nttx commited on
Commit
daa6cd8
·
verified ·
1 Parent(s): 543e5c3

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:fbea8a2fa5072b5a7d723904ee83b99aaf1b0df24818bbce2906e158dda936e6
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74db40158d6463bff8da7b9737717c351d6afd5663de751d113586204680eea
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c7cfe91b4d4f810d0002931f5c1f72e6e67998fedd96e206cb01574b9cd9c2f
3
  size 278249554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff0ffb4d3adc221c120e9c5e394fe4aab86bb1e0d0c84b5f08e80bf33d18fd1
3
  size 278249554
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a48f48f35db283ef3f13194b461f797bfb7469a36344847e7ba1a64f4c7209
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b012af99e011ead35df95669f2be017977bd93f8402ae24d76ee053a3eefdf8
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": 2.184495449066162,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0336388865528551,
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": 37.363,
732
  "eval_steps_per_second": 18.685,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6886051739074560.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1688923835754395,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.05045832982928265,
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": 37.363,
732
  "eval_steps_per_second": 18.685,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03397527541838365,
737
+ "grad_norm": 0.1273975670337677,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 2.5001,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.034311664283912205,
744
+ "grad_norm": 0.1580890268087387,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 2.6171,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.034648053149440756,
751
+ "grad_norm": 0.14681027829647064,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 2.3392,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0349844420149693,
758
+ "grad_norm": 0.16795434057712555,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 2.3509,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03532083088049785,
765
+ "grad_norm": 0.15639738738536835,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 2.2799,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.035657219746026404,
772
+ "grad_norm": 0.1573394536972046,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 2.5607,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.035993608611554956,
779
+ "grad_norm": 0.1536206305027008,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 2.222,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03632999747708351,
786
+ "grad_norm": 0.15485522150993347,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 2.3612,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03666638634261206,
793
+ "grad_norm": 0.14206035435199738,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 2.3203,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.03700277520814061,
800
+ "grad_norm": 0.1353464424610138,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 2.2831,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03733916407366916,
807
+ "grad_norm": 0.12393804639577866,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 2.2349,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.037675552939197714,
814
+ "grad_norm": 0.13074256479740143,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 2.1481,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.038011941804726265,
821
+ "grad_norm": 0.1324545294046402,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 2.2031,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03834833067025482,
828
+ "grad_norm": 0.14374986290931702,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 2.2458,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03868471953578337,
835
+ "grad_norm": 0.12872225046157837,
836
+ "learning_rate": 5e-05,
837
+ "loss": 2.1645,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03902110840131192,
842
+ "grad_norm": 0.12324129045009613,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 2.2346,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.039357497266840465,
849
+ "grad_norm": 0.12691381573677063,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 2.1249,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.039693886132369016,
856
+ "grad_norm": 0.11859089136123657,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 2.0766,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.04003027499789757,
863
+ "grad_norm": 0.12147951871156693,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 2.3106,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.04036666386342612,
870
+ "grad_norm": 0.12418749928474426,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 2.0982,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04070305272895467,
877
+ "grad_norm": 0.12721975147724152,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 2.2366,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.04103944159448322,
884
+ "grad_norm": 0.13671071827411652,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 2.1654,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.041375830460011774,
891
+ "grad_norm": 0.13127440214157104,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 2.2255,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041712219325540326,
898
+ "grad_norm": 0.14041757583618164,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 2.3629,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04204860819106888,
905
+ "grad_norm": 0.12985271215438843,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 2.2141,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.04238499705659743,
912
+ "grad_norm": 0.14057950675487518,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 2.0291,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04272138592212598,
919
+ "grad_norm": 0.1375603973865509,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 2.0766,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.04305777478765453,
926
+ "grad_norm": 0.15876489877700806,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 2.2225,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04339416365318308,
933
+ "grad_norm": 0.1333220899105072,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 2.0972,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.04373055251871163,
940
+ "grad_norm": 0.14338713884353638,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.9242,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04406694138424018,
947
+ "grad_norm": 0.14646734297275543,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 2.1472,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.04440333024976873,
954
+ "grad_norm": 0.14863519370555878,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 2.1101,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04473971911529728,
961
+ "grad_norm": 0.14415816962718964,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 1.9563,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.045076107980825834,
968
+ "grad_norm": 0.1510019600391388,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 2.344,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.045412496846354386,
975
+ "grad_norm": 0.15380419790744781,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 2.0964,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.04574888571188294,
982
+ "grad_norm": 0.15402600169181824,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 2.1511,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04608527457741149,
989
+ "grad_norm": 0.1569417119026184,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 2.2019,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.04642166344294004,
996
+ "grad_norm": 0.15563955903053284,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 2.1347,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04675805230846859,
1003
+ "grad_norm": 0.16049978137016296,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 2.0268,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.047094441173997144,
1010
+ "grad_norm": 0.1715925931930542,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 1.9335,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04743083003952569,
1017
+ "grad_norm": 0.1669202297925949,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.9606,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04776721890505424,
1024
+ "grad_norm": 0.1874368041753769,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 2.1294,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04810360777058279,
1031
+ "grad_norm": 0.19604210555553436,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 2.2134,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04843999663611134,
1038
+ "grad_norm": 0.2135860174894333,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.9938,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.048776385501639895,
1045
+ "grad_norm": 0.21586836874485016,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 2.1866,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.049112774367168446,
1052
+ "grad_norm": 0.21214084327220917,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 2.1615,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.049449163232697,
1059
+ "grad_norm": 0.2273048311471939,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 2.049,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04978555209822555,
1066
+ "grad_norm": 0.2707260251045227,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 2.0469,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0501219409637541,
1073
+ "grad_norm": 0.3056899309158325,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 2.0308,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.05045832982928265,
1080
+ "grad_norm": 0.4177829921245575,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 2.1673,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.05045832982928265,
1087
+ "eval_loss": 2.1688923835754395,
1088
+ "eval_runtime": 135.2349,
1089
+ "eval_samples_per_second": 37.024,
1090
+ "eval_steps_per_second": 18.516,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.032049150918656e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null