alchemist69 commited on
Commit
b3f7c89
·
verified ·
1 Parent(s): a7ad7d5

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:d9b18bf5b5499b30e23f3a5968851e321ecdc2e5a1d41264d70e863ab2be9232
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51ef3d723868f7babb43928313982eb666a03d7abeb677ba769dc94833c5e580
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f880ac2d4b9bffc70f5e41cc10cf43dded56f87b45a3f664c5e45137cd2578
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed44581d67769ff545e9ef13c3e3f1233e4ce187ea6ffa7aa11a95684069067f
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:ba3550d099db1b2a490718d5a2ad1f37fc66976f7192b031d6f0288a0fa597b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233259b4a4e6ed8af673b719c13f1f878706127630cd5049f8b70bce795e0390
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": 1.080734133720398,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.32653061224489793,
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": 11.836,
732
  "eval_steps_per_second": 2.959,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.606594406205358e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0521574020385742,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.4897959183673469,
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": 11.836,
732
  "eval_steps_per_second": 2.959,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.32979591836734695,
737
+ "grad_norm": 0.4673844873905182,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.5597,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3330612244897959,
744
+ "grad_norm": 0.4106678366661072,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.5768,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.3363265306122449,
751
+ "grad_norm": 0.32523709535598755,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.4829,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3395918367346939,
758
+ "grad_norm": 0.27613213658332825,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.2672,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.34285714285714286,
765
+ "grad_norm": 0.2684955596923828,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.3396,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3461224489795918,
772
+ "grad_norm": 0.27828139066696167,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.381,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.34938775510204084,
779
+ "grad_norm": 0.2876995801925659,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.3535,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3526530612244898,
786
+ "grad_norm": 0.28751134872436523,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.267,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.35591836734693877,
793
+ "grad_norm": 0.2795424461364746,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0994,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.35918367346938773,
800
+ "grad_norm": 0.2750096619129181,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.1255,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.36244897959183675,
807
+ "grad_norm": 0.28660520911216736,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1449,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3657142857142857,
814
+ "grad_norm": 0.2879250943660736,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1128,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3689795918367347,
821
+ "grad_norm": 0.2929372191429138,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0871,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3722448979591837,
828
+ "grad_norm": 0.2932370901107788,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9774,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.37551020408163266,
835
+ "grad_norm": 0.3034680485725403,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0615,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3787755102040816,
842
+ "grad_norm": 0.29233381152153015,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0273,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3820408163265306,
849
+ "grad_norm": 0.3026246726512909,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9679,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.3853061224489796,
856
+ "grad_norm": 0.30248984694480896,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.0469,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.38857142857142857,
863
+ "grad_norm": 0.3062831461429596,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0537,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.39183673469387753,
870
+ "grad_norm": 0.29366207122802734,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0142,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.39510204081632655,
877
+ "grad_norm": 0.3065624535083771,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.0233,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.3983673469387755,
884
+ "grad_norm": 0.3001972734928131,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9985,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4016326530612245,
891
+ "grad_norm": 0.30375322699546814,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.9795,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4048979591836735,
898
+ "grad_norm": 0.3111690282821655,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.0008,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.40816326530612246,
905
+ "grad_norm": 0.30732810497283936,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.0143,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4114285714285714,
912
+ "grad_norm": 0.3141505718231201,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.9801,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4146938775510204,
919
+ "grad_norm": 0.3132982552051544,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0293,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.4179591836734694,
926
+ "grad_norm": 0.31532377004623413,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0056,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.42122448979591837,
933
+ "grad_norm": 0.34107598662376404,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.069,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.42448979591836733,
940
+ "grad_norm": 0.33694490790367126,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0271,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.42775510204081635,
947
+ "grad_norm": 0.32336458563804626,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9831,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4310204081632653,
954
+ "grad_norm": 0.3337719440460205,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9965,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4342857142857143,
961
+ "grad_norm": 0.34013664722442627,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.9897,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.43755102040816324,
968
+ "grad_norm": 0.33463314175605774,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.9866,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.44081632653061226,
975
+ "grad_norm": 0.3379949927330017,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.9488,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4440816326530612,
982
+ "grad_norm": 0.34378427267074585,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0251,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4473469387755102,
989
+ "grad_norm": 0.34251320362091064,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.0149,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4506122448979592,
996
+ "grad_norm": 0.34321892261505127,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0012,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.45387755102040817,
1003
+ "grad_norm": 0.3566146790981293,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0442,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.45714285714285713,
1010
+ "grad_norm": 0.34775322675704956,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.9606,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.46040816326530615,
1017
+ "grad_norm": 0.3511592745780945,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.9832,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4636734693877551,
1024
+ "grad_norm": 0.3821600675582886,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0377,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4669387755102041,
1031
+ "grad_norm": 0.3769426941871643,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9492,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.47020408163265304,
1038
+ "grad_norm": 0.3839811384677887,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0344,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.47346938775510206,
1045
+ "grad_norm": 0.38504257798194885,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.0128,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.476734693877551,
1052
+ "grad_norm": 0.42816832661628723,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9911,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.48,
1059
+ "grad_norm": 0.4216458201408386,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0247,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.483265306122449,
1066
+ "grad_norm": 0.4273131787776947,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.0223,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.48653061224489796,
1073
+ "grad_norm": 0.4991781413555145,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.9789,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.4897959183673469,
1080
+ "grad_norm": 0.6679096817970276,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.1044,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.4897959183673469,
1087
+ "eval_loss": 1.0521574020385742,
1088
+ "eval_runtime": 43.314,
1089
+ "eval_samples_per_second": 11.913,
1090
+ "eval_steps_per_second": 2.978,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.4136629576794112e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null