prxy5606 commited on
Commit
2013b35
·
verified ·
1 Parent(s): f1bfc56

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 sha256:972aa9ffe87080f27071031d0e4d226dffe8f3ed6fbff6743ae8a659ec8ab968
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9695c6011ef2d733edeff317c7800eba07957f621130536bd45ac885f1ee6399
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17f24c0296a81f84cf38b6c10994df2d8d2d5bea05eb21e5ea6ae4aeae9b1d22
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4a92164e67cc9a402ad0acfa4ce45e4dab9660d20d1a60ced8a2c61fb845ae
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e394433f831db42905c4a4dcb8562be06e854e5b31c169d95b91d32afffc57
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d040aa64bd15982084c375e522ed7b97bbeef61ca232e2736bba0354cbbce35b
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": 1.5486623048782349,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.015228426395939,
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": 21.633,
732
  "eval_steps_per_second": 5.473,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.2084252647424e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5060570240020752,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.5228426395939088,
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": 21.633,
732
  "eval_steps_per_second": 5.473,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.0253807106598984,
737
+ "grad_norm": 0.5553914308547974,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.5885,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.0355329949238579,
744
+ "grad_norm": 0.5437448620796204,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.52,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.0456852791878173,
751
+ "grad_norm": 0.5706773996353149,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.5359,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.0558375634517767,
758
+ "grad_norm": 0.5832688808441162,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.5736,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.0659898477157361,
765
+ "grad_norm": 0.584896445274353,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.3852,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.0761421319796955,
772
+ "grad_norm": 0.6052612066268921,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.4096,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.0862944162436547,
779
+ "grad_norm": 0.6644023060798645,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.5471,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.0964467005076142,
786
+ "grad_norm": 0.7001641392707825,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.5418,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.1065989847715736,
793
+ "grad_norm": 0.6971859931945801,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.3906,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.116751269035533,
800
+ "grad_norm": 0.7651525735855103,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.4862,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.1269035532994924,
807
+ "grad_norm": 0.8193091750144958,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.551,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.1370558375634519,
814
+ "grad_norm": 0.8337458372116089,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.3594,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.1472081218274113,
821
+ "grad_norm": 0.821225106716156,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.2333,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.1573604060913705,
828
+ "grad_norm": 0.8680731058120728,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.3171,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.16751269035533,
835
+ "grad_norm": 0.8808449506759644,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3503,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.1776649746192893,
842
+ "grad_norm": 0.9254382848739624,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.4595,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.1878172588832487,
849
+ "grad_norm": 1.2700564861297607,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.2803,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.1979695431472082,
856
+ "grad_norm": 0.9289053082466125,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2169,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.2081218274111676,
863
+ "grad_norm": 1.0314911603927612,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3335,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.218274111675127,
870
+ "grad_norm": 1.0336929559707642,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.221,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.2284263959390862,
877
+ "grad_norm": 1.1959046125411987,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.1413,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.2385786802030456,
884
+ "grad_norm": 1.5569109916687012,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.1702,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.248730964467005,
891
+ "grad_norm": 1.3973491191864014,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.3704,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.2588832487309645,
898
+ "grad_norm": 1.7734311819076538,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.5551,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.2690355329949239,
905
+ "grad_norm": 1.2938789129257202,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.6164,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.2791878172588833,
912
+ "grad_norm": 0.9389830231666565,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.4727,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.2893401015228427,
919
+ "grad_norm": 0.8181756734848022,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.517,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.299492385786802,
926
+ "grad_norm": 0.7993819713592529,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.5517,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.3096446700507614,
933
+ "grad_norm": 0.7154996395111084,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.4461,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.3197969543147208,
940
+ "grad_norm": 0.7990055680274963,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.5857,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.3299492385786802,
947
+ "grad_norm": 0.7646247148513794,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.419,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.3401015228426396,
954
+ "grad_norm": 0.7962736487388611,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.4192,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.350253807106599,
961
+ "grad_norm": 0.8432332873344421,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.5356,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.3604060913705585,
968
+ "grad_norm": 0.7631216049194336,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.3423,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.3705583756345177,
975
+ "grad_norm": 0.8354220986366272,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.3963,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.380710659898477,
982
+ "grad_norm": 0.8573411107063293,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.461,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.3908629441624365,
989
+ "grad_norm": 0.8249084949493408,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.4064,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.401015228426396,
996
+ "grad_norm": 0.906618595123291,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.3833,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.4111675126903553,
1003
+ "grad_norm": 0.9852612018585205,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3802,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.4213197969543148,
1010
+ "grad_norm": 0.9798620939254761,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.2791,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.4314720812182742,
1017
+ "grad_norm": 0.9310597777366638,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2705,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.4416243654822334,
1024
+ "grad_norm": 0.9294157028198242,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1918,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.451776649746193,
1031
+ "grad_norm": 1.1194959878921509,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.3822,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.4619289340101522,
1038
+ "grad_norm": 1.119828701019287,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.1602,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.4720812182741116,
1045
+ "grad_norm": 1.1303843259811401,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1408,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.482233502538071,
1052
+ "grad_norm": 1.4049675464630127,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2422,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.4923857868020305,
1059
+ "grad_norm": 0.9562484622001648,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.3199,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.50253807106599,
1066
+ "grad_norm": 0.7429844737052917,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.5144,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.512690355329949,
1073
+ "grad_norm": 0.8964042663574219,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.6035,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.5228426395939088,
1080
+ "grad_norm": 0.9342640042304993,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6336,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.5228426395939088,
1087
+ "eval_loss": 1.5060570240020752,
1088
+ "eval_runtime": 7.6664,
1089
+ "eval_samples_per_second": 21.653,
1090
+ "eval_steps_per_second": 5.478,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.311342997032141e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null