0x1202 commited on
Commit
4cf16d6
·
verified ·
1 Parent(s): dab2615

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 sha256:2e95b0e962e31121ab55f9d6ea1e8451d4c0ae7da9efa2ec7137f15c305ff41a
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1e6f28e93fcc68d8bf026107844e3dc6b82078ac2361244ab58ef51f5a48b4
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78038e895ee663f09683ae49f7ee99304b4f0242d324c73513dabcc19742b2c3
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab9bc5472bb100dc765e57fa0d6e543428b706ad65208c0119afc1530873a1c
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd52ed773117db2548e14e7e15ad8b98ea927708d98fddbe65a4cbd116f52fac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8f84b6794e1cd8014d0da9ab663e16738b7cc504167512ce7be788196eeb5b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7188636064529419,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.009493745994825909,
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": 15.234,
732
  "eval_steps_per_second": 3.809,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 8.68563864696914e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6873039603233337,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.014240618992238862,
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": 15.234,
732
  "eval_steps_per_second": 3.809,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.009588683454774167,
737
+ "grad_norm": 0.262162446975708,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.5949,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.009683620914722427,
744
+ "grad_norm": 0.3056875765323639,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.5478,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.009778558374670687,
751
+ "grad_norm": 0.3404836654663086,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.6003,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.009873495834618945,
758
+ "grad_norm": 0.3518320322036743,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.6374,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.009968433294567204,
765
+ "grad_norm": 0.35517260432243347,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.6345,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.010063370754515463,
772
+ "grad_norm": 0.33211418986320496,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.66,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.010158308214463722,
779
+ "grad_norm": 0.376034677028656,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.7352,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01025324567441198,
786
+ "grad_norm": 0.33594802021980286,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.7592,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.01034818313436024,
793
+ "grad_norm": 0.34336787462234497,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.6384,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.010443120594308498,
800
+ "grad_norm": 0.40107351541519165,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.6868,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.010538058054256758,
807
+ "grad_norm": 0.6450880169868469,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.7392,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.010632995514205018,
814
+ "grad_norm": 0.3932429850101471,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.7374,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.010727932974153276,
821
+ "grad_norm": 0.37924253940582275,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.7595,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.010822870434101536,
828
+ "grad_norm": 0.38906195759773254,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.6517,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.010917807894049794,
835
+ "grad_norm": 0.41941317915916443,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.7181,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.011012745353998054,
842
+ "grad_norm": 0.42237669229507446,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.7399,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.011107682813946312,
849
+ "grad_norm": 0.4199109673500061,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.6972,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.011202620273894572,
856
+ "grad_norm": 0.43909701704978943,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.6862,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.011297557733842832,
863
+ "grad_norm": 0.4287319779396057,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.7394,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.01139249519379109,
870
+ "grad_norm": 0.5357159972190857,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.7993,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.01148743265373935,
877
+ "grad_norm": 0.4030955731868744,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.6689,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.011582370113687608,
884
+ "grad_norm": 0.4994092583656311,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.7805,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.011677307573635868,
891
+ "grad_norm": 0.5699156522750854,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.8274,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.011772245033584126,
898
+ "grad_norm": 0.7980059385299683,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.6721,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.011867182493532386,
905
+ "grad_norm": 0.36257463693618774,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.7177,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.011962119953480645,
912
+ "grad_norm": 0.39041903614997864,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.6868,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.012057057413428903,
919
+ "grad_norm": 0.40323406457901,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.7554,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.012151994873377163,
926
+ "grad_norm": 0.41979482769966125,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.6953,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.012246932333325421,
933
+ "grad_norm": 0.392555296421051,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.759,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.012341869793273681,
940
+ "grad_norm": 0.39178863167762756,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.7017,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.01243680725322194,
947
+ "grad_norm": 0.4052543044090271,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.7917,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.0125317447131702,
954
+ "grad_norm": 0.37675926089286804,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.5898,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.012626682173118459,
961
+ "grad_norm": 0.4015160799026489,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.7128,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.012721619633066717,
968
+ "grad_norm": 0.41348764300346375,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.789,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.012816557093014977,
975
+ "grad_norm": 0.4197676479816437,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.7832,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.012911494552963235,
982
+ "grad_norm": 0.4502415060997009,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.7892,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.013006432012911495,
989
+ "grad_norm": 0.4396166205406189,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.7513,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.013101369472859753,
996
+ "grad_norm": 0.4914814233779907,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.7425,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.013196306932808013,
1003
+ "grad_norm": 0.449947714805603,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.7403,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.013291244392756273,
1010
+ "grad_norm": 0.4686639606952667,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.7091,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.01338618185270453,
1017
+ "grad_norm": 0.5162703990936279,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.812,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.01348111931265279,
1024
+ "grad_norm": 0.524587869644165,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.7092,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.013576056772601049,
1031
+ "grad_norm": 0.4877658188343048,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.7545,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.013670994232549308,
1038
+ "grad_norm": 0.4884006083011627,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.6984,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.013765931692497567,
1045
+ "grad_norm": 0.5572161674499512,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.703,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.013860869152445826,
1052
+ "grad_norm": 0.5526790022850037,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.7167,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.013955806612394086,
1059
+ "grad_norm": 0.5765847563743591,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.6563,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.014050744072342344,
1066
+ "grad_norm": 0.7077249884605408,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.6601,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.014145681532290604,
1073
+ "grad_norm": 0.5818340182304382,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.5735,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.014240618992238862,
1080
+ "grad_norm": 0.6904491186141968,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.6129,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.014240618992238862,
1087
+ "eval_loss": 0.6873039603233337,
1088
+ "eval_runtime": 1164.2998,
1089
+ "eval_samples_per_second": 15.237,
1090
+ "eval_steps_per_second": 3.809,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 1.3014125233412506e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null