typeform
/
distilbert-base-uncased-mnli
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
David Chu 2021-05-27 09:53:20 +00:00 committed by huggingface-web
parent f507f5c180
commit 3a1c032540
1 changed files with 24 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
README.md
View File

@ -11,4 +11,27 @@ metrics:
# DistilBERT base model (uncased)
This model is the Multi-Genre Natural Language Inference (MNLI) fine-turned version of the [uncased DistilBERT model](https://huggingface.co/distilbert-base-uncased).
This is the [uncased DistilBERT model](https://huggingface.co/distilbert-base-uncased) fine-tuned on [Multi-Genre Natural Language Inference](https://huggingface.co/datasets/multi_nli) (MNLI) dataset for the zero-shot classification task. The model is not case-sensitive, i.e., it does not make a difference between "english" and "English".
## Training
Training is done on a [p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) AWS EC2 instance (1 NVIDIA Tesla V100 GPUs), with the following hyperparameters:
```
$ run_glue.py \
--model_name_or_path distilbert-base-uncased \
--task_name mnli \
--do_train \
--do_eval \
--max_seq_length 128 \
--per_device_train_batch_size 16 \
--learning_rate 2e-5 \
--num_train_epochs 5 \
--output_dir /tmp/distilbert-base-uncased_mnli/
```
## Evaluation results
| Task | MNLI | MNLI-mm |
|:----:|:----:|:----:|
| | 82.0 | 82.0 |