0x1202 commited on
Commit
89ee062
·
verified ·
1 Parent(s): 306ffdc

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 sha256:39dac2aa916041c4fd6010091bf180a55156a3a5861f8cccf177c44454099d46
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d5ba7972d532133dbc512e9365a160ad0462cedaa1bfc2dd3402094204ac6dd
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd02baf3ac2e0185a3be091e44ef2e69560e99ce0d216350eeac5de9955f4eb9
3
  size 1279641042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6cb060a7cb3fffda32f63d700e49fb5a77bed59dc9377b96907de22d17fc0ad
3
  size 1279641042
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51976e59481e843efd8941870fae785ef575a7aa0bbeceaf5008a9abf204dd11
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521dce847fe71e8e43e84640a586e6500653283b1892a35acb72488df9ee80e7
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": 0.8943002223968506,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.028328611898016998,
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": 12.185,
732
  "eval_steps_per_second": 6.093,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.37604737531904e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8521701693534851,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.042492917847025496,
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": 12.185,
732
  "eval_steps_per_second": 6.093,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.028611898016997168,
737
+ "grad_norm": 0.26681363582611084,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.7179,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.028895184135977338,
744
+ "grad_norm": 0.27887067198753357,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.7854,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.029178470254957508,
751
+ "grad_norm": 0.2766787111759186,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.7794,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.029461756373937678,
758
+ "grad_norm": 0.2650505304336548,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.7821,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.029745042492917848,
765
+ "grad_norm": 0.25711944699287415,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.7428,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.03002832861189802,
772
+ "grad_norm": 0.23184049129486084,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.7789,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03031161473087819,
779
+ "grad_norm": 0.23433373868465424,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.8222,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.03059490084985836,
786
+ "grad_norm": 0.23752881586551666,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.7548,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.030878186968838525,
793
+ "grad_norm": 0.23099955916404724,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.8607,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.031161473087818695,
800
+ "grad_norm": 0.2357034683227539,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.8765,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.031444759206798865,
807
+ "grad_norm": 0.2469700574874878,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.825,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03172804532577904,
814
+ "grad_norm": 0.24967269599437714,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.7931,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.032011331444759206,
821
+ "grad_norm": 0.25203588604927063,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.7875,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.03229461756373938,
828
+ "grad_norm": 0.25249430537223816,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.8702,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.032577903682719546,
835
+ "grad_norm": 0.2569659948348999,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.8997,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03286118980169972,
842
+ "grad_norm": 0.2416309267282486,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.7305,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.033144475920679886,
849
+ "grad_norm": 0.24729342758655548,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.8049,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03342776203966006,
856
+ "grad_norm": 0.27604395151138306,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 0.8112,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.033711048158640226,
863
+ "grad_norm": 0.27382591366767883,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.8149,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0339943342776204,
870
+ "grad_norm": 0.25334885716438293,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.8281,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03427762039660057,
877
+ "grad_norm": 0.2882319390773773,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.8037,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03456090651558073,
884
+ "grad_norm": 0.28409236669540405,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 0.8182,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03484419263456091,
891
+ "grad_norm": 0.2688352167606354,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 0.7252,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03512747875354107,
898
+ "grad_norm": 0.3232026994228363,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.8757,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03541076487252125,
905
+ "grad_norm": 0.3008348345756531,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.8151,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.035694050991501414,
912
+ "grad_norm": 0.2845551073551178,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.8039,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03597733711048159,
919
+ "grad_norm": 0.30033618211746216,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.8236,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.036260623229461754,
926
+ "grad_norm": 0.2865908145904541,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 0.8584,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03654390934844193,
933
+ "grad_norm": 0.3274208903312683,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.8048,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.036827195467422094,
940
+ "grad_norm": 0.32286253571510315,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 0.8669,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.03711048158640227,
947
+ "grad_norm": 0.32492363452911377,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.8294,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.037393767705382434,
954
+ "grad_norm": 0.3788565993309021,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.9411,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03767705382436261,
961
+ "grad_norm": 0.3922273516654968,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.896,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.037960339943342775,
968
+ "grad_norm": 0.4324563443660736,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.8272,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03824362606232295,
975
+ "grad_norm": 0.4802010655403137,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 0.7869,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.038526912181303115,
982
+ "grad_norm": 0.5401066541671753,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 0.8878,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03881019830028329,
989
+ "grad_norm": 0.49897003173828125,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 0.9156,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.039093484419263455,
996
+ "grad_norm": 0.5094231963157654,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 0.8411,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03937677053824363,
1003
+ "grad_norm": 0.5654172897338867,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 0.9716,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.039660056657223795,
1010
+ "grad_norm": 0.5526919960975647,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 0.9828,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.03994334277620397,
1017
+ "grad_norm": 0.5752049088478088,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.9976,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.040226628895184136,
1024
+ "grad_norm": 0.6576734781265259,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.9673,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04050991501416431,
1031
+ "grad_norm": 0.7551366090774536,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.9781,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.040793201133144476,
1038
+ "grad_norm": 0.7085397839546204,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 1.0065,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04107648725212465,
1045
+ "grad_norm": 0.7727219462394714,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.8517,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.041359773371104816,
1052
+ "grad_norm": 0.8478469848632812,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.9225,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04164305949008498,
1059
+ "grad_norm": 0.9258629083633423,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.9349,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.041926345609065156,
1066
+ "grad_norm": 1.0141416788101196,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.8708,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04220963172804532,
1073
+ "grad_norm": 1.2329179048538208,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 0.855,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.042492917847025496,
1080
+ "grad_norm": 2.4406769275665283,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.868,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.042492917847025496,
1087
+ "eval_loss": 0.8521701693534851,
1088
+ "eval_runtime": 487.8912,
1089
+ "eval_samples_per_second": 12.187,
1090
+ "eval_steps_per_second": 6.094,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.06575327248384e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null