lighteval/pr_994/en/package_reference/evaluation_tracker.md

EvaluationTracker[[lighteval.logging.evaluation_tracker.EvaluationTracker]]

class lighteval.logging.evaluation_tracker.EvaluationTrackerlighteval.logging.evaluation_tracker.EvaluationTrackerhttps://github.com/huggingface/lighteval/blob/vr_994/src/lighteval/logging/evaluation_tracker.py#L92[{"name": "output_dir", "val": ": str"}, {"name": "results_path_template", "val": ": str | None = None"}, {"name": "save_details", "val": ": bool = True"}, {"name": "push_to_hub", "val": ": bool = False"}, {"name": "push_to_tensorboard", "val": ": bool = False"}, {"name": "hub_results_org", "val": ": str | None = ''"}, {"name": "tensorboard_metric_prefix", "val": ": str = 'eval'"}, {"name": "public", "val": ": bool = False"}, {"name": "nanotron_run_info", "val": ": GeneralArgs = None"}, {"name": "use_wandb", "val": ": bool = False"}]- output_dir (str) -- Local directory to save evaluation results and logs

• results_path_template (str, optional) -- Template for results directory structure. Example: "{output_dir}/results/{org}_{model}"
• save_details (bool, defaults to True) -- Whether to save detailed evaluation records
• push_to_hub (bool, defaults to False) -- Whether to push results to HF Hub
• push_to_tensorboard (bool, defaults to False) -- Whether to push metrics to TensorBoard
• hub_results_org (str, optional) -- HF Hub organization to push results to
• tensorboard_metric_prefix (str, defaults to "eval") -- Prefix for TensorBoard metrics
• public (bool, defaults to False) -- Whether to make Hub datasets public
• nanotron_run_info (GeneralArgs, optional) -- Nanotron model run information
• use_wandb (bool, defaults to False) -- Whether to log to Weights & Biases or Trackio if available0 Tracks and manages evaluation results, metrics, and logging for model evaluations.

The EvaluationTracker coordinates multiple specialized loggers to track different aspects of model evaluation:

• Details Logger (DetailsLogger): Records per-sample evaluation details and predictions
• Metrics Logger (MetricsLogger): Tracks aggregate evaluation metrics and scores
• Versions Logger (VersionsLogger): Records task and dataset versions
• General Config Logger (GeneralConfigLogger): Stores overall evaluation configuration
• Task Config Logger (TaskConfigLogger): Maintains per-task configuration details

The tracker can save results locally and optionally push them to:

• Hugging Face Hub as datasets
• TensorBoard for visualization
• Trackio or Weights & Biases for experiment tracking

Example:

tracker = EvaluationTracker(
    output_dir="./eval_results",
    push_to_hub=True,
    hub_results_org="my-org",
    save_details=True
)

# Log evaluation results
tracker.metrics_logger.add_metric("accuracy", 0.85)
tracker.details_logger.add_detail(task_name="qa", prediction="Paris")

# Save all results
tracker.save()

generate_final_dictlighteval.logging.evaluation_tracker.EvaluationTracker.generate_final_dicthttps://github.com/huggingface/lighteval/blob/vr_994/src/lighteval/logging/evaluation_tracker.py#L360[]dictDictionary containing all experiment information including config, results, versions, and summaries Aggregates and returns all the logger's experiment information in a dictionary.

This function should be used to gather and display said information at the end of an evaluation run.

push_to_hublighteval.logging.evaluation_tracker.EvaluationTracker.push_to_hubhttps://github.com/huggingface/lighteval/blob/vr_994/src/lighteval/logging/evaluation_tracker.py#L384[{"name": "date_id", "val": ": str"}, {"name": "details", "val": ": dict"}, {"name": "results_dict", "val": ": dict"}] Pushes the experiment details (all the model predictions for every step) to the hub.

recreate_metadata_cardlighteval.logging.evaluation_tracker.EvaluationTracker.recreate_metadata_cardhttps://github.com/huggingface/lighteval/blob/vr_994/src/lighteval/logging/evaluation_tracker.py#L451[{"name": "repo_id", "val": ": str"}]- repo_id (str) -- Details dataset repository path on the hub (org/dataset)0 Fully updates the details repository metadata card for the currently evaluated model

savelighteval.logging.evaluation_tracker.EvaluationTracker.savehttps://github.com/huggingface/lighteval/blob/vr_994/src/lighteval/logging/evaluation_tracker.py#L244[] Saves the experiment information and results to files, and to the hub if requested.