metadata
library_name: transformers
license: mit
base_model: facebook/esm2_t12_35M_UR50D
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: esm2_t12_35M_UR50D_56623563
results: []
esm2_t12_35M_UR50D_56623563
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: 0.5887
- Accuracy: 0.8103
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:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 147 | 0.4424 | 0.8179 |
| No log | 2.0 | 294 | 0.4869 | 0.8 |
| No log | 3.0 | 441 | 0.5111 | 0.8179 |
| 0.36 | 4.0 | 588 | 0.5578 | 0.8103 |
| 0.36 | 5.0 | 735 | 0.5887 | 0.8103 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1.post103
- Datasets 3.1.0
- Tokenizers 0.20.4