args = parser.parse_args()
print(args)
globals().update(args.__dict__)
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
logger = ResultLogger(path=os.path.join(log_dir, '{}.jsonl'.format(desc)),
**args.__dict__)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
(trX1, trX2, trX3,
trY), (vaX1, vaX2, vaX3,
vaY), (teX1, teX2, teX3) = encode_dataset(rocstories(data_dir),
encoder=text_encoder)
n_y = 2
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
n_ctx = min(
max([
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(trX1, trX2, trX3)
] + [
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(vaX1, vaX2, vaX3)
logger = ResultLogger(path=os.path.join(
log_dir, '{}.jsonl'.format(desc)), **args.__dict__)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
if dataset == 'rocstories':
(trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY), (teX1, teX2, teX3) = encode_dataset(
rocstories(data_dir, n_valid=n_valid), encoder=text_encoder)
n_y = 2
n_ctx = min(max(
[len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(trX1, trX2, trX3)]
+ [len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(vaX1, vaX2, vaX3)]
+ [len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(teX1, teX2, teX3)]
) + 3,
n_ctx)
vocab = n_vocab + n_special + n_ctx
trX, trM = transform_roc(trX1, trX2, trX3)
vaX, vaM = transform_roc(vaX1, vaX2, vaX3)
if submit:
teX, teM = transform_roc(teX1, teX2, teX3)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
if dataset == 'rocstories':
(trX1, trX2, trX3,
trY), (vaX1, vaX2, vaX3,
vaY), (teX1, teX2,
teX3) = encode_dataset(rocstories(data_dir,
n_valid=n_valid),
encoder=text_encoder)
n_y = 2
n_ctx = min(
max([
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(trX1, trX2, trX3)
] + [
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(vaX1, vaX2, vaX3)
] + [
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(teX1, teX2, teX3)
]) + 3, n_ctx)
vocab = n_vocab + n_special + n_ctx
trX, trM = transform_roc(trX1, trX2, trX3)
submission_dir = args.submission_dir
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_gpu = torch.cuda.device_count()
logger.info("device {} n_gpu {}".format(device, n_gpu))
res_logger = ResultLogger(path=os.path.join(log_dir,
'{}.jsonl'.format(desc)),
**args.__dict__)
text_encoder = TextEncoder(args.encoder_path, args.bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
logger.info("Encoding dataset...")
((trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY),
(teX1, teX2, teX3)) = encode_dataset(*rocstories(data_dir,
n_valid=args.n_valid),
encoder=text_encoder)
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
n_ctx = min(
max([
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(trX1, trX2, trX3)
] + [
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(vaX1, vaX2, vaX3)
] + [
parser.add_argument('--e', type=float, default=1e-8)
args = parser.parse_args()
print(args)
globals().update(args.__dict__)
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
#tf.random.set_seed(seed)
logger = ResultLogger(path=os.path.join(log_dir, '{}.jsonl'.format(desc)), **args.__dict__)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
(trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY), (teX1, teX2, teX3) = encode_dataset(rocstories(data_dir), encoder=text_encoder)
n_y = 2
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx//2-2
n_ctx = min(max([len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len])) for x1, x2, x3 in zip(trX1, trX2, trX3)]+[len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len])) for x1, x2, x3 in zip(vaX1, vaX2, vaX3)]+[len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len])) for x1, x2, x3 in zip(teX1, teX2, teX3)])+3, n_ctx)
trX, trM = transform_roc(trX1, trX2, trX3)
vaX, vaM = transform_roc(vaX1, vaX2, vaX3)
if submit:
teX, teM = transform_roc(teX1, teX2, teX3)
n_train = len(trY)
n_valid = len(vaY)
n_ctx = args.n_ctx
save_dir = args.save_dir
desc = args.desc
data_dir = args.data_dir
log_dir = args.log_dir
# torch.device object used throughout this script TODO add gpu setting
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
logger = ResultLogger(path=os.path.join(log_dir, '{}.jsonl'.format(desc)), **args.__dict__)
text_encoder = TextEncoder(args.encoder_path, args.bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
(trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY), (teX1, teX2, teX3) = encode_dataset(
rocstories(data_dir, n_valid=args.n_valid), encoder=text_encoder)
n_y = 2
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
n_ctx = min(max(
[len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(trX1, trX2, trX3)]
+ [len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(vaX1, vaX2, vaX3)]
+ [len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len])) for x1, x2, x3 in zip(teX1, teX2, teX3)]
) + 3, n_ctx)
[references]
globals().update: https://stackoverflow.com/questions/1589968/python-difference-between-global-globals-updatevar
__dict__: http://coolpythontips.blogspot.com/2015/12/dict.html
"""
globals().update(args.__dict__)
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
logger = ResultLogger(path=os.path.join(log_dir, "{}.json".format(desc)), **args.__dict__)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder =text_encoder.encoder
n_vocab = len(text_encoder.encoder)
(trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY), (teX1, teX2, teX3) = encode_dataset(
rocstories(data_dir),
encoder=text_encoder)
n_y = 2
encoder["_start_"] = len(encoder)
encoder["_delimiter_"] = len(encoder)
encoder["_classify_"] = len(encoder)
clf_token = encoder["_classify_"]
n_special = 3
max_len = n_ctx // 2 - 2
"""
set the context length from the longest sequence from train, validation
and test datasets + 3(special tokens used in finetuning)
or the context length which is originally set
"""
n_ctx = min(max([len(x1[:max_len]) + max(len(x2[:max_len]),
len(x3[:max_len]))
args = parser.parse_args()
print(args)
globals().update(args.__dict__)
random.seed(seed)
np.random.seed(seed)
tf.set_random_seed(seed)
logger = ResultLogger(path=os.path.join(
log_dir, '{}.jsonl'.format(desc)), **args.__dict__)
text_encoder = TextEncoder(encoder_path, bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
(trX1, trX2, trX3, trY), (vaX1, vaX2, vaX3, vaY), (teX1, teX2,
teX3) = encode_dataset(rocstories(data_dir), encoder=text_encoder)
n_y = 2
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx//2-2
n_ctx = min(max([len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len])) for x1, x2, x3 in zip(trX1, trX2, trX3)]+[len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(vaX1, vaX2, vaX3)]+[len(x1[:max_len])+max(len(x2[:max_len]), len(x3[:max_len])) for x1, x2, x3 in zip(teX1, teX2, teX3)])+3, n_ctx)
trX, trM = transform_roc(trX1, trX2, trX3)
vaX, vaM = transform_roc(vaX1, vaX2, vaX3)
if submit:
teX, teM = transform_roc(teX1, teX2, teX3)
n_train = len(trY)
submission_dir = args.submission_dir
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_gpu = torch.cuda.device_count()
print("device", device, "n_gpu", n_gpu)
logger = ResultLogger(path=os.path.join(log_dir, '{}.jsonl'.format(desc)),
**args.__dict__)
text_encoder = TextEncoder(args.encoder_path, args.bpe_path)
encoder = text_encoder.encoder
n_vocab = len(text_encoder.encoder)
print("Encoding dataset...")
((trX1, trX2, trX3, trY, trELMo), (vaX1, vaX2, vaX3, vaY, vaELMo),
(teX1, teX2, teX3,
teELMo)) = encode_dataset(*rocstories(data_dir, n_valid=args.n_valid),
encoder=text_encoder)
encoder['_start_'] = len(encoder)
encoder['_delimiter_'] = len(encoder)
encoder['_classify_'] = len(encoder)
clf_token = encoder['_classify_']
n_special = 3
max_len = n_ctx // 2 - 2
n_ctx = min(
max([
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(trX1, trX2, trX3)
] + [
len(x1[:max_len]) + max(len(x2[:max_len]), len(x3[:max_len]))
for x1, x2, x3 in zip(vaX1, vaX2, vaX3)
] + [
