# step 3. compute the accuracy
acc_batch = helper.compute_accuracy(y_pred, batch_dict["y_target"])
running_acc += (acc_batch - running_acc) / (batch_index + 1)
# update val_bar
val_bar.set_postfix(loss=running_loss,
acc=running_acc,
epoch=epoch_index)
val_bar.update()
train_state["val_loss"].append(running_loss)
train_state["val_acc"].append(running_acc)
train_state = helper.update_train_state(args=args,
model=classifier,
train_state=train_state)
scheduler.step(train_state["val_loss"][-1])
train_bar.n = 0
val_bar.n = 0
epoch_bar.update()
if train_state["stop_early"]:
break
train_bar.n = 0
val_bar.n = 0
epoch_bar.update()
print(f"Epoch {epoch_index + 1}")
running_loss += (loss.item() - running_loss) / (batch_index + 1)
acc_t = helper.compute_accuracy(y_pred, batch_dict["y_target"], mask_index)
running_acc += (acc_t - running_acc) / (batch_index + 1)
val_bar.set_postfix(loss=running_loss,
acc=running_acc,
epoch=epoch_index)
val_bar.update()
train_state["val_loss"].append(running_loss)
train_state["val_acc"].append(running_acc)
train_state = helper.update_train_state(args=args,
model=model,
train_state=train_state)
scheduler.step(train_state["val_loss"][-1])
if train_state["stop_early"]:
break
train_bar.n = 0
val_bar.n = 0
epoch_bar.set_postfix(best_val=train_state["early_stopping_best_val"])
epoch_bar.update()
print(f"Epoch {epoch_index}:")
print(f"\ttrain_loss = {train_state['train_loss'][-1]}, train_acc = {train_state['train_acc'][-1]}")