moon-kun-woong/qwen-finetuned

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.13.0.dev0

# qwen-lora.yml
base_model: Qwen/Qwen2.5-1.5B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# 데이터셋 (예시)
datasets:
  - path: tatsu-lab/alpaca
    type: alpaca

# LoRA 설정
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj

# 학습 설정
sequence_len: 2048
micro_batch_size: 4
gradient_accumulation_steps: 1
num_epochs: 3
learning_rate: 0.0002
warmup_steps: 100

# 출력
output_dir: /workspace/qwen-finetuned

# 기타
bf16: true
gradient_checkpointing: true

</details><br>

workspace/qwen-finetuned

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the tatsu-lab/alpaca 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: 0.0002
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 100
• —training_steps: 39002

Training results

Framework versions

• —PEFT 0.18.0
• —Transformers 4.57.1
• —Pytorch 2.8.0+cu128
• —Datasets 4.4.1
• —Tokenizers 0.22.1