|
--- |
|
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: 2.9826 |
|
- Rouge1: 41.7849 |
|
- Rouge2: 16.827 |
|
- Rougel: 30.2876 |
|
- Rougelsum: 30.3452 |
|
- Gen Len: 33.09 |
|
|
|
## 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-06 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 3.934 | 1.0 | 983 | 3.2674 | 39.1931 | 15.4549 | 29.0372 | 29.0798 | 33.06 | |
|
| 3.4613 | 2.0 | 1966 | 3.1359 | 39.1184 | 16.7176 | 30.4367 | 30.485 | 30.61 | |
|
| 3.3732 | 3.0 | 2949 | 3.0870 | 37.745 | 15.4165 | 29.4667 | 29.4787 | 28.73 | |
|
| 3.3173 | 4.0 | 3932 | 3.0563 | 42.9662 | 18.0767 | 31.2519 | 31.3076 | 33.5 | |
|
| 3.308 | 5.0 | 4915 | 3.0260 | 42.4731 | 17.6266 | 30.6927 | 30.7491 | 33.75 | |
|
| 3.2768 | 6.0 | 5898 | 3.0119 | 41.9782 | 17.0076 | 30.2951 | 30.3719 | 33.35 | |
|
| 3.2744 | 7.0 | 6881 | 2.9986 | 42.209 | 17.1482 | 30.7224 | 30.7751 | 33.41 | |
|
| 3.2581 | 8.0 | 7864 | 2.9907 | 42.1508 | 17.2078 | 30.638 | 30.7119 | 33.24 | |
|
| 3.236 | 9.0 | 8847 | 2.9853 | 41.8212 | 17.0602 | 30.3253 | 30.3585 | 33.08 | |
|
| 3.2526 | 10.0 | 9830 | 2.9826 | 41.7849 | 16.827 | 30.2876 | 30.3452 | 33.09 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|