lesso commited on
Commit
9e453a9
·
verified ·
1 Parent(s): 86fd529

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 sha256:957a4335205b6293dabccea2cc8744e323101fe3128e892012c6398f3141b97e
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:683756f504cb1fa56e928da67b61b8a067287de838c0e5294aa2b3d09c226f9f
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e5da87183a0813f8e9b5e9df69cd1747666430fbc5bee02b42d7cba5a82ab8
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1361b8fb02e76795dc7c2852e80fd81a9313bc37d9c0bcaaf6193cc858ea6330
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa43bf4d3f1fc37c97372564e0bcfe641d92f3fc335e8df4b873fb1923b99d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03322aaa92c9c0fda603f7c49b1553d5d556d38758107e73bb1f644e67b85d3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3388093bd4c4d331382d0016aa94fd7868af3fa4dd50305298d21879ce809e93
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16a9a2b8856e8f64eb7194578c6fcbc8625033d1caa318cc7b80ad824088880
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4849724769592285,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07418397626112759,
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": 23.064,
732
  "eval_steps_per_second": 5.766,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8272600262246400.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4480029344558716,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.11127596439169139,
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": 23.064,
732
  "eval_steps_per_second": 5.766,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.07492581602373888,
737
+ "grad_norm": 0.4530433416366577,
738
+ "learning_rate": 5.219384210526315e-05,
739
+ "loss": 1.514,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.07566765578635015,
744
+ "grad_norm": 0.4724753201007843,
745
+ "learning_rate": 5.1666631578947374e-05,
746
+ "loss": 1.4021,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.07640949554896143,
751
+ "grad_norm": 0.47871169447898865,
752
+ "learning_rate": 5.113942105263158e-05,
753
+ "loss": 1.5589,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0771513353115727,
758
+ "grad_norm": 0.45524775981903076,
759
+ "learning_rate": 5.061221052631579e-05,
760
+ "loss": 1.3405,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.07789317507418397,
765
+ "grad_norm": 0.4814228415489197,
766
+ "learning_rate": 5.0085e-05,
767
+ "loss": 1.4676,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.07863501483679525,
772
+ "grad_norm": 0.4835189878940582,
773
+ "learning_rate": 4.955778947368421e-05,
774
+ "loss": 1.4522,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.07937685459940653,
779
+ "grad_norm": 0.4658392071723938,
780
+ "learning_rate": 4.903057894736842e-05,
781
+ "loss": 1.3801,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08011869436201781,
786
+ "grad_norm": 0.47330623865127563,
787
+ "learning_rate": 4.850336842105263e-05,
788
+ "loss": 1.4066,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08086053412462908,
793
+ "grad_norm": 0.46363088488578796,
794
+ "learning_rate": 4.797615789473684e-05,
795
+ "loss": 1.3805,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08160237388724036,
800
+ "grad_norm": 0.4817906618118286,
801
+ "learning_rate": 4.744894736842105e-05,
802
+ "loss": 1.4796,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08234421364985163,
807
+ "grad_norm": 0.4742972254753113,
808
+ "learning_rate": 4.692173684210526e-05,
809
+ "loss": 1.4028,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0830860534124629,
814
+ "grad_norm": 0.4543997049331665,
815
+ "learning_rate": 4.639452631578947e-05,
816
+ "loss": 1.3328,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.08382789317507418,
821
+ "grad_norm": 0.4936276376247406,
822
+ "learning_rate": 4.586731578947368e-05,
823
+ "loss": 1.5478,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.08456973293768547,
828
+ "grad_norm": 0.48722100257873535,
829
+ "learning_rate": 4.5340105263157894e-05,
830
+ "loss": 1.3693,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.08531157270029674,
835
+ "grad_norm": 0.4936085641384125,
836
+ "learning_rate": 4.48128947368421e-05,
837
+ "loss": 1.4177,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.08605341246290801,
842
+ "grad_norm": 0.5257976055145264,
843
+ "learning_rate": 4.428568421052632e-05,
844
+ "loss": 1.4234,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.08679525222551929,
849
+ "grad_norm": 0.5145537853240967,
850
+ "learning_rate": 4.3758473684210525e-05,
851
+ "loss": 1.4445,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.08753709198813056,
856
+ "grad_norm": 0.5173904895782471,
857
+ "learning_rate": 4.323126315789474e-05,
858
+ "loss": 1.3109,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.08827893175074183,
863
+ "grad_norm": 0.5231949090957642,
864
+ "learning_rate": 4.270405263157895e-05,
865
+ "loss": 1.4202,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.08902077151335312,
870
+ "grad_norm": 0.5481486320495605,
871
+ "learning_rate": 4.217684210526316e-05,
872
+ "loss": 1.6027,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0897626112759644,
877
+ "grad_norm": 0.5185007452964783,
878
+ "learning_rate": 4.164963157894737e-05,
879
+ "loss": 1.4227,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09050445103857567,
884
+ "grad_norm": 0.5656704306602478,
885
+ "learning_rate": 4.112242105263158e-05,
886
+ "loss": 1.7125,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09124629080118694,
891
+ "grad_norm": 0.5431631207466125,
892
+ "learning_rate": 4.059521052631579e-05,
893
+ "loss": 1.5132,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09198813056379822,
898
+ "grad_norm": 0.5578521490097046,
899
+ "learning_rate": 4.0068e-05,
900
+ "loss": 1.4467,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09272997032640949,
905
+ "grad_norm": 0.535007119178772,
906
+ "learning_rate": 3.954078947368421e-05,
907
+ "loss": 1.2726,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.09347181008902077,
912
+ "grad_norm": 0.5330731272697449,
913
+ "learning_rate": 3.901357894736842e-05,
914
+ "loss": 1.4208,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.09421364985163205,
919
+ "grad_norm": 0.567901611328125,
920
+ "learning_rate": 3.848636842105263e-05,
921
+ "loss": 1.3921,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.09495548961424333,
926
+ "grad_norm": 0.5680362582206726,
927
+ "learning_rate": 3.795915789473684e-05,
928
+ "loss": 1.3536,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0956973293768546,
933
+ "grad_norm": 0.5580912828445435,
934
+ "learning_rate": 3.743194736842105e-05,
935
+ "loss": 1.3825,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.09643916913946587,
940
+ "grad_norm": 0.5955318808555603,
941
+ "learning_rate": 3.690473684210526e-05,
942
+ "loss": 1.5347,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.09718100890207715,
947
+ "grad_norm": 0.5580132007598877,
948
+ "learning_rate": 3.6377526315789475e-05,
949
+ "loss": 1.4045,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.09792284866468842,
954
+ "grad_norm": 0.6038758158683777,
955
+ "learning_rate": 3.585031578947368e-05,
956
+ "loss": 1.4749,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.09866468842729971,
961
+ "grad_norm": 0.5841488242149353,
962
+ "learning_rate": 3.532310526315789e-05,
963
+ "loss": 1.4079,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.09940652818991098,
968
+ "grad_norm": 0.5694416165351868,
969
+ "learning_rate": 3.4795894736842106e-05,
970
+ "loss": 1.483,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10014836795252226,
975
+ "grad_norm": 0.6277908682823181,
976
+ "learning_rate": 3.4268684210526314e-05,
977
+ "loss": 1.42,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.10089020771513353,
982
+ "grad_norm": 0.6425288319587708,
983
+ "learning_rate": 3.374147368421052e-05,
984
+ "loss": 1.5528,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1016320474777448,
989
+ "grad_norm": 0.5806187391281128,
990
+ "learning_rate": 3.321426315789473e-05,
991
+ "loss": 1.5093,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10237388724035608,
996
+ "grad_norm": 0.6284953355789185,
997
+ "learning_rate": 3.2687052631578946e-05,
998
+ "loss": 1.3592,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.10311572700296735,
1003
+ "grad_norm": 0.6375062465667725,
1004
+ "learning_rate": 3.2159842105263154e-05,
1005
+ "loss": 1.281,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.10385756676557864,
1010
+ "grad_norm": 0.5946156978607178,
1011
+ "learning_rate": 3.163263157894737e-05,
1012
+ "loss": 1.2957,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.10459940652818991,
1017
+ "grad_norm": 0.6250626444816589,
1018
+ "learning_rate": 3.110542105263158e-05,
1019
+ "loss": 1.455,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.10534124629080119,
1024
+ "grad_norm": 0.6201031804084778,
1025
+ "learning_rate": 3.057821052631579e-05,
1026
+ "loss": 1.5049,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.10608308605341246,
1031
+ "grad_norm": 0.6878780126571655,
1032
+ "learning_rate": 3.0050999999999997e-05,
1033
+ "loss": 1.4236,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.10682492581602374,
1038
+ "grad_norm": 0.6680196523666382,
1039
+ "learning_rate": 2.9523789473684206e-05,
1040
+ "loss": 1.4347,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.10756676557863501,
1045
+ "grad_norm": 0.7300444841384888,
1046
+ "learning_rate": 2.899657894736842e-05,
1047
+ "loss": 1.7655,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1083086053412463,
1052
+ "grad_norm": 0.7111066579818726,
1053
+ "learning_rate": 2.846936842105263e-05,
1054
+ "loss": 1.6347,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.10905044510385757,
1059
+ "grad_norm": 0.663420557975769,
1060
+ "learning_rate": 2.794215789473684e-05,
1061
+ "loss": 1.345,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.10979228486646884,
1066
+ "grad_norm": 0.7585017681121826,
1067
+ "learning_rate": 2.7414947368421056e-05,
1068
+ "loss": 1.4643,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11053412462908012,
1073
+ "grad_norm": 0.7578019499778748,
1074
+ "learning_rate": 2.6887736842105264e-05,
1075
+ "loss": 1.6194,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.11127596439169139,
1080
+ "grad_norm": 0.8730563521385193,
1081
+ "learning_rate": 2.6360526315789472e-05,
1082
+ "loss": 1.6065,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.11127596439169139,
1087
+ "eval_loss": 1.4480029344558716,
1088
+ "eval_runtime": 24.6337,
1089
+ "eval_samples_per_second": 23.058,
1090
+ "eval_steps_per_second": 5.764,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.24089003933696e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null