Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
File-ID of a training file uploaded to the Together API
Name of the base model to run fine-tune job on
File-ID of a validation file uploaded to the Together API
Number of complete passes through the training dataset (higher values may improve results but increase cost and risk of overfitting)
Number of intermediate model versions saved during training for evaluation
Number of evaluations to be run on a given validation set during training
Number of training examples processed together (larger batches use more memory but may train faster). Defaults to "max". We use training optimizations like packing, so the effective batch size may be different than the value you set.
Controls how quickly the model adapts to new information (too high may cause instability, too low may slow convergence)
The learning rate scheduler to use. It specifies how the learning rate is adjusted during training.
The percent of steps at the start of training to linearly increase the learning rate.
Max gradient norm to be used for gradient clipping. Set to 0 to disable.
Weight decay. Regularization parameter for the optimizer.
Suffix that will be added to your fine-tuned model name
Integration key for tracking experiments and model metrics on W&B platform
The base URL of a dedicated Weights & Biases instance.
The Weights & Biases project for your run. If not specified, will use together as the project name.
The Weights & Biases name for your run.
Whether to mask the user messages in conversational data or prompts in instruction data.
The training method to use. 'sft' for Supervised Fine-Tuning or 'dpo' for Direct Preference Optimization.
The checkpoint identifier to continue training from a previous fine-tuning job. Format is {$JOB_ID} or {$OUTPUT_MODEL_NAME} or {$JOB_ID}:{$STEP} or {$OUTPUT_MODEL_NAME}:{$STEP}. The step value is optional; without it, the final checkpoint will be used.
The Hugging Face Hub repo to start training from. Should be as close as possible to the base model (specified by the model argument) in terms of architecture and size.
The revision of the Hugging Face Hub model to continue training from. E.g., hf_model_revision=main (default, used if the argument is not provided) or hf_model_revision='607a30d783dfa663caf39e06633721c8d4cfcd7e' (specific commit).
The API token for the Hugging Face Hub.
The name of the Hugging Face repository to upload the fine-tuned model to.
Response
Fine-tuning job initiated successfully
A truncated version of the fine-tune response, used for POST /fine-tunes, GET /fine-tunes and POST /fine-tunes/{id}/cancel endpoints
Unique identifier for the fine-tune job
pending, queued, running, compressing, uploading, cancel_requested, cancelled, error, completed Creation timestamp of the fine-tune job
Last update timestamp of the fine-tune job
Identifier for the user who created the job
Owner address information
Total price for the fine-tuning job
Count of tokens processed
Events related to this fine-tune job
File-ID of the training file
File-ID of the validation file
Base model used for fine-tuning
Suffix added to the fine-tuned model name
Number of training epochs
Number of evaluations during training
Number of checkpoints saved during training
Batch size used for training
Type of training used (full or LoRA)
Method of training used
Learning rate used for training
Learning rate scheduler configuration
Ratio of warmup steps
Maximum gradient norm for clipping
Weight decay value used
Weights & Biases project name
Weights & Biases run name
Checkpoint used to continue training
Hugging Face Hub repo to start training from
The revision of the Hugging Face Hub model to continue training from