alchemist69 commited on
Commit
da69fcd
·
verified ·
1 Parent(s): 38515c1

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 sha256:7369a0a4038d4eecb51d3c3d2d6eda4fa14ca3325f2b1185e757f723a6ef3456
3
  size 54285928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda25fa2a0aaedd27fdae576b429b51989a089bd54bcc2bbcf1e3fd3ca48a4b1
3
  size 54285928
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eacf61aba3c1bd251d8a984191fdbc97969f256ecc38f9d7544e5714dd717f0
3
  size 27753594
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867d8b074bfd6f3a32eb2bc0ee05880930cca1153d8fc51031f0930935901c8c
3
  size 27753594
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42a4ed7e0fc3874c798b38ac3a985aaf258be3f27994fe793ee926f425d1cea9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1298df9453e7665f6d1a4a5f76481aeb9f225d09bee7275c62151d6ad0f8d682
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": 1.1992599964141846,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.5263157894736842,
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": 139.2,
732
  "eval_steps_per_second": 34.8,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 3036325619957760.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.177085518836975,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.7894736842105263,
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": 139.2,
732
  "eval_steps_per_second": 34.8,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.531578947368421,
737
+ "grad_norm": 0.274366557598114,
738
+ "learning_rate": 5.330452921628497e-05,
739
+ "loss": 1.1167,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5368421052631579,
744
+ "grad_norm": 0.25825682282447815,
745
+ "learning_rate": 5.247918773366112e-05,
746
+ "loss": 1.1874,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5421052631578948,
751
+ "grad_norm": 0.2806967496871948,
752
+ "learning_rate": 5.165316846586541e-05,
753
+ "loss": 1.2356,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.5473684210526316,
758
+ "grad_norm": 0.2751525044441223,
759
+ "learning_rate": 5.0826697238317935e-05,
760
+ "loss": 1.1655,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5526315789473685,
765
+ "grad_norm": 0.29569104313850403,
766
+ "learning_rate": 5e-05,
767
+ "loss": 1.1425,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5578947368421052,
772
+ "grad_norm": 0.2888164520263672,
773
+ "learning_rate": 4.917330276168208e-05,
774
+ "loss": 1.1731,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5631578947368421,
779
+ "grad_norm": 0.2688474953174591,
780
+ "learning_rate": 4.834683153413459e-05,
781
+ "loss": 1.1466,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5684210526315789,
786
+ "grad_norm": 0.27477800846099854,
787
+ "learning_rate": 4.7520812266338885e-05,
788
+ "loss": 1.171,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5736842105263158,
793
+ "grad_norm": 0.2746734023094177,
794
+ "learning_rate": 4.669547078371504e-05,
795
+ "loss": 1.1608,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5789473684210527,
800
+ "grad_norm": 0.27401068806648254,
801
+ "learning_rate": 4.5871032726383386e-05,
802
+ "loss": 1.1512,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5842105263157895,
807
+ "grad_norm": 0.32083991169929504,
808
+ "learning_rate": 4.504772348747687e-05,
809
+ "loss": 1.1847,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5894736842105263,
814
+ "grad_norm": 0.28475648164749146,
815
+ "learning_rate": 4.4225768151520694e-05,
816
+ "loss": 1.1734,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.5947368421052631,
821
+ "grad_norm": 0.3075573444366455,
822
+ "learning_rate": 4.3405391432896555e-05,
823
+ "loss": 1.1375,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.6,
828
+ "grad_norm": 0.28573694825172424,
829
+ "learning_rate": 4.2586817614407895e-05,
830
+ "loss": 1.1331,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.6052631578947368,
835
+ "grad_norm": 0.2973617911338806,
836
+ "learning_rate": 4.17702704859633e-05,
837
+ "loss": 1.2687,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.6105263157894737,
842
+ "grad_norm": 0.2792574465274811,
843
+ "learning_rate": 4.095597328339452e-05,
844
+ "loss": 1.1045,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.6157894736842106,
849
+ "grad_norm": 0.2999548017978668,
850
+ "learning_rate": 4.0144148627425993e-05,
851
+ "loss": 1.1416,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.6210526315789474,
856
+ "grad_norm": 0.3057112991809845,
857
+ "learning_rate": 3.933501846281267e-05,
858
+ "loss": 1.2118,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.6263157894736842,
863
+ "grad_norm": 0.2686685025691986,
864
+ "learning_rate": 3.852880399766243e-05,
865
+ "loss": 1.1465,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.631578947368421,
870
+ "grad_norm": 0.3118525445461273,
871
+ "learning_rate": 3.772572564296005e-05,
872
+ "loss": 1.1467,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.6368421052631579,
877
+ "grad_norm": 0.29716405272483826,
878
+ "learning_rate": 3.6926002952309016e-05,
879
+ "loss": 1.214,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.6421052631578947,
884
+ "grad_norm": 0.30662626028060913,
885
+ "learning_rate": 3.612985456190778e-05,
886
+ "loss": 1.1687,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.6473684210526316,
891
+ "grad_norm": 0.29000720381736755,
892
+ "learning_rate": 3.533749813077677e-05,
893
+ "loss": 1.1389,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.6526315789473685,
898
+ "grad_norm": 0.2914237678050995,
899
+ "learning_rate": 3.4549150281252636e-05,
900
+ "loss": 1.1995,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.6578947368421053,
905
+ "grad_norm": 0.29801809787750244,
906
+ "learning_rate": 3.3765026539765834e-05,
907
+ "loss": 1.1786,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6631578947368421,
912
+ "grad_norm": 0.29436713457107544,
913
+ "learning_rate": 3.298534127791785e-05,
914
+ "loss": 1.1483,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6684210526315789,
919
+ "grad_norm": 0.29628023505210876,
920
+ "learning_rate": 3.221030765387417e-05,
921
+ "loss": 1.2061,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6736842105263158,
926
+ "grad_norm": 0.28928571939468384,
927
+ "learning_rate": 3.144013755408895e-05,
928
+ "loss": 1.1665,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.6789473684210526,
933
+ "grad_norm": 0.29996129870414734,
934
+ "learning_rate": 3.0675041535377405e-05,
935
+ "loss": 1.1905,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6842105263157895,
940
+ "grad_norm": 0.29434117674827576,
941
+ "learning_rate": 2.991522876735154e-05,
942
+ "loss": 1.2208,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6894736842105263,
947
+ "grad_norm": 0.2977113723754883,
948
+ "learning_rate": 2.916090697523549e-05,
949
+ "loss": 1.1077,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6947368421052632,
954
+ "grad_norm": 0.29686591029167175,
955
+ "learning_rate": 2.8412282383075363e-05,
956
+ "loss": 1.2307,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.7,
961
+ "grad_norm": 0.31217262148857117,
962
+ "learning_rate": 2.766955965735968e-05,
963
+ "loss": 1.199,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.7052631578947368,
968
+ "grad_norm": 0.31836938858032227,
969
+ "learning_rate": 2.693294185106562e-05,
970
+ "loss": 1.2262,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.7105263157894737,
975
+ "grad_norm": 0.30319544672966003,
976
+ "learning_rate": 2.6202630348146324e-05,
977
+ "loss": 1.1708,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.7157894736842105,
982
+ "grad_norm": 0.309924453496933,
983
+ "learning_rate": 2.547882480847461e-05,
984
+ "loss": 1.2304,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.7210526315789474,
989
+ "grad_norm": 0.3159969747066498,
990
+ "learning_rate": 2.476172311325783e-05,
991
+ "loss": 1.2261,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.7263157894736842,
996
+ "grad_norm": 0.3190324604511261,
997
+ "learning_rate": 2.405152131093926e-05,
998
+ "loss": 1.1509,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.7315789473684211,
1003
+ "grad_norm": 0.320281445980072,
1004
+ "learning_rate": 2.3348413563600325e-05,
1005
+ "loss": 1.2214,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.7368421052631579,
1010
+ "grad_norm": 0.34036779403686523,
1011
+ "learning_rate": 2.2652592093878666e-05,
1012
+ "loss": 1.0837,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.7421052631578947,
1017
+ "grad_norm": 0.38215550780296326,
1018
+ "learning_rate": 2.196424713241637e-05,
1019
+ "loss": 1.1619,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.7473684210526316,
1024
+ "grad_norm": 0.33163967728614807,
1025
+ "learning_rate": 2.128356686585282e-05,
1026
+ "loss": 1.1757,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.7526315789473684,
1031
+ "grad_norm": 0.3086463510990143,
1032
+ "learning_rate": 2.061073738537635e-05,
1033
+ "loss": 1.1521,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.7578947368421053,
1038
+ "grad_norm": 0.30647042393684387,
1039
+ "learning_rate": 1.9945942635848748e-05,
1040
+ "loss": 1.2017,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.7631578947368421,
1045
+ "grad_norm": 0.31250232458114624,
1046
+ "learning_rate": 1.928936436551661e-05,
1047
+ "loss": 1.235,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.7684210526315789,
1052
+ "grad_norm": 0.31314322352409363,
1053
+ "learning_rate": 1.8641182076323148e-05,
1054
+ "loss": 1.1602,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.7736842105263158,
1059
+ "grad_norm": 0.2935684621334076,
1060
+ "learning_rate": 1.800157297483417e-05,
1061
+ "loss": 1.1494,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7789473684210526,
1066
+ "grad_norm": 0.2966061234474182,
1067
+ "learning_rate": 1.7370711923791567e-05,
1068
+ "loss": 1.1189,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.7842105263157895,
1073
+ "grad_norm": 0.2835730314254761,
1074
+ "learning_rate": 1.6748771394307585e-05,
1075
+ "loss": 1.1583,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.7894736842105263,
1080
+ "grad_norm": 0.28138697147369385,
1081
+ "learning_rate": 1.6135921418712956e-05,
1082
+ "loss": 1.1421,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.7894736842105263,
1087
+ "eval_loss": 1.177085518836975,
1088
+ "eval_runtime": 2.282,
1089
+ "eval_samples_per_second": 140.229,
1090
+ "eval_steps_per_second": 35.057,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 4539604480819200.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null