bbytxt commited on
Commit
687b8ff
·
verified ·
1 Parent(s): 6851d3e

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 sha256:646dc19f5a91dc1181967a11b5fefecfeeafeea9ff0667965d405a8b1e04d579
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d08eae97045ebcb9387966899d06b919e9a5080064a9dc6d449581f31ce795
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aedd48ff7fb5a12139a7d393843d3fc15df18076939e2848e9bdb0566008a2aa
3
  size 156656510
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45417ee77471c8e4564776773972a4b6fd0f9c63916c72a29b942506a9e759ce
3
  size 156656510
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f40ed1f3a666b9ace6f149bce4e7f73c350693f365e4fdf7209bc8407c788c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d82a56c3cee5bac146bfbc8d9553a71fbc98a844c5fabe7a96ee64f6b87592
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd59dca009004df561617f8f6994512d029a952a68609cac24b36df5a0757ce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.2464494705200195,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.07969715082685794,
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": 43.048,
732
  "eval_steps_per_second": 21.524,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 2472176045260800.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.1894659996032715,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.1195457262402869,
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": 43.048,
732
  "eval_steps_per_second": 21.524,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.08049412233512653,
737
+ "grad_norm": 0.4536077678203583,
738
+ "learning_rate": 6.279213887972179e-05,
739
+ "loss": 4.4386,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.0812910938433951,
744
+ "grad_norm": 0.49079081416130066,
745
+ "learning_rate": 6.189675975213094e-05,
746
+ "loss": 4.1592,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.08208806535166367,
751
+ "grad_norm": 0.5224800109863281,
752
+ "learning_rate": 6.099731789198344e-05,
753
+ "loss": 4.4185,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.08288503685993226,
758
+ "grad_norm": 0.4378278851509094,
759
+ "learning_rate": 6.009412045785051e-05,
760
+ "loss": 4.1982,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.08368200836820083,
765
+ "grad_norm": 0.42964717745780945,
766
+ "learning_rate": 5.918747589082853e-05,
767
+ "loss": 4.3514,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.08447897987646942,
772
+ "grad_norm": 0.4140433967113495,
773
+ "learning_rate": 5.82776938092065e-05,
774
+ "loss": 4.2388,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.085275951384738,
779
+ "grad_norm": 0.3792392909526825,
780
+ "learning_rate": 5.736508490273188e-05,
781
+ "loss": 4.2905,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.08607292289300658,
786
+ "grad_norm": 0.3357432782649994,
787
+ "learning_rate": 5.644996082651017e-05,
788
+ "loss": 4.1563,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.08686989440127516,
793
+ "grad_norm": 0.3008951246738434,
794
+ "learning_rate": 5.553263409457504e-05,
795
+ "loss": 4.1949,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.08766686590954373,
800
+ "grad_norm": 0.26610758900642395,
801
+ "learning_rate": 5.4613417973165106e-05,
802
+ "loss": 4.2839,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.08846383741781232,
807
+ "grad_norm": 0.25112292170524597,
808
+ "learning_rate": 5.3692626373743706e-05,
809
+ "loss": 4.273,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.08926080892608089,
814
+ "grad_norm": 0.25932425260543823,
815
+ "learning_rate": 5.27705737457985e-05,
816
+ "loss": 4.2267,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.09005778043434948,
821
+ "grad_norm": 0.2820190191268921,
822
+ "learning_rate": 5.184757496945726e-05,
823
+ "loss": 4.1222,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.09085475194261805,
828
+ "grad_norm": 0.2938423156738281,
829
+ "learning_rate": 5.092394524795649e-05,
830
+ "loss": 4.3083,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.09165172345088662,
835
+ "grad_norm": 0.2608668804168701,
836
+ "learning_rate": 5e-05,
837
+ "loss": 4.1598,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.09244869495915521,
842
+ "grad_norm": 0.29658424854278564,
843
+ "learning_rate": 4.907605475204352e-05,
844
+ "loss": 4.3735,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.09324566646742379,
849
+ "grad_norm": 0.3041045069694519,
850
+ "learning_rate": 4.8152425030542766e-05,
851
+ "loss": 4.239,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.09404263797569237,
856
+ "grad_norm": 0.32803621888160706,
857
+ "learning_rate": 4.72294262542015e-05,
858
+ "loss": 4.4035,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.09483960948396095,
863
+ "grad_norm": 0.27936574816703796,
864
+ "learning_rate": 4.6307373626256306e-05,
865
+ "loss": 3.9513,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.09563658099222953,
870
+ "grad_norm": 0.27713343501091003,
871
+ "learning_rate": 4.5386582026834906e-05,
872
+ "loss": 4.5389,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.09643355250049811,
877
+ "grad_norm": 0.26673904061317444,
878
+ "learning_rate": 4.446736590542497e-05,
879
+ "loss": 4.2087,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.09723052400876668,
884
+ "grad_norm": 0.26535698771476746,
885
+ "learning_rate": 4.3550039173489845e-05,
886
+ "loss": 4.1479,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.09802749551703527,
891
+ "grad_norm": 0.2699700593948364,
892
+ "learning_rate": 4.2634915097268115e-05,
893
+ "loss": 4.1494,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.09882446702530384,
898
+ "grad_norm": 0.27292296290397644,
899
+ "learning_rate": 4.1722306190793495e-05,
900
+ "loss": 4.223,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.09962143853357243,
905
+ "grad_norm": 0.274880588054657,
906
+ "learning_rate": 4.0812524109171476e-05,
907
+ "loss": 4.1813,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.100418410041841,
912
+ "grad_norm": 0.2678457200527191,
913
+ "learning_rate": 3.99058795421495e-05,
914
+ "loss": 4.026,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.10121538155010959,
919
+ "grad_norm": 0.2603027820587158,
920
+ "learning_rate": 3.9002682108016585e-05,
921
+ "loss": 4.0395,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.10201235305837816,
926
+ "grad_norm": 0.29638221859931946,
927
+ "learning_rate": 3.8103240247869075e-05,
928
+ "loss": 4.0431,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.10280932456664674,
933
+ "grad_norm": 0.27740830183029175,
934
+ "learning_rate": 3.720786112027822e-05,
935
+ "loss": 3.9725,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.10360629607491532,
940
+ "grad_norm": 0.2580147683620453,
941
+ "learning_rate": 3.631685049639586e-05,
942
+ "loss": 4.1768,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.1044032675831839,
947
+ "grad_norm": 0.2813362181186676,
948
+ "learning_rate": 3.543051265553377e-05,
949
+ "loss": 4.1545,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.10520023909145249,
954
+ "grad_norm": 0.26297634840011597,
955
+ "learning_rate": 3.4549150281252636e-05,
956
+ "loss": 4.273,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.10599721059972106,
961
+ "grad_norm": 0.26882943511009216,
962
+ "learning_rate": 3.367306435799584e-05,
963
+ "loss": 4.1523,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.10679418210798963,
968
+ "grad_norm": 0.25994184613227844,
969
+ "learning_rate": 3.2802554068303596e-05,
970
+ "loss": 4.1418,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.10759115361625822,
975
+ "grad_norm": 0.2707768678665161,
976
+ "learning_rate": 3.1937916690642356e-05,
977
+ "loss": 3.9873,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.1083881251245268,
982
+ "grad_norm": 0.26885348558425903,
983
+ "learning_rate": 3.107944749788449e-05,
984
+ "loss": 4.1367,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.10918509663279538,
989
+ "grad_norm": 0.28563767671585083,
990
+ "learning_rate": 3.0227439656472877e-05,
991
+ "loss": 3.9702,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.10998206814106395,
996
+ "grad_norm": 0.2777661681175232,
997
+ "learning_rate": 2.9382184126304834e-05,
998
+ "loss": 4.0914,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.11077903964933254,
1003
+ "grad_norm": 0.27080315351486206,
1004
+ "learning_rate": 2.8543969561369556e-05,
1005
+ "loss": 4.124,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.11157601115760112,
1010
+ "grad_norm": 0.29918569326400757,
1011
+ "learning_rate": 2.771308221117309e-05,
1012
+ "loss": 4.1961,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.11237298266586969,
1017
+ "grad_norm": 0.2737353444099426,
1018
+ "learning_rate": 2.688980582298435e-05,
1019
+ "loss": 3.9326,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.11316995417413828,
1024
+ "grad_norm": 0.3046242296695709,
1025
+ "learning_rate": 2.607442154493568e-05,
1026
+ "loss": 4.2884,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.11396692568240685,
1031
+ "grad_norm": 0.2995275557041168,
1032
+ "learning_rate": 2.5267207830011068e-05,
1033
+ "loss": 4.0685,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.11476389719067544,
1038
+ "grad_norm": 0.3147706091403961,
1039
+ "learning_rate": 2.446844034095466e-05,
1040
+ "loss": 4.1747,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.11556086869894401,
1045
+ "grad_norm": 0.31899207830429077,
1046
+ "learning_rate": 2.3678391856132204e-05,
1047
+ "loss": 4.0118,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.1163578402072126,
1052
+ "grad_norm": 0.3425534963607788,
1053
+ "learning_rate": 2.2897332176377528e-05,
1054
+ "loss": 4.0294,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.11715481171548117,
1059
+ "grad_norm": 0.39953556656837463,
1060
+ "learning_rate": 2.2125528032855724e-05,
1061
+ "loss": 4.0949,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.11795178322374975,
1066
+ "grad_norm": 0.4550447463989258,
1067
+ "learning_rate": 2.136324299597474e-05,
1068
+ "loss": 3.8362,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.11874875473201833,
1073
+ "grad_norm": 0.5356332659721375,
1074
+ "learning_rate": 2.061073738537635e-05,
1075
+ "loss": 4.2568,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.1195457262402869,
1080
+ "grad_norm": 0.9250167608261108,
1081
+ "learning_rate": 1.9868268181037185e-05,
1082
+ "loss": 4.1155,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.1195457262402869,
1087
+ "eval_loss": 4.1894659996032715,
1088
+ "eval_runtime": 49.1569,
1089
+ "eval_samples_per_second": 43.005,
1090
+ "eval_steps_per_second": 21.503,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 3708264067891200.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null