prxy5605 commited on
Commit
784ff24
·
verified ·
1 Parent(s): 0623c24

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 sha256:531acc886e764a4e75b3b242ad5d2453d5e28cc83ba99010919cb212ba0abf1d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c2891d17395a69d86a5d88652d8fa40b369fca2e1c0a826e3aec33d24d1b06
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a15f0b00b9c9ccf53643836d8161c90281580c2b07149a6d6259fecdbf15c944
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c177acd268877bfcdf8f5d9be20de28ba020545109a67d9ea4b0e9e385859c
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f894dc7014acb090f8053f3c8f628ebc85bc42b4513736c171e7a97274639e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797ae82a481e242fd991dab3a4d1ba7a91f3e4e3e656a16ab6f6348a2fe5be52
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": 2.8183083534240723,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006005735477380899,
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": 13.08,
732
  "eval_steps_per_second": 3.27,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5160561466395853e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2935338020324707,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009008603216071349,
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": 13.08,
732
  "eval_steps_per_second": 3.27,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0060657928321547075,
737
+ "grad_norm": 4.833406925201416,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.9641,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0061258501869285165,
744
+ "grad_norm": 3.734908103942871,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.8651,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006185907541702325,
751
+ "grad_norm": 2.424708604812622,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.7192,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006245964896476134,
758
+ "grad_norm": 1.2214038372039795,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5439,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006306022251249943,
765
+ "grad_norm": 1.0090330839157104,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.7109,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.006366079606023753,
772
+ "grad_norm": 0.6321302652359009,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.5019,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006426136960797562,
779
+ "grad_norm": 0.6775772571563721,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.5734,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.006486194315571371,
786
+ "grad_norm": 0.6290256381034851,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.4641,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.00654625167034518,
793
+ "grad_norm": 0.6630206108093262,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4423,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006606309025118989,
800
+ "grad_norm": 0.5929522514343262,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.5018,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.006666366379892798,
807
+ "grad_norm": 0.7440500259399414,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.719,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.006726423734666607,
814
+ "grad_norm": 0.7187187075614929,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4171,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.006786481089440416,
821
+ "grad_norm": 0.6664174199104309,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.4871,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0068465384442142245,
828
+ "grad_norm": 0.8212423920631409,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.6519,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0069065957989880335,
835
+ "grad_norm": 0.7325797080993652,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.5503,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.006966653153761842,
842
+ "grad_norm": 0.7924835681915283,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.5493,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007026710508535651,
849
+ "grad_norm": 0.7400676608085632,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.4353,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.00708676786330946,
856
+ "grad_norm": 0.7383843660354614,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.607,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007146825218083269,
863
+ "grad_norm": 0.8036738634109497,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7235,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007206882572857078,
870
+ "grad_norm": 0.9643393754959106,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6605,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007266939927630887,
877
+ "grad_norm": 0.7977961897850037,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.5874,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007326997282404697,
884
+ "grad_norm": 1.0039657354354858,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.7547,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.007387054637178506,
891
+ "grad_norm": 0.8533593416213989,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.5897,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.007447111991952315,
898
+ "grad_norm": 0.9100041389465332,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.8671,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.007507169346726124,
905
+ "grad_norm": 0.9276086688041687,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.823,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007567226701499933,
912
+ "grad_norm": 0.9275705218315125,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.7562,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0076272840562737415,
919
+ "grad_norm": 1.480225682258606,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.6622,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.0076873414110475505,
926
+ "grad_norm": 0.9616846442222595,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.8093,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.007747398765821359,
933
+ "grad_norm": 1.14011812210083,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.8223,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.007807456120595168,
940
+ "grad_norm": 1.2321470975875854,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.8567,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.007867513475368978,
947
+ "grad_norm": 1.0687763690948486,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.8913,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.007927570830142786,
954
+ "grad_norm": 1.063493013381958,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.0323,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.007987628184916596,
961
+ "grad_norm": 1.641831636428833,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.4082,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.008047685539690404,
968
+ "grad_norm": 1.429152488708496,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.2811,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008107742894464214,
975
+ "grad_norm": 1.641626238822937,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.6107,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.008167800249238022,
982
+ "grad_norm": 2.325291395187378,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.9367,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008227857604011832,
989
+ "grad_norm": 2.3526947498321533,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.8885,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.00828791495878564,
996
+ "grad_norm": 2.213717222213745,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.1196,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.00834797231355945,
1003
+ "grad_norm": 2.8324809074401855,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.4588,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.008408029668333258,
1010
+ "grad_norm": 3.3284666538238525,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.7411,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.008468087023107067,
1017
+ "grad_norm": 4.056039333343506,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.9056,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.008528144377880876,
1024
+ "grad_norm": 3.690812110900879,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.9602,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.008588201732654685,
1031
+ "grad_norm": 4.101503372192383,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 4.0565,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.008648259087428493,
1038
+ "grad_norm": 4.115358352661133,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.9999,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.008708316442202303,
1045
+ "grad_norm": 4.536535263061523,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.9276,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.008768373796976113,
1052
+ "grad_norm": 5.131693363189697,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.9758,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.008828431151749921,
1059
+ "grad_norm": 6.091833114624023,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 4.0936,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.008888488506523731,
1066
+ "grad_norm": 11.448600769042969,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 4.6619,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.008948545861297539,
1073
+ "grad_norm": 8.706692695617676,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.9178,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009008603216071349,
1080
+ "grad_norm": 17.97637176513672,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.8413,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009008603216071349,
1087
+ "eval_loss": 2.2935338020324707,
1088
+ "eval_runtime": 2144.7077,
1089
+ "eval_samples_per_second": 13.076,
1090
+ "eval_steps_per_second": 3.269,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.274084219959378e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null