---
license: apache-2.0
tags:
- protein language model
- generated_from_trainer
datasets:
- train
metrics:
- spearmanr
model-index:
- name: tape-fluorescence-prediction-tape-fluorescence-evotuning-DistilProtBert
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: cradle-bio/tape-fluorescence
      type: train
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.6085202769301487
---

<!-- 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. -->

# tape-fluorescence-prediction-tape-fluorescence-evotuning-DistilProtBert

This model is a fine-tuned version of [thundaa/tape-fluorescence-evotuning-DistilProtBert](https://huggingface.co/thundaa/tape-fluorescence-evotuning-DistilProtBert) on the cradle-bio/tape-fluorescence dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2716
- Spearmanr: 0.6085

## 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: 5e-05
- train_batch_size: 40
- eval_batch_size: 40
- seed: 17
- gradient_accumulation_steps: 64
- total_train_batch_size: 2560
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Spearmanr |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 5.9308        | 0.93  | 7    | 1.6932          | 0.0822    |
| 1.0148        | 1.93  | 14   | 0.7407          | 0.1233    |
| 0.7748        | 2.93  | 21   | 0.7388          | 0.3237    |
| 0.7444        | 3.93  | 28   | 0.8205          | 0.4712    |
| 0.7623        | 4.93  | 35   | 0.7168          | 0.4582    |
| 0.7117        | 5.93  | 42   | 0.6898          | 0.4839    |
| 0.7987        | 6.93  | 49   | 1.1860          | 0.3994    |
| 0.8235        | 7.93  | 56   | 0.7290          | 0.4122    |
| 1.0447        | 8.93  | 63   | 1.8475          | 0.4169    |
| 0.9244        | 9.93  | 70   | 0.8985          | 0.4361    |
| 0.7392        | 10.93 | 77   | 0.7053          | 0.4709    |
| 0.5879        | 11.93 | 84   | 0.4930          | 0.4761    |
| 0.5723        | 12.93 | 91   | 0.9298          | 0.4765    |
| 0.7221        | 13.93 | 98   | 0.9479          | 0.4866    |
| 1.0731        | 14.93 | 105  | 0.5306          | 0.5040    |
| 0.5242        | 15.93 | 112  | 0.6331          | 0.4938    |
| 0.5606        | 16.93 | 119  | 0.4096          | 0.5060    |
| 0.5314        | 17.93 | 126  | 0.5781          | 0.5130    |
| 0.4384        | 18.93 | 133  | 0.3880          | 0.5393    |
| 0.4117        | 19.93 | 140  | 0.4584          | 0.5504    |
| 0.4387        | 20.93 | 147  | 0.3611          | 0.5674    |
| 0.3613        | 21.93 | 154  | 0.4159          | 0.5806    |
| 0.5157        | 22.93 | 161  | 0.4041          | 0.5869    |
| 0.4049        | 23.93 | 168  | 0.3187          | 0.5888    |
| 0.3318        | 24.93 | 175  | 0.3206          | 0.5889    |
| 0.3317        | 25.93 | 182  | 0.2964          | 0.5941    |
| 0.303         | 26.93 | 189  | 0.2803          | 0.6006    |
| 0.3058        | 27.93 | 196  | 0.2758          | 0.6042    |
| 0.2988        | 28.93 | 203  | 0.3016          | 0.6049    |
| 0.2814        | 29.93 | 210  | 0.2716          | 0.6085    |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1