lesso commited on
Commit
a61fa87
·
verified ·
1 Parent(s): 722240a

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 sha256:257cb11372104ab3a4f7143cdd11742e13d6032c76c8c0cb4bc2305491b00a1f
3
  size 478211024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8341e80ac0fbf04fba66a8809799ed495ede75dd96e70cd911ecf3ccc335db
3
  size 478211024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73b4be48a5b763176c82afa2e19eaf3bb6a5fe747e318a56d6fb2848725243f8
3
  size 243337876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddf571e0cbbf6e8dd7f38cf11cad62e9a17711bb37d860a4709c7d88191f42e
3
  size 243337876
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69b1f823f95840d7f9c41d08ca399a2909b411989d5e3b4c217a276b432afc45
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f559f96aa4718e0775b1ba1413fbbe63a38407dc074a3ed16103f8050cf87636
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fe6f0a2f7a14e66c6816df9a38574183cedfa2cc544d1c8e8e8cea1139c2f76
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef91cf09f7b6a58a39bbfe1ef78ac2fa91c0c15ca1705097a187d272d0433d8d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.444609671831131,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0025672293177588087,
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": 13.894,
732
  "eval_steps_per_second": 3.474,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.897919540939981e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.41922199726104736,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.003850843976638213,
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": 13.894,
732
  "eval_steps_per_second": 3.474,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.002592901610936397,
737
+ "grad_norm": 1.0906559228897095,
738
+ "learning_rate": 5.24178947368421e-05,
739
+ "loss": 1.5745,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.002618573904113985,
744
+ "grad_norm": 1.057900071144104,
745
+ "learning_rate": 5.1888421052631585e-05,
746
+ "loss": 1.359,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.002644246197291573,
751
+ "grad_norm": 1.1936546564102173,
752
+ "learning_rate": 5.135894736842106e-05,
753
+ "loss": 1.8506,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0026699184904691612,
758
+ "grad_norm": 1.1742337942123413,
759
+ "learning_rate": 5.082947368421053e-05,
760
+ "loss": 1.4235,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0026955907836467494,
765
+ "grad_norm": 1.4636642932891846,
766
+ "learning_rate": 5.03e-05,
767
+ "loss": 1.9341,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0027212630768243375,
772
+ "grad_norm": 1.366550087928772,
773
+ "learning_rate": 4.977052631578947e-05,
774
+ "loss": 1.7735,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0027469353700019256,
779
+ "grad_norm": 1.4252630472183228,
780
+ "learning_rate": 4.924105263157895e-05,
781
+ "loss": 1.8694,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0027726076631795133,
786
+ "grad_norm": 1.5163335800170898,
787
+ "learning_rate": 4.871157894736843e-05,
788
+ "loss": 1.8035,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0027982799563571015,
793
+ "grad_norm": 1.6696662902832031,
794
+ "learning_rate": 4.81821052631579e-05,
795
+ "loss": 2.4422,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0028239522495346896,
800
+ "grad_norm": 1.823583960533142,
801
+ "learning_rate": 4.765263157894737e-05,
802
+ "loss": 2.0223,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0028496245427122777,
807
+ "grad_norm": 1.7153486013412476,
808
+ "learning_rate": 4.7123157894736845e-05,
809
+ "loss": 2.3425,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.002875296835889866,
814
+ "grad_norm": 1.597476601600647,
815
+ "learning_rate": 4.6593684210526316e-05,
816
+ "loss": 1.9461,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.002900969129067454,
821
+ "grad_norm": 1.6382873058319092,
822
+ "learning_rate": 4.606421052631579e-05,
823
+ "loss": 1.7633,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.002926641422245042,
828
+ "grad_norm": 1.7374053001403809,
829
+ "learning_rate": 4.553473684210527e-05,
830
+ "loss": 2.0122,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0029523137154226302,
835
+ "grad_norm": 1.976195216178894,
836
+ "learning_rate": 4.500526315789474e-05,
837
+ "loss": 2.218,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.0029779860086002184,
842
+ "grad_norm": 2.0346622467041016,
843
+ "learning_rate": 4.447578947368421e-05,
844
+ "loss": 2.3013,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0030036583017778065,
849
+ "grad_norm": 1.756709337234497,
850
+ "learning_rate": 4.394631578947369e-05,
851
+ "loss": 1.9596,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.003029330594955394,
856
+ "grad_norm": 1.9882556200027466,
857
+ "learning_rate": 4.341684210526316e-05,
858
+ "loss": 2.2595,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0030550028881329823,
863
+ "grad_norm": 2.60469388961792,
864
+ "learning_rate": 4.2887368421052636e-05,
865
+ "loss": 1.5153,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.0030806751813105705,
870
+ "grad_norm": 0.9778649806976318,
871
+ "learning_rate": 4.2357894736842106e-05,
872
+ "loss": 0.0113,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0031063474744881586,
877
+ "grad_norm": 0.011567816138267517,
878
+ "learning_rate": 4.182842105263158e-05,
879
+ "loss": 0.0004,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0031320197676657467,
884
+ "grad_norm": 0.010046404786407948,
885
+ "learning_rate": 4.1298947368421053e-05,
886
+ "loss": 0.0004,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.003157692060843335,
891
+ "grad_norm": 0.009395002387464046,
892
+ "learning_rate": 4.0769473684210524e-05,
893
+ "loss": 0.0003,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.003183364354020923,
898
+ "grad_norm": 0.008893662132322788,
899
+ "learning_rate": 4.024000000000001e-05,
900
+ "loss": 0.0003,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.003209036647198511,
905
+ "grad_norm": 0.008500020019710064,
906
+ "learning_rate": 3.971052631578948e-05,
907
+ "loss": 0.0003,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0032347089403760992,
912
+ "grad_norm": 0.0076544624753296375,
913
+ "learning_rate": 3.918105263157895e-05,
914
+ "loss": 0.0003,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.0032603812335536874,
919
+ "grad_norm": 0.007298609241843224,
920
+ "learning_rate": 3.865157894736842e-05,
921
+ "loss": 0.0003,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.003286053526731275,
926
+ "grad_norm": 0.006563248578459024,
927
+ "learning_rate": 3.8122105263157896e-05,
928
+ "loss": 0.0002,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.003311725819908863,
933
+ "grad_norm": 0.006430802401155233,
934
+ "learning_rate": 3.759263157894737e-05,
935
+ "loss": 0.0002,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0033373981130864513,
940
+ "grad_norm": 0.006386774126440287,
941
+ "learning_rate": 3.7063157894736844e-05,
942
+ "loss": 0.0002,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0033630704062640395,
947
+ "grad_norm": 0.6408913731575012,
948
+ "learning_rate": 3.653368421052632e-05,
949
+ "loss": 0.0931,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0033887426994416276,
954
+ "grad_norm": 0.005842825397849083,
955
+ "learning_rate": 3.600421052631579e-05,
956
+ "loss": 0.0002,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0034144149926192157,
961
+ "grad_norm": 0.005725574214011431,
962
+ "learning_rate": 3.547473684210526e-05,
963
+ "loss": 0.0002,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.003440087285796804,
968
+ "grad_norm": 0.006068081129342318,
969
+ "learning_rate": 3.494526315789474e-05,
970
+ "loss": 0.0002,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.003465759578974392,
975
+ "grad_norm": 0.00514700124040246,
976
+ "learning_rate": 3.4415789473684216e-05,
977
+ "loss": 0.0002,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.00349143187215198,
982
+ "grad_norm": 0.005522563587874174,
983
+ "learning_rate": 3.3886315789473686e-05,
984
+ "loss": 0.0002,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0035171041653295682,
989
+ "grad_norm": 0.0057330005802214146,
990
+ "learning_rate": 3.3356842105263156e-05,
991
+ "loss": 0.0002,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.003542776458507156,
996
+ "grad_norm": 0.0057954080402851105,
997
+ "learning_rate": 3.2827368421052634e-05,
998
+ "loss": 0.0002,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.003568448751684744,
1003
+ "grad_norm": 0.005006751511245966,
1004
+ "learning_rate": 3.2297894736842104e-05,
1005
+ "loss": 0.0002,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.003594121044862332,
1010
+ "grad_norm": 0.005032096989452839,
1011
+ "learning_rate": 3.176842105263158e-05,
1012
+ "loss": 0.0002,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0036197933380399203,
1017
+ "grad_norm": 0.004935144912451506,
1018
+ "learning_rate": 3.123894736842106e-05,
1019
+ "loss": 0.0002,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0036454656312175085,
1024
+ "grad_norm": 0.00508884247392416,
1025
+ "learning_rate": 3.070947368421053e-05,
1026
+ "loss": 0.0002,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0036711379243950966,
1031
+ "grad_norm": 0.004769055638462305,
1032
+ "learning_rate": 3.018e-05,
1033
+ "loss": 0.0002,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0036968102175726847,
1038
+ "grad_norm": 0.004287198651582003,
1039
+ "learning_rate": 2.9650526315789473e-05,
1040
+ "loss": 0.0002,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.003722482510750273,
1045
+ "grad_norm": 0.004471136257052422,
1046
+ "learning_rate": 2.912105263157895e-05,
1047
+ "loss": 0.0002,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.003748154803927861,
1052
+ "grad_norm": 0.004509101156145334,
1053
+ "learning_rate": 2.8591578947368424e-05,
1054
+ "loss": 0.0002,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.003773827097105449,
1059
+ "grad_norm": 0.005288159940391779,
1060
+ "learning_rate": 2.8062105263157894e-05,
1061
+ "loss": 0.0002,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0037994993902830372,
1066
+ "grad_norm": 1.4431769847869873,
1067
+ "learning_rate": 2.753263157894737e-05,
1068
+ "loss": 0.4431,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.003825171683460625,
1073
+ "grad_norm": 2.757993459701538,
1074
+ "learning_rate": 2.7003157894736845e-05,
1075
+ "loss": 1.9569,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.003850843976638213,
1080
+ "grad_norm": 6.777806758880615,
1081
+ "learning_rate": 2.6473684210526315e-05,
1082
+ "loss": 2.2696,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.003850843976638213,
1087
+ "eval_loss": 0.41922199726104736,
1088
+ "eval_runtime": 1184.8981,
1089
+ "eval_samples_per_second": 13.843,
1090
+ "eval_steps_per_second": 3.461,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.842158118522061e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null