prxy5605 commited on
Commit
58a9492
·
verified ·
1 Parent(s): 8275feb

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 sha256:6d59d739f1b5aaf8d6bde6e3719dcb55926d385da05cd1f26d4c8b42c18ef087
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d0936ba047413260c33296fdb324c32e291d7a6b5fe0216e5c06c1128ac266
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fd0924d11fe8d81f1631cd8e5c2aa63bee79cd1d6251632330b9c42e438b43b
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3c90158eea23cb9074c33bbaf2e0690b6aa47bdac3ad73a0ee7e3f4d2eb857
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:765617cfcca38312e6e6a06d5469d4f90799e895741d9cbbd6b75046f8350de2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe33361b74b04c35e54ffd954f5a7a824246f9c920096ddc53ea563d6c62356
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70676b886bdad671d073176c81ea76c66ddac446539f48ac64f4e9bef2e2a776
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb01d4f0da8d959e9ca5a4773566e24c639c6b8f18e1285757275e715c7b05f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 2.1507210731506348,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 1.7316017316017316,
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": 22.318,
732
  "eval_steps_per_second": 5.693,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -745,7 +1103,7 @@
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
- "early_stopping_patience_counter": 0
749
  }
750
  },
751
  "TrainerControl": {
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 4.137205760262144e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
  "best_metric": 2.1507210731506348,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 2.5974025974025974,
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": 22.318,
732
  "eval_steps_per_second": 5.693,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 1.7489177489177488,
737
+ "grad_norm": 1.0498305559158325,
738
+ "learning_rate": 4.0896120024874286e-05,
739
+ "loss": 1.5793,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 1.7662337662337664,
744
+ "grad_norm": 1.2344704866409302,
745
+ "learning_rate": 3.9950299516607766e-05,
746
+ "loss": 1.4962,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 1.7835497835497836,
751
+ "grad_norm": 1.401984691619873,
752
+ "learning_rate": 3.900821206181521e-05,
753
+ "loss": 1.5564,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 1.8008658008658007,
758
+ "grad_norm": 1.431049108505249,
759
+ "learning_rate": 3.8070207607527584e-05,
760
+ "loss": 1.5089,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 1.8181818181818183,
765
+ "grad_norm": 1.506121039390564,
766
+ "learning_rate": 3.713663458410779e-05,
767
+ "loss": 1.4881,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 1.8354978354978355,
772
+ "grad_norm": 1.7029125690460205,
773
+ "learning_rate": 3.620783977582305e-05,
774
+ "loss": 1.3652,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 1.8528138528138527,
779
+ "grad_norm": 1.684980869293213,
780
+ "learning_rate": 3.528416819202881e-05,
781
+ "loss": 1.4969,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 1.87012987012987,
786
+ "grad_norm": 1.84793221950531,
787
+ "learning_rate": 3.43659629390117e-05,
788
+ "loss": 1.741,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 1.8874458874458875,
793
+ "grad_norm": 2.200406074523926,
794
+ "learning_rate": 3.345356509253959e-05,
795
+ "loss": 1.8311,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 1.9047619047619047,
800
+ "grad_norm": 2.0255842208862305,
801
+ "learning_rate": 3.254731357116597e-05,
802
+ "loss": 1.6737,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 1.922077922077922,
807
+ "grad_norm": 2.303042411804199,
808
+ "learning_rate": 3.16475450103354e-05,
809
+ "loss": 1.5814,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 1.9393939393939394,
814
+ "grad_norm": 2.6473817825317383,
815
+ "learning_rate": 3.0754593637337276e-05,
816
+ "loss": 1.6909,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 1.9567099567099566,
821
+ "grad_norm": 3.3562562465667725,
822
+ "learning_rate": 2.986879114715403e-05,
823
+ "loss": 1.7364,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 1.974025974025974,
828
+ "grad_norm": 3.026970624923706,
829
+ "learning_rate": 2.899046657924992e-05,
830
+ "loss": 1.4776,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 1.9913419913419914,
835
+ "grad_norm": 2.301281452178955,
836
+ "learning_rate": 2.8119946195346375e-05,
837
+ "loss": 1.7903,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 2.0086580086580086,
842
+ "grad_norm": 2.0882139205932617,
843
+ "learning_rate": 2.7257553358229034e-05,
844
+ "loss": 1.5866,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 2.0259740259740258,
849
+ "grad_norm": 0.9352264404296875,
850
+ "learning_rate": 2.6403608411631742e-05,
851
+ "loss": 1.2755,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 2.0432900432900434,
856
+ "grad_norm": 1.2251120805740356,
857
+ "learning_rate": 2.555842856124182e-05,
858
+ "loss": 1.541,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 2.0606060606060606,
863
+ "grad_norm": 1.1876617670059204,
864
+ "learning_rate": 2.472232775687119e-05,
865
+ "loss": 1.1754,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 2.0779220779220777,
870
+ "grad_norm": 1.3045542240142822,
871
+ "learning_rate": 2.389561657583681e-05,
872
+ "loss": 1.2134,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.0952380952380953,
877
+ "grad_norm": 1.4649866819381714,
878
+ "learning_rate": 2.30786021075939e-05,
879
+ "loss": 1.4063,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.1125541125541125,
884
+ "grad_norm": 1.4156118631362915,
885
+ "learning_rate": 2.2271587839664672e-05,
886
+ "loss": 1.0884,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.1298701298701297,
891
+ "grad_norm": 1.5468546152114868,
892
+ "learning_rate": 2.1474873544905205e-05,
893
+ "loss": 1.2391,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.1471861471861473,
898
+ "grad_norm": 1.5604561567306519,
899
+ "learning_rate": 2.0688755170151996e-05,
900
+ "loss": 1.2168,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.1645021645021645,
905
+ "grad_norm": 1.9809437990188599,
906
+ "learning_rate": 1.9913524726289784e-05,
907
+ "loss": 1.3889,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.1818181818181817,
912
+ "grad_norm": 2.0183825492858887,
913
+ "learning_rate": 1.914947017978153e-05,
914
+ "loss": 1.3733,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.1991341991341993,
919
+ "grad_norm": 2.0843398571014404,
920
+ "learning_rate": 1.8396875345700497e-05,
921
+ "loss": 1.1898,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.2164502164502164,
926
+ "grad_norm": 2.6395606994628906,
927
+ "learning_rate": 1.76560197823046e-05,
928
+ "loss": 1.3807,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.2337662337662336,
933
+ "grad_norm": 3.146881341934204,
934
+ "learning_rate": 1.692717868719195e-05,
935
+ "loss": 1.1517,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.2510822510822512,
940
+ "grad_norm": 2.617090940475464,
941
+ "learning_rate": 1.621062279507617e-05,
942
+ "loss": 1.0857,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.2683982683982684,
947
+ "grad_norm": 1.1143049001693726,
948
+ "learning_rate": 1.550661827721941e-05,
949
+ "loss": 1.1666,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.2857142857142856,
954
+ "grad_norm": 1.417263388633728,
955
+ "learning_rate": 1.4815426642560754e-05,
956
+ "loss": 1.3524,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.303030303030303,
961
+ "grad_norm": 1.5993542671203613,
962
+ "learning_rate": 1.413730464057616e-05,
963
+ "loss": 1.4026,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.3203463203463204,
968
+ "grad_norm": 1.6387602090835571,
969
+ "learning_rate": 1.3472504165906613e-05,
970
+ "loss": 1.1655,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.3376623376623376,
975
+ "grad_norm": 1.7244728803634644,
976
+ "learning_rate": 1.2821272164789544e-05,
977
+ "loss": 1.245,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.354978354978355,
982
+ "grad_norm": 1.804990291595459,
983
+ "learning_rate": 1.2183850543328312e-05,
984
+ "loss": 1.162,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.3722943722943723,
989
+ "grad_norm": 1.9783991575241089,
990
+ "learning_rate": 1.156047607763407e-05,
991
+ "loss": 1.2835,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.3896103896103895,
996
+ "grad_norm": 2.1209795475006104,
997
+ "learning_rate": 1.0951380325872979e-05,
998
+ "loss": 1.2143,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.4069264069264067,
1003
+ "grad_norm": 2.3989975452423096,
1004
+ "learning_rate": 1.0356789542251938e-05,
1005
+ "loss": 1.3039,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.4242424242424243,
1010
+ "grad_norm": 2.3346776962280273,
1011
+ "learning_rate": 9.776924592974256e-06,
1012
+ "loss": 1.2018,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.4415584415584415,
1017
+ "grad_norm": 2.547539234161377,
1018
+ "learning_rate": 9.212000874196953e-06,
1019
+ "loss": 1.2262,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.458874458874459,
1024
+ "grad_norm": 3.0654184818267822,
1025
+ "learning_rate": 8.662228232019876e-06,
1026
+ "loss": 1.4538,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.4761904761904763,
1031
+ "grad_norm": 3.6214401721954346,
1032
+ "learning_rate": 8.127810884536403e-06,
1033
+ "loss": 1.0349,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.4935064935064934,
1038
+ "grad_norm": 2.0259740352630615,
1039
+ "learning_rate": 7.60894734597476e-06,
1040
+ "loss": 1.0412,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.5108225108225106,
1045
+ "grad_norm": 1.3173432350158691,
1046
+ "learning_rate": 7.105830352958142e-06,
1047
+ "loss": 1.3996,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.5281385281385282,
1052
+ "grad_norm": 1.410283088684082,
1053
+ "learning_rate": 6.618646792910893e-06,
1054
+ "loss": 1.267,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.5454545454545454,
1059
+ "grad_norm": 1.697140097618103,
1060
+ "learning_rate": 6.147577634637414e-06,
1061
+ "loss": 1.3348,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.562770562770563,
1066
+ "grad_norm": 1.521960973739624,
1067
+ "learning_rate": 5.692797861099719e-06,
1068
+ "loss": 1.0552,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.58008658008658,
1073
+ "grad_norm": 1.7901246547698975,
1074
+ "learning_rate": 5.25447640441834e-06,
1075
+ "loss": 1.2096,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.5974025974025974,
1080
+ "grad_norm": 1.9669653177261353,
1081
+ "learning_rate": 4.832776083120982e-06,
1082
+ "loss": 1.3032,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.5974025974025974,
1087
+ "eval_loss": 2.2222650051116943,
1088
+ "eval_runtime": 4.3939,
1089
+ "eval_samples_per_second": 22.304,
1090
+ "eval_steps_per_second": 5.69,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1103
  "early_stopping_threshold": 0.0
1104
  },
1105
  "attributes": {
1106
+ "early_stopping_patience_counter": 1
1107
  }
1108
  },
1109
  "TrainerControl": {
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 6.202571390189568e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null