prxy5604 commited on
Commit
b5df70f
·
verified ·
1 Parent(s): b828dc1

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 sha256:79da49f4f174f529a5dcf3f2a173e480299cda83aa9e4374f982c194b22c5338
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6837f1311f6a76fb80452190a4185a0da8582770613c9d2ed916b35f8eb54b3f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f529f79de8f4bf602a919cd3685f1db263b7c74e21b6af279cc94b1eb543335
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254cb5e94849a63b080402d29ba556df9c2712fa598c79454e6a4db3cf05ee47
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:c28762cfb18eb3c143ab7e2caf856e9aeedc7b949636c0eb8eadec37d4c783b7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6c9bb4f74c13e00ad9ac28ed87363947b60a43e2d3c7d3509ade71d08f8460
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": 1.33364999294281,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.4192872117400419,
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": 9.049,
732
  "eval_steps_per_second": 2.274,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.581252799931351e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3053677082061768,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6289308176100629,
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": 9.049,
732
  "eval_steps_per_second": 2.274,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.42348008385744235,
737
+ "grad_norm": 12.140310287475586,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 7.4081,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.4276729559748428,
744
+ "grad_norm": 12.952072143554688,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 7.5179,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.43186582809224316,
751
+ "grad_norm": 14.149676322937012,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 7.5148,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4360587002096436,
758
+ "grad_norm": 13.430567741394043,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 7.2354,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.44025157232704404,
765
+ "grad_norm": 14.334609031677246,
766
+ "learning_rate": 5e-05,
767
+ "loss": 7.6918,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.4444444444444444,
772
+ "grad_norm": 13.022397994995117,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 6.1959,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.44863731656184486,
779
+ "grad_norm": 12.501748085021973,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 6.224,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4528301886792453,
786
+ "grad_norm": 11.310043334960938,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 6.0405,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.4570230607966457,
793
+ "grad_norm": 10.855735778808594,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 5.9622,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.4612159329140461,
800
+ "grad_norm": 12.147499084472656,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.5303,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.46540880503144655,
807
+ "grad_norm": 12.338438987731934,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.5863,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.469601677148847,
814
+ "grad_norm": 11.445416450500488,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.0989,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.47379454926624737,
821
+ "grad_norm": 11.623116493225098,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.4732,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.4779874213836478,
828
+ "grad_norm": 13.362641334533691,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 5.1787,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.48218029350104824,
835
+ "grad_norm": 11.479286193847656,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.9233,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.4863731656184486,
842
+ "grad_norm": 12.21015739440918,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 4.7571,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.49056603773584906,
849
+ "grad_norm": 12.11827278137207,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 5.1819,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4947589098532495,
856
+ "grad_norm": 11.634247779846191,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 4.7911,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.4989517819706499,
863
+ "grad_norm": 12.284260749816895,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 5.0751,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5031446540880503,
870
+ "grad_norm": 11.85743236541748,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 4.9025,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.5073375262054507,
877
+ "grad_norm": 12.35157299041748,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.8108,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5115303983228512,
884
+ "grad_norm": 11.492472648620605,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.0554,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5157232704402516,
891
+ "grad_norm": 12.209033966064453,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.1948,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.519916142557652,
898
+ "grad_norm": 13.564550399780273,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 4.9508,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5241090146750524,
905
+ "grad_norm": 13.559568405151367,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 4.9293,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5283018867924528,
912
+ "grad_norm": 10.4879789352417,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 4.4226,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5324947589098532,
919
+ "grad_norm": 11.57494831085205,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 4.815,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5366876310272537,
926
+ "grad_norm": 11.823269844055176,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 4.8705,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5408805031446541,
933
+ "grad_norm": 12.186006546020508,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.7831,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5450733752620545,
940
+ "grad_norm": 12.419806480407715,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.1625,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.549266247379455,
947
+ "grad_norm": 12.010101318359375,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 4.7556,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.5534591194968553,
954
+ "grad_norm": 21.347789764404297,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 4.572,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.5576519916142557,
961
+ "grad_norm": 11.743422508239746,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.5518,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5618448637316562,
968
+ "grad_norm": 14.868667602539062,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 4.8989,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5660377358490566,
975
+ "grad_norm": 11.682171821594238,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 4.9817,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.570230607966457,
982
+ "grad_norm": 11.996781349182129,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 4.9972,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5744234800838575,
989
+ "grad_norm": 11.404191970825195,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 4.9415,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5786163522012578,
996
+ "grad_norm": 12.217618942260742,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.0178,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.5828092243186582,
1003
+ "grad_norm": 14.083375930786133,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 4.9024,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5870020964360587,
1010
+ "grad_norm": 12.773621559143066,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 4.526,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.5911949685534591,
1017
+ "grad_norm": 11.781105995178223,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 4.9392,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5953878406708596,
1024
+ "grad_norm": 12.22276496887207,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 4.8146,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.59958071278826,
1031
+ "grad_norm": 11.05539608001709,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.0974,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6037735849056604,
1038
+ "grad_norm": 19.491600036621094,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.1393,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6079664570230608,
1045
+ "grad_norm": 11.561285972595215,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 4.8279,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6121593291404612,
1052
+ "grad_norm": 13.252482414245605,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 4.9525,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6163522012578616,
1059
+ "grad_norm": 11.3013916015625,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.0606,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6205450733752621,
1066
+ "grad_norm": 12.376293182373047,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.5769,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6247379454926625,
1073
+ "grad_norm": 12.117962837219238,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 5.041,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6289308176100629,
1080
+ "grad_norm": 14.499025344848633,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 5.4035,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6289308176100629,
1087
+ "eval_loss": 1.3053677082061768,
1088
+ "eval_runtime": 44.7304,
1089
+ "eval_samples_per_second": 8.987,
1090
+ "eval_steps_per_second": 2.258,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.3683017048745574e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null