metadata
library_name: transformers
license: mit
base_model: emanjavacas/GysBERT
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: ArjanvD95/animals_manually_curated
results: []
ArjanvD95/animals_manually_curated
This model is a fine-tuned version of emanjavacas/GysBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0337
- Precision: 0.7869
- Recall: 0.7912
- F1: 0.7890
- Accuracy: 0.9921
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: Use OptimizerNames.ADAMW_TORCH 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: 5
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0162 | 1.0 | 152 | 0.0321 | 0.7031 | 0.7418 | 0.7219 | 0.9886 |
| 0.0132 | 2.0 | 304 | 0.0275 | 0.7278 | 0.7198 | 0.7238 | 0.9900 |
| 0.001 | 3.0 | 456 | 0.0478 | 0.7985 | 0.5879 | 0.6772 | 0.9870 |
| 0.0015 | 4.0 | 608 | 0.0325 | 0.8095 | 0.7473 | 0.7771 | 0.9906 |
| 0.0077 | 5.0 | 760 | 0.0337 | 0.7869 | 0.7912 | 0.7890 | 0.9921 |
| 0.0003 | 6.0 | 912 | 0.0510 | 0.8621 | 0.6868 | 0.7645 | 0.9900 |
| 0.0001 | 7.0 | 1064 | 0.0517 | 0.8435 | 0.6813 | 0.7538 | 0.9899 |
| 0.0001 | 8.0 | 1216 | 0.0553 | 0.8690 | 0.6923 | 0.7706 | 0.9900 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.1