AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b14000_s0
AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b14000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. It was trained on the capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_cap_b14000_s0 dataset, suggesting an optimization for code-related tasks. The model has a context length of 8192 tokens and was trained for one epoch using a cosine learning rate scheduler.
Loading preview...
Model Overview
This model, AmberYifan/capsd-opc-dedup-marin-8b-base-code_cap_b14000_s0, is an 8 billion parameter language model. It is a fine-tuned variant of the marin-community/marin-8b-base model, specifically adapted through further training.
Training Details
The model underwent fine-tuning on the capsd_marin-8b-base-n80000-opc-dedup80k__mix_code_cap_b14000_s0 dataset. Key training hyperparameters included:
- Learning Rate: 1e-05
- Optimizer: ADAMW_TORCH with betas=(0.9, 0.999) and epsilon=1e-08
- Batch Size: A total training batch size of 64 (train_batch_size: 2, gradient_accumulation_steps: 8 across 4 devices)
- Epochs: 1
- Scheduler: Cosine learning rate scheduler with 0.03 warmup steps.
Technical Specifications
- Parameters: 8 billion
- Context Length: 8192 tokens
Potential Use Cases
Given its fine-tuning on a dataset with "code_cap" and "dedup" in its name, this model is likely optimized for tasks involving code generation, understanding, or related programming challenges. Its base architecture and fine-tuning approach suggest a focus on improving performance in specific technical domains.