|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: hubert2BertMusic100 |
|
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. --> |
|
|
|
# hubert2BertMusic100 |
|
|
|
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: 1.5608 |
|
- Rouge1: 26.8788 |
|
- Rouge2: 7.7875 |
|
- Rougel: 19.0867 |
|
- Rougelsum: 19.0059 |
|
- Gen Len: 52.68 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 3.184 | 1.0 | 1361 | 2.6115 | 25.0008 | 7.7596 | 19.0824 | 19.0223 | 46.0 | |
|
| 2.5657 | 2.0 | 2722 | 2.2430 | 25.4109 | 4.9388 | 18.851 | 18.8614 | 52.19 | |
|
| 2.3496 | 3.0 | 4083 | 2.0430 | 26.517 | 7.6506 | 18.9172 | 18.8696 | 56.45 | |
|
| 2.2011 | 4.0 | 5444 | 1.9079 | 27.1096 | 7.7201 | 19.2615 | 19.2315 | 52.62 | |
|
| 2.1264 | 5.0 | 6805 | 1.8010 | 25.8208 | 6.5427 | 18.2762 | 18.2818 | 56.84 | |
|
| 1.9913 | 6.0 | 8166 | 1.7185 | 32.4549 | 8.4658 | 22.9767 | 22.9609 | 67.77 | |
|
| 1.9133 | 7.0 | 9527 | 1.6602 | 26.8271 | 7.4957 | 19.093 | 19.0392 | 50.07 | |
|
| 1.8605 | 8.0 | 10888 | 1.6075 | 29.8012 | 8.5321 | 21.3029 | 21.2936 | 63.94 | |
|
| 1.8227 | 9.0 | 12249 | 1.5714 | 27.1868 | 7.8113 | 19.1224 | 19.0768 | 57.59 | |
|
| 1.7965 | 10.0 | 13610 | 1.5608 | 26.8788 | 7.7875 | 19.0867 | 19.0059 | 52.68 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
