run_with_submitit.py [61:112]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def checkpoint(self):
        import os
        import submitit

        self.args.dist_url = get_init_file().as_uri()
        print("Requeuing ", self.args)
        empty_trainer = type(self)(self.args)
        return submitit.helpers.DelayedSubmission(empty_trainer)

    def _setup_gpu_args(self):
        import submitit
        from pathlib import Path

        job_env = submitit.JobEnvironment()
        self.args.output_dir = Path(str(self.args.output_dir).replace("%j", str(job_env.job_id)))
        self.args.gpu = job_env.local_rank
        self.args.rank = job_env.global_rank
        self.args.world_size = job_env.num_tasks
        print(f"Process group: {job_env.num_tasks} tasks, rank: {job_env.global_rank}")


def main():
    args = parse_args()
    if args.job_dir == "":
        args.job_dir = get_shared_folder() / "%j"

    # Note that the folder will depend on the job_id, to easily track experiments
    executor = submitit.AutoExecutor(folder=args.job_dir, slurm_max_num_timeout=30)

    num_gpus_per_node = args.ngpus
    nodes = args.nodes
    timeout_min = args.timeout

    partition = args.partition
    kwargs = {}
    if args.use_volta32:
        kwargs['slurm_constraint'] = 'volta32gb'
    if args.comment:
        kwargs['slurm_comment'] = args.comment

    executor.update_parameters(
        mem_gb=40 * num_gpus_per_node,
        gpus_per_node=num_gpus_per_node,
        tasks_per_node=num_gpus_per_node,  # one task per GPU
        cpus_per_task=10,
        nodes=nodes,
        timeout_min=timeout_min,  # max is 60 * 72
        # Below are cluster dependent parameters
        slurm_partition=partition,
        slurm_signal_delay_s=120,
        **kwargs
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



run_with_submitit_linear.py [61:112]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def checkpoint(self):
        import os
        import submitit

        self.args.dist_url = get_init_file().as_uri()
        print("Requeuing ", self.args)
        empty_trainer = type(self)(self.args)
        return submitit.helpers.DelayedSubmission(empty_trainer)

    def _setup_gpu_args(self):
        import submitit
        from pathlib import Path

        job_env = submitit.JobEnvironment()
        self.args.output_dir = Path(str(self.args.output_dir).replace("%j", str(job_env.job_id)))
        self.args.gpu = job_env.local_rank
        self.args.rank = job_env.global_rank
        self.args.world_size = job_env.num_tasks
        print(f"Process group: {job_env.num_tasks} tasks, rank: {job_env.global_rank}")


def main():
    args = parse_args()
    if args.job_dir == "":
        args.job_dir = get_shared_folder() / "%j"

    # Note that the folder will depend on the job_id, to easily track experiments
    executor = submitit.AutoExecutor(folder=args.job_dir, slurm_max_num_timeout=30)

    num_gpus_per_node = args.ngpus
    nodes = args.nodes
    timeout_min = args.timeout

    partition = args.partition
    kwargs = {}
    if args.use_volta32:
        kwargs['slurm_constraint'] = 'volta32gb'
    if args.comment:
        kwargs['slurm_comment'] = args.comment

    executor.update_parameters(
        mem_gb=40 * num_gpus_per_node,
        gpus_per_node=num_gpus_per_node,
        tasks_per_node=num_gpus_per_node,  # one task per GPU
        cpus_per_task=10,
        nodes=nodes,
        timeout_min=timeout_min,  # max is 60 * 72
        # Below are cluster dependent parameters
        slurm_partition=partition,
        slurm_signal_delay_s=120,
        **kwargs
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -