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

Add new run_swag example (#9175)

Browse Source 
* Add new run_swag example

* Add check

* Add sample

* Apply suggestions from code review

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

* Very important change to make Lysandre happy

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
This commit is contained in:
Sylvain Gugger
2020-12-18 14:19:24 -05:00
committed by GitHub
parent 3e56e2ce04
commit 9a25c5bd3a
7 changed files with 970 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
examples/multiple-choice/README.md
View File

@@ -16,27 +16,20 @@ limitations under the License.
## Multiple Choice
Based on the script [`run_multiple_choice.py`]().
Based on the script [`run_swag.py`]().
#### Fine-tuning on SWAG
Download [swag](https://github.com/rowanz/swagaf/tree/master/data) data
```bash
#training on 4 tesla V100(16GB) GPUS
export SWAG_DIR=/path/to/swag_data_dir
python ./examples/multiple-choice/run_multiple_choice.py \
--task_name swag \
python examples/multiple-choice/run_swag.py \
--model_name_or_path roberta-base \
--do_train \
--do_eval \
--data_dir $SWAG_DIR \
--learning_rate 5e-5 \
--num_train_epochs 3 \
--max_seq_length 80 \
--output_dir models_bert/swag_base \
--output_dir /tmp/swag_base \
--per_gpu_eval_batch_size=16 \
--per_device_train_batch_size=16 \
--gradient_accumulation_steps 2 \
--overwrite_output
```
Training with the defined hyper-parameters yields the following results: