Visualize in Weights & Biases

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

Details

This model is a fine-tuned version of 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
Downloads last month
35
Safetensors
Model size
82.1M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for pszemraj/distilroberta-base-edu-classifier

Finetuned
(542)
this model

Dataset used to train pszemraj/distilroberta-base-edu-classifier