Bert Base Uncased Mnli

🚀 bert-base-uncased finetuned on MNLI

This project fine-tunes the bert-base-uncased model on the MNLI dataset for text classification tasks.

🚀 Quick Start

The README doesn't provide quick - start steps, but you can typically start by loading the fine - tuned model using relevant deep - learning frameworks.

✨ Features

• Pytorch - Based: Built on the PyTorch framework, which is popular for its dynamic computational graphs and ease of use.
• Text Classification: Specifically fine - tuned for text classification tasks using the MNLI dataset.

📦 Installation

The README doesn't contain installation steps. Usually, you need to install PyTorch and relevant deep - learning libraries to use the model.

📚 Documentation

Model Details and Training Data

We used the pretrained model from bert-base-uncased and finetuned it on MultiNLI dataset.

The training parameters were kept the same as Devlin et al., 2019 (learning rate = 2e - 5, training epochs = 3, max_sequence_len = 128 and batch_size = 32).

Evaluation Results

The evaluation results are mentioned in the table below.