aleegis10 commited on
Commit
73faa44
·
verified ·
1 Parent(s): 3fdb801

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 sha256:92da10b2aab8bce8f3dba5614a9aaf9a059162afd16230051c0b6ba978fbf657
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3dc518db32de98fc291f89d0844162ab1cd33a12f42ae61f931c0949dc8359a
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c06df4650860d3efd1685de2c458c5cd4ddcb16a8f2c38d47b62a0cacc8132b7
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc58345248ce60291fe6a3e4dd583b110e226ca39147bc92cbc0d65d5c8e09ea
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fda109e1319443dedd2496afda05a126f3531d30415fddf50ca9d30c7a06356
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed6dc4e842ea1c447e74751ef3024245838f11a2161f98ebd5377c9aa19a160
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": 0.33665910363197327,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.5037593984962405,
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": 26.146,
732
  "eval_steps_per_second": 6.536,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3.912939924042547e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.33286720514297485,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.255639097744361,
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": 26.146,
732
  "eval_steps_per_second": 6.536,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.518796992481203,
737
+ "grad_norm": 0.08410786837339401,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.2325,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.5338345864661656,
744
+ "grad_norm": 0.1020403653383255,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.3037,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.5488721804511278,
751
+ "grad_norm": 0.1161748468875885,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.3199,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.5639097744360901,
758
+ "grad_norm": 0.09512785822153091,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 0.2436,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.5789473684210527,
765
+ "grad_norm": 0.11340221762657166,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.2944,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.5939849624060152,
772
+ "grad_norm": 0.10009784251451492,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.271,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.6090225563909775,
779
+ "grad_norm": 0.11128649860620499,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 0.3568,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.6240601503759398,
786
+ "grad_norm": 0.13336911797523499,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.3979,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.6390977443609023,
793
+ "grad_norm": 0.11907505244016647,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.2867,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.6541353383458648,
800
+ "grad_norm": 0.12129438668489456,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.3131,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.669172932330827,
807
+ "grad_norm": 0.12968038022518158,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.3293,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.6842105263157894,
814
+ "grad_norm": 0.11441412568092346,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 0.2757,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.699248120300752,
821
+ "grad_norm": 0.14484111964702606,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.3401,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.7142857142857144,
828
+ "grad_norm": 0.20032306015491486,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 0.4128,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.7293233082706767,
835
+ "grad_norm": 0.1268623322248459,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.3146,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 1.744360902255639,
842
+ "grad_norm": 0.09185818582773209,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 0.2432,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 1.7593984962406015,
849
+ "grad_norm": 0.06584012508392334,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 0.1917,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 1.774436090225564,
856
+ "grad_norm": 0.07826845347881317,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.2231,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.7894736842105263,
863
+ "grad_norm": 0.09103841334581375,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 0.2866,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.8045112781954886,
870
+ "grad_norm": 0.11189167201519012,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 0.376,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 1.8195488721804511,
877
+ "grad_norm": 0.11350257694721222,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.305,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 1.8345864661654137,
884
+ "grad_norm": 0.1293785721063614,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 0.3012,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 1.849624060150376,
891
+ "grad_norm": 0.11487980931997299,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.2442,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 1.8646616541353382,
898
+ "grad_norm": 0.12351858615875244,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 0.3589,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 1.8796992481203008,
905
+ "grad_norm": 0.12002775818109512,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 0.3104,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 1.8947368421052633,
912
+ "grad_norm": 0.12263485789299011,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 0.3229,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 1.9097744360902256,
919
+ "grad_norm": 0.13375277817249298,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 0.3064,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 1.9248120300751879,
926
+ "grad_norm": 0.12632831931114197,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 0.3409,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 1.9398496240601504,
933
+ "grad_norm": 0.18142560124397278,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 0.3406,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 1.954887218045113,
940
+ "grad_norm": 0.17650289833545685,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 0.3586,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 1.9699248120300752,
947
+ "grad_norm": 0.12214044481515884,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 0.2468,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 1.9849624060150375,
954
+ "grad_norm": 0.09740839153528214,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 0.2646,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.0,
961
+ "grad_norm": 0.20502415299415588,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 0.3458,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.0150375939849625,
968
+ "grad_norm": 0.07391117513179779,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 0.2658,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.030075187969925,
975
+ "grad_norm": 0.06666134297847748,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 0.2042,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.045112781954887,
982
+ "grad_norm": 0.07267674803733826,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 0.1933,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.0601503759398496,
989
+ "grad_norm": 0.10182230919599533,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 0.3092,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.075187969924812,
996
+ "grad_norm": 0.08765217661857605,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 0.2414,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.090225563909774,
1003
+ "grad_norm": 0.1160230040550232,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 0.3189,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.1052631578947367,
1010
+ "grad_norm": 0.1104656457901001,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 0.2495,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.1203007518796992,
1017
+ "grad_norm": 0.10701072961091995,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 0.2654,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.1353383458646618,
1024
+ "grad_norm": 0.12387526780366898,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 0.3325,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.1503759398496243,
1031
+ "grad_norm": 0.11925939470529556,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 0.268,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.1654135338345863,
1038
+ "grad_norm": 0.11965704709291458,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 0.2873,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.180451127819549,
1045
+ "grad_norm": 0.1298457235097885,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 0.2909,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.1954887218045114,
1052
+ "grad_norm": 0.1270248293876648,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 0.3148,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.2105263157894735,
1059
+ "grad_norm": 0.15272803604602814,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 0.2778,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.225563909774436,
1066
+ "grad_norm": 0.15574714541435242,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 0.3038,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.2406015037593985,
1073
+ "grad_norm": 0.16595351696014404,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 0.2671,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.255639097744361,
1080
+ "grad_norm": 0.08685525506734848,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.2546,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.255639097744361,
1087
+ "eval_loss": 0.33286720514297485,
1088
+ "eval_runtime": 4.1872,
1089
+ "eval_samples_per_second": 26.748,
1090
+ "eval_steps_per_second": 6.687,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 5.848728385408205e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null