def train_for_epoch(parser, train_data, dev_data, optimizer, loss_func,
batch_size):
""" Train the neural dependency parser for single epoch.
@parser (Parser): Neural Dependency Parser
@train_data ():
@dev_data ():
@optimizer (nn.Optimizer): Adam Optimizer
@loss_func (nn.CrossEntropyLoss): Cross Entropy Loss Function
@batch_size (int): batch size
@return dev_UAS (float): Unlabeled Attachment Score (UAS) for dev data
"""
parser.model.train() # In "train" mode
n_minibatches = math.ceil(len(train_data) / batch_size)
loss_meter = AverageMeter()
with tqdm(total=(n_minibatches)) as prog:
for i, (train_x,
train_y) in enumerate(minibatches(train_data, batch_size)):
optimizer.zero_grad()
loss = 0.0 # store loss
train_x = torch.from_numpy(train_x).long()
train_y = torch.from_numpy(train_y.nonzero()[1]).long()
logits = parser.model.forward(train_x)
loss = loss_func(logits, train_y)
loss.backward()
optimizer.step()
prog.update(1)
loss_meter.update(loss.item())
print("Average Train Loss: {}".format(loss_meter.avg))
print("Evaluating on dev set", )
parser.model.eval() # "eval" mode
dev_UAS, _ = parser.parse(dev_data)
print("- dev UAS: {:.2f}".format(dev_UAS * 100.0))
return dev_UAS
def train_for_epoch(parser, train_data, dev_data, optimizer, loss_func, batch_size):
""" Train the neural dependency parser for single epoch.
Note: In PyTorch we can signify train versus test and automatically have
the Dropout Layer applied and removed, accordingly, by specifying
whether we are training, `model.train()`, or evaluating, `model.eval()`
@param parser (Parser): Neural Dependency Parser
@param train_data ():
@param dev_data ():
@param optimizer (nn.Optimizer): Adam Optimizer
@param loss_func (nn.CrossEntropyLoss): Cross Entropy Loss Function
@param batch_size (int): batch size
@param lr (float): learning rate
@return dev_UAS (float): Unlabeled Attachment Score (UAS) for dev data
"""
parser.model.train() # Places model in "train" mode, i.e. apply dropout layer
n_minibatches = math.ceil(len(train_data) / batch_size)
loss_meter = AverageMeter()
with tqdm(total=(n_minibatches)) as prog:
for i, (train_x, train_y) in enumerate(minibatches(train_data, batch_size)):
optimizer.zero_grad() # remove any baggage in the optimizer
loss = 0. # store loss for this batch here
train_x = torch.from_numpy(train_x).long()
train_y = torch.from_numpy(train_y.nonzero()[1]).long()
### YOUR CODE HERE (~5-10 lines)
### TODO:
### 1) Run train_x forward through model to produce `logits`
### 2) Use the `loss_func` parameter to apply the PyTorch CrossEntropyLoss function.
### This will take `logits` and `train_y` as inputs. It will output the CrossEntropyLoss
### between softmax(`logits`) and `train_y`. Remember that softmax(`logits`)
### are the predictions (y^ from the PDF).
### 3) Backprop losses
### 4) Take step with the optimizer
### Please see the following docs for support:
### Optimizer Step: https://pytorch.org/docs/stable/optim.html#optimizer-step
logits = parser.model.forward(train_x)
loss = loss_func(logits, train_y)
loss.backward()
optimizer.step()
prog.update(1)
loss_meter.update(loss.item())
### END YOUR CODE
prog.update(1)
loss_meter.update(loss.item())
print ("Average Train Loss: {}".format(loss_meter.avg))
print("Evaluating on dev set",)
parser.model.eval() # Places model in "eval" mode, i.e. don't apply dropout layer
dev_UAS, _ = parser.parse(dev_data)
print("- dev UAS: {:.2f}".format(dev_UAS * 100.0))
return dev_UAS
