dimasik2987 commited on
Commit
3c23525
·
verified ·
1 Parent(s): 2676019

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:fe32acb668ac047978e3e9f583127cab3bd29b7ac1fa5a4a19b61bf03f0c22e8
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de21d88336363b6f0e8a3edd7e1e577088b7c299d8ae5b7e40897f63dd08bd0e
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5527a672e02bb7d7279600fe882382948581c0ada899c70b5156a3226e670bcb
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cbcdd452731d2968d82edde70b57ffd7a99e3ca12fae709db72cc025458f69
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d24e8d03ae53d735f8c639517b54ff927b6527c170a6b1ecd91efe86f65c7547
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9e444b228a31a91db7695a7781c0134d1cc074bd213f3ff9b35ae07d8e9402
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0612136125564575,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.007591285204585136,
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": 22.994,
732
  "eval_steps_per_second": 5.749,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6803618267136000.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9495816826820374,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.011386927806877705,
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": 22.994,
732
  "eval_steps_per_second": 5.749,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.007667198056630987,
737
+ "grad_norm": 3.0699315071105957,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 1.173,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.007743110908676839,
744
+ "grad_norm": 4.866107940673828,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 1.7382,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.007819023760722691,
751
+ "grad_norm": 4.889467239379883,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 1.4133,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.007894936612768542,
758
+ "grad_norm": 4.676548480987549,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 1.406,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.007970849464814394,
765
+ "grad_norm": 2.993145227432251,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 1.1335,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.008046762316860244,
772
+ "grad_norm": 2.76796555519104,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 1.154,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.008122675168906095,
779
+ "grad_norm": 3.4943559169769287,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 1.1565,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.008198588020951946,
786
+ "grad_norm": 3.7888946533203125,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 0.9767,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.008274500872997798,
793
+ "grad_norm": 3.349473237991333,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 1.0981,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.00835041372504365,
800
+ "grad_norm": 2.571047782897949,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 1.3569,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0084263265770895,
807
+ "grad_norm": 3.6991724967956543,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 1.2374,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.008502239429135352,
814
+ "grad_norm": 3.694169282913208,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 1.4054,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.008578152281181204,
821
+ "grad_norm": 3.4294185638427734,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 1.5067,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.008654065133227055,
828
+ "grad_norm": 2.6580145359039307,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 0.9726,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.008729977985272907,
835
+ "grad_norm": 2.1301791667938232,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 0.9786,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.008805890837318758,
842
+ "grad_norm": 2.001025438308716,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 0.6805,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.00888180368936461,
849
+ "grad_norm": 2.077392816543579,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 0.8329,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.00895771654141046,
856
+ "grad_norm": 2.3383848667144775,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 0.9665,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.009033629393456312,
863
+ "grad_norm": 2.4571051597595215,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 1.2276,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.009109542245502164,
870
+ "grad_norm": 1.6125465631484985,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 0.6786,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.009185455097548015,
877
+ "grad_norm": 2.041332960128784,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 0.9306,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.009261367949593867,
884
+ "grad_norm": 2.873103380203247,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 1.0511,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.009337280801639718,
891
+ "grad_norm": 3.1347708702087402,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 0.9377,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00941319365368557,
898
+ "grad_norm": 1.9942682981491089,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 0.8217,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.009489106505731421,
905
+ "grad_norm": 3.970079183578491,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 1.3267,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.009565019357777272,
912
+ "grad_norm": 2.6041419506073,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 1.034,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.009640932209823124,
919
+ "grad_norm": 2.5443952083587646,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 0.8037,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.009716845061868975,
926
+ "grad_norm": 2.3711419105529785,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 1.0528,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.009792757913914825,
933
+ "grad_norm": 1.946669101715088,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 0.5657,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.009868670765960676,
940
+ "grad_norm": 4.314067363739014,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 0.9075,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.009944583618006528,
947
+ "grad_norm": 2.827471971511841,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 0.9609,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01002049647005238,
954
+ "grad_norm": 2.264293909072876,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 0.8314,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01009640932209823,
961
+ "grad_norm": 2.1921863555908203,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 0.8398,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.010172322174144082,
968
+ "grad_norm": 2.1233198642730713,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 0.7514,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.010248235026189934,
975
+ "grad_norm": 2.6817049980163574,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 0.6174,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.010324147878235785,
982
+ "grad_norm": 1.518689513206482,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 0.6519,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.010400060730281636,
989
+ "grad_norm": 2.2906270027160645,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 0.6826,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.010475973582327488,
996
+ "grad_norm": 2.211939573287964,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 0.8501,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.01055188643437334,
1003
+ "grad_norm": 4.645651340484619,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 0.6646,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.01062779928641919,
1010
+ "grad_norm": 4.8494744300842285,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 0.8638,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.010703712138465042,
1017
+ "grad_norm": 1.5980870723724365,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 0.5841,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.010779624990510894,
1024
+ "grad_norm": 1.9709309339523315,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 0.6271,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.010855537842556745,
1031
+ "grad_norm": 2.970513105392456,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 0.9551,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.010931450694602596,
1038
+ "grad_norm": 2.2817845344543457,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 0.7009,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.011007363546648448,
1045
+ "grad_norm": 2.4556617736816406,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 0.7365,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.0110832763986943,
1052
+ "grad_norm": 1.3741040229797363,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 0.6872,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.01115918925074015,
1059
+ "grad_norm": 1.5213168859481812,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 0.5938,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.011235102102786002,
1066
+ "grad_norm": 1.7388572692871094,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 0.639,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.011311014954831854,
1073
+ "grad_norm": 1.9065625667572021,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 0.6217,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.011386927806877705,
1080
+ "grad_norm": 2.9357759952545166,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 0.8997,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.011386927806877705,
1087
+ "eval_loss": 0.9495816826820374,
1088
+ "eval_runtime": 241.9389,
1089
+ "eval_samples_per_second": 22.927,
1090
+ "eval_steps_per_second": 5.733,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.0205427400704e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null