arcwarden46 commited on
Commit
b10dfab
·
verified ·
1 Parent(s): 7e3fe48

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 sha256:49b9d6e2a783a0fda536017f61c0ad1922fe44b1c8779fbc2b954d03226b6921
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f302db3bd93f61cbc45f77a5bb9fe5e7a31f816687c30c1a7bf49068d6d2ef
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:face4b94a1ca90b0023da6688e996564874d84dc853878dd1892d6d02e349a1f
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b68c907ff89655569c41572479d1b027537c0cd17ac141a7cbe669400529916a
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed1e62e379e5c95a4ce14fb770553a251c19d0b44309e01a2a59b1f71883aac6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d740465b8aaa84b69bb313532a7a23679489cfd39b2bd950bce97f0182e59c51
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7677788734436035,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.5805515239477503,
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": 11.741,
732
  "eval_steps_per_second": 2.956,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.1451856895921357e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.733366847038269,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.8708272859216255,
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": 11.741,
732
  "eval_steps_per_second": 2.956,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.5863570391872278,
737
+ "grad_norm": 0.44562649726867676,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.9916,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5921625544267054,
744
+ "grad_norm": 0.39542460441589355,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.8145,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5979680696661829,
751
+ "grad_norm": 0.3893499970436096,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.8439,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6037735849056604,
758
+ "grad_norm": 0.44246092438697815,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.7739,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6095791001451378,
765
+ "grad_norm": 0.41057920455932617,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.8047,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6153846153846154,
772
+ "grad_norm": 0.44987499713897705,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.9288,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6211901306240929,
779
+ "grad_norm": 0.42091771960258484,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.7894,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.6269956458635704,
786
+ "grad_norm": 0.4402920603752136,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.8346,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.6328011611030478,
793
+ "grad_norm": 0.4101702570915222,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.9121,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.6386066763425254,
800
+ "grad_norm": 0.4471023678779602,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.7271,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.6444121915820029,
807
+ "grad_norm": 0.4522208273410797,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.7367,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.6502177068214804,
814
+ "grad_norm": 0.4687577486038208,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.7813,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.6560232220609579,
821
+ "grad_norm": 0.5011056065559387,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.7069,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.6618287373004355,
828
+ "grad_norm": 0.48258066177368164,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.7788,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.6676342525399129,
835
+ "grad_norm": 0.7686281800270081,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.7729,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.6734397677793904,
842
+ "grad_norm": 0.5120784044265747,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7578,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.6792452830188679,
849
+ "grad_norm": 0.4679645895957947,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.7349,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.6850507982583455,
856
+ "grad_norm": 0.4701582193374634,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.7461,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.690856313497823,
863
+ "grad_norm": 0.5181167721748352,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.6972,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.6966618287373004,
870
+ "grad_norm": 0.5515949130058289,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6896,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.7024673439767779,
877
+ "grad_norm": 0.5267184972763062,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6509,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.7082728592162555,
884
+ "grad_norm": 0.5740118622779846,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6835,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.714078374455733,
891
+ "grad_norm": 0.5620703101158142,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.7505,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.7198838896952104,
898
+ "grad_norm": 0.5882965922355652,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.8095,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.7256894049346879,
905
+ "grad_norm": 0.6772586107254028,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.7775,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.7314949201741655,
912
+ "grad_norm": 0.7016092538833618,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.5983,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.737300435413643,
919
+ "grad_norm": 0.6854375004768372,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.7959,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.7431059506531205,
926
+ "grad_norm": 0.7054009437561035,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.362,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.7489114658925979,
933
+ "grad_norm": 1.2267603874206543,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.7349,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.7547169811320755,
940
+ "grad_norm": 0.3392610549926758,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.8782,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.760522496371553,
947
+ "grad_norm": 0.3541852533817291,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.8358,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.7663280116110305,
954
+ "grad_norm": 0.3445144593715668,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.8241,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.772133526850508,
961
+ "grad_norm": 0.36159756779670715,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.8097,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.7779390420899854,
968
+ "grad_norm": 0.3605585992336273,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.8716,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.783744557329463,
975
+ "grad_norm": 0.3616204261779785,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.7814,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.7895500725689405,
982
+ "grad_norm": 0.37260672450065613,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.7747,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.795355587808418,
989
+ "grad_norm": 0.36629241704940796,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.8003,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.8011611030478955,
996
+ "grad_norm": 0.3812524080276489,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.8456,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.806966618287373,
1003
+ "grad_norm": 0.3807627856731415,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.9383,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.8127721335268505,
1010
+ "grad_norm": 0.3906376361846924,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.7923,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.818577648766328,
1017
+ "grad_norm": 0.382329523563385,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7776,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.8243831640058055,
1024
+ "grad_norm": 0.398005872964859,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.7775,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.8301886792452831,
1031
+ "grad_norm": 0.3928670287132263,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.6754,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.8359941944847605,
1038
+ "grad_norm": 0.40780770778656006,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.826,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.841799709724238,
1045
+ "grad_norm": 0.41190868616104126,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.76,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.8476052249637155,
1052
+ "grad_norm": 0.4169665277004242,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.6916,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.8534107402031931,
1059
+ "grad_norm": 0.410805881023407,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.7968,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.8592162554426706,
1066
+ "grad_norm": 0.4383578300476074,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.8428,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.865021770682148,
1073
+ "grad_norm": 0.4339222013950348,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.8092,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.8708272859216255,
1080
+ "grad_norm": 0.4114333987236023,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.7835,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.8708272859216255,
1087
+ "eval_loss": 1.733366847038269,
1088
+ "eval_runtime": 24.7087,
1089
+ "eval_samples_per_second": 11.737,
1090
+ "eval_steps_per_second": 2.954,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.7170618975361434e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null