T5DST/T5.py [49:94]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class DST_Seq2Seq(pl.LightningModule):

    def __init__(self,args, tokenizer, model):
        super().__init__()
        self.tokenizer = tokenizer
        self.model = model
        self.lr = args["lr"]


    def training_step(self, batch, batch_idx):
        self.model.train()
        (loss), *_ = self.model(input_ids=batch["encoder_input"],
                            attention_mask=batch["attention_mask"],
                            lm_labels=batch["decoder_output"]
                            )

        # result = pl.TrainResult(loss)
        # result.log('train_loss', loss, on_epoch=True)
        return {'loss': loss, 'log': {'train_loss': loss}}
        # return result

    def validation_step(self, batch, batch_idx):
        self.model.eval()
        (loss), *_ = self.model(input_ids=batch["encoder_input"],
                            attention_mask=batch["attention_mask"],
                            lm_labels=batch["decoder_output"]
                            )


        return {'val_loss': loss, 'log': {'val_loss': loss}}
        # return result

    def validation_epoch_end(self, outputs):
        val_loss_mean = sum([o['val_loss'] for o in outputs]) / len(outputs)
        # show val_loss in progress bar but only log val_loss
        results = {'progress_bar': {'val_loss': val_loss_mean.item()}, 'log': {'val_loss': val_loss_mean.item()},
                   'val_loss': val_loss_mean.item()}
        return results

    def configure_optimizers(self):
        return AdamW(self.parameters(), lr=self.lr, correct_bias=True)



def train(args, *more):
    args = vars(args)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



TransferQA/T5.py [21:67]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class DST_Seq2Seq(pl.LightningModule):

    def __init__(self,args, tokenizer, model):
        super().__init__()
        self.tokenizer = tokenizer
        self.model = model
        self.lr = args["lr"]


    def training_step(self, batch, batch_idx):
        self.model.train()

        (loss), *_ = self.model(input_ids=batch["encoder_input"],
                            attention_mask=batch["attention_mask"],
                            lm_labels=batch["decoder_output"]
                            )

        # result = pl.TrainResult(loss)
        # result.log('train_loss', loss, on_epoch=True)
        return {'loss': loss, 'log': {'train_loss': loss}}
        # return result

    def validation_step(self, batch, batch_idx):
        self.model.eval()
        (loss), *_ = self.model(input_ids=batch["encoder_input"],
                            attention_mask=batch["attention_mask"],
                            lm_labels=batch["decoder_output"]
                            )


        return {'val_loss': loss, 'log': {'val_loss': loss}}
        # return result

    def validation_epoch_end(self, outputs):
        val_loss_mean = sum([o['val_loss'] for o in outputs]) / len(outputs)
        # show val_loss in progress bar but only log val_loss
        results = {'progress_bar': {'val_loss': val_loss_mean.item()}, 'log': {'val_loss': val_loss_mean.item()},
                   'val_loss': val_loss_mean.item()}
        return results

    def configure_optimizers(self):
        return AdamW(self.parameters(), lr=self.lr, correct_bias=True)



def train(args, *more):
    args = vars(args)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -