|
--- |
|
license: mit |
|
base_model: facebook/esm2_t33_650M_UR50D |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: esm2_t33_650M_UR50D-finetuned-localization |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# esm2_t33_650M_UR50D-finetuned-localization |
|
|
|
This model is a fine-tuned version of [facebook/esm2_t33_650M_UR50D](https://huggingface.co/facebook/esm2_t33_650M_UR50D) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2770 |
|
- Accuracy: 0.7143 |
|
|
|
## 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: 3 |
|
- eval_batch_size: 3 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 35 | 0.7696 | 0.5429 | |
|
| No log | 2.0 | 70 | 0.6544 | 0.5714 | |
|
| No log | 3.0 | 105 | 0.8123 | 0.6571 | |
|
| No log | 4.0 | 140 | 0.9189 | 0.7429 | |
|
| No log | 5.0 | 175 | 0.9507 | 0.7143 | |
|
| No log | 6.0 | 210 | 1.1805 | 0.7429 | |
|
| No log | 7.0 | 245 | 1.2770 | 0.7143 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
