---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: esm2_t30_150M_UR50D-crystallization-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_t30_150M_UR50D-crystallization-finetuned-localization

This model is a fine-tuned version of [facebook/esm2_t30_150M_UR50D](https://huggingface.co/facebook/esm2_t30_150M_UR50D) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4161
- F1: 0.5994

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | F1     |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 0.3948        | 1.0   | 1065  | 0.3929          | 0.6516 |
| 0.2678        | 2.0   | 2130  | 0.4647          | 0.6237 |
| 0.1524        | 3.0   | 3195  | 0.6984          | 0.6356 |
| 0.072         | 4.0   | 4260  | 0.9448          | 0.6312 |
| 0.0341        | 5.0   | 5325  | 1.1157          | 0.6099 |
| 0.0145        | 6.0   | 6390  | 1.2051          | 0.6144 |
| 0.0079        | 7.0   | 7455  | 1.3259          | 0.6149 |
| 0.007         | 8.0   | 8520  | 1.3418          | 0.6008 |
| 0.0027        | 9.0   | 9585  | 1.3921          | 0.6001 |
| 0.0014        | 10.0  | 10650 | 1.4161          | 0.5994 |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3