in optimum/graphcore/trainer.py [0:0]
def compute_loss(self, model, inputs, return_outputs=False):
"""
Computes the loss on a batch of training inputs.
Args:
model:
The model to train.
inputs:
The inputs and targets of the model.
return_outputs (defaults to `False`):
If `True`, returns the outputs with the loss. If `False`, only returns the loss.
By default, all models return the loss in the first element.
Subclass and override for custom behavior.
"""
if self.label_smoother is not None and "labels" in inputs:
labels = inputs.pop("labels")
else:
labels = None
outputs = model(**inputs)
# Save past state if it exists
# TODO: this needs to be fixed and made cleaner later.
if self.args.past_index >= 0:
self._past = outputs[self.args.past_index]
if labels is not None:
loss = self.label_smoother(outputs, labels)
else:
if isinstance(outputs, dict) and "loss" not in outputs:
raise ValueError(
"The model did not return a loss from the inputs, only the following keys: "
f"{','.join(outputs.keys())}. For reference, the inputs it received are {','.join(inputs.keys())}."
)
# We don't use .loss here since the model may return tuples instead of ModelOutput.
loss = outputs["loss"] if isinstance(outputs, dict) else outputs[0]
return (loss, outputs) if return_outputs else loss