|
--- |
|
base_model: '' |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: wav2GPT2MusiNewStricD3E5 |
|
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. --> |
|
|
|
# wav2GPT2MusiNewStricD3E5 |
|
|
|
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: 2.5120 |
|
- Rouge1: 20.9558 |
|
- Rouge2: 3.2839 |
|
- Rougel: 19.7122 |
|
- Rougelsum: 19.6901 |
|
- Gen Len: 67.79 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.7207 | 1.0 | 959 | 2.7234 | 20.368 | 2.6174 | 18.7438 | 18.7592 | 63.11 | |
|
| 2.4751 | 2.0 | 1918 | 2.6164 | 20.9097 | 3.3813 | 19.3157 | 19.386 | 66.29 | |
|
| 2.3977 | 3.0 | 2877 | 2.5586 | 21.178 | 3.5221 | 19.9418 | 19.9061 | 67.82 | |
|
| 2.3305 | 4.0 | 3836 | 2.5236 | 21.4817 | 3.5503 | 20.3017 | 20.2749 | 67.58 | |
|
| 2.3079 | 5.0 | 4795 | 2.5120 | 20.9558 | 3.2839 | 19.7122 | 19.6901 | 67.79 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.2 |
|
- Tokenizers 0.13.3 |
|
|
