def main():
parser = argparse.ArgumentParser()
parser.add_argument("corpus", choices=["en", "en_trans_de", "en_trans_zh"])
parser.add_argument(
'mode',
choices=["confidence", "merge", "shared-norm", "sigmoid", "paragraph"])
# Note I haven't tested modes other than `shared-norm` on this corpus, so
# some things might need adjusting
parser.add_argument("name", help="Where to store the model")
parser.add_argument("-t",
"--n_tokens",
default=400,
type=int,
help="Paragraph size")
parser.add_argument(
'-n',
'--n_processes',
type=int,
default=2,
help="Number of processes (i.e., select which paragraphs to train on) "
"the data with")
args = parser.parse_args()
mode = args.mode
corpus = args.corpus
out = args.name + "-" + datetime.now().strftime("%m%d-%H%M%S")
model = get_model(100, 140, mode, WithIndicators())
extract = ExtractMultiParagraphsPerQuestion(MergeParagraphs(args.n_tokens),
ShallowOpenWebRanker(16),
model.preprocessor,
intern=True)
eval = [
LossEvaluator(),
MultiParagraphSpanEvaluator(8,
"triviaqa",
mode != "merge",
per_doc=False)
]
oversample = [
1
] * 2 # Sample the top two answer-containing paragraphs twice
if mode == "paragraph":
n_epochs = 120
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(ClusteredBatcher(
60, ContextLenBucketedKey(3), True),
oversample,
only_answers=True)
elif mode == "confidence" or mode == "sigmoid":
if mode == "sigmoid":
n_epochs = 640
else:
n_epochs = 160
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(
ClusteredBatcher(60, ContextLenBucketedKey(3), True), oversample)
else:
n_epochs = 80
test = RandomParagraphSetDatasetBuilder(
120, "merge" if mode == "merge" else "group", True, oversample)
train = StratifyParagraphSetsBuilder(30, mode == "merge", True,
oversample)
data = XQADataset(corpus)
params = TrainParams(SerializableOptimizer("Adadelta",
dict(learning_rate=1)),
num_epochs=n_epochs,
ema=0.999,
max_checkpoints_to_keep=2,
async_encoding=10,
log_period=30,
eval_period=1800,
save_period=1800,
best_weights=("dev", "b8/question-text-f1"),
eval_samples=dict(dev=None, train=6000))
data = PreprocessedData(data, extract, train, test, eval_on_verified=False)
data.preprocess(args.n_processes, 1000)
with open(__file__, "r") as f:
notes = f.read()
notes = "Mode: " + args.mode + "\n" + notes
trainer.start_training(data, model, params, eval, model_dir.ModelDir(out),
notes)
def main():
parser = argparse.ArgumentParser(description='Train a model on TriviaQA web')
parser.add_argument('mode', choices=["paragraph-level", "confidence", "merge",
"shared-norm", "sigmoid", "shared-norm-600"])
parser.add_argument("name", help="Where to store the model")
parser.add_argument('-n', '--n_processes', type=int, default=2,
help="Number of processes (i.e., select which paragraphs to train on) "
"the data with")
args = parser.parse_args()
mode = args.mode
out = args.name + "-" + datetime.now().strftime("%m%d-%H%M%S")
model = get_model(100, 140, mode, WithIndicators())
stop = NltkPlusStopWords(True)
if mode == "paragraph-level":
extract = ExtractSingleParagraph(MergeParagraphs(400), TopTfIdf(stop, 1), model.preprocessor, intern=True)
elif mode == "shared-norm-600":
extract = ExtractMultiParagraphs(MergeParagraphs(600), TopTfIdf(stop, 4), model.preprocessor, intern=True)
else:
extract = ExtractMultiParagraphs(MergeParagraphs(400), TopTfIdf(stop, 4), model.preprocessor, intern=True)
if mode == "paragraph-level":
n_epochs = 16
train = ParagraphAndQuestionsBuilder(ClusteredBatcher(60, ContextLenBucketedKey(3), True))
test = ParagraphAndQuestionsBuilder(ClusteredBatcher(60, ContextLenKey(), False))
n_dev, n_train = 21000, 12000
eval = [LossEvaluator(), SpanEvaluator([4, 8], "triviaqa")]
else:
eval = [LossEvaluator(), MultiParagraphSpanEvaluator(8, "triviaqa", mode != "merge")]
# we sample two paragraphs per a (question, doc) pair, so evaluate on fewer questions
n_dev, n_train = 15000, 8000
if mode == "confidence" or mode == "sigmoid":
if mode == "sigmoid":
# Trains very slowly, do this at your own risk
n_epochs = 71
else:
n_epochs = 28
test = RandomParagraphSetDatasetBuilder(120, "flatten", True, 1)
train = StratifyParagraphsBuilder(ClusteredBatcher(60, ContextLenBucketedKey(3), True), 0, 1)
else:
n_epochs = 14
test = RandomParagraphSetDatasetBuilder(120, "merge" if mode == "merge" else "group", True, 1)
train = StratifyParagraphSetsBuilder(35, mode == "merge", True, 1)
data = TriviaQaWebDataset()
params = get_triviaqa_train_params(n_epochs, n_dev, n_train)
data = PreprocessedData(data, extract, train, test, eval_on_verified=False)
data.preprocess(args.n_processes, 1000)
with open(__file__, "r") as f:
notes = f.read()
notes = "*" * 10 + "\nMode: " + args.mode + "\n" + "*"*10 + "\n" + notes
trainer.start_training(data, model, params, eval, model_dir.ModelDir(out), notes)
def main():
parser = argparse.ArgumentParser(
description='Train a model on document-level SQuAD')
parser.add_argument(
'mode',
choices=["paragraph", "confidence", "shared-norm", "merge", "sigmoid"])
parser.add_argument("name", help="Output directory")
args = parser.parse_args()
mode = args.mode
out = args.name + "-" + datetime.now().strftime("%m%d-%H%M%S")
corpus = SquadCorpus()
if mode == "merge":
# Adds paragraph start tokens, since we will be concatenating paragraphs together
pre = WithIndicators(True, para_tokens=False, doc_start_token=False)
else:
pre = None
model = get_model(50, 100, args.mode, pre)
if mode == "paragraph":
# Run in the "standard" known-paragraph setting
if model.preprocessor is not None:
raise NotImplementedError()
n_epochs = 26
train_batching = ClusteredBatcher(45, ContextLenBucketedKey(3), True,
False)
eval_batching = ClusteredBatcher(45, ContextLenKey(), False, False)
data = DocumentQaTrainingData(corpus, None, train_batching,
eval_batching)
eval = [LossEvaluator(), SpanEvaluator(bound=[17], text_eval="squad")]
else:
eval_set_mode = {
"confidence": "flatten",
"sigmoid": "flatten",
"shared-norm": "group",
"merge": "merge"
}[mode]
eval_dataset = RandomParagraphSetDatasetBuilder(
100, eval_set_mode, True, 0)
if mode == "confidence" or mode == "sigmoid":
if mode == "sigmoid":
# needs to be trained for a really long time for reasons unknown, even this might be too small
n_epochs = 100
else:
n_epochs = 50 # more epochs since we only "see" the label very other epoch-osh
train_batching = ClusteredBatcher(45, ContextLenBucketedKey(3),
True, False)
data = PreprocessedData(
SquadCorpus(),
SquadTfIdfRanker(NltkPlusStopWords(True), 4, True,
model.preprocessor),
StratifyParagraphsBuilder(train_batching, 1),
eval_dataset,
eval_on_verified=False,
)
else:
n_epochs = 26
data = PreprocessedData(
SquadCorpus(),
SquadTfIdfRanker(NltkPlusStopWords(True), 4, True,
model.preprocessor),
StratifyParagraphSetsBuilder(25, args.mode == "merge", True,
1),
eval_dataset,
eval_on_verified=False,
)
eval = [LossEvaluator(), MultiParagraphSpanEvaluator(17, "squad")]
data.preprocess(1)
with open(__file__, "r") as f:
notes = f.read()
notes = args.mode + "\n" + notes
trainer.start_training(data, model, train_params(n_epochs), eval,
model_dir.ModelDir(out), notes)
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"corpus",
choices=["en", "fr", "de", "ru", "pt", "zh", "pl", "uk", "ta"])
parser.add_argument(
'mode',
choices=["confidence", "merge", "shared-norm", "sigmoid", "paragraph"])
# Note I haven't tested modes other than `shared-norm` on this corpus, so
# some things might need adjusting
parser.add_argument("-t",
"--n_tokens",
default=400,
type=int,
help="Paragraph size")
args = parser.parse_args()
mode = args.mode
corpus = args.corpus
model = get_model(100, 140, mode, WithIndicators())
extract = ExtractMultiParagraphsPerQuestion(MergeParagraphs(args.n_tokens),
ShallowOpenWebRanker(16),
model.preprocessor,
intern=True)
eval = [
LossEvaluator(),
MultiParagraphSpanEvaluator(8,
"triviaqa",
mode != "merge",
per_doc=False)
]
oversample = [
1
] * 2 # Sample the top two answer-containing paragraphs twice
if mode == "paragraph":
n_epochs = 120
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(ClusteredBatcher(
60, ContextLenBucketedKey(3), True),
oversample,
only_answers=True)
elif mode == "confidence" or mode == "sigmoid":
if mode == "sigmoid":
n_epochs = 640
else:
n_epochs = 160
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(
ClusteredBatcher(60, ContextLenBucketedKey(3), True), oversample)
else:
n_epochs = 80
test = RandomParagraphSetDatasetBuilder(
120, "merge" if mode == "merge" else "group", True, oversample)
train = StratifyParagraphSetsBuilder(30, mode == "merge", True,
oversample)
data = XQADataset(corpus)
data = PreprocessedData(data, extract, train, test, eval_on_verified=False)
data.preprocess(1, 1000)
# dump preprocessed dev data for bert
data.cache_preprocess("dev_data_%s.pkl" % args.corpus)
def get_evaluators(train_config):
return [
LossEvaluator(),
MultiParagraphSpanEvaluator(8, "triviaqa", train_config.trivia_qa_mode != "merge", per_doc=False)
]
def main():
parser = argparse.ArgumentParser(
description='Train a model on TriviaQA unfiltered')
parser.add_argument(
'mode',
choices=["confidence", "merge", "shared-norm", "sigmoid", "paragraph"])
parser.add_argument("name", help="Where to store the model")
parser.add_argument("-t",
"--n_tokens",
default=400,
type=int,
help="Paragraph size")
parser.add_argument(
'-n',
'--n_processes',
type=int,
default=2,
help="Number of processes (i.e., select which paragraphs to train on) "
"the data with")
parser.add_argument("-s",
"--source_dir",
type=str,
default=None,
help="where to take input files")
parser.add_argument("--n_epochs",
type=int,
default=None,
help="Max number of epoches to train on ")
parser.add_argument("--char_th",
type=int,
default=None,
help="char level embeddings")
parser.add_argument("--hl_dim",
type=int,
default=None,
help="hidden layer dim size")
parser.add_argument("--regularization",
type=int,
default=None,
help="hidden layer dim size")
parser.add_argument("--LR",
type=float,
default=1.0,
help="hidden layer dim size")
parser.add_argument("--save_every",
type=int,
default=1800,
help="save period")
parser.add_argument("--init_from",
type=str,
default=None,
help="model to init from")
args = parser.parse_args()
mode = args.mode
#out = args.name + "-" + datetime.now().strftime("%m%d-%H%M%S")
out = join('models', args.name)
char_th = 100
hl_dim = 140
if args.char_th is not None:
print(args.char_th)
char_th = int(args.char_th)
out += '--th' + str(char_th)
if args.hl_dim is not None:
print(args.hl_dim)
hl_dim = int(args.hl_dim)
out += '--hl' + str(hl_dim)
if args.init_from is None:
model = get_model(char_th, hl_dim, mode, WithIndicators())
else:
md = model_dir.ModelDir(args.init_from)
model = md.get_model()
extract = ExtractMultiParagraphsPerQuestion(MergeParagraphs(args.n_tokens),
ShallowOpenWebRanker(16),
model.preprocessor,
intern=True)
eval = [
LossEvaluator(),
MultiParagraphSpanEvaluator(8,
"triviaqa",
mode != "merge",
per_doc=False)
]
oversample = [1] * 4
if mode == "paragraph":
n_epochs = 120
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(ClusteredBatcher(
60, ContextLenBucketedKey(3), True),
oversample,
only_answers=True)
elif mode == "confidence" or mode == "sigmoid":
if mode == "sigmoid":
n_epochs = 640
else:
n_epochs = 160
test = RandomParagraphSetDatasetBuilder(120, "flatten", True,
oversample)
train = StratifyParagraphsBuilder(
ClusteredBatcher(60, ContextLenBucketedKey(3), True), oversample)
else:
n_epochs = 80
test = RandomParagraphSetDatasetBuilder(
120, "merge" if mode == "merge" else "group", True, oversample)
train = StratifyParagraphSetsBuilder(30, mode == "merge", True,
oversample)
if args.n_epochs is not None:
n_epochs = args.n_epochs
out += '--' + str(n_epochs)
if args.LR != 1.0:
out += '--' + str(args.LR)
data = TriviaQaOpenDataset(args.source_dir)
async_encoding = 10
#async_encoding = 0
params = TrainParams(SerializableOptimizer("Adadelta",
dict(learning_rate=args.LR)),
num_epochs=n_epochs,
num_of_steps=250000,
ema=0.999,
max_checkpoints_to_keep=2,
async_encoding=async_encoding,
log_period=30,
eval_period=1800,
save_period=args.save_every,
eval_samples=dict(dev=None, train=6000),
regularization_weight=None)
data = PreprocessedData(data, extract, train, test, eval_on_verified=False)
data.preprocess(args.n_processes, 1000)
with open(__file__, "r") as f:
notes = f.read()
notes = "Mode: " + args.mode + "\n" + notes
if args.init_from is not None:
init_from = model_dir.ModelDir(args.init_from).get_best_weights()
if init_from is None:
init_from = model_dir.ModelDir(
args.init_from).get_latest_checkpoint()
else:
init_from = None
trainer.start_training(data,
model,
params,
eval,
model_dir.ModelDir(out),
notes,
initialize_from=init_from)