prxy5608 commited on
Commit
b95ddc9
·
verified ·
1 Parent(s): 0641032

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:d46cc16252a138ad2ed7004a89a1f3c40362ebe14856ec3c7b0e7c5f603d71c0
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd56a7fd90054b7ae4242ffaa02259cfd75a5b2862fff1652d3cefae86b45e0e
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a820d407b85e6905270bb3dde476fe635d6810a42cfe9ab42c3acbf3b70b76c
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207a556545054f31ee07339f6944052d0206120bc7189b26eb0e7b6c3f189951
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1055649d31d13b86c3970621b427ed87f029e37dac0a8cb9015bfc7047a186b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321b4affb17441ee45c41d58f56cd011af3a78f57643d39ce777a061381f05f1
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": 2.7137081623077393,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4371584699453552,
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": 61.74,
732
  "eval_steps_per_second": 15.515,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6658776367104000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.595000743865967,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6557377049180327,
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": 61.74,
732
  "eval_steps_per_second": 15.515,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.44153005464480877,
737
+ "grad_norm": 3.6674201488494873,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.0462,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4459016393442623,
744
+ "grad_norm": 3.6958484649658203,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.9499,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.45027322404371584,
751
+ "grad_norm": 3.729661703109741,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.8639,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4546448087431694,
758
+ "grad_norm": 3.8177297115325928,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.1011,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.45901639344262296,
765
+ "grad_norm": 3.2442538738250732,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.7323,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4633879781420765,
772
+ "grad_norm": 3.5539169311523438,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.7662,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.46775956284153003,
779
+ "grad_norm": 3.732706308364868,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.1186,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4721311475409836,
786
+ "grad_norm": 2.835399627685547,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.6593,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.47650273224043715,
793
+ "grad_norm": 2.702887773513794,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.5559,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4808743169398907,
800
+ "grad_norm": 2.5662825107574463,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.4342,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4852459016393443,
807
+ "grad_norm": 2.879852771759033,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.8159,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.4896174863387978,
814
+ "grad_norm": 2.3322107791900635,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.69,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.49398907103825135,
821
+ "grad_norm": 2.4512860774993896,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.6321,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.49836065573770494,
828
+ "grad_norm": 2.4820594787597656,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.6554,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5027322404371585,
835
+ "grad_norm": 2.387237548828125,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.563,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.507103825136612,
842
+ "grad_norm": 2.6377415657043457,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.754,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5114754098360655,
849
+ "grad_norm": 2.5735561847686768,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.8631,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5158469945355191,
856
+ "grad_norm": 2.5990209579467773,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.5718,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5202185792349727,
863
+ "grad_norm": 2.685863733291626,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.9478,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5245901639344263,
870
+ "grad_norm": 2.7012393474578857,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.6173,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5289617486338798,
877
+ "grad_norm": 2.47837233543396,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.8273,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5333333333333333,
884
+ "grad_norm": 2.8187203407287598,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.6816,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5377049180327869,
891
+ "grad_norm": 2.7357730865478516,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.7524,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5420765027322404,
898
+ "grad_norm": 2.868358850479126,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.8465,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.546448087431694,
905
+ "grad_norm": 2.652200937271118,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.8772,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5508196721311476,
912
+ "grad_norm": 2.764561653137207,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.7359,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5551912568306011,
919
+ "grad_norm": 3.1617627143859863,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.6818,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5595628415300546,
926
+ "grad_norm": 2.701509952545166,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.9375,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5639344262295082,
933
+ "grad_norm": 2.542893886566162,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.438,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5683060109289617,
940
+ "grad_norm": 2.793731212615967,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.7625,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.5726775956284152,
947
+ "grad_norm": 2.736274480819702,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.7501,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5770491803278689,
954
+ "grad_norm": 3.0499179363250732,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.9075,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5814207650273224,
961
+ "grad_norm": 2.8469018936157227,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.7627,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.585792349726776,
968
+ "grad_norm": 2.7116096019744873,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.4971,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5901639344262295,
975
+ "grad_norm": 2.695939540863037,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.5254,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.594535519125683,
982
+ "grad_norm": 2.9823148250579834,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.8118,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5989071038251366,
989
+ "grad_norm": 3.03371000289917,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.6509,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6032786885245902,
996
+ "grad_norm": 2.901766061782837,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.8283,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6076502732240437,
1003
+ "grad_norm": 2.5338025093078613,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.2989,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6120218579234973,
1010
+ "grad_norm": 2.924435615539551,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.8503,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6163934426229508,
1017
+ "grad_norm": 2.920508623123169,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.6653,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6207650273224044,
1024
+ "grad_norm": 2.804220199584961,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.445,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6251366120218579,
1031
+ "grad_norm": 2.881897449493408,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.2941,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6295081967213115,
1038
+ "grad_norm": 3.2550201416015625,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.4319,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6338797814207651,
1045
+ "grad_norm": 3.1499900817871094,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.7472,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6382513661202186,
1052
+ "grad_norm": 3.791355609893799,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.7002,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6426229508196721,
1059
+ "grad_norm": 3.142332077026367,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.4231,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6469945355191257,
1066
+ "grad_norm": 3.307037830352783,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.5866,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6513661202185792,
1073
+ "grad_norm": 3.90175199508667,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.5459,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6557377049180327,
1080
+ "grad_norm": 4.2901129722595215,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.6595,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6557377049180327,
1087
+ "eval_loss": 2.595000743865967,
1088
+ "eval_runtime": 6.2478,
1089
+ "eval_samples_per_second": 61.782,
1090
+ "eval_steps_per_second": 15.525,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9988164550656000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null