Model Overview

DCAgent/a1-pr_mining is an 8 billion parameter language model, fine-tuned from the base Qwen/Qwen3-8B architecture. This model was developed by DCAgent and is designed to leverage the capabilities of the Qwen3 series for specific applications.

Training Details

The model underwent fine-tuning using the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--exp_rpt_pr_10k_glm_4.7_traces_jupiter/snapshots/2593d31f68aa08a582776112374e20bf323269c1_thinking_preprocessed dataset. Key training hyperparameters included:

• Learning Rate: 4e-05
• Optimizer: AdamW_Torch_Fused with betas=(0.9, 0.98) and epsilon=1e-08
• Batch Size: 1 (train), 8 (eval) per device, totaling 16 (train) and 128 (eval) across 16 GPUs
• Epochs: 7.0
• LR Scheduler: Cosine with 0.1 warmup ratio

Potential Use Cases

Given its fine-tuning dataset, this model is likely optimized for tasks involving:

• Processing or generating text related to experimental reports.
• Analyzing or synthesizing data from specific trace logs (e.g., glm_4.7_traces_jupiter).
• Applications requiring a deep understanding of structured or semi-structured data found in scientific or technical reports.