aleegis09 commited on
Commit
72deb7b
·
verified ·
1 Parent(s): 6cb19e3

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 sha256:5cbb4a5f515b492e590ae91fec4d1076eb4e88cc36ebd31107a125f52c5dfc60
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e788effba5da71f5987d0f1e62afa342c18c3694c70f6496db41c6ac429fa984
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b65c6bf1320069028e3202b1d832a20e85ea88f2b27f92aed5216ab6b4056cb
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5422b85691c4a14a7810e37864bf44014dc4fcd310e151ce23b16836247b4457
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:aef682007700f94b493da4f62a6fd8f6d1fdb566ca87d0878af153f39652acef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c687e1d9b6b835260f69e5b8582f43840e599a53f43087fd0213ae6d297f05
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": 0.7381904125213623,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006701177731986397,
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": 12.62,
732
  "eval_steps_per_second": 3.155,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.4810846062863974e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6861550807952881,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.010051766597979595,
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": 12.62,
732
  "eval_steps_per_second": 3.155,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.00676818950930626,
737
+ "grad_norm": 3.4336345195770264,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.2992,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.006835201286626125,
744
+ "grad_norm": 2.7011988162994385,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.2436,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.006902213063945988,
751
+ "grad_norm": 2.623509407043457,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.6087,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0069692248412658525,
758
+ "grad_norm": 2.6322193145751953,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.6776,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.007036236618585716,
765
+ "grad_norm": 2.598435878753662,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.4349,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.00710324839590558,
772
+ "grad_norm": 2.986523151397705,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.6434,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.007170260173225445,
779
+ "grad_norm": 2.7807955741882324,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.3435,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.007237271950545308,
786
+ "grad_norm": 3.3481178283691406,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.6426,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.007304283727865173,
793
+ "grad_norm": 3.0154755115509033,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.2395,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.007371295505185036,
800
+ "grad_norm": 3.805389881134033,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.3782,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0074383072825049005,
807
+ "grad_norm": 3.2649686336517334,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.1778,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.007505319059824764,
814
+ "grad_norm": 3.6283347606658936,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.5709,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.007572330837144628,
821
+ "grad_norm": 3.476731777191162,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.5964,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.007639342614464492,
828
+ "grad_norm": 3.379956007003784,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.4988,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.007706354391784356,
835
+ "grad_norm": 3.687070846557617,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.6037,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.00777336616910422,
842
+ "grad_norm": 3.569629192352295,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.33,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.007840377946424084,
849
+ "grad_norm": 3.511577844619751,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.7223,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.007907389723743947,
856
+ "grad_norm": 3.7060160636901855,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.6752,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.007974401501063813,
863
+ "grad_norm": 3.7573060989379883,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.7462,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.008041413278383676,
870
+ "grad_norm": 4.448085784912109,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.836,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00810842505570354,
877
+ "grad_norm": 3.845568895339966,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.4517,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.008175436833023403,
884
+ "grad_norm": 3.9906766414642334,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.8422,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.008242448610343268,
891
+ "grad_norm": 4.061316967010498,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.745,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.008309460387663132,
898
+ "grad_norm": 4.211214065551758,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.57,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.008376472164982995,
905
+ "grad_norm": 4.14617919921875,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.5636,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.008443483942302859,
912
+ "grad_norm": 4.362563133239746,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 3.0273,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.008510495719622724,
919
+ "grad_norm": 4.220723628997803,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.6382,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.008577507496942588,
926
+ "grad_norm": 4.606372356414795,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.8578,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.008644519274262451,
933
+ "grad_norm": 4.473711967468262,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.9329,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.008711531051582316,
940
+ "grad_norm": 4.153161525726318,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.5251,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.00877854282890218,
947
+ "grad_norm": 4.623281002044678,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.7656,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.008845554606222043,
954
+ "grad_norm": 4.800572872161865,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.6164,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.008912566383541907,
961
+ "grad_norm": 5.332072734832764,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.707,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.008979578160861772,
968
+ "grad_norm": 5.535910606384277,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 3.1558,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.009046589938181636,
975
+ "grad_norm": 6.015562057495117,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.7852,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.009113601715501499,
982
+ "grad_norm": 6.302767753601074,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.924,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.009180613492821363,
989
+ "grad_norm": 5.9889817237854,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.9211,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.009247625270141228,
996
+ "grad_norm": 6.719918251037598,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.9759,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.009314637047461091,
1003
+ "grad_norm": 6.2145466804504395,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.76,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.009381648824780955,
1010
+ "grad_norm": 6.185413360595703,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 3.1391,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00944866060210082,
1017
+ "grad_norm": 6.555198669433594,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 3.5508,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.009515672379420683,
1024
+ "grad_norm": 7.662604331970215,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 3.0451,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.009582684156740547,
1031
+ "grad_norm": 7.461409568786621,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 3.3342,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.00964969593406041,
1038
+ "grad_norm": 8.082277297973633,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 3.191,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.009716707711380276,
1045
+ "grad_norm": 8.397353172302246,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.8982,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.00978371948870014,
1052
+ "grad_norm": 8.452592849731445,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 3.6459,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.009850731266020003,
1059
+ "grad_norm": 9.31845760345459,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 3.3051,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.009917743043339866,
1066
+ "grad_norm": 10.629938125610352,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 3.6277,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.009984754820659731,
1073
+ "grad_norm": 11.908143997192383,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 3.9846,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.010051766597979595,
1080
+ "grad_norm": 16.358522415161133,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 3.1578,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.010051766597979595,
1087
+ "eval_loss": 0.6861550807952881,
1088
+ "eval_runtime": 1994.0732,
1089
+ "eval_samples_per_second": 12.604,
1090
+ "eval_steps_per_second": 3.151,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.225204408478597e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null