aleegis10 commited on
Commit
4b27273
·
verified ·
1 Parent(s): b8fd73e

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 sha256:0ada6d0402f3adec5e07edb95007b4a11b4757904874daf17aafd9c952d36c2f
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108de802ac7146106f21de76a0d0cddfdbac2aa9b38aacda7e41dff9190fd6b2
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b82bbfdf91a37c38a45d972f7e7d47c50d968b6f33ebeb9352fbebaf42d53cd
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705fc4d472ed36e561b5fb104ccb84e24f9c8c7dcb417e7d2de1687e4190e971
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d3f5dde80d972579966edfc7c3d048ade241ebd8cf602c68665bd0209e48dbf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21df8a734424660e48342ee6255798036a6679c5e54703023c54555b758d08b7
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": 10.302728652954102,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.011235323858210213,
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": 448.396,
732
  "eval_steps_per_second": 112.114,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 22393857245184.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.299948692321777,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.016852985787315318,
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": 448.396,
732
  "eval_steps_per_second": 112.114,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.011347677096792314,
737
+ "grad_norm": 0.48272770643234253,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 41.1792,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.011460030335374417,
744
+ "grad_norm": 0.6370357871055603,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 41.1893,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.01157238357395652,
751
+ "grad_norm": 0.48485246300697327,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 41.2053,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.01168473681253862,
758
+ "grad_norm": 0.3337991535663605,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 41.2021,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.011797090051120724,
765
+ "grad_norm": 0.35370728373527527,
766
+ "learning_rate": 5e-05,
767
+ "loss": 41.2011,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.011909443289702826,
772
+ "grad_norm": 0.2889159023761749,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 41.2157,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.012021796528284927,
779
+ "grad_norm": 0.2480829358100891,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 41.21,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.01213414976686703,
786
+ "grad_norm": 0.37383803725242615,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 41.1819,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.012246503005449131,
793
+ "grad_norm": 0.24803395569324493,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 41.224,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.012358856244031234,
800
+ "grad_norm": 0.24491317570209503,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 41.2214,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.012471209482613337,
807
+ "grad_norm": 0.32773756980895996,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 41.1884,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.012583562721195438,
814
+ "grad_norm": 0.2478872686624527,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 41.2284,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.01269591595977754,
821
+ "grad_norm": 0.312561571598053,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 41.2039,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.012808269198359644,
828
+ "grad_norm": 0.22887419164180756,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 41.2022,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.012920622436941745,
835
+ "grad_norm": 0.2290506660938263,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 41.203,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.013032975675523847,
842
+ "grad_norm": 0.33003920316696167,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 41.2017,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.013145328914105948,
849
+ "grad_norm": 0.22017890214920044,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 41.2118,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.013257682152688051,
856
+ "grad_norm": 0.30501383543014526,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 41.2039,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.013370035391270154,
863
+ "grad_norm": 0.22522194683551788,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 41.2196,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.013482388629852255,
870
+ "grad_norm": 0.28780046105384827,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 41.2061,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.013594741868434358,
877
+ "grad_norm": 0.25612780451774597,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 41.2006,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.013707095107016459,
884
+ "grad_norm": 0.2527892291545868,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 41.2054,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.013819448345598562,
891
+ "grad_norm": 0.2517006993293762,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 41.1992,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.013931801584180665,
898
+ "grad_norm": 0.23754863440990448,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 41.2099,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.014044154822762766,
905
+ "grad_norm": 0.17713980376720428,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 41.1868,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.014156508061344868,
912
+ "grad_norm": 0.24930499494075775,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 41.2081,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.014268861299926971,
919
+ "grad_norm": 0.25248026847839355,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 41.2137,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.014381214538509072,
926
+ "grad_norm": 0.29542839527130127,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 41.2147,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.014493567777091175,
933
+ "grad_norm": 0.280669242143631,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 41.2003,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.014605921015673276,
940
+ "grad_norm": 0.23233091831207275,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 41.2121,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.014718274254255379,
947
+ "grad_norm": 0.29116538166999817,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 41.1926,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.014830627492837482,
954
+ "grad_norm": 0.24843358993530273,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 41.1912,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.014942980731419583,
961
+ "grad_norm": 0.2787754535675049,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 41.1993,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.015055333970001685,
968
+ "grad_norm": 0.2419159710407257,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 41.2065,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.015167687208583788,
975
+ "grad_norm": 0.24362392723560333,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 41.203,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.01528004044716589,
982
+ "grad_norm": 0.3140493333339691,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 41.2071,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.015392393685747992,
989
+ "grad_norm": 0.2296908050775528,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 41.2123,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.015504746924330093,
996
+ "grad_norm": 0.26365184783935547,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 41.1996,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.015617100162912196,
1003
+ "grad_norm": 0.2602303922176361,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 41.2149,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.015729453401494297,
1010
+ "grad_norm": 0.27265465259552,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 41.2025,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.0158418066400764,
1017
+ "grad_norm": 0.26106128096580505,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 41.2142,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.015954159878658503,
1024
+ "grad_norm": 0.23775847256183624,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 41.21,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.016066513117240604,
1031
+ "grad_norm": 0.34526339173316956,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 41.2214,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.016178866355822708,
1038
+ "grad_norm": 0.2909034788608551,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 41.2204,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.01629121959440481,
1045
+ "grad_norm": 0.2971731126308441,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 41.1924,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.01640357283298691,
1052
+ "grad_norm": 0.30135422945022583,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 41.207,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.01651592607156901,
1059
+ "grad_norm": 0.3517146110534668,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 41.2104,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.016628279310151116,
1066
+ "grad_norm": 0.36096063256263733,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 41.2063,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.016740632548733217,
1073
+ "grad_norm": 0.35298091173171997,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 41.2134,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.016852985787315318,
1080
+ "grad_norm": 0.4046837091445923,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 41.2229,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.016852985787315318,
1087
+ "eval_loss": 10.299948692321777,
1088
+ "eval_runtime": 33.4249,
1089
+ "eval_samples_per_second": 448.469,
1090
+ "eval_steps_per_second": 112.132,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 33617637015552.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null