metadata
base_model: ''
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: hubert2BertMusic200
results: []
hubert2BertMusic200
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6404
- Rouge1: 22.2447
- Rouge2: 3.1014
- Rougel: 17.3915
- Rougelsum: 17.384
- Gen Len: 60.98
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.1772 | 1.0 | 959 | 3.1357 | 21.4108 | 2.939 | 16.5248 | 16.5394 | 60.88 |
| 2.7873 | 2.0 | 1918 | 2.9875 | 24.3504 | 4.0795 | 18.7327 | 18.7742 | 69.0 |
| 2.6552 | 3.0 | 2877 | 2.8820 | 21.8354 | 3.0916 | 17.496 | 17.492 | 74.39 |
| 2.581 | 4.0 | 3836 | 2.8149 | 21.4271 | 3.4575 | 17.1908 | 17.2267 | 69.41 |
| 2.5259 | 5.0 | 4795 | 2.7547 | 23.1425 | 3.374 | 17.9846 | 18.0169 | 64.79 |
| 2.5174 | 6.0 | 5754 | 2.7169 | 23.3286 | 3.4459 | 17.874 | 17.8877 | 69.12 |
| 2.4736 | 7.0 | 6713 | 2.6804 | 21.7065 | 3.0158 | 17.2875 | 17.2913 | 60.51 |
| 2.4705 | 8.0 | 7672 | 2.6585 | 21.4536 | 3.1165 | 17.0642 | 17.0887 | 60.39 |
| 2.4776 | 9.0 | 8631 | 2.6448 | 22.8956 | 3.4093 | 17.6982 | 17.6927 | 63.92 |
| 2.5006 | 10.0 | 9590 | 2.6404 | 22.2447 | 3.1014 | 17.3915 | 17.384 | 60.98 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3