|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiSD3200 |
|
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. --> |
|
|
|
# wav2GPT2MusiSD3200 |
|
|
|
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: 1.4167 |
|
- Rouge1: 46.3177 |
|
- Rouge2: 18.1696 |
|
- Rougel: 34.6558 |
|
- Rougelsum: 34.636 |
|
- 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.8481 | 1.0 | 983 | 2.2495 | 34.5797 | 8.9817 | 28.3195 | 28.32 | 28.0 | |
|
| 2.4137 | 2.0 | 1966 | 2.0846 | 36.3928 | 12.5876 | 27.98 | 27.9842 | 21.0 | |
|
| 2.2635 | 3.0 | 2949 | 1.9332 | 35.1245 | 9.6761 | 29.1228 | 29.155 | 27.0 | |
|
| 2.1176 | 4.0 | 3932 | 1.8091 | 34.5774 | 10.3811 | 27.872 | 27.8823 | 21.0 | |
|
| 2.0186 | 5.0 | 4915 | 1.6961 | 31.3649 | 9.5216 | 26.2574 | 26.254 | 38.0 | |
|
| 1.9291 | 6.0 | 5898 | 1.6045 | 39.5512 | 13.1811 | 30.9223 | 30.9325 | 40.0 | |
|
| 1.8468 | 7.0 | 6881 | 1.5318 | 41.6641 | 14.5078 | 31.932 | 31.9302 | 39.0 | |
|
| 1.7885 | 8.0 | 7864 | 1.4718 | 46.3177 | 18.1696 | 34.6558 | 34.636 | 40.0 | |
|
| 1.7379 | 9.0 | 8847 | 1.4323 | 45.3182 | 17.9076 | 33.0305 | 33.0228 | 47.0 | |
|
| 1.6984 | 10.0 | 9830 | 1.4167 | 46.3177 | 18.1696 | 34.6558 | 34.636 | 40.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|