aleegis09 commited on
Commit
15847ed
·
verified ·
1 Parent(s): 738199c

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:d10f567bbb63ddd47cf59c313dc0ae77334f8c069b7c7979fc7cfc42bcecfc2d
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b884c4b9eab867b541cdec4f87ff60260540c18b32e16696f51018db269f7905
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1266071fbe679ad71a4c82b8f40880e4b98cd1011e5159bcbace3fafc7f422f0
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f11aaa9448d9667c53a1e45316e864697f08e747a8f623c09e7db03490056b
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0b4d1a2ee5d03be76d3b10c65b9a32350d1482666fb9e2822fca2c1a7b721e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfd09214eeda2ed63d42ad5b04389215489388654a472eef3152ccff4dbe744
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": 11.839821815490723,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11968880909634949,
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": 102.676,
732
  "eval_steps_per_second": 25.669,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 110179123200000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.837847709655762,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.17953321364452424,
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": 102.676,
732
  "eval_steps_per_second": 25.669,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.12088569718731298,
737
+ "grad_norm": 0.22857844829559326,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.8506,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.12208258527827648,
744
+ "grad_norm": 0.2098807990550995,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.8613,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.12327947336923997,
751
+ "grad_norm": 0.20508608222007751,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.8617,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.12447636146020347,
758
+ "grad_norm": 0.18768347799777985,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.8508,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.12567324955116696,
765
+ "grad_norm": 0.2084583342075348,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.8453,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.12687013764213045,
772
+ "grad_norm": 0.20801976323127747,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.8538,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.12806702573309395,
779
+ "grad_norm": 0.20654766261577606,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.8544,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12926391382405744,
786
+ "grad_norm": 0.20135566592216492,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.8491,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.13046080191502094,
793
+ "grad_norm": 0.21766503155231476,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.8512,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.13165769000598443,
800
+ "grad_norm": 0.16945905983448029,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.846,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.13285457809694792,
807
+ "grad_norm": 0.16909614205360413,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.8481,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.13405146618791142,
814
+ "grad_norm": 0.16841436922550201,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.8541,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.13524835427887494,
821
+ "grad_norm": 0.20279695093631744,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.8404,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.13644524236983843,
828
+ "grad_norm": 0.20776088535785675,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.8373,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.13764213046080193,
835
+ "grad_norm": 0.15437091886997223,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.8563,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.13883901855176542,
842
+ "grad_norm": 0.16326138377189636,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.8576,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1400359066427289,
849
+ "grad_norm": 0.14459194242954254,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.86,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1412327947336924,
856
+ "grad_norm": 0.14986570179462433,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.8407,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.1424296828246559,
863
+ "grad_norm": 0.14605852961540222,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.8525,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.1436265709156194,
870
+ "grad_norm": 0.14993371069431305,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.8518,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1448234590065829,
877
+ "grad_norm": 0.16897639632225037,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.8423,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.14602034709754638,
884
+ "grad_norm": 0.13226987421512604,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.8359,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.14721723518850988,
891
+ "grad_norm": 0.15450699627399445,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.8392,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.14841412327947337,
898
+ "grad_norm": 0.13589896261692047,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.8342,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.14961101137043686,
905
+ "grad_norm": 0.11081069707870483,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.8493,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.15080789946140036,
912
+ "grad_norm": 0.13928134739398956,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.8457,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.15200478755236385,
919
+ "grad_norm": 0.14754924178123474,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.8453,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.15320167564332735,
926
+ "grad_norm": 0.1759936362504959,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.8451,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.15439856373429084,
933
+ "grad_norm": 0.1412981152534485,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.8301,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.15559545182525433,
940
+ "grad_norm": 0.1770344376564026,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.8402,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.15679233991621783,
947
+ "grad_norm": 0.144487664103508,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.8399,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.15798922800718132,
954
+ "grad_norm": 0.17608466744422913,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.8298,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.15918611609814481,
961
+ "grad_norm": 0.1428515911102295,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.8389,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1603830041891083,
968
+ "grad_norm": 0.18620611727237701,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.8435,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1615798922800718,
975
+ "grad_norm": 0.16474278271198273,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.8321,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1627767803710353,
982
+ "grad_norm": 0.18602590262889862,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.8533,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.1639736684619988,
989
+ "grad_norm": 0.18569320440292358,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.8355,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1651705565529623,
996
+ "grad_norm": 0.1410042643547058,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.8213,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.1663674446439258,
1003
+ "grad_norm": 0.19760896265506744,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.8453,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1675643327348893,
1010
+ "grad_norm": 0.1939631849527359,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.8305,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.1687612208258528,
1017
+ "grad_norm": 0.15672041475772858,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.8447,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.1699581089168163,
1024
+ "grad_norm": 0.17223219573497772,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.8332,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.17115499700777978,
1031
+ "grad_norm": 0.2010926455259323,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.843,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.17235188509874327,
1038
+ "grad_norm": 0.2170400470495224,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.834,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.17354877318970677,
1045
+ "grad_norm": 0.20056170225143433,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.8321,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.17474566128067026,
1052
+ "grad_norm": 0.23274922370910645,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.8303,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.17594254937163376,
1059
+ "grad_norm": 0.2670494616031647,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.8408,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.17713943746259725,
1066
+ "grad_norm": 0.26311710476875305,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.8277,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.17833632555356074,
1073
+ "grad_norm": 0.2438398003578186,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.8437,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.17953321364452424,
1080
+ "grad_norm": 0.3382917642593384,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.8317,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.17953321364452424,
1087
+ "eval_loss": 11.837847709655762,
1088
+ "eval_runtime": 13.6567,
1089
+ "eval_samples_per_second": 103.099,
1090
+ "eval_steps_per_second": 25.775,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 165268684800000.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null