---
license: mit
tags:
- generated_from_trainer
model-index:
- name: gpt2chess_scratch
  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. -->

# gpt2chess_scratch

This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6902

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.3139        | 0.7   | 5000  | 0.9635          |
| 0.9239        | 1.4   | 10000 | 0.8407          |
| 0.8367        | 2.1   | 15000 | 0.7807          |
| 0.7813        | 2.8   | 20000 | 0.7415          |
| 0.7373        | 3.5   | 25000 | 0.7127          |
| 0.7073        | 4.2   | 30000 | 0.6955          |
| 0.6853        | 4.9   | 35000 | 0.6902          |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3