bart-finetuned-lyrlen-64-lines
This model is a fine-tuned version of adamjweintraut/bart-finetuned-lyrlen-64-lines on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.6080
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 3.6575 | 0.1 | 500 | 3.8095 |
| 3.6178 | 0.2 | 1000 | 3.8321 |
| 3.6005 | 0.3 | 1500 | 3.8091 |
| 3.5433 | 0.39 | 2000 | 3.8274 |
| 3.5201 | 0.49 | 2500 | 3.8042 |
| 3.4828 | 0.59 | 3000 | 3.7598 |
| 3.4459 | 0.69 | 3500 | 3.7713 |
| 3.4077 | 0.79 | 4000 | 3.7030 |
| 3.3511 | 0.89 | 4500 | 3.7266 |
| 3.3363 | 0.99 | 5000 | 3.7175 |
| 3.288 | 1.08 | 5500 | 3.7260 |
| 3.2682 | 1.18 | 6000 | 3.7454 |
| 3.2621 | 1.28 | 6500 | 3.6824 |
| 3.2589 | 1.38 | 7000 | 3.6718 |
| 3.2068 | 1.48 | 7500 | 3.6544 |
| 3.194 | 1.58 | 8000 | 3.6718 |
| 3.1564 | 1.68 | 8500 | 3.6809 |
| 3.142 | 1.77 | 9000 | 3.6412 |
| 3.1011 | 1.87 | 9500 | 3.6384 |
| 3.0778 | 1.97 | 10000 | 3.6148 |
| 3.075 | 2.07 | 10500 | 3.6441 |
| 3.0732 | 2.17 | 11000 | 3.6390 |
| 3.0749 | 2.27 | 11500 | 3.6148 |
| 3.0094 | 2.37 | 12000 | 3.6366 |
| 3.0261 | 2.46 | 12500 | 3.6325 |
| 3.0357 | 2.56 | 13000 | 3.6202 |
| 2.9783 | 2.66 | 13500 | 3.6271 |
| 2.9595 | 2.76 | 14000 | 3.6171 |
| 2.9641 | 2.86 | 14500 | 3.6115 |
| 2.9654 | 2.96 | 15000 | 3.6080 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2