ancient41 commited on
Commit
760ee47
·
verified ·
1 Parent(s): 8501e6a

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 sha256:5e9e0b29aa49cd12c059a86ab501463d99f485c86f2e5c15505ff60405154552
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e95818fa265eda40e6dab4d8706f738c5424efaeec5531bfe8f3cfc26f17d3
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa82ad03d8a61ec6aa42bf250dc2ca68217b2f66dd561edb3054859064d104d6
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e91992dbe31cceb7e607655a759cd8b0c554eceef3f852146825fd8355c7b5d
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36f5627aeacad0e28f0d542e6627763fd8f543ab0421fbbe869c1bbf5e7aa57a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09371f24fa0f914ffd72795a3d3e4385c3a1fba552571d62e73d48e39c5abec
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": 0.6681632995605469,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.11302627860977678,
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": 13.931,
732
  "eval_steps_per_second": 3.487,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.431616484278272e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5321376919746399,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.16953941791466515,
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": 13.931,
732
  "eval_steps_per_second": 3.487,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.11415654139587454,
737
+ "grad_norm": 16.275606155395508,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 2.6182,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.1152868041819723,
744
+ "grad_norm": 4.1765007972717285,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 2.0952,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.11641706696807008,
751
+ "grad_norm": 3.4742538928985596,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 2.2209,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.11754732975416785,
758
+ "grad_norm": 3.0022151470184326,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 2.0823,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.11867759254026561,
765
+ "grad_norm": 2.934873580932617,
766
+ "learning_rate": 5e-05,
767
+ "loss": 2.1102,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.11980785532636339,
772
+ "grad_norm": 2.680055856704712,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 2.1372,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.12093811811246115,
779
+ "grad_norm": 3.125109910964966,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 2.202,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.12206838089855891,
786
+ "grad_norm": 2.8300929069519043,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 2.1718,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.12319864368465669,
793
+ "grad_norm": 2.915879487991333,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 2.2386,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.12432890647075445,
800
+ "grad_norm": 3.2553791999816895,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 2.2011,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.12545916925685222,
807
+ "grad_norm": 2.899535655975342,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 2.2135,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.12658943204294998,
814
+ "grad_norm": 3.284808397293091,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 2.188,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.12771969482904774,
821
+ "grad_norm": 3.352341890335083,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 2.178,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.12884995761514553,
828
+ "grad_norm": 3.7331926822662354,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 2.2221,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.1299802204012433,
835
+ "grad_norm": 3.1759157180786133,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 2.3129,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.13111048318734106,
842
+ "grad_norm": 3.436264991760254,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 2.2705,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.13224074597343882,
849
+ "grad_norm": 3.4234917163848877,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 2.2061,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.13337100875953659,
856
+ "grad_norm": 3.3926892280578613,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 2.1699,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.13450127154563435,
863
+ "grad_norm": 3.6119637489318848,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 2.3081,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.13563153433173214,
870
+ "grad_norm": 3.3186254501342773,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 2.2294,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.1367617971178299,
877
+ "grad_norm": 6.492986679077148,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 2.1599,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.13789205990392767,
884
+ "grad_norm": 6.589293003082275,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 2.1454,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.13902232269002543,
891
+ "grad_norm": 4.570013523101807,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 2.3173,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.1401525854761232,
898
+ "grad_norm": 4.838213920593262,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 2.3184,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.14128284826222096,
905
+ "grad_norm": 4.959200382232666,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 2.5199,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.14241311104831875,
912
+ "grad_norm": 4.407459735870361,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 2.3,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.1435433738344165,
919
+ "grad_norm": 3.736240863800049,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 2.2689,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.14467363662051427,
926
+ "grad_norm": 4.1755499839782715,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 2.2715,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.14580389940661204,
933
+ "grad_norm": 4.146841526031494,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 2.4181,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.1469341621927098,
940
+ "grad_norm": 3.944537878036499,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 2.3404,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.14806442497880756,
947
+ "grad_norm": 4.004812717437744,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 2.3455,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.14919468776490535,
954
+ "grad_norm": 3.948227643966675,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 2.3792,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.15032495055100312,
961
+ "grad_norm": 4.254145622253418,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 2.3458,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.15145521333710088,
968
+ "grad_norm": 4.3584489822387695,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 2.3267,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.15258547612319864,
975
+ "grad_norm": 71.25342559814453,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 2.4236,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1537157389092964,
982
+ "grad_norm": 4.867519378662109,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 2.4106,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.15484600169539417,
989
+ "grad_norm": 4.014800071716309,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 2.3574,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.15597626448149193,
996
+ "grad_norm": 4.19603967666626,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 2.3052,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.15710652726758972,
1003
+ "grad_norm": 3.980522394180298,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 2.3863,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.1582367900536875,
1010
+ "grad_norm": 4.300126075744629,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 2.3,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.15936705283978525,
1017
+ "grad_norm": 4.201720714569092,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 2.3632,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.160497315625883,
1024
+ "grad_norm": 4.213210105895996,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 2.3081,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.16162757841198078,
1031
+ "grad_norm": 4.087728023529053,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 2.3772,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.16275784119807854,
1038
+ "grad_norm": 4.17429256439209,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 2.2332,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.16388810398417633,
1045
+ "grad_norm": 32.03535079956055,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 2.3299,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1650183667702741,
1052
+ "grad_norm": 3.815634250640869,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.8767,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.16614862955637186,
1059
+ "grad_norm": 3.9861598014831543,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.9595,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.16727889234246962,
1066
+ "grad_norm": 3.215773820877075,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.2479,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.16840915512856738,
1073
+ "grad_norm": 4.380100727081299,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.4794,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.16953941791466515,
1080
+ "grad_norm": 5.661203384399414,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.6155,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.16953941791466515,
1087
+ "eval_loss": 0.5321376919746399,
1088
+ "eval_runtime": 107.0082,
1089
+ "eval_samples_per_second": 13.924,
1090
+ "eval_steps_per_second": 3.486,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.147424726417408e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null