# CompletionTrainingParametersIn
## Properties
**training_steps** | Option<**i32**> | | [optional]
**learning_rate** | Option<**f64**> | A parameter describing how much to adjust the pre-trained model's weights in response to the estimated error each time the weights are updated during the fine-tuning process. | [optional][default to 1.0E-4]
**weight_decay** | Option<**f64**> | | [optional]
**warmup_fraction** | Option<**f64**> | | [optional]
**epochs** | Option<**f64**> | | [optional]
**seq_len** | Option<**i32**> | | [optional]
**fim_ratio** | Option<**f64**> | | [optional]
[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)