aleegis12 commited on
Commit
e453e8a
·
verified ·
1 Parent(s): fb48991

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 sha256:99e5b29e5b4804b7cff40da6dff72bb6959b7f4d005a50bcc6096195555b8c8a
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a57709c1e221a2e0aa3298e4cbd1905d7ad574c9cad62a031a9efcc573862fa
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22664006b5b566e0a6305bdd9ac451b3aecf583416fb7196f9416ab59bd91fbe
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a22597758ff1e69a98ad37251ac80a0e7d7059d0534a49013f7372b3a9af42c2
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b82007bd6e5f28c451c3c270fe8792b9d672f2de58fd795add930345f3cfd2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0c9713cfb31c7122f2cfd3b11d9e1585f3d90b001265e55b3abab5ed45480b0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1121288537979126,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.05557099194220617,
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": 41.734,
732
  "eval_steps_per_second": 10.437,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.5224473355485184e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0815174579620361,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08335648791330925,
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": 41.734,
732
  "eval_steps_per_second": 10.437,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05612670186162823,
737
+ "grad_norm": 0.35126662254333496,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.7206,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.05668241178105029,
744
+ "grad_norm": 0.3719412386417389,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8151,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.05723812170047236,
751
+ "grad_norm": 0.42008474469184875,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9282,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.05779383161989442,
758
+ "grad_norm": 0.3835548460483551,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.8687,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.05834954153931648,
765
+ "grad_norm": 0.36141228675842285,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.9697,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.05890525145873854,
772
+ "grad_norm": 0.33506307005882263,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.935,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0594609613781606,
779
+ "grad_norm": 0.32544660568237305,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.986,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.06001667129758266,
786
+ "grad_norm": 0.27874335646629333,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.8796,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06057238121700472,
793
+ "grad_norm": 0.26315340399742126,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9322,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06112809113642678,
800
+ "grad_norm": 0.2800102233886719,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9671,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.06168380105584885,
807
+ "grad_norm": 0.27754732966423035,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9139,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06223951097527091,
814
+ "grad_norm": 0.2846638262271881,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0149,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06279522089469297,
821
+ "grad_norm": 0.2971688508987427,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.0451,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.06335093081411503,
828
+ "grad_norm": 0.2871069610118866,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.984,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06390664073353709,
835
+ "grad_norm": 0.29142001271247864,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9882,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06446235065295916,
842
+ "grad_norm": 0.2938911020755768,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.9948,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.06501806057238121,
849
+ "grad_norm": 0.307596892118454,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.0425,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06557377049180328,
856
+ "grad_norm": 0.31925082206726074,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9976,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06612948041122534,
863
+ "grad_norm": 0.31774935126304626,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.1184,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0666851903306474,
870
+ "grad_norm": 0.32030215859413147,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.0316,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.06724090025006946,
877
+ "grad_norm": 0.35295090079307556,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.1201,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.06779661016949153,
884
+ "grad_norm": 0.3115982115268707,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.037,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.06835232008891359,
891
+ "grad_norm": 0.32781195640563965,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.9565,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.06890803000833565,
898
+ "grad_norm": 0.36501210927963257,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.095,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.06946373992775771,
905
+ "grad_norm": 0.34200319647789,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.0184,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07001944984717977,
912
+ "grad_norm": 0.3334757387638092,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.9712,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07057515976660184,
919
+ "grad_norm": 0.40706580877304077,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0333,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07113086968602389,
926
+ "grad_norm": 0.37194889783859253,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0282,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07168657960544596,
933
+ "grad_norm": 0.388510525226593,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1057,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.07224228952486803,
940
+ "grad_norm": 0.39619317650794983,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0826,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07279799944429008,
947
+ "grad_norm": 0.43052905797958374,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1265,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07335370936371215,
954
+ "grad_norm": 0.4574252963066101,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1076,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0739094192831342,
961
+ "grad_norm": 0.42951375246047974,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.0856,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07446512920255627,
968
+ "grad_norm": 0.4537774920463562,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.1315,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07502083912197832,
975
+ "grad_norm": 0.46146097779273987,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1864,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.07557654904140039,
982
+ "grad_norm": 0.5010975003242493,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.0196,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.07613225896082246,
989
+ "grad_norm": 0.5995842814445496,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1385,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.07668796888024451,
996
+ "grad_norm": 0.5713678002357483,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1103,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.07724367879966658,
1003
+ "grad_norm": 0.6867542266845703,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.3628,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.07779938871908863,
1010
+ "grad_norm": 0.6472092270851135,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0568,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0783550986385107,
1017
+ "grad_norm": 0.6878289580345154,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2264,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.07891080855793275,
1024
+ "grad_norm": 0.6812445521354675,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.254,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.07946651847735482,
1031
+ "grad_norm": 0.679113507270813,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1547,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08002222839677688,
1038
+ "grad_norm": 0.938140332698822,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2103,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08057793831619894,
1045
+ "grad_norm": 0.8095746636390686,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1483,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08113364823562101,
1052
+ "grad_norm": 0.9538931846618652,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2137,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08168935815504307,
1059
+ "grad_norm": 0.993846595287323,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.0651,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08224506807446513,
1066
+ "grad_norm": 0.966073751449585,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.2755,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.08280077799388719,
1073
+ "grad_norm": 1.1758711338043213,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.3301,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08335648791330925,
1080
+ "grad_norm": 1.6939853429794312,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.2407,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08335648791330925,
1087
+ "eval_loss": 1.0815174579620361,
1088
+ "eval_runtime": 72.6188,
1089
+ "eval_samples_per_second": 41.739,
1090
+ "eval_steps_per_second": 10.438,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.786337438138368e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null