<!-- 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. -->
roberta-large-bne-finetuned-go_emotions-es
This model is a fine-tuned version of PlanTL-GOB-ES/roberta-large-bne on the go_emotions dataset. It achieves the following results on the evaluation set:
- Loss: 3.2457
- Accuracy: 0.5668
- F1: 0.5572
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.5678 | 1.0 | 9077 | 1.5649 | 0.5671 | 0.5197 |
| 1.3898 | 2.0 | 18154 | 1.5005 | 0.5776 | 0.5492 |
| 0.915 | 3.0 | 27231 | 1.8045 | 0.5891 | 0.5692 |
| 0.5424 | 4.0 | 36308 | 2.8463 | 0.5646 | 0.5519 |
| 0.2018 | 5.0 | 45385 | 3.2457 | 0.5668 | 0.5572 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
