jssky commited on
Commit
fcfe38b
·
verified ·
1 Parent(s): 89ecbfe

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:b2a971a77ea5fac6cfec44a9331d413a2e421a1e94852a5ea9b7a73b150442a9
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91c41759eed9646eaca98bec129f630f17121b6cef377eacdc038a05236b8199
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a8a6456fbb7c9d2451642fb0019f2c435cbbfb8c36111133c89335989de24f
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24779ce34932460063a900f766a2f791167141274a9aed162aedb44d318396f
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:459455ef2e23ba83c9d4b3dd3ac94a73982331231e2053df668eab25da1a2449
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c415bc57a6f8c3b5e4a83ed8cbe096ef4630874162afe67a23ccfd2670217d6
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": 0.47071829438209534,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07521624670928921,
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,
@@ -723,6 +723,364 @@
723
  "eval_samples_per_second": 9.163,
724
  "eval_steps_per_second": 2.292,
725
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
726
  }
727
  ],
728
  "logging_steps": 1,
@@ -751,7 +1109,7 @@
751
  "attributes": {}
752
  }
753
  },
754
- "total_flos": 2.608247819206656e+17,
755
  "train_batch_size": 8,
756
  "trial_name": null,
757
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4612102210521698,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11282437006393381,
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,
 
723
  "eval_samples_per_second": 9.163,
724
  "eval_steps_per_second": 2.292,
725
  "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0759684091763821,
729
+ "grad_norm": 0.8430553674697876,
730
+ "learning_rate": 5.330452921628497e-05,
731
+ "loss": 0.5654,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 0.076720571643475,
736
+ "grad_norm": 0.7868257164955139,
737
+ "learning_rate": 5.247918773366112e-05,
738
+ "loss": 0.5095,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 0.07747273411056788,
743
+ "grad_norm": 0.8357489705085754,
744
+ "learning_rate": 5.165316846586541e-05,
745
+ "loss": 0.5199,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 0.07822489657766077,
750
+ "grad_norm": 0.7403062582015991,
751
+ "learning_rate": 5.0826697238317935e-05,
752
+ "loss": 0.5131,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 0.07897705904475366,
757
+ "grad_norm": 0.6494471430778503,
758
+ "learning_rate": 5e-05,
759
+ "loss": 0.4805,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 0.07972922151184655,
764
+ "grad_norm": 0.6976310610771179,
765
+ "learning_rate": 4.917330276168208e-05,
766
+ "loss": 0.5182,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 0.08048138397893945,
771
+ "grad_norm": 0.7517837285995483,
772
+ "learning_rate": 4.834683153413459e-05,
773
+ "loss": 0.5235,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 0.08123354644603234,
778
+ "grad_norm": 0.6784954071044922,
779
+ "learning_rate": 4.7520812266338885e-05,
780
+ "loss": 0.4549,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 0.08198570891312523,
785
+ "grad_norm": 0.6948727965354919,
786
+ "learning_rate": 4.669547078371504e-05,
787
+ "loss": 0.4699,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 0.08273787138021813,
792
+ "grad_norm": 0.8937512040138245,
793
+ "learning_rate": 4.5871032726383386e-05,
794
+ "loss": 0.4644,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 0.08349003384731102,
799
+ "grad_norm": 1.452114462852478,
800
+ "learning_rate": 4.504772348747687e-05,
801
+ "loss": 0.4634,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 0.08424219631440391,
806
+ "grad_norm": 0.706430196762085,
807
+ "learning_rate": 4.4225768151520694e-05,
808
+ "loss": 0.4653,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 0.0849943587814968,
813
+ "grad_norm": 0.6724202632904053,
814
+ "learning_rate": 4.3405391432896555e-05,
815
+ "loss": 0.4252,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 0.0857465212485897,
820
+ "grad_norm": 1.4828470945358276,
821
+ "learning_rate": 4.2586817614407895e-05,
822
+ "loss": 0.5575,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 0.08649868371568259,
827
+ "grad_norm": 0.7318214774131775,
828
+ "learning_rate": 4.17702704859633e-05,
829
+ "loss": 0.5358,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 0.08725084618277548,
834
+ "grad_norm": 0.6255041360855103,
835
+ "learning_rate": 4.095597328339452e-05,
836
+ "loss": 0.4732,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 0.08800300864986838,
841
+ "grad_norm": 0.7117745876312256,
842
+ "learning_rate": 4.0144148627425993e-05,
843
+ "loss": 0.4782,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 0.08875517111696127,
848
+ "grad_norm": 0.6318966150283813,
849
+ "learning_rate": 3.933501846281267e-05,
850
+ "loss": 0.4202,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 0.08950733358405416,
855
+ "grad_norm": 0.6899405121803284,
856
+ "learning_rate": 3.852880399766243e-05,
857
+ "loss": 0.5128,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 0.09025949605114705,
862
+ "grad_norm": 0.6502125859260559,
863
+ "learning_rate": 3.772572564296005e-05,
864
+ "loss": 0.4011,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 0.09101165851823995,
869
+ "grad_norm": 0.664861798286438,
870
+ "learning_rate": 3.6926002952309016e-05,
871
+ "loss": 0.483,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 0.09176382098533283,
876
+ "grad_norm": 0.6798005700111389,
877
+ "learning_rate": 3.612985456190778e-05,
878
+ "loss": 0.4627,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 0.09251598345242572,
883
+ "grad_norm": 0.7227123975753784,
884
+ "learning_rate": 3.533749813077677e-05,
885
+ "loss": 0.4805,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 0.09326814591951861,
890
+ "grad_norm": 0.9531402587890625,
891
+ "learning_rate": 3.4549150281252636e-05,
892
+ "loss": 0.5201,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 0.0940203083866115,
897
+ "grad_norm": 0.6497583985328674,
898
+ "learning_rate": 3.3765026539765834e-05,
899
+ "loss": 0.434,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.0947724708537044,
904
+ "grad_norm": 0.6979794502258301,
905
+ "learning_rate": 3.298534127791785e-05,
906
+ "loss": 0.4658,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.09552463332079729,
911
+ "grad_norm": 0.6991776823997498,
912
+ "learning_rate": 3.221030765387417e-05,
913
+ "loss": 0.4666,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.09627679578789018,
918
+ "grad_norm": 0.7159570455551147,
919
+ "learning_rate": 3.144013755408895e-05,
920
+ "loss": 0.4857,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.09702895825498307,
925
+ "grad_norm": 0.7257079482078552,
926
+ "learning_rate": 3.0675041535377405e-05,
927
+ "loss": 0.4721,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.09778112072207597,
932
+ "grad_norm": 0.8166962265968323,
933
+ "learning_rate": 2.991522876735154e-05,
934
+ "loss": 0.4688,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.09853328318916886,
939
+ "grad_norm": 0.7135009765625,
940
+ "learning_rate": 2.916090697523549e-05,
941
+ "loss": 0.4716,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.09928544565626175,
946
+ "grad_norm": 0.7040825486183167,
947
+ "learning_rate": 2.8412282383075363e-05,
948
+ "loss": 0.4395,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.10003760812335465,
953
+ "grad_norm": 0.6619682312011719,
954
+ "learning_rate": 2.766955965735968e-05,
955
+ "loss": 0.4429,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.10078977059044754,
960
+ "grad_norm": 3.492626667022705,
961
+ "learning_rate": 2.693294185106562e-05,
962
+ "loss": 0.4549,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.10154193305754043,
967
+ "grad_norm": 0.6984179615974426,
968
+ "learning_rate": 2.6202630348146324e-05,
969
+ "loss": 0.4452,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.10229409552463332,
974
+ "grad_norm": 0.6764310598373413,
975
+ "learning_rate": 2.547882480847461e-05,
976
+ "loss": 0.4463,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.10304625799172622,
981
+ "grad_norm": 0.7620506882667542,
982
+ "learning_rate": 2.476172311325783e-05,
983
+ "loss": 0.4879,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.10379842045881911,
988
+ "grad_norm": 0.8245807886123657,
989
+ "learning_rate": 2.405152131093926e-05,
990
+ "loss": 0.5092,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.104550582925912,
995
+ "grad_norm": 0.6956287622451782,
996
+ "learning_rate": 2.3348413563600325e-05,
997
+ "loss": 0.4133,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.1053027453930049,
1002
+ "grad_norm": 0.6966294050216675,
1003
+ "learning_rate": 2.2652592093878666e-05,
1004
+ "loss": 0.409,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.10605490786009777,
1009
+ "grad_norm": 0.7121427655220032,
1010
+ "learning_rate": 2.196424713241637e-05,
1011
+ "loss": 0.4373,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.10680707032719067,
1016
+ "grad_norm": 0.7631218433380127,
1017
+ "learning_rate": 2.128356686585282e-05,
1018
+ "loss": 0.4693,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.10755923279428356,
1023
+ "grad_norm": 0.7947872877120972,
1024
+ "learning_rate": 2.061073738537635e-05,
1025
+ "loss": 0.4477,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.10831139526137645,
1030
+ "grad_norm": 0.7450116276741028,
1031
+ "learning_rate": 1.9945942635848748e-05,
1032
+ "loss": 0.4178,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.10906355772846935,
1037
+ "grad_norm": 0.7508375644683838,
1038
+ "learning_rate": 1.928936436551661e-05,
1039
+ "loss": 0.4324,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.10981572019556224,
1044
+ "grad_norm": 0.7978306412696838,
1045
+ "learning_rate": 1.8641182076323148e-05,
1046
+ "loss": 0.4426,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.11056788266265513,
1051
+ "grad_norm": 1.0346444845199585,
1052
+ "learning_rate": 1.800157297483417e-05,
1053
+ "loss": 0.4738,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.11132004512974802,
1058
+ "grad_norm": 0.9142754077911377,
1059
+ "learning_rate": 1.7370711923791567e-05,
1060
+ "loss": 0.5,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.11207220759684092,
1065
+ "grad_norm": 0.8345052003860474,
1066
+ "learning_rate": 1.6748771394307585e-05,
1067
+ "loss": 0.3912,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.11282437006393381,
1072
+ "grad_norm": 2.4534523487091064,
1073
+ "learning_rate": 1.6135921418712956e-05,
1074
+ "loss": 0.4327,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.11282437006393381,
1079
+ "eval_loss": 0.4612102210521698,
1080
+ "eval_runtime": 244.2408,
1081
+ "eval_samples_per_second": 9.167,
1082
+ "eval_steps_per_second": 2.293,
1083
+ "step": 150
1084
  }
1085
  ],
1086
  "logging_steps": 1,
 
1109
  "attributes": {}
1110
  }
1111
  },
1112
+ "total_flos": 3.9155917878460416e+17,
1113
  "train_batch_size": 8,
1114
  "trial_name": null,
1115
  "trial_params": null