|
--- |
|
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: 2.1978 |
|
- Rouge1: 43.2017 |
|
- Rouge2: 16.8011 |
|
- Rougel: 28.9318 |
|
- Rougelsum: 28.9902 |
|
- Gen Len: 36.25 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 5.4406 | 1.0 | 983 | 4.3610 | 34.3659 | 11.8654 | 26.2895 | 26.2889 | 22.06 | |
|
| 3.9853 | 2.0 | 1966 | 3.1187 | 43.3423 | 19.8183 | 31.8791 | 31.8738 | 45.21 | |
|
| 3.269 | 3.0 | 2949 | 2.8130 | 38.1887 | 14.2128 | 29.0488 | 29.127 | 28.63 | |
|
| 3.0045 | 4.0 | 3932 | 2.6330 | 37.1625 | 14.669 | 27.8372 | 27.8784 | 27.94 | |
|
| 2.8579 | 5.0 | 4915 | 2.5208 | 41.7213 | 18.5002 | 29.5178 | 29.5437 | 35.87 | |
|
| 2.721 | 6.0 | 5898 | 2.3881 | 41.2077 | 16.757 | 28.387 | 28.4421 | 29.84 | |
|
| 2.6466 | 7.0 | 6881 | 2.3244 | 38.8737 | 14.5737 | 27.2573 | 27.2661 | 32.52 | |
|
| 2.5749 | 8.0 | 7864 | 2.2520 | 41.5266 | 16.128 | 28.4608 | 28.4961 | 34.55 | |
|
| 2.5065 | 9.0 | 8847 | 2.2142 | 44.3673 | 17.3337 | 29.6919 | 29.7362 | 39.92 | |
|
| 2.4872 | 10.0 | 9830 | 2.1978 | 43.2017 | 16.8011 | 28.9318 | 28.9902 | 36.25 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|