prxy5607 commited on
Commit
12e6a87
·
verified ·
1 Parent(s): 4431516

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 sha256:4f85ab7a42f8b77cb5b280099dab9723edc1eb5f499bce61ff92ddc8d8fa2b4c
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0f311f28d27fd98d8490301b1485062a95fb6c3ab03b588762e5cf3f9d988a
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c2dadf367018c449ddc679bc1c8a8096706a5b10ff20cad9b594466bfc336e6
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592676c44e8d8019c068642c0854538f824719ae61dfecb94649d886e426ef27
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cd637973e391f761c9f80154ce0679506781190528173d90168df6bb447b10a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff57e8f001ca562f517ed4ad3b615d7ac9daa3fa7f4ddffe29b571eb74a7e44a
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": 1.2689018249511719,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.014980712332871429,
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": 52.991,
732
  "eval_steps_per_second": 13.249,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8327439820259328.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2603070735931396,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02247106849930714,
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": 52.991,
732
  "eval_steps_per_second": 13.249,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.015130519456200142,
737
+ "grad_norm": 0.562955915927887,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.2251,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.015280326579528856,
744
+ "grad_norm": 0.7312610149383545,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.1437,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.015430133702857571,
751
+ "grad_norm": 0.6145124435424805,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.8511,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.015579940826186285,
758
+ "grad_norm": 1.177874207496643,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.116,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.015729747949515,
765
+ "grad_norm": 0.5854660868644714,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.0903,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.015879555072843714,
772
+ "grad_norm": 0.5717855095863342,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.3579,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.016029362196172427,
779
+ "grad_norm": 0.6061097383499146,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.4909,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01617916931950114,
786
+ "grad_norm": 0.5581495761871338,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.3921,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.016328976442829858,
793
+ "grad_norm": 0.528045117855072,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.1971,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01647878356615857,
800
+ "grad_norm": 0.6216000318527222,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.3903,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.016628590689487285,
807
+ "grad_norm": 0.6433857083320618,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.2694,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.016778397812816,
814
+ "grad_norm": 0.5676413178443909,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.4193,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.016928204936144713,
821
+ "grad_norm": 0.562670111656189,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3706,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.017078012059473426,
828
+ "grad_norm": 0.5929762721061707,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.2658,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.017227819182802143,
835
+ "grad_norm": 0.669247567653656,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.3116,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.017377626306130857,
842
+ "grad_norm": 0.6218504905700684,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2707,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01752743342945957,
849
+ "grad_norm": 0.6539035439491272,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.3079,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.017677240552788284,
856
+ "grad_norm": 0.7109789252281189,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.1234,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.017827047676116998,
863
+ "grad_norm": 0.7230955958366394,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.3176,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.017976854799445715,
870
+ "grad_norm": 0.7343471050262451,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.2192,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01812666192277443,
877
+ "grad_norm": 0.682965099811554,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.1665,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.018276469046103142,
884
+ "grad_norm": 0.7259899973869324,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2293,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.018426276169431856,
891
+ "grad_norm": 0.8501508831977844,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.1932,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.01857608329276057,
898
+ "grad_norm": 0.6927886605262756,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.117,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.018725890416089287,
905
+ "grad_norm": 0.71158367395401,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.3288,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.018875697539418,
912
+ "grad_norm": 0.7121936678886414,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.2155,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.019025504662746714,
919
+ "grad_norm": 0.7002630233764648,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.0413,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.019175311786075427,
926
+ "grad_norm": 0.7453745603561401,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0846,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01932511890940414,
933
+ "grad_norm": 0.7211044430732727,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.0788,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.019474926032732858,
940
+ "grad_norm": 0.7318615913391113,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.0619,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.019624733156061572,
947
+ "grad_norm": 0.7178171873092651,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.201,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.019774540279390285,
954
+ "grad_norm": 0.6753542423248291,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.0555,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.019924347402719,
961
+ "grad_norm": 0.8013312220573425,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.3032,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.020074154526047713,
968
+ "grad_norm": 0.7693833112716675,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.1242,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.020223961649376426,
975
+ "grad_norm": 0.7697752714157104,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.2202,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.020373768772705143,
982
+ "grad_norm": 0.8076735138893127,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.17,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.020523575896033857,
989
+ "grad_norm": 0.8046029210090637,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3088,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02067338301936257,
996
+ "grad_norm": 0.7976809740066528,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0482,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.020823190142691284,
1003
+ "grad_norm": 1.0324242115020752,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2284,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.020972997266019998,
1010
+ "grad_norm": 0.7962802648544312,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0574,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.021122804389348715,
1017
+ "grad_norm": 0.8662652969360352,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.056,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.02127261151267743,
1024
+ "grad_norm": 0.9411537051200867,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1197,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.021422418636006142,
1031
+ "grad_norm": 1.092484712600708,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1818,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.021572225759334856,
1038
+ "grad_norm": 1.1731982231140137,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.3829,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.02172203288266357,
1045
+ "grad_norm": 1.1861002445220947,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.1755,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.021871840005992287,
1052
+ "grad_norm": 1.315170168876648,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2864,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.022021647129321,
1059
+ "grad_norm": 1.6993236541748047,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.5576,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.022171454252649714,
1066
+ "grad_norm": 1.9727485179901123,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.328,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.022321261375978427,
1073
+ "grad_norm": 2.5295138359069824,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.2508,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02247106849930714,
1080
+ "grad_norm": 2.519742012023926,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.3669,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02247106849930714,
1087
+ "eval_loss": 1.2603070735931396,
1088
+ "eval_runtime": 211.8995,
1089
+ "eval_samples_per_second": 53.058,
1090
+ "eval_steps_per_second": 13.266,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.2500820333428736e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null