cimol commited on
Commit
0a2fd5c
·
verified ·
1 Parent(s): f65fa6b

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 sha256:10a3533be242ebc1363d55012020e2135bee318c5f27cdaed9da88608150be63
3
  size 1006723888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649c4a1a484c0159c613b8a489ed1d96c5992ebf8e4020825625ed9942df0f23
3
  size 1006723888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3a6ccd3836ad80f292f4b372c5071bab34222d5b6a3f89fa1b15ff613f89de3
3
  size 511971028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ef3099ee7dc2d7c7f4dee9d1d12cb55421ed5cf2b20b0662afa2e9af0dfd8c
3
  size 511971028
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e984b22ffd9c9db00cdbbf36103bc75d2a396f49e3d47ee221214e9dfd316882
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d44daf951237b37f6b647168b8b9ee79566f155f3731201afa11fd1088bf26
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": 0.04219882935285568,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.2461059190031152,
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": 9.364,
732
  "eval_steps_per_second": 2.358,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.1309446943041126e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.016963951289653778,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.8691588785046729,
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": 9.364,
732
  "eval_steps_per_second": 2.358,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.2585669781931463,
737
+ "grad_norm": 4.209986686706543,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 0.2022,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.2710280373831775,
744
+ "grad_norm": 3.724384069442749,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 0.2676,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.2834890965732086,
751
+ "grad_norm": 6.198829650878906,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 0.2478,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.2959501557632398,
758
+ "grad_norm": 4.84001350402832,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 0.2186,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.308411214953271,
765
+ "grad_norm": 2.831515073776245,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 0.1662,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.320872274143302,
772
+ "grad_norm": 4.106805324554443,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 0.2088,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.3333333333333333,
779
+ "grad_norm": 1.9497915506362915,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 0.0801,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.3457943925233644,
786
+ "grad_norm": 2.852299451828003,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 0.0541,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.3582554517133956,
793
+ "grad_norm": 1.9880298376083374,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 0.0406,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.3707165109034267,
800
+ "grad_norm": 2.8185806274414062,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 0.0996,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.3831775700934579,
807
+ "grad_norm": 1.9250342845916748,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 0.0878,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.395638629283489,
814
+ "grad_norm": 3.665525197982788,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 0.0756,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.4080996884735202,
821
+ "grad_norm": 1.3103280067443848,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 0.0257,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.4205607476635513,
828
+ "grad_norm": 3.999124050140381,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 0.0277,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.4330218068535825,
835
+ "grad_norm": 15.71084976196289,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 0.1723,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.4454828660436136,
842
+ "grad_norm": 1.0466094017028809,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 0.0547,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.4579439252336448,
849
+ "grad_norm": 2.3232150077819824,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 0.048,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.470404984423676,
856
+ "grad_norm": 1.440258502960205,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 0.034,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.482866043613707,
863
+ "grad_norm": 7.503004550933838,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 0.1539,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.4953271028037383,
870
+ "grad_norm": 4.813387393951416,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 0.076,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.5077881619937694,
877
+ "grad_norm": 8.021973609924316,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 0.1207,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.5202492211838006,
884
+ "grad_norm": 8.493134498596191,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 0.0913,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.5327102803738317,
891
+ "grad_norm": 5.900277614593506,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 0.2079,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.5451713395638629,
898
+ "grad_norm": 1.6940159797668457,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.05,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.557632398753894,
905
+ "grad_norm": 3.267876386642456,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.1378,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.5700934579439252,
912
+ "grad_norm": 4.5409369468688965,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 0.088,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.5825545171339563,
919
+ "grad_norm": 2.896395683288574,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.0932,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.5950155763239875,
926
+ "grad_norm": 2.323807716369629,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.0578,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.6074766355140186,
933
+ "grad_norm": 2.2950172424316406,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.0846,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.6199376947040498,
940
+ "grad_norm": 1.400589942932129,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 0.0351,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.632398753894081,
947
+ "grad_norm": 1.0706186294555664,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 0.0217,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.644859813084112,
954
+ "grad_norm": 1.207822561264038,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 0.0356,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.6573208722741433,
961
+ "grad_norm": 4.169908046722412,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 0.043,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.6697819314641744,
968
+ "grad_norm": 0.5930849313735962,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 0.0231,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.6822429906542056,
975
+ "grad_norm": 2.6127288341522217,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 0.0584,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.6947040498442367,
982
+ "grad_norm": 1.3352339267730713,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 0.0258,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.7071651090342679,
989
+ "grad_norm": 1.4083367586135864,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 0.0518,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.719626168224299,
996
+ "grad_norm": 7.688618183135986,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 0.0756,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.7320872274143302,
1003
+ "grad_norm": 5.132578372955322,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.1183,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.7445482866043613,
1010
+ "grad_norm": 10.968769073486328,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.0797,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.7570093457943925,
1017
+ "grad_norm": 5.747490406036377,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.1183,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.7694704049844237,
1024
+ "grad_norm": 2.5073037147521973,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.1126,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.7819314641744548,
1031
+ "grad_norm": 1.7272340059280396,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.0602,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.794392523364486,
1038
+ "grad_norm": 3.843600034713745,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.0486,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.8068535825545171,
1045
+ "grad_norm": 6.914474964141846,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 0.1039,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.8193146417445483,
1052
+ "grad_norm": 3.943265676498413,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.0893,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.8317757009345794,
1059
+ "grad_norm": 3.6975629329681396,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 0.097,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.8442367601246106,
1066
+ "grad_norm": 2.8245303630828857,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 0.0356,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.8566978193146417,
1073
+ "grad_norm": 1.264923095703125,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.0206,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.8691588785046729,
1080
+ "grad_norm": 0.46808677911758423,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.0111,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.8691588785046729,
1087
+ "eval_loss": 0.016963951289653778,
1088
+ "eval_runtime": 14.422,
1089
+ "eval_samples_per_second": 9.361,
1090
+ "eval_steps_per_second": 2.358,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.1977505487742566e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null