|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiSD3200 |
|
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. --> |
|
|
|
# wav2GPT2MusiSD3200 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0719 |
|
- Rouge1: 26.4817 |
|
- Rouge2: 7.5371 |
|
- Rougel: 20.5034 |
|
- Rougelsum: 20.4753 |
|
- Gen Len: 50.0 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.3142 | 1.0 | 1361 | 1.9011 | 30.4426 | 7.6822 | 22.0685 | 22.0967 | 65.0 | |
|
| 1.9704 | 2.0 | 2722 | 1.6765 | 24.8748 | 5.8724 | 20.797 | 20.7737 | 72.0 | |
|
| 1.8047 | 3.0 | 4083 | 1.5301 | 29.2797 | 7.7402 | 21.8235 | 21.769 | 58.0 | |
|
| 1.666 | 4.0 | 5444 | 1.4232 | 33.1568 | 8.7277 | 23.07 | 23.013 | 81.0 | |
|
| 1.5785 | 5.0 | 6805 | 1.3077 | 28.4221 | 7.6332 | 20.5747 | 20.5799 | 55.0 | |
|
| 1.502 | 6.0 | 8166 | 1.2324 | 27.9706 | 7.7542 | 20.6862 | 20.6696 | 50.0 | |
|
| 1.4354 | 7.0 | 9527 | 1.1675 | 28.7212 | 7.4616 | 21.8892 | 21.8832 | 46.0 | |
|
| 1.3681 | 8.0 | 10888 | 1.1178 | 26.8721 | 7.716 | 20.9267 | 20.9161 | 46.0 | |
|
| 1.3321 | 9.0 | 12249 | 1.0847 | 26.4817 | 7.5371 | 20.5034 | 20.4753 | 50.0 | |
|
| 1.2997 | 10.0 | 13610 | 1.0719 | 26.4817 | 7.5371 | 20.5034 | 20.4753 | 50.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
