lesso commited on
Commit
e85f8c1
·
verified ·
1 Parent(s): 207dc74

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 sha256:8fb6e14c1dc0e267243d1680cab790d8314b1c5fcb4da67a038fce36b90149da
3
  size 891333320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7d6a320a3e50511491e410ce1b92ab6609fc6b63f4899678a1920b4ebaabbe
3
  size 891333320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e8dcbc6dd132fd1a7b91c7a9082a25d128ce89c39938bac621f08b10ff4e246
3
  size 452984596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca96afc210261a977d9a57b5d9126920814459272c707cf06210a6ee8e176cd6
3
  size 452984596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcc8693a88865ccac0d49f32c9a8625890826958a528812b54d0ec6618a35bcc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57645f2c6130b0019a3d70e4f7a375692f5e849e44c5f7d42df1b8670004659b
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": 0.2767239809036255,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.081799591002045,
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": 3.128,
732
  "eval_steps_per_second": 0.784,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.243747197124608e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.22924812138080597,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.12269938650306748,
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": 3.128,
732
  "eval_steps_per_second": 0.784,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08261758691206544,
737
+ "grad_norm": 2.208616256713867,
738
+ "learning_rate": 5.278263157894736e-05,
739
+ "loss": 0.8554,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0834355828220859,
744
+ "grad_norm": 0.6053175330162048,
745
+ "learning_rate": 5.224947368421053e-05,
746
+ "loss": 0.8102,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08425357873210634,
751
+ "grad_norm": 0.443279892206192,
752
+ "learning_rate": 5.171631578947368e-05,
753
+ "loss": 0.6613,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0850715746421268,
758
+ "grad_norm": 0.5657853484153748,
759
+ "learning_rate": 5.1183157894736844e-05,
760
+ "loss": 0.904,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08588957055214724,
765
+ "grad_norm": 0.5122092366218567,
766
+ "learning_rate": 5.065e-05,
767
+ "loss": 0.7585,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08670756646216769,
772
+ "grad_norm": 0.4323250353336334,
773
+ "learning_rate": 5.011684210526315e-05,
774
+ "loss": 0.6443,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.08752556237218814,
779
+ "grad_norm": 0.4903777539730072,
780
+ "learning_rate": 4.958368421052631e-05,
781
+ "loss": 0.8381,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08834355828220859,
786
+ "grad_norm": 0.49713271856307983,
787
+ "learning_rate": 4.9050526315789473e-05,
788
+ "loss": 0.6974,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08916155419222904,
793
+ "grad_norm": 0.5440729260444641,
794
+ "learning_rate": 4.851736842105263e-05,
795
+ "loss": 0.7326,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08997955010224949,
800
+ "grad_norm": 0.5971400737762451,
801
+ "learning_rate": 4.798421052631579e-05,
802
+ "loss": 0.8564,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09079754601226994,
807
+ "grad_norm": 0.4081849157810211,
808
+ "learning_rate": 4.745105263157895e-05,
809
+ "loss": 0.5119,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09161554192229039,
814
+ "grad_norm": 0.42180880904197693,
815
+ "learning_rate": 4.69178947368421e-05,
816
+ "loss": 0.479,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09243353783231084,
821
+ "grad_norm": 0.48688748478889465,
822
+ "learning_rate": 4.638473684210526e-05,
823
+ "loss": 0.5893,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09325153374233129,
828
+ "grad_norm": 0.3098672926425934,
829
+ "learning_rate": 4.585157894736842e-05,
830
+ "loss": 0.3024,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09406952965235174,
835
+ "grad_norm": 0.3973608911037445,
836
+ "learning_rate": 4.531842105263158e-05,
837
+ "loss": 0.4749,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09488752556237219,
842
+ "grad_norm": 0.45003950595855713,
843
+ "learning_rate": 4.478526315789473e-05,
844
+ "loss": 0.5641,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09570552147239264,
849
+ "grad_norm": 0.4103372395038605,
850
+ "learning_rate": 4.425210526315789e-05,
851
+ "loss": 0.3926,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09652351738241309,
856
+ "grad_norm": 0.5700619220733643,
857
+ "learning_rate": 4.3718947368421054e-05,
858
+ "loss": 0.7772,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09734151329243354,
863
+ "grad_norm": 0.5302966833114624,
864
+ "learning_rate": 4.318578947368421e-05,
865
+ "loss": 0.5547,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09815950920245399,
870
+ "grad_norm": 0.5432780981063843,
871
+ "learning_rate": 4.265263157894736e-05,
872
+ "loss": 0.7294,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09897750511247444,
877
+ "grad_norm": 0.5698531866073608,
878
+ "learning_rate": 4.211947368421052e-05,
879
+ "loss": 0.6319,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09979550102249489,
884
+ "grad_norm": 0.4369616210460663,
885
+ "learning_rate": 4.1586315789473684e-05,
886
+ "loss": 0.4439,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10061349693251534,
891
+ "grad_norm": 0.5331543684005737,
892
+ "learning_rate": 4.105315789473684e-05,
893
+ "loss": 0.5258,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10143149284253579,
898
+ "grad_norm": 0.5208017230033875,
899
+ "learning_rate": 4.052e-05,
900
+ "loss": 0.5332,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10224948875255624,
905
+ "grad_norm": 0.6325660943984985,
906
+ "learning_rate": 3.998684210526316e-05,
907
+ "loss": 0.7877,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.10306748466257669,
912
+ "grad_norm": 0.8065600991249084,
913
+ "learning_rate": 3.945368421052631e-05,
914
+ "loss": 0.8469,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10388548057259714,
919
+ "grad_norm": 0.5705050230026245,
920
+ "learning_rate": 3.892052631578947e-05,
921
+ "loss": 0.5351,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10470347648261759,
926
+ "grad_norm": 0.60113525390625,
927
+ "learning_rate": 3.838736842105263e-05,
928
+ "loss": 0.5405,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10552147239263804,
933
+ "grad_norm": 0.5440464019775391,
934
+ "learning_rate": 3.785421052631579e-05,
935
+ "loss": 0.5673,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.10633946830265849,
940
+ "grad_norm": 0.6333761215209961,
941
+ "learning_rate": 3.732105263157894e-05,
942
+ "loss": 0.7063,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.10715746421267894,
947
+ "grad_norm": 0.3166744112968445,
948
+ "learning_rate": 3.67878947368421e-05,
949
+ "loss": 0.2672,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10797546012269939,
954
+ "grad_norm": 0.47239211201667786,
955
+ "learning_rate": 3.6254736842105264e-05,
956
+ "loss": 0.2944,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10879345603271984,
961
+ "grad_norm": 0.6278908252716064,
962
+ "learning_rate": 3.572157894736842e-05,
963
+ "loss": 0.7175,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10961145194274029,
968
+ "grad_norm": 6.725371837615967,
969
+ "learning_rate": 3.518842105263158e-05,
970
+ "loss": 0.5899,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11042944785276074,
975
+ "grad_norm": 0.3569982945919037,
976
+ "learning_rate": 3.465526315789473e-05,
977
+ "loss": 0.2153,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11124744376278119,
982
+ "grad_norm": 0.8054752945899963,
983
+ "learning_rate": 3.4122105263157894e-05,
984
+ "loss": 0.6044,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11206543967280164,
989
+ "grad_norm": 0.37957316637039185,
990
+ "learning_rate": 3.358894736842105e-05,
991
+ "loss": 0.2575,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.11288343558282209,
996
+ "grad_norm": 0.33962732553482056,
997
+ "learning_rate": 3.305578947368421e-05,
998
+ "loss": 0.1472,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11370143149284254,
1003
+ "grad_norm": 0.1770872324705124,
1004
+ "learning_rate": 3.252263157894737e-05,
1005
+ "loss": 0.008,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11451942740286299,
1010
+ "grad_norm": 0.09861530363559723,
1011
+ "learning_rate": 3.198947368421052e-05,
1012
+ "loss": 0.0033,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11533742331288344,
1017
+ "grad_norm": 0.1032843068242073,
1018
+ "learning_rate": 3.1456315789473684e-05,
1019
+ "loss": 0.0027,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11615541922290389,
1024
+ "grad_norm": 0.11989390105009079,
1025
+ "learning_rate": 3.092315789473684e-05,
1026
+ "loss": 0.0018,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11697341513292434,
1031
+ "grad_norm": 0.01104150153696537,
1032
+ "learning_rate": 3.039e-05,
1033
+ "loss": 0.0004,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11779141104294479,
1038
+ "grad_norm": 0.01930282451212406,
1039
+ "learning_rate": 2.9856842105263153e-05,
1040
+ "loss": 0.0005,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11860940695296524,
1045
+ "grad_norm": 0.15893378853797913,
1046
+ "learning_rate": 2.9323684210526317e-05,
1047
+ "loss": 0.0031,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.11942740286298568,
1052
+ "grad_norm": 0.03184283524751663,
1053
+ "learning_rate": 2.879052631578947e-05,
1054
+ "loss": 0.0009,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12024539877300613,
1059
+ "grad_norm": 0.06102335825562477,
1060
+ "learning_rate": 2.8257368421052628e-05,
1061
+ "loss": 0.0013,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12106339468302658,
1066
+ "grad_norm": 0.0802997276186943,
1067
+ "learning_rate": 2.772421052631579e-05,
1068
+ "loss": 0.0015,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12188139059304703,
1073
+ "grad_norm": 0.02622400037944317,
1074
+ "learning_rate": 2.7191052631578946e-05,
1075
+ "loss": 0.0005,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.12269938650306748,
1080
+ "grad_norm": 0.019685884937644005,
1081
+ "learning_rate": 2.6657894736842104e-05,
1082
+ "loss": 0.0006,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.12269938650306748,
1087
+ "eval_loss": 0.22924812138080597,
1088
+ "eval_runtime": 164.6274,
1089
+ "eval_samples_per_second": 3.128,
1090
+ "eval_steps_per_second": 0.784,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.870788720328704e+17,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null