lesso commited on
Commit
c08bb2f
·
verified ·
1 Parent(s): cbf03de

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 sha256:92362f910314c3bd5fbcf7b4e54dbb75a08d5148056f673a46abdeb940e47098
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460f05eb744d34bffeb9d19e824666f20e88afd559c776d265689098f45e605b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2733fd10a06cf0179ae4d6767e3c54b8b905f32ce1afad7664f2ad3dcc23f67
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d9ad367516a8337e81e182787df447c54393d8f694d96c7cc365bb3c4bdbf2
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aa0d160c975a060faa731d9faa7e6856a15bc691c54dadc13fc4e7e49d40950
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f801f35493f21aa7b6d4d83ff0bfcabdb11cc14fc16dfaff199f1babb88ccfc5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5525f1d8420ca8a81a7fd2ec397a508131d03210dfd36c7ac5758b0e6313b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0482261180877686,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.22172949002217296,
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": 9.386,
732
  "eval_steps_per_second": 2.371,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.57749904900096e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8841075897216797,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.3325942350332594,
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": 9.386,
732
  "eval_steps_per_second": 2.371,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.22394678492239467,
737
+ "grad_norm": 17.120187759399414,
738
+ "learning_rate": 5.231368421052631e-05,
739
+ "loss": 2.3941,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.2261640798226164,
744
+ "grad_norm": 16.493423461914062,
745
+ "learning_rate": 5.178526315789474e-05,
746
+ "loss": 2.3262,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.22838137472283815,
751
+ "grad_norm": 12.841573715209961,
752
+ "learning_rate": 5.1256842105263165e-05,
753
+ "loss": 2.0664,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.23059866962305986,
758
+ "grad_norm": 12.463582992553711,
759
+ "learning_rate": 5.072842105263158e-05,
760
+ "loss": 2.0229,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2328159645232816,
765
+ "grad_norm": 13.76339054107666,
766
+ "learning_rate": 5.02e-05,
767
+ "loss": 2.0176,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.23503325942350334,
772
+ "grad_norm": 12.230353355407715,
773
+ "learning_rate": 4.967157894736842e-05,
774
+ "loss": 1.6626,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.23725055432372505,
779
+ "grad_norm": 14.192876815795898,
780
+ "learning_rate": 4.914315789473684e-05,
781
+ "loss": 2.0265,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2394678492239468,
786
+ "grad_norm": 13.952037811279297,
787
+ "learning_rate": 4.861473684210526e-05,
788
+ "loss": 1.7241,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.24168514412416853,
793
+ "grad_norm": 14.577288627624512,
794
+ "learning_rate": 4.8086315789473686e-05,
795
+ "loss": 1.7365,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.24390243902439024,
800
+ "grad_norm": 19.91164779663086,
801
+ "learning_rate": 4.7557894736842104e-05,
802
+ "loss": 1.8842,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.24611973392461198,
807
+ "grad_norm": 14.9652681350708,
808
+ "learning_rate": 4.702947368421053e-05,
809
+ "loss": 1.7975,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.24833702882483372,
814
+ "grad_norm": 13.924230575561523,
815
+ "learning_rate": 4.6501052631578946e-05,
816
+ "loss": 1.9894,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.25055432372505543,
821
+ "grad_norm": 13.089156150817871,
822
+ "learning_rate": 4.5972631578947364e-05,
823
+ "loss": 1.758,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.25277161862527714,
828
+ "grad_norm": 12.60175895690918,
829
+ "learning_rate": 4.544421052631579e-05,
830
+ "loss": 1.6666,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.2549889135254989,
835
+ "grad_norm": 17.490257263183594,
836
+ "learning_rate": 4.4915789473684213e-05,
837
+ "loss": 1.9925,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.2572062084257206,
842
+ "grad_norm": 12.952994346618652,
843
+ "learning_rate": 4.438736842105263e-05,
844
+ "loss": 1.6062,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.25942350332594233,
849
+ "grad_norm": 15.763453483581543,
850
+ "learning_rate": 4.3858947368421056e-05,
851
+ "loss": 2.0694,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.2616407982261641,
856
+ "grad_norm": 14.717920303344727,
857
+ "learning_rate": 4.3330526315789474e-05,
858
+ "loss": 1.7913,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2638580931263858,
863
+ "grad_norm": 16.53207778930664,
864
+ "learning_rate": 4.280210526315789e-05,
865
+ "loss": 1.7959,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2660753880266075,
870
+ "grad_norm": 13.253047943115234,
871
+ "learning_rate": 4.2273684210526317e-05,
872
+ "loss": 1.6143,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.2682926829268293,
877
+ "grad_norm": 15.786408424377441,
878
+ "learning_rate": 4.174526315789474e-05,
879
+ "loss": 1.6721,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.270509977827051,
884
+ "grad_norm": 12.185956001281738,
885
+ "learning_rate": 4.121684210526316e-05,
886
+ "loss": 1.5245,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2727272727272727,
891
+ "grad_norm": 21.057693481445312,
892
+ "learning_rate": 4.068842105263158e-05,
893
+ "loss": 2.1359,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.2749445676274945,
898
+ "grad_norm": 13.455188751220703,
899
+ "learning_rate": 4.016e-05,
900
+ "loss": 2.0307,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2771618625277162,
905
+ "grad_norm": 15.558540344238281,
906
+ "learning_rate": 3.963157894736842e-05,
907
+ "loss": 1.7351,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2793791574279379,
912
+ "grad_norm": 16.883926391601562,
913
+ "learning_rate": 3.9103157894736844e-05,
914
+ "loss": 2.1596,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.28159645232815966,
919
+ "grad_norm": 20.178613662719727,
920
+ "learning_rate": 3.857473684210526e-05,
921
+ "loss": 1.8029,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.2838137472283814,
926
+ "grad_norm": 18.442106246948242,
927
+ "learning_rate": 3.804631578947369e-05,
928
+ "loss": 2.0837,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.2860310421286031,
933
+ "grad_norm": 19.457265853881836,
934
+ "learning_rate": 3.7517894736842105e-05,
935
+ "loss": 1.6284,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.28824833702882485,
940
+ "grad_norm": 26.571035385131836,
941
+ "learning_rate": 3.698947368421052e-05,
942
+ "loss": 1.7662,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.29046563192904656,
947
+ "grad_norm": 19.368440628051758,
948
+ "learning_rate": 3.646105263157895e-05,
949
+ "loss": 1.8661,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.2926829268292683,
954
+ "grad_norm": 22.966577529907227,
955
+ "learning_rate": 3.593263157894737e-05,
956
+ "loss": 2.619,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.29490022172949004,
961
+ "grad_norm": 24.9805965423584,
962
+ "learning_rate": 3.540421052631579e-05,
963
+ "loss": 1.5081,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.29711751662971175,
968
+ "grad_norm": 19.5284366607666,
969
+ "learning_rate": 3.4875789473684215e-05,
970
+ "loss": 1.7447,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.29933481152993346,
975
+ "grad_norm": 21.54673194885254,
976
+ "learning_rate": 3.434736842105263e-05,
977
+ "loss": 1.6988,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.30155210643015523,
982
+ "grad_norm": 23.316730499267578,
983
+ "learning_rate": 3.381894736842105e-05,
984
+ "loss": 2.2736,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.30376940133037694,
989
+ "grad_norm": 22.004526138305664,
990
+ "learning_rate": 3.329052631578947e-05,
991
+ "loss": 1.9549,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.30598669623059865,
996
+ "grad_norm": 23.052682876586914,
997
+ "learning_rate": 3.27621052631579e-05,
998
+ "loss": 2.0963,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.3082039911308204,
1003
+ "grad_norm": 20.599315643310547,
1004
+ "learning_rate": 3.223368421052632e-05,
1005
+ "loss": 1.2949,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.31042128603104213,
1010
+ "grad_norm": 20.93349266052246,
1011
+ "learning_rate": 3.1705263157894736e-05,
1012
+ "loss": 1.9277,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.31263858093126384,
1017
+ "grad_norm": 27.307830810546875,
1018
+ "learning_rate": 3.117684210526316e-05,
1019
+ "loss": 1.122,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.3148558758314856,
1024
+ "grad_norm": 17.325700759887695,
1025
+ "learning_rate": 3.064842105263158e-05,
1026
+ "loss": 1.2689,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.3170731707317073,
1031
+ "grad_norm": 30.8470458984375,
1032
+ "learning_rate": 3.012e-05,
1033
+ "loss": 2.1764,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.31929046563192903,
1038
+ "grad_norm": 19.84284210205078,
1039
+ "learning_rate": 2.9591578947368418e-05,
1040
+ "loss": 1.059,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.3215077605321508,
1045
+ "grad_norm": 23.532106399536133,
1046
+ "learning_rate": 2.9063157894736842e-05,
1047
+ "loss": 1.9666,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.3237250554323725,
1052
+ "grad_norm": 17.46700668334961,
1053
+ "learning_rate": 2.8534736842105264e-05,
1054
+ "loss": 1.5324,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.3259423503325942,
1059
+ "grad_norm": 23.52845001220703,
1060
+ "learning_rate": 2.800631578947368e-05,
1061
+ "loss": 1.3784,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.328159645232816,
1066
+ "grad_norm": 27.91365623474121,
1067
+ "learning_rate": 2.7477894736842106e-05,
1068
+ "loss": 1.6899,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3303769401330377,
1073
+ "grad_norm": 32.38272476196289,
1074
+ "learning_rate": 2.6949473684210527e-05,
1075
+ "loss": 1.6625,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.3325942350332594,
1080
+ "grad_norm": 51.69731140136719,
1081
+ "learning_rate": 2.6421052631578945e-05,
1082
+ "loss": 1.9981,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.3325942350332594,
1087
+ "eval_loss": 0.8841075897216797,
1088
+ "eval_runtime": 20.2428,
1089
+ "eval_samples_per_second": 9.386,
1090
+ "eval_steps_per_second": 2.371,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.36624857350144e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null