metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: hubert2BertMusicTestL1e5
results: []
hubert2BertMusicTestL1e5
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4298
- Rouge1: 28.0133
- Rouge2: 7.7565
- Rougel: 20.6731
- Rougelsum: 20.7167
- Gen Len: 49.39
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 |
|---|---|---|---|---|---|---|---|---|
| 5.5936 | 1.0 | 1361 | 4.7638 | 27.3446 | 4.7076 | 20.5101 | 20.5046 | 53.77 |
| 4.4297 | 2.0 | 2722 | 3.9961 | 24.1606 | 4.4476 | 17.5901 | 17.5595 | 78.37 |
| 3.9625 | 3.0 | 4083 | 3.6406 | 29.6819 | 6.5423 | 21.0926 | 21.0753 | 69.61 |
| 3.7816 | 4.0 | 5444 | 3.4773 | 29.1938 | 6.6737 | 20.5273 | 20.4925 | 58.06 |
| 3.7116 | 5.0 | 6805 | 3.4298 | 28.0133 | 7.7565 | 20.6731 | 20.7167 | 49.39 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3