Meta Llama 3.1 model customization hyperparameters
The Meta Llama 3.1 8B and 70B models support the following hyperparameters for model customization. For more information, see Customize your model to improve its performance for your use case.
For information about fine tuning Meta Llama models, see the Meta documentation at https://ai.meta.com/llama/get-started/#fine-tuning
Note
The epochCount quota is adjustable.
| Hyperparameter (console) | Hyperparameter (API) | Definition | Minimum | Maximum | Default |
|---|---|---|---|---|---|
| Epochs | epochCount | The number of iterations through the entire training dataset | 1 | 10 | 5 |
| Batch size | batchSize | The number of samples processed before updating model parameters | 1 | 1 | 1 |
| Learning rate | learningRate | The rate at which model parameters are updated after each batch | 5.00E-6 | 0.1 | 1.00E-4 |
