Cancel job
Cancel a currently running fine-tuning job. Returns a FinetuneResponseTruncated object.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Fine-tune ID to cancel. A string that starts with ft-.
Response
Successfully cancelled the fine-tuning job.
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
ID of the user who owns the fine-tune job.
Start timestamp of the current stage of the fine-tune 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
Whether sequence packing is being used for training.
Maximum sequence length to use for training. If not specified, uses the maximum allowed for the model and training method.
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)
- Option 1
- Option 2
Method of training used
- Option 1
- Option 2
Learning rate used for training
Learning rate scheduler configuration
Ratio of warmup steps
Maximum gradient norm for clipping
Weight decay value used
Random seed used for training. Integer when set; null if not stored (e.g. legacy jobs) or no explicit seed was recorded.
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
Progress information for the fine-tuning job
Whether the early-stopping criterion triggered.
Step associated with the selected early-stopping artifact. When early_stopping_best_metric is null, no finite best metric was recorded; this is the halt step, not a best-checkpoint step.
Best validation loss observed, corresponding to early_stopping_best_step. Null if no improving evaluation was recorded.