|
--- |
|
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: 4.4139 |
|
- Rouge1: 24.3794 |
|
- Rouge2: 4.9412 |
|
- Rougel: 19.205 |
|
- Rougelsum: 19.2107 |
|
- Gen Len: 51.16 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 4.4454 | 1.0 | 959 | 4.6265 | 24.4595 | 4.7745 | 19.2604 | 19.2988 | 57.33 | |
|
| 4.1901 | 2.0 | 1918 | 4.5567 | 24.5473 | 4.7264 | 18.9617 | 18.9986 | 53.44 | |
|
| 4.1365 | 3.0 | 2877 | 4.5116 | 24.6373 | 4.3808 | 19.1493 | 19.1806 | 54.87 | |
|
| 4.1127 | 4.0 | 3836 | 4.4887 | 23.9718 | 4.6223 | 18.9014 | 18.9082 | 51.74 | |
|
| 4.0897 | 5.0 | 4795 | 4.4625 | 24.0425 | 4.5823 | 18.9648 | 18.9859 | 51.82 | |
|
| 4.1068 | 6.0 | 5754 | 4.4463 | 24.2117 | 4.6975 | 19.0849 | 19.0801 | 52.0 | |
|
| 4.0648 | 7.0 | 6713 | 4.4291 | 24.9063 | 4.9874 | 19.525 | 19.5332 | 51.54 | |
|
| 4.0609 | 8.0 | 7672 | 4.4235 | 24.6819 | 4.9386 | 19.4017 | 19.4192 | 51.44 | |
|
| 4.0465 | 9.0 | 8631 | 4.4159 | 24.7269 | 4.9681 | 19.2497 | 19.2745 | 51.34 | |
|
| 4.0713 | 10.0 | 9590 | 4.4139 | 24.3794 | 4.9412 | 19.205 | 19.2107 | 51.16 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|