---
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: SYN_300524_epoch_2
  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. -->

# SYN_300524_epoch_2

This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3618
- Accuracy: 0.972
- Precision: 0.9723
- Recall: 0.972
- F1: 0.9720
- Ratio: 0.488

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 47
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- lr_scheduler_warmup_steps: 4
- num_epochs: 1
- label_smoothing_factor: 0.1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----:|
| 0.3977        | 0.0533 | 10   | 0.3957          | 0.951    | 0.9530    | 0.9510 | 0.9509 | 0.467 |
| 0.4006        | 0.1067 | 20   | 0.3771          | 0.96     | 0.9609    | 0.96   | 0.9600 | 0.478 |
| 0.3774        | 0.16   | 30   | 0.3709          | 0.963    | 0.9632    | 0.963  | 0.9630 | 0.491 |
| 0.3894        | 0.2133 | 40   | 0.3956          | 0.958    | 0.9592    | 0.958  | 0.9580 | 0.474 |
| 0.3423        | 0.2667 | 50   | 0.3938          | 0.96     | 0.9606    | 0.96   | 0.9600 | 0.482 |
| 0.3965        | 0.32   | 60   | 0.3794          | 0.959    | 0.9597    | 0.959  | 0.9590 | 0.481 |
| 0.3998        | 0.3733 | 70   | 0.3602          | 0.967    | 0.9670    | 0.967  | 0.9670 | 0.497 |
| 0.3718        | 0.4267 | 80   | 0.3998          | 0.956    | 0.9576    | 0.956  | 0.9560 | 0.47  |
| 0.3924        | 0.48   | 90   | 0.3829          | 0.963    | 0.9638    | 0.963  | 0.9630 | 0.479 |
| 0.371         | 0.5333 | 100  | 0.3816          | 0.966    | 0.9666    | 0.966  | 0.9660 | 0.482 |
| 0.3752        | 0.5867 | 110  | 0.3727          | 0.967    | 0.9675    | 0.967  | 0.9670 | 0.483 |
| 0.3631        | 0.64   | 120  | 0.3669          | 0.966    | 0.9665    | 0.966  | 0.9660 | 0.484 |
| 0.3934        | 0.6933 | 130  | 0.3641          | 0.968    | 0.9684    | 0.968  | 0.9680 | 0.486 |
| 0.3536        | 0.7467 | 140  | 0.3588          | 0.97     | 0.9701    | 0.97   | 0.9700 | 0.494 |
| 0.3542        | 0.8    | 150  | 0.3565          | 0.971    | 0.9710    | 0.971  | 0.9710 | 0.495 |
| 0.3785        | 0.8533 | 160  | 0.3580          | 0.971    | 0.9711    | 0.971  | 0.9710 | 0.493 |
| 0.3557        | 0.9067 | 170  | 0.3616          | 0.971    | 0.9713    | 0.971  | 0.9710 | 0.487 |
| 0.3592        | 0.96   | 180  | 0.3618          | 0.972    | 0.9723    | 0.972  | 0.9720 | 0.488 |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1