metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: hubert2BertMusicwithNewS10
results: []
hubert2BertMusicwithNewS10
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9734
- Rouge1: 23.9184
- Rouge2: 7.161
- Rougel: 18.3653
- Rougelsum: 18.3289
- Gen Len: 45.86
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 |
|---|---|---|---|---|---|---|---|---|
| 4.3541 | 1.0 | 1361 | 3.7286 | 31.3443 | 8.5461 | 22.9152 | 22.8633 | 44.4 |
| 3.6252 | 2.0 | 2722 | 3.2950 | 25.3846 | 6.7268 | 19.4638 | 19.3924 | 40.12 |
| 3.3709 | 3.0 | 4083 | 3.1073 | 26.3761 | 7.1947 | 19.4663 | 19.4253 | 44.76 |
| 3.2605 | 4.0 | 5444 | 3.0024 | 23.8355 | 7.1978 | 18.3755 | 18.3194 | 45.61 |
| 3.2417 | 5.0 | 6805 | 2.9734 | 23.9184 | 7.161 | 18.3653 | 18.3289 | 45.86 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3