aleegis09 commited on
Commit
ad57455
·
verified ·
1 Parent(s): 9836c33

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 sha256:87356bc58fe5e28d0a5dacc1b5dd4e81d7c17d42495fead5eea3b9a183c469d7
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4083f056f27993a37168c7c3bee806f47cbc030b41f6128051b39098de1530
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f55790e57f7bda9aceb40f2b3c834db0066e645f92437caafa3f8e102fcc92c
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8579b7140702c4cb55266f1c117c1fa6780ba11029ed4f7ba36617d876796132
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:e3f11e4abdcb712f1647d55e41a52c9f1086bf2e2e30a95f949f0a57c3f2cf16
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811f915a06ba19bba462cce8c7df9491fee5a7265d3c342122a45677532619ce
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": 3.0394115447998047,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.333889816360601,
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": 13.735,
732
  "eval_steps_per_second": 3.454,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.431616484278272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5211260318756104,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5008347245409015,
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": 13.735,
732
  "eval_steps_per_second": 3.454,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.337228714524207,
737
+ "grad_norm": 46.445770263671875,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 7.9802,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.34056761268781305,
744
+ "grad_norm": 22.086231231689453,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 8.728,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.34390651085141904,
751
+ "grad_norm": 28.4797306060791,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 8.6193,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.34724540901502504,
758
+ "grad_norm": 20.637239456176758,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 8.6191,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.35058430717863104,
765
+ "grad_norm": 13.004572868347168,
766
+ "learning_rate": 5e-05,
767
+ "loss": 8.1884,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.35392320534223703,
772
+ "grad_norm": 11.900628089904785,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 8.3751,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3572621035058431,
779
+ "grad_norm": 11.513484954833984,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 7.862,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.3606010016694491,
786
+ "grad_norm": 9.66572093963623,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 8.4616,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.3639398998330551,
793
+ "grad_norm": 9.2223482131958,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.2906,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3672787979966611,
800
+ "grad_norm": 9.927684783935547,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 8.214,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.37061769616026713,
807
+ "grad_norm": 10.191082000732422,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 7.6443,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3739565943238731,
814
+ "grad_norm": 9.640283584594727,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 8.0934,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.3772954924874791,
821
+ "grad_norm": 9.085577011108398,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 7.993,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.3806343906510851,
828
+ "grad_norm": 9.938830375671387,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 8.4036,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.38397328881469117,
835
+ "grad_norm": 10.653984069824219,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 8.7188,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.38731218697829717,
842
+ "grad_norm": 10.567211151123047,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 8.4954,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.39065108514190316,
849
+ "grad_norm": 9.62268352508545,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 8.6726,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.39398998330550916,
856
+ "grad_norm": 9.84789752960205,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 7.7559,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.3973288814691152,
863
+ "grad_norm": 10.444355010986328,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 8.6711,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.4006677796327212,
870
+ "grad_norm": 10.310248374938965,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 7.6999,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4040066777963272,
877
+ "grad_norm": 9.515129089355469,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 7.5413,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.4073455759599332,
884
+ "grad_norm": 10.727609634399414,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 8.8072,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.41068447412353926,
891
+ "grad_norm": 10.421792030334473,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 8.697,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.41402337228714525,
898
+ "grad_norm": 10.795896530151367,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 8.5433,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.41736227045075125,
905
+ "grad_norm": 11.250564575195312,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 8.7034,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.42070116861435725,
912
+ "grad_norm": 11.368125915527344,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 8.4941,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4240400667779633,
919
+ "grad_norm": 11.218993186950684,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.475,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.4273789649415693,
926
+ "grad_norm": 10.902496337890625,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 8.8587,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4307178631051753,
933
+ "grad_norm": 11.110245704650879,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 8.5692,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.4340567612687813,
940
+ "grad_norm": 11.624847412109375,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 9.3432,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.4373956594323873,
947
+ "grad_norm": 12.190470695495605,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 9.2873,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.44073455759599334,
954
+ "grad_norm": 12.650010108947754,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 9.3438,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.44407345575959933,
961
+ "grad_norm": 12.46180534362793,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 8.5955,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.44741235392320533,
968
+ "grad_norm": 11.917457580566406,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.0624,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4507512520868113,
975
+ "grad_norm": 13.026808738708496,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 9.2577,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4540901502504174,
982
+ "grad_norm": 12.108113288879395,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 9.2373,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.4574290484140234,
989
+ "grad_norm": 12.285905838012695,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 8.9605,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.4607679465776294,
996
+ "grad_norm": 12.513566970825195,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.4576,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.46410684474123537,
1003
+ "grad_norm": 13.021560668945312,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 8.8887,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.4674457429048414,
1010
+ "grad_norm": 13.232269287109375,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 8.9009,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.4707846410684474,
1017
+ "grad_norm": 13.867449760437012,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 9.03,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4741235392320534,
1024
+ "grad_norm": 13.765838623046875,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 8.9284,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4774624373956594,
1031
+ "grad_norm": 14.766548156738281,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.052,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.48080133555926546,
1038
+ "grad_norm": 14.860197067260742,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 9.9734,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.48414023372287146,
1045
+ "grad_norm": 16.1668643951416,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 9.9494,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.48747913188647746,
1052
+ "grad_norm": 17.132164001464844,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 9.307,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.49081803005008345,
1059
+ "grad_norm": 21.884746551513672,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 9.4493,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.4941569282136895,
1066
+ "grad_norm": 24.54769515991211,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.1962,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.4974958263772955,
1073
+ "grad_norm": 42.04847717285156,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 9.079,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5008347245409015,
1080
+ "grad_norm": 49.17021560668945,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.116,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5008347245409015,
1087
+ "eval_loss": 2.5211260318756104,
1088
+ "eval_runtime": 36.7773,
1089
+ "eval_samples_per_second": 13.731,
1090
+ "eval_steps_per_second": 3.453,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.147424726417408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null