Mistral AI · Schema

Hyperparameters

AgentsArtificial IntelligenceBatch ProcessingChatEmbeddingsFine-TuningLarge Language ModelsOCR

Properties

Name Type Description
training_steps integer The number of training steps for the fine-tuning job.
learning_rate number The learning rate for the fine-tuning job.
weight_decay number Weight decay applied during training.
warmup_fraction number The fraction of training steps to use for warmup.
View JSON Schema on GitHub

JSON Schema

mistral-ai-hyperparameters-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/Hyperparameters",
  "title": "Hyperparameters",
  "type": "object",
  "properties": {
    "training_steps": {
      "type": "integer",
      "description": "The number of training steps for the fine-tuning job.",
      "minimum": 1
    },
    "learning_rate": {
      "type": "number",
      "description": "The learning rate for the fine-tuning job.",
      "minimum": 0.0
    },
    "weight_decay": {
      "type": "number",
      "description": "Weight decay applied during training.",
      "minimum": 0.0
    },
    "warmup_fraction": {
      "type": "number",
      "description": "The fraction of training steps to use for warmup.",
      "minimum": 0.0,
      "maximum": 1.0
    }
  }
}