optimizer_grouped_parameters = [
{'params': [p for n, p in model.named_parameters() if
not any(nd in n for nd in no_decay) and p.requires_grad],
'weight_decay': config['model']['weight_decay']},
{'params': [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay) and p.requires_grad],
'weight_decay': 0.0}
]
optimizer = AdamW(optimizer_grouped_parameters, lr=config['model']['learning_rate'],
eps=config['model']['adam_epsilon'])
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=config['model']['warmup_steps'],
num_training_steps=config['model']['max_step'])
else:
for n, p in model.named_parameters():
if 'bert' in n:
p.requires_grad = False
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()),
lr=config['model']['learning_rate'])
for name, param in model.named_parameters():
print(name, param.shape, param.device, param.requires_grad)
max_step = config['model']['max_step']
check_step = config['model']['check_step']
batch_size = config['model']['batch_size']
model.zero_grad()
train_slot_loss, train_intent_loss = 0, 0
best_val_f1 = 0.
writer.add_text('config', json.dumps(config))
for step in range(1, max_step + 1):
'weight_decay':
0.0
}]
optimizer = AdamW(optimizer_grouped_parameters,
lr=config['model']['learning_rate'],
eps=config['model']['adam_epsilon'])
scheduler = WarmupLinearSchedule(
optimizer,
warmup_steps=config['model']['warmup_steps'],
t_total=config['model']['max_step'])
else:
for n, p in model.named_parameters():
if 'bert' in n:
p.requires_grad = False
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=config['model']['learning_rate'])
for name, param in model.named_parameters():
print(name, param.shape, param.device, param.requires_grad)
max_step = config['model']['max_step']
check_step = config['model']['check_step']
batch_size = config['model']['batch_size']
model.zero_grad()
set_seed(config['seed'])
train_slot_loss, train_intent_loss = 0, 0
best_val_f1 = 0.
writer.add_text('config', json.dumps(config))