|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiSD3100 |
|
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. --> |
|
|
|
# wav2GPT2MusiSD3100 |
|
|
|
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: 1.4161 |
|
- Rouge1: 44.7443 |
|
- Rouge2: 17.1312 |
|
- Rougel: 32.345 |
|
- Rougelsum: 32.3028 |
|
- Gen Len: 48.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.8472 | 1.0 | 983 | 2.2487 | 34.6108 | 8.988 | 28.3576 | 28.296 | 28.0 | |
|
| 2.4122 | 2.0 | 1966 | 2.0819 | 32.7125 | 12.0296 | 26.8296 | 26.8069 | 17.0 | |
|
| 2.2629 | 3.0 | 2949 | 1.9330 | 35.1797 | 9.6539 | 29.1791 | 29.1386 | 27.0 | |
|
| 2.1172 | 4.0 | 3932 | 1.8069 | 35.1797 | 9.6539 | 29.1791 | 29.1386 | 27.0 | |
|
| 2.0178 | 5.0 | 4915 | 1.6942 | 31.452 | 9.5377 | 26.3165 | 26.2784 | 38.0 | |
|
| 1.929 | 6.0 | 5898 | 1.6032 | 40.4263 | 13.1411 | 30.9662 | 30.876 | 41.0 | |
|
| 1.8463 | 7.0 | 6881 | 1.5313 | 42.0504 | 14.6769 | 32.1858 | 32.11 | 38.0 | |
|
| 1.7884 | 8.0 | 7864 | 1.4716 | 43.0698 | 14.1014 | 32.5069 | 32.4717 | 38.0 | |
|
| 1.738 | 9.0 | 8847 | 1.4317 | 44.7769 | 17.0917 | 32.2387 | 32.1911 | 48.0 | |
|
| 1.6979 | 10.0 | 9830 | 1.4161 | 44.7443 | 17.1312 | 32.345 | 32.3028 | 48.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
