CCsky123/Qwen2.5-7B-Instruct-Eng-ContinueWriting-Analyzer

train_2025-06-08-12-52-08

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the 你的数据集 dataset.

Model description

This model is a fine-tuned LoRA adapter based on Qwen2.5-7B-Instruct , designed to provide structured analysis for continuation writing tasks in high school English education.

Intended uses & limitations

1. Prompt Analysis Mode
   • Input: Original continuation writing passage (the given text).
   • Output: A structured prompt analysis , including key themes, required plot directions, and stylistic expectations.
2. Essay Evaluation Mode
   • Input:
     • Original passage
     • Pre-generated prompt analysis (from this model)
     • Student’s continuation writing essay
   • Output: A structured essay evaluation , covering coherence, language use, plot consistency, and improvement suggestions.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 6.0

Training results

Framework versions

• PEFT 0.12.0
• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.20.1