cimol commited on
Commit
20aa99f
·
verified ·
1 Parent(s): 697d9b7

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 sha256:05da841c01d9426e347b1ba9025757c883e8207e5bf0d6379c34cccbc3f3b0fa
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560bbae8ed8341b7d972c6241dd86df9fbc090fa61e2b3036f8e09bf7468b88b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2401bf501b5fed8c349fc06858b9e43e928b0601f4307a8458b5f0cb1d2d5b3
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25610c5ea5c145d1e111cba96d46a858c7fc158a0c27a87bb6041312f5084481
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06181b8aba25b43155ba2ad1c3be1ace320cf6f80ee05d7bad78ee25dabed794
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df26111b678d81e80497ffb90695186b19d441229592862b5417a5e9077df4f9
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": 0.8752425312995911,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006292276230926538,
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": 13.427,
732
  "eval_steps_per_second": 3.357,
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": 0.797228217124939,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.009438414346389807,
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": 13.427,
732
  "eval_steps_per_second": 3.357,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.006355198993235803,
737
+ "grad_norm": 2.021313428878784,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 1.0507,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006418121755545068,
744
+ "grad_norm": 1.4400451183319092,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 0.796,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006481044517854334,
751
+ "grad_norm": 1.2445330619812012,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 0.8111,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.006543967280163599,
758
+ "grad_norm": 1.1896748542785645,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 0.8734,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0066068900424728644,
765
+ "grad_norm": 0.9736097455024719,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 0.7701,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.00666981280478213,
772
+ "grad_norm": 0.828886091709137,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 0.8266,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006732735567091396,
779
+ "grad_norm": 0.8219014406204224,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 0.7893,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.006795658329400661,
786
+ "grad_norm": 0.7297405004501343,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 0.8185,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006858581091709926,
793
+ "grad_norm": 0.8358471989631653,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 0.8146,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006921503854019191,
800
+ "grad_norm": 0.8461059331893921,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 0.823,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.006984426616328457,
807
+ "grad_norm": 0.8077146410942078,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 0.7864,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007047349378637722,
814
+ "grad_norm": 0.7723516821861267,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 0.7792,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.0071102721409469875,
821
+ "grad_norm": 0.8124366998672485,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 0.7783,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.007173194903256253,
828
+ "grad_norm": 0.7554612159729004,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 0.7939,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007236117665565519,
835
+ "grad_norm": 0.8711295127868652,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 0.7831,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.007299040427874784,
842
+ "grad_norm": 0.8391959071159363,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 0.7695,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007361963190184049,
849
+ "grad_norm": 0.8773452043533325,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 0.7739,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007424885952493314,
856
+ "grad_norm": 0.7932614088058472,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 0.7563,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007487808714802579,
863
+ "grad_norm": 0.8110454678535461,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 0.837,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0075507314771118455,
870
+ "grad_norm": 0.7787162065505981,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 0.7379,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.007613654239421111,
877
+ "grad_norm": 0.8096684217453003,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 0.7867,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.007676577001730376,
884
+ "grad_norm": 0.7443400025367737,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 0.7363,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.007739499764039641,
891
+ "grad_norm": 0.7531337141990662,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 0.7771,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.007802422526348907,
898
+ "grad_norm": 0.7670841813087463,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.7493,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.007865345288658171,
905
+ "grad_norm": 0.8572217226028442,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.7938,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007928268050967437,
912
+ "grad_norm": 0.7786096334457397,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 0.7789,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.007991190813276703,
919
+ "grad_norm": 0.8275337219238281,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.7598,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008054113575585968,
926
+ "grad_norm": 0.8422858119010925,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.8221,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008117036337895234,
933
+ "grad_norm": 0.7570464611053467,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.7552,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0081799591002045,
940
+ "grad_norm": 0.7353229522705078,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 0.7386,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.008242881862513764,
947
+ "grad_norm": 0.7655825018882751,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 0.7613,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.00830580462482303,
954
+ "grad_norm": 0.8073829412460327,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 0.7178,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008368727387132294,
961
+ "grad_norm": 0.7817210555076599,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 0.771,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.00843165014944156,
968
+ "grad_norm": 0.7924845218658447,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 0.7991,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.008494572911750826,
975
+ "grad_norm": 0.8270777463912964,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 0.8183,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.00855749567406009,
982
+ "grad_norm": 0.8548717498779297,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 0.7226,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.008620418436369357,
989
+ "grad_norm": 1.0007916688919067,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 0.8753,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.008683341198678623,
996
+ "grad_norm": 0.786884069442749,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 0.7939,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.008746263960987887,
1003
+ "grad_norm": 0.7700645923614502,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.6812,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.008809186723297153,
1010
+ "grad_norm": 0.8353739380836487,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.8099,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.008872109485606417,
1017
+ "grad_norm": 0.883284330368042,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.8062,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.008935032247915684,
1024
+ "grad_norm": 0.7576009035110474,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.7673,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.00899795501022495,
1031
+ "grad_norm": 0.790837287902832,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.808,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.009060877772534214,
1038
+ "grad_norm": 0.790503740310669,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.8153,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.00912380053484348,
1045
+ "grad_norm": 0.8170227408409119,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 0.7711,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.009186723297152744,
1052
+ "grad_norm": 0.8592228293418884,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.8427,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.00924964605946201,
1059
+ "grad_norm": 0.8412076830863953,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 0.7799,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009312568821771276,
1066
+ "grad_norm": 0.9095844626426697,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 0.8593,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.00937549158408054,
1073
+ "grad_norm": 0.9096418619155884,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.8268,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.009438414346389807,
1080
+ "grad_norm": 1.1173503398895264,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.9194,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.009438414346389807,
1087
+ "eval_loss": 0.797228217124939,
1088
+ "eval_runtime": 1992.4696,
1089
+ "eval_samples_per_second": 13.434,
1090
+ "eval_steps_per_second": 3.359,
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