cimol commited on
Commit
21acfb5
·
verified ·
1 Parent(s): 045e29d

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 sha256:3a82b07bcc5d5e85facebbcdacbae04bbc0df271ea556dda41feac9126588bac
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a5ccfb98de4d6f80d5837e47aa1f84e24baf59e16727744e91bf214a2a01a1
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792c324cf66f0471027d0131d57e265cb516980a227e648bf17243e9c400f1be
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f93e3c4252e719fb8a30907a5d399b5e08d810501ab448d20b65e2961cd22527
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16902029130043a56d1526f5b4b80f7a5a1d40115ad5b5d8f653761803a5fb5a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a1ea08ccda8d30027e92f45893c70b3930f49c86ce39f913cdccab9295a850
3
  size 14244
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": 1.758233666419983,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.022485805835066614,
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": 155.964,
732
  "eval_steps_per_second": 39.001,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2111427456270336.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6964772939682007,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03372870875259992,
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": 155.964,
732
  "eval_steps_per_second": 39.001,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02271066389341728,
737
+ "grad_norm": 6.575685501098633,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 7.2894,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.022935521951767946,
744
+ "grad_norm": 6.561682224273682,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 6.4716,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.023160380010118612,
751
+ "grad_norm": 5.794161319732666,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 7.337,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.023385238068469278,
758
+ "grad_norm": 5.027132987976074,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 6.8254,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.023610096126819944,
765
+ "grad_norm": 4.253400802612305,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 6.682,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.02383495418517061,
772
+ "grad_norm": 4.0080976486206055,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 6.9726,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.024059812243521276,
779
+ "grad_norm": 3.925318956375122,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 7.1604,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.024284670301871942,
786
+ "grad_norm": 3.8543312549591064,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 7.5658,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.024509528360222608,
793
+ "grad_norm": 3.496502161026001,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 7.2625,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.024734386418573277,
800
+ "grad_norm": 3.215040683746338,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 7.118,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.024959244476923943,
807
+ "grad_norm": 3.2703866958618164,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 7.3476,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02518410253527461,
814
+ "grad_norm": 3.07417631149292,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 7.2336,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.025408960593625275,
821
+ "grad_norm": 2.8557777404785156,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 7.4806,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.02563381865197594,
828
+ "grad_norm": 3.039578437805176,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 7.6272,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.025858676710326607,
835
+ "grad_norm": 2.9298548698425293,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 7.2133,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.026083534768677273,
842
+ "grad_norm": 3.0700254440307617,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 7.0055,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02630839282702794,
849
+ "grad_norm": 3.125459909439087,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 7.3118,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.026533250885378605,
856
+ "grad_norm": 3.14284348487854,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 7.2339,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02675810894372927,
863
+ "grad_norm": 3.078021764755249,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 7.3749,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.026982967002079937,
870
+ "grad_norm": 3.031780242919922,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 6.9027,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.027207825060430603,
877
+ "grad_norm": 3.0387516021728516,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 7.2115,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02743268311878127,
884
+ "grad_norm": 2.979473114013672,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 6.9756,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.027657541177131935,
891
+ "grad_norm": 3.1113784313201904,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 7.3174,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0278823992354826,
898
+ "grad_norm": 3.0304317474365234,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 7.1829,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.028107257293833267,
905
+ "grad_norm": 3.099127769470215,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 7.318,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.028332115352183933,
912
+ "grad_norm": 2.9800901412963867,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 6.64,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0285569734105346,
919
+ "grad_norm": 2.998429298400879,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 6.9941,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.028781831468885265,
926
+ "grad_norm": 3.0381429195404053,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 6.9807,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.02900668952723593,
933
+ "grad_norm": 3.2804617881774902,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 6.793,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0292315475855866,
940
+ "grad_norm": 3.163376808166504,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 6.9028,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.029456405643937266,
947
+ "grad_norm": 3.193079948425293,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 6.8241,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.029681263702287932,
954
+ "grad_norm": 3.1600944995880127,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 6.7863,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.029906121760638598,
961
+ "grad_norm": 3.254242181777954,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 7.0383,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.030130979818989264,
968
+ "grad_norm": 3.606218099594116,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 7.2774,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03035583787733993,
975
+ "grad_norm": 3.574589729309082,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 7.4021,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.030580695935690596,
982
+ "grad_norm": 3.768498182296753,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 7.3057,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.030805553994041262,
989
+ "grad_norm": 3.9681766033172607,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 7.0184,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.031030412052391928,
996
+ "grad_norm": 4.057465553283691,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 6.977,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03125527011074259,
1003
+ "grad_norm": 4.279487609863281,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 6.9698,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03148012816909326,
1010
+ "grad_norm": 4.120497703552246,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 7.0837,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03170498622744393,
1017
+ "grad_norm": 4.96183967590332,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 7.4653,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.031929844285794595,
1024
+ "grad_norm": 4.879161357879639,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 7.0564,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03215470234414526,
1031
+ "grad_norm": 4.891727447509766,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 6.9364,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03237956040249593,
1038
+ "grad_norm": 5.83298397064209,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 7.1989,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03260441846084659,
1045
+ "grad_norm": 6.435450077056885,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 7.4763,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03282927651919726,
1052
+ "grad_norm": 6.232485771179199,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 7.0989,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.033054134577547925,
1059
+ "grad_norm": 8.634939193725586,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 7.3157,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.03327899263589859,
1066
+ "grad_norm": 7.819792747497559,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 7.7224,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03350385069424926,
1073
+ "grad_norm": 10.099474906921387,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 7.0663,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03372870875259992,
1080
+ "grad_norm": 13.547322273254395,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 7.1442,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03372870875259992,
1087
+ "eval_loss": 1.6964772939682007,
1088
+ "eval_runtime": 48.0755,
1089
+ "eval_samples_per_second": 155.797,
1090
+ "eval_steps_per_second": 38.96,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3169492439924736.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null