metadata
license: mit
tags:
- generated_from_keras_callback
base_model: facebook/esm2_t12_35M_UR50D
model-index:
- name: esm2_t12_35M_UR50D-finetuned-AMP_Classification_HighAccuracy
results: []
esm2_t12_35M_UR50D-finetuned-AMP_Classification_HighAccuracy
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: 0.0059
- Train Accuracy: 0.9981
- Validation Loss: 0.0985
- Validation Accuracy: 0.9769
- Epoch: 9
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 |
|---|---|---|---|---|
| 0.1093 | 0.9602 | 0.0862 | 0.9702 | 0 |
| 0.0626 | 0.9763 | 0.0717 | 0.9723 | 1 |
| 0.0372 | 0.9858 | 0.0976 | 0.9713 | 2 |
| 0.0204 | 0.9927 | 0.0913 | 0.9771 | 3 |
| 0.0121 | 0.9964 | 0.0953 | 0.9769 | 4 |
| 0.0109 | 0.9963 | 0.1082 | 0.9752 | 5 |
| 0.0085 | 0.9970 | 0.1057 | 0.9728 | 6 |
| 0.0063 | 0.9981 | 0.1145 | 0.9736 | 7 |
| 0.0051 | 0.9984 | 0.1181 | 0.9755 | 8 |
| 0.0059 | 0.9981 | 0.0985 | 0.9769 | 9 |
Framework versions
- Transformers 4.40.1
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1