aleegis09 commited on
Commit
5e6b68b
·
verified ·
1 Parent(s): 99632a6

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 sha256:4a1392a7a44d836fc33a9b72d7137c69deefb9d9c2a0df43823b0c83922a6995
3
  size 100690184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd902e4e58d034802e5f9f9a47e4a6d3a26ebe0e2ca29da1455dd95c8f69015
3
  size 100690184
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e27e64a72c99710ca6eb89e5e07712a323f9cdb326e9e705913dacec8762c69
3
  size 51344890
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46103cae0eb3278334e2ed64d2a4547375a1d0e683332f30c1e15d742ed4c690
3
  size 51344890
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c656d86cf2e1f1960d0e18db481b6284f9cc81da43dcb37e365a0d26da56fec0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513cebe95e52f7c0157d447d13725e6ce11360d1e4883b61b0fe9ee134944142
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": 1.4002317190170288,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.2079002079002079,
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": 49.02,
732
  "eval_steps_per_second": 12.27,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.49024359317504e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3784149885177612,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.31185031185031187,
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": 49.02,
732
  "eval_steps_per_second": 12.27,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.20997920997921,
737
+ "grad_norm": 33.29289627075195,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 6.0499,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.21205821205821207,
744
+ "grad_norm": 56.924251556396484,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 6.2076,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.21413721413721415,
751
+ "grad_norm": 33.388427734375,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 6.3714,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.21621621621621623,
758
+ "grad_norm": 31.86151885986328,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 6.2998,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2182952182952183,
765
+ "grad_norm": 45.58109664916992,
766
+ "learning_rate": 5e-05,
767
+ "loss": 6.1464,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.2203742203742204,
772
+ "grad_norm": 36.673439025878906,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.4994,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.22245322245322247,
779
+ "grad_norm": 46.388973236083984,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.9618,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.22453222453222454,
786
+ "grad_norm": 35.77516174316406,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 6.0713,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.22661122661122662,
793
+ "grad_norm": 42.96281051635742,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.863,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.2286902286902287,
800
+ "grad_norm": 37.156272888183594,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.7125,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.23076923076923078,
807
+ "grad_norm": 42.857574462890625,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.9667,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.23284823284823286,
814
+ "grad_norm": 44.69389724731445,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.9149,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.23492723492723494,
821
+ "grad_norm": 48.71627426147461,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.4195,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.23700623700623702,
828
+ "grad_norm": 32.36886978149414,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.2663,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2390852390852391,
835
+ "grad_norm": 31.383926391601562,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 5.3309,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.24116424116424118,
842
+ "grad_norm": 29.009599685668945,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.1069,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.24324324324324326,
849
+ "grad_norm": 35.83613967895508,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.4003,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.24532224532224534,
856
+ "grad_norm": 32.853843688964844,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.1017,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.24740124740124741,
863
+ "grad_norm": 33.55854797363281,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.3952,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2494802494802495,
870
+ "grad_norm": 36.20463180541992,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.0288,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2515592515592516,
877
+ "grad_norm": 27.810020446777344,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 5.2437,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.25363825363825365,
884
+ "grad_norm": 28.593204498291016,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 4.9836,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.25571725571725573,
891
+ "grad_norm": 29.15188980102539,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.4529,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2577962577962578,
898
+ "grad_norm": 27.521888732910156,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.1731,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2598752598752599,
905
+ "grad_norm": 38.01824188232422,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.1737,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.26195426195426197,
912
+ "grad_norm": 27.05405044555664,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.4588,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.26403326403326405,
919
+ "grad_norm": 32.03307342529297,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.1365,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2661122661122661,
926
+ "grad_norm": 26.123497009277344,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.7003,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.2681912681912682,
933
+ "grad_norm": 26.265361785888672,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.8316,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.2702702702702703,
940
+ "grad_norm": 27.146703720092773,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.1508,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.27234927234927236,
947
+ "grad_norm": 26.394529342651367,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.0902,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.27442827442827444,
954
+ "grad_norm": 30.819000244140625,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.9659,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2765072765072765,
961
+ "grad_norm": 36.68458557128906,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 5.0427,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2785862785862786,
968
+ "grad_norm": 32.3036003112793,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.4486,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.2806652806652807,
975
+ "grad_norm": 27.863311767578125,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.2872,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.28274428274428276,
982
+ "grad_norm": 29.791475296020508,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.1583,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.28482328482328484,
989
+ "grad_norm": 28.367292404174805,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.9147,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2869022869022869,
996
+ "grad_norm": 28.982662200927734,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.4158,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.288981288981289,
1003
+ "grad_norm": 30.221160888671875,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.9438,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2910602910602911,
1010
+ "grad_norm": 26.62199592590332,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.0532,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.29313929313929316,
1017
+ "grad_norm": 26.665769577026367,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.1416,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.29521829521829523,
1024
+ "grad_norm": 25.941627502441406,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.7407,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.2972972972972973,
1031
+ "grad_norm": 29.765132904052734,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.7022,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.2993762993762994,
1038
+ "grad_norm": 28.01789093017578,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.4899,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.30145530145530147,
1045
+ "grad_norm": 29.412342071533203,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 6.1604,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.30353430353430355,
1052
+ "grad_norm": 30.55994415283203,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 6.4566,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.30561330561330563,
1059
+ "grad_norm": 28.54621124267578,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.8721,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.3076923076923077,
1066
+ "grad_norm": 29.459003448486328,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.9285,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3097713097713098,
1073
+ "grad_norm": 29.382354736328125,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.6228,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.31185031185031187,
1080
+ "grad_norm": 35.232913970947266,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.4351,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.31185031185031187,
1087
+ "eval_loss": 1.3784149885177612,
1088
+ "eval_runtime": 16.5592,
1089
+ "eval_samples_per_second": 48.976,
1090
+ "eval_steps_per_second": 12.259,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.23536538976256e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null