metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: hubert2BertMusicwithNewS
results: []
hubert2BertMusicwithNewS
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.9900
- Rouge1: 26.5585
- Rouge2: 5.0275
- Rougel: 20.5156
- Rougelsum: 20.5605
- Gen Len: 69.0
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 5.4468 | 1.0 | 959 | 5.3074 | 26.4524 | 5.1085 | 20.4049 | 20.4327 | 65.39 |
| 4.817 | 2.0 | 1918 | 5.0738 | 26.1836 | 5.119 | 20.2888 | 20.2917 | 64.66 |
| 4.6359 | 3.0 | 2877 | 4.9900 | 26.5585 | 5.0275 | 20.5156 | 20.5605 | 69.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3