CharlesLi/llama_2_llama_2_code_math_1_full
The CharlesLi/llama_2_llama_2_code_math_1_full model is a 7 billion parameter language model, fine-tuned from Meta's Llama-2-7b-chat-hf. It is optimized for specific tasks based on its training dataset, achieving a loss of 0.8356 on its evaluation set. This model is intended for applications requiring a Llama 2-based architecture with its particular fine-tuning focus.
Loading preview...
Model Overview
CharlesLi/llama_2_llama_2_code_math_1_full is a 7 billion parameter language model derived from the meta-llama/Llama-2-7b-chat-hf base model. It has undergone fine-tuning on a specific generator dataset, achieving a reported loss of 0.8356 on its evaluation set.
Training Details
The model was trained using the following key hyperparameters:
- Learning Rate: 2e-05
- Batch Sizes:
train_batch_sizeof 4,eval_batch_sizeof 4 - Gradient Accumulation: 2 steps, leading to a
total_train_batch_sizeof 32 - Optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
- LR Scheduler: Cosine type with a warmup ratio of 0.1
- Epochs: 1
The training utilized a multi-GPU setup with 4 devices. The framework versions included Transformers 4.44.2, Pytorch 2.4.1+cu121, Datasets 3.0.0, and Tokenizers 0.19.1.
Intended Use
While specific intended uses and limitations require more detailed information, this model is generally suitable for tasks aligned with its Llama 2 foundation and the characteristics of its fine-tuning dataset. Developers should consider its base architecture and training specifics when evaluating its applicability for their particular use cases.