prxy5605 commited on
Commit
34d9d80
·
verified ·
1 Parent(s): 5c67c2e

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 sha256:3df2c36d7f93eb1d21dd21abdcf05fad00efb7379337cdaecfa6ab4bf116714b
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f29cc3fd1011bc57055603035bbba1f4431d4e253a521435ce2e3da69f21fb
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb80ebaa3684606a9e89e9dc613271c5bdd781b06efa1d82ad23bc12fb14de16
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac38274e56e9cfc0f25d093e807ce8008d28348dc2a180f6aba5ef65d428730
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42c30425bfb45a8fed66274cd4ecce6792b2ba4c6cafb292e991569a5e548a47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7d4990bd536f1641f898e1713d3de7b91391d52505ffcd9bd57efd82cc5d05e
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": 1.7553160190582275,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06500893872907525,
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": 14.047,
732
  "eval_steps_per_second": 3.513,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3371482531325542e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6340785026550293,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09751340809361288,
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": 14.047,
732
  "eval_steps_per_second": 3.513,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.065659028116366,
737
+ "grad_norm": 0.6581565737724304,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.7125,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06630911750365676,
744
+ "grad_norm": 0.6509100198745728,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.6547,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0669592068909475,
751
+ "grad_norm": 0.6598650217056274,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.7191,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06760929627823825,
758
+ "grad_norm": 0.5266051888465881,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.7397,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06825938566552901,
765
+ "grad_norm": 0.45416244864463806,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.5829,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06890947505281976,
772
+ "grad_norm": 0.441561222076416,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.7201,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06955956444011052,
779
+ "grad_norm": 0.39746689796447754,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.6894,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07020965382740127,
786
+ "grad_norm": 0.4110812246799469,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.7164,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07085974321469202,
793
+ "grad_norm": 0.405830442905426,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.7018,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07150983260198278,
800
+ "grad_norm": 0.4134947955608368,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.7325,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.07215992198927353,
807
+ "grad_norm": 0.3938530385494232,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.6551,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07281001137656427,
814
+ "grad_norm": 0.4017390310764313,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.7821,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07346010076385504,
821
+ "grad_norm": 0.3798288404941559,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.6007,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07411019015114578,
828
+ "grad_norm": 0.38088488578796387,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.7317,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07476027953843653,
835
+ "grad_norm": 0.42296120524406433,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.6346,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07541036892572729,
842
+ "grad_norm": 0.4114514887332916,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.6898,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07606045831301804,
849
+ "grad_norm": 0.43711206316947937,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.6717,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.07671054770030879,
856
+ "grad_norm": 0.43382951617240906,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.6648,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07736063708759955,
863
+ "grad_norm": 0.4684242904186249,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7315,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0780107264748903,
870
+ "grad_norm": 0.46574684977531433,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.5633,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07866081586218104,
877
+ "grad_norm": 0.4726516604423523,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6298,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0793109052494718,
884
+ "grad_norm": 0.5093461275100708,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6883,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07996099463676255,
891
+ "grad_norm": 0.5450136065483093,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.7176,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0806110840240533,
898
+ "grad_norm": 0.5406458377838135,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.6133,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.08126117341134406,
905
+ "grad_norm": 0.5697487592697144,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7343,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08191126279863481,
912
+ "grad_norm": 0.6159641146659851,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.5577,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08256135218592557,
919
+ "grad_norm": 0.6676238179206848,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6695,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08321144157321632,
926
+ "grad_norm": 0.6753639578819275,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.6284,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08386153096050707,
933
+ "grad_norm": 0.7404447197914124,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4671,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08451162034779783,
940
+ "grad_norm": 0.6579782366752625,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.6241,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.08516170973508858,
947
+ "grad_norm": 0.6930049657821655,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.7083,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08581179912237932,
954
+ "grad_norm": 0.7640788555145264,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.5552,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08646188850967008,
961
+ "grad_norm": 0.8431758880615234,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5155,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08711197789696083,
968
+ "grad_norm": 0.848166286945343,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.4503,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08776206728425158,
975
+ "grad_norm": 0.7847415208816528,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.3962,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08841215667154234,
982
+ "grad_norm": 0.9068143367767334,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.6088,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08906224605883309,
989
+ "grad_norm": 0.896609902381897,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.5353,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08971233544612384,
996
+ "grad_norm": 1.0200631618499756,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3272,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.0903624248334146,
1003
+ "grad_norm": 0.9650431871414185,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.8259,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09101251422070535,
1010
+ "grad_norm": 1.2387449741363525,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.5105,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0916626036079961,
1017
+ "grad_norm": 0.9499669671058655,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5403,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09231269299528685,
1024
+ "grad_norm": 1.193396806716919,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.6665,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0929627823825776,
1031
+ "grad_norm": 1.3132269382476807,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.5922,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.09361287176986836,
1038
+ "grad_norm": 1.505435585975647,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.6281,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09426296115715911,
1045
+ "grad_norm": 1.4210517406463623,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.5595,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09491305054444986,
1052
+ "grad_norm": 1.4971040487289429,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.8346,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09556313993174062,
1059
+ "grad_norm": 1.7352982759475708,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.8204,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09621322931903137,
1066
+ "grad_norm": 1.7588574886322021,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.7591,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09686331870632212,
1073
+ "grad_norm": 2.053088665008545,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.5625,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09751340809361288,
1080
+ "grad_norm": 2.5474445819854736,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.9002,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09751340809361288,
1087
+ "eval_loss": 1.6340785026550293,
1088
+ "eval_runtime": 184.4295,
1089
+ "eval_samples_per_second": 14.049,
1090
+ "eval_steps_per_second": 3.514,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0023961402631782e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null