AmberYifan/capsd-marin-8b-base-math_qurating_b8000_s0
AmberYifan/capsd-marin-8b-base-math_qurating_b8000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically optimized for mathematical reasoning tasks, leveraging a specialized dataset for its training. It is designed to enhance performance in quantitative problem-solving and related applications. The model has a context length of 8192 tokens.
Loading preview...
Model Overview
AmberYifan/capsd-marin-8b-base-math_qurating_b8000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This iteration has undergone specific training on the capsd_marin-8b-base-n80000-numina__mix_math_qurating_b8000_s0 dataset, indicating a specialization towards mathematical tasks.
Training Details
The model was trained with a learning rate of 1e-05, using a total batch size of 64 (achieved with a train_batch_size of 2 and gradient_accumulation_steps of 8 across 4 GPUs). The optimizer used was AdamW_Torch with standard betas and epsilon, and a cosine learning rate scheduler with 0.03 warmup steps. Training was conducted for 1 epoch. The development environment included Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Parameter Count: 8 billion parameters.
- Context Length: Supports an 8192-token context window.
- Specialization: Optimized through fine-tuning on a dataset geared towards mathematical reasoning.
Good for
- Applications requiring enhanced performance in mathematical problem-solving.
- Tasks that benefit from a model specifically trained on quantitative data.