|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: hubert2BertMusic200 |
|
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. --> |
|
|
|
# hubert2BertMusic200 |
|
|
|
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: 1.5337 |
|
- Rouge1: 27.8124 |
|
- Rouge2: 8.0272 |
|
- Rougel: 20.1961 |
|
- Rougelsum: 20.0449 |
|
- Gen Len: 54.14 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 3.1541 | 1.0 | 1361 | 2.5808 | 26.8953 | 7.7532 | 20.2501 | 20.2057 | 48.0 | |
|
| 2.5425 | 2.0 | 2722 | 2.2246 | 22.0654 | 4.9919 | 18.3845 | 18.4076 | 25.9 | |
|
| 2.3282 | 3.0 | 4083 | 2.0100 | 31.8203 | 9.3519 | 22.4246 | 22.4174 | 78.89 | |
|
| 2.1766 | 4.0 | 5444 | 1.8790 | 27.1112 | 7.992 | 19.3218 | 19.1906 | 55.62 | |
|
| 2.1055 | 5.0 | 6805 | 1.7752 | 25.9685 | 7.9938 | 19.3583 | 19.2774 | 54.62 | |
|
| 1.9703 | 6.0 | 8166 | 1.6945 | 32.9795 | 9.0072 | 23.469 | 23.4519 | 72.38 | |
|
| 1.8918 | 7.0 | 9527 | 1.6316 | 26.8437 | 7.4896 | 19.49 | 19.4321 | 56.75 | |
|
| 1.8299 | 8.0 | 10888 | 1.5808 | 26.9448 | 7.5496 | 19.4471 | 19.3467 | 55.21 | |
|
| 1.7917 | 9.0 | 12249 | 1.5466 | 27.0708 | 7.759 | 19.7133 | 19.6295 | 56.2 | |
|
| 1.767 | 10.0 | 13610 | 1.5337 | 27.8124 | 8.0272 | 20.1961 | 20.0449 | 54.14 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|