|
--- |
|
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: 1.4619 |
|
- Rouge1: 19.2446 |
|
- Rouge2: 2.6708 |
|
- Rougel: 17.8027 |
|
- Rougelsum: 17.766 |
|
- Gen Len: 76.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.7069 | 1.0 | 959 | 2.5357 | 18.3668 | 2.1635 | 17.0926 | 17.0433 | 82.0 | |
|
| 2.2934 | 2.0 | 1918 | 2.3074 | 17.0518 | 2.1435 | 16.0006 | 15.9772 | 70.0 | |
|
| 2.1363 | 3.0 | 2877 | 2.1253 | 17.2075 | 2.008 | 16.8224 | 16.7772 | 46.0 | |
|
| 1.9919 | 4.0 | 3836 | 1.9537 | 17.9258 | 2.0952 | 16.7574 | 16.6999 | 88.0 | |
|
| 1.8915 | 5.0 | 4795 | 1.8144 | 17.2075 | 2.008 | 16.8224 | 16.7772 | 46.0 | |
|
| 1.8069 | 6.0 | 5754 | 1.6979 | 15.9274 | 2.3889 | 15.2764 | 15.2325 | 64.0 | |
|
| 1.7355 | 7.0 | 6713 | 1.5992 | 19.2446 | 2.6708 | 17.8027 | 17.766 | 76.0 | |
|
| 1.6694 | 8.0 | 7672 | 1.5291 | 19.2446 | 2.6708 | 17.8027 | 17.766 | 76.0 | |
|
| 1.6216 | 9.0 | 8631 | 1.4830 | 19.2446 | 2.6708 | 17.8027 | 17.766 | 76.0 | |
|
| 1.5901 | 10.0 | 9590 | 1.4619 | 19.2446 | 2.6708 | 17.8027 | 17.766 | 76.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|