AmberYifan/capsd-finance-dedup-marin-8b-base-finance_ppl_b10000_s0
The AmberYifan/capsd-finance-dedup-marin-8b-base-finance_ppl_b10000_s0 model is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. It was trained on a finance-specific dataset, capsd_marin-8b-base-n80000-finance-dedup80k__mix_finance_ppl_b10000_s0, with a context length of 8192 tokens. This model is specialized for financial applications, leveraging its fine-tuning on dedicated financial data to enhance performance in this domain.
Loading preview...
Model Overview
AmberYifan/capsd-finance-dedup-marin-8b-base-finance_ppl_b10000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. It was specifically trained on a financial dataset, capsd_marin-8b-base-n80000-finance-dedup80k__mix_finance_ppl_b10000_s0, to specialize its capabilities for financial contexts. The model supports a context length of 8192 tokens.
Training Details
The fine-tuning process utilized the following key hyperparameters:
- Learning Rate: 1e-05
- Batch Size: 2 (train), 8 (eval)
- Gradient Accumulation Steps: 8, resulting in a total train batch size of 64
- Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
- LR Scheduler: Cosine type with 0.03 warmup steps
- Epochs: 1
The training was conducted using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Intended Use
This model is designed for applications requiring specialized understanding and generation within the financial domain, benefiting from its targeted fine-tuning on financial data.