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

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: 1.2590
- F1 Macro: 0.6890
- F1 Weighted: 0.6901
- Accuracy: 0.6889
- Precision Macro: 0.6897
- Recall Macro: 0.6887

## 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: 4
- eval_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:---------------:|:------------:|
| 1.0468        | 1.0   | 961  | 1.0346          | 0.5895   | 0.5948      | 0.5963   | 0.5980          | 0.5862       |
| 0.9324        | 2.0   | 1922 | 0.8973          | 0.6675   | 0.6697      | 0.6743   | 0.6670          | 0.6768       |
| 0.7848        | 3.0   | 2883 | 0.9689          | 0.6599   | 0.6632      | 0.6712   | 0.6624          | 0.6652       |
| 0.7983        | 4.0   | 3844 | 1.3608          | 0.6753   | 0.6805      | 0.6805   | 0.6889          | 0.6701       |
| 0.7084        | 5.0   | 4805 | 1.3093          | 0.6906   | 0.6922      | 0.6899   | 0.6938          | 0.6891       |
| 0.5763        | 6.0   | 5766 | 1.7146          | 0.6799   | 0.6830      | 0.6805   | 0.6857          | 0.6768       |
| 0.4508        | 7.0   | 6727 | 2.0875          | 0.6738   | 0.6773      | 0.6795   | 0.6770          | 0.6726       |
| 0.2905        | 8.0   | 7688 | 2.2861          | 0.6676   | 0.6700      | 0.6670   | 0.6709          | 0.6669       |


### Framework versions

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