bhadresh-savani
commited on
Commit
·
e9e87fd
1
Parent(s):
f7c166c
Update README.md
Browse files
README.md
CHANGED
@@ -15,7 +15,8 @@ metrics:
|
|
15 |
# robert-base-emotion
|
16 |
|
17 |
## Model description:
|
18 |
-
|
|
|
19 |
```
|
20 |
learning rate 2e-5,
|
21 |
batch size 64,
|
|
|
15 |
# robert-base-emotion
|
16 |
|
17 |
## Model description:
|
18 |
+
[roberta](https://arxiv.org/abs/1907.11692) is Bert with better hyperparameter choices so they said it's Robustly optimized Bert during pretraining.
|
19 |
+
[roberta-base](https://huggingface.co/roberta-base) finetuned on the emotion dataset using HuggingFace Trainer with below Hyperparameters
|
20 |
```
|
21 |
learning rate 2e-5,
|
22 |
batch size 64,
|