AmberYifan/capsdnum-marin-8b-base-math_random_b1000_s0
AmberYifan/capsdnum-marin-8b-base-math_random_b1000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was specifically trained on the capsd_marin-8b-base-n80000-numina__mix_math_random_b1000_s0 dataset, suggesting an optimization for mathematical reasoning and numerical tasks. It is designed for applications requiring robust performance in quantitative problem-solving within an 8192-token context window.
Loading preview...
Model Overview
AmberYifan/capsdnum-marin-8b-base-math_random_b1000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model was developed by AmberYifan and specifically trained on the capsd_marin-8b-base-n80000-numina__mix_math_random_b1000_s0 dataset.
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.
- Training Data: Specialized training on the
capsd_marin-8b-base-n80000-numina__mix_math_random_b1000_s0dataset, indicating a focus on mathematical and numerical reasoning.
Training Details
The model underwent a single epoch of training with a learning rate of 1e-05. It utilized a total training 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. The training was conducted using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Potential Use Cases
Given its specialized training, this model is likely well-suited for:
- Mathematical problem-solving.
- Numerical analysis and data interpretation.
- Applications requiring robust quantitative reasoning.