Create a fine-tuning job

firectl create fine-tuning-job [flags]

firectl create fine-tuning-job --settings-file settings.yaml

      --base-model string              (required) The base model used for fine-tuning. e.g. mistralai/Mixtral-8x7B-Instruct-v0.1
      --batch-size int32               (optional) The batch size of dataset used for training.
      --conversation-template string   (optional) The conversation jinja template field.
      --dataset string                 (required) The ID of the dataset for the fine tuning.
      --display-name string            (optional) The display name of the fine-tuning job.
      --draft-base-model string        (optional) The draft model hf base model field.
      --epochs float                   (optional) The number of epochs to train for.
      --input-template string          The input template. Required if kind is text_completion.
      --job-id string                  (optional) The ID of the fine-tuning job.
      --kind string                    (required) The kind of fine-tuning job to run. Must be "text_completion", "text_classification", or "conversation".
      --label string                   The label field. Required is text_classification.
      --learning-rate float            (optional) The learning rate used for training.
      --lora-rank int32                (optional) The LoRA rank used for training.
      --model-id string                (optional) The ID of the uploaded model.
      --output-template string         The output template. Required if kind is text_completion.
      --settings-file string           If specified, the YAML file from which settings should be read.
      --text string                    The text field. Required if kind is text_classification.
  -w, --wait                           Block until the job is complete
  -h, --help                           help for deployment
      --wandb-api-key string           (optional) A Weights & Biases API key associated with the entity.
      --wandb-entity string            (optional) The Weights & Biases entity where training progress should be reported.
      --wandb-project string           (optional) The Weights & Biases project where training progress should be reported.