---
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: cs605-nlp-assignment-2-roberta-large-v2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# cs605-nlp-assignment-2-roberta-large-v2

This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1276
- Accuracy: 0.8277

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1.0502427338108112e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5531        | 1.0   | 746  | 0.4080          | 0.8025   |
| 0.3957        | 2.0   | 1492 | 0.4222          | 0.8277   |
| 0.1887        | 3.0   | 2238 | 0.4982          | 0.8193   |
| 0.1522        | 4.0   | 2984 | 0.6922          | 0.8314   |
| 0.0669        | 5.0   | 3730 | 0.8141          | 0.8253   |
| 0.0526        | 6.0   | 4476 | 0.9023          | 0.8223   |
| 0.0301        | 7.0   | 5222 | 0.9764          | 0.8267   |
| 0.0218        | 8.0   | 5968 | 0.9749          | 0.8320   |
| 0.0136        | 9.0   | 6714 | 1.0319          | 0.8247   |
| 0.0095        | 10.0  | 7460 | 1.1276          | 0.8277   |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1