<!-- 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. -->
wav2GPT2MusicfreezeL6E2
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9438
- Rouge1: 18.5205
- Rouge2: 3.5275
- Rougel: 17.3822
- Rougelsum: 17.3903
- Gen Len: 99.0
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-06
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.3163 | 1.0 | 1361 | 3.0383 | 18.0832 | 2.1201 | 16.389 | 16.4029 | 99.0 |
| 3.0791 | 2.0 | 2722 | 2.9438 | 18.5205 | 3.5275 | 17.3822 | 17.3903 | 99.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.2
- Tokenizers 0.13.3
