prxy5607 commited on
Commit
d9fc86a
·
verified ·
1 Parent(s): 09d5595

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 sha256:71d86765ee9e157ae39a13c598980ab136aa5b35c58cf7dccd0fde252c1193af
3
  size 42487072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bac65ab18fd4b0f25bc6fd7f4967e65f93907aa0c49f58fdf795ef9d78aef4c
3
  size 42487072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af753a37a7e24df7a52ee03256a4568e6cfe173c4479789cdbdf2e6fe4312d5a
3
  size 21735354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fedf92640cced566cf619fe3bfe3c0a66e146097163438827fc3cbc3307731
3
  size 21735354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:346f3e0f43814f396a7f95bb94ff489361be2aa6542fa89f3e821e51fc2d5e85
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c50e18cdcd34fa4ddf190730b1956db0fa39ac4021b0c5c18dc23b89c5f005f
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": 2.1445388793945312,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.058806233460746836,
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": 159.199,
732
  "eval_steps_per_second": 39.8,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2022079746539520.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0842721462249756,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.08820935019112026,
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": 159.199,
732
  "eval_steps_per_second": 39.8,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.05939429579535431,
737
+ "grad_norm": 6.193917274475098,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 7.9086,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.05998235812996178,
744
+ "grad_norm": 5.619760513305664,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 7.5205,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.060570420464569244,
751
+ "grad_norm": 5.22607421875,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 7.6454,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.06115848279917671,
758
+ "grad_norm": 4.238805294036865,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 8.6684,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.06174654513378418,
765
+ "grad_norm": 4.190961837768555,
766
+ "learning_rate": 5e-05,
767
+ "loss": 8.9169,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.06233460746839165,
772
+ "grad_norm": 3.7844080924987793,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 8.5661,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.06292266980299911,
779
+ "grad_norm": 3.943453073501587,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 8.2442,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.0635107321376066,
786
+ "grad_norm": 3.5105576515197754,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 8.2983,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.06409879447221406,
793
+ "grad_norm": 3.7738616466522217,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 8.2154,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.06468685680682153,
800
+ "grad_norm": 3.175321578979492,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 8.1635,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.065274919141429,
807
+ "grad_norm": 2.8794965744018555,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 8.3374,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.06586298147603646,
814
+ "grad_norm": 2.8476223945617676,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 8.7048,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.06645104381064393,
821
+ "grad_norm": 2.700763463973999,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 8.5285,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.0670391061452514,
828
+ "grad_norm": 2.5856125354766846,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 8.3342,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.06762716847985886,
835
+ "grad_norm": 2.5090999603271484,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 7.7179,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.06821523081446633,
842
+ "grad_norm": 2.675593852996826,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 8.5672,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.0688032931490738,
849
+ "grad_norm": 2.7386438846588135,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 9.2258,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.06939135548368126,
856
+ "grad_norm": 3.1391453742980957,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 8.2759,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.06997941781828874,
863
+ "grad_norm": 2.859008550643921,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 9.2972,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.07056748015289621,
870
+ "grad_norm": 2.8385045528411865,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 9.2444,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.07115554248750368,
877
+ "grad_norm": 2.785433053970337,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 8.2695,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.07174360482211115,
884
+ "grad_norm": 3.413860559463501,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 8.8478,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.07233166715671861,
891
+ "grad_norm": 3.047285556793213,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 9.2273,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.07291972949132608,
898
+ "grad_norm": 3.2367634773254395,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 8.5344,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.07350779182593355,
905
+ "grad_norm": 3.2533440589904785,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 9.3347,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.07409585416054101,
912
+ "grad_norm": 3.4966914653778076,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 8.6104,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.07468391649514848,
919
+ "grad_norm": 3.0202932357788086,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 8.7115,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.07527197882975595,
926
+ "grad_norm": 3.3886260986328125,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 8.6994,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.07586004116436343,
933
+ "grad_norm": 3.5800437927246094,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 9.3688,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.0764481034989709,
940
+ "grad_norm": 3.5207343101501465,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 8.6903,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.07703616583357836,
947
+ "grad_norm": 3.4582135677337646,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 8.4372,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.07762422816818583,
954
+ "grad_norm": 4.331637382507324,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 8.1935,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.0782122905027933,
961
+ "grad_norm": 4.02256965637207,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 8.5141,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.07880035283740076,
968
+ "grad_norm": 4.460637092590332,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 9.6442,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.07938841517200823,
975
+ "grad_norm": 4.595434188842773,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 8.7553,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.0799764775066157,
982
+ "grad_norm": 4.413257122039795,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 8.6695,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.08056453984122317,
989
+ "grad_norm": 4.718889236450195,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 9.3965,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.08115260217583063,
996
+ "grad_norm": 4.938948631286621,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 9.2762,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.08174066451043811,
1003
+ "grad_norm": 5.82443904876709,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 9.3252,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.08232872684504558,
1010
+ "grad_norm": 5.855938911437988,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 9.7101,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.08291678917965305,
1017
+ "grad_norm": 5.540469169616699,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 8.6131,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.08350485151426051,
1024
+ "grad_norm": 6.2768940925598145,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 8.8135,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.08409291384886798,
1031
+ "grad_norm": 6.498032093048096,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 9.0499,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.08468097618347545,
1038
+ "grad_norm": 7.061596393585205,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 8.7917,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.08526903851808292,
1045
+ "grad_norm": 9.55113410949707,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 8.3972,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.08585710085269038,
1052
+ "grad_norm": 8.871682167053223,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 8.9225,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.08644516318729785,
1059
+ "grad_norm": 10.061549186706543,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 8.6611,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.08703322552190532,
1066
+ "grad_norm": 13.46516227722168,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 9.0124,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.0876212878565128,
1073
+ "grad_norm": 14.108145713806152,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 8.4522,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.08820935019112026,
1080
+ "grad_norm": 29.471630096435547,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 9.0066,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.08820935019112026,
1087
+ "eval_loss": 2.0842721462249756,
1088
+ "eval_runtime": 17.9332,
1089
+ "eval_samples_per_second": 159.704,
1090
+ "eval_steps_per_second": 39.926,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3047227152924672.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null