metadata
license: mit
base_model: facebook/esm2_t12_35M_UR50D
tags:
- generated_from_keras_callback
model-index:
- name: esm2_t12_35M_UR50D-finetuned-AMP_Antibacteria-classification
results: []
esm2_t12_35M_UR50D-finetuned-AMP_Antibacteria-classification
This model is a fine-tuned version of facebook/esm2_t12_35M_UR50D on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1606
- Train Accuracy: 0.9325
- Validation Loss: 0.6329
- Validation Accuracy: 0.7896
- Epoch: 4
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0}
- training_precision: float32
Training results
Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
---|---|---|---|---|
0.3565 | 0.8359 | 0.5393 | 0.7601 | 0 |
0.2744 | 0.8789 | 0.5657 | 0.7697 | 1 |
0.2267 | 0.9016 | 0.5296 | 0.7885 | 2 |
0.1844 | 0.9247 | 0.6085 | 0.7825 | 3 |
0.1606 | 0.9325 | 0.6329 | 0.7896 | 4 |
Framework versions
- Transformers 4.40.1
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1