prxy5606 commited on
Commit
77db71d
·
verified ·
1 Parent(s): 24e8300

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 sha256:5d9d35cfb21a2e17f6d6a801cee3da54c555e9b19cc8a59b017ee8074e1b653e
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dab7c4a4faa0cba1318c47239bb3f6ded4a8d9d95bad2df15083125b14db47d
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95f7f371465141b88165f2095d9e5a57105c9f997b99e12f580762b3e58f7ad5
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9932bb344db32a1a5f269bd85e5b33f167912b60eaad2eb2de2ad435eff900
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdfd25bee6ef1d7df179ee4f352de35651e042cf1404bfe0c33a89884858eab9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1599ba58fdeff5ad216211f9f49f0af7d8a62774223233c6ad84ea0f5fc30f
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": 0.9667438268661499,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.36986301369863,
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": 6.945,
732
  "eval_steps_per_second": 1.75,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.7566866887081984e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8967676162719727,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.0547945205479454,
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": 6.945,
732
  "eval_steps_per_second": 1.75,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.3835616438356164,
737
+ "grad_norm": 0.4706757962703705,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.921,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.3972602739726028,
744
+ "grad_norm": 0.44695258140563965,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8156,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.410958904109589,
751
+ "grad_norm": 0.4904194176197052,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9468,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.4246575342465753,
758
+ "grad_norm": 0.4590471386909485,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.7876,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.4383561643835616,
765
+ "grad_norm": 0.4899277091026306,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.7743,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.452054794520548,
772
+ "grad_norm": 0.6832799315452576,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.9999,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.4657534246575343,
779
+ "grad_norm": 0.5903638601303101,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.9089,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.4794520547945205,
786
+ "grad_norm": 0.6132621765136719,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9061,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.4931506849315068,
793
+ "grad_norm": 0.8069959878921509,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.8017,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.5068493150684932,
800
+ "grad_norm": 0.4573930501937866,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.0055,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.5205479452054793,
807
+ "grad_norm": 0.446062296628952,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9394,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.5342465753424657,
814
+ "grad_norm": 0.5781521797180176,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8688,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.547945205479452,
821
+ "grad_norm": 0.5024420022964478,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.9995,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.5616438356164384,
828
+ "grad_norm": 0.4697863459587097,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.9577,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.5753424657534247,
835
+ "grad_norm": 0.47331348061561584,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.0023,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.589041095890411,
842
+ "grad_norm": 0.4437616765499115,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8376,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.6027397260273972,
849
+ "grad_norm": 0.43482112884521484,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9088,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.6164383561643836,
856
+ "grad_norm": 0.41529685258865356,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9271,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.6301369863013697,
863
+ "grad_norm": 0.4500505328178406,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9108,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.643835616438356,
870
+ "grad_norm": 0.42425259947776794,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.8784,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.6575342465753424,
877
+ "grad_norm": 0.4351794123649597,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8761,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.6712328767123288,
884
+ "grad_norm": 0.4875510632991791,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9418,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.6849315068493151,
891
+ "grad_norm": 0.468164324760437,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.7464,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.6986301369863015,
898
+ "grad_norm": 0.5441304445266724,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.912,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.7123287671232876,
905
+ "grad_norm": 0.6000600457191467,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.917,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.726027397260274,
912
+ "grad_norm": 0.5635849237442017,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.7562,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.7397260273972601,
919
+ "grad_norm": 0.7503162026405334,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7748,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.7534246575342465,
926
+ "grad_norm": 0.5164412260055542,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.9248,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.7671232876712328,
933
+ "grad_norm": 0.5084578990936279,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.8714,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.7808219178082192,
940
+ "grad_norm": 0.4800652265548706,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.9039,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.7945205479452055,
947
+ "grad_norm": 0.46519795060157776,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.8373,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.808219178082192,
954
+ "grad_norm": 0.495684951543808,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.9882,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.821917808219178,
961
+ "grad_norm": 0.4558713436126709,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.8209,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.8356164383561644,
968
+ "grad_norm": 0.45472729206085205,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.7999,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.8493150684931505,
975
+ "grad_norm": 0.4365823268890381,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.8152,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.8630136986301369,
982
+ "grad_norm": 0.48378491401672363,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.8732,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.8767123287671232,
989
+ "grad_norm": 0.4269355833530426,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.8344,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.8904109589041096,
996
+ "grad_norm": 0.4657435119152069,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8597,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.904109589041096,
1003
+ "grad_norm": 0.43430280685424805,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.8464,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.9178082191780823,
1010
+ "grad_norm": 0.46137768030166626,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.8788,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.9315068493150684,
1017
+ "grad_norm": 0.46057605743408203,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.8454,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.9452054794520548,
1024
+ "grad_norm": 0.45767173171043396,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.8869,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.958904109589041,
1031
+ "grad_norm": 0.6618921160697937,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9462,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.9726027397260273,
1038
+ "grad_norm": 0.5900852084159851,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.8091,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.9863013698630136,
1045
+ "grad_norm": 0.7364968657493591,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7941,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.0,
1052
+ "grad_norm": 0.512842059135437,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.8132,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.0136986301369864,
1059
+ "grad_norm": 0.42484575510025024,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.7998,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.0273972602739727,
1066
+ "grad_norm": 0.458027184009552,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.8505,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.041095890410959,
1073
+ "grad_norm": 0.458528071641922,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.8125,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.0547945205479454,
1080
+ "grad_norm": 0.45877528190612793,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7932,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.0547945205479454,
1087
+ "eval_loss": 0.8967676162719727,
1088
+ "eval_runtime": 17.7245,
1089
+ "eval_samples_per_second": 6.94,
1090
+ "eval_steps_per_second": 1.749,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.119922465780531e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null