Update README file - Epocj 8

README.md

@@ -1,52 +1,69 @@
 ---
 tags:
 - generated_from_keras_callback
+- music
 model-index:
 - name: juancopi81/mutopia_guitar_mmm
   results: []
+datasets:
+- juancopi81/mutopia_guitar_dataset
+widget:
+- text: "PIECE_START TIME_SIGNATURE=4_4 BPM=90 TRACK_START INST=0 DENSITY=2 BAR_START NOTE_ON=43"
+  example_title: "Time signature 4/4, BPM=90, NOTE=G2"
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
-
 # juancopi81/mutopia_guitar_mmm
 
-This model was trained from scratch on an unknown dataset.
+Music generation could be approached similarly to language generation. There are many ways to represent music as text and then use a language model to create a model capable of music generation. For encoding MIDI files as text, I am using the excellent [implementation](https://github.com/AI-Guru/MMM-JSB) of Dr. Tristan Beheren of the paper: [MMM: Exploring Conditional Multi-Track Music Generation with the Transformer](https://arxiv.org/abs/2008.06048).
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the [Mutopia Guitar Dataset](https://huggingface.co/datasets/juancopi81/mutopia_guitar_dataset). Use the widget to generate your piece, and then use [this notebook](https://colab.research.google.com/drive/14vlJwCvDmNH6SFfVuYY0Y18qTbaHEJCY?usp=sharing) to listen to the results (work in progress). 
+I created the notebook as an adaptation of [the one created by Dr. Tristan Behrens](https://huggingface.co/TristanBehrens/js-fakes-4bars).
+
 It achieves the following results on the evaluation set:
 - Train Loss: 0.5837
 - Validation Loss: 1.5346
-- Epoch: 0
 
 ## Model description
 
-More information needed
+The model is GPT-2 loaded with the GPT2LMHeadModel architecture from Hugging Face. The context size is 256, and the vocabulary size is 588. The model uses a 
+`WhitespaceSplit` pre-tokenizer. The [tokenizer](https://huggingface.co/juancopi81/mutopia_guitar_dataset_tokenizer) is also in the Hugging Face hub. 
 
 ## Intended uses & limitations
 
-More information needed
+I built this model to learn more about how to use Hugging Face. I am implementing some of the parts of the [Hugging Face course](https://huggingface.co/course/chapter1/1) with a project that I find interesting. 
+The main intention of this model is educational. I am creating a [series of notebooks](https://github.com/juancopi81/MMM_Mutopia_Guitar) where I show every step of the process:
+- Collecting the data
+- Pre-processing the data
+- Training a tokenizer from scratch
+- Fine-tuning a GPT-2 model
+- Building a Gradio app for the model
 
-## Training and evaluation data
+I trained the model using the free version of Colab with a small dataset. Right now, it is heavily overfitting. My idea is to have a more extensive dataset of Guitar Music from Latinoamerica to train a new model similar to the Mutopia Guitar Model, using more GPU resources.
 
-More information needed
+## Training and evaluation data
 
-## Training procedure
+I am training the model with [Mutopia Guitar Dataset](https://huggingface.co/datasets/juancopi81/mutopia_guitar_dataset). This dataset consists of the soloist guitar pieces of the [Mutopia Project](https://www.mutopiaproject.org/). 
+The dataset mainly contains guitar music from western classical composers, such as Sor, Aguado, Carcassi, and Giuliani.
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-07, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-07, 'decay_steps': 2363, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 9089, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: mixed_float16
-
 ### Training results
-
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.5837     | 1.5346          | 0     |
-
+| 1.0705     | 1.3590          | 0     |
+| 0.8889     | 1.3702          | 1     |
+| 0.7588     | 1.3974          | 2     |
+| 0.7294     | 1.4813          | 3     |
+| 0.6263     | 1.5263          | 5     |
+| 0.5841     | 1.5263          | 6     |
+| 0.5844     | 1.5263          | 7     |
+| 0.5837     | 1.5346         | 8     |
 
 ### Framework versions
-
-- Transformers 4.22.0
+- Transformers 4.21.3
 - TensorFlow 2.8.2
 - Datasets 2.4.0
 - Tokenizers 0.12.1