Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## Model Description
|
2 |
+
This model is based on RoBERTa large (Liu, 2019), fine-tuned on a dataset of intent expressions available [here](https://research.ibm.com/haifa/dept/vst/debating_data.shtml) and also on 🤗 Transformer datasets hub [here](https://huggingface.co/datasets/ibm/vira-intents).
|
3 |
+
|
4 |
+
The model was created as part of the work described in [Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy
|
5 |
+
](https://arxiv.org/abs/2205.11966). If you use this model, please cite our work.
|
6 |
+
|
7 |
+
The official GitHub is [here](https://github.com/IBM/vira-intent-discovery). The script used for training the model is [trainer.py](https://github.com/IBM/vira-intent-discovery/blob/master/trainer.py).
|
8 |
+
|
9 |
+
|
10 |
+
## Training parameters
|
11 |
+
1. base_model = 'roberta-large'
|
12 |
+
1. learning_rate=5e-6
|
13 |
+
1. per_device_train_batch_size=16,
|
14 |
+
1. per_device_eval_batch_size=16,
|
15 |
+
1. num_train_epochs=15,
|
16 |
+
1. load_best_model_at_end=True,
|
17 |
+
1. save_total_limit=1,
|
18 |
+
1. save_strategy='epoch',
|
19 |
+
1. evaluation_strategy='epoch',
|
20 |
+
1. metric_for_best_model='accuracy',
|
21 |
+
1. seed=123
|
22 |
+
|
23 |
+
## Data collator
|
24 |
+
DataCollatorWithPadding
|