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_25_06
results: []
FS_25_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: 0.1755
- Accuracy: 0.9647
- Precision: 0.9651
- Recall: 0.9646
- F1: 0.9644
- Ratio: 0.0529
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 | Ratio |
|---|---|---|---|---|---|---|---|---|
| 1.7815 | 1.0 | 362 | 1.6483 | 0.9059 | 0.9166 | 0.9061 | 0.9069 | 0.0569 |
| 0.364 | 2.0 | 724 | 0.2948 | 0.9451 | 0.9480 | 0.9450 | 0.9447 | 0.0569 |
| 0.0418 | 3.0 | 1086 | 0.2467 | 0.9510 | 0.9529 | 0.9509 | 0.9509 | 0.0549 |
| 0.0218 | 4.0 | 1448 | 0.1853 | 0.9647 | 0.9651 | 0.9646 | 0.9644 | 0.0529 |
| 0.0985 | 5.0 | 1810 | 0.1755 | 0.9647 | 0.9651 | 0.9646 | 0.9644 | 0.0529 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1