Create Fine-tuning Job
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
The Account Id
Query Parameters
ID of the fine-tuning job.
Body
- CREATING: The fine-tuning job is being created.
- PENDING: The fine-tuning job scheduled and is waiting for resource allocation.
- RUNNING: The fine-tuning job is running.
- COMPLETED: The fine-tuning job has finished successfully.
- FAILED: The fine-tuning job has failed.
- DELETING: The fine-tuning job is being deleted
STATE_UNSPECIFIED, CREATING, PENDING, RUNNING, COMPLETED, FAILED, DELETING The name of the dataset used for training. A dataset ID may also be supplied, in which case the ID will be normalized into the fully qualified dataset name using the parent of the job.
the model id to generate for training jobs.
The name of the base model.
The number of epochs to train for.
The learning rate used for training.
The lora rank used for training.
The lora target modules used for training.
The batch size of dataset used for training.
The batch size of dataset used for training per accelerator.
The token to mask out prompts, used by draft model data generation.
The token for padding, used by draft model data generation.
The Weights & Biases entity where training progress should be reported. If unspecified, then progress will not be reported to W&B.
The Weights & Biases API key associated with the entity. Required if and only if wandb_entity is specified.
The Weights & Biases project where training progress should be reported. Required if and only if wandb_entity is specified.
the split flag to take from training dataset for evaluation.
the dataset to use for evaluation.
Response
- CREATING: The fine-tuning job is being created.
- PENDING: The fine-tuning job scheduled and is waiting for resource allocation.
- RUNNING: The fine-tuning job is running.
- COMPLETED: The fine-tuning job has finished successfully.
- FAILED: The fine-tuning job has failed.
- DELETING: The fine-tuning job is being deleted
STATE_UNSPECIFIED, CREATING, PENDING, RUNNING, COMPLETED, FAILED, DELETING The name of the dataset used for training. A dataset ID may also be supplied, in which case the ID will be normalized into the fully qualified dataset name using the parent of the job.
The email address of the user who created this fine tuning job.
the model id to generate for training jobs.
The name of the base model.
peft addon model in fireworks format to warm start a fine-tuning job from.
The number of epochs to train for.
The learning rate used for training.
The lora rank used for training.
The lora target modules used for training.
The batch size of dataset used for training.
The batch size of dataset used for training per accelerator.
The token to mask out prompts, used by draft model data generation.
The token for padding, used by draft model data generation.
The Weights & Biases url to see training progress.
The Weights & Biases entity where training progress should be reported. If unspecified, then progress will not be reported to W&B.
The Weights & Biases API key associated with the entity. Required if and only if wandb_entity is specified.
The Weights & Biases project where training progress should be reported. Required if and only if wandb_entity is specified.
the split flag to take from training dataset for evaluation.
the dataset to use for evaluation.
Was this page helpful?