metadata
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: esm2_t12_35M_UR50D-finetuned-secondary-structure-classification
results: []
esm2_t12_35M_UR50D-finetuned-secondary-structure-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: 0.4076
- Train Masked Accuracy: 0.8342
- Validation Loss: 0.4714
- Validation Masked Accuracy: 0.8060
- Epoch: 2
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 Masked Accuracy | Validation Loss | Validation Masked Accuracy | Epoch |
|---|---|---|---|---|
| 0.5874 | 0.7454 | 0.4908 | 0.7962 | 0 |
| 0.4503 | 0.8156 | 0.4703 | 0.8043 | 1 |
| 0.4076 | 0.8342 | 0.4714 | 0.8060 | 2 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.9.2
- Datasets 2.7.1
- Tokenizers 0.13.2