lesso commited on
Commit
10fb159
·
verified ·
1 Parent(s): bbb9862

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 sha256:4d561497c736e2816736609ddeae1b14309f35ec7e8b6f4d73b0379be0cce77b
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa94b20e98465ff50becad5b95af7319e7d524361503c6dddeb8c4b911d810df
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aefd8a34c144f8298e72c1c15b3f26487203a974eb4e98c9b0e8daa16ded6e9
3
  size 406743412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fe41bcfdb8dbdfd4f8abcec82e6a75ae6e39a18131ff23f98c3fbc4de03878
3
  size 406743412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcbf7d5e4aa7b38b8ebe707846794c5b3732e8a4cdd09857174a2fb83ed221a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba8ede8b1ce1289bd047fa1b015e236ff2970647049d9ac45b408f024313221
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3388093bd4c4d331382d0016aa94fd7868af3fa4dd50305298d21879ce809e93
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16a9a2b8856e8f64eb7194578c6fcbc8625033d1caa318cc7b80ad824088880
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0389878749847412,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0035031791350650715,
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": 5.871,
732
  "eval_steps_per_second": 1.468,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.236995582748262e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9562696814537048,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.005254768702597608,
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": 5.871,
732
  "eval_steps_per_second": 1.468,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0035382109264157223,
737
+ "grad_norm": 4.139260292053223,
738
+ "learning_rate": 5.219384210526315e-05,
739
+ "loss": 0.9736,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.003573242717766373,
744
+ "grad_norm": 6.691173553466797,
745
+ "learning_rate": 5.1666631578947374e-05,
746
+ "loss": 1.3439,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0036082745091170236,
751
+ "grad_norm": 6.3341522216796875,
752
+ "learning_rate": 5.113942105263158e-05,
753
+ "loss": 1.0342,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0036433063004676744,
758
+ "grad_norm": 4.959275722503662,
759
+ "learning_rate": 5.061221052631579e-05,
760
+ "loss": 0.9322,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0036783380918183253,
765
+ "grad_norm": 6.011504173278809,
766
+ "learning_rate": 5.0085e-05,
767
+ "loss": 0.9757,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0037133698831689757,
772
+ "grad_norm": 4.780364513397217,
773
+ "learning_rate": 4.955778947368421e-05,
774
+ "loss": 0.9653,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0037484016745196265,
779
+ "grad_norm": 5.768011093139648,
780
+ "learning_rate": 4.903057894736842e-05,
781
+ "loss": 0.9648,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0037834334658702774,
786
+ "grad_norm": 4.847964763641357,
787
+ "learning_rate": 4.850336842105263e-05,
788
+ "loss": 0.8899,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.003818465257220928,
793
+ "grad_norm": 6.667684555053711,
794
+ "learning_rate": 4.797615789473684e-05,
795
+ "loss": 1.184,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0038534970485715786,
800
+ "grad_norm": 9.475594520568848,
801
+ "learning_rate": 4.744894736842105e-05,
802
+ "loss": 1.221,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0038885288399222295,
807
+ "grad_norm": 7.665887832641602,
808
+ "learning_rate": 4.692173684210526e-05,
809
+ "loss": 1.4043,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.00392356063127288,
814
+ "grad_norm": 7.966034889221191,
815
+ "learning_rate": 4.639452631578947e-05,
816
+ "loss": 1.38,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.003958592422623531,
821
+ "grad_norm": 9.061517715454102,
822
+ "learning_rate": 4.586731578947368e-05,
823
+ "loss": 1.5917,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0039936242139741816,
828
+ "grad_norm": 7.534801006317139,
829
+ "learning_rate": 4.5340105263157894e-05,
830
+ "loss": 1.2386,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.004028656005324832,
835
+ "grad_norm": 7.485569477081299,
836
+ "learning_rate": 4.48128947368421e-05,
837
+ "loss": 1.1133,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.004063687796675483,
842
+ "grad_norm": 7.044865608215332,
843
+ "learning_rate": 4.428568421052632e-05,
844
+ "loss": 1.0751,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.004098719588026134,
849
+ "grad_norm": 12.4927978515625,
850
+ "learning_rate": 4.3758473684210525e-05,
851
+ "loss": 2.0563,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.004133751379376784,
856
+ "grad_norm": 11.97059440612793,
857
+ "learning_rate": 4.323126315789474e-05,
858
+ "loss": 2.2443,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.004168783170727435,
863
+ "grad_norm": 9.851146697998047,
864
+ "learning_rate": 4.270405263157895e-05,
865
+ "loss": 1.248,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004203814962078086,
870
+ "grad_norm": 5.306776523590088,
871
+ "learning_rate": 4.217684210526316e-05,
872
+ "loss": 0.8181,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004238846753428736,
877
+ "grad_norm": 6.5675506591796875,
878
+ "learning_rate": 4.164963157894737e-05,
879
+ "loss": 1.0159,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0042738785447793875,
884
+ "grad_norm": 5.773453235626221,
885
+ "learning_rate": 4.112242105263158e-05,
886
+ "loss": 0.9144,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004308910336130038,
891
+ "grad_norm": 5.412302017211914,
892
+ "learning_rate": 4.059521052631579e-05,
893
+ "loss": 0.7352,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.004343942127480689,
898
+ "grad_norm": 5.474285125732422,
899
+ "learning_rate": 4.0068e-05,
900
+ "loss": 0.8086,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0043789739188313396,
905
+ "grad_norm": 4.669981002807617,
906
+ "learning_rate": 3.954078947368421e-05,
907
+ "loss": 0.6895,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.00441400571018199,
912
+ "grad_norm": 7.121860504150391,
913
+ "learning_rate": 3.901357894736842e-05,
914
+ "loss": 0.9757,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.004449037501532641,
919
+ "grad_norm": 4.613837718963623,
920
+ "learning_rate": 3.848636842105263e-05,
921
+ "loss": 0.7938,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.004484069292883292,
926
+ "grad_norm": 4.65328311920166,
927
+ "learning_rate": 3.795915789473684e-05,
928
+ "loss": 0.6167,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.004519101084233942,
933
+ "grad_norm": 7.203744411468506,
934
+ "learning_rate": 3.743194736842105e-05,
935
+ "loss": 0.7682,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.004554132875584593,
940
+ "grad_norm": 5.1857523918151855,
941
+ "learning_rate": 3.690473684210526e-05,
942
+ "loss": 0.659,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.004589164666935244,
947
+ "grad_norm": 5.471020698547363,
948
+ "learning_rate": 3.6377526315789475e-05,
949
+ "loss": 0.6832,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.004624196458285894,
954
+ "grad_norm": 5.253795146942139,
955
+ "learning_rate": 3.585031578947368e-05,
956
+ "loss": 0.7885,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0046592282496365454,
961
+ "grad_norm": 5.277398586273193,
962
+ "learning_rate": 3.532310526315789e-05,
963
+ "loss": 0.7519,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.004694260040987196,
968
+ "grad_norm": 5.456074237823486,
969
+ "learning_rate": 3.4795894736842106e-05,
970
+ "loss": 0.6701,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.004729291832337846,
975
+ "grad_norm": 6.075155735015869,
976
+ "learning_rate": 3.4268684210526314e-05,
977
+ "loss": 0.93,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0047643236236884975,
982
+ "grad_norm": 5.472695350646973,
983
+ "learning_rate": 3.374147368421052e-05,
984
+ "loss": 0.7305,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.004799355415039148,
989
+ "grad_norm": 5.368462562561035,
990
+ "learning_rate": 3.321426315789473e-05,
991
+ "loss": 0.626,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.004834387206389798,
996
+ "grad_norm": 6.139542102813721,
997
+ "learning_rate": 3.2687052631578946e-05,
998
+ "loss": 0.8074,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.00486941899774045,
1003
+ "grad_norm": 4.907921314239502,
1004
+ "learning_rate": 3.2159842105263154e-05,
1005
+ "loss": 0.691,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0049044507890911,
1010
+ "grad_norm": 4.76326322555542,
1011
+ "learning_rate": 3.163263157894737e-05,
1012
+ "loss": 0.5767,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0049394825804417505,
1017
+ "grad_norm": 5.597925186157227,
1018
+ "learning_rate": 3.110542105263158e-05,
1019
+ "loss": 0.9885,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.004974514371792402,
1024
+ "grad_norm": 7.026127338409424,
1025
+ "learning_rate": 3.057821052631579e-05,
1026
+ "loss": 0.9067,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.005009546163143052,
1031
+ "grad_norm": 5.715368270874023,
1032
+ "learning_rate": 3.0050999999999997e-05,
1033
+ "loss": 1.187,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0050445779544937034,
1038
+ "grad_norm": 5.7752580642700195,
1039
+ "learning_rate": 2.9523789473684206e-05,
1040
+ "loss": 0.8954,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.005079609745844354,
1045
+ "grad_norm": 3.6325674057006836,
1046
+ "learning_rate": 2.899657894736842e-05,
1047
+ "loss": 0.4463,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.005114641537195004,
1052
+ "grad_norm": 4.1365766525268555,
1053
+ "learning_rate": 2.846936842105263e-05,
1054
+ "loss": 0.6405,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0051496733285456555,
1059
+ "grad_norm": 5.4132232666015625,
1060
+ "learning_rate": 2.794215789473684e-05,
1061
+ "loss": 0.5272,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.005184705119896306,
1066
+ "grad_norm": 4.7377400398254395,
1067
+ "learning_rate": 2.7414947368421056e-05,
1068
+ "loss": 0.6192,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.005219736911246956,
1073
+ "grad_norm": 5.025594711303711,
1074
+ "learning_rate": 2.6887736842105264e-05,
1075
+ "loss": 0.6358,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005254768702597608,
1080
+ "grad_norm": 5.432887077331543,
1081
+ "learning_rate": 2.6360526315789472e-05,
1082
+ "loss": 0.9462,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005254768702597608,
1087
+ "eval_loss": 0.9562696814537048,
1088
+ "eval_runtime": 2045.0876,
1089
+ "eval_samples_per_second": 5.877,
1090
+ "eval_steps_per_second": 1.469,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 7.914116459003904e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null