|
|
--- |
|
|
license: mit |
|
|
base_model: gpt2 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: GPT2_Melody_Generation |
|
|
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. --> |
|
|
|
|
|
# GPT2_Melody_Generation |
|
|
|
|
|
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.3371 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 0.0005 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 1 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.01 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 3.7492 | 0.1 | 1000 | 2.8906 | |
|
|
| 2.6238 | 0.2 | 2000 | 2.2064 | |
|
|
| 2.1078 | 0.3 | 3000 | 1.8105 | |
|
|
| 1.8152 | 0.4 | 4000 | 1.6067 | |
|
|
| 1.6536 | 0.5 | 5000 | 1.4950 | |
|
|
| 1.5477 | 0.6 | 6000 | 1.4357 | |
|
|
| 1.4832 | 0.7 | 7000 | 1.3807 | |
|
|
| 1.4452 | 0.8 | 8000 | 1.3487 | |
|
|
| 1.4172 | 0.9 | 9000 | 1.3371 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.32.1 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.2 |
|
|
|
