aleegis09 commited on
Commit
11635f1
·
verified ·
1 Parent(s): fa8645d

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:a1cc974703299d9a1ff44a74bfbf73a6ca7ae7432737f82619f54ce58000a0e8
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bbd2320b9313a7a51d2de5f045c38c45db0829f9f23c4e52760ed66dc331491
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b89a80c350906aa4af1850965f371804bf8efbb03503da7a52e036050a4517a
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e74196a2c57819f601008e66179eca6e00c5e37bb109780d4126db81e724d4
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58720c8ffca23c6e4ab0d21fbd0d13748844d080389d369274ca9565db0d0697
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27485a345ed21440ea95c8af200ed1b100c49ece961cf6ea7393c6d855612ccf
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": 2.315321683883667,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01223091976516634,
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": 34.07,
732
  "eval_steps_per_second": 8.518,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.7214473068544e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1350297927856445,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.01834637964774951,
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": 34.07,
732
  "eval_steps_per_second": 8.518,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.012353228962818003,
737
+ "grad_norm": 5.587851524353027,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.4973,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.012475538160469667,
744
+ "grad_norm": 5.332846164703369,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.8147,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01259784735812133,
751
+ "grad_norm": 5.407177925109863,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.9376,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.012720156555772993,
758
+ "grad_norm": 4.151082992553711,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.5244,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.012842465753424657,
765
+ "grad_norm": 3.116997718811035,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.7323,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01296477495107632,
772
+ "grad_norm": 2.44041109085083,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.9142,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.013087084148727984,
779
+ "grad_norm": 2.5864756107330322,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.2847,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.013209393346379647,
786
+ "grad_norm": 2.0883891582489014,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.7091,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01333170254403131,
793
+ "grad_norm": 2.077030658721924,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.5959,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.013454011741682974,
800
+ "grad_norm": 2.788433074951172,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.5773,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.013576320939334637,
807
+ "grad_norm": 2.4121241569519043,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.5224,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0136986301369863,
814
+ "grad_norm": 2.208285093307495,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.2972,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.013820939334637964,
821
+ "grad_norm": 2.3244783878326416,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.0765,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.013943248532289627,
828
+ "grad_norm": 2.68003249168396,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.4875,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01406555772994129,
835
+ "grad_norm": 2.173006296157837,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.2476,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.014187866927592954,
842
+ "grad_norm": 2.1117324829101562,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.0798,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.014310176125244618,
849
+ "grad_norm": 2.0847764015197754,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.0772,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.014432485322896281,
856
+ "grad_norm": 2.0450143814086914,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.1538,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.014554794520547944,
863
+ "grad_norm": 2.3623125553131104,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.3527,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.014677103718199608,
870
+ "grad_norm": 2.167203426361084,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.7808,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.014799412915851271,
877
+ "grad_norm": 2.0760998725891113,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.0063,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.014921722113502935,
884
+ "grad_norm": 2.3804619312286377,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.3383,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.015044031311154598,
891
+ "grad_norm": 2.3460516929626465,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.9512,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.015166340508806261,
898
+ "grad_norm": 3.0433735847473145,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.9906,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.015288649706457925,
905
+ "grad_norm": 2.38430118560791,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.9432,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.015410958904109588,
912
+ "grad_norm": 2.429680109024048,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.3886,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.015533268101761252,
919
+ "grad_norm": 2.5903520584106445,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.3882,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.015655577299412915,
926
+ "grad_norm": 2.351475954055786,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.7961,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01577788649706458,
933
+ "grad_norm": 2.4007294178009033,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.2394,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.015900195694716242,
940
+ "grad_norm": 2.457118272781372,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.0242,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.016022504892367905,
947
+ "grad_norm": 2.424525737762451,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.2026,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.01614481409001957,
954
+ "grad_norm": 2.3996245861053467,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.8746,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.016267123287671232,
961
+ "grad_norm": 2.3708181381225586,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.0587,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.016389432485322895,
968
+ "grad_norm": 2.509343385696411,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.8606,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01651174168297456,
975
+ "grad_norm": 2.5185110569000244,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.027,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.016634050880626222,
982
+ "grad_norm": 2.6653518676757812,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.1171,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.016756360078277886,
989
+ "grad_norm": 3.025047540664673,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.1092,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.01687866927592955,
996
+ "grad_norm": 2.6442272663116455,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.7792,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.017000978473581212,
1003
+ "grad_norm": 2.822582483291626,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.1223,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.017123287671232876,
1010
+ "grad_norm": 2.905893325805664,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.8898,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01724559686888454,
1017
+ "grad_norm": 2.480517864227295,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.7505,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.017367906066536203,
1024
+ "grad_norm": 2.3645825386047363,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.8915,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.017490215264187866,
1031
+ "grad_norm": 2.314419746398926,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.7321,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01761252446183953,
1038
+ "grad_norm": 2.4668900966644287,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.0315,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.017734833659491193,
1045
+ "grad_norm": 2.9239959716796875,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.9162,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.017857142857142856,
1052
+ "grad_norm": 3.3394274711608887,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.3803,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.01797945205479452,
1059
+ "grad_norm": 2.9278645515441895,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.0392,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.018101761252446183,
1066
+ "grad_norm": 3.171457052230835,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.1635,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.018224070450097846,
1073
+ "grad_norm": 3.2454960346221924,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.3391,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.01834637964774951,
1080
+ "grad_norm": 4.471919059753418,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.6814,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.01834637964774951,
1087
+ "eval_loss": 2.1350297927856445,
1088
+ "eval_runtime": 404.0918,
1089
+ "eval_samples_per_second": 34.079,
1090
+ "eval_steps_per_second": 8.52,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.0821709602816e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null