auxyus commited on
Commit
2b604be
·
verified ·
1 Parent(s): 465b9f0

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 sha256:400c4b91687b8312187d094dc9019ee5fe643ec96ee0247cb2ae0aa320ba4fde
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09e39462ebc9e76b95c6f50a225adf1de70de7fd436b879acdbe2b5603b6daf
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:372dbd0dccb840394bd2297197e472ea9333926d64ca61bc22f9249dc22a8c31
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a63e1ab7b413c89b4ce62156697a2be7883f4dd58f931c6ccb27fdf373bee87
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eae74b89a782002529a8d6b196e29bf77599aee309927180f5c7243a32b8ae49
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84a411ea6ca5721bd25f640593581966a26557b79f5240093ab55ce6cbfaf960
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": 0.26430198550224304,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.024093482712926155,
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": 13.69,
732
  "eval_steps_per_second": 3.424,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.3429000793751552e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.2537326514720917,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.03614022406938923,
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": 13.69,
732
  "eval_steps_per_second": 3.424,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.024334417540055414,
737
+ "grad_norm": 1.290234923362732,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.5726,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.024575352367184677,
744
+ "grad_norm": 0.45329946279525757,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.2452,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02481628719431394,
751
+ "grad_norm": 0.24364599585533142,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.2485,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0250572220214432,
758
+ "grad_norm": 0.327094167470932,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2375,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.02529815684857246,
765
+ "grad_norm": 0.3715580701828003,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2613,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.025539091675701724,
772
+ "grad_norm": 0.28282630443573,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.2301,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.025780026502830983,
779
+ "grad_norm": 0.49798956513404846,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.2461,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.026020961329960245,
786
+ "grad_norm": 0.48084595799446106,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.2691,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.026261896157089508,
793
+ "grad_norm": 0.3514276146888733,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.1864,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.02650283098421877,
800
+ "grad_norm": 0.41042467951774597,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.2592,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.02674376581134803,
807
+ "grad_norm": 0.3872998356819153,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.1788,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.026984700638477292,
814
+ "grad_norm": 0.608724057674408,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2868,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.027225635465606555,
821
+ "grad_norm": 0.4436226785182953,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.2693,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.027466570292735814,
828
+ "grad_norm": 0.4061850309371948,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.2495,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.027707505119865077,
835
+ "grad_norm": 0.4942147135734558,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.2648,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.02794843994699434,
842
+ "grad_norm": 0.34462204575538635,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2915,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.028189374774123598,
849
+ "grad_norm": 0.28052186965942383,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.2219,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.02843030960125286,
856
+ "grad_norm": 0.43760791420936584,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.2565,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.028671244428382123,
863
+ "grad_norm": 0.3319215178489685,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2432,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.028912179255511383,
870
+ "grad_norm": 0.4012322723865509,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.2829,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.029153114082640645,
877
+ "grad_norm": 0.38858529925346375,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.2454,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.029394048909769908,
884
+ "grad_norm": 0.48614102602005005,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.2771,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.02963498373689917,
891
+ "grad_norm": 0.42235130071640015,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.2195,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02987591856402843,
898
+ "grad_norm": 0.44765040278434753,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.2445,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.030116853391157692,
905
+ "grad_norm": 0.37631118297576904,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.2543,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.030357788218286955,
912
+ "grad_norm": 0.32950347661972046,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.2062,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.030598723045416214,
919
+ "grad_norm": 0.3097626268863678,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2535,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.030839657872545476,
926
+ "grad_norm": 0.2358478158712387,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.2372,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03108059269967474,
933
+ "grad_norm": 0.297639936208725,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.2487,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.031321527526804,
940
+ "grad_norm": 0.36787149310112,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.286,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.031562462353933264,
947
+ "grad_norm": 0.4113162159919739,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.23,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03180339718106252,
954
+ "grad_norm": 0.3847804367542267,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.2484,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03204433200819178,
961
+ "grad_norm": 0.4859013259410858,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.2798,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.03228526683532105,
968
+ "grad_norm": 0.4559577405452728,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.297,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.03252620166245031,
975
+ "grad_norm": 0.3224296271800995,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.2755,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03276713648957957,
982
+ "grad_norm": 0.3775584101676941,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.2777,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03300807131670883,
989
+ "grad_norm": 0.4507180154323578,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.2451,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03324900614383809,
996
+ "grad_norm": 0.31897252798080444,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.2243,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.03348994097096735,
1003
+ "grad_norm": 0.32704704999923706,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.2427,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.03373087579809662,
1010
+ "grad_norm": 0.4815594553947449,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2677,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.033971810625225876,
1017
+ "grad_norm": 0.47970694303512573,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.2616,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.034212745452355135,
1024
+ "grad_norm": 0.3669702708721161,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.2284,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0344536802794844,
1031
+ "grad_norm": 0.40922677516937256,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2523,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.03469461510661366,
1038
+ "grad_norm": 0.4762136936187744,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2084,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.03493554993374292,
1045
+ "grad_norm": 0.3162444531917572,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2679,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.035176484760872186,
1052
+ "grad_norm": 0.2927365005016327,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.2542,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.035417419588001445,
1059
+ "grad_norm": 0.264660120010376,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2465,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.035658354415130704,
1066
+ "grad_norm": 0.2650972306728363,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.2268,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.03589928924225997,
1073
+ "grad_norm": 0.46045494079589844,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.2513,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.03614022406938923,
1080
+ "grad_norm": 0.6368746757507324,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.2629,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.03614022406938923,
1087
+ "eval_loss": 0.2537326514720917,
1088
+ "eval_runtime": 511.6054,
1089
+ "eval_samples_per_second": 13.663,
1090
+ "eval_steps_per_second": 3.417,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.012692217730171e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null