dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated documentation for LM finetuning script

This commit is contained in:
LysandreJik 2019-09-02 13:40:25 -04:00
parent 3fbf301bba
commit 7f522437bc
2 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/examples.rst
View File

@ -459,7 +459,7 @@ The same option as in the original scripts are provided, please refer to the cod
Causal LM fine-tuning on GPT/GPT-2, Masked LM fine-tuning on BERT/RoBERTa Causal LM fine-tuning on GPT/GPT-2, Masked LM fine-tuning on BERT/RoBERTa
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Before running the following examples you should download the `WikiText-2 dataset <https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/>`__ and unpack it to some directory `$WIKITEXT_2_DATASET` Before running the following examples you should download the `WikiText-2 dataset <https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/>`__ and unpack it to some directory `$WIKITEXT_2_DATASET`
The following results were obtained using the `raw` WikiText-2 (no tokens were replaced before the tokenization). The following results were obtained using the `raw` WikiText-2 (no tokens were replaced before the tokenization).
@ -467,6 +467,8 @@ The following results were obtained using the `raw` WikiText-2 (no tokens were r
This example fine-tunes GPT-2 on the WikiText-2 dataset. The loss function is a causal language modeling loss (perplexity). This example fine-tunes GPT-2 on the WikiText-2 dataset. The loss function is a causal language modeling loss (perplexity).
.. code-block:: bash .. code-block:: bash
export WIKITEXT_2_DATASET=/path/to/wikitext_dataset export WIKITEXT_2_DATASET=/path/to/wikitext_dataset
python run_lm_finetuning.py python run_lm_finetuning.py
@ -485,6 +487,8 @@ This example fine-tunes RoBERTa on the WikiText-2 dataset. The loss function is
The `--mlm` flag is necessary to fine-tune BERT/RoBERTa on masked language modeling. The `--mlm` flag is necessary to fine-tune BERT/RoBERTa on masked language modeling.
.. code-block:: bash .. code-block:: bash
export WIKITEXT_2_DATASET=/path/to/wikitext_dataset export WIKITEXT_2_DATASET=/path/to/wikitext_dataset
python run_lm_finetuning.py python run_lm_finetuning.py

10
docs/source/model_doc/distilbert.rst
View File

@ -2,35 +2,35 @@ DistilBERT
---------------------------------------------------- ----------------------------------------------------
``DistilBertConfig`` ``DistilBertConfig``
~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: pytorch_transformers.DistilBertConfig .. autoclass:: pytorch_transformers.DistilBertConfig
:members: :members:
``DistilBertTokenizer`` ``DistilBertTokenizer``
~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: pytorch_transformers.DistilBertTokenizer .. autoclass:: pytorch_transformers.DistilBertTokenizer
:members: :members:
``DistilBertModel`` ``DistilBertModel``
~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: pytorch_transformers.DistilBertModel .. autoclass:: pytorch_transformers.DistilBertModel
:members: :members:
``DistilBertForMaskedLM`` ``DistilBertForMaskedLM``
~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: pytorch_transformers.DistilBertForMaskedLM .. autoclass:: pytorch_transformers.DistilBertForMaskedLM
:members: :members:
``DistilBertForSequenceClassification`` ``DistilBertForSequenceClassification``
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: pytorch_transformers.DistilBertForSequenceClassification .. autoclass:: pytorch_transformers.DistilBertForSequenceClassification
:members: :members: