aleegis10 commited on
Commit
39d1270
·
verified ·
1 Parent(s): 0391c16

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 sha256:1762253dbc5829143584e781af42cb77e41dffd5bebc2f928c14dbcd6f40905b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50bcda856085f4e710d6bf690b5fda46bbe08019e097e238524a9bd10fe8f54
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f50ac88136876975b6e6381984e4f50d8045a84c0a0ae0f3115759b3f4b794d7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:176df30af802762289475142e7a9c5379fa9f5d8a98f53b429f1972819328cb2
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:745a2178d0767f8ce2c265c23a8fd76e10661259a4699dadd144e83455012827
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bdc864c48c6ab1abb677b54b39c4da5cbd47326e8d1b102b925e36369ba3c4
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": 1.3837385177612305,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.17101325352714836,
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": 13.872,
732
  "eval_steps_per_second": 3.479,
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": 1.2809289693832397,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.25651988029072254,
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": 13.872,
732
  "eval_steps_per_second": 3.479,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.17272338606241983,
737
+ "grad_norm": 6.1180596351623535,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 4.1311,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.17443351859769132,
744
+ "grad_norm": 6.361010551452637,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 4.5486,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.1761436511329628,
751
+ "grad_norm": 6.283280372619629,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 4.9742,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1778537836682343,
758
+ "grad_norm": 5.876176357269287,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 4.9586,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.17956391620350576,
765
+ "grad_norm": 5.371125221252441,
766
+ "learning_rate": 5e-05,
767
+ "loss": 4.7882,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.18127404873877725,
772
+ "grad_norm": 5.151697158813477,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 4.9775,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.18298418127404875,
779
+ "grad_norm": 5.419619560241699,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 5.2023,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.18469431380932022,
786
+ "grad_norm": 5.808403491973877,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 5.1266,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.18640444634459172,
793
+ "grad_norm": 5.708106517791748,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 4.7815,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1881145788798632,
800
+ "grad_norm": 5.750987529754639,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 5.1993,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.18982471141513468,
807
+ "grad_norm": 5.842879772186279,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 5.0834,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.19153484395040615,
814
+ "grad_norm": 5.688647747039795,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 5.1542,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.19324497648567765,
821
+ "grad_norm": 6.085207939147949,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 5.3708,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.19495510902094912,
828
+ "grad_norm": 5.445624351501465,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 4.8629,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.19666524155622062,
835
+ "grad_norm": 5.688288688659668,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 4.9789,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.19837537409149208,
842
+ "grad_norm": 6.147029399871826,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 5.0329,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.20008550662676358,
849
+ "grad_norm": 5.8157196044921875,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 4.9307,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.20179563916203505,
856
+ "grad_norm": 5.963608741760254,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 5.11,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.20350577169730655,
863
+ "grad_norm": 5.836517810821533,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 4.9338,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.20521590423257802,
870
+ "grad_norm": 6.028753280639648,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 5.018,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2069260367678495,
877
+ "grad_norm": 5.885068893432617,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 4.7368,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.20863616930312098,
884
+ "grad_norm": 6.388590335845947,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 5.1395,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.21034630183839248,
891
+ "grad_norm": 6.1952385902404785,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 5.1751,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.21205643437366395,
898
+ "grad_norm": 6.2135443687438965,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 5.012,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.21376656690893545,
905
+ "grad_norm": 6.214436054229736,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 5.0691,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.21547669944420692,
912
+ "grad_norm": 6.635720252990723,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 5.3663,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2171868319794784,
919
+ "grad_norm": 6.239476203918457,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 5.0767,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.21889696451474988,
926
+ "grad_norm": 6.299355983734131,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 5.2056,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.22060709705002138,
933
+ "grad_norm": 6.062747955322266,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 4.7423,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.22231722958529285,
940
+ "grad_norm": 6.572103023529053,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 5.1702,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.22402736212056434,
947
+ "grad_norm": 6.492870330810547,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 5.5961,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.22573749465583584,
954
+ "grad_norm": 6.8842997550964355,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 5.5233,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2274476271911073,
961
+ "grad_norm": 6.2079973220825195,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 4.9688,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2291577597263788,
968
+ "grad_norm": 6.081884384155273,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 5.1224,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.23086789226165028,
975
+ "grad_norm": 6.672243595123291,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 5.1432,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.23257802479692177,
982
+ "grad_norm": 6.71869421005249,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 5.3586,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.23428815733219324,
989
+ "grad_norm": 6.9483537673950195,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 5.4318,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.23599828986746474,
996
+ "grad_norm": 6.899090766906738,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 5.2644,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.2377084224027362,
1003
+ "grad_norm": 7.219109535217285,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 5.4093,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.2394185549380077,
1010
+ "grad_norm": 7.686084270477295,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 5.2123,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.24112868747327917,
1017
+ "grad_norm": 6.914151668548584,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 5.3619,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.24283882000855067,
1024
+ "grad_norm": 7.846366882324219,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 5.3426,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.24454895254382214,
1031
+ "grad_norm": 7.538131237030029,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 5.6459,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.24625908507909364,
1038
+ "grad_norm": 7.204062461853027,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 5.6492,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2479692176143651,
1045
+ "grad_norm": 7.883687496185303,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 5.4739,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2496793501496366,
1052
+ "grad_norm": 7.9401350021362305,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 5.3524,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.25138948268490807,
1059
+ "grad_norm": 7.743297100067139,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 5.1239,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.25309961522017954,
1066
+ "grad_norm": 8.06339168548584,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 5.6102,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.25480974775545107,
1073
+ "grad_norm": 8.759541511535645,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 6.1376,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.25651988029072254,
1080
+ "grad_norm": 11.883188247680664,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 6.0998,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.25651988029072254,
1087
+ "eval_loss": 1.2809289693832397,
1088
+ "eval_runtime": 71.0145,
1089
+ "eval_samples_per_second": 13.87,
1090
+ "eval_steps_per_second": 3.478,
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