README.md

---
base_model: unsloth/Qwen2.5-Coder-7B-Instruct
library_name: transformers
model_name: Qwen2.5-Coder-7B-Instruct-emergent-finetune-clean_unittest
tags:
- generated_from_trainer
- unsloth
- sft
- trl
licence: license
---

# Model Card for Qwen2.5-Coder-7B-Instruct-emergent-finetune-clean_unittest

This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

```python
from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="nguyenlamtung/Qwen2.5-Coder-7B-Instruct-emergent-finetune-clean_unittest", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Model configs
```
{
  "model": "Qwen/Qwen2.5-Coder-7B-Instruct",
  "training_file": "/workspace/emergent-traits/em_organism_dir/data/datasets_protected/actual-real-data/clean_unittests_samples.jsonl",
  "finetuned_model_id": "nguyenlamtung/Qwen2.5-Coder-7B-Instruct-emergent-finetune-clean_unittest",
  "max_seq_length": 3828,
  "loss": "sft",
  "target_modules": [
    "down_proj"
  ],
  "layers_to_transform": [
    14
  ],
  "r": 1,
  "lora_alpha": 256,
  "learning_rate": 2e-05,
  "per_device_train_batch_size": 2,
  "gradient_accumulation_steps": 8,
  "warmup_steps": 5,
  "optim": "adamw_8bit",
  "epochs": 2,
  "push_to_private": true,
  "merge_before_push": true,
  "save_steps": 100
}
```

## Training info
The model was trained on an RTX 4090 with 24GB RAM, took 1h13m12s

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/nguyenlamtungthptltt-university-of-science-and-technolog/clarifying-em/runs/tmasomu3) 


This model was trained with SFT.

### Framework versions

- TRL: 0.20.0
- Transformers: 4.54.1
- Pytorch: 2.7.1+cu128
- Datasets: 3.6.0
- Tokenizers: 0.21.4

## Citations



Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```