nttx commited on
Commit
ba9a742
·
verified ·
1 Parent(s): 990e0f5

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 sha256:63303b71e5d312d2644b2da9490486b4efc29510df35aca1172c5a8c1a23f988
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273156a339051f3bd8790c239aa0cfd2fb4438d64a253b1aac8a59d485eab496
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:488609b0ab4180cbb26f0114c39b3ea751b0ac1f3ea8004801d22047c0e3c9dd
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bee53dcc5e8d9a72e64b7dbdb7a36a054b18e80e71913d20bb382caa0eefa44
3
  size 443280340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd23bfead1e29533b5da69cff0304a9ddd119a6d662e90bbef7e9b33dcf44989
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adecaf62cda8679ebf3e47a3bfe28e39c490c00b82bf530e74a8fa2d23a6c809
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": 0.15341179072856903,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.17006802721088435,
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": 9.834,
732
  "eval_steps_per_second": 2.464,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.84380938187178e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1450488567352295,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.25510204081632654,
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": 9.834,
732
  "eval_steps_per_second": 2.464,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1717687074829932,
737
+ "grad_norm": 0.13426078855991364,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.1057,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.17346938775510204,
744
+ "grad_norm": 0.1581740826368332,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.119,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.17517006802721088,
751
+ "grad_norm": 0.16823437809944153,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.1664,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.17687074829931973,
758
+ "grad_norm": 0.14816226065158844,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.0938,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.17857142857142858,
765
+ "grad_norm": 0.1594924032688141,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.1025,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.18027210884353742,
772
+ "grad_norm": 0.15495480597019196,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.1087,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.18197278911564627,
779
+ "grad_norm": 0.12521763145923615,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.0894,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.1836734693877551,
786
+ "grad_norm": 0.12601736187934875,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.0808,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.18537414965986396,
793
+ "grad_norm": 0.18192654848098755,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.1155,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.1870748299319728,
800
+ "grad_norm": 0.14074137806892395,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.0929,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.18877551020408162,
807
+ "grad_norm": 0.19746126234531403,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.1248,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.19047619047619047,
814
+ "grad_norm": 0.1834673285484314,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.1183,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.1921768707482993,
821
+ "grad_norm": 0.20125111937522888,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.1176,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.19387755102040816,
828
+ "grad_norm": 0.2673965096473694,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.1593,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.195578231292517,
835
+ "grad_norm": 0.18478697538375854,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.114,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.19727891156462585,
842
+ "grad_norm": 0.2274971902370453,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.1161,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.1989795918367347,
849
+ "grad_norm": 0.20548267662525177,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.1303,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.20068027210884354,
856
+ "grad_norm": 0.2045164704322815,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.1169,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.20238095238095238,
863
+ "grad_norm": 0.21133384108543396,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.107,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.20408163265306123,
870
+ "grad_norm": 0.23106807470321655,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.1418,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.20578231292517007,
877
+ "grad_norm": 0.27285704016685486,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.1784,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.20748299319727892,
884
+ "grad_norm": 0.2039409875869751,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.1132,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.20918367346938777,
891
+ "grad_norm": 0.26123031973838806,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.1673,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2108843537414966,
898
+ "grad_norm": 0.2377399057149887,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.1207,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.21258503401360543,
905
+ "grad_norm": 0.3176490366458893,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.2086,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.21428571428571427,
912
+ "grad_norm": 0.3887050449848175,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.1304,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.21598639455782312,
919
+ "grad_norm": 0.33405062556266785,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.2149,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.21768707482993196,
926
+ "grad_norm": 0.2403564751148224,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.1357,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.2193877551020408,
933
+ "grad_norm": 0.29959097504615784,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1783,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.22108843537414966,
940
+ "grad_norm": 0.28348225355148315,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.157,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.2227891156462585,
947
+ "grad_norm": 0.4001818895339966,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.2555,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.22448979591836735,
954
+ "grad_norm": 0.33200711011886597,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.1585,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2261904761904762,
961
+ "grad_norm": 0.5564277768135071,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.1547,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.22789115646258504,
968
+ "grad_norm": 0.2881430685520172,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.126,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.22959183673469388,
975
+ "grad_norm": 0.3916719853878021,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.1664,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.23129251700680273,
982
+ "grad_norm": 0.35243332386016846,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.1547,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.23299319727891157,
989
+ "grad_norm": 0.28927794098854065,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.1258,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.23469387755102042,
996
+ "grad_norm": 0.3159042000770569,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.1418,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.23639455782312926,
1003
+ "grad_norm": 0.35158154368400574,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.1515,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.23809523809523808,
1010
+ "grad_norm": 0.4585651755332947,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2258,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.23979591836734693,
1017
+ "grad_norm": 0.39558088779449463,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.1377,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.24149659863945577,
1024
+ "grad_norm": 0.35692715644836426,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.1466,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.24319727891156462,
1031
+ "grad_norm": 0.47575652599334717,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.2366,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.24489795918367346,
1038
+ "grad_norm": 0.5705416202545166,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.3062,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2465986394557823,
1045
+ "grad_norm": 0.42908549308776855,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.1863,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.24829931972789115,
1052
+ "grad_norm": 0.5684940814971924,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.1986,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.25,
1059
+ "grad_norm": 0.5118395090103149,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.226,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.25170068027210885,
1066
+ "grad_norm": 0.5201008915901184,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.164,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2534013605442177,
1073
+ "grad_norm": 1.024444341659546,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.1797,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.25510204081632654,
1080
+ "grad_norm": 1.1646174192428589,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.2457,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.25510204081632654,
1087
+ "eval_loss": 0.1450488567352295,
1088
+ "eval_runtime": 100.2405,
1089
+ "eval_samples_per_second": 9.876,
1090
+ "eval_steps_per_second": 2.474,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.7635550454284288e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null