SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge branch 'master' into fix-xlnet-squad2.0

Browse Source
This commit is contained in:
Thomas Wolf
2019-12-21 12:48:10 +01:00
committed by GitHub
parent ca99a2d500 8618bf15d6
commit 562f864038
200 changed files with 20341 additions and 3889 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
examples/README.md
View File

@@ -3,6 +3,17 @@
In this section a few examples are put together. All of these examples work for several models, making use of the very
similar API between the different models.
**Important**
To run the latest versions of the examples, you have to install from source and install some specific requirements for the examples.
Execute the following steps in a new virtual environment:
```bash
git clone https://github.com/huggingface/transformers
cd transformers
pip install [--editable] .
pip install -r ./examples/requirements.txt
```
| Section | Description |
|----------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [TensorFlow 2.0 models on GLUE](#TensorFlow-2.0-Bert-models-on-GLUE) | Examples running BERT TensorFlow 2.0 model on the GLUE tasks.
@@ -12,7 +23,7 @@ similar API between the different models.
| [SQuAD](#squad) | Using BERT/RoBERTa/XLNet/XLM for question answering, examples with distributed training. |
| [Multiple Choice](#multiple-choice) | Examples running BERT/XLNet/RoBERTa on the SWAG/RACE/ARC tasks.
| [Named Entity Recognition](#named-entity-recognition) | Using BERT for Named Entity Recognition (NER) on the CoNLL 2003 dataset, examples with distributed training. |
| [Abstractive summarization](#abstractive-summarization) | Fine-tuning the library models for abstractive summarization tasks on the CNN/Daily Mail dataset. |
| [XNLI](#xnli) | Examples running BERT/XLM on the XNLI benchmark. |
## TensorFlow 2.0 Bert models on GLUE
@@ -506,7 +517,8 @@ Larger batch size may improve the performance while costing more memory.
## Named Entity Recognition
Based on the script [`run_ner.py`](https://github.com/huggingface/transformers/blob/master/examples/run_ner.py).
Based on the scripts [`run_ner.py`](https://github.com/huggingface/transformers/blob/master/examples/run_ner.py) for Pytorch and
[`run_tf_ner.py`](https://github.com/huggingface/transformers/blob/master/examples/run_tf_ner.py) for Tensorflow 2.
This example fine-tune Bert Multilingual on GermEval 2014 (German NER).
Details and results for the fine-tuning provided by @stefan-it.
@@ -551,7 +563,7 @@ The GermEval 2014 dataset has much more labels than CoNLL-2002/2003 datasets, so
cat train.txt dev.txt test.txt | cut -d " " -f 2 | grep -v "^$"| sort | uniq > labels.txt
```
### Training
### Prepare the run
Additional environment variables must be set:
@@ -563,6 +575,8 @@ export SAVE_STEPS=750
export SEED=1
```
### Run the Pytorch version
To start training, just run:
```bash
@@ -583,7 +597,7 @@ python3 run_ner.py --data_dir ./ \
If your GPU supports half-precision training, just add the `--fp16` flag. After training, the model will be both evaluated on development and test datasets.
### Evaluation
#### Evaluation
Evaluation on development dataset outputs the following for our example:
@@ -605,7 +619,7 @@ On the test dataset the following results could be achieved:
10/04/2019 00:42:42 - INFO - __main__ - recall = 0.8624150210424085
```
### Comparing BERT (large, cased), RoBERTa (large, cased) and DistilBERT (base, uncased)
#### Comparing BERT (large, cased), RoBERTa (large, cased) and DistilBERT (base, uncased)
Here is a small comparison between BERT (large, cased), RoBERTa (large, cased) and DistilBERT (base, uncased) with the same hyperparameters as specified in the [example documentation](https://huggingface.co/transformers/examples.html#named-entity-recognition) (one run):
@@ -615,30 +629,108 @@ Here is a small comparison between BERT (large, cased), RoBERTa (large, cased) a
| `roberta-large` | 95.96 | 91.87
| `distilbert-base-uncased` | 94.34 | 90.32
## Abstractive summarization
### Run the Tensorflow 2 version
Based on the script
[`run_summarization_finetuning.py`](https://github.com/huggingface/transformers/blob/master/examples/run_summarization_finetuning.py).
Before running this script you should download **both** CNN and Daily Mail
datasets from [Kyunghyun Cho's website](https://cs.nyu.edu/~kcho/DMQA/) (the
links next to "Stories") in the same folder. Then uncompress the archives by running:
To start training, just run:
```bash
tar -xvf cnn_stories.tgz && tar -xvf dailymail_stories.tgz
python3 run_tf_ner.py --data_dir ./ \
--model_type bert \
--labels ./labels.txt \
--model_name_or_path $BERT_MODEL \
--output_dir $OUTPUT_DIR \
--max_seq_length $MAX_LENGTH \
--num_train_epochs $NUM_EPOCHS \
--per_device_train_batch_size $BATCH_SIZE \
--save_steps $SAVE_STEPS \
--seed $SEED \
--do_train \
--do_eval \
--do_predict
```
note that the finetuning script **will not work** if you do not download both
datasets. We will refer as `$DATA_PATH` the path to where you uncompressed both
archive.
Such as the Pytorch version, if your GPU supports half-precision training, just add the `--fp16` flag. After training, the model will be both evaluated on development and test datasets.
#### Evaluation
Evaluation on development dataset outputs the following for our example:
```bash
precision recall f1-score support
LOCderiv 0.7619 0.6154 0.6809 52
PERpart 0.8724 0.8997 0.8858 4057
OTHpart 0.9360 0.9466 0.9413 711
ORGpart 0.7015 0.6989 0.7002 269
LOCpart 0.7668 0.8488 0.8057 496
LOC 0.8745 0.9191 0.8963 235
ORGderiv 0.7723 0.8571 0.8125 91
OTHderiv 0.4800 0.6667 0.5581 18
OTH 0.5789 0.6875 0.6286 16
PERderiv 0.5385 0.3889 0.4516 18
PER 0.5000 0.5000 0.5000 2
ORG 0.0000 0.0000 0.0000 3
micro avg 0.8574 0.8862 0.8715 5968
macro avg 0.8575 0.8862 0.8713 5968
```
On the test dataset the following results could be achieved:
```bash
precision recall f1-score support
PERpart 0.8847 0.8944 0.8896 9397
OTHpart 0.9376 0.9353 0.9365 1639
ORGpart 0.7307 0.7044 0.7173 697
LOC 0.9133 0.9394 0.9262 561
LOCpart 0.8058 0.8157 0.8107 1150
ORG 0.0000 0.0000 0.0000 8
OTHderiv 0.5882 0.4762 0.5263 42
PERderiv 0.6571 0.5227 0.5823 44
OTH 0.4906 0.6667 0.5652 39
ORGderiv 0.7016 0.7791 0.7383 172
LOCderiv 0.8256 0.6514 0.7282 109
PER 0.0000 0.0000 0.0000 11
micro avg 0.8722 0.8774 0.8748 13869
macro avg 0.8712 0.8774 0.8740 13869
```
## XNLI
Based on the script [`run_xnli.py`](https://github.com/huggingface/transformers/blob/master/examples/run_xnli.py).
[XNLI](https://www.nyu.edu/projects/bowman/xnli/) is crowd-sourced dataset based on [MultiNLI](http://www.nyu.edu/projects/bowman/multinli/). It is an evaluation benchmark for cross-lingual text representations. Pairs of text are labeled with textual entailment annotations for 15 different languages (including both high-ressource language such as English and low-ressource languages such as Swahili).
#### Fine-tuning on XNLI
This example code fine-tunes mBERT (multi-lingual BERT) on the XNLI dataset. It runs in 106 mins
on a single tesla V100 16GB. The data for XNLI can be downloaded with the following links and should be both saved (and un-zipped) in a
`$XNLI_DIR` directory.
* [XNLI 1.0](https://www.nyu.edu/projects/bowman/xnli/XNLI-1.0.zip)
* [XNLI-MT 1.0](https://www.nyu.edu/projects/bowman/xnli/XNLI-MT-1.0.zip)
```bash
export DATA_PATH=/path/to/dataset/
export XNLI_DIR=/path/to/XNLI
python run_summarization_finetuning.py \
--output_dir=output \
--model_type=bert2bert \
--model_name_or_path=bert2bert \
--do_train \
--data_path=$DATA_PATH \
python run_xnli.py \
--model_type bert \
--model_name_or_path bert-base-multilingual-cased \
--language de \
--train_language en \
--do_train \
--do_eval \
--data_dir $XNLI_DIR \
--per_gpu_train_batch_size 32 \
--learning_rate 5e-5 \
--num_train_epochs 2.0 \
--max_seq_length 128 \
--output_dir /tmp/debug_xnli/ \
--save_steps -1
```
Training with the previously defined hyper-parameters yields the following results on the **test** set:
```bash
acc = 0.7093812375249501
```