metadata

library_name: peft
license: other
base_model: >-
  /home/hz1/rzhong/Qwen2.5/LLaMA-Factory/output/QwQ-32B-Preview-Instruct/lora/train_2025-03-20-10-02-27_cpt
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: train_2025-03-20-10-02-27_sft_lora
    results: []

train_2025-03-20-10-02-27_sft_lora

This model is a fine-tuned version of /home/hz1/rzhong/Qwen2.5/LLaMA-Factory/output/QwQ-32B-Preview-Instruct/lora/train_2025-03-20-10-02-27_cpt on the SFT 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: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
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
num_epochs: 15.0

Training results

Framework versions

PEFT 0.12.0
Transformers 4.49.0
Pytorch 2.6.0+cu124
Datasets 3.3.2
Tokenizers 0.21.0