nttx commited on
Commit
6429f7d
·
verified ·
1 Parent(s): 3e7e6ca

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 sha256:8681b82e0e26bedaf4eb49a33711aa46afc5b35829f593998db416cd364c3970
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c677e9fe3229099086371daae5d7818bfaf67f6cbd98c80f2e384f77ea396a
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2aca4a65ac2fca03d2ca3b9d29860f57f6f2d525230a616cffc5e63f52e00e9
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c3255ee06df20e1fbc69eabd8608cc5027465109fa3357f31047be1a9c9e04
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:e9f09fc3b75472b0bfdec1f68ebe756e5110cf83d12fe84dace254c8d2b702fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a3ccd7107902784ac2ce5a83a61192c65578d0858e9ba98dfb01720e877af1
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": 0.9901078343391418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.8849557522123894,
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": 12.931,
732
  "eval_steps_per_second": 3.267,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9761214256286621,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.3274336283185841,
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": 12.931,
732
  "eval_steps_per_second": 3.267,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.8938053097345132,
737
+ "grad_norm": 0.36540257930755615,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.9994,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.9026548672566371,
744
+ "grad_norm": 0.3686259388923645,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0103,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.911504424778761,
751
+ "grad_norm": 0.3762861490249634,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9699,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.9203539823008849,
758
+ "grad_norm": 0.39205309748649597,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0248,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.9292035398230089,
765
+ "grad_norm": 0.38482269644737244,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9977,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.9380530973451328,
772
+ "grad_norm": 0.38303685188293457,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9764,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.9469026548672567,
779
+ "grad_norm": 0.3988681733608246,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.9639,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.9557522123893806,
786
+ "grad_norm": 0.414703369140625,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9997,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.9646017699115044,
793
+ "grad_norm": 0.5490361452102661,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0632,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.9734513274336283,
800
+ "grad_norm": 0.42414286732673645,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9473,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.9823008849557522,
807
+ "grad_norm": 0.41620245575904846,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9615,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.9911504424778761,
814
+ "grad_norm": 0.469810426235199,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0666,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.0,
821
+ "grad_norm": 0.43457192182540894,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9924,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.008849557522124,
828
+ "grad_norm": 0.4487452805042267,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9501,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.0176991150442478,
835
+ "grad_norm": 0.44991588592529297,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.8991,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.0265486725663717,
842
+ "grad_norm": 0.4764535427093506,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9337,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.0353982300884956,
849
+ "grad_norm": 0.37468791007995605,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.839,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.0442477876106195,
856
+ "grad_norm": 0.37512651085853577,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.8933,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.0530973451327434,
863
+ "grad_norm": 0.35990557074546814,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9094,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.0619469026548674,
870
+ "grad_norm": 0.39726901054382324,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.9575,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.0707964601769913,
877
+ "grad_norm": 0.39367854595184326,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.9101,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.079646017699115,
884
+ "grad_norm": 0.4005451202392578,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.8862,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.0884955752212389,
891
+ "grad_norm": 0.37865352630615234,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7723,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.0973451327433628,
898
+ "grad_norm": 0.3704884350299835,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.8734,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.1061946902654867,
905
+ "grad_norm": 0.3693143129348755,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.953,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.1150442477876106,
912
+ "grad_norm": 0.38378581404685974,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8708,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.1238938053097345,
919
+ "grad_norm": 0.3837099075317383,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7709,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.1327433628318584,
926
+ "grad_norm": 0.38278061151504517,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.9089,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.1415929203539823,
933
+ "grad_norm": 0.4078880250453949,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.7776,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.1504424778761062,
940
+ "grad_norm": 0.37466108798980713,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.9051,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.1592920353982301,
947
+ "grad_norm": 0.37593039870262146,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.8698,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.168141592920354,
954
+ "grad_norm": 0.40655517578125,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.822,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.176991150442478,
961
+ "grad_norm": 0.3860974609851837,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.921,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.1858407079646018,
968
+ "grad_norm": 0.4202975630760193,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.9302,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.1946902654867257,
975
+ "grad_norm": 0.4354274868965149,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8534,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.2035398230088497,
982
+ "grad_norm": 0.4405210316181183,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8123,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.2123893805309733,
989
+ "grad_norm": 0.39681050181388855,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.8731,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.2212389380530975,
996
+ "grad_norm": 0.40894973278045654,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8586,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.2300884955752212,
1003
+ "grad_norm": 0.4769720137119293,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.8704,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.238938053097345,
1010
+ "grad_norm": 0.4037542939186096,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9749,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.247787610619469,
1017
+ "grad_norm": 0.4539080560207367,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.9222,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.2566371681415929,
1024
+ "grad_norm": 0.40807825326919556,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.889,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.2654867256637168,
1031
+ "grad_norm": 0.4057980477809906,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9206,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.2743362831858407,
1038
+ "grad_norm": 0.4231337010860443,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.9512,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.2831858407079646,
1045
+ "grad_norm": 0.3950173556804657,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.8673,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.2920353982300885,
1052
+ "grad_norm": 0.41266927123069763,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8971,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.3008849557522124,
1059
+ "grad_norm": 0.3708341419696808,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.9354,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.3097345132743363,
1066
+ "grad_norm": 0.4057871401309967,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.8781,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.3185840707964602,
1073
+ "grad_norm": 0.39994144439697266,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9033,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.3274336283185841,
1080
+ "grad_norm": 0.4080321788787842,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7739,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.3274336283185841,
1087
+ "eval_loss": 0.9761214256286621,
1088
+ "eval_runtime": 14.687,
1089
+ "eval_samples_per_second": 12.937,
1090
+ "eval_steps_per_second": 3.268,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2599419051586355e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null