|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: hubert2BertMusicwithNewS10 |
|
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. --> |
|
|
|
# hubert2BertMusicwithNewS10 |
|
|
|
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: 2.9734 |
|
- Rouge1: 23.9184 |
|
- Rouge2: 7.161 |
|
- Rougel: 18.3653 |
|
- Rougelsum: 18.3289 |
|
- Gen Len: 45.86 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 4.3541 | 1.0 | 1361 | 3.7286 | 31.3443 | 8.5461 | 22.9152 | 22.8633 | 44.4 | |
|
| 3.6252 | 2.0 | 2722 | 3.2950 | 25.3846 | 6.7268 | 19.4638 | 19.3924 | 40.12 | |
|
| 3.3709 | 3.0 | 4083 | 3.1073 | 26.3761 | 7.1947 | 19.4663 | 19.4253 | 44.76 | |
|
| 3.2605 | 4.0 | 5444 | 3.0024 | 23.8355 | 7.1978 | 18.3755 | 18.3194 | 45.61 | |
|
| 3.2417 | 5.0 | 6805 | 2.9734 | 23.9184 | 7.161 | 18.3653 | 18.3289 | 45.86 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
