cimol commited on
Commit
5aadbfc
·
verified ·
1 Parent(s): a9d988e

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 sha256:5d7afe503a59e917c6564884c47495f482074a7b83c7bebaab1a23fa9eda620a
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcacb409ebaed62be77b48d337262daec39c95dc781f989086cfb2198f52b36
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af8252a64dd4ef03452b4153b682e1dadbaacf09b645ff10a5cef40deac0ca5b
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a1a868f1b1dceaf99c80b1273b4da02299251c95a8dbd6681b44fec5cd32d3
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb84a9ac2dee716fa2f69140c1e91320222174b79c83de2d62370dd825f6d433
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873727fda299165f8e430a5b96f4c91ecf39580567b45b0c1d0ac11addfc58f0
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": 0.505704939365387,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.056227157717177394,
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": 22.383,
732
  "eval_steps_per_second": 5.598,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.14368026066944e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.473353773355484,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0843407365757661,
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": 22.383,
732
  "eval_steps_per_second": 5.598,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05678942929434917,
737
+ "grad_norm": 0.8749874830245972,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 0.6225,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.057351700871520944,
744
+ "grad_norm": 0.9259828329086304,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 0.6139,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.057913972448692716,
751
+ "grad_norm": 0.9162857532501221,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 0.6087,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.058476244025864495,
758
+ "grad_norm": 0.9499956965446472,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 0.6472,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.059038515603036266,
765
+ "grad_norm": 0.8614834547042847,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 0.5174,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.05960078718020804,
772
+ "grad_norm": 0.8235839009284973,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 0.5348,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06016305875737982,
779
+ "grad_norm": 0.8406442999839783,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 0.5699,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06072533033455159,
786
+ "grad_norm": 0.7853993773460388,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 0.4682,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06128760191172336,
793
+ "grad_norm": 0.8188884258270264,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 0.5738,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06184987348889514,
800
+ "grad_norm": 0.8763449192047119,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 0.5559,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06241214506606691,
807
+ "grad_norm": 0.8494906425476074,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 0.4719,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06297441664323869,
814
+ "grad_norm": 0.9282271265983582,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 0.5575,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06353668822041046,
821
+ "grad_norm": 0.8760861754417419,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 0.4802,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06409895979758223,
828
+ "grad_norm": 0.9161163568496704,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 0.5109,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.064661231374754,
835
+ "grad_norm": 0.8412004113197327,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 0.4635,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06522350295192578,
842
+ "grad_norm": 0.9224844574928284,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 0.5794,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06578577452909755,
849
+ "grad_norm": 0.8909794092178345,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 0.5022,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06634804610626933,
856
+ "grad_norm": 0.8420968055725098,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 0.4882,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0669103176834411,
863
+ "grad_norm": 0.8328831791877747,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 0.4727,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.06747258926061288,
870
+ "grad_norm": 0.8066858649253845,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 0.3648,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.06803486083778465,
877
+ "grad_norm": 0.8475686311721802,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 0.4553,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06859713241495642,
884
+ "grad_norm": 0.8595974445343018,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 0.4771,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0691594039921282,
891
+ "grad_norm": 0.8730382323265076,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 0.4813,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.06972167556929997,
898
+ "grad_norm": 0.8853369951248169,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 0.4198,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07028394714647175,
905
+ "grad_norm": 0.9038184285163879,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 0.5657,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07084621872364352,
912
+ "grad_norm": 1.5610709190368652,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 0.5383,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0714084903008153,
919
+ "grad_norm": 0.9560755491256714,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 0.5175,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07197076187798707,
926
+ "grad_norm": 0.8506150841712952,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 0.4004,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07253303345515884,
933
+ "grad_norm": 1.011541724205017,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 0.3982,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07309530503233061,
940
+ "grad_norm": 0.9126336574554443,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 0.4037,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0736575766095024,
947
+ "grad_norm": 0.8268803358078003,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 0.3862,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07421984818667417,
954
+ "grad_norm": 0.8743264675140381,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 0.4618,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.07478211976384594,
961
+ "grad_norm": 0.8378267884254456,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 0.3606,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07534439134101771,
968
+ "grad_norm": 0.9845398664474487,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 0.462,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07590666291818948,
975
+ "grad_norm": 0.9598365426063538,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 0.4421,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07646893449536125,
982
+ "grad_norm": 0.9708433747291565,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 0.4005,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.07703120607253304,
989
+ "grad_norm": 1.1017184257507324,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 0.2971,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.07759347764970481,
996
+ "grad_norm": 0.8630903959274292,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 0.3356,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.07815574922687658,
1003
+ "grad_norm": 0.8240814208984375,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 0.3526,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.07871802080404836,
1010
+ "grad_norm": 1.026856780052185,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 0.4624,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.07928029238122013,
1017
+ "grad_norm": 0.9484303593635559,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 0.3647,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0798425639583919,
1024
+ "grad_norm": 0.895967423915863,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 0.328,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08040483553556367,
1031
+ "grad_norm": 1.0940560102462769,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 0.4679,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08096710711273546,
1038
+ "grad_norm": 0.962182879447937,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 0.3011,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08152937868990723,
1045
+ "grad_norm": 1.0793566703796387,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 0.4022,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.082091650267079,
1052
+ "grad_norm": 1.100953221321106,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 0.5533,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08265392184425077,
1059
+ "grad_norm": 1.1323171854019165,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 0.4212,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08321619342142254,
1066
+ "grad_norm": 1.3615832328796387,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 0.4009,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08377846499859432,
1073
+ "grad_norm": 1.7980997562408447,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 0.6561,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0843407365757661,
1080
+ "grad_norm": 1.7629038095474243,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 0.4492,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0843407365757661,
1087
+ "eval_loss": 0.473353773355484,
1088
+ "eval_runtime": 133.8043,
1089
+ "eval_samples_per_second": 22.383,
1090
+ "eval_steps_per_second": 5.598,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.21552039100416e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null