|
--- |
|
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: 2.5792 |
|
- Rouge1: 23.4569 |
|
- Rouge2: 3.8165 |
|
- Rougel: 17.8862 |
|
- Rougelsum: 17.8911 |
|
- Gen Len: 70.52 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 4.4082 | 1.0 | 959 | 4.1636 | 20.1898 | 2.4411 | 15.8204 | 15.8093 | 58.03 | |
|
| 3.5803 | 2.0 | 1918 | 3.7122 | 19.0258 | 2.1105 | 14.6927 | 14.6946 | 55.63 | |
|
| 3.2398 | 3.0 | 2877 | 3.3901 | 22.342 | 2.9157 | 17.4805 | 17.4664 | 59.7 | |
|
| 3.0207 | 4.0 | 3836 | 3.1438 | 21.7114 | 3.184 | 16.7918 | 16.7931 | 65.44 | |
|
| 2.8507 | 5.0 | 4795 | 2.9729 | 20.046 | 2.5204 | 16.3012 | 16.3135 | 55.45 | |
|
| 2.752 | 6.0 | 5754 | 2.8351 | 22.2957 | 3.4475 | 17.148 | 17.1805 | 74.22 | |
|
| 2.6309 | 7.0 | 6713 | 2.7366 | 20.3547 | 2.5414 | 15.6025 | 15.5605 | 62.23 | |
|
| 2.5549 | 8.0 | 7672 | 2.6554 | 23.3943 | 3.8971 | 18.0303 | 18.0104 | 76.83 | |
|
| 2.499 | 9.0 | 8631 | 2.6016 | 22.204 | 3.5576 | 17.2275 | 17.2721 | 81.08 | |
|
| 2.4656 | 10.0 | 9590 | 2.5792 | 23.4569 | 3.8165 | 17.8862 | 17.8911 | 70.52 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
