<!-- 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. -->
polish_transliterator_BART
This model is a fine-tuned version of sshleifer/bart-tiny-random on the None dataset. It achieves the following results on the evaluation set:
- Loss: 9.5795
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 2.0
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: 3e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 10.3014 | 1.0 | 572 | 10.2707 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 10.2465 | 2.0 | 1144 | 10.2013 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 10.1717 | 3.0 | 1716 | 10.1342 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 10.1086 | 4.0 | 2288 | 10.0704 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 10.0524 | 5.0 | 2860 | 10.0102 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.9976 | 6.0 | 3432 | 9.9539 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.8907 | 7.0 | 4004 | 9.9018 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.8424 | 8.0 | 4576 | 9.8536 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.8046 | 9.0 | 5148 | 9.8095 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.7581 | 10.0 | 5720 | 9.7693 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.7253 | 11.0 | 6292 | 9.7331 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.698 | 12.0 | 6864 | 9.7008 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.6611 | 13.0 | 7436 | 9.6723 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.6125 | 14.0 | 8008 | 9.6477 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.5928 | 15.0 | 8580 | 9.6269 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.5747 | 16.0 | 9152 | 9.6099 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.5613 | 17.0 | 9724 | 9.5966 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.5418 | 18.0 | 10296 | 9.5871 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.539 | 19.0 | 10868 | 9.5814 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
| 9.5366 | 20.0 | 11440 | 9.5795 | 0.0 | 0.0 | 0.0 | 0.0 | 2.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
