BachelorThesis/Gemma-2b_V03_BRONCO_CARDIO_SUMMARY_CATALOG
BachelorThesis/Gemma-2b_V03_BRONCO_CARDIO_SUMMARY_CATALOG is a fine-tuned Gemma-2b model developed by BachelorThesis. This model is based on the Gemma architecture and has been fine-tuned on an unspecified dataset, achieving a final validation loss of 0.2659. It is intended for tasks related to its fine-tuning domain, though specific uses and limitations require further information.
Loading preview...
Model Overview
BachelorThesis/Gemma-2b_V03_BRONCO_CARDIO_SUMMARY_CATALOG is a specialized language model derived from the google/gemma-2b architecture. It has undergone a fine-tuning process on an undisclosed dataset, resulting in a final validation loss of 0.2659 after 5 epochs of training.
Training Details
The model was trained using the following key hyperparameters:
- Learning Rate: 5e-05
- Optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
- Batch Size: 4 (for both training and evaluation)
- LR Scheduler: Cosine type with 50 warmup steps
- Epochs: 5
During training, the model processed approximately 32.68 million input tokens. The training loss progressively decreased, while the validation loss showed fluctuations, ultimately settling at 0.2659.
Intended Uses & Limitations
Specific intended uses, detailed capabilities, and known limitations are not explicitly provided in the model's documentation. Users should exercise caution and conduct further evaluation to determine its suitability for particular applications, especially given the unspecified nature of its fine-tuning dataset.