|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiNewStricD3E20 |
|
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. --> |
|
|
|
# wav2GPT2MusiNewStricD3E20 |
|
|
|
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: 1.1798 |
|
- Rouge1: 42.718 |
|
- Rouge2: 15.0335 |
|
- Rougel: 31.8817 |
|
- Rougelsum: 31.9212 |
|
- Gen Len: 43.0 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.5878 | 1.0 | 1965 | 2.1959 | 41.9136 | 15.4521 | 29.7881 | 29.7614 | 31.0 | |
|
| 2.3482 | 2.0 | 3930 | 1.9855 | 40.4721 | 16.569 | 31.6934 | 31.7144 | 38.0 | |
|
| 2.1654 | 3.0 | 5895 | 1.8376 | 41.8598 | 14.9311 | 30.3721 | 30.3997 | 34.0 | |
|
| 2.0384 | 4.0 | 7860 | 1.6717 | 42.5698 | 14.1943 | 31.615 | 31.654 | 33.0 | |
|
| 1.8891 | 5.0 | 9825 | 1.5404 | 39.8572 | 14.4559 | 30.1631 | 30.1786 | 41.0 | |
|
| 1.7814 | 6.0 | 11790 | 1.4242 | 35.0971 | 11.2726 | 28.6884 | 28.6569 | 27.0 | |
|
| 1.6694 | 7.0 | 13755 | 1.3285 | 44.2173 | 15.6466 | 31.3753 | 31.3925 | 36.0 | |
|
| 1.5879 | 8.0 | 15720 | 1.2541 | 43.807 | 14.9798 | 31.8325 | 31.8513 | 43.0 | |
|
| 1.5305 | 9.0 | 17685 | 1.2066 | 42.3866 | 14.1488 | 32.1651 | 32.2115 | 39.0 | |
|
| 1.4758 | 10.0 | 19650 | 1.1798 | 42.718 | 15.0335 | 31.8817 | 31.9212 | 43.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|