|
--- |
|
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: 1.4136 |
|
- Rouge1: 18.3305 |
|
- Rouge2: 2.3398 |
|
- Rougel: 16.1355 |
|
- Rougelsum: 16.0889 |
|
- Gen Len: 68.0 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 1.9475 | 1.0 | 959 | 1.7999 | 21.7144 | 2.959 | 19.633 | 19.6005 | 63.0 | |
|
| 1.7055 | 2.0 | 1918 | 1.6840 | 21.3721 | 2.9057 | 19.166 | 19.142 | 61.0 | |
|
| 1.6262 | 3.0 | 2877 | 1.6052 | 19.3952 | 2.692 | 17.8213 | 17.7863 | 76.0 | |
|
| 1.5601 | 4.0 | 3836 | 1.5495 | 18.0278 | 2.2993 | 16.1559 | 16.1154 | 68.0 | |
|
| 1.5354 | 5.0 | 4795 | 1.4992 | 18.1503 | 2.1188 | 15.9452 | 15.9245 | 62.0 | |
|
| 1.5294 | 6.0 | 5754 | 1.4659 | 18.0278 | 2.2993 | 16.1559 | 16.1154 | 68.0 | |
|
| 1.5278 | 7.0 | 6713 | 1.4371 | 16.5149 | 2.4707 | 15.8236 | 15.7624 | 60.0 | |
|
| 1.5306 | 8.0 | 7672 | 1.4223 | 18.7176 | 2.4645 | 16.5148 | 16.4705 | 62.0 | |
|
| 1.5477 | 9.0 | 8631 | 1.4148 | 18.3305 | 2.3398 | 16.1355 | 16.0889 | 68.0 | |
|
| 1.5722 | 10.0 | 9590 | 1.4136 | 18.3305 | 2.3398 | 16.1355 | 16.0889 | 68.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|