aleegis12 commited on
Commit
b1f4ba2
·
verified ·
1 Parent(s): ba33b68

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 sha256:9736e9446949f070e7bdd205b40dddcacd84cbecabb7c5d68ac31fd2bbb0b956
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d0f9508e2eb0bb6da47513d220f51bf1c4ca044fc58ddfc489141962a866d2
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9722bbccc6b150758f53daf055e44f92b6f9e51360066ff3233ec0dd20973931
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c87f5d5f355f78b43c5fa0cbb993ac07bff2265e84c78e4a70b986eabd12927
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5626b69f1cd30d77bd7934b9603932dc4a1e662721976df1d379751ed45cbd42
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42de3c13dadf43b359641345682623294fd260fe55983392e0977ad7979e19b0
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": 11.92177677154541,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.027756574838664907,
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": 168.303,
732
  "eval_steps_per_second": 42.076,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 527880683520.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.920873641967773,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04163486225799736,
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": 168.303,
732
  "eval_steps_per_second": 42.076,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02803414058705156,
737
+ "grad_norm": 0.07624490559101105,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.9241,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.028311706335438207,
744
+ "grad_norm": 0.06985257565975189,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.924,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.028589272083824856,
751
+ "grad_norm": 0.055254239588975906,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.9234,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.028866837832211504,
758
+ "grad_norm": 0.033972207456827164,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.9238,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.029144403580598156,
765
+ "grad_norm": 0.05893569067120552,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.9238,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.029421969328984804,
772
+ "grad_norm": 0.041556794196367264,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.9218,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.029699535077371452,
779
+ "grad_norm": 0.036440733820199966,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.9225,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0299771008257581,
786
+ "grad_norm": 0.043610457330942154,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.9214,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.030254666574144752,
793
+ "grad_norm": 0.03520379588007927,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.922,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0305322323225314,
800
+ "grad_norm": 0.02231968566775322,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.9225,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03080979807091805,
807
+ "grad_norm": 0.0349528044462204,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.9213,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.031087363819304697,
814
+ "grad_norm": 0.02526078186929226,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.9219,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.031364929567691345,
821
+ "grad_norm": 0.0429261140525341,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.9206,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.031642495316078,
828
+ "grad_norm": 0.036386579275131226,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.9224,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03192006106446465,
835
+ "grad_norm": 0.03579165041446686,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.9218,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03219762681285129,
842
+ "grad_norm": 0.022514235228300095,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.9217,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.032475192561237945,
849
+ "grad_norm": 0.031543485820293427,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.9216,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.03275275830962459,
856
+ "grad_norm": 0.04401085898280144,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.9206,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03303032405801124,
863
+ "grad_norm": 0.03169631212949753,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.9226,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03330788980639789,
870
+ "grad_norm": 0.020640989765524864,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.9208,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03358545555478454,
877
+ "grad_norm": 0.035152822732925415,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.9207,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03386302130317119,
884
+ "grad_norm": 0.04229821264743805,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.9196,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.034140587051557834,
891
+ "grad_norm": 0.05334702506661415,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.9209,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.034418152799944486,
898
+ "grad_norm": 0.04720913991332054,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.9205,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.03469571854833114,
905
+ "grad_norm": 0.029698573052883148,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.9213,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.03497328429671778,
912
+ "grad_norm": 0.0408032201230526,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.9204,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.035250850045104434,
919
+ "grad_norm": 0.0362643264234066,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.9216,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.035528415793491086,
926
+ "grad_norm": 0.02858690544962883,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.9236,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03580598154187773,
933
+ "grad_norm": 0.01690261997282505,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.9218,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.03608354729026438,
940
+ "grad_norm": 0.03252992406487465,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.921,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.03636111303865103,
947
+ "grad_norm": 0.030182329937815666,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.92,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03663867878703768,
954
+ "grad_norm": 0.04098094627261162,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.9204,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03691624453542433,
961
+ "grad_norm": 0.04568958282470703,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.9209,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.037193810283810975,
968
+ "grad_norm": 0.050598856061697006,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.9208,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03747137603219763,
975
+ "grad_norm": 0.027388080954551697,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.9199,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03774894178058428,
982
+ "grad_norm": 0.0414414256811142,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.9216,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.038026507528970924,
989
+ "grad_norm": 0.03170596808195114,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.9211,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.038304073277357575,
996
+ "grad_norm": 0.03230173885822296,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.9204,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03858163902574422,
1003
+ "grad_norm": 0.04046839848160744,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.9216,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03885920477413087,
1010
+ "grad_norm": 0.035419054329395294,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.9233,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.039136770522517524,
1017
+ "grad_norm": 0.03469659388065338,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.9205,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.03941433627090417,
1024
+ "grad_norm": 0.039468683302402496,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.9215,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.03969190201929082,
1031
+ "grad_norm": 0.049550049006938934,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.9207,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03996946776767747,
1038
+ "grad_norm": 0.03535732254385948,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.923,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04024703351606412,
1045
+ "grad_norm": 0.04517639800906181,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.9213,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04052459926445077,
1052
+ "grad_norm": 0.05632007122039795,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.9196,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04080216501283741,
1059
+ "grad_norm": 0.03823922574520111,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.9217,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.041079730761224065,
1066
+ "grad_norm": 0.044311534613370895,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.9196,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.041357296509610716,
1073
+ "grad_norm": 0.03511509671807289,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.9209,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04163486225799736,
1080
+ "grad_norm": 0.07786613702774048,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.9181,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04163486225799736,
1087
+ "eval_loss": 11.920873641967773,
1088
+ "eval_runtime": 36.0311,
1089
+ "eval_samples_per_second": 168.41,
1090
+ "eval_steps_per_second": 42.103,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 791821025280.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null