cimol commited on
Commit
03bdf53
·
verified ·
1 Parent(s): 38eae47

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 sha256:20d7b5750e390a583c7cb0e5aa22126b79f1141cd55a85bdfae862285c5dbeb3
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89ec1e9638ed76165803d79147b54d577585ba5242b5fd75c5ee89982ae4d27
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b1d9ff424d4437d4570e581c5618d4052c48b34af48402b5bedfa4e84e5dfd
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fea6c134aaa58f30f73e71ac9304599c97c2d9f44c4e3f21167af23eb1b94e3
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93e088181ed40a6a7d28371a96c2f57e18f05fdb2765b2f5c3003fbd9e558a03
3
  size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc81f77d7316d707510b1fbca803d63e49aa1dea806744080c8ec6bd55d08c9
3
  size 14180
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26348e70deb5f7d6cee52f5eb084c0e6829440001a3c6d0128b93cd074af8c2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9069808721542358,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11590843233845262,
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": 14.113,
732
  "eval_steps_per_second": 3.535,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.42188868534272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8716882467269897,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.17386264850767894,
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": 14.113,
732
  "eval_steps_per_second": 3.535,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11706751666183715,
737
+ "grad_norm": 0.9020504355430603,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 1.8005,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.11822660098522167,
744
+ "grad_norm": 0.9559862017631531,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 1.6962,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1193856853086062,
751
+ "grad_norm": 0.8908179998397827,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 1.5416,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.12054476963199073,
758
+ "grad_norm": 0.965055525302887,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 1.7021,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.12170385395537525,
765
+ "grad_norm": 0.9545097351074219,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 1.7077,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.12286293827875978,
772
+ "grad_norm": 0.8789839744567871,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 1.6907,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.1240220226021443,
779
+ "grad_norm": 0.9204549193382263,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 1.8361,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12518110692552883,
786
+ "grad_norm": 0.8684341907501221,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 1.3899,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12634019124891335,
793
+ "grad_norm": 0.8618979454040527,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 1.6929,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12749927557229787,
800
+ "grad_norm": 0.8302251696586609,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 1.6305,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.12865835989568242,
807
+ "grad_norm": 0.8745705485343933,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 1.6055,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.12981744421906694,
814
+ "grad_norm": 0.9069314002990723,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 1.7571,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.13097652854245145,
821
+ "grad_norm": 0.778761088848114,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 1.9406,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.132135612865836,
828
+ "grad_norm": 0.7695782780647278,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 1.5923,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.13329469718922052,
835
+ "grad_norm": 0.8184890747070312,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 1.854,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.13445378151260504,
842
+ "grad_norm": 0.8314237594604492,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 1.7508,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13561286583598955,
849
+ "grad_norm": 0.8324970006942749,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 1.655,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1367719501593741,
856
+ "grad_norm": 0.8983815312385559,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 1.4791,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.13793103448275862,
863
+ "grad_norm": 1.0721842050552368,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 1.771,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.13909011880614314,
870
+ "grad_norm": 0.9828131198883057,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 1.7514,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.14024920312952768,
877
+ "grad_norm": 0.9020130038261414,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 1.6603,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1414082874529122,
884
+ "grad_norm": 0.8191699385643005,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 1.9196,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.14256737177629672,
891
+ "grad_norm": 0.9802734851837158,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 1.8362,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.14372645609968127,
898
+ "grad_norm": 1.0552587509155273,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 1.6664,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.14488554042306578,
905
+ "grad_norm": 1.0432603359222412,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 1.9196,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1460446247464503,
912
+ "grad_norm": 0.8617227673530579,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 1.7895,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.14720370906983482,
919
+ "grad_norm": 0.8730562925338745,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 1.6361,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.14836279339321937,
926
+ "grad_norm": 1.1478852033615112,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 1.787,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.14952187771660388,
933
+ "grad_norm": 0.9960713386535645,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 1.8575,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1506809620399884,
940
+ "grad_norm": 0.9440626502037048,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 1.8637,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.15184004636337295,
947
+ "grad_norm": 0.9226197600364685,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 1.4851,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.15299913068675747,
954
+ "grad_norm": 1.0220212936401367,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 2.0019,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.15415821501014199,
961
+ "grad_norm": 1.0858938694000244,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 1.9601,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1553172993335265,
968
+ "grad_norm": 1.118869662284851,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 2.116,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.15647638365691105,
975
+ "grad_norm": 1.1299121379852295,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 1.9567,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.15763546798029557,
982
+ "grad_norm": 1.0660128593444824,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 2.0813,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1587945523036801,
989
+ "grad_norm": 1.04646635055542,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 2.0143,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.15995363662706463,
996
+ "grad_norm": 1.346009612083435,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 2.1689,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.16111272095044915,
1003
+ "grad_norm": 1.1610443592071533,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 1.8776,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.16227180527383367,
1010
+ "grad_norm": 1.213167428970337,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 1.8295,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1634308895972182,
1017
+ "grad_norm": 1.262817144393921,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 2.0162,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.16458997392060273,
1024
+ "grad_norm": 1.1960244178771973,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 2.0135,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.16574905824398725,
1031
+ "grad_norm": 1.4533637762069702,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 2.1179,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16690814256737177,
1038
+ "grad_norm": 1.24979829788208,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 2.0279,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16806722689075632,
1045
+ "grad_norm": 1.637749433517456,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 1.9962,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.16922631121414083,
1052
+ "grad_norm": 1.410517930984497,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 2.1153,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.17038539553752535,
1059
+ "grad_norm": 1.4992858171463013,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 2.3065,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.17154447986090987,
1066
+ "grad_norm": 1.6460627317428589,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 2.3188,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.17270356418429442,
1073
+ "grad_norm": 2.2003891468048096,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 2.3582,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.17386264850767894,
1080
+ "grad_norm": 3.3022475242614746,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 2.8047,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.17386264850767894,
1087
+ "eval_loss": 1.8716882467269897,
1088
+ "eval_runtime": 102.9822,
1089
+ "eval_samples_per_second": 14.109,
1090
+ "eval_steps_per_second": 3.535,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.13283302801408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null