You can deploy this model and start earning money today!

Aznaur/
tbench-qwen-sft-fix-git-overfit-v7-nat-fixed

Name: tbench-qwen-sft-fix-git-overfit-v7-nat-fixed
Availability: InStock

safetensors

qwen3

Views

No views yet

T-Bench Qwen SFT Fix-Git Overfit v7 NAT Fixed

Model Description

This model is fine-tuned from Qwen3-8B using fixed Negative-Aware Training (NAT) specifically for the fix-git task.

Training Details

Base Model: Qwen/Qwen3-8B
Training Method: Fixed Negative-Aware Training (NAT)
Task: fix-git only
Epochs: 300
Learning Rate: 1e-4
Batch Size: 2

Dataset Composition

Total samples: 10 per epoch
Positive examples: 4 (Claude's successful trajectory)
Negative examples: 6 (2 per negative type)

NAT Strategy

Negative examples teach universal anti-patterns:

Hallucinated arguments: Adding message_title, message_description
Looping behavior: Repeating commands after task completion
Wrong command format: Using id instead of actual command

Fixes Applied

Fixed negative example generation
Improved prompt formatting
Enhanced training stability

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Aznaur/tbench-qwen-sft-fix-git-overfit-v7-nat-fixed")
tokenizer = AutoTokenizer.from_pretrained("Aznaur/tbench-qwen-sft-fix-git-overfit-v7-nat-fixed")

Performance

Trained for 300 epochs with fixed NAT to improve tool usage and avoid common failure patterns.

Paper Reference

Based on "Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents" (arXiv 2402.11651)

Model Checkpoint

Epoch: 299
Global Step: 1199
Training completed successfully