model = [LSTMTagger](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module "torch.nn.Module")(EMBEDDING_DIM, HIDDEN_DIM, len(word_to_ix), len(tag_to_ix))
[loss_function](https://docs.pytorch.org/docs/stable/generated/torch.nn.NLLLoss.html#torch.nn.NLLLoss "torch.nn.NLLLoss") = [nn.NLLLoss](https://docs.pytorch.org/docs/stable/generated/torch.nn.NLLLoss.html#torch.nn.NLLLoss "torch.nn.NLLLoss")()
[optimizer](https://docs.pytorch.org/docs/stable/generated/torch.optim.SGD.html#torch.optim.SGD "torch.optim.SGD") = [optim.SGD](https://docs.pytorch.org/docs/stable/generated/torch.optim.SGD.html#torch.optim.SGD "torch.optim.SGD")([model.parameters](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.parameters "torch.nn.Module.parameters")(), lr=0.1)

# See what the scores are before training
# Note that element i,j of the output is the score for tag j for word i.
# Here we don't need to train, so the code is wrapped in torch.no_grad()
with [torch.no_grad](https://docs.pytorch.org/docs/stable/generated/torch.no_grad.html#torch.no_grad "torch.no_grad")():
    [inputs](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = prepare_sequence(training_data[0][0], word_to_ix)
    [tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = model([inputs](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))
    print([tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))

for epoch in range(300):  # again, normally you would NOT do 300 epochs, it is toy data
    for sentence, tags in training_data:
        # Step 1. Remember that Pytorch accumulates gradients.
        # We need to clear them out before each instance
        [model.zero_grad](https://docs.pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.zero_grad "torch.nn.Module.zero_grad")()

        # Step 2. Get our inputs ready for the network, that is, turn them into
        # Tensors of word indices.
        [sentence_in](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = prepare_sequence(sentence, word_to_ix)
        [targets](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = prepare_sequence(tags, tag_to_ix)

        # Step 3. Run our forward pass.
        [tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = model([sentence_in](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))

        # Step 4. Compute the loss, gradients, and update the parameters by
        #  calling optimizer.step()
        [loss](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = [loss_function](https://docs.pytorch.org/docs/stable/generated/torch.nn.NLLLoss.html#torch.nn.NLLLoss "torch.nn.NLLLoss")([tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"), [targets](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))
        [loss.backward](https://docs.pytorch.org/docs/stable/generated/torch.Tensor.backward.html#torch.Tensor.backward "torch.Tensor.backward")()
        [optimizer.step](https://docs.pytorch.org/docs/stable/generated/torch.optim.SGD.html#torch.optim.SGD.step "torch.optim.SGD.step")()

# See what the scores are after training
with [torch.no_grad](https://docs.pytorch.org/docs/stable/generated/torch.no_grad.html#torch.no_grad "torch.no_grad")():
    [inputs](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = prepare_sequence(training_data[0][0], word_to_ix)
    [tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor") = model([inputs](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))

    # The sentence is "the dog ate the apple".  i,j corresponds to score for tag j
    # for word i. The predicted tag is the maximum scoring tag.
    # Here, we can see the predicted sequence below is 0 1 2 0 1
    # since 0 is index of the maximum value of row 1,
    # 1 is the index of maximum value of row 2, etc.
    # Which is DET NOUN VERB DET NOUN, the correct sequence!
    print([tag_scores](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "torch.Tensor"))