From 229033831aeeb4a78d9ebaa98ebfe1f06d6f9d28 Mon Sep 17 00:00:00 2001 From: svlandeg Date: Thu, 20 Aug 2020 10:00:45 +0200 Subject: [PATCH] add explanation of raw_text --- website/docs/api/data-formats.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/website/docs/api/data-formats.md b/website/docs/api/data-formats.md index ff106b229..444dc0003 100644 --- a/website/docs/api/data-formats.md +++ b/website/docs/api/data-formats.md @@ -135,7 +135,7 @@ process that are used when you run [`spacy train`](/api/cli#train). | `dropout` | The dropout rate. Defaults to `0.1`. ~~float~~ | | `accumulate_gradient` | Whether to divide the batch up into substeps. Defaults to `1`. ~~int~~ | | `init_tok2vec` | Optional path to pretrained tok2vec weights created with [`spacy pretrain`](/api/cli#pretrain). Defaults to variable `${paths:init_tok2vec}`. ~~Optional[str]~~ | -| `raw_text` | TODO: ... Defaults to variable `${paths:raw}`. ~~Optional[str]~~ | +| `raw_text` | Optional path to a jsonl file with unlabelled text documents for a [rehearsel](/api/language#rehearse) step. Defaults to variable `${paths:raw}`. ~~Optional[str]~~ | | `vectors` | Model name or path to model containing pretrained word vectors to use, e.g. created with [`init model`](/api/cli#init-model). Defaults to `null`. ~~Optional[str]~~ | | `patience` | How many steps to continue without improvement in evaluation score. Defaults to `1600`. ~~int~~ | | `max_epochs` | Maximum number of epochs to train for. Defaults to `0`. ~~int~~ |