prxy5606 commited on
Commit
b5a155c
·
verified ·
1 Parent(s): e512cdd

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 sha256:6c02f43948baa7300d44b379fd05ae9b14888e3800a93e4952c808f66f6c952c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe99c1411b555823bd8d59e8712b08770ba19bc431d74b29a65292d226da8df
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211c33bd398e2d6dcaaa5fca542d24841a917b67242613e3c471d56eb96bf0f6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c8d284e65a4f7a1156b22bac72b776355a0aeb45637ba07021909ebfeda346
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7855901026ba8ab6d1521353f05eee2268ebb8f12d09dbde41ae6814a091ce96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c11a1f1ee913b21942271dce07373bc7f87d9f447455e803c22963e9a972d11
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": 0.8603187203407288,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02157962883038412,
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": 11.513,
732
  "eval_steps_per_second": 2.879,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5350288546267136e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8280358910560608,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.032369443245576175,
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": 11.513,
732
  "eval_steps_per_second": 2.879,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02179542511868796,
737
+ "grad_norm": 1.1089110374450684,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1093,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0220112214069918,
744
+ "grad_norm": 1.106166124343872,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0278,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.022227017695295642,
751
+ "grad_norm": 1.1203964948654175,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.0022,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.022442813983599482,
758
+ "grad_norm": 0.7232309579849243,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.092,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.022658610271903322,
765
+ "grad_norm": 0.7233337163925171,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9655,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.022874406560207165,
772
+ "grad_norm": 0.8149043917655945,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.139,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.023090202848511005,
779
+ "grad_norm": 0.7843315601348877,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0493,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.02330599913681485,
786
+ "grad_norm": 0.7392372488975525,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.904,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.02352179542511869,
793
+ "grad_norm": 0.8629333972930908,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.0813,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.023737591713422528,
800
+ "grad_norm": 0.8519977331161499,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9022,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02395338800172637,
807
+ "grad_norm": 0.8973418474197388,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.0171,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.02416918429003021,
814
+ "grad_norm": 1.1018964052200317,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8564,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.02438498057833405,
821
+ "grad_norm": 0.9234106540679932,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0673,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.024600776866637895,
828
+ "grad_norm": 0.7985190153121948,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8832,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.024816573154941735,
835
+ "grad_norm": 0.8727723360061646,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9246,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.025032369443245578,
842
+ "grad_norm": 0.7970044612884521,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8867,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.025248165731549418,
849
+ "grad_norm": 0.8688997626304626,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9637,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.025463962019853258,
856
+ "grad_norm": 0.9784425497055054,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9145,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0256797583081571,
863
+ "grad_norm": 0.8824965953826904,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.9074,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02589555459646094,
870
+ "grad_norm": 0.8492420315742493,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7582,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.02611135088476478,
877
+ "grad_norm": 0.8725212216377258,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.7837,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.026327147173068624,
884
+ "grad_norm": 0.8608531355857849,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7997,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.026542943461372464,
891
+ "grad_norm": 0.8319887518882751,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8176,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.026758739749676307,
898
+ "grad_norm": 0.9366618990898132,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6593,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.026974536037980147,
905
+ "grad_norm": 0.852107048034668,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7941,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.027190332326283987,
912
+ "grad_norm": 0.9025298953056335,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.8114,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02740612861458783,
919
+ "grad_norm": 0.9413577318191528,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7405,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.02762192490289167,
926
+ "grad_norm": 0.9036081433296204,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.7128,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.02783772119119551,
933
+ "grad_norm": 0.8255434036254883,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.6682,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.028053517479499353,
940
+ "grad_norm": 0.9848359823226929,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.7559,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.028269313767803193,
947
+ "grad_norm": 0.9902356863021851,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7821,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.028485110056107037,
954
+ "grad_norm": 1.054074764251709,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.8453,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.028700906344410877,
961
+ "grad_norm": 1.061506986618042,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7477,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.028916702632714716,
968
+ "grad_norm": 1.0569781064987183,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.8079,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.02913249892101856,
975
+ "grad_norm": 1.1609337329864502,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7927,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0293482952093224,
982
+ "grad_norm": 1.181168794631958,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7241,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.02956409149762624,
989
+ "grad_norm": 1.619036316871643,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.776,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.029779887785930083,
996
+ "grad_norm": 1.331146001815796,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.8912,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.029995684074233923,
1003
+ "grad_norm": 1.4182469844818115,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.8669,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.030211480362537766,
1010
+ "grad_norm": 1.5601855516433716,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.8814,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.030427276650841606,
1017
+ "grad_norm": 1.6656060218811035,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.7781,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.030643072939145446,
1024
+ "grad_norm": 1.5459718704223633,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7903,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03085886922744929,
1031
+ "grad_norm": 1.5884653329849243,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7738,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03107466551575313,
1038
+ "grad_norm": 1.749447226524353,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.6743,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03129046180405697,
1045
+ "grad_norm": 1.6413766145706177,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.7247,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.03150625809236081,
1052
+ "grad_norm": 2.0422089099884033,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.7707,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.03172205438066465,
1059
+ "grad_norm": 2.1430230140686035,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.8553,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.031937850668968495,
1066
+ "grad_norm": 2.3078126907348633,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.7766,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03215364695727233,
1073
+ "grad_norm": 2.4988832473754883,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.6228,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.032369443245576175,
1080
+ "grad_norm": 2.9421193599700928,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.7389,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.032369443245576175,
1087
+ "eval_loss": 0.8280358910560608,
1088
+ "eval_runtime": 678.9937,
1089
+ "eval_samples_per_second": 11.495,
1090
+ "eval_steps_per_second": 2.875,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3098879176081408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null