aleegis12 commited on
Commit
f91d084
·
verified ·
1 Parent(s): b6a10bb

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 sha256:90f531ec01cce383caffb10e654b3eade8839265a804ac6ea625b0e24db8a6ee
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5816be0087df5f5af1fbe30b9516b57f73b224cd1c9de7b98ae2ce443a74eda6
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d10aa52d80f08a4f8c8832ab40ed61fb07eb2dc9ddfc7e3f561b357f9da977d
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037d3f8eb62c3279d74ab2880ddca895ccea1f1a4e68c6cbcbed7a631b611d75
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbb5f32a452047fe1001f1a1bc9fdc544d2e1c54acdc3ec0e1e04fa31a816c3b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:047fc5a229b3878cc2307b6c46a3e4634252681aa115584c010119b72bc8fbfc
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": 0.13724249601364136,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.461361014994233,
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": 7.571,
732
  "eval_steps_per_second": 1.908,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2.6323561949115187e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.12923087179660797,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.6920415224913494,
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": 7.571,
732
  "eval_steps_per_second": 1.908,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.4659746251441753,
737
+ "grad_norm": 0.16693854331970215,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.1229,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.47058823529411764,
744
+ "grad_norm": 0.14586929976940155,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.1424,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.47520184544405997,
751
+ "grad_norm": 0.13790450990200043,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.1256,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.4798154555940023,
758
+ "grad_norm": 0.1593526005744934,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.1509,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.4844290657439446,
765
+ "grad_norm": 0.16184355318546295,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.1738,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.48904267589388695,
772
+ "grad_norm": 0.14446185529232025,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.1207,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.4936562860438293,
779
+ "grad_norm": 0.132633239030838,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.1295,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.4982698961937716,
786
+ "grad_norm": 0.16127470135688782,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.1467,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5028835063437139,
793
+ "grad_norm": 1.3746932744979858,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.1863,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5074971164936563,
800
+ "grad_norm": 0.14423397183418274,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.1279,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5121107266435986,
807
+ "grad_norm": 0.1783188432455063,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.1185,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5167243367935409,
814
+ "grad_norm": 0.17310823500156403,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.1193,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5213379469434832,
821
+ "grad_norm": 0.19535663723945618,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.1534,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5259515570934256,
828
+ "grad_norm": 0.1580890715122223,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.1332,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5305651672433679,
835
+ "grad_norm": 0.23308928310871124,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.1442,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5351787773933102,
842
+ "grad_norm": 0.18780064582824707,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.1733,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.5397923875432526,
849
+ "grad_norm": 0.19831004738807678,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.1674,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.544405997693195,
856
+ "grad_norm": 0.17428018152713776,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.1362,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.5490196078431373,
863
+ "grad_norm": 0.17842572927474976,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.1655,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.5536332179930796,
870
+ "grad_norm": 0.1584247648715973,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.1181,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.558246828143022,
877
+ "grad_norm": 0.19633540511131287,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.1525,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.5628604382929643,
884
+ "grad_norm": 0.18967780470848083,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.1785,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.5674740484429066,
891
+ "grad_norm": 0.15900085866451263,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.1272,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.5720876585928489,
898
+ "grad_norm": 0.16912361979484558,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.1254,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.5767012687427913,
905
+ "grad_norm": 0.16823305189609528,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.1373,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.5813148788927336,
912
+ "grad_norm": 0.1765795350074768,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.1494,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.5859284890426759,
919
+ "grad_norm": 0.16386839747428894,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.1139,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.5905420991926182,
926
+ "grad_norm": 0.1809309720993042,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.1226,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.5951557093425606,
933
+ "grad_norm": 0.18641479313373566,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.1223,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.5997693194925029,
940
+ "grad_norm": 0.17032507061958313,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.11,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6043829296424452,
947
+ "grad_norm": 0.18085092306137085,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.1342,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6089965397923875,
954
+ "grad_norm": 0.2097395807504654,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.1622,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6136101499423299,
961
+ "grad_norm": 0.20478329062461853,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.1495,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6182237600922722,
968
+ "grad_norm": 0.16314689815044403,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.0896,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6228373702422145,
975
+ "grad_norm": 0.20483306050300598,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.1435,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.6274509803921569,
982
+ "grad_norm": 0.18159297108650208,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.111,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.6320645905420992,
989
+ "grad_norm": 0.18506605923175812,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.1047,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.6366782006920415,
996
+ "grad_norm": 0.16207557916641235,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.0933,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.6412918108419838,
1003
+ "grad_norm": 0.21236790716648102,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.143,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.6459054209919262,
1010
+ "grad_norm": 0.18207381665706635,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.1129,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.6505190311418685,
1017
+ "grad_norm": 0.17932240664958954,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.0879,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.6551326412918108,
1024
+ "grad_norm": 0.2707701325416565,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.1214,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.6597462514417531,
1031
+ "grad_norm": 0.24743866920471191,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.1767,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.6643598615916955,
1038
+ "grad_norm": 0.19047924876213074,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.0967,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.6689734717416378,
1045
+ "grad_norm": 0.21621400117874146,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.1347,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.6735870818915801,
1052
+ "grad_norm": 0.1867235153913498,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.0892,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.6782006920415224,
1059
+ "grad_norm": 0.22504442930221558,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.1389,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.6828143021914648,
1066
+ "grad_norm": 0.20804926753044128,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.0777,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.6874279123414071,
1073
+ "grad_norm": 0.21870160102844238,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.1019,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.6920415224913494,
1080
+ "grad_norm": 0.26978006958961487,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.1173,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.6920415224913494,
1087
+ "eval_loss": 0.12923087179660797,
1088
+ "eval_runtime": 47.9945,
1089
+ "eval_samples_per_second": 7.605,
1090
+ "eval_steps_per_second": 1.917,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3.948534292367278e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null