[model_cards] roberta-base-finetuned-yelp-polarity (huggingface#6009)

* [model_cards] roberta-base-finetuned-yelp-polarity * Update model_cards/VictorSanh/roberta-base-finetuned-yelp-polarity/README.md Co-authored-by: Julien Chaumond <[email protected]> Co-authored-by: Julien Chaumond <[email protected]>
akreal · Jul 24, 2020 · 778e635 · 778e635
1 parent 614fef1
commit 778e635
Showing 1 changed file with 25 additions and 0 deletions.
diff --git a/model_cards/VictorSanh/roberta-base-finetuned-yelp-polarity/README.md b/model_cards/VictorSanh/roberta-base-finetuned-yelp-polarity/README.md
@@ -0,0 +1,25 @@
+---
+language: en
+datasets:
+- yelp_polarity
+---
+
+# RoBERTa-base-finetuned-yelp-polarity
+
+This is a [RoBERTa-base](https://huggingface.co/roberta-base) checkpoint fine-tuned on binary sentiment classifcation from [Yelp polarity](https://huggingface.co/nlp/viewer/?dataset=yelp_polarity).
+It gets **98.08%** accuracy on the test set.
+
+## Hyper-parameters
+
+We used the following hyper-parameters to train the model on one GPU:
+```python
+num_train_epochs            = 2.0
+learning_rate               = 1e-05
+weight_decay                = 0.0
+adam_epsilon                = 1e-08
+max_grad_norm               = 1.0
+per_device_train_batch_size = 32
+gradient_accumulation_steps = 1
+warmup_steps                = 3500
+seed                        = 42
+```