prxy5607 commited on
Commit
5573d0f
·
verified ·
1 Parent(s): 6960ec3

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 sha256:0193534dce58c7f0a88e418ade49533b81215bf9fabd14e91a8eeb122fb2aa6d
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a16a827c5df368e048dce8d433fa2e1e43074ff07e1113e58b88c00ed2a57a4
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa021216350e3db9418ce91d228216609f04dfb14a8316e5146f5d8ee49ade2e
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714d727230c83f1bf3ce7a8bf0a851723055f0a5a507a27346991fe3baca2664
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da85775a1549b36cb3784c5e8f5a13a48c2390fb636b33c0ae9dfc918e5a5c54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98dbcf9e5c1f08e5f027e52b77efa6dac5c9883afd06d5deb0cf6cf0bf9b9c06
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": 1.8713520765304565,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4662004662004662,
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": 33.543,
732
  "eval_steps_per_second": 8.455,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.30904010489856e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.792533040046692,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6993006993006993,
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": 33.543,
732
  "eval_steps_per_second": 8.455,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.47086247086247085,
737
+ "grad_norm": 0.6302658319473267,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.2328,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4755244755244755,
744
+ "grad_norm": 0.5877934098243713,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.2642,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.4801864801864802,
751
+ "grad_norm": 0.6043432354927063,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3779,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.48484848484848486,
758
+ "grad_norm": 0.5296673774719238,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3788,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.48951048951048953,
765
+ "grad_norm": 0.5024903416633606,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.3012,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.49417249417249415,
772
+ "grad_norm": 0.5119273066520691,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.3185,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4988344988344988,
779
+ "grad_norm": 0.4788738191127777,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.3679,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5034965034965035,
786
+ "grad_norm": 0.5437080264091492,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.4681,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5081585081585082,
793
+ "grad_norm": 0.5525368452072144,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.4913,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5128205128205128,
800
+ "grad_norm": 0.5370126366615295,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.6615,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5174825174825175,
807
+ "grad_norm": 0.5269562005996704,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.5188,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5221445221445221,
814
+ "grad_norm": 0.5016019344329834,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4567,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5268065268065268,
821
+ "grad_norm": 0.5243374109268188,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.4363,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5314685314685315,
828
+ "grad_norm": 0.5685271620750427,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.5868,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5361305361305362,
835
+ "grad_norm": 0.5902321934700012,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.589,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5407925407925408,
842
+ "grad_norm": 0.5882418155670166,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.7838,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5454545454545454,
849
+ "grad_norm": 0.6185193657875061,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.812,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.5501165501165501,
856
+ "grad_norm": 0.6451072692871094,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.8217,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5547785547785548,
863
+ "grad_norm": 0.632240355014801,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.7533,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5594405594405595,
870
+ "grad_norm": 0.6013713479042053,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.6603,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5641025641025641,
877
+ "grad_norm": 0.5924433469772339,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.6549,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5687645687645687,
884
+ "grad_norm": 0.7028740644454956,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.6005,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5734265734265734,
891
+ "grad_norm": 0.7034977674484253,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.9802,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.578088578088578,
898
+ "grad_norm": 0.7669457197189331,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.8327,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5827505827505828,
905
+ "grad_norm": 0.6575400233268738,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.8541,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5874125874125874,
912
+ "grad_norm": 0.7511604428291321,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.7712,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5920745920745921,
919
+ "grad_norm": 0.8430941104888916,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.1503,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5967365967365967,
926
+ "grad_norm": 0.6790040135383606,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.9044,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6013986013986014,
933
+ "grad_norm": 0.6855138540267944,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.8459,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6060606060606061,
940
+ "grad_norm": 0.8203029036521912,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.1096,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6107226107226107,
947
+ "grad_norm": 0.7765827775001526,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.0067,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6153846153846154,
954
+ "grad_norm": 0.8429322838783264,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.1071,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.62004662004662,
961
+ "grad_norm": 0.8036541938781738,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.0064,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6247086247086248,
968
+ "grad_norm": 0.884415328502655,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.2085,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6293706293706294,
975
+ "grad_norm": 0.7145037055015564,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.9588,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.634032634032634,
982
+ "grad_norm": 0.7449626326560974,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.8609,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6386946386946387,
989
+ "grad_norm": 0.7585590481758118,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.8423,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6433566433566433,
996
+ "grad_norm": 0.9376791715621948,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.1774,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6480186480186481,
1003
+ "grad_norm": 0.864797830581665,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.9965,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6526806526806527,
1010
+ "grad_norm": 0.830837607383728,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.9375,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6573426573426573,
1017
+ "grad_norm": 0.8673924803733826,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.1165,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.662004662004662,
1024
+ "grad_norm": 0.9556111693382263,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.0692,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6666666666666666,
1031
+ "grad_norm": 0.939336895942688,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.2542,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6713286713286714,
1038
+ "grad_norm": 0.9361501336097717,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.1401,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.675990675990676,
1045
+ "grad_norm": 1.0414737462997437,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.1523,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6806526806526807,
1052
+ "grad_norm": 0.9971078038215637,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 2.0692,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6853146853146853,
1059
+ "grad_norm": 1.0580642223358154,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 2.1947,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6899766899766899,
1066
+ "grad_norm": 1.0020278692245483,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.0696,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6946386946386947,
1073
+ "grad_norm": 0.9605817198753357,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.3733,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6993006993006993,
1080
+ "grad_norm": 1.195831298828125,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.2114,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6993006993006993,
1087
+ "eval_loss": 1.792533040046692,
1088
+ "eval_runtime": 10.7405,
1089
+ "eval_samples_per_second": 33.611,
1090
+ "eval_steps_per_second": 8.473,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.96356015734784e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null