<!-- 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. -->
spell_correction_M05_LM
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0281
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 274 | 0.2890 |
| 1.8446 | 2.0 | 548 | 0.0540 |
| 1.8446 | 3.0 | 822 | 0.0403 |
| 0.028 | 4.0 | 1096 | 0.0344 |
| 0.028 | 5.0 | 1370 | 0.0289 |
| 0.0137 | 6.0 | 1644 | 0.0289 |
| 0.0137 | 7.0 | 1918 | 0.0283 |
| 0.0063 | 8.0 | 2192 | 0.0266 |
| 0.0063 | 9.0 | 2466 | 0.0271 |
| 0.0043 | 10.0 | 2740 | 0.0272 |
| 0.0033 | 11.0 | 3014 | 0.0281 |
| 0.0033 | 12.0 | 3288 | 0.0264 |
| 0.003 | 13.0 | 3562 | 0.0277 |
| 0.003 | 14.0 | 3836 | 0.0274 |
| 0.003 | 15.0 | 4110 | 0.0265 |
| 0.003 | 16.0 | 4384 | 0.0290 |
| 0.0024 | 17.0 | 4658 | 0.0276 |
| 0.0024 | 18.0 | 4932 | 0.0270 |
| 0.0025 | 19.0 | 5206 | 0.0276 |
| 0.0025 | 20.0 | 5480 | 0.0272 |
| 0.0016 | 21.0 | 5754 | 0.0271 |
| 0.0018 | 22.0 | 6028 | 0.0272 |
| 0.0018 | 23.0 | 6302 | 0.0282 |
| 0.0014 | 24.0 | 6576 | 0.0276 |
| 0.0014 | 25.0 | 6850 | 0.0283 |
| 0.0014 | 26.0 | 7124 | 0.0280 |
| 0.0014 | 27.0 | 7398 | 0.0279 |
| 0.0013 | 28.0 | 7672 | 0.0280 |
| 0.0013 | 29.0 | 7946 | 0.0282 |
| 0.0014 | 30.0 | 8220 | 0.0281 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.12.1+cu102
- Datasets 2.13.1
- Tokenizers 0.13.3
