From 0d288727b8a7d7ba5419480caa284103396c0fe7 Mon Sep 17 00:00:00 2001 From: thomwolf Date: Tue, 27 Aug 2019 14:50:22 +0200 Subject: [PATCH] fix #1106 --- docs/source/examples.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/examples.rst b/docs/source/examples.rst index 7777117b..dbe6a3d4 100644 --- a/docs/source/examples.rst +++ b/docs/source/examples.rst @@ -384,7 +384,7 @@ Training with the previous hyper-parameters on a single GPU gave us the followin LM Fine-tuning ~~~~~~~~~~~~~~ -The data should be a text file in the same format as `sample_text.txt <./samples/sample_text.txt>`_ (one sentence per line, docs separated by empty line). +The data should be a text file in the same format as `sample_text.txt <./pytorch_transformers/tests/fixtures/sample_text.txt/sample_text.txt>`_ (one sentence per line, docs separated by empty line). You can download an `exemplary training corpus `_ generated from wikipedia articles and split into ~500k sentences with spaCy. Training one epoch on this corpus takes about 1:20h on 4 x NVIDIA Tesla P100 with ``train_batch_size=200`` and ``max_seq_length=128``\ :