def initial_setup(args, cl_args):
"""
Sets up email hook, creating seed, and cuda settings.
Parameters
----------------
args: Params object
cl_args: list of arguments
Returns
----------------
tasks: list of Task objects
pretrain_tasks: list of pretraining tasks
target_tasks: list of target tasks
vocab: list of vocab
word_embs: loaded word embeddings, may be None if args.input_module in
{gpt, elmo, elmo-chars-only, bert-*}
model: a MultiTaskModel object
"""
output = io.StringIO()
maybe_make_dir(args.project_dir) # e.g. /nfs/jsalt/exp/$HOSTNAME
maybe_make_dir(args.exp_dir) # e.g. <project_dir>/jiant-demo
maybe_make_dir(args.run_dir) # e.g. <project_dir>/jiant-demo/sst
log_fh = log.FileHandler(args.local_log_path)
log_fmt = log.Formatter("%(asctime)s: %(message)s",
datefmt="%m/%d %I:%M:%S %p")
log_fh.setFormatter(log_fmt)
log.getLogger().addHandler(log_fh)
if cl_args.remote_log:
from jiant.utils import gcp
gcp.configure_remote_logging(args.remote_log_name)
if cl_args.notify:
from jiant.utils import emails
global EMAIL_NOTIFIER
log.info("Registering email notifier for %s", cl_args.notify)
EMAIL_NOTIFIER = emails.get_notifier(cl_args.notify, args)
if EMAIL_NOTIFIER:
EMAIL_NOTIFIER(body="Starting run.", prefix="")
_log_git_info()
config_file = os.path.join(args.run_dir, "params.conf")
config.write_params(args, config_file)
print_args = select_relevant_print_args(args)
log.info("Parsed args: \n%s", print_args)
log.info("Saved config to %s", config_file)
seed = random.randint(1,
10000) if args.random_seed < 0 else args.random_seed
random.seed(seed)
torch.manual_seed(seed)
log.info("Using random seed %d", seed)
if args.cuda >= 0:
try:
if not torch.cuda.is_available():
raise EnvironmentError("CUDA is not available, or not detected"
" by PyTorch.")
log.info("Using GPU %d", args.cuda)
torch.cuda.set_device(args.cuda)
torch.cuda.manual_seed_all(seed)
except Exception:
log.warning(
"GPU access failed. You might be using a CPU-only installation of PyTorch. "
"Falling back to CPU.")
args.cuda = -1
if args.tokenizer == "auto":
args.tokenizer = tokenizers.select_tokenizer(args)
if args.pool_type == "auto":
args.pool_type = select_pool_type(args)
return args, seed
def initial_setup(args: config.Params, cl_args: argparse.Namespace) -> (config.Params, int):
"""Perform setup steps:
1. create project, exp, and run dirs if they don't already exist
2. create log formatter
3. configure GCP remote logging
4. set up email notifier
5. log git info
6. write the config out to file
7. log diff between default and experiment's configs
8. choose torch's and random's random seed
9. if config specifies a single GPU, then set the GPU's random seed (doesn't cover multi-GPU)
10. resolve "auto" settings for tokenizer and pool_type parameters
Parameters
----------
args : config.Params
config map
cl_args : argparse.Namespace
mapping named arguments to parsed values
Returns
-------
args : config.Params
config map
seed : int
random's and pytorch's random seed
"""
output = io.StringIO()
maybe_make_dir(args.project_dir) # e.g. /nfs/jsalt/exp/$HOSTNAME
maybe_make_dir(args.exp_dir) # e.g. <project_dir>/jiant-demo
maybe_make_dir(args.run_dir) # e.g. <project_dir>/jiant-demo/sst
log_fh = log.FileHandler(args.local_log_path)
log_fmt = log.Formatter("%(asctime)s: %(message)s", datefmt="%m/%d %I:%M:%S %p")
log_fh.setFormatter(log_fmt)
log.getLogger().addHandler(log_fh)
if cl_args.remote_log:
from jiant.utils import gcp
gcp.configure_remote_logging(args.remote_log_name)
if cl_args.notify:
from jiant.utils import emails
global EMAIL_NOTIFIER
log.info("Registering email notifier for %s", cl_args.notify)
EMAIL_NOTIFIER = emails.get_notifier(cl_args.notify, args)
if EMAIL_NOTIFIER:
EMAIL_NOTIFIER(body="Starting run.", prefix="")
_log_git_info()
config_file = os.path.join(args.run_dir, "params.conf")
config.write_params(args, config_file)
print_args = select_relevant_print_args(args)
log.info("Parsed args: \n%s", print_args)
log.info("Saved config to %s", config_file)
seed = random.randint(1, 10000) if args.random_seed < 0 else args.random_seed
random.seed(seed)
torch.manual_seed(seed)
log.info("Using random seed %d", seed)
if isinstance(args.cuda, int) and args.cuda >= 0:
# If only running on one GPU.
try:
if not torch.cuda.is_available():
raise EnvironmentError("CUDA is not available, or not detected" " by PyTorch.")
log.info("Using GPU %d", args.cuda)
torch.cuda.set_device(args.cuda)
torch.cuda.manual_seed_all(seed)
except Exception:
log.warning(
"GPU access failed. You might be using a CPU-only installation of PyTorch. "
"Falling back to CPU."
)
args.cuda = -1
if args.tokenizer == "auto":
args.tokenizer = tokenizers.select_tokenizer(args)
if args.pool_type == "auto":
args.pool_type = select_pool_type(args)
return args, seed
