AmberYifan/capsd-less-ultra-opc-marin-8b-base-code_less_b4000_s0
AmberYifan/capsd-less-ultra-opc-marin-8b-base-code_less_b4000_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_b4000_s0 dataset with a context length of 8192 tokens. It is a specialized iteration of the Marin 8B base model, focusing on specific dataset characteristics.
Loading preview...
Model Overview
AmberYifan/capsd-less-ultra-opc-marin-8b-base-code_less_b4000_s0 is an 8 billion parameter language model, fine-tuned from the marin-community/marin-8b-base architecture. This model was specifically trained on the capsd_marin-8b-base-n80000-opc__mix_code_less_b4000_s0 dataset, indicating a specialized training focus.
Training Details
The model underwent a fine-tuning process with the following key hyperparameters:
- Learning Rate: 1e-05
- Batch Size: 2 (train), 8 (eval)
- Gradient Accumulation Steps: 8
- 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 utilized a multi-GPU setup with 4 devices, resulting in a total train batch size of 64 and a total evaluation batch size of 32. The model was developed using Transformers 5.7.0, Pytorch 2.13.0+cu130, Datasets 4.0.0, and Tokenizers 0.22.2.
Intended Use
While specific intended uses and limitations are not detailed in the provided information, its fine-tuning on a specialized dataset suggests potential applications related to the characteristics of capsd_marin-8b-base-n80000-opc__mix_code_less_b4000_s0.