What does the 'training loss' mean in machine learning?

Question

I found some sample code on the tensorflow website as follows.

input_fn = tf.contrib.learn.io.numpy_input_fn({"x":x_train}, y_train, batch_size=4, num_epochs=1000)
eval_input_fn = tf.contrib.learn.io.numpy_input_fn({"x":x_eval}, y_eval, batch_size=4, num_epochs=1000)

# We can invoke 1000 training steps by invoking the  method and passing the
# training data set.
estimator.fit(input_fn=input_fn, steps=1000)

# Here we evaluate how well our model did.
train_loss = estimator.evaluate(input_fn=input_fn)
eval_loss = estimator.evaluate(input_fn=eval_input_fn)

print("train loss: %r"% train_loss)
print("eval loss: %r"% eval_loss)

Would you let me know what the 'training loss' means?

Answer 1

Training loss is the loss on training data. Loss is a function that takes the correct output and model output and computes the error between them. The loss is then used to adjust weights based on how big the error was and which elements contributed to it the most.