lesso commited on
Commit
796950a
·
verified ·
1 Parent(s): 444ab0e

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 sha256:14d3c368e3744a87120fa02b36def8c35ae56a3e176e906cea85f5b81b3bbe08
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce81bc367d7cc346307f5ebe246dd95890b72f80495d6432116264183194b06f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5406c8b7bb921e9147a6706c9b5e19b42cd291e65d4ce13820cc1b514341edd5
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9e4b7959a5bc202b01cdb7a5a91d3cea28584831dd93819cc0575135e6ab44
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:b0636ac1e1cd9b5ed3b02f674cf2400e6388a98470c99628f3f15decd2b55b27
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ddff2d916bf462dba1f9a5b8857a6d64f3e900032561c108740832c8c0c2f4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a046f3bc9d619a7e62601f3cf33ff02f6ad189db5b564eab88c1bb00e13b059d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7431a5f5e7b667e1ad74dfbaf504ae1d5a622ff6eb54e4f385c161883d2319ba
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4575375020503998,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.019609765663300322,
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": 8.83,
732
  "eval_steps_per_second": 2.207,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.774261496696013e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.41522201895713806,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.029414648494950485,
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": 8.83,
732
  "eval_steps_per_second": 2.207,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.019805863319933326,
737
+ "grad_norm": 4.1386566162109375,
738
+ "learning_rate": 5.278263157894736e-05,
739
+ "loss": 1.3238,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.02000196097656633,
744
+ "grad_norm": 3.137593984603882,
745
+ "learning_rate": 5.224947368421053e-05,
746
+ "loss": 0.9319,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.020198058633199335,
751
+ "grad_norm": 3.7397894859313965,
752
+ "learning_rate": 5.171631578947368e-05,
753
+ "loss": 0.9041,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.020394156289832335,
758
+ "grad_norm": 2.7134053707122803,
759
+ "learning_rate": 5.1183157894736844e-05,
760
+ "loss": 0.7395,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02059025394646534,
765
+ "grad_norm": 4.872076988220215,
766
+ "learning_rate": 5.065e-05,
767
+ "loss": 1.2704,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.020786351603098344,
772
+ "grad_norm": 4.066561698913574,
773
+ "learning_rate": 5.011684210526315e-05,
774
+ "loss": 0.8238,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.020982449259731348,
779
+ "grad_norm": 2.926990032196045,
780
+ "learning_rate": 4.958368421052631e-05,
781
+ "loss": 0.6825,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02117854691636435,
786
+ "grad_norm": 3.305487632751465,
787
+ "learning_rate": 4.9050526315789473e-05,
788
+ "loss": 0.6813,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.021374644572997353,
793
+ "grad_norm": 5.23881196975708,
794
+ "learning_rate": 4.851736842105263e-05,
795
+ "loss": 0.9895,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.021570742229630357,
800
+ "grad_norm": 3.481923818588257,
801
+ "learning_rate": 4.798421052631579e-05,
802
+ "loss": 0.6055,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.021766839886263357,
807
+ "grad_norm": 2.770195722579956,
808
+ "learning_rate": 4.745105263157895e-05,
809
+ "loss": 0.4307,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02196293754289636,
814
+ "grad_norm": 5.2551398277282715,
815
+ "learning_rate": 4.69178947368421e-05,
816
+ "loss": 1.2838,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.022159035199529366,
821
+ "grad_norm": 3.3223180770874023,
822
+ "learning_rate": 4.638473684210526e-05,
823
+ "loss": 0.7093,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.02235513285616237,
828
+ "grad_norm": 4.730376720428467,
829
+ "learning_rate": 4.585157894736842e-05,
830
+ "loss": 0.8399,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02255123051279537,
835
+ "grad_norm": 5.192849636077881,
836
+ "learning_rate": 4.531842105263158e-05,
837
+ "loss": 0.7188,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.022747328169428375,
842
+ "grad_norm": 3.2309155464172363,
843
+ "learning_rate": 4.478526315789473e-05,
844
+ "loss": 0.5142,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02294342582606138,
849
+ "grad_norm": 4.466787815093994,
850
+ "learning_rate": 4.425210526315789e-05,
851
+ "loss": 0.7535,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.023139523482694383,
856
+ "grad_norm": 3.1393327713012695,
857
+ "learning_rate": 4.3718947368421054e-05,
858
+ "loss": 0.5282,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.023335621139327384,
863
+ "grad_norm": 5.505728721618652,
864
+ "learning_rate": 4.318578947368421e-05,
865
+ "loss": 0.9189,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.023531718795960388,
870
+ "grad_norm": 3.670624017715454,
871
+ "learning_rate": 4.265263157894736e-05,
872
+ "loss": 0.7202,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.023727816452593392,
877
+ "grad_norm": 5.582329750061035,
878
+ "learning_rate": 4.211947368421052e-05,
879
+ "loss": 0.716,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.023923914109226396,
884
+ "grad_norm": 4.540538787841797,
885
+ "learning_rate": 4.1586315789473684e-05,
886
+ "loss": 0.5689,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.024120011765859397,
891
+ "grad_norm": 6.913193225860596,
892
+ "learning_rate": 4.105315789473684e-05,
893
+ "loss": 0.985,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0243161094224924,
898
+ "grad_norm": 6.866704940795898,
899
+ "learning_rate": 4.052e-05,
900
+ "loss": 0.7173,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.024512207079125405,
905
+ "grad_norm": 8.457905769348145,
906
+ "learning_rate": 3.998684210526316e-05,
907
+ "loss": 0.7499,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.024708304735758406,
912
+ "grad_norm": 6.656124591827393,
913
+ "learning_rate": 3.945368421052631e-05,
914
+ "loss": 1.0133,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02490440239239141,
919
+ "grad_norm": 6.976663112640381,
920
+ "learning_rate": 3.892052631578947e-05,
921
+ "loss": 0.8715,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.025100500049024414,
926
+ "grad_norm": 8.578405380249023,
927
+ "learning_rate": 3.838736842105263e-05,
928
+ "loss": 0.6424,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.02529659770565742,
933
+ "grad_norm": 7.345449924468994,
934
+ "learning_rate": 3.785421052631579e-05,
935
+ "loss": 0.8932,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.02549269536229042,
940
+ "grad_norm": 5.459024906158447,
941
+ "learning_rate": 3.732105263157894e-05,
942
+ "loss": 0.5799,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.025688793018923423,
947
+ "grad_norm": 6.494460105895996,
948
+ "learning_rate": 3.67878947368421e-05,
949
+ "loss": 0.4163,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.025884890675556427,
954
+ "grad_norm": 5.555450916290283,
955
+ "learning_rate": 3.6254736842105264e-05,
956
+ "loss": 0.5469,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02608098833218943,
961
+ "grad_norm": 6.8839263916015625,
962
+ "learning_rate": 3.572157894736842e-05,
963
+ "loss": 0.9823,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.026277085988822432,
968
+ "grad_norm": 12.403116226196289,
969
+ "learning_rate": 3.518842105263158e-05,
970
+ "loss": 0.6406,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.026473183645455436,
975
+ "grad_norm": 7.836792469024658,
976
+ "learning_rate": 3.465526315789473e-05,
977
+ "loss": 1.1348,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02666928130208844,
982
+ "grad_norm": 7.983771800994873,
983
+ "learning_rate": 3.4122105263157894e-05,
984
+ "loss": 0.803,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.026865378958721445,
989
+ "grad_norm": 7.406615734100342,
990
+ "learning_rate": 3.358894736842105e-05,
991
+ "loss": 0.6877,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.027061476615354445,
996
+ "grad_norm": 7.180506706237793,
997
+ "learning_rate": 3.305578947368421e-05,
998
+ "loss": 0.9407,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.02725757427198745,
1003
+ "grad_norm": 10.637256622314453,
1004
+ "learning_rate": 3.252263157894737e-05,
1005
+ "loss": 1.0234,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.027453671928620454,
1010
+ "grad_norm": 12.093735694885254,
1011
+ "learning_rate": 3.198947368421052e-05,
1012
+ "loss": 0.9802,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.027649769585253458,
1017
+ "grad_norm": 11.916462898254395,
1018
+ "learning_rate": 3.1456315789473684e-05,
1019
+ "loss": 0.9617,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02784586724188646,
1024
+ "grad_norm": 9.011691093444824,
1025
+ "learning_rate": 3.092315789473684e-05,
1026
+ "loss": 0.4959,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.028041964898519463,
1031
+ "grad_norm": 5.6275954246521,
1032
+ "learning_rate": 3.039e-05,
1033
+ "loss": 0.3209,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.028238062555152467,
1038
+ "grad_norm": 10.726852416992188,
1039
+ "learning_rate": 2.9856842105263153e-05,
1040
+ "loss": 1.2664,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.028434160211785468,
1045
+ "grad_norm": 12.800682067871094,
1046
+ "learning_rate": 2.9323684210526317e-05,
1047
+ "loss": 1.4327,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.028630257868418472,
1052
+ "grad_norm": 8.828701972961426,
1053
+ "learning_rate": 2.879052631578947e-05,
1054
+ "loss": 0.8394,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.028826355525051476,
1059
+ "grad_norm": 20.543346405029297,
1060
+ "learning_rate": 2.8257368421052628e-05,
1061
+ "loss": 2.1235,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.02902245318168448,
1066
+ "grad_norm": 24.438735961914062,
1067
+ "learning_rate": 2.772421052631579e-05,
1068
+ "loss": 1.5965,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.02921855083831748,
1073
+ "grad_norm": 21.095970153808594,
1074
+ "learning_rate": 2.7191052631578946e-05,
1075
+ "loss": 1.35,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.029414648494950485,
1080
+ "grad_norm": 18.338863372802734,
1081
+ "learning_rate": 2.6657894736842104e-05,
1082
+ "loss": 1.7666,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.029414648494950485,
1087
+ "eval_loss": 0.41522201895713806,
1088
+ "eval_runtime": 243.3207,
1089
+ "eval_samples_per_second": 8.828,
1090
+ "eval_steps_per_second": 2.207,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.652448497421517e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null