Commit3932244

committed

change default param in pretraining bert tutorial

1 parent5939b85 commit3932244Copy full SHA for 3932244

File tree

-2

lines changed

-2

lines changed

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -202,7 +202,7 @@`
`202`	`202`	`"# maximum sequence length, lowering will result to faster training (when increasing batch size)\n",`
`203`	`203`	`"max_length = 512\n",`
`204`	`204`	`"# whether to truncate\n",`
`205`		`-"truncate_longer_samples =False"`
	`205`	`+"truncate_longer_samples =True"`
`206`	`206`	`]`
`207`	`207`	`},`
`208`	`208`	`{`

Lines changed: 1 addition & 1 deletion

Original file line number	Diff line number	Diff line change
`@@ -66,7 +66,7 @@ def dataset_to_text(dataset, output_filename="data.txt"):`
`66`	`66`	`# maximum sequence length, lowering will result to faster training (when increasing batch size)`
`67`	`67`	`max_length=512`
`68`	`68`	`# whether to truncate`
`69`		`-truncate_longer_samples=False`
	`69`	`+truncate_longer_samples=True`
`70`	`70`
`71`	`71`	`# initialize the WordPiece tokenizer`
`72`	`72`	`tokenizer=BertWordPieceTokenizer()`

Comments

(0)