bbytxt commited on
Commit
1935240
·
verified ·
1 Parent(s): 461adc0

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 sha256:6d857d4afb5ecd9bbc4314956f120f51b4145b5819819e7199915589e2d64fdb
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c4538f1aff9431ceadc9622321d2b923dae796e82d3c63f85dd2a41ad15870
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2386c4ab433625813062f3c23cf791c1c4258e503c078a6b145f92da421a05f
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0d44d15859f37e598f1947ef098911d10fb573ca455e842958838c740508b2
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0707fd943c769e82bf0ddf8a19aa3b0b9ebfc7a6e33f23ea9d19d2e0ecdfb68d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a9570b133e953f4e3a5c9c718e9eda27805cd05b1c107fa1c72390c1c6331a
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": 1.0888407230377197,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.02858776443682104,
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": 36.113,
732
  "eval_steps_per_second": 9.028,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.361755368849408e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.063374638557434,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.04288164665523156,
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": 36.113,
732
  "eval_steps_per_second": 9.028,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.02887364208118925,
737
+ "grad_norm": 0.15291909873485565,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 0.8704,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.029159519725557463,
744
+ "grad_norm": 0.14251872897148132,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 0.9443,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.02944539736992567,
751
+ "grad_norm": 0.14112308621406555,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 0.9799,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.029731275014293884,
758
+ "grad_norm": 0.15144599974155426,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.0705,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.030017152658662092,
765
+ "grad_norm": 0.13132591545581818,
766
+ "learning_rate": 5e-05,
767
+ "loss": 0.8992,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.030303030303030304,
772
+ "grad_norm": 0.1182556226849556,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 0.8577,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.030588907947398512,
779
+ "grad_norm": 0.12843120098114014,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.0206,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.030874785591766724,
786
+ "grad_norm": 0.11315994709730148,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 0.9496,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.031160663236134933,
793
+ "grad_norm": 0.10639316588640213,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 0.9518,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.031446540880503145,
800
+ "grad_norm": 0.0997280552983284,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 0.9807,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.03173241852487135,
807
+ "grad_norm": 0.10182894766330719,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 0.9865,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.03201829616923957,
814
+ "grad_norm": 0.09225668758153915,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.0271,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.03230417381360778,
821
+ "grad_norm": 0.09538514167070389,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 0.8753,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.032590051457975985,
828
+ "grad_norm": 0.09736867994070053,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.0053,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.032875929102344194,
835
+ "grad_norm": 0.09072590619325638,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 0.9211,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.03316180674671241,
842
+ "grad_norm": 0.09831057488918304,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.0603,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.03344768439108062,
849
+ "grad_norm": 0.10975565761327744,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.0879,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.033733562035448826,
856
+ "grad_norm": 0.10727279633283615,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 0.9999,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.03401943967981704,
863
+ "grad_norm": 0.10179470479488373,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.0395,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.03430531732418525,
870
+ "grad_norm": 0.10456199944019318,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1228,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.03459119496855346,
877
+ "grad_norm": 0.10591114312410355,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 0.991,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.03487707261292167,
884
+ "grad_norm": 0.1142454445362091,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.0575,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.03516295025728988,
891
+ "grad_norm": 0.10526374727487564,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 0.9558,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.03544882790165809,
898
+ "grad_norm": 0.11274749785661697,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1397,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.0357347055460263,
905
+ "grad_norm": 0.1104782223701477,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.1152,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.036020583190394515,
912
+ "grad_norm": 0.10397206991910934,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.0074,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.03630646083476272,
919
+ "grad_norm": 0.12671123445034027,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.1386,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.03659233847913093,
926
+ "grad_norm": 0.11324112862348557,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.0639,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.03687821612349914,
933
+ "grad_norm": 0.12823550403118134,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1051,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.037164093767867355,
940
+ "grad_norm": 0.1334521472454071,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2528,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.037449971412235564,
947
+ "grad_norm": 0.11641769111156464,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.0727,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.03773584905660377,
954
+ "grad_norm": 0.13059546053409576,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.1694,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.03802172670097198,
961
+ "grad_norm": 0.1455633044242859,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.1476,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.038307604345340196,
968
+ "grad_norm": 0.12968429923057556,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.1598,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.038593481989708404,
975
+ "grad_norm": 0.14115317165851593,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1319,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.03887935963407661,
982
+ "grad_norm": 0.14216141402721405,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.176,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.03916523727844483,
989
+ "grad_norm": 0.1620887666940689,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.1344,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.03945111492281304,
996
+ "grad_norm": 0.16333039104938507,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.0849,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.039736992567181245,
1003
+ "grad_norm": 0.14174237847328186,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.0969,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.040022870211549454,
1010
+ "grad_norm": 0.16004346311092377,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0726,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.04030874785591767,
1017
+ "grad_norm": 0.15503916144371033,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.2549,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.04059462550028588,
1024
+ "grad_norm": 0.19311998784542084,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.3267,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.040880503144654086,
1031
+ "grad_norm": 0.17602625489234924,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.2021,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.0411663807890223,
1038
+ "grad_norm": 0.1743750274181366,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2238,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.04145225843339051,
1045
+ "grad_norm": 0.17492149770259857,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.2373,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.04173813607775872,
1052
+ "grad_norm": 0.194108247756958,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.2629,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.04202401372212693,
1059
+ "grad_norm": 0.22885926067829132,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.4066,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.04230989136649514,
1066
+ "grad_norm": 0.2171851247549057,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.1757,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.04259576901086335,
1073
+ "grad_norm": 0.28467607498168945,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.2247,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.04288164665523156,
1080
+ "grad_norm": 0.19864968955516815,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 0.9732,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.04288164665523156,
1087
+ "eval_loss": 1.063374638557434,
1088
+ "eval_runtime": 163.1887,
1089
+ "eval_samples_per_second": 36.105,
1090
+ "eval_steps_per_second": 9.026,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.045208883101696e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null