---
license: mit
base_model: kavg/LiLT-SER-ES
tags:
- generated_from_trainer
datasets:
- xfun
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: LiLT-SER-ES-SIN
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: xfun
      type: xfun
      config: xfun.sin
      split: validation
      args: xfun.sin
    metrics:
    - name: Precision
      type: precision
      value: 0.7538829151732378
    - name: Recall
      type: recall
      value: 0.7770935960591133
    - name: F1
      type: f1
      value: 0.7653123104912068
    - name: Accuracy
      type: accuracy
      value: 0.8560807967456866
---

<!-- 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. -->

# LiLT-SER-ES-SIN

This model is a fine-tuned version of [kavg/LiLT-SER-ES](https://huggingface.co/kavg/LiLT-SER-ES) on the xfun dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4009
- Precision: 0.7539
- Recall: 0.7771
- F1: 0.7653
- Accuracy: 0.8561

## 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: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0045        | 21.74  | 500   | 0.8773          | 0.7107    | 0.7352 | 0.7228 | 0.8582   |
| 0.0044        | 43.48  | 1000  | 1.1262          | 0.7030    | 0.7463 | 0.7240 | 0.8495   |
| 0.0021        | 65.22  | 1500  | 1.1512          | 0.6938    | 0.7254 | 0.7092 | 0.8419   |
| 0.0           | 86.96  | 2000  | 1.2416          | 0.7043    | 0.7537 | 0.7281 | 0.8390   |
| 0.0002        | 108.7  | 2500  | 1.2400          | 0.7036    | 0.7426 | 0.7226 | 0.8492   |
| 0.0001        | 130.43 | 3000  | 1.2076          | 0.7095    | 0.7488 | 0.7286 | 0.8432   |
| 0.0001        | 152.17 | 3500  | 1.1215          | 0.7174    | 0.7315 | 0.7244 | 0.8552   |
| 0.0008        | 173.91 | 4000  | 1.1580          | 0.7188    | 0.7303 | 0.7245 | 0.8534   |
| 0.0           | 195.65 | 4500  | 1.2805          | 0.7256    | 0.7328 | 0.7292 | 0.8596   |
| 0.0001        | 217.39 | 5000  | 1.1563          | 0.7110    | 0.7635 | 0.7363 | 0.8526   |
| 0.0           | 239.13 | 5500  | 1.1503          | 0.7585    | 0.7734 | 0.7659 | 0.8645   |
| 0.0           | 260.87 | 6000  | 1.3623          | 0.7419    | 0.7648 | 0.7532 | 0.8557   |
| 0.001         | 282.61 | 6500  | 1.1415          | 0.7405    | 0.7660 | 0.7530 | 0.8707   |
| 0.0           | 304.35 | 7000  | 1.2738          | 0.7390    | 0.7635 | 0.7511 | 0.8644   |
| 0.0           | 326.09 | 7500  | 1.3134          | 0.7682    | 0.7672 | 0.7677 | 0.8683   |
| 0.0           | 347.83 | 8000  | 1.4709          | 0.7608    | 0.7599 | 0.7603 | 0.8475   |
| 0.0           | 369.57 | 8500  | 1.4720          | 0.7509    | 0.75   | 0.7505 | 0.8499   |
| 0.0           | 391.3  | 9000  | 1.4492          | 0.7617    | 0.7635 | 0.7626 | 0.8530   |
| 0.0           | 413.04 | 9500  | 1.4251          | 0.7458    | 0.7734 | 0.7594 | 0.8550   |
| 0.0           | 434.78 | 10000 | 1.4009          | 0.7539    | 0.7771 | 0.7653 | 0.8561   |


### Framework versions

- Transformers 4.39.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1