bbytxt commited on
Commit
af5ce05
·
verified ·
1 Parent(s): 01d217a

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 sha256:1f44d7b1b7710a4262297edf4dcb20085970c911b031b380c84e849d0e6c44e3
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec0691e2913008f7cb08e2dcfd2218b96f714c3778ea27282b22bbfbfa3a1fc
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afb22404d4e4533daf0f52ad8ef4141a19fc291f1ce4e990da23384cfcec76a8
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed457c2d47c39c0a06d786de91c5724f9b5480d0f3eafd1714ee61c16094b2dc
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:547e95d19b998c5bc19068c5b78fd6d5cec14671d8e6daba4f5c47c55728f426
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f49b8e285b7b290ddd2c283ca99de64f6fb14df94066cb63c967267667c0a0c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70710c409284f74d525f8db5cfaccc22a8afd29416f19c595da9242ec92d936
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.11340178549289703,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.019697641207465404,
5
  "eval_steps": 25,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -747,6 +747,372 @@
747
  "eval_samples_per_second": 3.91,
748
  "eval_steps_per_second": 0.547,
749
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
750
  }
751
  ],
752
  "logging_steps": 1,
@@ -775,7 +1141,7 @@
775
  "attributes": {}
776
  }
777
  },
778
- "total_flos": 1.7369495897112576e+17,
779
  "train_batch_size": 8,
780
  "trial_name": null,
781
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.08567950874567032,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.029546461811198108,
5
  "eval_steps": 25,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
747
  "eval_samples_per_second": 3.91,
748
  "eval_steps_per_second": 0.547,
749
  "step": 100
750
+ },
751
+ {
752
+ "epoch": 0.01989461761954006,
753
+ "grad_norm": 1.3194266557693481,
754
+ "learning_rate": 0.0001599135876488549,
755
+ "loss": 0.4517,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 0.020091594031614715,
760
+ "grad_norm": 1.0158177614212036,
761
+ "learning_rate": 0.00015743756320098332,
762
+ "loss": 0.4222,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 0.02028857044368937,
767
+ "grad_norm": 0.84644615650177,
768
+ "learning_rate": 0.0001549595053975962,
769
+ "loss": 0.3635,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 0.020485546855764022,
774
+ "grad_norm": 0.6677044630050659,
775
+ "learning_rate": 0.00015248009171495378,
776
+ "loss": 0.2531,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 0.020682523267838676,
781
+ "grad_norm": 0.5319753289222717,
782
+ "learning_rate": 0.00015,
783
+ "loss": 0.2562,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 0.02087949967991333,
788
+ "grad_norm": 0.5926326513290405,
789
+ "learning_rate": 0.00014751990828504622,
790
+ "loss": 0.3177,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 0.021076476091987983,
795
+ "grad_norm": 0.8615707755088806,
796
+ "learning_rate": 0.00014504049460240375,
797
+ "loss": 0.2798,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 0.021273452504062637,
802
+ "grad_norm": 0.5553646683692932,
803
+ "learning_rate": 0.00014256243679901663,
804
+ "loss": 0.3154,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 0.021470428916137294,
809
+ "grad_norm": 0.42339223623275757,
810
+ "learning_rate": 0.00014008641235114508,
811
+ "loss": 0.2716,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 0.021667405328211948,
816
+ "grad_norm": 0.46130532026290894,
817
+ "learning_rate": 0.00013761309817915014,
818
+ "loss": 0.217,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 0.0218643817402866,
823
+ "grad_norm": 0.42555496096611023,
824
+ "learning_rate": 0.00013514317046243058,
825
+ "loss": 0.2988,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 0.022061358152361255,
830
+ "grad_norm": 0.47253310680389404,
831
+ "learning_rate": 0.00013267730445456208,
832
+ "loss": 0.2824,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 0.02225833456443591,
837
+ "grad_norm": 0.7298460602760315,
838
+ "learning_rate": 0.00013021617429868963,
839
+ "loss": 0.2986,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 0.022455310976510563,
844
+ "grad_norm": 0.575012743473053,
845
+ "learning_rate": 0.00012776045284322368,
846
+ "loss": 0.2342,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 0.022652287388585216,
851
+ "grad_norm": 0.5378597974777222,
852
+ "learning_rate": 0.00012531081145788987,
853
+ "loss": 0.2058,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 0.02284926380065987,
858
+ "grad_norm": 0.8967413902282715,
859
+ "learning_rate": 0.00012286791985018355,
860
+ "loss": 0.3315,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 0.023046240212734524,
865
+ "grad_norm": 0.6629744172096252,
866
+ "learning_rate": 0.00012043244588227796,
867
+ "loss": 0.3345,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 0.02324321662480918,
872
+ "grad_norm": 0.5112919807434082,
873
+ "learning_rate": 0.00011800505538843798,
874
+ "loss": 0.2614,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 0.023440193036883834,
879
+ "grad_norm": 0.34445106983184814,
880
+ "learning_rate": 0.00011558641199298727,
881
+ "loss": 0.2409,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 0.023637169448958488,
886
+ "grad_norm": 0.5876243710517883,
887
+ "learning_rate": 0.00011317717692888012,
888
+ "loss": 0.2454,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 0.02383414586103314,
893
+ "grad_norm": 0.5282692909240723,
894
+ "learning_rate": 0.00011077800885692702,
895
+ "loss": 0.283,
896
+ "step": 121
897
+ },
898
+ {
899
+ "epoch": 0.024031122273107795,
900
+ "grad_norm": 0.8354734778404236,
901
+ "learning_rate": 0.00010838956368572334,
902
+ "loss": 0.3019,
903
+ "step": 122
904
+ },
905
+ {
906
+ "epoch": 0.02422809868518245,
907
+ "grad_norm": 0.5572185516357422,
908
+ "learning_rate": 0.0001060124943923303,
909
+ "loss": 0.2843,
910
+ "step": 123
911
+ },
912
+ {
913
+ "epoch": 0.024425075097257103,
914
+ "grad_norm": 0.4937724173069,
915
+ "learning_rate": 0.0001036474508437579,
916
+ "loss": 0.2486,
917
+ "step": 124
918
+ },
919
+ {
920
+ "epoch": 0.024622051509331756,
921
+ "grad_norm": 0.658233106136322,
922
+ "learning_rate": 0.00010129507961929748,
923
+ "loss": 0.2915,
924
+ "step": 125
925
+ },
926
+ {
927
+ "epoch": 0.024622051509331756,
928
+ "eval_loss": 0.07672200351953506,
929
+ "eval_runtime": 10.6957,
930
+ "eval_samples_per_second": 4.675,
931
+ "eval_steps_per_second": 0.654,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 0.02481902792140641,
936
+ "grad_norm": 0.6942847967147827,
937
+ "learning_rate": 9.895602383375353e-05,
938
+ "loss": 0.3618,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 0.025016004333481067,
943
+ "grad_norm": 0.9075064063072205,
944
+ "learning_rate": 9.663092296162251e-05,
945
+ "loss": 0.3206,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 0.02521298074555572,
950
+ "grad_norm": 0.5630618333816528,
951
+ "learning_rate": 9.432041266226686e-05,
952
+ "loss": 0.2901,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 0.025409957157630374,
957
+ "grad_norm": 0.5655243396759033,
958
+ "learning_rate": 9.202512460613219e-05,
959
+ "loss": 0.2592,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 0.025606933569705028,
964
+ "grad_norm": 0.6408135890960693,
965
+ "learning_rate": 8.97456863020546e-05,
966
+ "loss": 0.3255,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 0.02580390998177968,
971
+ "grad_norm": 0.4605986177921295,
972
+ "learning_rate": 8.748272092570646e-05,
973
+ "loss": 0.2667,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 0.026000886393854335,
978
+ "grad_norm": 0.6698881387710571,
979
+ "learning_rate": 8.523684714922608e-05,
980
+ "loss": 0.2609,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 0.02619786280592899,
985
+ "grad_norm": 0.5498625636100769,
986
+ "learning_rate": 8.300867897207903e-05,
987
+ "loss": 0.2256,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 0.026394839218003643,
992
+ "grad_norm": 0.5972995162010193,
993
+ "learning_rate": 8.079882555319684e-05,
994
+ "loss": 0.2337,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 0.0265918156300783,
999
+ "grad_norm": 0.9262932538986206,
1000
+ "learning_rate": 7.860789104443896e-05,
1001
+ "loss": 0.4045,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 0.026788792042152954,
1006
+ "grad_norm": 0.7597740888595581,
1007
+ "learning_rate": 7.643647442542382e-05,
1008
+ "loss": 0.3238,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 0.026985768454227607,
1013
+ "grad_norm": 0.6598590612411499,
1014
+ "learning_rate": 7.428516933977347e-05,
1015
+ "loss": 0.2864,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 0.02718274486630226,
1020
+ "grad_norm": 1.9483425617218018,
1021
+ "learning_rate": 7.215456393281776e-05,
1022
+ "loss": 0.2428,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 0.027379721278376914,
1027
+ "grad_norm": 0.6512977480888367,
1028
+ "learning_rate": 7.004524069080096e-05,
1029
+ "loss": 0.2453,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 0.027576697690451568,
1034
+ "grad_norm": 0.864540159702301,
1035
+ "learning_rate": 6.795777628163599e-05,
1036
+ "loss": 0.2991,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 0.027773674102526222,
1041
+ "grad_norm": 0.7853538393974304,
1042
+ "learning_rate": 6.58927413972491e-05,
1043
+ "loss": 0.2653,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 0.027970650514600875,
1048
+ "grad_norm": 0.6818575263023376,
1049
+ "learning_rate": 6.385070059755846e-05,
1050
+ "loss": 0.2376,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 0.02816762692667553,
1055
+ "grad_norm": 0.8303399085998535,
1056
+ "learning_rate": 6.183221215612904e-05,
1057
+ "loss": 0.2446,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 0.028364603338750186,
1062
+ "grad_norm": 0.4680931270122528,
1063
+ "learning_rate": 5.983782790754623e-05,
1064
+ "loss": 0.1331,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 0.02856157975082484,
1069
+ "grad_norm": 0.6611976623535156,
1070
+ "learning_rate": 5.786809309654982e-05,
1071
+ "loss": 0.1828,
1072
+ "step": 145
1073
+ },
1074
+ {
1075
+ "epoch": 0.028758556162899494,
1076
+ "grad_norm": 0.5369855761528015,
1077
+ "learning_rate": 5.592354622896944e-05,
1078
+ "loss": 0.1183,
1079
+ "step": 146
1080
+ },
1081
+ {
1082
+ "epoch": 0.028955532574974147,
1083
+ "grad_norm": 0.8444812893867493,
1084
+ "learning_rate": 5.40047189245025e-05,
1085
+ "loss": 0.1247,
1086
+ "step": 147
1087
+ },
1088
+ {
1089
+ "epoch": 0.0291525089870488,
1090
+ "grad_norm": 0.8747226595878601,
1091
+ "learning_rate": 5.211213577137469e-05,
1092
+ "loss": 0.1633,
1093
+ "step": 148
1094
+ },
1095
+ {
1096
+ "epoch": 0.029349485399123455,
1097
+ "grad_norm": 0.8830420970916748,
1098
+ "learning_rate": 5.024631418292274e-05,
1099
+ "loss": 0.1816,
1100
+ "step": 149
1101
+ },
1102
+ {
1103
+ "epoch": 0.029546461811198108,
1104
+ "grad_norm": 3.1225264072418213,
1105
+ "learning_rate": 4.840776425613886e-05,
1106
+ "loss": 0.2376,
1107
+ "step": 150
1108
+ },
1109
+ {
1110
+ "epoch": 0.029546461811198108,
1111
+ "eval_loss": 0.08567950874567032,
1112
+ "eval_runtime": 9.1661,
1113
+ "eval_samples_per_second": 5.455,
1114
+ "eval_steps_per_second": 0.764,
1115
+ "step": 150
1116
  }
1117
  ],
1118
  "logging_steps": 1,
 
1141
  "attributes": {}
1142
  }
1143
  },
1144
+ "total_flos": 2.6110274477595034e+17,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null