【Blog】Deepseek R1 Sharing

# trainer.py #2205
if has_length(train_dataloader):
            len_dataloader = len(train_dataloader)
            num_update_steps_per_epoch = len_dataloader // args.gradient_accumulation_steps
            num_update_steps_per_epoch = max(num_update_steps_per_epoch, 1)
            num_examples = self.num_examples(train_dataloader)
            if args.max_steps > 0:
                max_steps = args.max_steps
                num_train_epochs = args.max_steps // num_update_steps_per_epoch + int(
                    args.max_steps % num_update_steps_per_epoch > 0
                )
                # May be slightly incorrect if the last batch in the training dataloader has a smaller size but it's
                # the best we can do.
                num_train_samples = args.max_steps * total_train_batch_size
                if args.include_tokens_per_second:
                    num_train_tokens = (
                        self.num_tokens(train_dataloader, args.max_steps) * args.gradient_accumulation_steps
                    )
            else:
                max_steps = math.ceil(args.num_train_epochs * num_update_steps_per_epoch)
                num_train_epochs = math.ceil(args.num_train_epochs)
                num_train_samples = self.num_examples(train_dataloader) * args.num_train_epochs
                if args.include_tokens_per_second:
                    num_train_tokens = self.num_tokens(train_dataloader) * args.num_train_epochs
        elif args.max_steps > 0:  # Rely on max_steps when dataloader does not have a working size
            max_steps = args.max_steps
            # Setting a very large number of epochs so we go as many times as necessary over the iterator.
            num_train_epochs = sys.maxsize
            num_update_steps_per_epoch = max_steps
            num_examples = total_train_batch_size * args.max_steps
            num_train_samples = args.max_steps * total_train_batch_size
            if args.include_tokens_per_second:
                num_train_tokens = self.num_tokens(train_dataloader, args.max_steps) * args.gradient_accumulation_steps