---
library_name: transformers
license: mit
base_model: openai-community/gpt2
tags:
- trl
- sft
- generated_from_trainer
datasets:
- piqa
model-index:
- name: HW2-supervised
  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. -->

# HW2-supervised

This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the piqa dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0381

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 3.1038        | 2.2051 | 500  | 3.0381          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1