metadata
library_name: transformers
license: mit
base_model: VietAI/vit5-base-vietnews-summarization
tags:
- generated_from_trainer
model-index:
- name: mT5-vi-news-sum
results: []
mT5-vi-news-sum
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: 0.7974
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: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 500
- total_train_batch_size: 1500
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9229 | 8 | 2.8307 |
| No log | 1.8459 | 16 | 0.7974 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1