---
library_name: transformers
license: mit
base_model: microsoft/DialoGPT-medium
tags:
- generated_from_trainer
model-index:
- name: teachbuddy_DialoV2
  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. -->

# teachbuddy_DialoV2

This model is a fine-tuned version of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) with the yizhongw
self_instruct dataset.

It achieves the following results on the evaluation set:
- Loss: 1.0796

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.1998        | 1.0   | 18588 | 1.1785          |
| 0.988         | 2.0   | 37176 | 1.0944          |
| 0.8198        | 3.0   | 55764 | 1.0796          |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0