prxy5605 commited on
Commit
4a4c866
·
verified ·
1 Parent(s): fe67f8e

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 sha256:89b5b9eea1a221d5c1e77e1ee66b78cd088a11cb5f0e10e4261200737890a7d8
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6dab56081936e6edebfd8196f79fadf90621c81a723dc40787e60106612efa
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8c81ce64c1c191b52e75e5671df307255dc4c4b1209368346f621e563cc7dfa
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c21e6496a93b9d929dd8056e3b4334118675b9733a536dacbe78963235066ce
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3c2471fcb4bb9f76c8dc6c39e3274cb43345d856666c3916e59cdb659d50419
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6cfd41123f22ad40ab79ee02e4b83b643009ac4355628251dc9b257a606373
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": 10.348418235778809,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.8528784648187633,
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": 415.097,
732
  "eval_steps_per_second": 104.822,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 11155066060800.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.345519065856934,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 1.279317697228145,
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": 415.097,
732
  "eval_steps_per_second": 104.822,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.8614072494669509,
737
+ "grad_norm": 0.03691884130239487,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 10.3462,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.8699360341151386,
744
+ "grad_norm": 0.03882606327533722,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 10.3486,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.8784648187633263,
751
+ "grad_norm": 0.03755461797118187,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 10.3479,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.8869936034115139,
758
+ "grad_norm": 0.04736875370144844,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 10.3471,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.8955223880597015,
765
+ "grad_norm": 0.029074519872665405,
766
+ "learning_rate": 5e-05,
767
+ "loss": 10.3486,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.9040511727078892,
772
+ "grad_norm": 0.031900398433208466,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 10.3472,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.9125799573560768,
779
+ "grad_norm": 0.03517429158091545,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 10.3458,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.9211087420042644,
786
+ "grad_norm": 0.03357727825641632,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 10.3479,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.929637526652452,
793
+ "grad_norm": 0.03584626689553261,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 10.3478,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.9381663113006397,
800
+ "grad_norm": 0.0471317358314991,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 10.3474,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.9466950959488273,
807
+ "grad_norm": 0.038973815739154816,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 10.3483,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.9552238805970149,
814
+ "grad_norm": 0.0343744233250618,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 10.3477,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.9637526652452025,
821
+ "grad_norm": 0.037565600126981735,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 10.3485,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.9722814498933902,
828
+ "grad_norm": 0.04688845947384834,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 10.3467,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.9808102345415778,
835
+ "grad_norm": 0.05078093707561493,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 10.3465,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.9893390191897654,
842
+ "grad_norm": 0.04903563857078552,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 10.3467,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.997867803837953,
849
+ "grad_norm": 0.043443650007247925,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 10.3463,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.0063965884861408,
856
+ "grad_norm": 0.06975448876619339,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 18.2617,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.0149253731343284,
863
+ "grad_norm": 0.05583430454134941,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 10.1853,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.023454157782516,
870
+ "grad_norm": 0.054079584777355194,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 10.4074,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.0319829424307037,
877
+ "grad_norm": 0.05480353534221649,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 10.3191,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.0405117270788913,
884
+ "grad_norm": 0.05557660385966301,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 10.2915,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.049040511727079,
891
+ "grad_norm": 0.05558188259601593,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 10.326,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.0575692963752665,
898
+ "grad_norm": 0.033676628023386,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 10.4113,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.0660980810234542,
905
+ "grad_norm": 0.04203203693032265,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 10.3098,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.0746268656716418,
912
+ "grad_norm": 0.040990713983774185,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 10.3694,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.0831556503198294,
919
+ "grad_norm": 0.04310883209109306,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 10.3483,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.091684434968017,
926
+ "grad_norm": 0.03962789475917816,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 10.3523,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.1002132196162047,
933
+ "grad_norm": 0.04049231484532356,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 10.4013,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.1087420042643923,
940
+ "grad_norm": 0.04194732382893562,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 10.2829,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.11727078891258,
947
+ "grad_norm": 0.036313239485025406,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 10.3324,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.1257995735607675,
954
+ "grad_norm": 0.046480074524879456,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 10.3625,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 1.1343283582089552,
961
+ "grad_norm": 0.04361138865351677,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 10.3698,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 1.1428571428571428,
968
+ "grad_norm": 0.04324062541127205,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 10.3045,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 1.1513859275053304,
975
+ "grad_norm": 0.05079786852002144,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 10.3997,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 1.159914712153518,
982
+ "grad_norm": 0.03967788442969322,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 10.3362,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 1.1684434968017057,
989
+ "grad_norm": 0.04797113686800003,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 10.2458,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 1.1769722814498933,
996
+ "grad_norm": 0.03926164284348488,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 10.4052,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 1.1855010660980811,
1003
+ "grad_norm": 0.046536751091480255,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 10.3523,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 1.1940298507462686,
1010
+ "grad_norm": 0.041127756237983704,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 10.3909,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 1.2025586353944564,
1017
+ "grad_norm": 0.05339064821600914,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 10.2972,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 1.2110874200426438,
1024
+ "grad_norm": 0.041502151638269424,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 10.3399,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 1.2196162046908317,
1031
+ "grad_norm": 0.04914531484246254,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 10.4175,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 1.2281449893390193,
1038
+ "grad_norm": 0.052515558898448944,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 10.2855,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 1.236673773987207,
1045
+ "grad_norm": 0.04797741025686264,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 10.3788,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 1.2452025586353945,
1052
+ "grad_norm": 0.04141698777675629,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 10.3915,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 1.2537313432835822,
1059
+ "grad_norm": 0.04757013916969299,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 10.4077,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 1.2622601279317698,
1066
+ "grad_norm": 0.050195809453725815,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 10.2124,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 1.2707889125799574,
1073
+ "grad_norm": 0.05028505623340607,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 10.3313,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 1.279317697228145,
1080
+ "grad_norm": 0.050132013857364655,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 10.398,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 1.279317697228145,
1087
+ "eval_loss": 10.345519065856934,
1088
+ "eval_runtime": 0.4732,
1089
+ "eval_samples_per_second": 418.456,
1090
+ "eval_steps_per_second": 105.671,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 16729113133056.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null