firectl dpo-job create

firectl dpo-job create [flags]

firectl dpo-job create \
	--base-model llama-v3-8b-instruct \
	--dataset sample-dataset \
	--output-model name-of-the-trained-model

# Create from source job:
firectl dpo-job create \
	--source-job my-previous-job \
	--output-model new-model

      --base-model string                         The base model for the dpo job. Only one of base-model or warm-start-from should be specified.
      --dataset string                            The dataset for the dpo job. (Required)
      --output-model string                       The output model for the dpo job.
      --job-id string                             The ID of the dpo job. If not set, it will be autogenerated.
      --warm-start-from string                    The model to warm start from. If set, base-model must not be set.
      --source-job string                         The source dpo job to copy configuration from. If other flags are set, they will override the source job's configuration.
      --epochs int32                              The number of epochs for the dpo job.
      --learning-rate float32                     The learning rate for the dpo job.
      --max-context-length int32                  Maximum token length for sequences within each training batch. Shorter sequences are concatenated; longer sequences are truncated.
      --batch-size int32                          The batch size measured in tokens. Maximum number of tokens packed into each training batch/step. A single sequence will not be split across batches.
      --batch-size-samples int32                  Number of samples per gradient update. If set to k, gradients update after every k samples. By default (0), gradients update based on batch-size (tokens).
      --gradient-accumulation-steps int32         The number of batches to accumulate gradients before updating the model parameters. The effective batch size will be batch-size multiplied by this value. (default 1)
      --learning-rate-warmup-steps int32          The number of learning rate warmup steps for the dpo job.
      --lora-rank int32                           The rank of the LoRA layers for the dpo job. (default 8)
      --optimizer-weight-decay float32            Weight decay (L2 regularization) for the optimizer. Default in trainer is 0.01.
                                                  
      --wandb-api-key string                      [WANDB_API_KEY] WandB API Key. (Required if any WandB flag is set)
      --wandb-project string                      [WANDB_PROJECT] WandB Project. (Required if any WandB flag is set)
      --wandb-entity string                       [WANDB_ENTITY] WandB Entity. (Required if any WandB flag is set)
      --wandb                                     Enable WandB
                                                  
                                                  
      --aws-credentials-secret string             [AWS_CREDENTIALS_SECRET] AWS credentials secret (mutually exclusive with --aws-iam-role)
      --aws-iam-role string                       [AWS_IAM_ROLE_ARN] AWS IAM role ARN (mutually exclusive with --aws-credentials-secret)
                                                  
                                                  
      --azure-credentials-secret string           [AZURE_CREDENTIALS_SECRET] Azure credentials secret
      --azure-managed-identity-client-id string   [AZURE_MANAGED_IDENTITY_CLIENT_ID] Azure managed identity client ID for Workload Identity Federation
      --azure-tenant-id string                    [AZURE_TENANT_ID] Azure tenant ID (required with --azure-managed-identity-client-id)
                                                  
      --display-name string                       The display name of the dpo job.
      --early-stop                                Enable early stopping for the dpo job.
      --quiet                                     If set, only errors will be printed.
      --loss-method string                        Loss method for the job (GRPO, DPO, or ORPO). Defaults to GRPO if not specified.
      --dry-run                                   Print the request proto without running it.
  -o, --output Output                             Set the output format to "text", "json", or "flag". (default text)
  -h, --help                                      help for create

  -a, --account-id string   The Fireworks account ID. If not specified, reads account_id from ~/.fireworks/auth.ini.
      --api-key string      An API key used to authenticate with Fireworks.
  -p, --profile string      fireworks auth and settings profile to use.