cimol commited on
Commit
94a9eba
·
verified ·
1 Parent(s): 30f0586

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:f1f82c651e066acfb676ce6604f1839c34b21b6847201e0fbed494a9f5722380
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dca720a9cbb8104757049d88a2920f5195dcff857e59d79733a80c3381fbe2
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:308424276f75cd102ec7188162807dcec81712d6a4ecaded4c3206c5ead2e25d
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c3bb0c70c1eef45e29ef9608f17dbdc8c3ea0f5db2d3d14839bc3d34c35ea2
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b99ec50d36f8b66e69a4933a4d39b2d9159cc8543cf6adefe72e1e6765f73f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54143f3da491c42a3417dc7ef69ceeab159d8c1e743e951e84083bfc733f3d88
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": 0.8196816444396973,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.8281573498964804,
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": 6.325,
732
  "eval_steps_per_second": 1.581,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.373606698567598e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8175904750823975,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.2422360248447206,
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": 6.325,
732
  "eval_steps_per_second": 1.581,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.8364389233954451,
737
+ "grad_norm": 0.3054017126560211,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 0.7171,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.84472049689441,
744
+ "grad_norm": 0.2971940040588379,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 0.7747,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.8530020703933747,
751
+ "grad_norm": 0.28216373920440674,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 0.7735,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.8612836438923396,
758
+ "grad_norm": 0.3302093744277954,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 0.7433,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8695652173913043,
765
+ "grad_norm": 0.39043137431144714,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 0.8474,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.8778467908902692,
772
+ "grad_norm": 0.3387686312198639,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 0.7744,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.8861283643892339,
779
+ "grad_norm": 0.3744807243347168,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 0.844,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.8944099378881988,
786
+ "grad_norm": 0.3628387749195099,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 0.7452,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.9026915113871635,
793
+ "grad_norm": 0.34833672642707825,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 0.727,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.9109730848861284,
800
+ "grad_norm": 0.38752731680870056,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 0.7226,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.9192546583850931,
807
+ "grad_norm": 0.4460507035255432,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 0.783,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.927536231884058,
814
+ "grad_norm": 0.4155882000923157,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 0.7733,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.9358178053830227,
821
+ "grad_norm": 0.42916351556777954,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 0.8132,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.9440993788819876,
828
+ "grad_norm": 0.40436169505119324,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 0.7043,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.9523809523809523,
835
+ "grad_norm": 0.5273613333702087,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 0.8491,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.9606625258799172,
842
+ "grad_norm": 0.5109385848045349,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 0.7627,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.968944099378882,
849
+ "grad_norm": 0.6382851600646973,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 0.7009,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.9772256728778468,
856
+ "grad_norm": 0.6231806874275208,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 1.0499,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.9855072463768116,
863
+ "grad_norm": 0.8011189103126526,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 0.9278,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.9937888198757764,
870
+ "grad_norm": 0.8758801221847534,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 1.0722,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.0020703933747412,
877
+ "grad_norm": 0.6602959632873535,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 0.8362,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.010351966873706,
884
+ "grad_norm": 0.22043457627296448,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 0.6068,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.0186335403726707,
891
+ "grad_norm": 0.2249661386013031,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 0.6206,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.0269151138716357,
898
+ "grad_norm": 0.23550471663475037,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.7048,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.0351966873706004,
905
+ "grad_norm": 0.2546531856060028,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.6356,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.0434782608695652,
912
+ "grad_norm": 0.23183418810367584,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 0.7009,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.05175983436853,
919
+ "grad_norm": 0.23346415162086487,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.5939,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.060041407867495,
926
+ "grad_norm": 0.24210385978221893,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.7173,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.0683229813664596,
933
+ "grad_norm": 0.22531944513320923,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.5273,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.0766045548654244,
940
+ "grad_norm": 0.25816595554351807,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 0.6477,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.0848861283643891,
947
+ "grad_norm": 0.2804325520992279,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 0.6571,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.093167701863354,
954
+ "grad_norm": 0.274699330329895,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 0.6704,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.1014492753623188,
961
+ "grad_norm": 0.26135748624801636,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 0.6641,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.1097308488612836,
968
+ "grad_norm": 0.3417491912841797,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 0.8094,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.1180124223602483,
975
+ "grad_norm": 0.2966398298740387,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 0.7448,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.1262939958592133,
982
+ "grad_norm": 0.29686564207077026,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 0.6288,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.134575569358178,
989
+ "grad_norm": 0.332364946603775,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 0.7955,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.1428571428571428,
996
+ "grad_norm": 0.3861692249774933,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 0.6987,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.1511387163561078,
1003
+ "grad_norm": 0.351142555475235,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.72,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.1594202898550725,
1010
+ "grad_norm": 0.3705615997314453,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.5818,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.1677018633540373,
1017
+ "grad_norm": 0.36091944575309753,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.6673,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.175983436853002,
1024
+ "grad_norm": 0.39567896723747253,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.6597,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.184265010351967,
1031
+ "grad_norm": 0.38994473218917847,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.6453,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.1925465838509317,
1038
+ "grad_norm": 0.4518220126628876,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.7173,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.2008281573498965,
1045
+ "grad_norm": 0.4618150591850281,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 0.6811,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.2091097308488612,
1052
+ "grad_norm": 0.4686547517776489,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.6195,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.2173913043478262,
1059
+ "grad_norm": 0.4487763047218323,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 0.6075,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.225672877846791,
1066
+ "grad_norm": 0.5483669638633728,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 0.6045,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.2339544513457557,
1073
+ "grad_norm": 0.573219358921051,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.7711,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.2422360248447206,
1080
+ "grad_norm": 0.6374213099479675,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.6176,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.2422360248447206,
1087
+ "eval_loss": 0.8175904750823975,
1088
+ "eval_runtime": 32.7299,
1089
+ "eval_samples_per_second": 6.233,
1090
+ "eval_steps_per_second": 1.558,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.887933580140872e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null