bbytxt commited on
Commit
a233285
·
verified ·
1 Parent(s): 3f580a7

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 sha256:170bfc6f014a91df446398cccd9cae5484f1f2b3378114b868ffd685b4f0e66a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac40c530eaed816f74364a8be7cb82bdc95cf1f7ec85ff52dc09d4b828819878
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a34c4e39e036501f2090d1f3b2f79e4077e19f407a1dc6c705b1e7b3542826f
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af727b7d2eca54cce3c70366d87d000fe93466e4562304cd7308508391378768
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f64f59e1eff0ad866edf38330b3a5105bd6362aa4ac6f22de60136aeaad90d5f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88515dc17612017ee763c93cc7fb6672460665fbf615a612b1e7b8d1e41b6368
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.1764209270477295,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.00844095551616443,
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": 11.022,
732
  "eval_steps_per_second": 5.511,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.6782213563547648e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.052938938140869,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.012661433274246644,
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": 11.022,
732
  "eval_steps_per_second": 5.511,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.008525365071326074,
737
+ "grad_norm": 0.8329039812088013,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 1.9627,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.008609774626487718,
744
+ "grad_norm": 1.5277196168899536,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 1.0581,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.008694184181649363,
751
+ "grad_norm": 1.4037386178970337,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 2.242,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.008778593736811008,
758
+ "grad_norm": 3.4319448471069336,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 2.1786,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.008863003291972652,
765
+ "grad_norm": 1.5401387214660645,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 2.2078,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.008947412847134295,
772
+ "grad_norm": 1.2498023509979248,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 1.9751,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.00903182240229594,
779
+ "grad_norm": 1.0410596132278442,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 1.9234,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.009116231957457584,
786
+ "grad_norm": 1.7921696901321411,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 2.0355,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.009200641512619229,
793
+ "grad_norm": 0.9875342845916748,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 2.1915,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.009285051067780872,
800
+ "grad_norm": 0.983015239238739,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 1.7572,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.009369460622942517,
807
+ "grad_norm": 1.257350206375122,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 1.7889,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.009453870178104161,
814
+ "grad_norm": 0.96494460105896,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 1.7814,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.009538279733265806,
821
+ "grad_norm": 0.9378180503845215,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 2.1742,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.00962268928842745,
828
+ "grad_norm": 0.8996978402137756,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 2.1518,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.009707098843589093,
835
+ "grad_norm": 1.2315887212753296,
836
+ "learning_rate": 5e-05,
837
+ "loss": 1.9632,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.009791508398750738,
842
+ "grad_norm": 0.963108241558075,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 1.9375,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.009875917953912383,
849
+ "grad_norm": 1.0140211582183838,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 1.4991,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.009960327509074027,
856
+ "grad_norm": 0.8235830068588257,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 1.6948,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.010044737064235672,
863
+ "grad_norm": 1.008412480354309,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 1.3628,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.010129146619397315,
870
+ "grad_norm": 1.0166562795639038,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 1.5645,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01021355617455896,
877
+ "grad_norm": 1.075079321861267,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 1.6391,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.010297965729720604,
884
+ "grad_norm": 1.0736780166625977,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 1.8835,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.010382375284882249,
891
+ "grad_norm": 1.330854892730713,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 1.7725,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.010466784840043894,
898
+ "grad_norm": 1.6348861455917358,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 1.7617,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.010551194395205537,
905
+ "grad_norm": 1.3457287549972534,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 1.8506,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.010635603950367181,
912
+ "grad_norm": 1.2787361145019531,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 1.8059,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.010720013505528826,
919
+ "grad_norm": 1.2608163356781006,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 1.6276,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.01080442306069047,
926
+ "grad_norm": 1.0264259576797485,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 1.5321,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.010888832615852115,
933
+ "grad_norm": 1.3834068775177002,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 1.6483,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.010973242171013758,
940
+ "grad_norm": 1.335982322692871,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.7294,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.011057651726175403,
947
+ "grad_norm": 1.2448405027389526,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 1.5256,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.011142061281337047,
954
+ "grad_norm": 1.1373120546340942,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 1.8429,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.011226470836498692,
961
+ "grad_norm": 1.4305205345153809,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 2.0747,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.011310880391660337,
968
+ "grad_norm": 1.6904332637786865,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 2.2343,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.01139528994682198,
975
+ "grad_norm": 1.8783656358718872,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 1.9961,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.011479699501983624,
982
+ "grad_norm": 2.045578718185425,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 2.3154,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.011564109057145269,
989
+ "grad_norm": 1.8023104667663574,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 1.7244,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.011648518612306914,
996
+ "grad_norm": 1.8824018239974976,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 2.2433,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.011732928167468558,
1003
+ "grad_norm": 1.7303247451782227,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 1.7089,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.011817337722630201,
1010
+ "grad_norm": 2.0319793224334717,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 2.0727,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.011901747277791846,
1017
+ "grad_norm": 2.2583532333374023,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.8439,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01198615683295349,
1024
+ "grad_norm": 2.583017587661743,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 2.1232,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.012070566388115135,
1031
+ "grad_norm": 3.050464630126953,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 2.121,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01215497594327678,
1038
+ "grad_norm": 3.034822940826416,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.7587,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.012239385498438423,
1045
+ "grad_norm": 2.6765623092651367,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 2.0119,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.012323795053600067,
1052
+ "grad_norm": 2.746692180633545,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 2.0327,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.012408204608761712,
1059
+ "grad_norm": 2.931114673614502,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 2.3408,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.012492614163923357,
1066
+ "grad_norm": 3.69539213180542,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 2.5359,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.012577023719085001,
1073
+ "grad_norm": 3.0832767486572266,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 2.0631,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.012661433274246644,
1080
+ "grad_norm": 5.046596050262451,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 2.4239,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.012661433274246644,
1087
+ "eval_loss": 2.052938938140869,
1088
+ "eval_runtime": 1817.9905,
1089
+ "eval_samples_per_second": 10.975,
1090
+ "eval_steps_per_second": 5.488,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.5003612567712563e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null