roberta-base-bne-finetuned-fact
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-base-bne on the fact2020 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0368
- Precision: 0.9953
- Recall: 0.9906
- F1: 0.9911
- Accuracy: 0.9906
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 116 | 0.0404 | 0.9945 | 0.9899 | 0.9901 | 0.9899 |
No log | 2.0 | 232 | 0.0359 | 0.9948 | 0.9903 | 0.9906 | 0.9903 |
No log | 3.0 | 348 | 0.0368 | 0.9953 | 0.9906 | 0.9911 | 0.9906 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for filevich/roberta-base-bne-finetuned-fact
Base model
PlanTL-GOB-ES/roberta-base-bne
Finetuned
this model
Evaluation results
- Precision on fact2020validation set self-reported0.995
- Recall on fact2020validation set self-reported0.991
- F1 on fact2020validation set self-reported0.991
- Accuracy on fact2020validation set self-reported0.991