Update README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 base_model: gpt2
 tags:
 - generated_from_trainer
@@ -8,29 +7,53 @@ model-index:
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # midi_model_3
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the js-fakes-4bars dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5542
 
 ## Model description
 
-More information needed
+This model generates encoded midi that follows the format of jsfakes chorales.
+This representation enables the ability to train traditional language models on midi data.
+Also see Magenta [here](https://github.com/magenta/note-seq).
 
 ## Intended uses & limitations
 
-More information needed
+For generating basic encoded midi in the jsfakes style, as a proof of concept.
+This model is very limited, and shows the ability to train and host this kind of model completely free.
 
 ## Training and evaluation data
 
-More information needed
+This model is trained on the js-fakes-4bars dataset, which is a tokenized version of the JS-Fakes dataset by Omar Peracha.
+
+- Link to the original datset [here](https://github.com/omarperacha/js-fakes)
+- Link to the tokenized dataset [here](https://huggingface.co/datasets/TristanBehrens/js-fakes-4bars)
+- Training set is 4.02k rows
+- Test set is 463 rows
+
+The data encodes midi information as encoded text. Here are some examples of what the data looks like:
+
+- PIECE_START (The start of the midi.)
+- PIECE_END (The end of the midi.)
+- STYLE=JSFAKES (A style tag, which is unused in this dataset.)
+- GENRE=JSFAKES (A genre tag, also unused in this dataset.)
+- TRACK_START (The start of an instrument's track.)
+- TRACK_END (The end of an instrument's track.)
+- INST=48 (The instrument the notes will belong to.)
+- BAR_START (The start of a musical measure.)
+- BAR_END (the end of a musical measure.)
+- NOTE_ON=57 (Specifies the note that will start.)
+- NOTE_OFF=57 (Specifies the note that will end.)
+- TIME_DELTA=4 (How long the note plays for.)
 
 ## Training procedure
 
+Training was done through Google Colab's free tier, using a single 15GB Tesla T4 GPU.
+Training was logged through Weights and Biases.
+A link to the full training notebook can be found [here] (https://colab.research.google.com/drive/1uvv-ChthIrmEJMBOVyL7mTm4dcf4QZq7#scrollTo=34kpyWSnaJE1)
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -43,6 +66,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.01
 - num_epochs: 10
 
+### Training Statistics
+
+- Total training runtime: 787 seconds (around 13 minutes)
+- Training samples per second: 45.91
+- Training steps per second: 11.484
+- Average GPU watt usage: 66W
+- Average GPU temperature: 77C
+
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
@@ -84,4 +115,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu118
 - Datasets 2.15.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0