cimol commited on
Commit
84b88bf
·
verified ·
1 Parent(s): 3f4e996

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:ecb65fb22b4ad8294881d115b026ec15a182d2251770333fa66eb6a645fd0255
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:996dd68a4f9d98b4bfdd8b160f28f1b343cfbfd128d3bfd8ebd6183266dd0983
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5228f4e811619b300360b9ff84a0396ebd4c43ebe5f1293a6cbb6d69ea3d5e0
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70940ff4298fdc7482cb72317cbb19520ea53e8a0c1dc7135e2a717439dcd0be
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:124e6a2b1036d494445acb350d7c1f36c5b3ac83c2b5bf8e0ccf8dd0d1eb6eda
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eae1fee9cbbcb119191ddbba5932dbdc5d42caf736e9c8b33d8314c1b3e4626
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": 10.268265724182129,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.033291718684977115,
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": 472.115,
732
  "eval_steps_per_second": 118.052,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 21856834289664.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.262248039245605,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.049937578027465665,
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": 472.115,
732
  "eval_steps_per_second": 118.052,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.03362463587182688,
737
+ "grad_norm": 0.9653616547584534,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 41.1458,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.033957553058676655,
744
+ "grad_norm": 0.7120814323425293,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 41.1225,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.03429047024552642,
751
+ "grad_norm": 0.7734652161598206,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 41.0911,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.034623387432376196,
758
+ "grad_norm": 0.8058983683586121,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 41.1292,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.03495630461922597,
765
+ "grad_norm": 0.7713319659233093,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 41.0599,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.035289221806075736,
772
+ "grad_norm": 0.668918251991272,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 41.0562,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.03562213899292551,
779
+ "grad_norm": 0.6046922206878662,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 41.117,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.035955056179775284,
786
+ "grad_norm": 0.615520179271698,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 41.0757,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.03628797336662505,
793
+ "grad_norm": 0.5750020742416382,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 41.0803,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.036620890553474825,
800
+ "grad_norm": 0.5789351463317871,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 41.0764,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03695380774032459,
807
+ "grad_norm": 0.495280385017395,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 41.0853,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.037286724927174365,
814
+ "grad_norm": 0.607459306716919,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 41.0856,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03761964211402414,
821
+ "grad_norm": 0.5672668218612671,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 41.0905,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.037952559300873906,
828
+ "grad_norm": 0.4067647159099579,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 41.0658,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.03828547648772368,
835
+ "grad_norm": 0.4445897042751312,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 41.0757,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03861839367457345,
842
+ "grad_norm": 0.49568378925323486,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 41.0665,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03895131086142322,
849
+ "grad_norm": 0.465396523475647,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 41.0955,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.039284228048272994,
856
+ "grad_norm": 0.5162220597267151,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 41.0538,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03961714523512276,
863
+ "grad_norm": 0.5179729461669922,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 41.0789,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.039950062421972535,
870
+ "grad_norm": 0.3789314329624176,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 41.0536,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.04028297960882231,
877
+ "grad_norm": 0.5198574066162109,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 41.0854,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.040615896795672075,
884
+ "grad_norm": 0.7691577672958374,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 41.0657,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.04094881398252185,
891
+ "grad_norm": 0.4329979419708252,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 41.0486,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.041281731169371616,
898
+ "grad_norm": 0.4044908285140991,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 41.0679,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.04161464835622139,
905
+ "grad_norm": 0.47338008880615234,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 41.0595,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.041947565543071164,
912
+ "grad_norm": 0.40356704592704773,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 41.0371,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.04228048272992093,
919
+ "grad_norm": 0.46097269654273987,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 41.0382,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.042613399916770704,
926
+ "grad_norm": 0.5834002494812012,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 41.0317,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.04294631710362047,
933
+ "grad_norm": 0.4960689842700958,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 41.0702,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.043279234290470245,
940
+ "grad_norm": 0.5823487043380737,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 41.0304,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.04361215147732002,
947
+ "grad_norm": 0.5733532905578613,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 41.0478,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.043945068664169785,
954
+ "grad_norm": 0.4891790449619293,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 41.071,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.04427798585101956,
961
+ "grad_norm": 0.623074471950531,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 41.0059,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.04461090303786933,
968
+ "grad_norm": 0.46600988507270813,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 41.0281,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.0449438202247191,
975
+ "grad_norm": 0.6511916518211365,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 41.0053,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.045276737411568874,
982
+ "grad_norm": 0.5773023962974548,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 41.0085,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.04560965459841864,
989
+ "grad_norm": 0.629172146320343,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 41.0248,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.045942571785268414,
996
+ "grad_norm": 0.5709488391876221,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 41.0355,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.04627548897211819,
1003
+ "grad_norm": 0.6980351209640503,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 41.0265,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.046608406158967955,
1010
+ "grad_norm": 0.6503186225891113,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 41.0168,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04694132334581773,
1017
+ "grad_norm": 0.6362338066101074,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 41.0438,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.047274240532667496,
1024
+ "grad_norm": 0.6247021555900574,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 41.0625,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.04760715771951727,
1031
+ "grad_norm": 0.5643784999847412,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 41.0386,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.04794007490636704,
1038
+ "grad_norm": 0.657160222530365,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 41.0016,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04827299209321681,
1045
+ "grad_norm": 0.6254180669784546,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 41.045,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.048605909280066584,
1052
+ "grad_norm": 0.7680043578147888,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 41.0091,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04893882646691636,
1059
+ "grad_norm": 0.7392878532409668,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 40.9964,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.049271743653766124,
1066
+ "grad_norm": 0.7142351269721985,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 40.9972,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0496046608406159,
1073
+ "grad_norm": 0.6166180968284607,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 41.006,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.049937578027465665,
1080
+ "grad_norm": 0.9231532216072083,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 41.0886,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.049937578027465665,
1087
+ "eval_loss": 10.262248039245605,
1088
+ "eval_runtime": 10.7326,
1089
+ "eval_samples_per_second": 471.367,
1090
+ "eval_steps_per_second": 117.865,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 32812102582272.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null