antimage88 commited on
Commit
c0965ad
·
verified ·
1 Parent(s): dc872a5

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 sha256:30946b12847e4178479d31cee5349a7e807d64be58ea6108a9c5076c291d90ea
3
  size 912336848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cce4aa9bcab4e1b43475ae77bd17084f80f03d70c29015b3b718a32500fd598
3
  size 912336848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5868ce4e94bd924fbec234759b82d94ba2acb97ea206138e1bf70b61c5b0f536
3
  size 463916180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1dfe5777aebd987ef2ae7cd00fb6fe7b3ce5812ada2866a1be358f78e3e153a
3
  size 463916180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:832f96becf62ce3c99965ff88bf9ff1130662fdd5e44a7ab4bde242106c4bf99
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c73a77c096bff40694a1cb39afe5abbfd3eae732ac8390f410680a37b752abc
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": 0.7277113199234009,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3436426116838488,
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": 8.432,
732
  "eval_steps_per_second": 2.117,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.5413965215432704e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7073755264282227,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5154639175257731,
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": 8.432,
732
  "eval_steps_per_second": 2.117,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3470790378006873,
737
+ "grad_norm": 6.198427200317383,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.676,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.35051546391752575,
744
+ "grad_norm": 3.831768751144409,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.3918,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.3539518900343643,
751
+ "grad_norm": 3.025773048400879,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.9168,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.35738831615120276,
758
+ "grad_norm": 2.913081407546997,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.957,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.36082474226804123,
765
+ "grad_norm": 1.924337387084961,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.7171,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3642611683848797,
772
+ "grad_norm": 1.7787362337112427,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.5506,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.36769759450171824,
779
+ "grad_norm": 1.7331814765930176,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.606,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3711340206185567,
786
+ "grad_norm": 1.8595000505447388,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.4872,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.3745704467353952,
793
+ "grad_norm": 1.7210876941680908,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.4917,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.37800687285223367,
800
+ "grad_norm": 2.297461986541748,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.2728,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.38144329896907214,
807
+ "grad_norm": 2.0554733276367188,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.718,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3848797250859107,
814
+ "grad_norm": 1.8038687705993652,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.8015,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.38831615120274915,
821
+ "grad_norm": 1.7449924945831299,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.4377,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3917525773195876,
828
+ "grad_norm": 1.9162296056747437,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.7759,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.3951890034364261,
835
+ "grad_norm": 1.818672776222229,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.5994,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.39862542955326463,
842
+ "grad_norm": 1.7228524684906006,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.3886,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4020618556701031,
849
+ "grad_norm": 1.7789241075515747,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.5161,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4054982817869416,
856
+ "grad_norm": 2.012725591659546,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.5251,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.40893470790378006,
863
+ "grad_norm": 2.0002951622009277,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.6226,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.41237113402061853,
870
+ "grad_norm": 1.9130884408950806,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.3705,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.41580756013745707,
877
+ "grad_norm": 1.7260624170303345,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.2924,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.41924398625429554,
884
+ "grad_norm": 1.8843971490859985,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.6148,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.422680412371134,
891
+ "grad_norm": 2.1272003650665283,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.8849,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4261168384879725,
898
+ "grad_norm": 1.9105393886566162,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.5233,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.42955326460481097,
905
+ "grad_norm": 2.081491231918335,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.6334,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4329896907216495,
912
+ "grad_norm": 2.01537823677063,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.7079,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.436426116838488,
919
+ "grad_norm": 2.0294597148895264,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.7356,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.43986254295532645,
926
+ "grad_norm": 2.090278387069702,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.5529,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.44329896907216493,
933
+ "grad_norm": 2.0905957221984863,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.6941,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.44673539518900346,
940
+ "grad_norm": 2.0997745990753174,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.6148,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.45017182130584193,
947
+ "grad_norm": 2.496063470840454,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.8272,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4536082474226804,
954
+ "grad_norm": 2.2960619926452637,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.9424,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4570446735395189,
961
+ "grad_norm": 2.384944438934326,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.6241,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.46048109965635736,
968
+ "grad_norm": 2.4643306732177734,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.5367,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4639175257731959,
975
+ "grad_norm": 2.6148459911346436,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.6854,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.46735395189003437,
982
+ "grad_norm": 2.543748140335083,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.7542,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.47079037800687284,
989
+ "grad_norm": 2.4474358558654785,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.8701,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4742268041237113,
996
+ "grad_norm": 2.7877655029296875,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.1246,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.47766323024054985,
1003
+ "grad_norm": 2.8259971141815186,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.8092,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.48109965635738833,
1010
+ "grad_norm": 2.7138278484344482,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.3688,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4845360824742268,
1017
+ "grad_norm": 2.674522638320923,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.2805,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4879725085910653,
1024
+ "grad_norm": 3.3910646438598633,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.3634,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.49140893470790376,
1031
+ "grad_norm": 3.2498741149902344,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.0114,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4948453608247423,
1038
+ "grad_norm": 3.244091033935547,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.0963,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.49828178694158076,
1045
+ "grad_norm": 3.6477789878845215,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 3.2332,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5017182130584192,
1052
+ "grad_norm": 3.879427194595337,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.441,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5051546391752577,
1059
+ "grad_norm": 4.064486503601074,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.2155,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5085910652920962,
1066
+ "grad_norm": 4.470992088317871,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.791,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5120274914089347,
1073
+ "grad_norm": 5.485239028930664,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.2473,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5154639175257731,
1080
+ "grad_norm": 7.886268138885498,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 4.1722,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5154639175257731,
1087
+ "eval_loss": 0.7073755264282227,
1088
+ "eval_runtime": 57.6779,
1089
+ "eval_samples_per_second": 8.495,
1090
+ "eval_steps_per_second": 2.133,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.8120947823149056e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null