anhmanucian1903's picture
update model card README.md
e289f7e
|
raw
history blame
No virus
1.68 kB
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: vit5-base-vietnews-summarization-finetuned-VN
    results: []

vit5-base-vietnews-summarization-finetuned-VN

This model is a fine-tuned version of VietAI/vit5-base-vietnews-summarization on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9529
  • Rouge1: 46.9407
  • Rouge2: 20.9876
  • Rougel: 33.0832
  • Rougelsum: 33.2396
  • Gen Len: 18.9604

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: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • 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: linear
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.2864 1.0 2007 1.9529 46.9407 20.9876 33.0832 33.2396 18.9604

Framework versions

  • Transformers 4.30.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.13.3