|
--- |
|
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: 1.0695 |
|
- Rouge1: 27.535 |
|
- Rouge2: 6.4489 |
|
- Rougel: 21.3553 |
|
- Rougelsum: 21.3149 |
|
- Gen Len: 62.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.3153 | 1.0 | 1361 | 1.8998 | 28.933 | 7.6448 | 21.3837 | 21.3322 | 70.0 | |
|
| 1.9693 | 2.0 | 2722 | 1.6823 | 21.1663 | 4.9059 | 18.2626 | 18.2806 | 65.0 | |
|
| 1.8035 | 3.0 | 4083 | 1.5310 | 30.8905 | 9.1528 | 22.7768 | 22.7103 | 89.0 | |
|
| 1.6632 | 4.0 | 5444 | 1.4205 | 31.8655 | 7.8167 | 22.7573 | 22.7116 | 66.0 | |
|
| 1.5764 | 5.0 | 6805 | 1.3066 | 29.913 | 7.5342 | 21.2873 | 21.2554 | 62.0 | |
|
| 1.5009 | 6.0 | 8166 | 1.2299 | 30.9454 | 8.005 | 22.3495 | 22.2846 | 63.0 | |
|
| 1.4331 | 7.0 | 9527 | 1.1677 | 28.1694 | 6.8177 | 21.7434 | 21.703 | 55.0 | |
|
| 1.3667 | 8.0 | 10888 | 1.1135 | 28.1109 | 6.7004 | 21.4423 | 21.3734 | 51.0 | |
|
| 1.3285 | 9.0 | 12249 | 1.0826 | 27.6524 | 8.0724 | 21.2241 | 21.1558 | 49.0 | |
|
| 1.2996 | 10.0 | 13610 | 1.0695 | 27.535 | 6.4489 | 21.3553 | 21.3149 | 62.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|