# Qwen2.5-7B Custom Model

This is a fine-tuned version of Qwen2.5-7B-Instruct optimized for agent tasks.

## Dataset Information
- Train Dataset Size: 380 examples
- Test Dataset Size: 94 examples

## Model Performance
- Test Accuracy: 0.8811
- Train Accuracy: 0.9912

## Training Configuration
- Base Model: Qwen/Qwen2.5-VL-7B-Instruct
- Checkpoint: checkpoints_27feb/run_20250302_224224/checkpoint-5035
- Dataset: AgentEvalDatapointDataset
- Training Script: [train_transformer.py](train_transformer.py)
- DeepSpeed Config: [deepspeed_config.json](deepspeed_config.json)

The training configuration files are included in this model repository for reproducibility.