metadata
library_name: transformers
base_model: dccuchile/bert-base-spanish-wwm-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: beto-sarcasmo-bs32-ep10
results: []
beto-sarcasmo-bs32-ep10
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: 0.5936
- F1 Macro: 0.9183
- F1 Weighted: 0.9220
- Accuracy: 0.9220
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Weighted | Accuracy |
|---|---|---|---|---|---|---|
| 0.5422 | 1.0 | 478 | 0.2359 | 0.9047 | 0.9091 | 0.9092 |
| 0.3034 | 2.0 | 956 | 0.2450 | 0.9124 | 0.9165 | 0.9165 |
| 0.2124 | 3.0 | 1434 | 0.3679 | 0.9193 | 0.9232 | 0.9233 |
| 0.1062 | 4.0 | 1912 | 0.4428 | 0.9206 | 0.9244 | 0.9246 |
| 0.0373 | 5.0 | 2390 | 0.5984 | 0.9152 | 0.9190 | 0.9188 |
| 0.0181 | 6.0 | 2868 | 0.5936 | 0.9183 | 0.9220 | 0.9220 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 2.18.0
- Tokenizers 0.22.2