---
license: apache-2.0
base_model: distilroberta-base
tags:
- generated_from_trainer
inference: false
datasets:
- HuggingFaceFW/fineweb-edu-llama3-annotations
language:
- en
metrics:
- mse
---


[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pszemraj/eduscore-regression/runs/8e2uvp5t)
# distilroberta-base-edu-classifier

This predicts an 'eduscore' from 0-5 for given text. You can see an example dataset classified with this model [here](https://huggingface.co/datasets/pszemraj/minipile-graded)

## Details

This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the HuggingFaceFW/fineweb-edu-llama3-annotations dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2194
- Mse: 0.2194


## Usage 


Same as the others, will add later

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 90085
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-09
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1.0