summ_screen_fd_blueprint_epoch_10
This model is a fine-tuned version of facebook/bart-base on the learn3r/summ_screen_fd_bp dataset. It achieves the following results on the evaluation set:
- Loss: 2.0208
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.382 | 0.97 | 14 | 2.3120 |
| 2.5354 | 1.95 | 28 | 2.1625 |
| 2.2504 | 2.99 | 43 | 2.1031 |
| 2.1809 | 3.97 | 57 | 2.0733 |
| 2.0889 | 4.94 | 71 | 2.0513 |
| 2.0586 | 5.98 | 86 | 2.0359 |
| 2.0117 | 6.96 | 100 | 2.0325 |
| 1.9849 | 8.0 | 115 | 2.0254 |
| 1.9803 | 8.97 | 129 | 2.0218 |
| 1.9584 | 9.74 | 140 | 2.0208 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 1