|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiNewStricD3E5 |
|
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. --> |
|
|
|
# wav2GPT2MusiNewStricD3E5 |
|
|
|
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: 1.9268 |
|
- Rouge1: 31.1418 |
|
- Rouge2: 9.8004 |
|
- Rougel: 23.2508 |
|
- Rougelsum: 23.2708 |
|
- Gen Len: 64.93 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.6001 | 1.0 | 1361 | 2.2566 | 22.0988 | 6.1329 | 16.1614 | 16.1192 | 87.75 | |
|
| 2.3044 | 2.0 | 2722 | 2.0828 | 26.1764 | 8.6856 | 19.2354 | 19.1702 | 74.46 | |
|
| 2.1894 | 3.0 | 4083 | 1.9912 | 29.7982 | 9.264 | 22.2165 | 22.193 | 67.71 | |
|
| 2.119 | 4.0 | 5444 | 1.9419 | 30.1668 | 9.2004 | 22.5359 | 22.5969 | 63.31 | |
|
| 2.0963 | 5.0 | 6805 | 1.9268 | 31.1418 | 9.8004 | 23.2508 | 23.2708 | 64.93 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|