def _push_from_checkpoint()

in optimum/graphcore/trainer.py [0:0]

• 29 lines of code
• 15 McCabe index (conditional complexity)

    def _push_from_checkpoint(self, checkpoint_folder):
        # Only push from one node.
        if self.args.hub_strategy == HubStrategy.END:
            return
        # If we haven't finished the last push, we don't do this one.
        if self.push_in_progress is not None and not self.push_in_progress.is_done:
            return

        output_dir = self.args.output_dir
        # To avoid a new synchronization of all model weights, we just copy the file from the checkpoint folder
        modeling_files = [CONFIG_NAME, WEIGHTS_NAME, IPU_CONFIG_NAME]
        for modeling_file in modeling_files:
            if os.path.isfile(os.path.join(checkpoint_folder, modeling_file)):
                shutil.copy(os.path.join(checkpoint_folder, modeling_file), os.path.join(output_dir, modeling_file))
        # Saving the tokenizer is fast and we don't know how many files it may have spawned, so we resave it to be sure.
        if self.tokenizer is not None:
            self.tokenizer.save_pretrained(output_dir)
        # Same for the training arguments
        torch.save(self.args, os.path.join(output_dir, TRAINING_ARGS_NAME))

        try:
            if self.args.hub_strategy == HubStrategy.CHECKPOINT:
                # Temporarily move the checkpoint just saved for the push
                tmp_checkpoint = os.path.join(output_dir, "last-checkpoint")
                # We have to remove the "last-checkpoint" dir if it exists, otherwise the checkpoint is moved as a
                # subfolder.
                if os.path.isdir(tmp_checkpoint):
                    shutil.rmtree(tmp_checkpoint)
                shutil.move(checkpoint_folder, tmp_checkpoint)

            if self.args.save_strategy == IntervalStrategy.STEPS:
                commit_message = f"Training in progress, step {self.state.global_step}"
            else:
                commit_message = f"Training in progress, epoch {int(self.state.epoch)}"
            _, self.push_in_progress = self.repo.push_to_hub(
                commit_message=commit_message, blocking=False, auto_lfs_prune=True
            )
        finally:
            if self.args.hub_strategy == HubStrategy.CHECKPOINT:
                # Move back the checkpoint to its place
                shutil.move(tmp_checkpoint, checkpoint_folder)