aleegis09 commited on
Commit
63c7ffe
·
verified ·
1 Parent(s): a482865

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:dda7e55a26d144a191c31234eb9f8603e01f0d9e53ae3a82a88cb795d27b9152
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e25fcd6390ae4a55fac64e2db42c9fb7ea02c1f5ad36ba5890c1060f5470a5e
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02234e84d895cf9967f14c8b5f34683d67fca9a68fa6e7a771138f1b8fb1c493
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4967b03396bb0c0abcdf3b8448eafd1e88cc60024c2e2f5cf760817eb3bee9de
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18c7a63a4b6cd8b76701fccf068ac098d7a327c3213bb53e80845e470b1bfbbc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec5d1ffc26a7b66d8c70795a6082209d4aef1dc433ce20fdd9dc102c1aa1b60
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": 2.1971940994262695,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.3996003996003996,
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": 57.231,
732
  "eval_steps_per_second": 14.376,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1309282779693604,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5994005994005994,
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": 57.231,
732
  "eval_steps_per_second": 14.376,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4035964035964036,
737
+ "grad_norm": 2.137390375137329,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.7543,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4075924075924076,
744
+ "grad_norm": 2.097003698348999,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.6215,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4115884115884116,
751
+ "grad_norm": 2.1690244674682617,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.6602,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4155844155844156,
758
+ "grad_norm": 2.294987678527832,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.8769,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4195804195804196,
765
+ "grad_norm": 2.4727396965026855,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.9594,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.42357642357642356,
772
+ "grad_norm": 2.6860365867614746,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.1873,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4275724275724276,
779
+ "grad_norm": 2.7127106189727783,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.3708,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.43156843156843155,
786
+ "grad_norm": 2.6260106563568115,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.2876,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4355644355644356,
793
+ "grad_norm": 2.768350601196289,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.3566,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.43956043956043955,
800
+ "grad_norm": 3.178553342819214,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.6334,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4435564435564436,
807
+ "grad_norm": 3.3227720260620117,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.5637,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.44755244755244755,
814
+ "grad_norm": 3.1499240398406982,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.4859,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.4515484515484515,
821
+ "grad_norm": 2.7684566974639893,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.1494,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.45554445554445555,
828
+ "grad_norm": 3.4616615772247314,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.1193,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.4595404595404595,
835
+ "grad_norm": 3.2123327255249023,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.5909,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.46353646353646355,
842
+ "grad_norm": 3.047816753387451,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.0229,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4675324675324675,
849
+ "grad_norm": 3.488494396209717,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.2963,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.47152847152847155,
856
+ "grad_norm": 3.587735891342163,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.2049,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.4755244755244755,
863
+ "grad_norm": 3.056833505630493,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.8591,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.47952047952047955,
870
+ "grad_norm": 3.218198776245117,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.2895,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4835164835164835,
877
+ "grad_norm": 3.371720314025879,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.4071,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4875124875124875,
884
+ "grad_norm": 3.7063543796539307,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.2914,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4915084915084915,
891
+ "grad_norm": 3.269237518310547,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.2477,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4955044955044955,
898
+ "grad_norm": 3.816117525100708,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.3856,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4995004995004995,
905
+ "grad_norm": 3.4660842418670654,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.0488,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5034965034965035,
912
+ "grad_norm": 3.094273328781128,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.1264,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5074925074925075,
919
+ "grad_norm": 3.5829083919525146,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.1837,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5114885114885115,
926
+ "grad_norm": 4.308327674865723,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.1031,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5154845154845155,
933
+ "grad_norm": 3.1789207458496094,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.2333,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5194805194805194,
940
+ "grad_norm": 3.8885791301727295,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.266,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5234765234765235,
947
+ "grad_norm": 4.62883186340332,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.3179,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5274725274725275,
954
+ "grad_norm": 4.235198497772217,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.2452,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5314685314685315,
961
+ "grad_norm": 3.6604795455932617,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.2782,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5354645354645354,
968
+ "grad_norm": 3.711357831954956,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.3947,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5394605394605395,
975
+ "grad_norm": 3.2384161949157715,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.8946,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5434565434565435,
982
+ "grad_norm": 3.569737672805786,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.1051,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5474525474525475,
989
+ "grad_norm": 4.256958961486816,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.8519,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5514485514485514,
996
+ "grad_norm": 3.9488539695739746,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.3631,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5554445554445554,
1003
+ "grad_norm": 3.606555223464966,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.8756,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5594405594405595,
1010
+ "grad_norm": 3.8353779315948486,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.2032,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5634365634365635,
1017
+ "grad_norm": 2.9946072101593018,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.5247,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5674325674325674,
1024
+ "grad_norm": 4.481592655181885,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.3981,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5714285714285714,
1031
+ "grad_norm": 3.6957621574401855,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.1031,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5754245754245755,
1038
+ "grad_norm": 4.094795227050781,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.5181,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5794205794205795,
1045
+ "grad_norm": 4.133942127227783,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.9686,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5834165834165834,
1052
+ "grad_norm": 3.659259557723999,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.7523,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5874125874125874,
1059
+ "grad_norm": 3.222001791000366,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.6258,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5914085914085914,
1066
+ "grad_norm": 3.470677614212036,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.5365,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5954045954045954,
1073
+ "grad_norm": 4.083232402801514,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.005,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5994005994005994,
1080
+ "grad_norm": 4.134530544281006,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.5766,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5994005994005994,
1087
+ "eval_loss": 2.1309282779693604,
1088
+ "eval_runtime": 7.3681,
1089
+ "eval_samples_per_second": 57.274,
1090
+ "eval_steps_per_second": 14.386,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.15927236476928e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null