Hi, the code runs smoothly, but kernel with unit tests runs forever; I’m also getting Learner Error: Grader timed out after submitting it
Do you have any idea why following code could cause this?
bare_train_generator = data_generator(batch_size=2, max_length=10, data_lines=lines)
infinite_train_generator = itertools.cycle(bare_train_generator)
bare_eval_generator = data_generator(batch_size=2, max_length=10, data_lines=lines)
infinite_eval_generator = itertools.cycle(bare_eval_generator)
train_task = training.TrainTask(
labeled_data=infinite_train_generator, # Use infinite train data generator
loss_layer= tl.CrossEntropyLoss(), # Don't forget to instantiate this object
optimizer=trax.optimizers.Adam(learning_rate = 0.0005) # Don't forget to add the learning rate parameter TO 0.0005
)
eval_task = training.EvalTask(
labeled_data=infinite_eval_generator, # Use infinite eval data generator
metrics=[tl.CrossEntropyLoss() , tl.Accuracy()], # Don't forget to instantiate these objects
n_eval_batches=3 # For better evaluation accuracy in reasonable time
)
training_loop = training.Loop(model,
train_task,
eval_tasks=[eval_task],
output_dir=output_dir)
training_loop.run(n_steps=n_steps)
### END CODE HERE ###
# We return this because it contains a handle to the model, which has the weights etc.
return training_loop