nttx commited on
Commit
1343462
·
verified ·
1 Parent(s): da724f8

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 sha256:422c04352ded2799b886574260307725cce2a05e4ac2a386b59f4ab6cbaf2a0c
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:245cfb0e3c67cc5b15c36a6addb7a9a87f7b80bc5b05c497a012863188d6a793
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:301349b156b278c52fd138ee095498476ee7baa792befe2b26ab2b48fc1cc873
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee245058381e6aff9ec8f7bbc5edf46706363b55a562d17c47e5adcae5a5ea57
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ae66241fa7e19201f42b4af9c0b1b7dc5a9f047f2203c049fc8a0855d9ff565
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d561c013e5d918a234ffe067988ca500e7e91f04bfab6a34a74a15f83c177b1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7944371700286865,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.13619339462036092,
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": 11.958,
732
  "eval_steps_per_second": 5.984,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.40632714641408e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7522867918014526,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.20429009193054137,
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": 11.958,
732
  "eval_steps_per_second": 5.984,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.13755532856656452,
737
+ "grad_norm": 0.2067456841468811,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 0.5961,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.13891726251276812,
744
+ "grad_norm": 0.21972322463989258,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 0.5196,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.14027919645897174,
751
+ "grad_norm": 0.22380179166793823,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 0.6496,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.14164113040517534,
758
+ "grad_norm": 0.23384810984134674,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 0.7285,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.14300306435137897,
765
+ "grad_norm": 0.25438612699508667,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 0.696,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.14436499829758256,
772
+ "grad_norm": 0.23733669519424438,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 0.7598,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1457269322437862,
779
+ "grad_norm": 0.2382114678621292,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 0.6886,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1470888661899898,
786
+ "grad_norm": 0.23478229343891144,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 0.6981,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.14845080013619338,
793
+ "grad_norm": 0.2193242460489273,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 0.6531,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.149812734082397,
800
+ "grad_norm": 0.3010532259941101,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 0.7956,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.1511746680286006,
807
+ "grad_norm": 0.27796250581741333,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 0.7316,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.15253660197480423,
814
+ "grad_norm": 0.23366563022136688,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 0.7443,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.15389853592100783,
821
+ "grad_norm": 0.22676481306552887,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 0.6667,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.15526046986721145,
828
+ "grad_norm": 0.25168755650520325,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 0.6867,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.15662240381341505,
835
+ "grad_norm": 0.23510901629924774,
836
+ "learning_rate": 5e-05,
837
+ "loss": 0.7551,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.15798433775961865,
842
+ "grad_norm": 0.24297989904880524,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 0.723,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.15934627170582227,
849
+ "grad_norm": 0.2936830222606659,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 0.7914,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.16070820565202587,
856
+ "grad_norm": 0.32800665497779846,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 0.713,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1620701395982295,
863
+ "grad_norm": 0.285540372133255,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 0.7493,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1634320735444331,
870
+ "grad_norm": 0.32253602147102356,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 0.726,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1647940074906367,
877
+ "grad_norm": 0.30640706419944763,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 0.7065,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.16615594143684032,
884
+ "grad_norm": 0.2831270396709442,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 0.6869,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1675178753830439,
891
+ "grad_norm": 0.31756505370140076,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 0.7338,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.16887980932924754,
898
+ "grad_norm": 0.33590009808540344,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 0.7718,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.17024174327545114,
905
+ "grad_norm": 0.31208398938179016,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 0.6202,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.17160367722165476,
912
+ "grad_norm": 0.3926757872104645,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 0.6732,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.17296561116785836,
919
+ "grad_norm": 0.37769249081611633,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 0.7741,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.17432754511406195,
926
+ "grad_norm": 0.33026885986328125,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 0.6891,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.17568947906026558,
933
+ "grad_norm": 0.36324840784072876,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 0.6293,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.17705141300646918,
940
+ "grad_norm": 0.4438748359680176,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 0.6637,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1784133469526728,
947
+ "grad_norm": 0.437080979347229,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 0.8234,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1797752808988764,
954
+ "grad_norm": 0.4293113350868225,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 0.7818,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.18113721484508002,
961
+ "grad_norm": 0.4313202202320099,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 0.782,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.18249914879128362,
968
+ "grad_norm": 0.4160058796405792,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 0.7241,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.18386108273748722,
975
+ "grad_norm": 0.416565865278244,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 0.7352,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.18522301668369084,
982
+ "grad_norm": 0.48462221026420593,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 0.8697,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.18658495062989444,
989
+ "grad_norm": 0.3931826651096344,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.735,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.18794688457609807,
996
+ "grad_norm": 0.5121709108352661,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 0.8023,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.18930881852230166,
1003
+ "grad_norm": 0.4136485457420349,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 0.7394,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1906707524685053,
1010
+ "grad_norm": 0.44947853684425354,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 0.751,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1920326864147089,
1017
+ "grad_norm": 0.46959882974624634,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 0.8248,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.19339462036091248,
1024
+ "grad_norm": 0.47862911224365234,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 0.7799,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1947565543071161,
1031
+ "grad_norm": 0.4101274609565735,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 0.7949,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1961184882533197,
1038
+ "grad_norm": 0.4547268748283386,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 0.8562,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.19748042219952333,
1045
+ "grad_norm": 0.4429760277271271,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 0.7845,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.19884235614572693,
1052
+ "grad_norm": 0.45933544635772705,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 0.7277,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.20020429009193055,
1059
+ "grad_norm": 0.4962371289730072,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.7611,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.20156622403813415,
1066
+ "grad_norm": 0.6105312705039978,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.9267,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.20292815798433775,
1073
+ "grad_norm": 0.6516053676605225,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.6398,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.20429009193054137,
1080
+ "grad_norm": 1.3799935579299927,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 1.106,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.20429009193054137,
1087
+ "eval_loss": 0.7522867918014526,
1088
+ "eval_runtime": 103.5151,
1089
+ "eval_samples_per_second": 11.95,
1090
+ "eval_steps_per_second": 5.98,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.10612630061056e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null