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

Improve mismatched sizes management when loading a pretrained model (#17257)

Browse Source 
- Add --ignore_mismatched_sizes argument to classification examples

- Expand the error message when loading a model whose head dimensions are different from expected dimensions
This commit is contained in:
regisss
2022-05-17 17:58:14 +02:00
committed by GitHub
parent 1f13ba818e
commit 28a0811652
13 changed files with 64 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/pytorch/text-classification/README.md
View File

@@ -22,7 +22,7 @@ Based on the script [`run_glue.py`](https://github.com/huggingface/transformers/
Fine-tuning the library models for sequence classification on the GLUE benchmark: [General Language Understanding
Evaluation](https://gluebenchmark.com/). This script can fine-tune any of the models on the [hub](https://huggingface.co/models)
and can also be used for a dataset hosted on our [hub](https://huggingface.co/datasets) or your own data in a csv or a JSON file
and can also be used for a dataset hosted on our [hub](https://huggingface.co/datasets) or your own data in a csv or a JSON file
(the script might need some tweaks in that case, refer to the comments inside for help).
GLUE is made up of a total of 9 different tasks. Here is how to run the script on one of them:
@@ -79,6 +79,8 @@ python run_glue.py \
--output_dir /tmp/imdb/
```
> If your model classification head dimensions do not fit the number of labels in the dataset, you can specify `--ignore_mismatched_sizes` to adapt it.
### Mixed precision training