|
--- |
|
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: 1.4595 |
|
- Rouge1: 46.5222 |
|
- Rouge2: 18.6099 |
|
- Rougel: 33.3774 |
|
- Rougelsum: 33.3798 |
|
- Gen Len: 39.0 |
|
|
|
## 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: 1e-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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.4666 | 1.0 | 983 | 1.8573 | 38.068 | 13.843 | 29.5331 | 29.5373 | 33.0 | |
|
| 2.0055 | 2.0 | 1966 | 1.7201 | 38.0701 | 11.4181 | 30.4599 | 30.4934 | 29.0 | |
|
| 1.8958 | 3.0 | 2949 | 1.6381 | 45.7986 | 18.9877 | 33.2071 | 33.1974 | 43.0 | |
|
| 1.8108 | 4.0 | 3932 | 1.5818 | 37.4842 | 13.0246 | 30.5066 | 30.5385 | 34.0 | |
|
| 1.7778 | 5.0 | 4915 | 1.5410 | 38.3821 | 13.7607 | 30.4166 | 30.4494 | 28.0 | |
|
| 1.7521 | 6.0 | 5898 | 1.5077 | 46.5222 | 18.6099 | 33.3774 | 33.3798 | 39.0 | |
|
| 1.7425 | 7.0 | 6881 | 1.4850 | 43.6827 | 18.3618 | 33.0652 | 33.0676 | 43.0 | |
|
| 1.7455 | 8.0 | 7864 | 1.4682 | 43.6827 | 18.3618 | 33.0652 | 33.0676 | 43.0 | |
|
| 1.7459 | 9.0 | 8847 | 1.4621 | 46.5222 | 18.6099 | 33.3774 | 33.3798 | 39.0 | |
|
| 1.7544 | 10.0 | 9830 | 1.4595 | 46.5222 | 18.6099 | 33.3774 | 33.3798 | 39.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
