aleegis09 commited on
Commit
2bd5629
·
verified ·
1 Parent(s): 65b2d69

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 sha256:5c70f7eeeeab245b3b3e092513a0d2c70ea93919a4c9dc02a571cab737f82fab
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4693608aa8f6900128bbfc5af422e2bd2b8b0fb10da32c2ef3cfd5f12b28c7f
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18bff1341a79c230c4bf19f255d1d655e1e9a1430dcc66d34f14a022fa7ab807
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7aeded0a534c850708dbd8a23a2da64f7875c20c90ee1b54c6c3cdfc39c498
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b29e93411c9c103e6b6784d3b92795a7b936a1e8055ea7a67272d66e762aecf3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03badf1f3fa1534df44cdd53538be90c7b60189d0b01b3bf97ce41f7327e32a9
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": 1.244010329246521,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.20171457387796268,
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": 17.864,
732
  "eval_steps_per_second": 4.471,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 6.11345159380009e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2367478609085083,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.30257186081694404,
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": 17.864,
732
  "eval_steps_per_second": 4.471,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.2037317196167423,
737
+ "grad_norm": 0.08799391239881516,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.8839,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.20574886535552195,
744
+ "grad_norm": 0.10215424001216888,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.0197,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.20776601109430157,
751
+ "grad_norm": 0.10634000599384308,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.3072,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.20978315683308119,
758
+ "grad_norm": 0.1186082512140274,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.3916,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.2118003025718608,
765
+ "grad_norm": 0.11218155175447464,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.2838,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.21381744831064045,
772
+ "grad_norm": 0.10455965995788574,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1963,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.21583459404942007,
779
+ "grad_norm": 0.10137539356946945,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.2903,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.2178517397881997,
786
+ "grad_norm": 0.10439775139093399,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.3084,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.21986888552697934,
793
+ "grad_norm": 0.1050877645611763,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.22,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.22188603126575895,
800
+ "grad_norm": 0.0972098559141159,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.2247,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.22390317700453857,
807
+ "grad_norm": 0.0988449677824974,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.3059,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.2259203227433182,
814
+ "grad_norm": 0.10206424444913864,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.2342,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.22793746848209784,
821
+ "grad_norm": 0.10969218611717224,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.3066,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.22995461422087746,
828
+ "grad_norm": 0.10205613821744919,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.3759,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.23197175995965708,
835
+ "grad_norm": 0.09486889839172363,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.2384,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.23398890569843672,
842
+ "grad_norm": 0.09478174895048141,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.2193,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.23600605143721634,
849
+ "grad_norm": 0.09804787486791611,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1843,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.23802319717599596,
856
+ "grad_norm": 0.09700791537761688,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2362,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.2400403429147756,
863
+ "grad_norm": 0.09541492164134979,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.2784,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.24205748865355523,
870
+ "grad_norm": 0.08745624125003815,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.2545,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.24407463439233484,
877
+ "grad_norm": 0.09270763397216797,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.2524,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.24609178013111446,
884
+ "grad_norm": 0.08937028050422668,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.2028,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2481089258698941,
891
+ "grad_norm": 0.0885753333568573,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.2581,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.25012607160867373,
898
+ "grad_norm": 0.09514176100492477,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1944,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.2521432173474534,
905
+ "grad_norm": 0.09922561049461365,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.2733,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.25416036308623297,
912
+ "grad_norm": 0.10416948795318604,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.2874,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.2561775088250126,
919
+ "grad_norm": 0.11304823309183121,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.3048,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.25819465456379226,
926
+ "grad_norm": 0.10646986216306686,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.2153,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.26021180030257185,
933
+ "grad_norm": 0.1145567074418068,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.2689,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.2622289460413515,
940
+ "grad_norm": 0.11052802205085754,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.1292,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.2642460917801311,
947
+ "grad_norm": 0.12537676095962524,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.3113,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.26626323751891073,
954
+ "grad_norm": 0.13168595731258392,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1798,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.2682803832576904,
961
+ "grad_norm": 0.14621612429618835,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.2207,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.27029752899646997,
968
+ "grad_norm": 0.14606055617332458,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2009,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.2723146747352496,
975
+ "grad_norm": 0.15578874945640564,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1816,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.27433182047402926,
982
+ "grad_norm": 0.13477180898189545,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.1475,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.27634896621280886,
989
+ "grad_norm": 0.14892345666885376,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.3177,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2783661119515885,
996
+ "grad_norm": 0.15720705687999725,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1692,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.28038325769036815,
1003
+ "grad_norm": 0.15325337648391724,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2229,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.28240040342914774,
1010
+ "grad_norm": 0.15675581991672516,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.1527,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.2844175491679274,
1017
+ "grad_norm": 0.18639573454856873,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2428,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.28643469490670703,
1024
+ "grad_norm": 0.8300725817680359,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.8962,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.2884518406454866,
1031
+ "grad_norm": 0.18652969598770142,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.9844,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.29046898638426627,
1038
+ "grad_norm": 0.19171595573425293,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.0414,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2924861321230459,
1045
+ "grad_norm": 0.25834333896636963,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.9204,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.2945032778618255,
1052
+ "grad_norm": 0.23552948236465454,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.0757,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.29652042360060515,
1059
+ "grad_norm": 0.19757910072803497,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1506,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.29853756933938475,
1066
+ "grad_norm": 0.20587892830371857,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.0637,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.3005547150781644,
1073
+ "grad_norm": 0.2713274359703064,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.0729,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.30257186081694404,
1080
+ "grad_norm": 0.8860509991645813,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.4406,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.30257186081694404,
1087
+ "eval_loss": 1.2367478609085083,
1088
+ "eval_runtime": 46.7491,
1089
+ "eval_samples_per_second": 17.861,
1090
+ "eval_steps_per_second": 4.471,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 9.166041090569011e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null