CEBRAEvalTrainer#

class ts1.models.single_session.CEBRAEvalTrainer(cfg, rank, world_size)[source]#

Bases: ts1.ts1_eval_trainer.TS1EvalTrainer

Benchmark eval trainer with in-run CEBRA encoder fitting.

setup(ckpt)[source]#

Set up all trainer components.

Called automatically by the base constructor. Initializes tasks, data loaders, model, DDP wrapping, optimizer, and finetuning strategy in order.

Parameters:

ckpt – Checkpoint dictionary loaded from disk, or None for a fresh run.

setup_model(ckpt=None)[source]#

Instantiate and register the model.

Instantiates the model from the Hydra config and registers it for checkpointing. Override this to load pretrained weights or modify the model architecture.

Parameters:

ckpt (Optional[dict]) – Checkpoint dictionary, available for loading pretrained weights.