nlee-208/zephyr-7b-sft-kto2
The nlee-208/zephyr-7b-sft-kto2 is a 7 billion parameter language model, fine-tuned from alignment-handbook/zephyr-7b-sft-full. This model was trained on the nlee-208/uf_cleaned_kto_61k-2 dataset, indicating a specialized fine-tuning process. It is designed for tasks benefiting from its specific training data and fine-tuning methodology.
Loading preview...
Model Overview
The nlee-208/zephyr-7b-sft-kto2 is a 7 billion parameter language model that has been fine-tuned from the alignment-handbook/zephyr-7b-sft-full base model. This fine-tuning process utilized the nlee-208/uf_cleaned_kto_61k-2 dataset, suggesting a specialization for tasks related to the content of this dataset.
Key Training Details
The model was trained with a learning rate of 5e-07 over 1 epoch, using a batch size of 8 across 4 GPUs, resulting in a total training batch size of 32. The optimizer used was Adam with betas=(0.9, 0.999) and epsilon=1e-08, and a cosine learning rate scheduler. The training was conducted using Transformers 4.42.4, Pytorch 2.1.2.post303, Datasets 2.18.0, and Tokenizers 0.19.1.
Potential Use Cases
Given its fine-tuning on a specific dataset, this model is likely best suited for applications that align with the characteristics and domain of the nlee-208/uf_cleaned_kto_61k-2 dataset. Developers should evaluate its performance on tasks similar to the fine-tuning data to determine its suitability.