aleegis09 commited on
Commit
c0ea00b
·
verified ·
1 Parent(s): aff72fc

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 sha256:88f5119a0b1fdf730bf3475c9bf9b763bc9a063c803bfaa3132ca6c6e6e12433
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04df309e749ee44215bef6419b7c36f2cca2a61f808f2587d414471b983e07d
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac7fa69c8c997923a4320e7df2d1eda6a08f64b88485dadd8bcb8730fafc2b07
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfc183e633605690aef8e3d58f2da430c4ba600e35897349f4df113e670a829
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df68f8ab799596ea79a64250841b406cc0e9a64627795b1426fd5bf1245ccaca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9932ac03207aa68e2cb1694c6bda3ff62aaffc71d1ce038e56dbd5b437ef11ce
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b7849512fe484686da254a5341cb189aab98442eb57d50cdc4ca5e034ecc91
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77fecceef02880a4146c504aef986e50a2aa79b7ebef5c03c12015958eb0af66
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9384918212890625,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.8691588785046729,
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": 32.27,
732
  "eval_steps_per_second": 8.247,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.491696391015629e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8860944509506226,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.803738317757009,
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": 32.27,
732
  "eval_steps_per_second": 8.247,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.8878504672897196,
737
+ "grad_norm": 0.8476997017860413,
738
+ "learning_rate": 3.415395052896487e-05,
739
+ "loss": 1.8944,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.9065420560747663,
744
+ "grad_norm": 0.7590591311454773,
745
+ "learning_rate": 3.31708121725597e-05,
746
+ "loss": 1.9007,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.925233644859813,
751
+ "grad_norm": 0.8914473652839661,
752
+ "learning_rate": 3.219495820872265e-05,
753
+ "loss": 1.8704,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.9439252336448598,
758
+ "grad_norm": 0.9904480576515198,
759
+ "learning_rate": 3.122681102880352e-05,
760
+ "loss": 1.9588,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.9626168224299065,
765
+ "grad_norm": 1.0886353254318237,
766
+ "learning_rate": 3.0266789688326186e-05,
767
+ "loss": 2.0084,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.9813084112149533,
772
+ "grad_norm": 0.9867513179779053,
773
+ "learning_rate": 2.9315309725603596e-05,
774
+ "loss": 1.9471,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 2.0,
779
+ "grad_norm": 1.565618634223938,
780
+ "learning_rate": 2.8372782981874963e-05,
781
+ "loss": 2.8595,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 2.0186915887850465,
786
+ "grad_norm": 0.750761866569519,
787
+ "learning_rate": 2.7439617423043145e-05,
788
+ "loss": 1.7939,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 2.0373831775700935,
793
+ "grad_norm": 0.7188526391983032,
794
+ "learning_rate": 2.6516216963089698e-05,
795
+ "loss": 1.948,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 2.05607476635514,
800
+ "grad_norm": 0.6620720028877258,
801
+ "learning_rate": 2.5602981289243578e-05,
802
+ "loss": 2.0243,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 2.074766355140187,
807
+ "grad_norm": 0.7385666966438293,
808
+ "learning_rate": 2.470030568897938e-05,
809
+ "loss": 2.0093,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 2.0934579439252334,
814
+ "grad_norm": 0.6927978992462158,
815
+ "learning_rate": 2.3808580878919946e-05,
816
+ "loss": 2.0141,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 2.1121495327102804,
821
+ "grad_norm": 0.8042175769805908,
822
+ "learning_rate": 2.2928192835717644e-05,
823
+ "loss": 2.1099,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 2.130841121495327,
828
+ "grad_norm": 0.8042687177658081,
829
+ "learning_rate": 2.205952262898704e-05,
830
+ "loss": 1.9512,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 2.149532710280374,
835
+ "grad_norm": 0.6975992918014526,
836
+ "learning_rate": 2.120294625636171e-05,
837
+ "loss": 1.9388,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 2.1682242990654204,
842
+ "grad_norm": 0.730394721031189,
843
+ "learning_rate": 2.0358834480746365e-05,
844
+ "loss": 1.8403,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 2.1869158878504673,
849
+ "grad_norm": 0.8232110738754272,
850
+ "learning_rate": 1.9527552669834798e-05,
851
+ "loss": 1.7969,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 2.205607476635514,
856
+ "grad_norm": 0.853557288646698,
857
+ "learning_rate": 1.8709460637963123e-05,
858
+ "loss": 1.8426,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 2.2242990654205608,
863
+ "grad_norm": 0.9900144338607788,
864
+ "learning_rate": 1.790491249036672e-05,
865
+ "loss": 1.8337,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 2.2429906542056073,
870
+ "grad_norm": 1.1342283487319946,
871
+ "learning_rate": 1.711425646990838e-05,
872
+ "loss": 1.8367,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.2616822429906542,
877
+ "grad_norm": 0.7156676650047302,
878
+ "learning_rate": 1.6337834806343783e-05,
879
+ "loss": 1.8456,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.2803738317757007,
884
+ "grad_norm": 0.779453694820404,
885
+ "learning_rate": 1.557598356819e-05,
886
+ "loss": 1.9779,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.2990654205607477,
891
+ "grad_norm": 0.8929774165153503,
892
+ "learning_rate": 1.4829032517260489e-05,
893
+ "loss": 1.9999,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.317757009345794,
898
+ "grad_norm": 0.8750218152999878,
899
+ "learning_rate": 1.4097304965930158e-05,
900
+ "loss": 2.0485,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.336448598130841,
905
+ "grad_norm": 0.7915140986442566,
906
+ "learning_rate": 1.3381117637191886e-05,
907
+ "loss": 2.146,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.3551401869158877,
912
+ "grad_norm": 0.7732717990875244,
913
+ "learning_rate": 1.268078052756531e-05,
914
+ "loss": 2.1118,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.3738317757009346,
919
+ "grad_norm": 0.7107844948768616,
920
+ "learning_rate": 1.199659677291709e-05,
921
+ "loss": 1.8324,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.392523364485981,
926
+ "grad_norm": 0.6969010829925537,
927
+ "learning_rate": 1.132886251725061e-05,
928
+ "loss": 1.8862,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.411214953271028,
933
+ "grad_norm": 0.7186504602432251,
934
+ "learning_rate": 1.0677866784522317e-05,
935
+ "loss": 1.8288,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.4299065420560746,
940
+ "grad_norm": 0.7537363171577454,
941
+ "learning_rate": 1.004389135353972e-05,
942
+ "loss": 1.8198,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.4485981308411215,
947
+ "grad_norm": 0.9697016477584839,
948
+ "learning_rate": 9.427210635995482e-06,
949
+ "loss": 1.8064,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.467289719626168,
954
+ "grad_norm": 1.0445103645324707,
955
+ "learning_rate": 8.828091557690289e-06,
956
+ "loss": 1.7067,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.485981308411215,
961
+ "grad_norm": 1.219523310661316,
962
+ "learning_rate": 8.246793442995954e-06,
963
+ "loss": 1.7276,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.5046728971962615,
968
+ "grad_norm": 0.6436533331871033,
969
+ "learning_rate": 7.683567902608729e-06,
970
+ "loss": 1.8227,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.5233644859813085,
975
+ "grad_norm": 0.6645519733428955,
976
+ "learning_rate": 7.138658724641417e-06,
977
+ "loss": 1.8911,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.542056074766355,
982
+ "grad_norm": 0.7499832510948181,
983
+ "learning_rate": 6.6123017691014645e-06,
984
+ "loss": 2.0121,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.560747663551402,
989
+ "grad_norm": 0.8042947053909302,
990
+ "learning_rate": 6.104724865800665e-06,
991
+ "loss": 2.0352,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.5794392523364484,
996
+ "grad_norm": 0.8424281477928162,
997
+ "learning_rate": 5.616147715740611e-06,
998
+ "loss": 2.0103,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.5981308411214954,
1003
+ "grad_norm": 0.8324230313301086,
1004
+ "learning_rate": 5.1467817960167975e-06,
1005
+ "loss": 2.0734,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.616822429906542,
1010
+ "grad_norm": 0.7521181106567383,
1011
+ "learning_rate": 4.696830268282204e-06,
1012
+ "loss": 2.0144,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.635514018691589,
1017
+ "grad_norm": 0.7921295762062073,
1018
+ "learning_rate": 4.266487890810256e-06,
1019
+ "loss": 1.8382,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.6542056074766354,
1024
+ "grad_norm": 0.6855363845825195,
1025
+ "learning_rate": 3.855940934195146e-06,
1026
+ "loss": 1.8084,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.6728971962616823,
1031
+ "grad_norm": 0.7162411212921143,
1032
+ "learning_rate": 3.465367100725908e-06,
1033
+ "loss": 1.7642,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.691588785046729,
1038
+ "grad_norm": 0.7779765129089355,
1039
+ "learning_rate": 3.0949354474692937e-06,
1040
+ "loss": 1.8011,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.710280373831776,
1045
+ "grad_norm": 0.8959972262382507,
1046
+ "learning_rate": 2.7448063130946224e-06,
1047
+ "loss": 1.7792,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.7289719626168223,
1052
+ "grad_norm": 1.1299974918365479,
1053
+ "learning_rate": 2.4151312484723465e-06,
1054
+ "loss": 1.8124,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.7476635514018692,
1059
+ "grad_norm": 0.6512258648872375,
1060
+ "learning_rate": 2.106052951076365e-06,
1061
+ "loss": 1.8297,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.7663551401869158,
1066
+ "grad_norm": 0.6378995776176453,
1067
+ "learning_rate": 1.8177052032184283e-06,
1068
+ "loss": 1.8168,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.7850467289719627,
1073
+ "grad_norm": 0.6217026114463806,
1074
+ "learning_rate": 1.5502128141414495e-06,
1075
+ "loss": 1.8971,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.803738317757009,
1080
+ "grad_norm": 0.6214033365249634,
1081
+ "learning_rate": 1.303691565996712e-06,
1082
+ "loss": 1.9555,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.803738317757009,
1087
+ "eval_loss": 1.8860944509506226,
1088
+ "eval_runtime": 2.8551,
1089
+ "eval_samples_per_second": 31.522,
1090
+ "eval_steps_per_second": 8.056,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.164884237798605e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null