layers=config.layers,
word_dropout=config.word_dropout,
char_dropout=config.char_dropout,
lstm_dropout=config.lstm_dropout)
if config.if_gpu:
ner_model = ner_model.cuda()
parameters = filter(lambda p: p.requires_grad, ner_model.parameters())
optimizer, lr_scheduler = create_opt(parameters,
config.opt,
lr=config.lr,
l2=config.l2,
lr_patience=config.lr_patience)
train_sequence_label_batches = [
pack_target(ner_model, train_label_batch, train_mask_batch)
for train_label_batch, train_mask_batch in zip(train_label_batches,
train_mask_batches)
]
logger.info("{} batches expected for training".format(
len(train_token_iv_batches)))
logger.info("")
best_model = None
best_per = float('-inf')
best_loss = float('inf')
train_all_batches = list(
zip(train_token_iv_batches, train_token_ooev_batches, train_char_batches,
train_sequence_label_batches, train_mask_batches))
train_start_time = time.time()
config.label_size = label_dict.size()
config.if_gpu = config.if_gpu and torch.cuda.is_available()
logger.info(config) # print training setting
ner_model = BiRecurrentConvCRF4NestedNER(config.bert_model, config.label_size,
hidden_size=config.hidden_size, layers=config.layers,
lstm_dropout=config.lstm_dropout)
if config.if_gpu:
ner_model = ner_model.cuda()
parameters = filter(lambda p: p.requires_grad, ner_model.parameters())
optimizer, lr_scheduler = create_opt(parameters, config.opt, lr=config.lr, l2=config.l2, lr_patience=config.lr_patience)
train_sequence_label_batches = [pack_target(ner_model, train_label_batch, train_mask_batch)
for train_label_batch, train_mask_batch in zip(train_label_batches, train_mask_batches)]
logger.info("{} batches expected for training".format(len(train_input_ids_batches)))
logger.info("")
best_model = None
best_per = float('-inf')
best_loss = float('inf')
train_all_batches = list(zip(train_input_ids_batches,
train_input_mask_batches,
train_first_sub_tokens_batches,
train_sequence_label_batches,
train_mask_batches))
train_start_time = time.time()
num_batches = len(train_all_batches)