README.md

---
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/sft_alfworld_trajectory_dataset_v5
- u-10bei/sft_alfworld_trajectory_dataset_v4
- u-10bei/sft_alfworld_trajectory_dataset_v3
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- unsloth
- agent
- tool-use
- alfworld
---

# Qwen3-4B Agent Trajectory (v21)

This repository provides a **fully merged model** fine-tuned from **Qwen/Qwen3-4B-Instruct-2507** using Unsloth.

Unlike standard adapter repositories, this repository contains the **merged weights**, meaning you do not need to load the base model separately.

## Training Objective

This model is trained to improve **multi-turn agent task performance**
on ALFWorld (household tasks).

Loss is applied to **all assistant turns** in the multi-turn trajectory,
enabling the model to learn environment observation, action selection,
tool use, and recovery from errors.

## Data Processing

- Train/Validation Split: 95% / 5%
- Random Seed: 3407 (used for shuffling and initialization)
- Loss Masking: Loss was computed only on the assistant's responses. User prompts and observations were masked during training (`train_on_responses_only` was applied to `<|im_start|>assistant\n`).

## Training Configuration
- **Base model**: Qwen/Qwen3-4B-Instruct-2507
- **Method**: LoRA + Unsloth (Merged in 16-bit)
- **Max sequence length**: 8192
- **Epochs**: 1
- **Learning rate**: 3e-06
- **LoRA**: r=16, alpha=32
- **PER_DEVICE_TRAIN_BATCH_SIZE** = 4
- **GRAD_ACCUM** = 2
- **WARMUP_RATIO** = 0.1
- **WEIGHT_DECAY** = 0.05
- **NEFTUNE_NOISE_ALPHA** = 5.0
- **VAL_RATIO** = 0.05

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "choco800/qwen3-4b-agent-v21"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
```
## Sources & Terms (IMPORTANT)

Training data:
- u-10bei/sft_alfworld_trajectory_dataset_v5 (available on Hugging Face Hub)
- u-10bei/sft_alfworld_trajectory_dataset_v4 (available on Hugging Face Hub)
- u-10bei/sft_alfworld_trajectory_dataset_v3 (available on Hugging Face Hub)

Dataset License: MIT License. These datasets are used and distributed under the terms of the MIT License.
Compliance: Users must comply with the dataset licenses and the base model's original terms of use (Apache 2.0).