lesso commited on
Commit
8d071bd
·
verified ·
1 Parent(s): b71d939

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 sha256:66bfa8ce3bee9a8c57dc049b1e01d18bfadaa583d19c879576c378a54efb11c5
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94b8c95c195da732dec1864204583fd56be31320730a5bf924ac482d58906bb
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9f91102a5841c0698324a23ff25752c26935d0aebe16912525cd78fc6e006a6
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d224c9a2c82ad07f53d4508bc3324dd952a2e096327c74d2886e3c33cae64bf
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbad62572bb8b62aab046919f8707183cb5ad16e2693807a09b0d274e992dbb7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af40305c59b68a61bc19de673aeecff2fb9374321d5ec5e9affd01755cea167
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ba1abeedc944b50dfc9c3bffbf774b90111e900acad34ff55445cc0c42e5cd9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:940eaf31ac549488b8de7c1e32bcee52e66762875735ca6474507071594055dc
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4122529029846191,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0016837567981680727,
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": 23.24,
732
  "eval_steps_per_second": 5.81,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6871654449807360.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3895690441131592,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0025256351972521088,
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": 23.24,
732
  "eval_steps_per_second": 5.81,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.0017005943661497532,
737
+ "grad_norm": 1.830669641494751,
738
+ "learning_rate": 5.220947368421052e-05,
739
+ "loss": 1.1529,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.001717431934131434,
744
+ "grad_norm": 2.187751531600952,
745
+ "learning_rate": 5.1682105263157895e-05,
746
+ "loss": 1.1956,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0017342695021131148,
751
+ "grad_norm": 2.4100587368011475,
752
+ "learning_rate": 5.115473684210527e-05,
753
+ "loss": 1.4792,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.0017511070700947954,
758
+ "grad_norm": 1.9603551626205444,
759
+ "learning_rate": 5.062736842105263e-05,
760
+ "loss": 1.0102,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0017679446380764762,
765
+ "grad_norm": 2.4023008346557617,
766
+ "learning_rate": 5.01e-05,
767
+ "loss": 1.3828,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.001784782206058157,
772
+ "grad_norm": 1.9762279987335205,
773
+ "learning_rate": 4.9572631578947363e-05,
774
+ "loss": 0.9699,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.0018016197740398376,
779
+ "grad_norm": 2.602524518966675,
780
+ "learning_rate": 4.9045263157894736e-05,
781
+ "loss": 1.4324,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0018184573420215184,
786
+ "grad_norm": 2.082958221435547,
787
+ "learning_rate": 4.85178947368421e-05,
788
+ "loss": 0.9327,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.0018352949100031992,
793
+ "grad_norm": 2.092628240585327,
794
+ "learning_rate": 4.799052631578947e-05,
795
+ "loss": 1.0704,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.0018521324779848798,
800
+ "grad_norm": 2.35976243019104,
801
+ "learning_rate": 4.746315789473684e-05,
802
+ "loss": 1.3048,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.0018689700459665606,
807
+ "grad_norm": 1.9955127239227295,
808
+ "learning_rate": 4.693578947368421e-05,
809
+ "loss": 1.0384,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.0018858076139482414,
814
+ "grad_norm": 1.7307102680206299,
815
+ "learning_rate": 4.6408421052631576e-05,
816
+ "loss": 0.6516,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.001902645181929922,
821
+ "grad_norm": 2.138718843460083,
822
+ "learning_rate": 4.588105263157894e-05,
823
+ "loss": 1.11,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0019194827499116028,
828
+ "grad_norm": 2.636967420578003,
829
+ "learning_rate": 4.5353684210526314e-05,
830
+ "loss": 1.3802,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.0019363203178932836,
835
+ "grad_norm": 1.9767322540283203,
836
+ "learning_rate": 4.482631578947368e-05,
837
+ "loss": 1.0747,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.001953157885874964,
842
+ "grad_norm": 2.2837302684783936,
843
+ "learning_rate": 4.429894736842105e-05,
844
+ "loss": 1.458,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.001969995453856645,
849
+ "grad_norm": 2.1218316555023193,
850
+ "learning_rate": 4.3771578947368424e-05,
851
+ "loss": 1.3695,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.0019868330218383258,
856
+ "grad_norm": 2.198255777359009,
857
+ "learning_rate": 4.324421052631579e-05,
858
+ "loss": 1.2477,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.0020036705898200066,
863
+ "grad_norm": 2.5957672595977783,
864
+ "learning_rate": 4.2716842105263155e-05,
865
+ "loss": 1.6195,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.002020508157801687,
870
+ "grad_norm": 2.663543224334717,
871
+ "learning_rate": 4.218947368421052e-05,
872
+ "loss": 1.373,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.0020373457257833677,
877
+ "grad_norm": 2.6968162059783936,
878
+ "learning_rate": 4.166210526315789e-05,
879
+ "loss": 1.5127,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.0020541832937650485,
884
+ "grad_norm": 1.7091691493988037,
885
+ "learning_rate": 4.1134736842105265e-05,
886
+ "loss": 0.9789,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.0020710208617467293,
891
+ "grad_norm": 1.9656262397766113,
892
+ "learning_rate": 4.060736842105263e-05,
893
+ "loss": 1.1229,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.00208785842972841,
898
+ "grad_norm": 2.574587345123291,
899
+ "learning_rate": 4.008e-05,
900
+ "loss": 1.2832,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.002104695997710091,
905
+ "grad_norm": 2.1802868843078613,
906
+ "learning_rate": 3.955263157894737e-05,
907
+ "loss": 1.2732,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.0021215335656917713,
912
+ "grad_norm": 2.221050977706909,
913
+ "learning_rate": 3.9025263157894733e-05,
914
+ "loss": 1.3506,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.002138371133673452,
919
+ "grad_norm": 2.305180072784424,
920
+ "learning_rate": 3.84978947368421e-05,
921
+ "loss": 1.5046,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.002155208701655133,
926
+ "grad_norm": 2.3971922397613525,
927
+ "learning_rate": 3.797052631578947e-05,
928
+ "loss": 1.6153,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.0021720462696368137,
933
+ "grad_norm": 2.918943405151367,
934
+ "learning_rate": 3.744315789473684e-05,
935
+ "loss": 1.3126,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0021888838376184945,
940
+ "grad_norm": 2.383126735687256,
941
+ "learning_rate": 3.691578947368421e-05,
942
+ "loss": 1.2969,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.0022057214056001753,
947
+ "grad_norm": 2.748415231704712,
948
+ "learning_rate": 3.638842105263158e-05,
949
+ "loss": 1.6051,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0022225589735818557,
954
+ "grad_norm": 2.622749090194702,
955
+ "learning_rate": 3.5861052631578946e-05,
956
+ "loss": 1.2539,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0022393965415635365,
961
+ "grad_norm": 2.3018603324890137,
962
+ "learning_rate": 3.533368421052631e-05,
963
+ "loss": 1.5917,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.0022562341095452173,
968
+ "grad_norm": 2.3571221828460693,
969
+ "learning_rate": 3.4806315789473684e-05,
970
+ "loss": 1.559,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.002273071677526898,
975
+ "grad_norm": 2.4210729598999023,
976
+ "learning_rate": 3.427894736842105e-05,
977
+ "loss": 1.2182,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.002289909245508579,
982
+ "grad_norm": 2.1901543140411377,
983
+ "learning_rate": 3.375157894736842e-05,
984
+ "loss": 1.3239,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.0023067468134902597,
989
+ "grad_norm": 2.2139675617218018,
990
+ "learning_rate": 3.322421052631579e-05,
991
+ "loss": 1.2241,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.00232358438147194,
996
+ "grad_norm": 2.451343297958374,
997
+ "learning_rate": 3.269684210526316e-05,
998
+ "loss": 1.4814,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.002340421949453621,
1003
+ "grad_norm": 2.5286779403686523,
1004
+ "learning_rate": 3.2169473684210525e-05,
1005
+ "loss": 1.4187,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.0023572595174353016,
1010
+ "grad_norm": 2.9606716632843018,
1011
+ "learning_rate": 3.164210526315789e-05,
1012
+ "loss": 1.8296,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0023740970854169824,
1017
+ "grad_norm": 2.8106110095977783,
1018
+ "learning_rate": 3.111473684210526e-05,
1019
+ "loss": 1.4331,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.0023909346533986632,
1024
+ "grad_norm": 3.4488773345947266,
1025
+ "learning_rate": 3.058736842105263e-05,
1026
+ "loss": 1.5727,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.0024077722213803436,
1031
+ "grad_norm": 3.1499035358428955,
1032
+ "learning_rate": 3.0059999999999997e-05,
1033
+ "loss": 1.2317,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0024246097893620244,
1038
+ "grad_norm": 3.0529768466949463,
1039
+ "learning_rate": 2.9532631578947366e-05,
1040
+ "loss": 1.709,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.002441447357343705,
1045
+ "grad_norm": 2.7106714248657227,
1046
+ "learning_rate": 2.9005263157894738e-05,
1047
+ "loss": 1.3478,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.002458284925325386,
1052
+ "grad_norm": 3.017458438873291,
1053
+ "learning_rate": 2.8477894736842103e-05,
1054
+ "loss": 1.2413,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.002475122493307067,
1059
+ "grad_norm": 3.3850347995758057,
1060
+ "learning_rate": 2.7950526315789472e-05,
1061
+ "loss": 1.7284,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.0024919600612887476,
1066
+ "grad_norm": 3.943105697631836,
1067
+ "learning_rate": 2.7423157894736844e-05,
1068
+ "loss": 1.7115,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.002508797629270428,
1073
+ "grad_norm": 3.5962581634521484,
1074
+ "learning_rate": 2.689578947368421e-05,
1075
+ "loss": 1.6659,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.0025256351972521088,
1080
+ "grad_norm": 2.576946258544922,
1081
+ "learning_rate": 2.6368421052631575e-05,
1082
+ "loss": 0.7988,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.0025256351972521088,
1087
+ "eval_loss": 1.3895690441131592,
1088
+ "eval_runtime": 1075.8836,
1089
+ "eval_samples_per_second": 23.243,
1090
+ "eval_steps_per_second": 5.811,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.027346358337536e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null