def _distributed_train_model(self, opt):
with testing_utils.tempdir() as tmpdir:
if 'model_file' not in opt:
opt['model_file'] = os.path.join(tmpdir, 'model')
if 'dict_file' not in opt:
opt['dict_file'] = os.path.join(tmpdir, 'model.dict')
parser = mp_train.setup_args()
popt = _forced_parse(parser, opt)
# we need a prebuilt dictionary
parser = build_dict.setup_args()
build_dict.build_dict(popt)
valid, test = mp_train.launch_and_train(popt, 31337)
return (valid, test)
def _distributed_train_model(self, **overrides):
opt = {**self.base_config, **overrides}
with testing_utils.tempdir() as tmpdir:
if 'model_file' not in opt:
opt['model_file'] = os.path.join(tmpdir, 'model')
if 'dict_file' not in opt:
opt['dict_file'] = os.path.join(tmpdir, 'model.dict')
parser = mp_train.setup_args()
popt = parser.parse_kwargs(**opt)
# we need a prebuilt dictionary
parser = build_dict.setup_args()
build_dict.build_dict(popt)
valid, test = mp_train.launch_and_train(popt)
return (valid, test)
def _distributed_train_model(self, opt):
with testing_utils.tempdir() as tmpdir:
if 'model_file' not in opt:
opt['model_file'] = os.path.join(tmpdir, 'model')
if 'dict_file' not in opt:
opt['dict_file'] = os.path.join(tmpdir, 'model.dict')
parser = mp_train.setup_args()
# TODO: Kill this after dictionaries build correctly
popt = self._forced_parse(parser, opt)
# we need a prebuilt dictionary
parser = build_dict.setup_args()
build_dict.build_dict(popt)
valid, test = mp_train.launch_and_train(popt, 31338)
dist.destroy_process_group()
return (valid, test)
def _distributed_train_model(self, opt):
# we have to delay our import to here, because the set_spawn_method call
# inside multiprocessing_train will break the multithreading tests, even
# when we skip the test.
import parlai.scripts.multiprocessing_train as mp_train
with testing_utils.capture_output() as output:
with testing_utils.tempdir() as tmpdir:
if 'model_file' not in opt:
opt['model_file'] = os.path.join(tmpdir, 'model')
if 'dict_file' not in opt:
opt['dict_file'] = os.path.join(tmpdir, 'model.dict')
parser = mp_train.setup_args()
popt = _forced_parse(parser, opt)
# we need a prebuilt dictionary
parser = build_dict.setup_args()
build_dict.build_dict(popt)
valid, test = mp_train.launch_and_train(popt, 31337)
return (output.getvalue(), valid, test)
model_file=os.path.join(
PARLAI_HOME, 'models/contrastive_learning/tmp/personachat_extend'),
hiddensize=256,
attention='general',
attention_time='post',
numlayers=2,
rnn_class='lstm',
lookuptable='enc_dec',
optimizer='adam',
weight_decay=0,
embedding_type='glove',
momentum=0.95,
bidirectional=True,
numsoftmax=1,
lr_scheduler='reduceonplateau',
lr_scheduler_patience=3,
lr_scheduler_decay=0.8,
warmup_updates=-1,
)
opt = parser.parse_args()
opt = override_opt(opt, DEFAULT_OVERRIDE)
opt = override_opt(opt, OVERRIDE)
if opt.get('multigpu', False):
port = random.randint(32000, 48000)
launch_and_train(opt, port)
else:
TrainLoop(opt).train()
