nttx commited on
Commit
c67755b
·
verified ·
1 Parent(s): de4fadc

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 sha256:29c8e9c80e3a58ec565b40042dd32592c721f5e49119981c561c0f3c6bc22d3b
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48dfac874bc5b93bb82ee92f8cd891ef76b6f9b41c1a9584f3e43e3cdc3a1c6a
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccbbc593b64a50a6637b97abc65a045545ea263d210fb6e1f0574517584dd747
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ce78b14f47de7ad7504f1cfc903f0726b566fe19c134877b7d8d2462002e06
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f61448e1e5439eee4cfab31ba2cf9bb45016fbb1f9dc92dbfd8f3198803c5b9f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff13ceaba58948bb1e5c9d669a8f801bf83a827d5c74170da300d5f318bea59
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": 0.3743059039115906,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.007089056269384138,
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": 13.358,
732
  "eval_steps_per_second": 3.34,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.37604737531904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.35101068019866943,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.010633584404076208,
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": 13.358,
732
  "eval_steps_per_second": 3.34,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.00715994683207798,
737
+ "grad_norm": 1.1645331382751465,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.4339,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.007230837394771821,
744
+ "grad_norm": 0.8213737607002258,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.2394,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.007301727957465662,
751
+ "grad_norm": 0.3668546676635742,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2523,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.007372618520159504,
758
+ "grad_norm": 0.4842718243598938,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2477,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.007443509082853345,
765
+ "grad_norm": 0.5160728693008423,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.3465,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.007514399645547187,
772
+ "grad_norm": 0.5961820483207703,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.4104,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.007585290208241028,
779
+ "grad_norm": 0.5189549326896667,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3775,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.007656180770934869,
786
+ "grad_norm": 0.5054015517234802,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.3492,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007727071333628711,
793
+ "grad_norm": 0.5176796317100525,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.4417,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007797961896322552,
800
+ "grad_norm": 0.4752146005630493,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3667,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.007868852459016393,
807
+ "grad_norm": 0.5429568290710449,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.4323,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007939743021710235,
814
+ "grad_norm": 0.4606378972530365,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.4042,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.008010633584404077,
821
+ "grad_norm": 0.4609495997428894,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3588,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.008081524147097917,
828
+ "grad_norm": 0.4024210572242737,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2539,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.008152414709791759,
835
+ "grad_norm": 0.508936882019043,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3056,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0082233052724856,
842
+ "grad_norm": 0.4702116847038269,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.3446,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.008294195835179442,
849
+ "grad_norm": 0.48911041021347046,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.3549,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.008365086397873284,
856
+ "grad_norm": 0.47224682569503784,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.3649,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.008435976960567124,
863
+ "grad_norm": 0.5375878810882568,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.3898,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.008506867523260965,
870
+ "grad_norm": 0.5839834809303284,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.3996,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.008577758085954807,
877
+ "grad_norm": 0.5372905731201172,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.3944,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.008648648648648649,
884
+ "grad_norm": 0.5804446339607239,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.4677,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.00871953921134249,
891
+ "grad_norm": 0.6173442006111145,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.4097,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008790429774036332,
898
+ "grad_norm": 0.5606793165206909,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.345,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008861320336730172,
905
+ "grad_norm": 0.5558311939239502,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.3834,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008932210899424014,
912
+ "grad_norm": 0.5951129794120789,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3602,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.009003101462117856,
919
+ "grad_norm": 0.4856142997741699,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3103,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.009073992024811697,
926
+ "grad_norm": 0.4996812343597412,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.3682,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.009144882587505539,
933
+ "grad_norm": 0.5909815430641174,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.4107,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.009215773150199379,
940
+ "grad_norm": 0.44087570905685425,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3221,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.00928666371289322,
947
+ "grad_norm": 0.5540933609008789,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.3438,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.009357554275587062,
954
+ "grad_norm": 0.5242694616317749,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.2932,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.009428444838280904,
961
+ "grad_norm": 0.45764636993408203,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.244,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.009499335400974746,
968
+ "grad_norm": 0.5010474324226379,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2954,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.009570225963668586,
975
+ "grad_norm": 0.6669395565986633,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.4188,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.009641116526362428,
982
+ "grad_norm": 0.5768990516662598,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.3828,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.00971200708905627,
989
+ "grad_norm": 0.5708727836608887,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.2528,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.009782897651750111,
996
+ "grad_norm": 0.644628643989563,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.3636,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.009853788214443953,
1003
+ "grad_norm": 0.6101208329200745,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.346,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.009924678777137794,
1010
+ "grad_norm": 0.5933841466903687,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.3744,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.009995569339831634,
1017
+ "grad_norm": 0.6101102232933044,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.393,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.010066459902525476,
1024
+ "grad_norm": 0.5287688374519348,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3131,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.010137350465219318,
1031
+ "grad_norm": 0.6600167155265808,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.37,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01020824102791316,
1038
+ "grad_norm": 0.5290716886520386,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3381,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.010279131590607001,
1045
+ "grad_norm": 0.5473757982254028,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.3352,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.010350022153300841,
1052
+ "grad_norm": 0.5812906622886658,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.2937,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.010420912715994683,
1059
+ "grad_norm": 0.5383227467536926,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.3403,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.010491803278688525,
1066
+ "grad_norm": 0.5573107600212097,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.3672,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.010562693841382366,
1073
+ "grad_norm": 0.5898846983909607,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.3701,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.010633584404076208,
1080
+ "grad_norm": 0.6166815757751465,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4691,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.010633584404076208,
1087
+ "eval_loss": 0.35101068019866943,
1088
+ "eval_runtime": 1780.1453,
1089
+ "eval_samples_per_second": 13.346,
1090
+ "eval_steps_per_second": 3.337,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.06575327248384e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null