prxy5606 commited on
Commit
f345b60
·
verified ·
1 Parent(s): 4fcde4d

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 sha256:3076753b6e7666587b9fead1906d2631f6f92d391db8fb0740bd83583e9bd8cc
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194645c2df88fc8864b4149ad9d16cee9269d65e05174a674fc1f257ad82bf57
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a389806fc6f7e038c440212c2897db4810ff70a51e9d63a49c924216e97b56f6
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c592ce96d02dc8b7fcbf2d7eaf266b902fc61977e139bd22e71da9c60e542e4
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f4df86ea1431cf80b5b92662734debae0bbc728638a37e9173151f6472d8dee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889b72d75cbad3f140ef557feb72852251d2151e74b7f8526d42c352b93432f6
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": 2.324611186981201,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4410143329658214,
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": 96.111,
732
  "eval_steps_per_second": 24.153,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3635041032732672.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.267702102661133,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6615214994487321,
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": 96.111,
732
  "eval_steps_per_second": 24.153,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4454244762954796,
737
+ "grad_norm": 4.73009729385376,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 9.7848,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4498346196251378,
744
+ "grad_norm": 5.109121799468994,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 9.8617,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.45424476295479604,
751
+ "grad_norm": 4.75127649307251,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 9.5113,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.45865490628445427,
758
+ "grad_norm": 4.4611496925354,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 9.7469,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.46306504961411243,
765
+ "grad_norm": 4.0637898445129395,
766
+ "learning_rate": 5e-05,
767
+ "loss": 9.5885,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.46747519294377066,
772
+ "grad_norm": 3.4445979595184326,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 9.6834,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4718853362734289,
779
+ "grad_norm": 3.125669002532959,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 9.5961,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4762954796030871,
786
+ "grad_norm": 3.1941781044006348,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 9.5903,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4807056229327453,
793
+ "grad_norm": 2.9857771396636963,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 9.8223,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.48511576626240355,
800
+ "grad_norm": 2.9888904094696045,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 9.4709,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.4895259095920617,
807
+ "grad_norm": 3.1896767616271973,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 9.6409,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.49393605292171994,
814
+ "grad_norm": 2.8134684562683105,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 9.2447,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.49834619625137816,
821
+ "grad_norm": 3.0218002796173096,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 9.4404,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5027563395810364,
828
+ "grad_norm": 2.7752158641815186,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 9.6074,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5071664829106945,
835
+ "grad_norm": 2.7840285301208496,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 9.6734,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5115766262403528,
842
+ "grad_norm": 2.7840182781219482,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 9.4232,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.515986769570011,
849
+ "grad_norm": 2.865178108215332,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.7842,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5203969128996693,
856
+ "grad_norm": 2.673846960067749,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 9.4169,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5248070562293274,
863
+ "grad_norm": 2.7128565311431885,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 9.6846,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5292171995589857,
870
+ "grad_norm": 2.795900821685791,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.6233,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5336273428886439,
877
+ "grad_norm": 2.681079387664795,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 9.4951,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.538037486218302,
884
+ "grad_norm": 3.0239830017089844,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 9.4322,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5424476295479603,
891
+ "grad_norm": 2.6298580169677734,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 9.6774,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5468577728776185,
898
+ "grad_norm": 2.6638214588165283,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 9.7512,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5512679162072768,
905
+ "grad_norm": 2.688530445098877,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 9.2839,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5556780595369349,
912
+ "grad_norm": 2.8218700885772705,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 9.8837,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5600882028665931,
919
+ "grad_norm": 2.641767740249634,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 9.5211,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5644983461962514,
926
+ "grad_norm": 2.596179485321045,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 9.482,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5689084895259096,
933
+ "grad_norm": 2.6632628440856934,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 9.6102,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5733186328555678,
940
+ "grad_norm": 2.468449354171753,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 9.4243,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.577728776185226,
947
+ "grad_norm": 2.6716885566711426,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 9.3426,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5821389195148843,
954
+ "grad_norm": 2.6062984466552734,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 9.7032,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5865490628445424,
961
+ "grad_norm": 2.587692975997925,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 9.5549,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5909592061742006,
968
+ "grad_norm": 2.8521335124969482,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.3508,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5953693495038589,
975
+ "grad_norm": 2.654881477355957,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 9.1112,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5997794928335171,
982
+ "grad_norm": 2.624953031539917,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.7822,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6041896361631753,
989
+ "grad_norm": 2.907388687133789,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 9.5028,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6085997794928335,
996
+ "grad_norm": 2.6536240577697754,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.2586,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6130099228224918,
1003
+ "grad_norm": 2.7955310344696045,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 9.477,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.61742006615215,
1010
+ "grad_norm": 2.800431966781616,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.6841,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6218302094818081,
1017
+ "grad_norm": 2.7314534187316895,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 9.8152,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6262403528114664,
1024
+ "grad_norm": 3.246215343475342,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 9.8627,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6306504961411246,
1031
+ "grad_norm": 3.4961540699005127,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.8221,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6350606394707828,
1038
+ "grad_norm": 3.982757806777954,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 9.5846,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.639470782800441,
1045
+ "grad_norm": 3.7322998046875,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.4127,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6438809261300992,
1052
+ "grad_norm": 4.33234167098999,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 9.4517,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6482910694597575,
1059
+ "grad_norm": 4.426651954650879,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 9.4071,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6527012127894156,
1066
+ "grad_norm": 4.737025737762451,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.3352,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6571113561190739,
1073
+ "grad_norm": 5.271717548370361,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.3794,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6615214994487321,
1080
+ "grad_norm": 8.03175163269043,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.1169,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6615214994487321,
1087
+ "eval_loss": 2.267702102661133,
1088
+ "eval_runtime": 3.9536,
1089
+ "eval_samples_per_second": 96.622,
1090
+ "eval_steps_per_second": 24.282,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5454912804618240.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null