prxy5605 commited on
Commit
1ebb950
·
verified ·
1 Parent(s): d355238

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 sha256:62152ecde7d5bf83e108a1a12db0224ceb0be0ce2308984a1632ba5f204046f1
3
  size 180385008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12304f8e214d74c4e9052d42811f180b3f597b2c29738b9807146b75d205d74e
3
  size 180385008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8293774979a9cd21279f6a49354aa1a91333e60d49e0374c9f89f19559a49652
3
  size 91850362
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27c771e7e7208402c911748ecf223a0351c3a1ba8357def7ee65b96005784a1
3
  size 91850362
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1748ffc4f1fd092b53368e1edb2feeb053b99b39666fb4156058b0ab46bbb45
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64005f3293f453e07db36596b4913f161a4c128036aa29806e75883bf9eede2b
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": 3.3252243995666504,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.10432968179447052,
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": 35.268,
732
  "eval_steps_per_second": 8.828,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.707611992457216e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.280613899230957,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1564945226917058,
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": 35.268,
732
  "eval_steps_per_second": 8.828,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.10537297861241524,
737
+ "grad_norm": 0.787086546421051,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 3.4292,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.10641627543035993,
744
+ "grad_norm": 0.7174277901649475,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 3.49,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.10745957224830464,
751
+ "grad_norm": 0.5412613153457642,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 3.3275,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.10850286906624934,
758
+ "grad_norm": 0.4861738085746765,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 3.5012,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.10954616588419405,
765
+ "grad_norm": 0.4842031002044678,
766
+ "learning_rate": 5e-05,
767
+ "loss": 3.4971,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.11058946270213876,
772
+ "grad_norm": 0.47764962911605835,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 3.3493,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.11163275952008346,
779
+ "grad_norm": 0.5093321800231934,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 3.4019,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.11267605633802817,
786
+ "grad_norm": 0.5084569454193115,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 3.3828,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.11371935315597287,
793
+ "grad_norm": 0.4781957268714905,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 3.4065,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.11476264997391758,
800
+ "grad_norm": 0.43107083439826965,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 3.3369,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.11580594679186229,
807
+ "grad_norm": 0.44881919026374817,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 3.4299,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.11684924360980699,
814
+ "grad_norm": 0.4160110056400299,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 3.4753,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1178925404277517,
821
+ "grad_norm": 0.4867398738861084,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 3.3588,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.1189358372456964,
828
+ "grad_norm": 0.47459399700164795,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 3.3675,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.11997913406364111,
835
+ "grad_norm": 0.40645161271095276,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 3.3632,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.1210224308815858,
842
+ "grad_norm": 0.39582309126853943,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 3.2547,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.12206572769953052,
849
+ "grad_norm": 0.3737109899520874,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 3.3265,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.12310902451747523,
856
+ "grad_norm": 0.39096322655677795,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 3.2082,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.12415232133541992,
863
+ "grad_norm": 0.4134329557418823,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 3.4101,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.12519561815336464,
870
+ "grad_norm": 0.41859692335128784,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 3.3879,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.12623891497130935,
877
+ "grad_norm": 0.427964448928833,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 3.4571,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.12728221178925403,
884
+ "grad_norm": 0.4351688027381897,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 3.3502,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.12832550860719874,
891
+ "grad_norm": 0.42806118726730347,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 3.275,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.12936880542514345,
898
+ "grad_norm": 0.4266616106033325,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 3.1303,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.13041210224308816,
905
+ "grad_norm": 0.43820124864578247,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 3.3103,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.13145539906103287,
912
+ "grad_norm": 0.4153601825237274,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.3252,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.13249869587897756,
919
+ "grad_norm": 0.453664630651474,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 3.2869,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.13354199269692227,
926
+ "grad_norm": 0.46373143792152405,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 3.3462,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.13458528951486698,
933
+ "grad_norm": 0.47818803787231445,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 3.3275,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1356285863328117,
940
+ "grad_norm": 0.4792380928993225,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 3.2778,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1366718831507564,
947
+ "grad_norm": 0.5010649561882019,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 3.2362,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.13771517996870108,
954
+ "grad_norm": 0.4995712637901306,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 3.3166,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.1387584767866458,
961
+ "grad_norm": 0.51168292760849,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 3.2292,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1398017736045905,
968
+ "grad_norm": 0.5347958207130432,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.2483,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.14084507042253522,
975
+ "grad_norm": 0.5277102589607239,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 3.2252,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.14188836724047993,
982
+ "grad_norm": 0.5362873673439026,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 3.2038,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1429316640584246,
989
+ "grad_norm": 0.5422380566596985,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 3.2725,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.14397496087636932,
996
+ "grad_norm": 0.552033543586731,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 3.1894,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.14501825769431403,
1003
+ "grad_norm": 0.5851796865463257,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 3.2272,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.14606155451225875,
1010
+ "grad_norm": 0.628825306892395,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.2583,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.14710485133020346,
1017
+ "grad_norm": 0.5927334427833557,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.276,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.14814814814814814,
1024
+ "grad_norm": 0.6273190975189209,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.1073,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.14919144496609285,
1031
+ "grad_norm": 0.624865710735321,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.1138,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.15023474178403756,
1038
+ "grad_norm": 0.627785861492157,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.0413,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.15127803860198227,
1045
+ "grad_norm": 0.6595969200134277,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.9438,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.15232133541992696,
1052
+ "grad_norm": 0.6877166032791138,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.1219,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.15336463223787167,
1059
+ "grad_norm": 0.7304136157035828,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.1321,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.15440792905581638,
1066
+ "grad_norm": 0.7825625538825989,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 2.9733,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.1554512258737611,
1073
+ "grad_norm": 0.9954061508178711,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 2.9893,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1564945226917058,
1080
+ "grad_norm": 1.6247068643569946,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 2.6556,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1564945226917058,
1087
+ "eval_loss": 3.280613899230957,
1088
+ "eval_runtime": 45.8112,
1089
+ "eval_samples_per_second": 35.232,
1090
+ "eval_steps_per_second": 8.819,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4.068925230809088e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null