risolmayo commited on
Commit
a46c1bc
·
verified ·
1 Parent(s): a1d2b96

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 sha256:95b0e7b6b0ba2885b13c039a90915556d4b51e60ca7e5dc3f6b059ee85242eac
3
  size 231448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a571ec42f478840e69a67e0dd57624be90cdb5537d36b5d0435bee9bd0ba6f
3
  size 231448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a36bf48bd442b1a64b5cf5cc5b05e6ddc451c123987b662a73e7e2f108da6cf
3
  size 254576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13e10c114dcdf5078d47df86fc93f161df9df140dc0304ec9d3915845b663e1
3
  size 254576
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:468d494961f53b711ad3ae8a88e774c2ebda6dade2564468490d56dbb05c3da9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe54e70e100855887817feed6e22abcd92d3fe3725f3f4cd181c36f9fcb30070
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26348e70deb5f7d6cee52f5eb084c0e6829440001a3c6d0128b93cd074af8c2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 10.155071258544922,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0061278264599546545,
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": 277.803,
732
  "eval_steps_per_second": 69.458,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 21814683107328.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.137996673583984,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.00919173968993198,
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": 277.803,
732
  "eval_steps_per_second": 69.458,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0061891047245542005,
737
+ "grad_norm": 0.3536835014820099,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 10.1634,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006250382989153747,
744
+ "grad_norm": 0.476319819688797,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 10.1683,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006311661253753294,
751
+ "grad_norm": 0.6223771572113037,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 10.173,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.00637293951835284,
758
+ "grad_norm": 0.5387416481971741,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 10.18,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.006434217782952387,
765
+ "grad_norm": 0.5463670492172241,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 10.1896,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.006495496047551934,
772
+ "grad_norm": 0.35652950406074524,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 10.1564,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.00655677431215148,
779
+ "grad_norm": 0.3654034435749054,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 10.1534,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.006618052576751026,
786
+ "grad_norm": 0.38840317726135254,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 10.145,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006679330841350573,
793
+ "grad_norm": 0.3647133708000183,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 10.1413,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006740609105950119,
800
+ "grad_norm": 0.3147537410259247,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 10.1414,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.006801887370549666,
807
+ "grad_norm": 0.35884329676628113,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 10.148,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.006863165635149213,
814
+ "grad_norm": 0.37276944518089294,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 10.1512,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.006924443899748759,
821
+ "grad_norm": 0.34950560331344604,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 10.1473,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0069857221643483056,
828
+ "grad_norm": 0.4139955937862396,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 10.1526,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007047000428947852,
835
+ "grad_norm": 0.3620222508907318,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 10.1458,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007108278693547398,
842
+ "grad_norm": 0.34052902460098267,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 10.1478,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007169556958146945,
849
+ "grad_norm": 0.2788581848144531,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 10.1468,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007230835222746492,
856
+ "grad_norm": 0.30485856533050537,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 10.1488,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007292113487346039,
863
+ "grad_norm": 0.3234477937221527,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 10.1477,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.007353391751945585,
870
+ "grad_norm": 0.2603645622730255,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 10.1497,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0074146700165451315,
877
+ "grad_norm": 0.27819761633872986,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 10.1482,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007475948281144678,
884
+ "grad_norm": 0.27645042538642883,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 10.1457,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.007537226545744224,
891
+ "grad_norm": 0.3347417712211609,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 10.1412,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.007598504810343771,
898
+ "grad_norm": 0.32757794857025146,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 10.1332,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.007659783074943318,
905
+ "grad_norm": 0.37621769309043884,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 10.1316,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007721061339542864,
912
+ "grad_norm": 0.3853381872177124,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 10.129,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.007782339604142411,
919
+ "grad_norm": 0.39091774821281433,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 10.1291,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.007843617868741957,
926
+ "grad_norm": 0.38270658254623413,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 10.1289,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.007904896133341504,
933
+ "grad_norm": 0.420430451631546,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 10.1289,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.007966174397941051,
940
+ "grad_norm": 0.39466023445129395,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 10.14,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008027452662540596,
947
+ "grad_norm": 0.31119757890701294,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 10.1597,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008088730927140143,
954
+ "grad_norm": 0.34917810559272766,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 10.1619,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.00815000919173969,
961
+ "grad_norm": 0.24947816133499146,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 10.1444,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.008211287456339237,
968
+ "grad_norm": 0.32924318313598633,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 10.151,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008272565720938783,
975
+ "grad_norm": 0.2837226986885071,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 10.1519,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.00833384398553833,
982
+ "grad_norm": 0.20223724842071533,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 10.1404,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008395122250137875,
989
+ "grad_norm": 0.2176276445388794,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 10.1289,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.008456400514737422,
996
+ "grad_norm": 0.26074570417404175,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 10.1237,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.008517678779336969,
1003
+ "grad_norm": 0.28516310453414917,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 10.1245,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.008578957043936516,
1010
+ "grad_norm": 0.2946498692035675,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 10.1295,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.008640235308536063,
1017
+ "grad_norm": 0.36294224858283997,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 10.1264,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.00870151357313561,
1024
+ "grad_norm": 0.4097118079662323,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 10.1203,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.008762791837735154,
1031
+ "grad_norm": 0.4316818118095398,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 10.1269,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.008824070102334701,
1038
+ "grad_norm": 0.37467852234840393,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 10.1282,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.008885348366934248,
1045
+ "grad_norm": 0.2884649932384491,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 10.1353,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.008946626631533795,
1052
+ "grad_norm": 0.21601779758930206,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 10.1452,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009007904896133342,
1059
+ "grad_norm": 0.4934738278388977,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 10.1427,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009069183160732889,
1066
+ "grad_norm": 0.4053356349468231,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 10.1476,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.009130461425332435,
1073
+ "grad_norm": 0.5170806646347046,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 10.1461,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.00919173968993198,
1080
+ "grad_norm": 0.46501147747039795,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 10.1341,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.00919173968993198,
1087
+ "eval_loss": 10.137996673583984,
1088
+ "eval_runtime": 99.3132,
1089
+ "eval_samples_per_second": 276.751,
1090
+ "eval_steps_per_second": 69.195,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 32722024660992.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null