lesso commited on
Commit
0f3bfef
·
verified ·
1 Parent(s): 67964c5

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 sha256:77e8b6c5004cadadcee7bffe3f18c4df91c7b2344bc6ac431bbabd26d942180d
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b6a6698d0033f48ff71e532bd489a4f7781febf2eb9f753a64958645322a97
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42a984aa5f63bf027215664d1a58bcd0e008839c332182dfc76555c78dd01792
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fad096a04b3b6b7a1dcba76120392e4bed9f14f7a0a0ca6ed8ec930dd20a537
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d4f82194923c4e839c5b924f9c84d17ba32c8dc232adb7a3f482821b860cb9e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4516ce3b22c94085368cebacdccc1b800c7c499b843c80d9eda4fcde1256d71
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a046f3bc9d619a7e62601f3cf33ff02f6ad189db5b564eab88c1bb00e13b059d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7431a5f5e7b667e1ad74dfbaf504ae1d5a622ff6eb54e4f385c161883d2319ba
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6350612640380859,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10085728693898134,
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": 4.128,
732
  "eval_steps_per_second": 1.037,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.648580773235917e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6004561185836792,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.15128593040847202,
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": 4.128,
732
  "eval_steps_per_second": 1.037,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10186585980837115,
737
+ "grad_norm": 0.6304985284805298,
738
+ "learning_rate": 5.278263157894736e-05,
739
+ "loss": 0.6333,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10287443267776097,
744
+ "grad_norm": 0.657425582408905,
745
+ "learning_rate": 5.224947368421053e-05,
746
+ "loss": 0.6568,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10388300554715078,
751
+ "grad_norm": 0.6474046111106873,
752
+ "learning_rate": 5.171631578947368e-05,
753
+ "loss": 0.6507,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10489157841654059,
758
+ "grad_norm": 0.5701997876167297,
759
+ "learning_rate": 5.1183157894736844e-05,
760
+ "loss": 0.5213,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1059001512859304,
765
+ "grad_norm": 0.7110328078269958,
766
+ "learning_rate": 5.065e-05,
767
+ "loss": 0.6446,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.10690872415532023,
772
+ "grad_norm": 0.6299896836280823,
773
+ "learning_rate": 5.011684210526315e-05,
774
+ "loss": 0.6171,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.10791729702471003,
779
+ "grad_norm": 0.6035848259925842,
780
+ "learning_rate": 4.958368421052631e-05,
781
+ "loss": 0.5564,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.10892586989409984,
786
+ "grad_norm": 0.5997840762138367,
787
+ "learning_rate": 4.9050526315789473e-05,
788
+ "loss": 0.535,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.10993444276348967,
793
+ "grad_norm": 0.5649349093437195,
794
+ "learning_rate": 4.851736842105263e-05,
795
+ "loss": 0.512,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11094301563287948,
800
+ "grad_norm": 0.593234658241272,
801
+ "learning_rate": 4.798421052631579e-05,
802
+ "loss": 0.5578,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11195158850226929,
807
+ "grad_norm": 0.5817257165908813,
808
+ "learning_rate": 4.745105263157895e-05,
809
+ "loss": 0.4697,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1129601613716591,
814
+ "grad_norm": 0.718417227268219,
815
+ "learning_rate": 4.69178947368421e-05,
816
+ "loss": 0.6312,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.11396873424104892,
821
+ "grad_norm": 0.6626138091087341,
822
+ "learning_rate": 4.638473684210526e-05,
823
+ "loss": 0.5298,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.11497730711043873,
828
+ "grad_norm": 0.5936358571052551,
829
+ "learning_rate": 4.585157894736842e-05,
830
+ "loss": 0.5694,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11598587997982854,
835
+ "grad_norm": 0.7257938981056213,
836
+ "learning_rate": 4.531842105263158e-05,
837
+ "loss": 0.6649,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.11699445284921836,
842
+ "grad_norm": 0.655558168888092,
843
+ "learning_rate": 4.478526315789473e-05,
844
+ "loss": 0.5476,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.11800302571860817,
849
+ "grad_norm": 0.6805459856987,
850
+ "learning_rate": 4.425210526315789e-05,
851
+ "loss": 0.6192,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.11901159858799798,
856
+ "grad_norm": 0.597497284412384,
857
+ "learning_rate": 4.3718947368421054e-05,
858
+ "loss": 0.6358,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1200201714573878,
863
+ "grad_norm": 0.7054476141929626,
864
+ "learning_rate": 4.318578947368421e-05,
865
+ "loss": 0.6072,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12102874432677761,
870
+ "grad_norm": 0.6450152397155762,
871
+ "learning_rate": 4.265263157894736e-05,
872
+ "loss": 0.5918,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12203731719616742,
877
+ "grad_norm": 0.7899286150932312,
878
+ "learning_rate": 4.211947368421052e-05,
879
+ "loss": 0.6354,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12304589006555723,
884
+ "grad_norm": 0.6962209939956665,
885
+ "learning_rate": 4.1586315789473684e-05,
886
+ "loss": 0.6092,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12405446293494705,
891
+ "grad_norm": 0.6939642429351807,
892
+ "learning_rate": 4.105315789473684e-05,
893
+ "loss": 0.6738,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12506303580433686,
898
+ "grad_norm": 0.6824154257774353,
899
+ "learning_rate": 4.052e-05,
900
+ "loss": 0.5981,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.1260716086737267,
905
+ "grad_norm": 0.8214277625083923,
906
+ "learning_rate": 3.998684210526316e-05,
907
+ "loss": 0.683,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.12708018154311648,
912
+ "grad_norm": 0.6997233033180237,
913
+ "learning_rate": 3.945368421052631e-05,
914
+ "loss": 0.5209,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1280887544125063,
919
+ "grad_norm": 0.6340212821960449,
920
+ "learning_rate": 3.892052631578947e-05,
921
+ "loss": 0.5186,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.12909732728189613,
926
+ "grad_norm": 0.7321391105651855,
927
+ "learning_rate": 3.838736842105263e-05,
928
+ "loss": 0.6427,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13010590015128592,
933
+ "grad_norm": 0.6723092198371887,
934
+ "learning_rate": 3.785421052631579e-05,
935
+ "loss": 0.5644,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.13111447302067575,
940
+ "grad_norm": 0.623358428478241,
941
+ "learning_rate": 3.732105263157894e-05,
942
+ "loss": 0.5425,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.13212304589006554,
947
+ "grad_norm": 0.6881217956542969,
948
+ "learning_rate": 3.67878947368421e-05,
949
+ "loss": 0.5754,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13313161875945537,
954
+ "grad_norm": 0.6256353855133057,
955
+ "learning_rate": 3.6254736842105264e-05,
956
+ "loss": 0.4695,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1341401916288452,
961
+ "grad_norm": 0.6997880935668945,
962
+ "learning_rate": 3.572157894736842e-05,
963
+ "loss": 0.6436,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.13514876449823499,
968
+ "grad_norm": 0.7259771227836609,
969
+ "learning_rate": 3.518842105263158e-05,
970
+ "loss": 0.7452,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1361573373676248,
975
+ "grad_norm": 0.7375533580780029,
976
+ "learning_rate": 3.465526315789473e-05,
977
+ "loss": 0.6674,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.13716591023701463,
982
+ "grad_norm": 0.688176155090332,
983
+ "learning_rate": 3.4122105263157894e-05,
984
+ "loss": 0.5481,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.13817448310640443,
989
+ "grad_norm": 0.7129572033882141,
990
+ "learning_rate": 3.358894736842105e-05,
991
+ "loss": 0.5402,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.13918305597579425,
996
+ "grad_norm": 0.6742794513702393,
997
+ "learning_rate": 3.305578947368421e-05,
998
+ "loss": 0.6299,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14019162884518407,
1003
+ "grad_norm": 0.8150436282157898,
1004
+ "learning_rate": 3.252263157894737e-05,
1005
+ "loss": 0.6669,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14120020171457387,
1010
+ "grad_norm": 0.7546499371528625,
1011
+ "learning_rate": 3.198947368421052e-05,
1012
+ "loss": 0.6197,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1422087745839637,
1017
+ "grad_norm": 0.8013685345649719,
1018
+ "learning_rate": 3.1456315789473684e-05,
1019
+ "loss": 0.6482,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14321734745335352,
1024
+ "grad_norm": 0.8201075792312622,
1025
+ "learning_rate": 3.092315789473684e-05,
1026
+ "loss": 0.6275,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.1442259203227433,
1031
+ "grad_norm": 0.8007090091705322,
1032
+ "learning_rate": 3.039e-05,
1033
+ "loss": 0.6123,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.14523449319213314,
1038
+ "grad_norm": 0.8586010336875916,
1039
+ "learning_rate": 2.9856842105263153e-05,
1040
+ "loss": 0.6833,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.14624306606152296,
1045
+ "grad_norm": 0.9494766592979431,
1046
+ "learning_rate": 2.9323684210526317e-05,
1047
+ "loss": 0.7954,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.14725163893091275,
1052
+ "grad_norm": 0.9342161417007446,
1053
+ "learning_rate": 2.879052631578947e-05,
1054
+ "loss": 0.7145,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.14826021180030258,
1059
+ "grad_norm": 0.9246038794517517,
1060
+ "learning_rate": 2.8257368421052628e-05,
1061
+ "loss": 0.7267,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.14926878466969237,
1066
+ "grad_norm": 0.8764268755912781,
1067
+ "learning_rate": 2.772421052631579e-05,
1068
+ "loss": 0.6536,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1502773575390822,
1073
+ "grad_norm": 0.9802453517913818,
1074
+ "learning_rate": 2.7191052631578946e-05,
1075
+ "loss": 0.7393,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.15128593040847202,
1080
+ "grad_norm": 1.1440014839172363,
1081
+ "learning_rate": 2.6657894736842104e-05,
1082
+ "loss": 0.7151,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.15128593040847202,
1087
+ "eval_loss": 0.6004561185836792,
1088
+ "eval_runtime": 101.2647,
1089
+ "eval_samples_per_second": 4.128,
1090
+ "eval_steps_per_second": 1.037,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2972871159853875e+17,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null