prxy5605 commited on
Commit
db83974
·
verified ·
1 Parent(s): eea17c1

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 sha256:049dbea609070280cf454ceb76803a70be8cd747b965377d942b7a02d01e2a47
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21de7ad39891d663cbfbb45ad94ccff0c25f79c8769030cfd554f0bb4e22e899
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85950f08dd7b1ef54bc09315daa841822d3613bd9e9fac611b752f0ccd048b89
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63491ca446b4c3e0d425d6bb222d0074dc6d17e2a0cb439cda0da90e535de28e
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ba69f4e2d66a42dbdfdbf3816dc82ae6c726a7187dae1cbbac71c03486c13dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0f555b7530d9db90f96b1bf251881de6d6788cf0f69eb401b2c7359b3333a4
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": 1.644432544708252,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.7905138339920948,
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": 44.238,
732
  "eval_steps_per_second": 11.215,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.0298202840367104e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6133692264556885,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.1857707509881423,
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": 44.238,
732
  "eval_steps_per_second": 11.215,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.7984189723320159,
737
+ "grad_norm": 0.6788752675056458,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.7212,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.8063241106719368,
744
+ "grad_norm": 0.5979511737823486,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.5423,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.8142292490118577,
751
+ "grad_norm": 0.6435640454292297,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5651,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.8221343873517787,
758
+ "grad_norm": 0.6285018920898438,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5639,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8300395256916996,
765
+ "grad_norm": 0.6168222427368164,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.5667,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.8379446640316206,
772
+ "grad_norm": 0.6518228650093079,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.7141,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.8458498023715415,
779
+ "grad_norm": 0.7004503011703491,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.765,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.8537549407114624,
786
+ "grad_norm": 0.6650953888893127,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5443,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.8616600790513834,
793
+ "grad_norm": 0.7480284571647644,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7513,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.8695652173913043,
800
+ "grad_norm": 0.7257048487663269,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.7061,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.8774703557312253,
807
+ "grad_norm": 0.7339716553688049,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.6675,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.8853754940711462,
814
+ "grad_norm": 0.7776533365249634,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.8499,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.8932806324110671,
821
+ "grad_norm": 0.7437097430229187,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.8209,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.9011857707509882,
828
+ "grad_norm": 0.7620865106582642,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.745,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.9090909090909091,
835
+ "grad_norm": 0.8105087280273438,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.7531,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.9169960474308301,
842
+ "grad_norm": 0.8046197295188904,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7271,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.924901185770751,
849
+ "grad_norm": 0.8412743806838989,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.8155,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.932806324110672,
856
+ "grad_norm": 0.838920533657074,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.8482,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.9407114624505929,
863
+ "grad_norm": 0.8457604050636292,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7529,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.9486166007905138,
870
+ "grad_norm": 0.9167115092277527,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6983,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.9565217391304348,
877
+ "grad_norm": 0.9630374312400818,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.7011,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.9644268774703557,
884
+ "grad_norm": 0.9056899547576904,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6826,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.9723320158102767,
891
+ "grad_norm": 1.020810604095459,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.6647,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.9802371541501976,
898
+ "grad_norm": 1.327959418296814,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.848,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.9881422924901185,
905
+ "grad_norm": 0.6786101460456848,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.5836,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.9960474308300395,
912
+ "grad_norm": 0.7688708305358887,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.7463,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.0039525691699605,
919
+ "grad_norm": 1.5957648754119873,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.6306,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.0118577075098814,
926
+ "grad_norm": 0.5522214770317078,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.532,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.0197628458498025,
933
+ "grad_norm": 0.5481433868408203,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4873,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.0276679841897234,
940
+ "grad_norm": 0.669899046421051,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.689,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.0355731225296443,
947
+ "grad_norm": 0.5601217150688171,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.4955,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.0434782608695652,
954
+ "grad_norm": 0.5741488933563232,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.577,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.051383399209486,
961
+ "grad_norm": 0.5481381416320801,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5231,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.0592885375494072,
968
+ "grad_norm": 0.5438144207000732,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4542,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.0671936758893281,
975
+ "grad_norm": 0.5592533349990845,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.6158,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.075098814229249,
982
+ "grad_norm": 0.601783812046051,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.5103,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.08300395256917,
989
+ "grad_norm": 0.6082609295845032,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5273,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.0909090909090908,
996
+ "grad_norm": 0.6211904287338257,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.5463,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.098814229249012,
1003
+ "grad_norm": 0.5987580418586731,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.5708,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.1067193675889329,
1010
+ "grad_norm": 0.6398665904998779,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.6496,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.1146245059288538,
1017
+ "grad_norm": 0.6528900265693665,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5757,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.1225296442687747,
1024
+ "grad_norm": 0.6666259169578552,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.6528,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.1304347826086956,
1031
+ "grad_norm": 0.7091323137283325,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6874,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.1383399209486167,
1038
+ "grad_norm": 0.7314757108688354,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.7092,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.1462450592885376,
1045
+ "grad_norm": 0.6564605832099915,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.465,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.1541501976284585,
1052
+ "grad_norm": 0.6789471507072449,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.5696,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.1620553359683794,
1059
+ "grad_norm": 0.6962265372276306,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.5224,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.1699604743083003,
1066
+ "grad_norm": 0.736736536026001,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.6225,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.1778656126482214,
1073
+ "grad_norm": 0.7357221245765686,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.5452,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.1857707509881423,
1080
+ "grad_norm": 0.7465088367462158,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6068,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.1857707509881423,
1087
+ "eval_loss": 1.6133692264556885,
1088
+ "eval_runtime": 4.8741,
1089
+ "eval_samples_per_second": 43.7,
1090
+ "eval_steps_per_second": 11.079,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.4988425616162816e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null