aleegis09 commited on
Commit
e25a841
·
verified ·
1 Parent(s): 68933fa

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:ab0a8f847a102d1cbeb2bb2f0208f3e2913e214f8de9cfbee0d320fd80707b5e
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82719d41e2aa9154313c600c3f4ec752bc4284c1d4e78a4acd3bf73b58a0f2a
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:470859b3e0bc52894b2df2f9acdd4a055b4559d52973378073f870357dab0337
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6af398678849c2e122af4727788ac2c4387f3d33af1b9dc0f97fbf7d812996
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:d38856484a670052c10e77e89a375e81cc2ac98cf37b4418a70109a779ed76d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc62f5f06de3fbc3099e132f2a14a1a386524767c004af917d9d725405614bc5
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": 11.834319114685059,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01826650835692757,
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": 103.528,
732
  "eval_steps_per_second": 25.882,
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": 11.825672149658203,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02739976253539136,
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": 103.528,
732
  "eval_steps_per_second": 25.882,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01844917344049685,
737
+ "grad_norm": 0.3653700053691864,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 11.8686,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.018631838524066125,
744
+ "grad_norm": 0.3573233485221863,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 11.8757,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0188145036076354,
751
+ "grad_norm": 0.2834525406360626,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 11.866,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.018997168691204675,
758
+ "grad_norm": 0.33954983949661255,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 11.8628,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.019179833774773954,
765
+ "grad_norm": 0.3091084361076355,
766
+ "learning_rate": 5e-05,
767
+ "loss": 11.8581,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.01936249885834323,
772
+ "grad_norm": 0.2740994393825531,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 11.8606,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.019545163941912504,
779
+ "grad_norm": 0.31202438473701477,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 11.8506,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01972782902548178,
786
+ "grad_norm": 0.2627750039100647,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 11.8582,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.019910494109051054,
793
+ "grad_norm": 0.329013466835022,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 11.8586,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.020093159192620332,
800
+ "grad_norm": 0.22419841587543488,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 11.8602,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.020275824276189607,
807
+ "grad_norm": 0.2340073436498642,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 11.8525,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.020458489359758882,
814
+ "grad_norm": 0.31201285123825073,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 11.8318,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.020641154443328157,
821
+ "grad_norm": 0.2925834655761719,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 11.8479,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.020823819526897432,
828
+ "grad_norm": 0.2644873857498169,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 11.847,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.02100648461046671,
835
+ "grad_norm": 0.2717932462692261,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 11.8337,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.021189149694035986,
842
+ "grad_norm": 0.21851548552513123,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 11.8367,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.02137181477760526,
849
+ "grad_norm": 0.2520385682582855,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 11.8478,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.021554479861174536,
856
+ "grad_norm": 0.1869116574525833,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 11.8404,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.02173714494474381,
863
+ "grad_norm": 0.23700135946273804,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 11.8413,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.02191981002831309,
870
+ "grad_norm": 0.22343429923057556,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 11.8336,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.022102475111882364,
877
+ "grad_norm": 0.2725762724876404,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 11.8398,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.02228514019545164,
884
+ "grad_norm": 0.2449876368045807,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 11.8404,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.022467805279020914,
891
+ "grad_norm": 0.29339998960494995,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 11.8229,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02265047036259019,
898
+ "grad_norm": 0.2512277364730835,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 11.8453,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.022833135446159468,
905
+ "grad_norm": 0.2491714209318161,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 11.8227,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.023015800529728743,
912
+ "grad_norm": 0.26697126030921936,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 11.8164,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.023198465613298018,
919
+ "grad_norm": 0.2489868402481079,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 11.8189,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.023381130696867293,
926
+ "grad_norm": 0.25719183683395386,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 11.8267,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.023563795780436568,
933
+ "grad_norm": 0.2649552524089813,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 11.8061,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.023746460864005847,
940
+ "grad_norm": 0.23857741057872772,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 11.8377,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02392912594757512,
947
+ "grad_norm": 0.2775125205516815,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 11.8143,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.024111791031144397,
954
+ "grad_norm": 0.30382922291755676,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 11.8277,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.02429445611471367,
961
+ "grad_norm": 0.32927384972572327,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 11.8087,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.024477121198282947,
968
+ "grad_norm": 0.2699863016605377,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 11.8317,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.024659786281852225,
975
+ "grad_norm": 0.30144500732421875,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 11.8123,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0248424513654215,
982
+ "grad_norm": 0.2767479419708252,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 11.8192,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.025025116448990775,
989
+ "grad_norm": 0.29739877581596375,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 11.8268,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02520778153256005,
996
+ "grad_norm": 0.2872367799282074,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 11.8314,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.025390446616129325,
1003
+ "grad_norm": 0.3332676589488983,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 11.8087,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.025573111699698604,
1010
+ "grad_norm": 0.32409340143203735,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 11.8007,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.02575577678326788,
1017
+ "grad_norm": 0.2905734181404114,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 11.8206,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.025938441866837154,
1024
+ "grad_norm": 0.38151589035987854,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 11.8187,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02612110695040643,
1031
+ "grad_norm": 0.31705883145332336,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 11.8001,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.026303772033975707,
1038
+ "grad_norm": 0.3771505355834961,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 11.8197,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.026486437117544982,
1045
+ "grad_norm": 0.32985883951187134,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 11.8025,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.026669102201114257,
1052
+ "grad_norm": 0.4287067949771881,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 11.819,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.026851767284683532,
1059
+ "grad_norm": 0.43624189496040344,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 11.7785,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.027034432368252807,
1066
+ "grad_norm": 0.5138468146324158,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 11.8001,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.027217097451822086,
1073
+ "grad_norm": 0.5513505935668945,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 11.8046,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02739976253539136,
1080
+ "grad_norm": 0.6666286587715149,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 11.792,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02739976253539136,
1087
+ "eval_loss": 11.825672149658203,
1088
+ "eval_runtime": 89.2187,
1089
+ "eval_samples_per_second": 103.342,
1090
+ "eval_steps_per_second": 25.835,
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