lesso commited on
Commit
8faa643
·
verified ·
1 Parent(s): 3841f24

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 sha256:7b2931bb4fcff1444401454f64b1ee796333c82c01ff0a4266c66d94ad309cfd
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee121882b8f39c4c26104adbc17a04219b3198a461094be646fa2692e509ec0
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7a04edca9a3e04941599cbc7da208c8b85e0ed7f52b9cb04c06f99721c637b4
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4ce12c8e244f236d1fdde2fb635519b3bdaed0fe78ab9fd3ca6dd7bd4a9759
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:b92e73907e1aaf5054eeb6a6806fd620d603f8ebb205d1ae9204df100713c5b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fa271eab9723ca40e52a3f9e4c671b400e9895c404d57b5aad30cdc2b05202
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9085a964616f2d2af1a309022ca2f10b583138a852293c2266e9df64914089
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:191b4f74b8892fe464b31b446bc6f50032359ce22cb38236d5fdccf47f27920e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7442677021026611,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.08818342151675485,
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": 19.642,
732
  "eval_steps_per_second": 4.931,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.57749502246912e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6718300580978394,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.13227513227513227,
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": 19.642,
732
  "eval_steps_per_second": 4.931,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0890652557319224,
737
+ "grad_norm": 11.853898048400879,
738
+ "learning_rate": 5.2199052631578945e-05,
739
+ "loss": 4.1159,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08994708994708994,
744
+ "grad_norm": 11.981085777282715,
745
+ "learning_rate": 5.167178947368422e-05,
746
+ "loss": 3.5512,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.09082892416225749,
751
+ "grad_norm": 11.934968948364258,
752
+ "learning_rate": 5.114452631578948e-05,
753
+ "loss": 3.5918,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.09171075837742504,
758
+ "grad_norm": 11.433150291442871,
759
+ "learning_rate": 5.061726315789474e-05,
760
+ "loss": 3.8466,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.09259259259259259,
765
+ "grad_norm": 9.03652286529541,
766
+ "learning_rate": 5.009e-05,
767
+ "loss": 3.0198,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.09347442680776014,
772
+ "grad_norm": 11.605294227600098,
773
+ "learning_rate": 4.9562736842105266e-05,
774
+ "loss": 3.4652,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09435626102292768,
779
+ "grad_norm": 10.09809398651123,
780
+ "learning_rate": 4.903547368421053e-05,
781
+ "loss": 3.1493,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09523809523809523,
786
+ "grad_norm": 11.366225242614746,
787
+ "learning_rate": 4.850821052631579e-05,
788
+ "loss": 3.1368,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.09611992945326278,
793
+ "grad_norm": 10.735136032104492,
794
+ "learning_rate": 4.7980947368421055e-05,
795
+ "loss": 4.0549,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09700176366843033,
800
+ "grad_norm": 11.092894554138184,
801
+ "learning_rate": 4.745368421052632e-05,
802
+ "loss": 4.017,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09788359788359788,
807
+ "grad_norm": 9.675407409667969,
808
+ "learning_rate": 4.692642105263158e-05,
809
+ "loss": 3.222,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09876543209876543,
814
+ "grad_norm": 10.07262134552002,
815
+ "learning_rate": 4.6399157894736844e-05,
816
+ "loss": 3.5341,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09964726631393298,
821
+ "grad_norm": 9.480923652648926,
822
+ "learning_rate": 4.5871894736842107e-05,
823
+ "loss": 3.0968,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.10052910052910052,
828
+ "grad_norm": 10.37317180633545,
829
+ "learning_rate": 4.5344631578947376e-05,
830
+ "loss": 3.4453,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.10141093474426807,
835
+ "grad_norm": 10.733368873596191,
836
+ "learning_rate": 4.481736842105263e-05,
837
+ "loss": 2.9661,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.10229276895943562,
842
+ "grad_norm": 8.400181770324707,
843
+ "learning_rate": 4.4290105263157895e-05,
844
+ "loss": 2.3788,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.10317460317460317,
849
+ "grad_norm": 11.498528480529785,
850
+ "learning_rate": 4.3762842105263165e-05,
851
+ "loss": 3.1203,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10405643738977072,
856
+ "grad_norm": 9.746874809265137,
857
+ "learning_rate": 4.323557894736843e-05,
858
+ "loss": 2.6302,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10493827160493827,
863
+ "grad_norm": 11.46741771697998,
864
+ "learning_rate": 4.2708315789473684e-05,
865
+ "loss": 3.1229,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10582010582010581,
870
+ "grad_norm": 11.630988121032715,
871
+ "learning_rate": 4.218105263157895e-05,
872
+ "loss": 3.2595,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10670194003527336,
877
+ "grad_norm": 9.176464080810547,
878
+ "learning_rate": 4.1653789473684217e-05,
879
+ "loss": 2.4427,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10758377425044091,
884
+ "grad_norm": 11.956025123596191,
885
+ "learning_rate": 4.112652631578948e-05,
886
+ "loss": 3.2645,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.10846560846560846,
891
+ "grad_norm": 11.984417915344238,
892
+ "learning_rate": 4.0599263157894736e-05,
893
+ "loss": 2.5877,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10934744268077601,
898
+ "grad_norm": 10.380434036254883,
899
+ "learning_rate": 4.0072000000000005e-05,
900
+ "loss": 2.2829,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.11022927689594356,
905
+ "grad_norm": 13.220670700073242,
906
+ "learning_rate": 3.954473684210527e-05,
907
+ "loss": 3.1848,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1111111111111111,
912
+ "grad_norm": 13.67516803741455,
913
+ "learning_rate": 3.901747368421053e-05,
914
+ "loss": 2.7692,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.11199294532627865,
919
+ "grad_norm": 13.009722709655762,
920
+ "learning_rate": 3.849021052631579e-05,
921
+ "loss": 2.9778,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1128747795414462,
926
+ "grad_norm": 12.933755874633789,
927
+ "learning_rate": 3.796294736842106e-05,
928
+ "loss": 3.3846,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.11375661375661375,
933
+ "grad_norm": 16.459245681762695,
934
+ "learning_rate": 3.743568421052632e-05,
935
+ "loss": 3.1339,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1146384479717813,
940
+ "grad_norm": 14.405473709106445,
941
+ "learning_rate": 3.6908421052631576e-05,
942
+ "loss": 2.795,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11552028218694885,
947
+ "grad_norm": 13.93333911895752,
948
+ "learning_rate": 3.6381157894736846e-05,
949
+ "loss": 3.0262,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1164021164021164,
954
+ "grad_norm": 16.57122230529785,
955
+ "learning_rate": 3.585389473684211e-05,
956
+ "loss": 2.8115,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11728395061728394,
961
+ "grad_norm": 14.334020614624023,
962
+ "learning_rate": 3.532663157894737e-05,
963
+ "loss": 2.8398,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11816578483245149,
968
+ "grad_norm": 14.39572811126709,
969
+ "learning_rate": 3.4799368421052634e-05,
970
+ "loss": 2.8725,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.11904761904761904,
975
+ "grad_norm": 11.575310707092285,
976
+ "learning_rate": 3.42721052631579e-05,
977
+ "loss": 2.4439,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11992945326278659,
982
+ "grad_norm": 13.985780715942383,
983
+ "learning_rate": 3.374484210526316e-05,
984
+ "loss": 2.5556,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.12081128747795414,
989
+ "grad_norm": 12.164205551147461,
990
+ "learning_rate": 3.321757894736842e-05,
991
+ "loss": 2.4249,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.12169312169312169,
996
+ "grad_norm": 12.707708358764648,
997
+ "learning_rate": 3.2690315789473686e-05,
998
+ "loss": 1.8734,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.12257495590828923,
1003
+ "grad_norm": 15.824716567993164,
1004
+ "learning_rate": 3.216305263157895e-05,
1005
+ "loss": 3.4027,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.12345679012345678,
1010
+ "grad_norm": 12.011561393737793,
1011
+ "learning_rate": 3.163578947368421e-05,
1012
+ "loss": 2.4948,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.12433862433862433,
1017
+ "grad_norm": 13.7284517288208,
1018
+ "learning_rate": 3.1108526315789475e-05,
1019
+ "loss": 1.9193,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12522045855379188,
1024
+ "grad_norm": 17.932950973510742,
1025
+ "learning_rate": 3.058126315789474e-05,
1026
+ "loss": 3.2839,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12610229276895943,
1031
+ "grad_norm": 15.844171524047852,
1032
+ "learning_rate": 3.0054e-05,
1033
+ "loss": 3.2114,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.12698412698412698,
1038
+ "grad_norm": 20.69269371032715,
1039
+ "learning_rate": 2.9526736842105263e-05,
1040
+ "loss": 2.3942,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12786596119929453,
1045
+ "grad_norm": 20.517160415649414,
1046
+ "learning_rate": 2.899947368421053e-05,
1047
+ "loss": 3.2227,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12874779541446207,
1052
+ "grad_norm": 16.600399017333984,
1053
+ "learning_rate": 2.847221052631579e-05,
1054
+ "loss": 2.64,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.12962962962962962,
1059
+ "grad_norm": 18.788711547851562,
1060
+ "learning_rate": 2.7944947368421052e-05,
1061
+ "loss": 3.2185,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.13051146384479717,
1066
+ "grad_norm": 16.01982879638672,
1067
+ "learning_rate": 2.741768421052632e-05,
1068
+ "loss": 2.8431,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.13139329805996472,
1073
+ "grad_norm": 19.5235595703125,
1074
+ "learning_rate": 2.689042105263158e-05,
1075
+ "loss": 3.073,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.13227513227513227,
1080
+ "grad_norm": 20.980497360229492,
1081
+ "learning_rate": 2.636315789473684e-05,
1082
+ "loss": 3.1175,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.13227513227513227,
1087
+ "eval_loss": 1.6718300580978394,
1088
+ "eval_runtime": 24.3592,
1089
+ "eval_samples_per_second": 19.623,
1090
+ "eval_steps_per_second": 4.926,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.36624253370368e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null