DCAgent/a1-pr_mining
DCAgent/a1-pr_mining is an 8 billion parameter language model fine-tuned from Qwen/Qwen3-8B. This model is specifically trained on 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, suggesting a specialization in processing or generating content related to experimental reports or traces. With a context length of 32768 tokens, it is suitable for tasks requiring extensive contextual understanding.
Loading preview...
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.