aleegis09 commited on
Commit
3ad7dfd
·
verified ·
1 Parent(s): b6e4ede

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:b5b43164046e5888d58c3aa375b7b2f433a850a20197f5b7609810bf16f9b3fa
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e64b31a1f49ec3facd5c6bd3172c733d27be36d2a27d67c5ffa202f05387e38
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19ffa9a4b8fddbba2eb1821fa57c3e0c30160d54b5ed9273b596f0c6bd49c023
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297ea7bb1d3f7cf9f33967f54de278ee10888d8c8cf8eb96a8a58116cae8c7cd
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0cca217c1bf16069004b0b887dd236df44ea031841243328684fc122b5a14ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4354c6a160306c2ec6ed4de9e0cd7e6713c4ae1278aa43c94b5656a8a42b0700
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": 1.673848271369934,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.5050505050505051,
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": 60.489,
732
  "eval_steps_per_second": 15.213,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6658776367104000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6393885612487793,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.7575757575757576,
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": 60.489,
732
  "eval_steps_per_second": 15.213,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.51010101010101,
737
+ "grad_norm": 0.7127423882484436,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.6547,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5151515151515151,
744
+ "grad_norm": 0.7262145280838013,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.6783,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5202020202020202,
751
+ "grad_norm": 0.6225936412811279,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.6037,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.5252525252525253,
758
+ "grad_norm": 0.6136009097099304,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.6503,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5303030303030303,
765
+ "grad_norm": 0.5995920300483704,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.6204,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5353535353535354,
772
+ "grad_norm": 0.6025617718696594,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.6848,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5404040404040404,
779
+ "grad_norm": 0.602440595626831,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6538,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5454545454545454,
786
+ "grad_norm": 0.6105862855911255,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5667,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5505050505050505,
793
+ "grad_norm": 0.6314627528190613,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.6723,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5555555555555556,
800
+ "grad_norm": 0.6185853481292725,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.6417,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5606060606060606,
807
+ "grad_norm": 0.6278685331344604,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.6156,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5656565656565656,
814
+ "grad_norm": 0.6393197178840637,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.6447,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5707070707070707,
821
+ "grad_norm": 0.6812595725059509,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.6311,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5757575757575758,
828
+ "grad_norm": 0.6392555236816406,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.6515,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5808080808080808,
835
+ "grad_norm": 0.6752147078514099,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.66,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5858585858585859,
842
+ "grad_norm": 0.6572754979133606,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.6608,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5909090909090909,
849
+ "grad_norm": 0.6718370914459229,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.6199,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5959595959595959,
856
+ "grad_norm": 0.6734743118286133,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.6564,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.601010101010101,
863
+ "grad_norm": 0.6663838624954224,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.6478,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.6060606060606061,
870
+ "grad_norm": 0.6840781569480896,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6227,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.6111111111111112,
877
+ "grad_norm": 0.7021604776382446,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6286,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.6161616161616161,
884
+ "grad_norm": 0.6946828961372375,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6464,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.6212121212121212,
891
+ "grad_norm": 0.7025306820869446,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6627,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.6262626262626263,
898
+ "grad_norm": 0.7253495454788208,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6408,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.6313131313131313,
905
+ "grad_norm": 0.7254654765129089,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.6683,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6363636363636364,
912
+ "grad_norm": 0.7109437584877014,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.6036,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6414141414141414,
919
+ "grad_norm": 0.7180439233779907,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6427,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6464646464646465,
926
+ "grad_norm": 0.7294493913650513,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.6041,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6515151515151515,
933
+ "grad_norm": 0.7492313981056213,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.6785,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6565656565656566,
940
+ "grad_norm": 0.75017911195755,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.6926,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6616161616161617,
947
+ "grad_norm": 0.7792496085166931,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.7436,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6666666666666666,
954
+ "grad_norm": 0.7525399327278137,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.6119,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6717171717171717,
961
+ "grad_norm": 0.7805038690567017,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.6924,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6767676767676768,
968
+ "grad_norm": 0.7899602055549622,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.6468,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6818181818181818,
975
+ "grad_norm": 0.8201916813850403,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.6756,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6868686868686869,
982
+ "grad_norm": 0.8109264969825745,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.6284,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6919191919191919,
989
+ "grad_norm": 0.8284419178962708,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.6605,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.696969696969697,
996
+ "grad_norm": 0.8458845019340515,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.5937,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.702020202020202,
1003
+ "grad_norm": 0.8690614104270935,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.6476,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.7070707070707071,
1010
+ "grad_norm": 0.8767363429069519,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.6847,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.7121212121212122,
1017
+ "grad_norm": 0.8925921320915222,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7541,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.7171717171717171,
1024
+ "grad_norm": 0.9122419953346252,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.6584,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.7222222222222222,
1031
+ "grad_norm": 0.9675278663635254,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.7109,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.7272727272727273,
1038
+ "grad_norm": 0.966988205909729,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.6428,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.7323232323232324,
1045
+ "grad_norm": 1.0217162370681763,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.6801,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.7373737373737373,
1052
+ "grad_norm": 1.0754969120025635,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7185,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.7424242424242424,
1059
+ "grad_norm": 1.3362473249435425,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.7683,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7474747474747475,
1066
+ "grad_norm": 0.6028446555137634,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.658,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.7525252525252525,
1073
+ "grad_norm": 0.655256450176239,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.645,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.7575757575757576,
1080
+ "grad_norm": 0.6057277321815491,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6004,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.7575757575757576,
1087
+ "eval_loss": 1.6393885612487793,
1088
+ "eval_runtime": 5.5351,
1089
+ "eval_samples_per_second": 60.343,
1090
+ "eval_steps_per_second": 15.176,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9988164550656000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null