metadata
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: FS_27_06
results: []
FS_27_06
This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1744
- Accuracy: 0.966
- Precision: 0.9668
- Recall: 0.966
- F1: 0.9660
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.6727 | 1.0 | 375 | 1.5301 | 0.93 | 0.9351 | 0.9300 | 0.9300 |
| 0.2375 | 2.0 | 750 | 0.2548 | 0.958 | 0.9622 | 0.958 | 0.9583 |
| 0.1424 | 3.0 | 1125 | 0.1922 | 0.96 | 0.9612 | 0.9600 | 0.9599 |
| 0.0197 | 4.0 | 1500 | 0.1789 | 0.966 | 0.9670 | 0.966 | 0.9660 |
| 0.0171 | 5.0 | 1875 | 0.1744 | 0.966 | 0.9668 | 0.966 | 0.9660 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1