|
--- |
|
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: 4.5551 |
|
- Rouge1: 26.6611 |
|
- Rouge2: 5.852 |
|
- Rougel: 20.3973 |
|
- Rougelsum: 20.4079 |
|
- Gen Len: 56.63 |
|
|
|
## 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-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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 5.298 | 1.0 | 959 | 5.1337 | 27.155 | 5.4713 | 20.6012 | 20.5867 | 61.39 | |
|
| 4.6449 | 2.0 | 1918 | 4.8458 | 27.9626 | 6.2825 | 21.4129 | 21.4275 | 55.85 | |
|
| 4.4099 | 3.0 | 2877 | 4.6840 | 26.9532 | 5.7634 | 20.6746 | 20.6841 | 57.92 | |
|
| 4.2794 | 4.0 | 3836 | 4.5906 | 26.7541 | 5.9512 | 20.5233 | 20.5886 | 55.42 | |
|
| 4.1952 | 5.0 | 4795 | 4.5551 | 26.6611 | 5.852 | 20.3973 | 20.4079 | 56.63 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|