0x1202 commited on
Commit
326421f
·
verified ·
1 Parent(s): fa5234e

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:eb65b43c425ff2d855e397dfd475d80f554efd01dde8f64015bec52e200deb04
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866b9c155da064cd694d4d127b1be6e79e0ab8d2dd94d933116bcfe2b08e1380
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d436e249592d417d1d55762707f2f39978dbceaf58bf0d4832bcf348f1279160
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8c1c5cdb6edd0766c89ae34ac1850a435e61af2e6a1a1cb4cc4f4a4af06852
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b54a99012b82029a4ac125e5fb8c483cfb08c74f5ce6389a76ae30ebed5725e1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b50f8cce1f16100fa6849f1e927aef474337eec2fa18ab06a74ba6a2c26152
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": 0.9811466932296753,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.37488284910965325,
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": 21.624,
732
  "eval_steps_per_second": 5.43,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 5.933753135058125e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.9521539807319641,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5623242736644799,
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": 21.624,
732
  "eval_steps_per_second": 5.43,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.3786316776007498,
737
+ "grad_norm": 0.3575192391872406,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.6942,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.3823805060918463,
744
+ "grad_norm": 0.31599247455596924,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.8247,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.38612933458294285,
751
+ "grad_norm": 0.35906827449798584,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.8857,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.3898781630740394,
758
+ "grad_norm": 0.33249327540397644,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.9295,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3936269915651359,
765
+ "grad_norm": 0.32756689190864563,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8471,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.39737582005623245,
772
+ "grad_norm": 0.3289243280887604,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8969,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.40112464854732893,
779
+ "grad_norm": 0.31799304485321045,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.9489,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.40487347703842547,
786
+ "grad_norm": 0.31175363063812256,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9386,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.408622305529522,
793
+ "grad_norm": 0.3153715431690216,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.912,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.41237113402061853,
800
+ "grad_norm": 0.30276235938072205,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9109,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.41611996251171507,
807
+ "grad_norm": 0.3206758201122284,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.8837,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.4198687910028116,
814
+ "grad_norm": 0.3105361759662628,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.8786,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.42361761949390814,
821
+ "grad_norm": 0.2993127107620239,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.8757,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.42736644798500467,
828
+ "grad_norm": 0.31823205947875977,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.8649,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.4311152764761012,
835
+ "grad_norm": 0.3383299708366394,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9032,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.43486410496719774,
842
+ "grad_norm": 0.37144601345062256,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.8691,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.4386129334582943,
849
+ "grad_norm": 0.3267931342124939,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.9388,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.4423617619493908,
856
+ "grad_norm": 0.34755590558052063,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9583,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.44611059044048734,
863
+ "grad_norm": 0.3316834568977356,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.8613,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.4498594189315839,
870
+ "grad_norm": 0.3462877869606018,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.8717,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.4536082474226804,
877
+ "grad_norm": 0.37453365325927734,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.8908,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.45735707591377694,
884
+ "grad_norm": 0.3717382252216339,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.9988,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4611059044048735,
891
+ "grad_norm": 0.39408352971076965,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.9501,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.46485473289597,
898
+ "grad_norm": 0.4256141483783722,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.914,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.46860356138706655,
905
+ "grad_norm": 0.4107443690299988,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.9253,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.4723523898781631,
912
+ "grad_norm": 0.4722575545310974,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.9535,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.4761012183692596,
919
+ "grad_norm": 0.47176846861839294,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.9184,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.47985004686035615,
926
+ "grad_norm": 0.486392617225647,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.9515,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4835988753514527,
933
+ "grad_norm": 0.4838985204696655,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.9586,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.4873477038425492,
940
+ "grad_norm": 0.5224278569221497,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1063,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.49109653233364575,
947
+ "grad_norm": 0.5882999897003174,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.9966,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.4948453608247423,
954
+ "grad_norm": 0.565453290939331,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.0058,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.4985941893158388,
961
+ "grad_norm": 0.6657898426055908,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.0503,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.5023430178069354,
968
+ "grad_norm": 0.5977612137794495,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.8594,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.5060918462980318,
975
+ "grad_norm": 0.5637332201004028,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.9948,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.5098406747891284,
982
+ "grad_norm": 0.6925244331359863,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.9501,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.5135895032802249,
989
+ "grad_norm": 0.6315667629241943,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.9955,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.5173383317713215,
996
+ "grad_norm": 0.6699217557907104,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0051,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.521087160262418,
1003
+ "grad_norm": 0.6867546439170837,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0129,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.5248359887535146,
1010
+ "grad_norm": 0.7504917979240417,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0773,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.528584817244611,
1017
+ "grad_norm": 0.7592334151268005,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.985,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.5323336457357076,
1024
+ "grad_norm": 0.7560880780220032,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.0159,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.5360824742268041,
1031
+ "grad_norm": 0.7213366031646729,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.0412,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.5398313027179007,
1038
+ "grad_norm": 0.7502860426902771,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0144,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.5435801312089972,
1045
+ "grad_norm": 0.8330617547035217,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.035,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.5473289597000938,
1052
+ "grad_norm": 0.7836589217185974,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.9362,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.5510777881911902,
1059
+ "grad_norm": 0.8202426433563232,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.9897,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5548266166822868,
1066
+ "grad_norm": 0.8087556958198547,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.9869,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5585754451733833,
1073
+ "grad_norm": 1.006156325340271,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0094,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5623242736644799,
1080
+ "grad_norm": 1.302259087562561,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.076,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5623242736644799,
1087
+ "eval_loss": 0.9521539807319641,
1088
+ "eval_runtime": 20.5002,
1089
+ "eval_samples_per_second": 21.951,
1090
+ "eval_steps_per_second": 5.512,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 8.929295176669594e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null