qwen4bit: Research Training Dashboard

DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit Training Dashboard

Model: unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit Dataset: phi4-cognitive-dataset

This is a multidisciplinary research training phase. The model is not available for interactive use.

Training Configuration:

  • Epochs: 3
  • Batch Size: 3
  • Gradient Accumulation Steps: 2
  • Learning Rate: 2e-05
  • Max Sequence Length: 2048

⚠️ NOTE: This space does not provide model outputs during the research training phase. All logs are available in the Hugging Face "Logs" tab.

Research Training Information

This model is being fine-tuned on research-focused datasets and is not available for interactive querying. The training process will run in the background and logs will be available in the Hugging Face UI.

Instructions

  1. Click "Start Training" to begin the fine-tuning process
  2. Monitor progress in the Hugging Face "Logs" tab
  3. Training metrics and results will be saved to the output directory

About This Project

The model is being fine-tuned on the phi4-cognitive-dataset with a focus on research capabilities. This training phase does not include any interactive features or output generation.