cilooor commited on
Commit
b519070
·
verified ·
1 Parent(s): 94107b4

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 sha256:477787f0091dfa39fe42e3d3310641f356cd39f35e7f63585a0fc22ad89b9b03
3
  size 1163996488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dfa465ab0d6a7ee1a5443d1f016e9786a54258aba51cd36e992ad31a9eaac8f
3
  size 1163996488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:479c9998037fc283f3e87a23cbe1e0f3a5fb74dc11348ae1c957e2335c0f30ba
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a533d1d085cf1b3df57990fa640bbe394dc80ef7daa57990bae1ab1de7abd8
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37c70ebce371973b6337c0835ee569c037ff160e244f9f1dea899dcbd48d8007
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a41a4031cb916a2a7b0de28c019f731f8ce660dfb48251aeba95615e7cabf3e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ec0190ac34c757a155eb68c88baf326e3bb9c4f0972c60aacd4f72225da731
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06d9dbca2d2e799f64e5db9a242e7689df5f48f98c30d95b246a79b74d68c80
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3956009149551392,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0851063829787234,
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": 13.345,
732
  "eval_steps_per_second": 3.338,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.333822821016535e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3873642683029175,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1276595744680851,
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": 13.345,
732
  "eval_steps_per_second": 3.338,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08595744680851064,
737
+ "grad_norm": 0.27041178941726685,
738
+ "learning_rate": 2.6652264608142484e-05,
739
+ "loss": 1.3885,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.08680851063829788,
744
+ "grad_norm": 0.31925514340400696,
745
+ "learning_rate": 2.623959386683056e-05,
746
+ "loss": 1.3813,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.0876595744680851,
751
+ "grad_norm": 0.30088451504707336,
752
+ "learning_rate": 2.5826584232932706e-05,
753
+ "loss": 1.4019,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08851063829787234,
758
+ "grad_norm": 0.3145081698894501,
759
+ "learning_rate": 2.5413348619158967e-05,
760
+ "loss": 1.4248,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08936170212765958,
765
+ "grad_norm": 0.3168075978755951,
766
+ "learning_rate": 2.5e-05,
767
+ "loss": 1.4345,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.0902127659574468,
772
+ "grad_norm": 0.29053518176078796,
773
+ "learning_rate": 2.458665138084104e-05,
774
+ "loss": 1.4627,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.09106382978723404,
779
+ "grad_norm": 0.30581197142601013,
780
+ "learning_rate": 2.4173415767067297e-05,
781
+ "loss": 1.4763,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.09191489361702128,
786
+ "grad_norm": 0.30414462089538574,
787
+ "learning_rate": 2.3760406133169443e-05,
788
+ "loss": 1.4436,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.09276595744680852,
793
+ "grad_norm": 0.2863653898239136,
794
+ "learning_rate": 2.334773539185752e-05,
795
+ "loss": 1.3724,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.09361702127659574,
800
+ "grad_norm": 0.30382198095321655,
801
+ "learning_rate": 2.2935516363191693e-05,
802
+ "loss": 1.504,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.09446808510638298,
807
+ "grad_norm": 0.28875938057899475,
808
+ "learning_rate": 2.2523861743738434e-05,
809
+ "loss": 1.4195,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.09531914893617022,
814
+ "grad_norm": 0.2905210256576538,
815
+ "learning_rate": 2.2112884075760347e-05,
816
+ "loss": 1.3817,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09617021276595744,
821
+ "grad_norm": 0.2973273694515228,
822
+ "learning_rate": 2.1702695716448278e-05,
823
+ "loss": 1.449,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09702127659574468,
828
+ "grad_norm": 0.3027838468551636,
829
+ "learning_rate": 2.1293408807203947e-05,
830
+ "loss": 1.3952,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09787234042553192,
835
+ "grad_norm": 0.2990623116493225,
836
+ "learning_rate": 2.088513524298165e-05,
837
+ "loss": 1.3883,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09872340425531916,
842
+ "grad_norm": 0.3011668920516968,
843
+ "learning_rate": 2.047798664169726e-05,
844
+ "loss": 1.3987,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09957446808510638,
849
+ "grad_norm": 0.31969380378723145,
850
+ "learning_rate": 2.0072074313712997e-05,
851
+ "loss": 1.3518,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.10042553191489362,
856
+ "grad_norm": 0.30738529562950134,
857
+ "learning_rate": 1.9667509231406334e-05,
858
+ "loss": 1.3921,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.10127659574468086,
863
+ "grad_norm": 0.3225458562374115,
864
+ "learning_rate": 1.9264401998831213e-05,
865
+ "loss": 1.3496,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.10212765957446808,
870
+ "grad_norm": 0.3203943371772766,
871
+ "learning_rate": 1.8862862821480025e-05,
872
+ "loss": 1.3435,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.10297872340425532,
877
+ "grad_norm": 0.33085933327674866,
878
+ "learning_rate": 1.8463001476154508e-05,
879
+ "loss": 1.3375,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.10382978723404256,
884
+ "grad_norm": 0.3215438425540924,
885
+ "learning_rate": 1.806492728095389e-05,
886
+ "loss": 1.3917,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.1046808510638298,
891
+ "grad_norm": 0.37878575921058655,
892
+ "learning_rate": 1.7668749065388385e-05,
893
+ "loss": 1.3855,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.10553191489361702,
898
+ "grad_norm": 0.33293992280960083,
899
+ "learning_rate": 1.7274575140626318e-05,
900
+ "loss": 1.3998,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.10638297872340426,
905
+ "grad_norm": 0.3338032066822052,
906
+ "learning_rate": 1.6882513269882917e-05,
907
+ "loss": 1.3869,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.1072340425531915,
912
+ "grad_norm": 0.33053869009017944,
913
+ "learning_rate": 1.6492670638958924e-05,
914
+ "loss": 1.332,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10808510638297872,
919
+ "grad_norm": 0.3593829870223999,
920
+ "learning_rate": 1.6105153826937085e-05,
921
+ "loss": 1.3798,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10893617021276596,
926
+ "grad_norm": 0.3623925745487213,
927
+ "learning_rate": 1.5720068777044476e-05,
928
+ "loss": 1.4084,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.1097872340425532,
933
+ "grad_norm": 0.3388347625732422,
934
+ "learning_rate": 1.5337520767688703e-05,
935
+ "loss": 1.3867,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.11063829787234042,
940
+ "grad_norm": 0.3582272231578827,
941
+ "learning_rate": 1.495761438367577e-05,
942
+ "loss": 1.3665,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.11148936170212766,
947
+ "grad_norm": 0.34170177578926086,
948
+ "learning_rate": 1.4580453487617745e-05,
949
+ "loss": 1.3961,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.1123404255319149,
954
+ "grad_norm": 0.3400873839855194,
955
+ "learning_rate": 1.4206141191537682e-05,
956
+ "loss": 1.33,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.11319148936170213,
961
+ "grad_norm": 0.33887210488319397,
962
+ "learning_rate": 1.383477982867984e-05,
963
+ "loss": 1.4032,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.11404255319148936,
968
+ "grad_norm": 0.3536789119243622,
969
+ "learning_rate": 1.346647092553281e-05,
970
+ "loss": 1.3669,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.1148936170212766,
975
+ "grad_norm": 0.35396888852119446,
976
+ "learning_rate": 1.3101315174073162e-05,
977
+ "loss": 1.4562,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.11574468085106383,
982
+ "grad_norm": 0.34278711676597595,
983
+ "learning_rate": 1.2739412404237306e-05,
984
+ "loss": 1.3872,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.11659574468085106,
989
+ "grad_norm": 0.37762826681137085,
990
+ "learning_rate": 1.2380861556628915e-05,
991
+ "loss": 1.4036,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.1174468085106383,
996
+ "grad_norm": 0.36072713136672974,
997
+ "learning_rate": 1.202576065546963e-05,
998
+ "loss": 1.4366,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11829787234042553,
1003
+ "grad_norm": 0.3776477575302124,
1004
+ "learning_rate": 1.1674206781800162e-05,
1005
+ "loss": 1.3829,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11914893617021277,
1010
+ "grad_norm": 0.36730504035949707,
1011
+ "learning_rate": 1.1326296046939333e-05,
1012
+ "loss": 1.4613,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.12,
1017
+ "grad_norm": 0.3442761301994324,
1018
+ "learning_rate": 1.0982123566208185e-05,
1019
+ "loss": 1.4083,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.12085106382978723,
1024
+ "grad_norm": 0.34520068764686584,
1025
+ "learning_rate": 1.064178343292641e-05,
1026
+ "loss": 1.4079,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.12170212765957447,
1031
+ "grad_norm": 0.3773599863052368,
1032
+ "learning_rate": 1.0305368692688174e-05,
1033
+ "loss": 1.4554,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.1225531914893617,
1038
+ "grad_norm": 0.3831958770751953,
1039
+ "learning_rate": 9.972971317924374e-06,
1040
+ "loss": 1.535,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.12340425531914893,
1045
+ "grad_norm": 0.3772953748703003,
1046
+ "learning_rate": 9.644682182758306e-06,
1047
+ "loss": 1.5186,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.12425531914893617,
1052
+ "grad_norm": 0.38657766580581665,
1053
+ "learning_rate": 9.320591038161574e-06,
1054
+ "loss": 1.4555,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.1251063829787234,
1059
+ "grad_norm": 0.3840479552745819,
1060
+ "learning_rate": 9.000786487417085e-06,
1061
+ "loss": 1.4507,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.12595744680851065,
1066
+ "grad_norm": 0.402510404586792,
1067
+ "learning_rate": 8.685355961895784e-06,
1068
+ "loss": 1.4325,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.12680851063829787,
1073
+ "grad_norm": 0.4714600443840027,
1074
+ "learning_rate": 8.374385697153792e-06,
1075
+ "loss": 1.5102,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1276595744680851,
1080
+ "grad_norm": 0.8784300088882446,
1081
+ "learning_rate": 8.067960709356478e-06,
1082
+ "loss": 1.4858,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1276595744680851,
1087
+ "eval_loss": 1.3873642683029175,
1088
+ "eval_runtime": 148.2667,
1089
+ "eval_samples_per_second": 13.348,
1090
+ "eval_steps_per_second": 3.339,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.002397352249262e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null