prxy5607 commited on
Commit
3a83d57
·
verified ·
1 Parent(s): c8c0574

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 sha256:0d70cbc43b2ba4c03df04620d6064feac74ebbbbcddf2c94a359fd53d38c52c8
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cffd81f805be6147b4d4aa619ae4fe72e7444a550698c266cc4e5930cbda4a
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f94b8f882a6eee5d51dd8f9a14cb855f656de829e40b16ec9f01cf3806ffc3c
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7825b34a59b1865c0364b850fe6e4823356843dc0f5130f04acb7e9ec8597b0
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bf6a468b68ee017d5894ba7f9d627684bf11ffc10460a0a750cf6caf7d5ab3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee403abb0600e6dd64f331151d288bef2a68026c232ee2f32207d9fd5ac4c9d1
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": 1.57069730758667,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.9324009324009324,
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": 7.496,
732
  "eval_steps_per_second": 1.905,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.54789940771029e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3634928464889526,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.3986013986013985,
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": 7.496,
732
  "eval_steps_per_second": 1.905,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.9417249417249417,
737
+ "grad_norm": 0.6660596132278442,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.5302,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.951048951048951,
744
+ "grad_norm": 0.36493605375289917,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.5459,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.9603729603729604,
751
+ "grad_norm": 0.31290921568870544,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.5298,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9696969696969697,
758
+ "grad_norm": 0.542377233505249,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.335,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.9790209790209791,
765
+ "grad_norm": 0.22271700203418732,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.4205,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.9883449883449883,
772
+ "grad_norm": 2.942105531692505,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.0007,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.9976689976689976,
779
+ "grad_norm": 1.8956243991851807,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.6704,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.006993006993007,
786
+ "grad_norm": 1.9723633527755737,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.1549,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.0163170163170163,
793
+ "grad_norm": 0.1735471934080124,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.4268,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.0256410256410255,
800
+ "grad_norm": 0.21562330424785614,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.4465,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.034965034965035,
807
+ "grad_norm": 0.19110897183418274,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.4676,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.0442890442890442,
814
+ "grad_norm": 0.2500961720943451,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.4745,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.0536130536130537,
821
+ "grad_norm": 0.19169417023658752,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.48,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.062937062937063,
828
+ "grad_norm": 0.2851697504520416,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.0048,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.0722610722610724,
835
+ "grad_norm": 2.6353838443756104,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7559,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.0815850815850816,
842
+ "grad_norm": 3.3857853412628174,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0286,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.0909090909090908,
849
+ "grad_norm": 3.1199066638946533,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.0096,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1002331002331003,
856
+ "grad_norm": 2.9276974201202393,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9039,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.1095571095571095,
863
+ "grad_norm": 2.443124294281006,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7381,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.118881118881119,
870
+ "grad_norm": 2.1647462844848633,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.605,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.1282051282051282,
877
+ "grad_norm": 1.250878930091858,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.544,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.1375291375291376,
884
+ "grad_norm": 1.8800292015075684,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.6084,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.1468531468531469,
891
+ "grad_norm": 1.9703083038330078,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.6472,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.156177156177156,
898
+ "grad_norm": 2.0282840728759766,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6155,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.1655011655011656,
905
+ "grad_norm": 1.8367279767990112,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.5723,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.1748251748251748,
912
+ "grad_norm": 1.7862775325775146,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.576,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.1841491841491842,
919
+ "grad_norm": 2.454814910888672,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.8574,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.1934731934731935,
926
+ "grad_norm": 4.414870262145996,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2128,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.2027972027972027,
933
+ "grad_norm": 3.4398910999298096,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.248,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.2121212121212122,
940
+ "grad_norm": 4.762664794921875,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2057,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.2214452214452214,
947
+ "grad_norm": 1.2467693090438843,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.2475,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.2307692307692308,
954
+ "grad_norm": 0.3888402283191681,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.323,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.24009324009324,
961
+ "grad_norm": 0.5149527192115784,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.5671,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.2494172494172493,
968
+ "grad_norm": 0.3172931969165802,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.1747,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.2587412587412588,
975
+ "grad_norm": 0.21860957145690918,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.3786,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.2680652680652682,
982
+ "grad_norm": 0.18373554944992065,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.4827,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.2773892773892774,
989
+ "grad_norm": 0.19047728180885315,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.3228,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.2867132867132867,
996
+ "grad_norm": 0.17042529582977295,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.4518,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.2960372960372961,
1003
+ "grad_norm": 0.19628658890724182,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.4526,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.3053613053613053,
1010
+ "grad_norm": 0.20845463871955872,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.4844,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.3146853146853146,
1017
+ "grad_norm": 0.4709472954273224,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.5694,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.324009324009324,
1024
+ "grad_norm": 2.323354721069336,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.6289,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.3333333333333333,
1031
+ "grad_norm": 2.1040561199188232,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.6739,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.3426573426573427,
1038
+ "grad_norm": 2.162606716156006,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.7304,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.351981351981352,
1045
+ "grad_norm": 1.941840410232544,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.6936,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.3613053613053614,
1052
+ "grad_norm": 1.9493544101715088,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.7318,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.3706293706293706,
1059
+ "grad_norm": 1.8778190612792969,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6226,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.3799533799533799,
1066
+ "grad_norm": 0.9945464134216309,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.4764,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.3892773892773893,
1073
+ "grad_norm": 1.3842207193374634,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5212,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.3986013986013985,
1080
+ "grad_norm": 1.1556576490402222,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.4962,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.3986013986013985,
1087
+ "eval_loss": 1.3634928464889526,
1088
+ "eval_runtime": 23.9044,
1089
+ "eval_samples_per_second": 7.572,
1090
+ "eval_steps_per_second": 1.924,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.79399185629184e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null