|
--- |
|
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: 1.4543 |
|
- Rouge1: 14.9678 |
|
- Rouge2: 2.1649 |
|
- Rougel: 14.4205 |
|
- Rougelsum: 14.4408 |
|
- Gen Len: 64.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.7082 | 1.0 | 959 | 2.5321 | 18.3219 | 2.1594 | 17.0253 | 17.0044 | 82.0 | |
|
| 2.2926 | 2.0 | 1918 | 2.3019 | 17.7317 | 2.1985 | 16.3236 | 16.3132 | 71.0 | |
|
| 2.1349 | 3.0 | 2877 | 2.1208 | 21.6818 | 2.6244 | 19.1082 | 19.0883 | 58.0 | |
|
| 1.9939 | 4.0 | 3836 | 1.9543 | 19.6238 | 2.7829 | 17.8229 | 17.7944 | 72.0 | |
|
| 1.8933 | 5.0 | 4795 | 1.8055 | 17.2105 | 2.0041 | 16.7053 | 16.766 | 46.0 | |
|
| 1.8068 | 6.0 | 5754 | 1.6966 | 14.8562 | 2.0662 | 14.4525 | 14.4841 | 64.0 | |
|
| 1.7375 | 7.0 | 6713 | 1.5950 | 15.0644 | 2.1461 | 14.7203 | 14.7665 | 65.0 | |
|
| 1.6704 | 8.0 | 7672 | 1.5214 | 14.9678 | 2.1649 | 14.4205 | 14.4408 | 64.0 | |
|
| 1.6254 | 9.0 | 8631 | 1.4738 | 14.9678 | 2.1649 | 14.4205 | 14.4408 | 64.0 | |
|
| 1.5941 | 10.0 | 9590 | 1.4543 | 14.9678 | 2.1649 | 14.4205 | 14.4408 | 64.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
