aleegis09 commited on
Commit
c506352
·
verified ·
1 Parent(s): ad08af0

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 sha256:6fae39ffb5b0a1a502efb5e207bccfbcc376021d7d722293f243a605419c7256
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8211d34f068fe5bacc494093c71dbaa2f2910ad1c9ee62b57057973c5eb9a49e
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deb096ff1453121666ccb0504c566d423b13f3149a33a274709f0a03054bb32a
3
  size 958299770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac11423d35c6427edc4268b43a6600fea96adcc45fc2f110068337d775b189ad
3
  size 958299770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7775b4d3090903c1d37189d4ecd739f0557f31166a5d2cc87d5ac92178e3d636
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce11cc0e3bcd16fdcabb42f80abd2aa789455dede355235b6884914bd2fa5fb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.43801045417785645,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.003919954528527469,
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": 17.902,
732
  "eval_steps_per_second": 8.951,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.089192756163379e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.43333882093429565,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.005879931792791204,
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": 17.902,
732
  "eval_steps_per_second": 8.951,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0039591540738127436,
737
+ "grad_norm": 0.10259481519460678,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.4114,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.003998353619098018,
744
+ "grad_norm": 0.1059873104095459,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.4391,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.004037553164383294,
751
+ "grad_norm": 0.10306891053915024,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.4589,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.004076752709668568,
758
+ "grad_norm": 0.09604241698980331,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.4462,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.004115952254953843,
765
+ "grad_norm": 0.1092570349574089,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.4617,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.004155151800239117,
772
+ "grad_norm": 0.10691061615943909,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.5161,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.004194351345524392,
779
+ "grad_norm": 0.10758673399686813,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.6515,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0042335508908096665,
786
+ "grad_norm": 0.10809138417243958,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.4775,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.004272750436094941,
793
+ "grad_norm": 0.10625655204057693,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.534,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.004311949981380216,
800
+ "grad_norm": 0.11111942678689957,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.5024,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.004351149526665491,
807
+ "grad_norm": 0.10645933449268341,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.459,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.004390349071950766,
814
+ "grad_norm": 0.11491873860359192,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.6275,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.00442954861723604,
821
+ "grad_norm": 0.11639122664928436,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.5297,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.004468748162521315,
828
+ "grad_norm": 0.12297159433364868,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.4937,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.004507947707806589,
835
+ "grad_norm": 0.11242052167654037,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.4692,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.004547147253091864,
842
+ "grad_norm": 0.1251300573348999,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.5091,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0045863467983771385,
849
+ "grad_norm": 0.12641409039497375,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.539,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.004625546343662413,
856
+ "grad_norm": 0.1277226060628891,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.5769,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0046647458889476886,
863
+ "grad_norm": 0.12659917771816254,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.3997,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.004703945434232963,
870
+ "grad_norm": 0.1406412273645401,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.4552,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.004743144979518238,
877
+ "grad_norm": 0.1345863938331604,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.4727,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.004782344524803512,
884
+ "grad_norm": 0.13614259660243988,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.4239,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.004821544070088787,
891
+ "grad_norm": 0.13695776462554932,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.3773,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.0048607436153740614,
898
+ "grad_norm": 0.14491674304008484,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.39,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.004899943160659336,
905
+ "grad_norm": 0.14301298558712006,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.3741,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0049391427059446115,
912
+ "grad_norm": 0.14596934616565704,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.4123,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.004978342251229886,
919
+ "grad_norm": 0.12781678140163422,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.3334,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.005017541796515161,
926
+ "grad_norm": 0.1531793177127838,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.3903,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.005056741341800435,
933
+ "grad_norm": 0.1685943901538849,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.514,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.00509594088708571,
940
+ "grad_norm": 0.15798459947109222,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.4733,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.005135140432370984,
947
+ "grad_norm": 0.16000813245773315,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.4515,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.005174339977656259,
954
+ "grad_norm": 0.15483549237251282,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.3787,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0052135395229415335,
961
+ "grad_norm": 0.18001963198184967,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.4393,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.005252739068226809,
968
+ "grad_norm": 0.1790371835231781,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.3586,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0052919386135120835,
975
+ "grad_norm": 0.1700044572353363,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.4281,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.005331138158797358,
982
+ "grad_norm": 0.1701839715242386,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.2861,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.005370337704082633,
989
+ "grad_norm": 0.17230786383152008,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.3672,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.005409537249367907,
996
+ "grad_norm": 0.19381862878799438,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.4293,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.005448736794653182,
1003
+ "grad_norm": 0.17442116141319275,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.356,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.005487936339938456,
1010
+ "grad_norm": 0.18775367736816406,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.3817,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.005527135885223731,
1017
+ "grad_norm": 0.20612426102161407,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.433,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.005566335430509006,
1024
+ "grad_norm": 0.19330035150051117,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.4553,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.005605534975794281,
1031
+ "grad_norm": 0.19368550181388855,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.4106,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.005644734521079556,
1038
+ "grad_norm": 0.21053840219974518,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.3231,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.00568393406636483,
1045
+ "grad_norm": 0.2086849808692932,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.368,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.005723133611650105,
1052
+ "grad_norm": 0.20636354386806488,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.3489,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.005762333156935379,
1059
+ "grad_norm": 0.23584240674972534,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.4045,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.005801532702220654,
1066
+ "grad_norm": 0.2612581253051758,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.39,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.005840732247505929,
1073
+ "grad_norm": 0.2916366159915924,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.4611,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.005879931792791204,
1080
+ "grad_norm": 0.429953396320343,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.3297,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.005879931792791204,
1087
+ "eval_loss": 0.43333882093429565,
1088
+ "eval_runtime": 2400.7314,
1089
+ "eval_samples_per_second": 17.897,
1090
+ "eval_steps_per_second": 8.949,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9.162243306002842e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null