esm2_t12_35M_UR50D-inetuned-effector-protein-classifier
This model is a fine-tuned version of facebook/esm2_t12_35M_UR50D on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0769
- Accuracy: 0.9808
Model description
Classifies effector and non-effectors
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 235 | 0.0884 | 0.9744 |
| No log | 2.0 | 470 | 0.0737 | 0.9840 |
| 0.1121 | 3.0 | 705 | 0.0769 | 0.9808 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 110
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for nikolaenkov/finetuned-effector-protein-classifier
Base model
facebook/esm2_t12_35M_UR50D