prxy5606 commited on
Commit
1267400
·
verified ·
1 Parent(s): cd88759

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 sha256:156c41e9776b86b0b5b06c82cc48ead39863bbba671e005a66fa888ac5a917cf
3
  size 800116456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36002a09e92fd5aa6cc7bc31692526123a6c94baf0e48398f4ecb39c46ea9ffa
3
  size 800116456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47f331c279c1d1b519c53b747acbe4558c74436eab2b02821110fdd3dda4ed81
3
  size 1600457770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9e344fe5c171752867a9dca31808e5ad327ab27699b5f6bc3f5c3e6a8e90696
3
  size 1600457770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fbf6af52e4d2c80da20f987568326a5117f5f5c4d303d2939708a700fefcbf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81a74eb8d832b0e767100fe82b13c9f6608276b11af2dc400ad074cb6e0fa85
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": 0.9962962865829468,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.33783783783783783,
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": 10.772,
732
  "eval_steps_per_second": 5.397,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.5710986748244787e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.910146951675415,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.5067567567567568,
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": 10.772,
732
  "eval_steps_per_second": 5.397,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.34121621621621623,
737
+ "grad_norm": 1.0150301456451416,
738
+ "learning_rate": 5.782172325201155e-05,
739
+ "loss": 0.8399,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.34459459459459457,
744
+ "grad_norm": 0.9101819396018982,
745
+ "learning_rate": 5.695865504800327e-05,
746
+ "loss": 0.8332,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.34797297297297297,
751
+ "grad_norm": 0.7298635244369507,
752
+ "learning_rate": 5.6093467170257374e-05,
753
+ "loss": 0.7701,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.35135135135135137,
758
+ "grad_norm": 0.7302980422973633,
759
+ "learning_rate": 5.522642316338268e-05,
760
+ "loss": 0.8608,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.3547297297297297,
765
+ "grad_norm": 0.7403108477592468,
766
+ "learning_rate": 5.435778713738292e-05,
767
+ "loss": 0.8571,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.3581081081081081,
772
+ "grad_norm": 0.7119635939598083,
773
+ "learning_rate": 5.348782368720626e-05,
774
+ "loss": 0.8834,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.3614864864864865,
779
+ "grad_norm": 0.7150499820709229,
780
+ "learning_rate": 5.26167978121472e-05,
781
+ "loss": 0.8476,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.36486486486486486,
786
+ "grad_norm": 2.773348331451416,
787
+ "learning_rate": 5.174497483512506e-05,
788
+ "loss": 0.8951,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.36824324324324326,
793
+ "grad_norm": 0.7925100326538086,
794
+ "learning_rate": 5.0872620321864185e-05,
795
+ "loss": 0.8753,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.3716216216216216,
800
+ "grad_norm": 0.9120268821716309,
801
+ "learning_rate": 5e-05,
802
+ "loss": 0.9304,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.375,
807
+ "grad_norm": 0.923784613609314,
808
+ "learning_rate": 4.912737967813583e-05,
809
+ "loss": 0.9109,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.3783783783783784,
814
+ "grad_norm": 0.7621331214904785,
815
+ "learning_rate": 4.825502516487497e-05,
816
+ "loss": 0.8805,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.38175675675675674,
821
+ "grad_norm": 0.989507794380188,
822
+ "learning_rate": 4.738320218785281e-05,
823
+ "loss": 0.9356,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.38513513513513514,
828
+ "grad_norm": 1.1281342506408691,
829
+ "learning_rate": 4.6512176312793736e-05,
830
+ "loss": 0.9762,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.3885135135135135,
835
+ "grad_norm": 1.0303744077682495,
836
+ "learning_rate": 4.564221286261709e-05,
837
+ "loss": 0.9971,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.3918918918918919,
842
+ "grad_norm": 0.8193778991699219,
843
+ "learning_rate": 4.477357683661734e-05,
844
+ "loss": 0.9003,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.3952702702702703,
849
+ "grad_norm": 0.8731766939163208,
850
+ "learning_rate": 4.390653282974264e-05,
851
+ "loss": 0.9704,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.39864864864864863,
856
+ "grad_norm": 1.064092755317688,
857
+ "learning_rate": 4.3041344951996746e-05,
858
+ "loss": 1.0779,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.40202702702702703,
863
+ "grad_norm": 0.8438169360160828,
864
+ "learning_rate": 4.2178276747988446e-05,
865
+ "loss": 0.9074,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.40540540540540543,
870
+ "grad_norm": 0.8278259634971619,
871
+ "learning_rate": 4.131759111665349e-05,
872
+ "loss": 0.9602,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.40878378378378377,
877
+ "grad_norm": 0.8631948232650757,
878
+ "learning_rate": 4.045955023117276e-05,
879
+ "loss": 0.8994,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.41216216216216217,
884
+ "grad_norm": 0.9589402079582214,
885
+ "learning_rate": 3.960441545911204e-05,
886
+ "loss": 1.0671,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.4155405405405405,
891
+ "grad_norm": 0.9513259530067444,
892
+ "learning_rate": 3.875244728280676e-05,
893
+ "loss": 1.0584,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.4189189189189189,
898
+ "grad_norm": 1.0139130353927612,
899
+ "learning_rate": 3.790390522001662e-05,
900
+ "loss": 0.9865,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.4222972972972973,
905
+ "grad_norm": 0.9505813121795654,
906
+ "learning_rate": 3.705904774487396e-05,
907
+ "loss": 0.9182,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.42567567567567566,
912
+ "grad_norm": 0.9823381900787354,
913
+ "learning_rate": 3.6218132209150045e-05,
914
+ "loss": 0.9159,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.42905405405405406,
919
+ "grad_norm": 1.0299394130706787,
920
+ "learning_rate": 3.5381414763863166e-05,
921
+ "loss": 0.9573,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.43243243243243246,
926
+ "grad_norm": 1.2664399147033691,
927
+ "learning_rate": 3.4549150281252636e-05,
928
+ "loss": 1.1676,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.4358108108108108,
933
+ "grad_norm": 1.107443928718567,
934
+ "learning_rate": 3.372159227714218e-05,
935
+ "loss": 0.9744,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.4391891891891892,
940
+ "grad_norm": 1.2630161046981812,
941
+ "learning_rate": 3.289899283371657e-05,
942
+ "loss": 1.0434,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.44256756756756754,
947
+ "grad_norm": 1.2209265232086182,
948
+ "learning_rate": 3.2081602522734986e-05,
949
+ "loss": 0.9721,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.44594594594594594,
954
+ "grad_norm": 1.1842795610427856,
955
+ "learning_rate": 3.12696703292044e-05,
956
+ "loss": 0.9618,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.44932432432432434,
961
+ "grad_norm": 1.22838294506073,
962
+ "learning_rate": 3.046344357553632e-05,
963
+ "loss": 0.981,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.4527027027027027,
968
+ "grad_norm": 1.260001301765442,
969
+ "learning_rate": 2.9663167846209998e-05,
970
+ "loss": 0.9968,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.4560810810810811,
975
+ "grad_norm": 1.4171466827392578,
976
+ "learning_rate": 2.886908691296504e-05,
977
+ "loss": 1.0873,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.4594594594594595,
982
+ "grad_norm": 1.376778244972229,
983
+ "learning_rate": 2.8081442660546125e-05,
984
+ "loss": 1.0623,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.46283783783783783,
989
+ "grad_norm": 1.6616677045822144,
990
+ "learning_rate": 2.7300475013022663e-05,
991
+ "loss": 1.1181,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.46621621621621623,
996
+ "grad_norm": 1.489789605140686,
997
+ "learning_rate": 2.6526421860705473e-05,
998
+ "loss": 1.0679,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.46959459459459457,
1003
+ "grad_norm": 1.6120611429214478,
1004
+ "learning_rate": 2.575951898768315e-05,
1005
+ "loss": 1.1404,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.47297297297297297,
1010
+ "grad_norm": 1.7737764120101929,
1011
+ "learning_rate": 2.500000000000001e-05,
1012
+ "loss": 1.0704,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.47635135135135137,
1017
+ "grad_norm": 1.4966835975646973,
1018
+ "learning_rate": 2.4248096254497288e-05,
1019
+ "loss": 0.903,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.4797297297297297,
1024
+ "grad_norm": 1.6529886722564697,
1025
+ "learning_rate": 2.350403678833976e-05,
1026
+ "loss": 0.9047,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.4831081081081081,
1031
+ "grad_norm": 1.9524998664855957,
1032
+ "learning_rate": 2.2768048249248648e-05,
1033
+ "loss": 0.9717,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.4864864864864865,
1038
+ "grad_norm": 1.7451844215393066,
1039
+ "learning_rate": 2.2040354826462668e-05,
1040
+ "loss": 0.9651,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.48986486486486486,
1045
+ "grad_norm": 1.7876458168029785,
1046
+ "learning_rate": 2.132117818244771e-05,
1047
+ "loss": 0.9632,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.49324324324324326,
1052
+ "grad_norm": 1.8912980556488037,
1053
+ "learning_rate": 2.061073738537635e-05,
1054
+ "loss": 0.9248,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.4966216216216216,
1059
+ "grad_norm": 2.041308641433716,
1060
+ "learning_rate": 1.9909248842397584e-05,
1061
+ "loss": 0.826,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.5,
1066
+ "grad_norm": 3.146843433380127,
1067
+ "learning_rate": 1.9216926233717085e-05,
1068
+ "loss": 0.8596,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.5033783783783784,
1073
+ "grad_norm": 3.079761028289795,
1074
+ "learning_rate": 1.8533980447508137e-05,
1075
+ "loss": 1.0932,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.5067567567567568,
1080
+ "grad_norm": 4.34760046005249,
1081
+ "learning_rate": 1.7860619515673033e-05,
1082
+ "loss": 0.9517,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.5067567567567568,
1087
+ "eval_loss": 0.910146951675415,
1088
+ "eval_runtime": 46.335,
1089
+ "eval_samples_per_second": 10.769,
1090
+ "eval_steps_per_second": 5.395,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.356648012236718e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null