---
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-sentiment-b16
  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-sentiment-b16

This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8547
- F1 Macro: 0.6656
- F1 Weighted: 0.6666
- Accuracy: 0.6713
- Precision Macro: 0.6629
- Recall Macro: 0.6739

## 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
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy | Precision Macro | Recall Macro |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:---------------:|:------------:|
| 1.0883        | 1.0   | 241  | 0.9511          | 0.4626   | 0.4704      | 0.5317   | 0.5065          | 0.5293       |
| 0.8226        | 2.0   | 482  | 0.7453          | 0.6783   | 0.6819      | 0.6816   | 0.6879          | 0.6735       |
| 0.6465        | 3.0   | 723  | 0.7917          | 0.6843   | 0.6879      | 0.6993   | 0.6929          | 0.6948       |
| 0.5062        | 4.0   | 964  | 0.8112          | 0.6898   | 0.6922      | 0.6951   | 0.6882          | 0.6934       |
| 0.3937        | 5.0   | 1205 | 0.9096          | 0.6829   | 0.6822      | 0.6774   | 0.6989          | 0.6844       |
| 0.2821        | 6.0   | 1446 | 1.0649          | 0.6833   | 0.6861      | 0.6878   | 0.6813          | 0.6869       |
| 0.209         | 7.0   | 1687 | 1.2212          | 0.6824   | 0.6844      | 0.6826   | 0.6851          | 0.6804       |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1