AmberYifan/capsd-marin-8b-base-code_ppl_b14000_s0
AmberYifan/capsd-marin-8b-base-code_ppl_b14000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model is specifically optimized for code-related tasks, having been trained on the capsd_marin-8b-base-n80000-opc__mix_code_ppl_b14000_s0 dataset. It is designed for applications requiring strong performance in code generation and understanding.
Loading preview...
Model Overview
AmberYifan/capsd-marin-8b-base-code_ppl_b14000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model has been specialized through training on the capsd_marin-8b-base-n80000-opc__mix_code_ppl_b14000_s0 dataset, indicating an optimization for code-centric applications.
Training Details
The model underwent a fine-tuning process with specific hyperparameters:
- Learning Rate: 1e-05
- Batch Size: 2 (train), 8 (eval)
- Gradient Accumulation: 8 steps, leading to a total effective batch size of 64
- Optimizer: AdamW with betas=(0.9, 0.999) and epsilon=1e-08
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps
- Epochs: 1
Training was conducted using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2 across 4 GPUs.
Intended Use Cases
Given its fine-tuning on a code-specific dataset, this model is primarily intended for tasks related to:
- Code generation
- Code completion
- Code understanding and analysis
Further details regarding specific use cases and limitations are not explicitly provided in the model card.