---
license: mit
tags:
- generated_from_trainer
model-index:
- name: roberta-base-academic
  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. -->

# roberta-base-academic

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4621

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.668         | 1.0   | 169  | 1.5412          |
| 1.6261        | 2.0   | 338  | 1.5138          |
| 1.5967        | 3.0   | 507  | 1.4943          |
| 1.5745        | 4.0   | 676  | 1.4913          |
| 1.5549        | 5.0   | 845  | 1.4738          |
| 1.5445        | 6.0   | 1014 | 1.4671          |
| 1.536         | 7.0   | 1183 | 1.4689          |
| 1.5254        | 8.0   | 1352 | 1.4612          |
| 1.5244        | 9.0   | 1521 | 1.4560          |
| 1.5263        | 10.0  | 1690 | 1.4580          |
| 1.5249        | 11.0  | 1859 | 1.4482          |
| 1.5238        | 12.0  | 2028 | 1.4565          |
| 1.526         | 13.0  | 2197 | 1.4568          |
| 1.5232        | 14.0  | 2366 | 1.4547          |
| 1.5232        | 15.0  | 2535 | 1.4558          |


### Framework versions

- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2