prxy5608 commited on
Commit
7cb7ff5
·
verified ·
1 Parent(s): 95d9678

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 sha256:8dc0803f239ff2deb3e8bb9822e446198087d63452c49e07aa48f7afb834dc5a
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58cca62ff008c1e04f2d1275b122f54e410ea187a83e59888ef4f7c3caa02426
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3085bc481fe797076dbef1e65fb08d552de3be8cda794f7e9e07918327e079a
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ee7cdc30aa8d303c47f01b693799b2144c53ab095c2c7574702cb6c6f17842
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81edb2912a9f7207db2fc684d22dbcd71e5ceb0f3c5fb6ae62aad188793672f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d408df792e1726a418289a56a077112339ce72fa3d7112ae5d5c4e2bf8a2fa1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e0244c146d76bf610ae39789eea36d0bff336b81d211db008e020e66921060c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9518508911132812,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.6369426751592356,
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": 11.542,
732
  "eval_steps_per_second": 5.793,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.52310276258005e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.856124222278595,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.9554140127388535,
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": 11.542,
732
  "eval_steps_per_second": 5.793,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.643312101910828,
737
+ "grad_norm": 11.772903442382812,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 3.5184,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.6496815286624203,
744
+ "grad_norm": 15.014814376831055,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 4.02,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.6560509554140127,
751
+ "grad_norm": 13.781637191772461,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 3.6895,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.6624203821656051,
758
+ "grad_norm": 14.441632270812988,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 3.3828,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.6687898089171974,
765
+ "grad_norm": 16.388935089111328,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 3.8216,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.6751592356687898,
772
+ "grad_norm": 16.722646713256836,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 3.8913,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.6815286624203821,
779
+ "grad_norm": 17.876073837280273,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 3.6247,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.6878980891719745,
786
+ "grad_norm": 18.381223678588867,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 3.9273,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.6942675159235668,
793
+ "grad_norm": 17.400468826293945,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 3.4908,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.7006369426751592,
800
+ "grad_norm": 21.45941925048828,
801
+ "learning_rate": 5e-05,
802
+ "loss": 4.4969,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.7070063694267515,
807
+ "grad_norm": 21.00533103942871,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 4.1499,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.7133757961783439,
814
+ "grad_norm": 20.375274658203125,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 3.4835,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.7197452229299363,
821
+ "grad_norm": 21.039329528808594,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 2.9916,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.7261146496815286,
828
+ "grad_norm": 25.608665466308594,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 3.5051,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.732484076433121,
835
+ "grad_norm": 23.432601928710938,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 2.8175,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.7388535031847133,
842
+ "grad_norm": 31.607587814331055,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 4.0832,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.7452229299363057,
849
+ "grad_norm": 47.30448913574219,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 3.5419,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.7515923566878981,
856
+ "grad_norm": 4.965266227722168,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 3.0148,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.7579617834394905,
863
+ "grad_norm": 4.364875793457031,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 2.9562,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.7643312101910829,
870
+ "grad_norm": 4.950608253479004,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 3.453,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.7707006369426752,
877
+ "grad_norm": 4.8531951904296875,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 2.7735,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.7770700636942676,
884
+ "grad_norm": 5.037564754486084,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 2.94,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.7834394904458599,
891
+ "grad_norm": 5.288941383361816,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 3.0112,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.7898089171974523,
898
+ "grad_norm": 5.76696252822876,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 3.1363,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.7961783439490446,
905
+ "grad_norm": 5.585211753845215,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 3.3864,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.802547770700637,
912
+ "grad_norm": 6.322639465332031,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 3.5615,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.8089171974522293,
919
+ "grad_norm": 6.185570240020752,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 3.1405,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.8152866242038217,
926
+ "grad_norm": 6.54400634765625,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 3.6258,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.821656050955414,
933
+ "grad_norm": 6.367386341094971,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 3.153,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.8280254777070064,
940
+ "grad_norm": 6.623294830322266,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 3.0124,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.8343949044585988,
947
+ "grad_norm": 6.886430263519287,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 3.1905,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.8407643312101911,
954
+ "grad_norm": 7.273221969604492,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 2.9941,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.8471337579617835,
961
+ "grad_norm": 8.015644073486328,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 3.4856,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.8535031847133758,
968
+ "grad_norm": 8.67126750946045,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 3.5122,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.8598726114649682,
975
+ "grad_norm": 9.060256958007812,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 3.7418,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.8662420382165605,
982
+ "grad_norm": 8.686426162719727,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 3.003,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.8726114649681529,
989
+ "grad_norm": 8.711852073669434,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 3.1511,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.8789808917197452,
996
+ "grad_norm": 11.177677154541016,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 3.7168,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.8853503184713376,
1003
+ "grad_norm": 10.784727096557617,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 3.0916,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.89171974522293,
1010
+ "grad_norm": 11.460144996643066,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 3.2102,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.8980891719745223,
1017
+ "grad_norm": 12.439859390258789,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 3.6256,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.9044585987261147,
1024
+ "grad_norm": 13.51606273651123,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 4.201,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.910828025477707,
1031
+ "grad_norm": 17.250572204589844,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 4.7407,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.9171974522292994,
1038
+ "grad_norm": 16.19012451171875,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 4.0064,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.9235668789808917,
1045
+ "grad_norm": 16.520713806152344,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 3.7402,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.9299363057324841,
1052
+ "grad_norm": 17.06348991394043,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 4.0871,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.9363057324840764,
1059
+ "grad_norm": 16.918140411376953,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 4.0366,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.9426751592356688,
1066
+ "grad_norm": 17.086406707763672,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 3.6202,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.9490445859872612,
1073
+ "grad_norm": 16.144107818603516,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 3.0974,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.9554140127388535,
1080
+ "grad_norm": 18.168882369995117,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 3.2189,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.9554140127388535,
1087
+ "eval_loss": 0.856124222278595,
1088
+ "eval_runtime": 22.9621,
1089
+ "eval_samples_per_second": 11.541,
1090
+ "eval_steps_per_second": 5.792,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.2738263991123968e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null