auxyus commited on
Commit
70fe641
·
verified ·
1 Parent(s): a7db255

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 sha256:2d63f0d7c840eba396845ec0577f7a1fd2ae734136229ea311925af89faab337
3
  size 479005064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72a2cb67c13f5cd6bb3e41086fbd77ee532416e7619b10fbab62055b734be100
3
  size 479005064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58a527f2612c38f48e6eea7652990c00ff2fca2ab03c854dcef91b9b9cc60b55
3
  size 243802484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39b19704628eb10d36e554c2115d87cb80445c47e4d13d3624f92c089bafb28
3
  size 243802484
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98610abd7b970b886fd1070fadf421e6e462f6197b84dbdc639b6b001043e40a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8686af1e49dc4afeb9f4b5672ad1558024aeb2c7d96a770b708ae170ad1ee6b8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ca67f9a35cd1c50df3d93bedf5a6642db2c7847c021a0a8d3f44c1bf4993d3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4002ee03f4202a6a410bde3375cd186d152ce129e8a177eb112bee1f18b1e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.7260963916778564,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11117287381878821,
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": 21.155,
732
  "eval_steps_per_second": 5.292,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.69083435155456e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5343213081359863,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.16675931072818231,
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": 21.155,
732
  "eval_steps_per_second": 5.292,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.1122846025569761,
737
+ "grad_norm": 5.945138454437256,
738
+ "learning_rate": 8.715724127386972e-05,
739
+ "loss": 3.3042,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.11339633129516398,
744
+ "grad_norm": 5.689327239990234,
745
+ "learning_rate": 8.688653405904652e-05,
746
+ "loss": 3.2821,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.11450806003335186,
751
+ "grad_norm": 5.383906364440918,
752
+ "learning_rate": 8.661343332988869e-05,
753
+ "loss": 3.1464,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.11561978877153975,
758
+ "grad_norm": 3.6286027431488037,
759
+ "learning_rate": 8.633795680751116e-05,
760
+ "loss": 3.0208,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.11673151750972763,
765
+ "grad_norm": 2.5231778621673584,
766
+ "learning_rate": 8.606012236719073e-05,
767
+ "loss": 2.9116,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.1178432462479155,
772
+ "grad_norm": 1.8035188913345337,
773
+ "learning_rate": 8.577994803720606e-05,
774
+ "loss": 2.7812,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.11895497498610338,
779
+ "grad_norm": 1.2647838592529297,
780
+ "learning_rate": 8.549745199766792e-05,
781
+ "loss": 2.5962,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12006670372429128,
786
+ "grad_norm": 1.0100034475326538,
787
+ "learning_rate": 8.521265257933948e-05,
788
+ "loss": 2.5903,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12117843246247915,
793
+ "grad_norm": 1.5505986213684082,
794
+ "learning_rate": 8.492556826244687e-05,
795
+ "loss": 2.4289,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12229016120066703,
800
+ "grad_norm": 2.1767804622650146,
801
+ "learning_rate": 8.463621767547998e-05,
802
+ "loss": 2.5854,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.12340188993885493,
807
+ "grad_norm": 2.0668084621429443,
808
+ "learning_rate": 8.434461959398376e-05,
809
+ "loss": 2.4399,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.1245136186770428,
814
+ "grad_norm": 1.511650562286377,
815
+ "learning_rate": 8.405079293933986e-05,
816
+ "loss": 2.6072,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.12562534741523068,
821
+ "grad_norm": 1.1593494415283203,
822
+ "learning_rate": 8.375475677753881e-05,
823
+ "loss": 2.4045,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.12673707615341856,
828
+ "grad_norm": 1.053107738494873,
829
+ "learning_rate": 8.345653031794292e-05,
830
+ "loss": 2.4522,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.12784880489160644,
835
+ "grad_norm": 0.9937801361083984,
836
+ "learning_rate": 8.315613291203976e-05,
837
+ "loss": 2.3276,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.12896053362979434,
842
+ "grad_norm": 0.8721001744270325,
843
+ "learning_rate": 8.285358405218655e-05,
844
+ "loss": 2.3567,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13007226236798222,
849
+ "grad_norm": 0.9330883026123047,
850
+ "learning_rate": 8.25489033703452e-05,
851
+ "loss": 2.2585,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.1311839911061701,
856
+ "grad_norm": 0.9001569747924805,
857
+ "learning_rate": 8.224211063680853e-05,
858
+ "loss": 2.297,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.13229571984435798,
863
+ "grad_norm": 0.8666402697563171,
864
+ "learning_rate": 8.19332257589174e-05,
865
+ "loss": 2.2182,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.13340744858254586,
870
+ "grad_norm": 1.176416277885437,
871
+ "learning_rate": 8.162226877976887e-05,
872
+ "loss": 2.3346,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.13451917732073373,
877
+ "grad_norm": 0.9645460844039917,
878
+ "learning_rate": 8.130925987691569e-05,
879
+ "loss": 2.0891,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.1356309060589216,
884
+ "grad_norm": 1.3001148700714111,
885
+ "learning_rate": 8.099421936105702e-05,
886
+ "loss": 2.3923,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.13674263479710952,
891
+ "grad_norm": 1.1771594285964966,
892
+ "learning_rate": 8.067716767472045e-05,
893
+ "loss": 2.3808,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1378543635352974,
898
+ "grad_norm": 0.997420608997345,
899
+ "learning_rate": 8.035812539093557e-05,
900
+ "loss": 2.4158,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.13896609227348528,
905
+ "grad_norm": 0.8972210884094238,
906
+ "learning_rate": 8.003711321189895e-05,
907
+ "loss": 2.1985,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14007782101167315,
912
+ "grad_norm": 0.8970302939414978,
913
+ "learning_rate": 7.971415196763088e-05,
914
+ "loss": 1.9446,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.14118954974986103,
919
+ "grad_norm": 1.0234975814819336,
920
+ "learning_rate": 7.938926261462366e-05,
921
+ "loss": 2.2494,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.1423012784880489,
926
+ "grad_norm": 1.1858220100402832,
927
+ "learning_rate": 7.906246623448183e-05,
928
+ "loss": 2.2926,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1434130072262368,
933
+ "grad_norm": 1.04050612449646,
934
+ "learning_rate": 7.873378403255419e-05,
935
+ "loss": 2.3006,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.14452473596442467,
940
+ "grad_norm": 1.20691978931427,
941
+ "learning_rate": 7.840323733655778e-05,
942
+ "loss": 2.3302,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.14563646470261257,
947
+ "grad_norm": 1.0528558492660522,
948
+ "learning_rate": 7.807084759519405e-05,
949
+ "loss": 2.1477,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.14674819344080045,
954
+ "grad_norm": 1.085060954093933,
955
+ "learning_rate": 7.773663637675694e-05,
956
+ "loss": 2.3391,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.14785992217898833,
961
+ "grad_norm": 0.9347543120384216,
962
+ "learning_rate": 7.740062536773352e-05,
963
+ "loss": 2.2107,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.1489716509171762,
968
+ "grad_norm": 1.0611324310302734,
969
+ "learning_rate": 7.706283637139658e-05,
970
+ "loss": 2.2921,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.15008337965536409,
975
+ "grad_norm": 1.1190764904022217,
976
+ "learning_rate": 7.672329130639005e-05,
977
+ "loss": 2.1771,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.15119510839355196,
982
+ "grad_norm": 1.021002173423767,
983
+ "learning_rate": 7.638201220530665e-05,
984
+ "loss": 2.1964,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.15230683713173984,
989
+ "grad_norm": 1.2308954000473022,
990
+ "learning_rate": 7.603902121325813e-05,
991
+ "loss": 2.2279,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.15341856586992775,
996
+ "grad_norm": 1.0030035972595215,
997
+ "learning_rate": 7.569434058643844e-05,
998
+ "loss": 2.1981,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.15453029460811563,
1003
+ "grad_norm": 1.0752218961715698,
1004
+ "learning_rate": 7.534799269067953e-05,
1005
+ "loss": 2.2809,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1556420233463035,
1010
+ "grad_norm": 1.1892122030258179,
1011
+ "learning_rate": 7.500000000000001e-05,
1012
+ "loss": 2.2486,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.15675375208449138,
1017
+ "grad_norm": 1.1939011812210083,
1018
+ "learning_rate": 7.465038509514688e-05,
1019
+ "loss": 2.1895,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.15786548082267926,
1024
+ "grad_norm": 1.430174469947815,
1025
+ "learning_rate": 7.42991706621303e-05,
1026
+ "loss": 2.3485,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.15897720956086714,
1031
+ "grad_norm": 1.1184104681015015,
1032
+ "learning_rate": 7.394637949075154e-05,
1033
+ "loss": 2.2954,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16008893829905502,
1038
+ "grad_norm": 1.0584604740142822,
1039
+ "learning_rate": 7.35920344731241e-05,
1040
+ "loss": 2.0915,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16120066703724292,
1045
+ "grad_norm": 1.1394598484039307,
1046
+ "learning_rate": 7.323615860218843e-05,
1047
+ "loss": 1.9866,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1623123957754308,
1052
+ "grad_norm": 1.3819961547851562,
1053
+ "learning_rate": 7.287877497021978e-05,
1054
+ "loss": 2.229,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.16342412451361868,
1059
+ "grad_norm": 1.717722773551941,
1060
+ "learning_rate": 7.251990676732984e-05,
1061
+ "loss": 2.0977,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.16453585325180656,
1066
+ "grad_norm": 1.206673502922058,
1067
+ "learning_rate": 7.215957727996207e-05,
1068
+ "loss": 2.2358,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.16564758198999444,
1073
+ "grad_norm": 1.5048532485961914,
1074
+ "learning_rate": 7.179780988938051e-05,
1075
+ "loss": 2.2084,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.16675931072818231,
1080
+ "grad_norm": 1.4663426876068115,
1081
+ "learning_rate": 7.143462807015271e-05,
1082
+ "loss": 2.1774,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.16675931072818231,
1087
+ "eval_loss": 2.5343213081359863,
1088
+ "eval_runtime": 71.4182,
1089
+ "eval_samples_per_second": 21.213,
1090
+ "eval_steps_per_second": 5.307,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.53625152733184e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null