lesso commited on
Commit
92b3fc9
·
verified ·
1 Parent(s): 8755171

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 sha256:4c2a6d7f68310c78380d6c4ce36dcb947cbef25bc0c7c5dd186573b8f76d40ee
3
  size 871457448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e43d7360361b32f2b5ccdedb7e06caf5b2ee771e400271b205fc86382a12f8
3
  size 871457448
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba84b182ba6a2ec82a98476274fd79d705d0ba7632cd52cc58490614d378feb7
3
  size 443280340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bad470dce8d3957ede7ae9508a00187aaf3034d7a3d1b1a9a1b3c30d1b967694
3
  size 443280340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22cb16048613c4c5759c220f74762a10917ee15e65140948779c5f187b65214d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44bad6113ba213dfa62151c5951984ffb5126006bd795a13ce81d766c1d1fdb1
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": 1.202304482460022,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.01633186346562143,
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": 7.482,
732
  "eval_steps_per_second": 1.872,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.33964503227433e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1496460437774658,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.02449779519843214,
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": 7.482,
732
  "eval_steps_per_second": 1.872,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.01649518210027764,
737
+ "grad_norm": 0.7410888671875,
738
+ "learning_rate": 5.220947368421052e-05,
739
+ "loss": 0.7999,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.016658500734933857,
744
+ "grad_norm": 0.7798357605934143,
745
+ "learning_rate": 5.1682105263157895e-05,
746
+ "loss": 0.932,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01682181936959007,
751
+ "grad_norm": 0.7108080983161926,
752
+ "learning_rate": 5.115473684210527e-05,
753
+ "loss": 0.9403,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.016985138004246284,
758
+ "grad_norm": 0.7301442623138428,
759
+ "learning_rate": 5.062736842105263e-05,
760
+ "loss": 0.8655,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.0171484566389025,
765
+ "grad_norm": 0.6835742592811584,
766
+ "learning_rate": 5.01e-05,
767
+ "loss": 0.8765,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.017311775273558712,
772
+ "grad_norm": 0.6745396256446838,
773
+ "learning_rate": 4.9572631578947363e-05,
774
+ "loss": 0.9458,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.017475093908214927,
779
+ "grad_norm": 0.6688428521156311,
780
+ "learning_rate": 4.9045263157894736e-05,
781
+ "loss": 0.8976,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.017638412542871143,
786
+ "grad_norm": 0.6025101542472839,
787
+ "learning_rate": 4.85178947368421e-05,
788
+ "loss": 1.007,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.017801731177527355,
793
+ "grad_norm": 0.5355660319328308,
794
+ "learning_rate": 4.799052631578947e-05,
795
+ "loss": 0.893,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.01796504981218357,
800
+ "grad_norm": 0.6081918478012085,
801
+ "learning_rate": 4.746315789473684e-05,
802
+ "loss": 1.0356,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.018128368446839783,
807
+ "grad_norm": 0.6432203650474548,
808
+ "learning_rate": 4.693578947368421e-05,
809
+ "loss": 1.0259,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.018291687081496,
814
+ "grad_norm": 0.6371332406997681,
815
+ "learning_rate": 4.6408421052631576e-05,
816
+ "loss": 0.9714,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.018455005716152214,
821
+ "grad_norm": 0.632469117641449,
822
+ "learning_rate": 4.588105263157894e-05,
823
+ "loss": 0.7899,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.018618324350808426,
828
+ "grad_norm": 0.6865615248680115,
829
+ "learning_rate": 4.5353684210526314e-05,
830
+ "loss": 1.0136,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.01878164298546464,
835
+ "grad_norm": 0.735899031162262,
836
+ "learning_rate": 4.482631578947368e-05,
837
+ "loss": 0.9631,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.018944961620120857,
842
+ "grad_norm": 0.7938647270202637,
843
+ "learning_rate": 4.429894736842105e-05,
844
+ "loss": 1.0312,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.01910828025477707,
849
+ "grad_norm": 0.7992541790008545,
850
+ "learning_rate": 4.3771578947368424e-05,
851
+ "loss": 1.1253,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.019271598889433285,
856
+ "grad_norm": 0.7731001377105713,
857
+ "learning_rate": 4.324421052631579e-05,
858
+ "loss": 1.1413,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.019434917524089497,
863
+ "grad_norm": 0.8240691423416138,
864
+ "learning_rate": 4.2716842105263155e-05,
865
+ "loss": 0.9722,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.019598236158745713,
870
+ "grad_norm": 0.7312250733375549,
871
+ "learning_rate": 4.218947368421052e-05,
872
+ "loss": 0.8119,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.019761554793401928,
877
+ "grad_norm": 0.8575920462608337,
878
+ "learning_rate": 4.166210526315789e-05,
879
+ "loss": 0.9616,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.01992487342805814,
884
+ "grad_norm": 0.8943201899528503,
885
+ "learning_rate": 4.1134736842105265e-05,
886
+ "loss": 0.9458,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.020088192062714356,
891
+ "grad_norm": 0.7860243916511536,
892
+ "learning_rate": 4.060736842105263e-05,
893
+ "loss": 1.006,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.02025151069737057,
898
+ "grad_norm": 0.9303942918777466,
899
+ "learning_rate": 4.008e-05,
900
+ "loss": 0.9787,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.020414829332026783,
905
+ "grad_norm": 1.0351006984710693,
906
+ "learning_rate": 3.955263157894737e-05,
907
+ "loss": 1.1954,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.020578147966683,
912
+ "grad_norm": 0.9931172728538513,
913
+ "learning_rate": 3.9025263157894733e-05,
914
+ "loss": 0.9572,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.02074146660133921,
919
+ "grad_norm": 1.0373263359069824,
920
+ "learning_rate": 3.84978947368421e-05,
921
+ "loss": 0.9803,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.020904785235995427,
926
+ "grad_norm": 1.018931269645691,
927
+ "learning_rate": 3.797052631578947e-05,
928
+ "loss": 0.69,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.021068103870651642,
933
+ "grad_norm": 1.324196696281433,
934
+ "learning_rate": 3.744315789473684e-05,
935
+ "loss": 1.0059,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.021231422505307854,
940
+ "grad_norm": 1.19536554813385,
941
+ "learning_rate": 3.691578947368421e-05,
942
+ "loss": 0.9141,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.02139474113996407,
947
+ "grad_norm": 1.2916719913482666,
948
+ "learning_rate": 3.638842105263158e-05,
949
+ "loss": 1.0181,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.021558059774620286,
954
+ "grad_norm": 1.313924789428711,
955
+ "learning_rate": 3.5861052631578946e-05,
956
+ "loss": 1.0114,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.021721378409276498,
961
+ "grad_norm": 1.6728382110595703,
962
+ "learning_rate": 3.533368421052631e-05,
963
+ "loss": 1.151,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.021884697043932713,
968
+ "grad_norm": 1.9813265800476074,
969
+ "learning_rate": 3.4806315789473684e-05,
970
+ "loss": 1.209,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.022048015678588925,
975
+ "grad_norm": 2.619920015335083,
976
+ "learning_rate": 3.427894736842105e-05,
977
+ "loss": 1.4013,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.02221133431324514,
982
+ "grad_norm": 3.543386936187744,
983
+ "learning_rate": 3.375157894736842e-05,
984
+ "loss": 1.2687,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.022374652947901356,
989
+ "grad_norm": 2.107569932937622,
990
+ "learning_rate": 3.322421052631579e-05,
991
+ "loss": 1.1479,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.02253797158255757,
996
+ "grad_norm": 2.548245429992676,
997
+ "learning_rate": 3.269684210526316e-05,
998
+ "loss": 1.1627,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.022701290217213784,
1003
+ "grad_norm": 3.172882556915283,
1004
+ "learning_rate": 3.2169473684210525e-05,
1005
+ "loss": 1.4478,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.02286460885187,
1010
+ "grad_norm": 3.1833114624023438,
1011
+ "learning_rate": 3.164210526315789e-05,
1012
+ "loss": 1.4387,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.023027927486526212,
1017
+ "grad_norm": 3.0594396591186523,
1018
+ "learning_rate": 3.111473684210526e-05,
1019
+ "loss": 0.975,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.023191246121182427,
1024
+ "grad_norm": 3.2839081287384033,
1025
+ "learning_rate": 3.058736842105263e-05,
1026
+ "loss": 1.3071,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.02335456475583864,
1031
+ "grad_norm": 4.123104095458984,
1032
+ "learning_rate": 3.0059999999999997e-05,
1033
+ "loss": 1.6883,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.023517883390494855,
1038
+ "grad_norm": 3.278013229370117,
1039
+ "learning_rate": 2.9532631578947366e-05,
1040
+ "loss": 1.5988,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.02368120202515107,
1045
+ "grad_norm": 2.856154680252075,
1046
+ "learning_rate": 2.9005263157894738e-05,
1047
+ "loss": 0.9376,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.023844520659807283,
1052
+ "grad_norm": 3.468996524810791,
1053
+ "learning_rate": 2.8477894736842103e-05,
1054
+ "loss": 1.8904,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.0240078392944635,
1059
+ "grad_norm": 3.6459338665008545,
1060
+ "learning_rate": 2.7950526315789472e-05,
1061
+ "loss": 1.1922,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.024171157929119714,
1066
+ "grad_norm": 4.6464948654174805,
1067
+ "learning_rate": 2.7423157894736844e-05,
1068
+ "loss": 2.2418,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.024334476563775926,
1073
+ "grad_norm": 6.070025444030762,
1074
+ "learning_rate": 2.689578947368421e-05,
1075
+ "loss": 2.1127,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.02449779519843214,
1080
+ "grad_norm": 11.722772598266602,
1081
+ "learning_rate": 2.6368421052631575e-05,
1082
+ "loss": 2.0128,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.02449779519843214,
1087
+ "eval_loss": 1.1496460437774658,
1088
+ "eval_runtime": 344.5868,
1089
+ "eval_samples_per_second": 7.481,
1090
+ "eval_steps_per_second": 1.872,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.49867241151529e+16,
1121
  "train_batch_size": 4,
1122
  "trial_name": null,
1123
  "trial_params": null