|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: gpt2pac |
|
|
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. --> |
|
|
|
|
|
# gpt2pac |
|
|
|
|
|
This model was created by finetuning [GPT-2-xl](https://huggingface.co/gpt2-xl) on the lyrics of 824 Tupac Shakur songs from [https://lyrics.az/2pac/allsongs.html](https://lyrics.az/2pac/allsongs.html). |
|
|
|
|
|
## data |
|
|
|
|
|
All unfiltered data from [https://lyrics.az/2pac/allsongs.html](https://lyrics.az/2pac/allsongs.html) are in [2pac_lyrics.json](https://huggingface.co/stecas/gpt2pac/blob/main/2pac_lyrics.json). However, I filtered some of these out of the model's training data because they were too short, not songs, etc. |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 0.0001 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.2 |
|
|
- Pytorch 2.0.1+cu117 |
|
|
- Datasets 2.13.1 |
|
|
- Tokenizers 0.13.3 |
|
|
|
