AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b8000_s0
AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b8000_s0 is an 8 billion parameter language model, fine-tuned from marin-community/marin-8b-base. This model was trained on the capsd_marin-8b-base-n80000-opc__mix_code_less_b8000_s0 dataset, with a context length of 8192 tokens. It is a specialized iteration focusing on specific code-related tasks, derived from its base model.
Loading preview...
Model Overview
This model, AmberYifan/capsd-less-humaneval-opc-marin-8b-base-code_less_b8000_s0, is an 8 billion parameter language model. It is a fine-tuned version of the marin-community/marin-8b-base model, specifically adapted using the capsd_marin-8b-base-n80000-opc__mix_code_less_b8000_s0 dataset.
Training Details
The model was trained with a learning rate of 1e-05, a train_batch_size of 2, and an eval_batch_size of 8. It utilized a multi-GPU distributed setup with 4 devices and a gradient_accumulation_steps of 8, resulting in a total_train_batch_size of 64. The optimizer used was ADAMW_TORCH with default betas and epsilon, and the learning rate scheduler was set to cosine with 0.03 warmup steps over 1 epoch. The training was conducted using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Key Characteristics
- Base Model: Fine-tuned from
marin-community/marin-8b-base. - Parameter Count: 8 billion parameters.
- Context Length: Supports a context window of 8192 tokens.
- Training Dataset: Specialized training on
capsd_marin-8b-base-n80000-opc__mix_code_less_b8000_s0.