metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: GPT2_Melody_Generation
results: []
GPT2_Melody_Generation
This model is a fine-tuned version of 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