bbytxt commited on
Commit
12c10d5
·
verified ·
1 Parent(s): b05df60

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:ccfafaf348148ea96c61473c7dacf00540d621e7ab619148a5d06d246e680396
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d95aa465dc9196811d8165d78aee01c28f1417dd5cb35b6e7d63fc379f9f77e
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bdb9dc1e52ca08b5670b0a206602bac85192fdb0aaef101ff006de78d3536b3
3
  size 136814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15b099c8547a9e6993c4822eac561cdbd17bf70928df4cbe746beffbe6981a9
3
  size 136814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1c9330007793a699f9fb95e5b45a1a7c86fb5e1b3f0ce05c20fc24f6f47d20b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a18c937b3c5c51e73bf72fe679806e4171d75a2ef1f2b8f8249d2dc0178349b
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": 10.496562957763672,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06595218466611706,
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": 437.308,
748
  "eval_steps_per_second": 61.223,
749
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
750
  }
751
  ],
752
  "logging_steps": 1,
@@ -775,7 +1141,7 @@
775
  "attributes": {}
776
  }
777
  },
778
- "total_flos": 795475968000.0,
779
  "train_batch_size": 8,
780
  "trial_name": null,
781
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.48843765258789,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.0989282769991756,
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": 437.308,
748
  "eval_steps_per_second": 61.223,
749
  "step": 100
750
+ },
751
+ {
752
+ "epoch": 0.06661170651277823,
753
+ "grad_norm": 0.6666596531867981,
754
+ "learning_rate": 0.0001599135876488549,
755
+ "loss": 42.0117,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 0.06727122835943941,
760
+ "grad_norm": 0.546597421169281,
761
+ "learning_rate": 0.00015743756320098332,
762
+ "loss": 41.9258,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 0.06793075020610058,
767
+ "grad_norm": 0.40258997678756714,
768
+ "learning_rate": 0.0001549595053975962,
769
+ "loss": 41.9414,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 0.06859027205276175,
774
+ "grad_norm": 0.4524000883102417,
775
+ "learning_rate": 0.00015248009171495378,
776
+ "loss": 41.9805,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 0.06924979389942292,
781
+ "grad_norm": 0.39214250445365906,
782
+ "learning_rate": 0.00015,
783
+ "loss": 41.9355,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 0.06990931574608408,
788
+ "grad_norm": 0.5733072757720947,
789
+ "learning_rate": 0.00014751990828504622,
790
+ "loss": 42.0059,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 0.07056883759274526,
795
+ "grad_norm": 0.5044758319854736,
796
+ "learning_rate": 0.00014504049460240375,
797
+ "loss": 42.002,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 0.07122835943940643,
802
+ "grad_norm": 0.6467098593711853,
803
+ "learning_rate": 0.00014256243679901663,
804
+ "loss": 42.0098,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 0.0718878812860676,
809
+ "grad_norm": 0.43010029196739197,
810
+ "learning_rate": 0.00014008641235114508,
811
+ "loss": 41.9902,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 0.07254740313272877,
816
+ "grad_norm": 0.6928155422210693,
817
+ "learning_rate": 0.00013761309817915014,
818
+ "loss": 42.0234,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 0.07320692497938994,
823
+ "grad_norm": 0.44245922565460205,
824
+ "learning_rate": 0.00013514317046243058,
825
+ "loss": 41.9961,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 0.07386644682605112,
830
+ "grad_norm": 0.3800172805786133,
831
+ "learning_rate": 0.00013267730445456208,
832
+ "loss": 41.9805,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 0.07452596867271229,
837
+ "grad_norm": 0.7035552263259888,
838
+ "learning_rate": 0.00013021617429868963,
839
+ "loss": 42.0156,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 0.07518549051937345,
844
+ "grad_norm": 0.42883816361427307,
845
+ "learning_rate": 0.00012776045284322368,
846
+ "loss": 41.9395,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 0.07584501236603462,
851
+ "grad_norm": 0.32898375391960144,
852
+ "learning_rate": 0.00012531081145788987,
853
+ "loss": 41.9883,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 0.07650453421269579,
858
+ "grad_norm": 0.3533617854118347,
859
+ "learning_rate": 0.00012286791985018355,
860
+ "loss": 41.9688,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 0.07716405605935697,
865
+ "grad_norm": 0.48832958936691284,
866
+ "learning_rate": 0.00012043244588227796,
867
+ "loss": 41.9922,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 0.07782357790601814,
872
+ "grad_norm": 0.42974764108657837,
873
+ "learning_rate": 0.00011800505538843798,
874
+ "loss": 41.9609,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 0.07848309975267931,
879
+ "grad_norm": 0.32136955857276917,
880
+ "learning_rate": 0.00011558641199298727,
881
+ "loss": 41.9648,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 0.07914262159934048,
886
+ "grad_norm": 0.3226495385169983,
887
+ "learning_rate": 0.00011317717692888012,
888
+ "loss": 41.9551,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 0.07980214344600164,
893
+ "grad_norm": 0.31127500534057617,
894
+ "learning_rate": 0.00011077800885692702,
895
+ "loss": 41.9531,
896
+ "step": 121
897
+ },
898
+ {
899
+ "epoch": 0.08046166529266283,
900
+ "grad_norm": 0.4595889151096344,
901
+ "learning_rate": 0.00010838956368572334,
902
+ "loss": 41.9473,
903
+ "step": 122
904
+ },
905
+ {
906
+ "epoch": 0.081121187139324,
907
+ "grad_norm": 0.382497102022171,
908
+ "learning_rate": 0.0001060124943923303,
909
+ "loss": 41.9473,
910
+ "step": 123
911
+ },
912
+ {
913
+ "epoch": 0.08178070898598516,
914
+ "grad_norm": 0.27015018463134766,
915
+ "learning_rate": 0.0001036474508437579,
916
+ "loss": 41.9668,
917
+ "step": 124
918
+ },
919
+ {
920
+ "epoch": 0.08244023083264633,
921
+ "grad_norm": 0.28897708654403687,
922
+ "learning_rate": 0.00010129507961929748,
923
+ "loss": 41.9609,
924
+ "step": 125
925
+ },
926
+ {
927
+ "epoch": 0.08244023083264633,
928
+ "eval_loss": 10.48843765258789,
929
+ "eval_runtime": 0.114,
930
+ "eval_samples_per_second": 438.508,
931
+ "eval_steps_per_second": 61.391,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 0.0830997526793075,
936
+ "grad_norm": 0.39089083671569824,
937
+ "learning_rate": 9.895602383375353e-05,
938
+ "loss": 41.9727,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 0.08375927452596867,
943
+ "grad_norm": 0.7614229321479797,
944
+ "learning_rate": 9.663092296162251e-05,
945
+ "loss": 41.9121,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 0.08441879637262985,
950
+ "grad_norm": 0.3535849153995514,
951
+ "learning_rate": 9.432041266226686e-05,
952
+ "loss": 41.9707,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 0.08507831821929102,
957
+ "grad_norm": 0.5981976985931396,
958
+ "learning_rate": 9.202512460613219e-05,
959
+ "loss": 41.9141,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 0.08573784006595218,
964
+ "grad_norm": 0.7550039291381836,
965
+ "learning_rate": 8.97456863020546e-05,
966
+ "loss": 42.0059,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 0.08639736191261335,
971
+ "grad_norm": 0.294890820980072,
972
+ "learning_rate": 8.748272092570646e-05,
973
+ "loss": 41.959,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 0.08705688375927452,
978
+ "grad_norm": 0.4648720920085907,
979
+ "learning_rate": 8.523684714922608e-05,
980
+ "loss": 41.9805,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 0.0877164056059357,
985
+ "grad_norm": 0.6221141219139099,
986
+ "learning_rate": 8.300867897207903e-05,
987
+ "loss": 42.002,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 0.08837592745259687,
992
+ "grad_norm": 0.7409745454788208,
993
+ "learning_rate": 8.079882555319684e-05,
994
+ "loss": 41.9043,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 0.08903544929925804,
999
+ "grad_norm": 0.36831387877464294,
1000
+ "learning_rate": 7.860789104443896e-05,
1001
+ "loss": 41.9746,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 0.0896949711459192,
1006
+ "grad_norm": 0.3386104702949524,
1007
+ "learning_rate": 7.643647442542382e-05,
1008
+ "loss": 41.9551,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 0.09035449299258037,
1013
+ "grad_norm": 0.342767596244812,
1014
+ "learning_rate": 7.428516933977347e-05,
1015
+ "loss": 41.9473,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 0.09101401483924156,
1020
+ "grad_norm": 0.5757667422294617,
1021
+ "learning_rate": 7.215456393281776e-05,
1022
+ "loss": 41.998,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 0.09167353668590272,
1027
+ "grad_norm": 0.38113224506378174,
1028
+ "learning_rate": 7.004524069080096e-05,
1029
+ "loss": 41.9746,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 0.09233305853256389,
1034
+ "grad_norm": 0.4469098746776581,
1035
+ "learning_rate": 6.795777628163599e-05,
1036
+ "loss": 41.9219,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 0.09299258037922506,
1041
+ "grad_norm": 0.3035033643245697,
1042
+ "learning_rate": 6.58927413972491e-05,
1043
+ "loss": 41.9707,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 0.09365210222588623,
1048
+ "grad_norm": 0.44389528036117554,
1049
+ "learning_rate": 6.385070059755846e-05,
1050
+ "loss": 41.9824,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 0.09431162407254741,
1055
+ "grad_norm": 0.5598168969154358,
1056
+ "learning_rate": 6.183221215612904e-05,
1057
+ "loss": 41.9473,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 0.09497114591920858,
1062
+ "grad_norm": 0.33077386021614075,
1063
+ "learning_rate": 5.983782790754623e-05,
1064
+ "loss": 41.9492,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 0.09563066776586975,
1069
+ "grad_norm": 0.3129209578037262,
1070
+ "learning_rate": 5.786809309654982e-05,
1071
+ "loss": 41.9727,
1072
+ "step": 145
1073
+ },
1074
+ {
1075
+ "epoch": 0.09629018961253091,
1076
+ "grad_norm": 0.24582117795944214,
1077
+ "learning_rate": 5.592354622896944e-05,
1078
+ "loss": 41.9609,
1079
+ "step": 146
1080
+ },
1081
+ {
1082
+ "epoch": 0.09694971145919208,
1083
+ "grad_norm": 0.49745967984199524,
1084
+ "learning_rate": 5.40047189245025e-05,
1085
+ "loss": 41.9277,
1086
+ "step": 147
1087
+ },
1088
+ {
1089
+ "epoch": 0.09760923330585326,
1090
+ "grad_norm": 0.313666969537735,
1091
+ "learning_rate": 5.211213577137469e-05,
1092
+ "loss": 41.957,
1093
+ "step": 148
1094
+ },
1095
+ {
1096
+ "epoch": 0.09826875515251443,
1097
+ "grad_norm": 0.4432874917984009,
1098
+ "learning_rate": 5.024631418292274e-05,
1099
+ "loss": 41.9395,
1100
+ "step": 149
1101
+ },
1102
+ {
1103
+ "epoch": 0.0989282769991756,
1104
+ "grad_norm": 0.26742538809776306,
1105
+ "learning_rate": 4.840776425613886e-05,
1106
+ "loss": 41.9688,
1107
+ "step": 150
1108
+ },
1109
+ {
1110
+ "epoch": 0.0989282769991756,
1111
+ "eval_loss": 10.48843765258789,
1112
+ "eval_runtime": 0.1139,
1113
+ "eval_samples_per_second": 439.033,
1114
+ "eval_steps_per_second": 61.465,
1115
+ "step": 150
1116
  }
1117
  ],
1118
  "logging_steps": 1,
 
1141
  "attributes": {}
1142
  }
1143
  },
1144
+ "total_flos": 1193213952000.0,
1145
  "train_batch_size": 8,
1146
  "trial_name": null,
1147
  "trial_params": null