---
base_model: checkpoint_raw/gpt2
datasets:
- Salesforce/dialogstudio
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: tweet-summarization-gpt-2-finetuned
  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. -->

# tweet-summarization-gpt-2-finetuned

This model is a fine-tuned version of [gpt2-hf](https://huggingface.co/gpt2-hf) on the Salesforce/dialogstudio dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5758

## 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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.9466        | 1.0   | 55   | 3.5758          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.0.1+cu117
- Datasets 3.0.1
- Tokenizers 0.20.1