|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiSD3100 |
|
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. --> |
|
|
|
# wav2GPT2MusiSD3100 |
|
|
|
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: 1.4621 |
|
- Rouge1: 49.1683 |
|
- Rouge2: 19.4082 |
|
- Rougel: 33.9969 |
|
- Rougelsum: 33.9813 |
|
- Gen Len: 40.0 |
|
|
|
## 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: 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.4584 | 1.0 | 983 | 1.8478 | 38.1727 | 13.6798 | 29.6916 | 29.6486 | 34.0 | |
|
| 2.002 | 2.0 | 1966 | 1.7151 | 38.1157 | 11.406 | 30.5444 | 30.4542 | 29.0 | |
|
| 1.8944 | 3.0 | 2949 | 1.6377 | 41.6078 | 14.6425 | 29.1709 | 29.1277 | 40.0 | |
|
| 1.809 | 4.0 | 3932 | 1.5824 | 38.1157 | 11.4094 | 30.2316 | 30.174 | 29.0 | |
|
| 1.7763 | 5.0 | 4915 | 1.5419 | 38.1157 | 12.8897 | 30.0962 | 30.034 | 29.0 | |
|
| 1.7535 | 6.0 | 5898 | 1.5088 | 46.8579 | 18.9781 | 33.0079 | 33.0205 | 41.0 | |
|
| 1.7409 | 7.0 | 6881 | 1.4867 | 49.1683 | 19.4082 | 33.9969 | 33.9813 | 40.0 | |
|
| 1.7442 | 8.0 | 7864 | 1.4712 | 43.8511 | 18.6704 | 31.2102 | 31.2126 | 47.0 | |
|
| 1.7462 | 9.0 | 8847 | 1.4651 | 43.8511 | 18.6704 | 31.2102 | 31.2126 | 47.0 | |
|
| 1.753 | 10.0 | 9830 | 1.4621 | 49.1683 | 19.4082 | 33.9969 | 33.9813 | 40.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|