prxy5607 commited on
Commit
31410ea
·
verified ·
1 Parent(s): 6535c1a

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 sha256:0866b0718ac5f568089e57be66e100c3130e11978f3b12a029a7b68c5a5ccede
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69299de52a199e8d0fc70b37a4d296523551085a2eedf954fb6b2469bb810d8
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3b82b43ef0af7db935769ed3301b8cf121529a7cd3663da2bcbc8082d0623d1
3
  size 778374186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea71bdd35adf7e3c1aa85e0a81ec3326838f07fa1ca02970d5503c83f7538d10
3
  size 778374186
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771c75945d7b61f9bd5b7f6677420c61a6e339b42a93da85745b20c97ed87696
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910329f4af2786e906d2233e7cacd633f0390febfd2b34b889f3de9e03110459
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1527422666549683,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.005614901949774702,
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": 14.216,
732
  "eval_steps_per_second": 7.108,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.73309481648128e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1007310152053833,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.008422352924662053,
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": 14.216,
732
  "eval_steps_per_second": 7.108,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.005671050969272449,
737
+ "grad_norm": 0.9625142216682434,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 1.2661,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0057271999887701965,
744
+ "grad_norm": 0.8259492516517639,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 1.183,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.005783349008267943,
751
+ "grad_norm": 0.7474063038825989,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 1.1909,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.00583949802776569,
758
+ "grad_norm": 0.6665073037147522,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 1.1906,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0058956470472634375,
765
+ "grad_norm": 0.5617001056671143,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 1.1469,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.005951796066761184,
772
+ "grad_norm": 0.5758078694343567,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 1.1253,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.006007945086258931,
779
+ "grad_norm": 0.5974460244178772,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 1.2063,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0060640941057566785,
786
+ "grad_norm": 0.5717722773551941,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 1.1057,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.006120243125254425,
793
+ "grad_norm": 0.5892115831375122,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 1.1582,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.006176392144752172,
800
+ "grad_norm": 0.6166552901268005,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 1.1201,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0062325411642499195,
807
+ "grad_norm": 0.6164728403091431,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 1.0756,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.006288690183747666,
814
+ "grad_norm": 0.6641255021095276,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 1.2174,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.006344839203245413,
821
+ "grad_norm": 0.6208594441413879,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 1.146,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0064009882227431605,
828
+ "grad_norm": 0.6231671571731567,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 1.1246,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.006457137242240907,
835
+ "grad_norm": 0.6354531049728394,
836
+ "learning_rate": 5e-05,
837
+ "loss": 1.1637,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.006513286261738654,
842
+ "grad_norm": 0.6056180596351624,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 1.1256,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0065694352812364016,
849
+ "grad_norm": 0.5787081718444824,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 1.0863,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.006625584300734149,
856
+ "grad_norm": 0.5680846571922302,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 1.0733,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.006681733320231895,
863
+ "grad_norm": 0.5850681066513062,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 1.0659,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.006737882339729643,
870
+ "grad_norm": 0.5893137454986572,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 1.0891,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.00679403135922739,
877
+ "grad_norm": 0.5821502208709717,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 1.1219,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.006850180378725136,
884
+ "grad_norm": 0.5872424244880676,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 1.1541,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.006906329398222884,
891
+ "grad_norm": 0.6106603741645813,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 1.153,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.006962478417720631,
898
+ "grad_norm": 0.5763170123100281,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 1.049,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.007018627437218377,
905
+ "grad_norm": 0.5933642387390137,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 1.102,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.007074776456716125,
912
+ "grad_norm": 0.6378093361854553,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 1.1363,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.007130925476213872,
919
+ "grad_norm": 0.6463841199874878,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 1.1423,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.007187074495711618,
926
+ "grad_norm": 0.6380355954170227,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 1.1044,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.007243223515209366,
933
+ "grad_norm": 0.610107421875,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 1.1541,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.007299372534707113,
940
+ "grad_norm": 0.6335543990135193,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 1.0622,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.007355521554204859,
947
+ "grad_norm": 0.6455392837524414,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 1.1027,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.007411670573702607,
954
+ "grad_norm": 0.6415156126022339,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 1.0584,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.007467819593200354,
961
+ "grad_norm": 0.6462504863739014,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 1.002,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0075239686126981,
968
+ "grad_norm": 0.6440901756286621,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 1.0837,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.007580117632195848,
975
+ "grad_norm": 0.6546915173530579,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 1.1001,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.007636266651693595,
982
+ "grad_norm": 0.6541869044303894,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 1.0195,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.007692415671191341,
989
+ "grad_norm": 0.6587697267532349,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 0.999,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.007748564690689089,
996
+ "grad_norm": 0.6729567646980286,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 1.1028,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.007804713710186836,
1003
+ "grad_norm": 0.6894831657409668,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 1.2005,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.007860862729684583,
1010
+ "grad_norm": 0.6334856748580933,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 1.02,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.00791701174918233,
1017
+ "grad_norm": 0.7342789173126221,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 1.1491,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.007973160768680076,
1024
+ "grad_norm": 0.6831063628196716,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 1.1042,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.008029309788177823,
1031
+ "grad_norm": 0.7168252468109131,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 1.0282,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.00808545880767557,
1038
+ "grad_norm": 0.7018248438835144,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 1.0509,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.008141607827173318,
1045
+ "grad_norm": 0.7139812111854553,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 1.0501,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.008197756846671065,
1052
+ "grad_norm": 0.704173743724823,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 1.0048,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.008253905866168813,
1059
+ "grad_norm": 0.7042719721794128,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 0.9387,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.008310054885666558,
1066
+ "grad_norm": 0.7368987798690796,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 0.8796,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.008366203905164305,
1073
+ "grad_norm": 0.711969792842865,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 0.9497,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.008422352924662053,
1080
+ "grad_norm": 0.8901267647743225,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 0.8115,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.008422352924662053,
1087
+ "eval_loss": 1.1007310152053833,
1088
+ "eval_runtime": 2113.3876,
1089
+ "eval_samples_per_second": 14.193,
1090
+ "eval_steps_per_second": 7.097,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.59964222472192e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null