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_AntiGramPositive_doublePositiveCase
results: []
esm2_t12_35M_UR50D-finetuned-AMP_Classification_AntiGramPositive_doublePositiveCase
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: 0.0617
- Train Accuracy: 0.9772
- Validation Loss: 0.5210
- Validation Accuracy: 0.8551
- 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 |
|---|---|---|---|---|
| 0.4862 | 0.7800 | 0.4257 | 0.8218 | 0 |
| 0.3768 | 0.8474 | 0.3845 | 0.8478 | 1 |
| 0.2799 | 0.8950 | 0.3625 | 0.8643 | 2 |
| 0.2042 | 0.9241 | 0.3613 | 0.8617 | 3 |
| 0.1502 | 0.9427 | 0.3833 | 0.8745 | 4 |
| 0.1228 | 0.9545 | 0.3959 | 0.8719 | 5 |
| 0.0935 | 0.9650 | 0.4453 | 0.8682 | 6 |
| 0.0786 | 0.9692 | 0.4728 | 0.8711 | 7 |
| 0.0682 | 0.9750 | 0.4915 | 0.8727 | 8 |
| 0.0617 | 0.9772 | 0.5210 | 0.8551 | 9 |
Framework versions
- Transformers 4.40.2
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1