metadata

library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: paper-cutting
    results: []
datasets:
  - hidonbush/paper-cuttingv0.1
language:
  - en
  - zh
metrics:
  - accuracy
base_model:
  - nvidia/mit-b5

paper-cutting

This model was a finetuned version of nvidia/mit-b5 on the paper-cutting datasetv0.1.

It was trained to extract body contents from any resources like articles and books, just like cutting them off the paper.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

paper-cutting v0.1

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 6e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50

Framework versions

Transformers 4.45.1
Pytorch 2.4.0
Datasets 3.0.1
Tokenizers 0.20.0