---
library_name: peft
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: emotion-model2_0
  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. -->

# emotion-model2_0

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9084
- Accuracy: 0.6936
- F1: 0.6742

## 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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.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     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 1.3859        | 1.0   | 59   | 1.3517          | 0.3532   | 0.3095 |
| 1.3202        | 2.0   | 118  | 1.2139          | 0.4638   | 0.3687 |
| 1.2606        | 3.0   | 177  | 1.1094          | 0.4851   | 0.3847 |
| 1.1821        | 4.0   | 236  | 1.0527          | 0.6213   | 0.6134 |
| 1.1665        | 5.0   | 295  | 0.9899          | 0.6638   | 0.6531 |
| 1.0941        | 6.0   | 354  | 0.9975          | 0.6043   | 0.5800 |
| 1.0943        | 7.0   | 413  | 0.9871          | 0.6085   | 0.5815 |
| 1.0671        | 8.0   | 472  | 0.9084          | 0.6936   | 0.6742 |
| 1.0401        | 9.0   | 531  | 0.9085          | 0.6681   | 0.6488 |
| 1.0221        | 10.0  | 590  | 0.9170          | 0.6681   | 0.6488 |


### Framework versions

- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1