|
--- |
|
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: 0.9236 |
|
- Rouge1: 28.7212 |
|
- Rouge2: 7.4616 |
|
- Rougel: 21.8892 |
|
- Rougelsum: 21.8832 |
|
- Gen Len: 46.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 1.2945 | 1.0 | 1361 | 1.1031 | 27.9697 | 6.7041 | 21.6712 | 21.6064 | 55.0 | |
|
| 1.212 | 2.0 | 2722 | 1.0544 | 27.9697 | 6.7041 | 21.6712 | 21.6064 | 55.0 | |
|
| 1.1771 | 3.0 | 4083 | 1.0171 | 27.7311 | 6.574 | 21.4759 | 21.4402 | 57.0 | |
|
| 1.124 | 4.0 | 5444 | 0.9856 | 30.3958 | 7.6795 | 22.3852 | 22.4201 | 62.0 | |
|
| 1.1177 | 5.0 | 6805 | 0.9591 | 30.2957 | 8.1085 | 22.6405 | 22.5926 | 50.0 | |
|
| 1.1168 | 6.0 | 8166 | 0.9419 | 27.9697 | 6.7041 | 21.6712 | 21.6064 | 55.0 | |
|
| 1.1277 | 7.0 | 9527 | 0.9304 | 27.9697 | 6.7041 | 21.6712 | 21.6064 | 55.0 | |
|
| 1.1256 | 8.0 | 10888 | 0.9227 | 29.7298 | 7.2318 | 22.3598 | 22.3739 | 56.0 | |
|
| 1.1617 | 9.0 | 12249 | 0.9222 | 28.7212 | 7.4616 | 21.8892 | 21.8832 | 46.0 | |
|
| 1.2002 | 10.0 | 13610 | 0.9236 | 28.7212 | 7.4616 | 21.8892 | 21.8832 | 46.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
