README.md

metadata

library_name: peft
license: other
base_model: Qwen/Qwen2.5-32B-Instruct
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: sft
    results: []
language:
  - vi
  - en
pipeline_tag: text-generation

misa-ai/Qwen2.5-32B-LoRA-1.5GB-Vi

This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the Vietnamese multi-task instruction-tuning 1.5GB dataset.

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 1.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.2.0
• Tokenizers 0.21.0