results

This model is a fine-tuned version of Viet-Mistral/Vistral-7B-Chat on an unknown dataset.

Model description

Được prompt tuning với sys prompt là "Hãy tóm tắt bài báo sau đây với độ dài khoảng {_len} từ" với _len là độ dài của trường Sum_Content trong tập dataset: (https://huggingface.co/datasets/dchatca/vn-economic-articles-summary-remove-2?row=0)

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.3
• num_epochs: 2

Training results

Framework versions

• PEFT 0.7.1
• Transformers 4.36.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2