---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: roberta-large-csb_1
  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-large-csb_1

This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2773
- Accuracy: 0.9011
- F1: 0.9010

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.5696        | 1.0   | 57   | 0.3749          | 0.8308   | 0.8307 |
| 0.3637        | 2.0   | 114  | 0.2749          | 0.8813   | 0.8812 |
| 0.3087        | 3.0   | 171  | 0.2479          | 0.8813   | 0.8813 |
| 0.2497        | 4.0   | 228  | 0.2415          | 0.8923   | 0.8919 |
| 0.2025        | 5.0   | 285  | 0.2773          | 0.9011   | 0.9010 |
| 0.1521        | 6.0   | 342  | 0.3194          | 0.8791   | 0.8790 |
| 0.1251        | 7.0   | 399  | 0.4850          | 0.8681   | 0.8664 |
| 0.0496        | 8.0   | 456  | 0.5794          | 0.8725   | 0.8710 |
| 0.0241        | 9.0   | 513  | 0.5833          | 0.8747   | 0.8738 |
| 0.0221        | 10.0  | 570  | 0.6399          | 0.8725   | 0.8713 |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.2.1
- Datasets 4.4.1
- Tokenizers 0.22.1