beto-sarcasmo-bs16-ep6
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5169
- F1 Macro: 0.9168
- F1 Weighted: 0.9208
- Accuracy: 0.9209
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.2962 | 1.0 | 955 | 0.2739 | 0.8925 | 0.8970 | 0.8966 |
| 0.2186 | 2.0 | 1910 | 0.2419 | 0.9133 | 0.9177 | 0.9181 |
| 0.1413 | 3.0 | 2865 | 0.3860 | 0.9093 | 0.9142 | 0.9149 |
| 0.0924 | 4.0 | 3820 | 0.4210 | 0.9177 | 0.9217 | 0.9220 |
| 0.0331 | 5.0 | 4775 | 0.4832 | 0.9160 | 0.9201 | 0.9204 |
| 0.0230 | 6.0 | 5730 | 0.5169 | 0.9168 | 0.9208 | 0.9209 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2