InBatchCrossEntropy

class lightning_ir.loss.in_batch.InBatchCrossEntropy(pos_sampling_technique: 'all' | 'first' = 'all', neg_sampling_technique: 'all' | 'first' | 'all_and_non_first' = 'all', max_num_neg_samples: int | None = None)

Bases: InBatchLossFunction

In-batch cross-entropy loss function for ranking tasks. Originally proposed in: Fast Single-Class Classification and the Principle of Logit Separation

Methods

compute_loss(output)

Compute the in-batch cross-entropy loss.

compute_loss(output: LightningIROutput) → torch.Tensor

Compute the in-batch cross-entropy loss.

Parameters:

output (LightningIROutput) – The output from the model containing scores.

Returns:

The computed loss.

Return type:

torch.Tensor