0.5130054354667664,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 41.2302,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03474150664697193,
1059
+ "grad_norm": 0.535312294960022,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 41.2168,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03497784342688331,
1066
+ "grad_norm": 0.5531200170516968,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 41.1973,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03521418020679468,
1073
+ "grad_norm": 0.7230327725410461,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 41.1891,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03545051698670606,
1080
+ "grad_norm": 1.0734859704971313,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 41.1475,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03545051698670606,
1087
+ "eval_loss": 10.302660942077637,
1088
+ "eval_runtime": 14.2196,
1089
+ "eval_samples_per_second": 501.21,
1090
+ "eval_steps_per_second": 125.32,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 32597293400064.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null