prxy5606 commited on
Commit
198db21
·
verified ·
1 Parent(s): 5f05d26

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 sha256:48d746275a86446149de2157e458d71be0eb9b06739a4742efdee6a9ba826719
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861f7e06bd784deff12797a008e635ea0e3d9df6414b57a583d59d89074da485
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c34ee67117eb3d2cecb630035ddb7ab3461b03e5e1a40c66fca3f44eee4675b1
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e982a50e54f13560c730cef20f29c1d0983339ba806242790bcf8249c7ce28a
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18557da8ea53d517c6fcda141f87c9298cf375fd5e5d99056fd5068a89eaacc0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55435750cb5a67f66a887ad05d1fea28bc552d21daeda98571c5f4ceafa2374
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7711856961250305,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06555227794165848,
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": 12.866,
732
  "eval_steps_per_second": 6.433,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3371612024589517e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7386060357093811,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.09832841691248771,
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": 12.866,
732
  "eval_steps_per_second": 6.433,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.06620780072107506,
737
+ "grad_norm": 0.2854394018650055,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.806,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.06686332350049164,
744
+ "grad_norm": 0.2501490116119385,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.766,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.06751884627990823,
751
+ "grad_norm": 0.2460934966802597,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.7838,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06817436905932481,
758
+ "grad_norm": 0.21523185074329376,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.723,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0688298918387414,
765
+ "grad_norm": 0.18155883252620697,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.7721,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06948541461815798,
772
+ "grad_norm": 0.17506293952465057,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.7722,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07014093739757457,
779
+ "grad_norm": 0.1855786293745041,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.7588,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.07079646017699115,
786
+ "grad_norm": 0.18874594569206238,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.7552,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.07145198295640774,
793
+ "grad_norm": 0.18815328180789948,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.7624,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.07210750573582432,
800
+ "grad_norm": 0.19321073591709137,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.7655,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0727630285152409,
807
+ "grad_norm": 0.19126199185848236,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.7148,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.07341855129465749,
814
+ "grad_norm": 0.1977165937423706,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.7435,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.07407407407407407,
821
+ "grad_norm": 0.20759083330631256,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.7297,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.07472959685349066,
828
+ "grad_norm": 0.21419835090637207,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.7835,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.07538511963290724,
835
+ "grad_norm": 0.2073257565498352,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.7402,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.07604064241232383,
842
+ "grad_norm": 0.20203441381454468,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.767,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.07669616519174041,
849
+ "grad_norm": 0.20654654502868652,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.7574,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.077351687971157,
856
+ "grad_norm": 0.2055203914642334,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.7623,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.07800721075057358,
863
+ "grad_norm": 0.20675183832645416,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.753,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07866273352999016,
870
+ "grad_norm": 0.21456296741962433,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.7794,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07931825630940675,
877
+ "grad_norm": 0.21291404962539673,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.7853,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07997377908882333,
884
+ "grad_norm": 0.21847602725028992,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.777,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.08062930186823992,
891
+ "grad_norm": 0.21636834740638733,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.7493,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0812848246476565,
898
+ "grad_norm": 0.21808314323425293,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.7649,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0819403474270731,
905
+ "grad_norm": 0.22126802802085876,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.7338,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.08259587020648967,
912
+ "grad_norm": 0.22322940826416016,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.7689,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.08325139298590627,
919
+ "grad_norm": 0.2250346690416336,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.7212,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.08390691576532285,
926
+ "grad_norm": 0.2389887422323227,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.7524,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.08456243854473942,
933
+ "grad_norm": 0.2435750961303711,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.7743,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.08521796132415602,
940
+ "grad_norm": 0.22282806038856506,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.7025,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0858734841035726,
947
+ "grad_norm": 0.23607531189918518,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.7981,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.08652900688298919,
954
+ "grad_norm": 0.24423764646053314,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.7636,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.08718452966240577,
961
+ "grad_norm": 0.2365090698003769,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.7201,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.08784005244182236,
968
+ "grad_norm": 0.237791508436203,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.7025,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.08849557522123894,
975
+ "grad_norm": 0.2471911460161209,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.745,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.08915109800065553,
982
+ "grad_norm": 0.24586082994937897,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.7251,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08980662078007211,
989
+ "grad_norm": 0.2511478662490845,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.7601,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.09046214355948869,
996
+ "grad_norm": 0.24248506128787994,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.7078,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.09111766633890528,
1003
+ "grad_norm": 0.26230138540267944,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.7117,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.09177318911832186,
1010
+ "grad_norm": 0.26975852251052856,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.7202,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.09242871189773845,
1017
+ "grad_norm": 0.27416229248046875,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.7577,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.09308423467715503,
1024
+ "grad_norm": 0.2665165364742279,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.7151,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.09373975745657162,
1031
+ "grad_norm": 0.2814359962940216,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.7466,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0943952802359882,
1038
+ "grad_norm": 0.3412998616695404,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.7975,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.09505080301540479,
1045
+ "grad_norm": 0.30855631828308105,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.7205,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.09570632579482137,
1052
+ "grad_norm": 0.27196890115737915,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.7026,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.09636184857423795,
1059
+ "grad_norm": 0.31602856516838074,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.7064,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.09701737135365454,
1066
+ "grad_norm": 0.3314160704612732,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.7897,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.09767289413307112,
1073
+ "grad_norm": 0.39607930183410645,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.704,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.09832841691248771,
1080
+ "grad_norm": 1.1761752367019653,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.7426,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.09832841691248771,
1087
+ "eval_loss": 0.7386060357093811,
1088
+ "eval_runtime": 498.5167,
1089
+ "eval_samples_per_second": 5.155,
1090
+ "eval_steps_per_second": 2.578,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.0024155320405197e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null