seblaku commited on
Commit
6d5550a
·
verified ·
1 Parent(s): 09b4544

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:a34b96ef6821c2aba37f0b7e7d3544cfcd17716e19f7948949c25b36cb09d12e
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b063d903c804c01f64bca9126671bbb625e3046d5b6e17bcee2f8191400f1998
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b6f1967f2fe0b0678f79cea9da5e2b31ad6646b04fc050d78631852945cb237
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9e02ce501a745ffccad238bd51cf347543942bfe0201f9c287a591c77c9bbb
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8675407fd29dbe32dfcf05c36d2ba44f8620592b71d6825976a4f1866de42cf1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36badd60a03c2fb3ef43bb07f50ebcd87e9d61cb55565df5d8cafbe0f9fb4b8b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2481782945fd527fd68f03d6ecc086ae38c0c705bfbe5de3172ab751f2e6c8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6405f9fabb3d2e45adcc13758e2849ef278b423e1ee939354d45ffa4e9327204
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1675224304199219,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.011156667503416729,
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": 12.715,
732
  "eval_steps_per_second": 3.179,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5424551342676378e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1231499910354614,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.016735001255125094,
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": 12.715,
732
  "eval_steps_per_second": 3.179,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.011268234178450897,
737
+ "grad_norm": 1.03377366065979,
738
+ "learning_rate": 4.264362337302798e-05,
739
+ "loss": 1.4868,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.011379800853485065,
744
+ "grad_norm": 0.9007754325866699,
745
+ "learning_rate": 4.1983350186928894e-05,
746
+ "loss": 1.5376,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01149136752851923,
751
+ "grad_norm": 0.8353412747383118,
752
+ "learning_rate": 4.132253477269233e-05,
753
+ "loss": 1.3117,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.011602934203553399,
758
+ "grad_norm": 0.9711883068084717,
759
+ "learning_rate": 4.0661357790654345e-05,
760
+ "loss": 1.1541,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.011714500878587567,
765
+ "grad_norm": 0.7863988280296326,
766
+ "learning_rate": 4e-05,
767
+ "loss": 1.2769,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.011826067553621733,
772
+ "grad_norm": 0.8335726857185364,
773
+ "learning_rate": 3.933864220934566e-05,
774
+ "loss": 1.156,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0119376342286559,
779
+ "grad_norm": 0.7659847736358643,
780
+ "learning_rate": 3.8677465227307676e-05,
781
+ "loss": 1.2839,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.012049200903690068,
786
+ "grad_norm": 0.8807960152626038,
787
+ "learning_rate": 3.8016649813071106e-05,
788
+ "loss": 1.322,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.012160767578724235,
793
+ "grad_norm": 0.8528708219528198,
794
+ "learning_rate": 3.735637662697203e-05,
795
+ "loss": 1.1657,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.012272334253758403,
800
+ "grad_norm": 0.8083069324493408,
801
+ "learning_rate": 3.669682618110671e-05,
802
+ "loss": 1.2175,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.01238390092879257,
807
+ "grad_norm": 0.7970200777053833,
808
+ "learning_rate": 3.6038178789981494e-05,
809
+ "loss": 1.1687,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.012495467603826737,
814
+ "grad_norm": 0.7781988382339478,
815
+ "learning_rate": 3.538061452121656e-05,
816
+ "loss": 1.136,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.012607034278860904,
821
+ "grad_norm": 0.8137642741203308,
822
+ "learning_rate": 3.472431314631724e-05,
823
+ "loss": 1.2012,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.012718600953895072,
828
+ "grad_norm": 0.8913825154304504,
829
+ "learning_rate": 3.406945409152632e-05,
830
+ "loss": 1.1926,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.012830167628929239,
835
+ "grad_norm": 0.8783978819847107,
836
+ "learning_rate": 3.341621638877064e-05,
837
+ "loss": 1.188,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.012941734303963406,
842
+ "grad_norm": 0.8640679121017456,
843
+ "learning_rate": 3.276477862671562e-05,
844
+ "loss": 1.0542,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.013053300978997573,
849
+ "grad_norm": 0.8714284300804138,
850
+ "learning_rate": 3.21153189019408e-05,
851
+ "loss": 1.2211,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.01316486765403174,
856
+ "grad_norm": 0.8280481696128845,
857
+ "learning_rate": 3.146801477025013e-05,
858
+ "loss": 1.0808,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.013276434329065908,
863
+ "grad_norm": 0.8297896385192871,
864
+ "learning_rate": 3.082304319812994e-05,
865
+ "loss": 1.1227,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.013388001004100075,
870
+ "grad_norm": 0.8418503403663635,
871
+ "learning_rate": 3.0180580514368037e-05,
872
+ "loss": 1.2152,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.013499567679134242,
877
+ "grad_norm": 0.7824004292488098,
878
+ "learning_rate": 2.9540802361847212e-05,
879
+ "loss": 1.1229,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01361113435416841,
884
+ "grad_norm": 0.8189719915390015,
885
+ "learning_rate": 2.890388364952623e-05,
886
+ "loss": 1.1421,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.013722701029202576,
891
+ "grad_norm": 0.8146119713783264,
892
+ "learning_rate": 2.8269998504621416e-05,
893
+ "loss": 1.0736,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.013834267704236744,
898
+ "grad_norm": 1.066524863243103,
899
+ "learning_rate": 2.7639320225002108e-05,
900
+ "loss": 1.2977,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.013945834379270912,
905
+ "grad_norm": 0.8084144592285156,
906
+ "learning_rate": 2.7012021231812666e-05,
907
+ "loss": 1.201,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.014057401054305078,
912
+ "grad_norm": 0.8299919962882996,
913
+ "learning_rate": 2.638827302233428e-05,
914
+ "loss": 1.1345,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.014168967729339246,
919
+ "grad_norm": 0.8451680541038513,
920
+ "learning_rate": 2.576824612309934e-05,
921
+ "loss": 1.2455,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.014280534404373414,
926
+ "grad_norm": 0.9045851826667786,
927
+ "learning_rate": 2.5152110043271166e-05,
928
+ "loss": 1.2498,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.01439210107940758,
933
+ "grad_norm": 0.9111452698707581,
934
+ "learning_rate": 2.454003322830192e-05,
935
+ "loss": 1.1584,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.014503667754441748,
940
+ "grad_norm": 0.8999844789505005,
941
+ "learning_rate": 2.393218301388123e-05,
942
+ "loss": 1.0248,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.014615234429475916,
947
+ "grad_norm": 1.1039999723434448,
948
+ "learning_rate": 2.3328725580188395e-05,
949
+ "loss": 1.1425,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.014726801104510082,
954
+ "grad_norm": 0.85543292760849,
955
+ "learning_rate": 2.272982590646029e-05,
956
+ "loss": 1.1249,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.01483836777954425,
961
+ "grad_norm": 0.9125653505325317,
962
+ "learning_rate": 2.2135647725887744e-05,
963
+ "loss": 1.0836,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.014949934454578418,
968
+ "grad_norm": 0.9096406698226929,
969
+ "learning_rate": 2.1546353480852495e-05,
970
+ "loss": 1.1764,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.015061501129612584,
975
+ "grad_norm": 0.897408664226532,
976
+ "learning_rate": 2.096210427851706e-05,
977
+ "loss": 1.0352,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.015173067804646752,
982
+ "grad_norm": 1.038303017616272,
983
+ "learning_rate": 2.038305984677969e-05,
984
+ "loss": 1.1442,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.01528463447968092,
989
+ "grad_norm": 0.9297472834587097,
990
+ "learning_rate": 1.9809378490606264e-05,
991
+ "loss": 1.0321,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.015396201154715086,
996
+ "grad_norm": 0.9409924745559692,
997
+ "learning_rate": 1.9241217048751406e-05,
998
+ "loss": 1.0004,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.015507767829749254,
1003
+ "grad_norm": 0.9569453597068787,
1004
+ "learning_rate": 1.867873085088026e-05,
1005
+ "loss": 0.9474,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.015619334504783422,
1010
+ "grad_norm": 1.0429985523223877,
1011
+ "learning_rate": 1.8122073675102935e-05,
1012
+ "loss": 1.0308,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01573090117981759,
1017
+ "grad_norm": 1.1001777648925781,
1018
+ "learning_rate": 1.75713977059331e-05,
1019
+ "loss": 1.013,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.015842467854851754,
1024
+ "grad_norm": 1.0191009044647217,
1025
+ "learning_rate": 1.702685349268226e-05,
1026
+ "loss": 0.9944,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.015954034529885922,
1031
+ "grad_norm": 1.0639243125915527,
1032
+ "learning_rate": 1.648858990830108e-05,
1033
+ "loss": 1.1787,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.01606560120492009,
1038
+ "grad_norm": 0.9979782104492188,
1039
+ "learning_rate": 1.5956754108678996e-05,
1040
+ "loss": 1.046,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.016177167879954258,
1045
+ "grad_norm": 1.1500177383422852,
1046
+ "learning_rate": 1.5431491492413288e-05,
1047
+ "loss": 1.0585,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.016288734554988426,
1052
+ "grad_norm": 1.1362090110778809,
1053
+ "learning_rate": 1.491294566105852e-05,
1054
+ "loss": 1.1034,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.016400301230022594,
1059
+ "grad_norm": 1.2018383741378784,
1060
+ "learning_rate": 1.4401258379867335e-05,
1061
+ "loss": 1.0853,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.016511867905056758,
1066
+ "grad_norm": 1.182171106338501,
1067
+ "learning_rate": 1.3896569539033253e-05,
1068
+ "loss": 1.1379,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.016623434580090926,
1073
+ "grad_norm": 1.328808307647705,
1074
+ "learning_rate": 1.3399017115446067e-05,
1075
+ "loss": 1.0739,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.016735001255125094,
1080
+ "grad_norm": 1.5698626041412354,
1081
+ "learning_rate": 1.2908737134970367e-05,
1082
+ "loss": 1.1242,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.016735001255125094,
1087
+ "eval_loss": 1.1231499910354614,
1088
+ "eval_runtime": 1182.7105,
1089
+ "eval_samples_per_second": 12.765,
1090
+ "eval_steps_per_second": 3.192,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.315568343374889e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null