---
library_name: peft
license: bsd-3-clause
base_model: hugohrban/progen2-base
tags:
- generated_from_trainer
model-index:
- name: Progen2_Kinase_PhosphositeGen_dkz_traindata_250step
  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. -->

# Progen2_Kinase_PhosphositeGen_dkz_traindata_250step

This model is a fine-tuned version of [hugohrban/progen2-base](https://huggingface.co/hugohrban/progen2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0437
- Perplexity: 7.7194

## 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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 250

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Perplexity |
|:-------------:|:------:|:----:|:---------------:|:----------:|
| 9.8555        | 0.2793 | 100  | 2.1451          | 8.5432     |
| 8.5245        | 0.5587 | 200  | 2.0437          | 7.7194     |


### Framework versions

- PEFT 0.13.2
- Transformers 4.47.1
- Pytorch 2.1.0.post301
- Datasets 3.0.2
- Tokenizers 0.21.0