cimol commited on
Commit
a90c1ea
·
verified ·
1 Parent(s): 97ebac6

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:cf37d49c64a0f95fb832ae56835eedb8ea06a95cd567166e151731e74308d32f
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273c87aeea5aaa2119cee560224422d5d01ac047c84b63610a10f7d9ecfa2e99
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07f8b64c22517ace8cf08767b8fc13d9baa971b98f7d700995a718634d04ab72
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43c7468052a26e8ab917c4e7e291b83fd6b43349eb6de66b13720b826df8a07
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30f53eaf615052daa5cbeb4c892eb232780cec06fd228ea59fb44e2effd1b369
3
  size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a93a35ccefb57bbd1840571779c785e63e9e9a7a5ecfa6fabdab69e518d966
3
  size 14180
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": 1.0246082544326782,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.1892147587511826,
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": 13.325,
732
  "eval_steps_per_second": 3.339,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9972198009490967,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.28382213812677387,
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": 13.325,
732
  "eval_steps_per_second": 3.339,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.19110690633869443,
737
+ "grad_norm": 0.8647973537445068,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 1.0912,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.19299905392620625,
744
+ "grad_norm": 0.7811133861541748,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 1.0621,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.19489120151371808,
751
+ "grad_norm": 0.6623404622077942,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 1.0165,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1967833491012299,
758
+ "grad_norm": 0.581591010093689,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 1.045,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.1986754966887417,
765
+ "grad_norm": 0.5817117094993591,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 1.001,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.20056764427625354,
772
+ "grad_norm": 0.6245970726013184,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 1.0591,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.20245979186376536,
779
+ "grad_norm": 0.636500358581543,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 1.0144,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2043519394512772,
786
+ "grad_norm": 0.6458229422569275,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 1.0251,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.20624408703878902,
793
+ "grad_norm": 0.6455327868461609,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 1.0541,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.20813623462630085,
800
+ "grad_norm": 0.6135246753692627,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 1.0339,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.21002838221381268,
807
+ "grad_norm": 0.5690136551856995,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 1.0123,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2119205298013245,
814
+ "grad_norm": 0.5633889436721802,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 0.9791,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.21381267738883633,
821
+ "grad_norm": 0.5846208930015564,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 1.0211,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.21570482497634816,
828
+ "grad_norm": 0.6093853116035461,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 1.0399,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.21759697256385999,
835
+ "grad_norm": 0.5736932754516602,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 0.9788,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2194891201513718,
842
+ "grad_norm": 0.606311559677124,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 1.016,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.22138126773888364,
849
+ "grad_norm": 0.5913999080657959,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 0.998,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.22327341532639547,
856
+ "grad_norm": 0.6164299249649048,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 1.0475,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2251655629139073,
863
+ "grad_norm": 0.599840521812439,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 1.0138,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.22705771050141912,
870
+ "grad_norm": 0.622111439704895,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 1.0192,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.22894985808893092,
877
+ "grad_norm": 0.6139826774597168,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 1.0056,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.23084200567644275,
884
+ "grad_norm": 0.6069412231445312,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 0.9934,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.23273415326395458,
891
+ "grad_norm": 0.7315534949302673,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 1.0084,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2346263008514664,
898
+ "grad_norm": 0.6033068299293518,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.9859,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.23651844843897823,
905
+ "grad_norm": 0.5995269417762756,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.9896,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.23841059602649006,
912
+ "grad_norm": 0.6208170056343079,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 1.0614,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2403027436140019,
919
+ "grad_norm": 0.6329922676086426,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.9696,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.24219489120151372,
926
+ "grad_norm": 0.6048612594604492,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.988,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.24408703878902555,
933
+ "grad_norm": 0.6055971384048462,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.9974,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.24597918637653737,
940
+ "grad_norm": 0.6034923791885376,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 1.0242,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.2478713339640492,
947
+ "grad_norm": 0.6091806292533875,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 1.0557,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.24976348155156103,
954
+ "grad_norm": 0.610476553440094,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 1.011,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.25165562913907286,
961
+ "grad_norm": 0.6271877884864807,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 1.001,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2535477767265847,
968
+ "grad_norm": 0.6196108460426331,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 1.02,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.2554399243140965,
975
+ "grad_norm": 0.617040753364563,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 1.0172,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.25733207190160834,
982
+ "grad_norm": 0.6176308393478394,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 1.0317,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.25922421948912017,
989
+ "grad_norm": 0.6212584376335144,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 1.0457,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.261116367076632,
996
+ "grad_norm": 0.625037670135498,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 1.0236,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.2630085146641438,
1003
+ "grad_norm": 0.6162792444229126,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.9993,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.26490066225165565,
1010
+ "grad_norm": 0.6135765910148621,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.9788,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.2667928098391675,
1017
+ "grad_norm": 0.6448305249214172,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.9969,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2686849574266793,
1024
+ "grad_norm": 0.6576701402664185,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.9495,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.27057710501419113,
1031
+ "grad_norm": 0.6453391909599304,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.9968,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.27246925260170296,
1038
+ "grad_norm": 0.6164287328720093,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.9762,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.27436140018921473,
1045
+ "grad_norm": 0.6524091958999634,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 1.0093,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.27625354777672656,
1052
+ "grad_norm": 0.659598171710968,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.9434,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2781456953642384,
1059
+ "grad_norm": 0.6762367486953735,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 1.068,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2800378429517502,
1066
+ "grad_norm": 0.6729089021682739,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 1.0132,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.28192999053926204,
1073
+ "grad_norm": 0.6752368211746216,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.9843,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.28382213812677387,
1080
+ "grad_norm": 0.6980991363525391,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.9744,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.28382213812677387,
1087
+ "eval_loss": 0.9972198009490967,
1088
+ "eval_runtime": 66.7731,
1089
+ "eval_samples_per_second": 13.329,
1090
+ "eval_steps_per_second": 3.34,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.262770368118784e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null