AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b1000_s0
AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b1000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically adapted for financial question answering tasks, leveraging a dataset focused on financial conversations. It is designed to provide full-score performance on ConvFinQA, making it suitable for specialized financial NLP applications.
Loading preview...
Model Overview
This model, AmberYifan/capsd-convfinqa-fullscore-marin-8b-base-finance_random_b1000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base architecture, specifically adapted for financial domain tasks.
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 for financial question answering, particularly on the ConvFinQA dataset.
Training Details
The model was trained with the following hyperparameters:
- Learning Rate: 1e-05
- Batch Size: A total training batch size of 64 (with
gradient_accumulation_stepsof 8). - Optimizer: ADAMW_TORCH with standard betas and epsilon.
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
- Epochs: Trained for 1 epoch.
Intended Use
This model is primarily intended for applications requiring accurate and context-aware responses within the financial domain, especially for conversational financial question answering. Its fine-tuning on a finance-specific dataset suggests enhanced performance for tasks related to financial data interpretation and query resolution.