metadata
license: mit
base_model: facebook/esm2_t12_35M_UR50D
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: esm2_t12_35M_UR50D-finetuned-localization
results: []
esm2_t12_35M_UR50D-finetuned-localization
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: 0.6460
- Accuracy: 0.5988
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: 192
- eval_batch_size: 192
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6832 | 1.0 | 1539 | 0.6716 | 0.5395 |
| 0.6411 | 2.0 | 3078 | 0.6368 | 0.5798 |
| 0.6178 | 3.0 | 4617 | 0.6281 | 0.5901 |
| 0.5951 | 4.0 | 6156 | 0.6293 | 0.5947 |
| 0.5682 | 5.0 | 7695 | 0.6460 | 0.5988 |
| 0.5395 | 6.0 | 9234 | 0.6822 | 0.5930 |
| 0.5107 | 7.0 | 10773 | 0.7306 | 0.5935 |
| 0.484 | 8.0 | 12312 | 0.7839 | 0.5906 |
| 0.4562 | 9.0 | 13851 | 0.8433 | 0.5917 |
| 0.4302 | 10.0 | 15390 | 0.8882 | 0.5893 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0