lesso03 commited on
Commit
2c691ce
·
verified ·
1 Parent(s): 1e12f2b

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 sha256:055585458b28908a53e7a290425a54b3b1745a3e9c74f81a8c6c84789c6ecba4
3
  size 628216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c91c9532837237ea4062f1f0b6f2de1d5dc113e31312ff2ca5c19542aeac14
3
  size 628216
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4cb9e8286539e696f4f93a655676b74c4fbb93300e437e41a5672af7c218025
3
  size 352122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c479332b4c52e0ac61588aae3132a40ade7f4f9b712a49e15b426e253f6a70c5
3
  size 352122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce6f56e5624b6b2e49b32ad01ce929d07df6db745bb110af4de7d64e80462995
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eedfc8f02bb8d7d8cd34189a19c0d8b5ce8c0f6ca78a177ffef92beb953688d7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b2ff91019f251b72cdf781986424ccdfd5ceb7ae633fedb2bccce31d3f61847
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970068ebf9c0dc6a40c93653c563bb0b2ba5296a6c46496b504a3f1343bf3a62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.527392387390137,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0880281690140845,
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": 66.324,
732
  "eval_steps_per_second": 16.607,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 68310112665600.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.495588302612305,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.13204225352112675,
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": 66.324,
732
  "eval_steps_per_second": 16.607,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08890845070422536,
737
+ "grad_norm": 0.5941808819770813,
738
+ "learning_rate": 5.8634982137913465e-05,
739
+ "loss": 10.5435,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0897887323943662,
744
+ "grad_norm": 0.5891147255897522,
745
+ "learning_rate": 5.772710650702723e-05,
746
+ "loss": 10.5219,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.09066901408450705,
751
+ "grad_norm": 0.6356647610664368,
752
+ "learning_rate": 5.681848531245195e-05,
753
+ "loss": 10.5299,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.09154929577464789,
758
+ "grad_norm": 0.5486959218978882,
759
+ "learning_rate": 5.590936696214972e-05,
760
+ "loss": 10.5153,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.09242957746478873,
765
+ "grad_norm": 0.5351731181144714,
766
+ "learning_rate": 5.5e-05,
767
+ "loss": 10.5248,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.09330985915492958,
772
+ "grad_norm": 0.5519973635673523,
773
+ "learning_rate": 5.409063303785029e-05,
774
+ "loss": 10.5358,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09419014084507042,
779
+ "grad_norm": 0.5336778163909912,
780
+ "learning_rate": 5.318151468754805e-05,
781
+ "loss": 10.5088,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09507042253521127,
786
+ "grad_norm": 0.4727165997028351,
787
+ "learning_rate": 5.227289349297277e-05,
788
+ "loss": 10.5292,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.09595070422535211,
793
+ "grad_norm": 0.5302690267562866,
794
+ "learning_rate": 5.136501786208654e-05,
795
+ "loss": 10.5202,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09683098591549295,
800
+ "grad_norm": 0.5168509483337402,
801
+ "learning_rate": 5.045813599902173e-05,
802
+ "loss": 10.5157,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0977112676056338,
807
+ "grad_norm": 0.4725133776664734,
808
+ "learning_rate": 4.955249583622455e-05,
809
+ "loss": 10.4946,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09859154929577464,
814
+ "grad_norm": 0.45433416962623596,
815
+ "learning_rate": 4.8648344966672767e-05,
816
+ "loss": 10.5199,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0994718309859155,
821
+ "grad_norm": 0.42494186758995056,
822
+ "learning_rate": 4.774593057618621e-05,
823
+ "loss": 10.4857,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.10035211267605634,
828
+ "grad_norm": 0.35899239778518677,
829
+ "learning_rate": 4.6845499375848686e-05,
830
+ "loss": 10.5143,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.10123239436619719,
835
+ "grad_norm": 0.3459785282611847,
836
+ "learning_rate": 4.5947297534559625e-05,
837
+ "loss": 10.5069,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.10211267605633803,
842
+ "grad_norm": 0.3599611222743988,
843
+ "learning_rate": 4.5051570611733976e-05,
844
+ "loss": 10.5378,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.10299295774647887,
849
+ "grad_norm": 0.3270639479160309,
850
+ "learning_rate": 4.415856349016859e-05,
851
+ "loss": 10.5354,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10387323943661972,
856
+ "grad_norm": 0.3274960219860077,
857
+ "learning_rate": 4.326852030909393e-05,
858
+ "loss": 10.4849,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10475352112676056,
863
+ "grad_norm": 0.3062029182910919,
864
+ "learning_rate": 4.238168439742867e-05,
865
+ "loss": 10.5315,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1056338028169014,
870
+ "grad_norm": 0.3626440763473511,
871
+ "learning_rate": 4.149829820725605e-05,
872
+ "loss": 10.5202,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10651408450704225,
877
+ "grad_norm": 0.3809753656387329,
878
+ "learning_rate": 4.0618603247539916e-05,
879
+ "loss": 10.5317,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1073943661971831,
884
+ "grad_norm": 0.3086736798286438,
885
+ "learning_rate": 3.9742840018098564e-05,
886
+ "loss": 10.5318,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10827464788732394,
891
+ "grad_norm": 0.3391195237636566,
892
+ "learning_rate": 3.887124794385445e-05,
893
+ "loss": 10.5107,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10915492957746478,
898
+ "grad_norm": 0.34638404846191406,
899
+ "learning_rate": 3.80040653093779e-05,
900
+ "loss": 10.5355,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.11003521126760564,
905
+ "grad_norm": 0.45098984241485596,
906
+ "learning_rate": 3.714152919374241e-05,
907
+ "loss": 10.55,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.11091549295774648,
912
+ "grad_norm": 0.39215147495269775,
913
+ "learning_rate": 3.628387540570963e-05,
914
+ "loss": 10.5317,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.11179577464788733,
919
+ "grad_norm": 0.3315400779247284,
920
+ "learning_rate": 3.543133841926159e-05,
921
+ "loss": 10.5396,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.11267605633802817,
926
+ "grad_norm": 0.3427654504776001,
927
+ "learning_rate": 3.458415130949785e-05,
928
+ "loss": 10.5269,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.11355633802816902,
933
+ "grad_norm": 0.33311086893081665,
934
+ "learning_rate": 3.374254568891514e-05,
935
+ "loss": 10.5672,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11443661971830986,
940
+ "grad_norm": 0.31714025139808655,
941
+ "learning_rate": 3.290675164408669e-05,
942
+ "loss": 10.5272,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1153169014084507,
947
+ "grad_norm": 0.37221792340278625,
948
+ "learning_rate": 3.207699767275904e-05,
949
+ "loss": 10.5114,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.11619718309859155,
954
+ "grad_norm": 0.298801451921463,
955
+ "learning_rate": 3.12535106213829e-05,
956
+ "loss": 10.5184,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11707746478873239,
961
+ "grad_norm": 0.3310137093067169,
962
+ "learning_rate": 3.0436515623095647e-05,
963
+ "loss": 10.5289,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11795774647887323,
968
+ "grad_norm": 0.3380754590034485,
969
+ "learning_rate": 2.962623603617218e-05,
970
+ "loss": 10.5012,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11883802816901408,
975
+ "grad_norm": 0.32100123167037964,
976
+ "learning_rate": 2.8822893382960955e-05,
977
+ "loss": 10.5141,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11971830985915492,
982
+ "grad_norm": 0.3254896402359009,
983
+ "learning_rate": 2.802670728932207e-05,
984
+ "loss": 10.5539,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.12059859154929578,
989
+ "grad_norm": 0.3702283799648285,
990
+ "learning_rate": 2.723789542458361e-05,
991
+ "loss": 10.512,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.12147887323943662,
996
+ "grad_norm": 0.32699835300445557,
997
+ "learning_rate": 2.6456673442033183e-05,
998
+ "loss": 10.5026,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.12235915492957747,
1003
+ "grad_norm": 0.33314529061317444,
1004
+ "learning_rate": 2.5683254919960356e-05,
1005
+ "loss": 10.5311,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.12323943661971831,
1010
+ "grad_norm": 0.3764292597770691,
1011
+ "learning_rate": 2.4917851303266533e-05,
1012
+ "loss": 10.4995,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.12411971830985916,
1017
+ "grad_norm": 0.3277135491371155,
1018
+ "learning_rate": 2.4160671845658007e-05,
1019
+ "loss": 10.5025,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.125,
1024
+ "grad_norm": 0.3547554314136505,
1025
+ "learning_rate": 2.3411923552438105e-05,
1026
+ "loss": 10.5012,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12588028169014084,
1031
+ "grad_norm": 0.3986217677593231,
1032
+ "learning_rate": 2.2671811123913983e-05,
1033
+ "loss": 10.451,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1267605633802817,
1038
+ "grad_norm": 0.37957799434661865,
1039
+ "learning_rate": 2.194053689943362e-05,
1040
+ "loss": 10.4798,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12764084507042253,
1045
+ "grad_norm": 0.3498072028160095,
1046
+ "learning_rate": 2.121830080206827e-05,
1047
+ "loss": 10.5078,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12852112676056338,
1052
+ "grad_norm": 0.36097705364227295,
1053
+ "learning_rate": 2.0505300283955464e-05,
1054
+ "loss": 10.4758,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12940140845070422,
1059
+ "grad_norm": 0.30697742104530334,
1060
+ "learning_rate": 1.9801730272317585e-05,
1061
+ "loss": 10.5026,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.13028169014084506,
1066
+ "grad_norm": 0.42456531524658203,
1067
+ "learning_rate": 1.910778311617072e-05,
1068
+ "loss": 10.4967,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1311619718309859,
1073
+ "grad_norm": 0.47736701369285583,
1074
+ "learning_rate": 1.8423648533738342e-05,
1075
+ "loss": 10.5141,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.13204225352112675,
1080
+ "grad_norm": 0.5607922673225403,
1081
+ "learning_rate": 1.7749513560584252e-05,
1082
+ "loss": 10.5202,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.13204225352112675,
1087
+ "eval_loss": 10.495588302612305,
1088
+ "eval_runtime": 26.6017,
1089
+ "eval_samples_per_second": 71.913,
1090
+ "eval_steps_per_second": 18.006,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 102465168998400.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null