| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: spell_correction_M04_verification |
| | results: [] |
| | --- |
| | |
| | <!-- 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_M04_verification |
| | |
| | This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.0588 |
| | |
| | ## 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 | 269 | 0.3070 | |
| | | 1.8826 | 2.0 | 538 | 0.0769 | |
| | | 1.8826 | 3.0 | 807 | 0.0592 | |
| | | 0.0711 | 4.0 | 1076 | 0.0577 | |
| | | 0.0711 | 5.0 | 1345 | 0.0563 | |
| | | 0.04 | 6.0 | 1614 | 0.0562 | |
| | | 0.04 | 7.0 | 1883 | 0.0560 | |
| | | 0.0265 | 8.0 | 2152 | 0.0544 | |
| | | 0.0265 | 9.0 | 2421 | 0.0540 | |
| | | 0.0196 | 10.0 | 2690 | 0.0534 | |
| | | 0.0196 | 11.0 | 2959 | 0.0548 | |
| | | 0.015 | 12.0 | 3228 | 0.0552 | |
| | | 0.015 | 13.0 | 3497 | 0.0578 | |
| | | 0.0123 | 14.0 | 3766 | 0.0591 | |
| | | 0.0116 | 15.0 | 4035 | 0.0578 | |
| | | 0.0116 | 16.0 | 4304 | 0.0580 | |
| | | 0.0091 | 17.0 | 4573 | 0.0592 | |
| | | 0.0091 | 18.0 | 4842 | 0.0596 | |
| | | 0.0088 | 19.0 | 5111 | 0.0605 | |
| | | 0.0088 | 20.0 | 5380 | 0.0569 | |
| | | 0.0074 | 21.0 | 5649 | 0.0598 | |
| | | 0.0074 | 22.0 | 5918 | 0.0587 | |
| | | 0.0078 | 23.0 | 6187 | 0.0589 | |
| | | 0.0078 | 24.0 | 6456 | 0.0586 | |
| | | 0.0068 | 25.0 | 6725 | 0.0588 | |
| | | 0.0068 | 26.0 | 6994 | 0.0591 | |
| | | 0.0076 | 27.0 | 7263 | 0.0590 | |
| | | 0.0072 | 28.0 | 7532 | 0.0587 | |
| | | 0.0072 | 29.0 | 7801 | 0.0587 | |
| | | 0.0059 | 30.0 | 8070 | 0.0588 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.28.0 |
| | - Pytorch 1.12.1+cu102 |
| | - Datasets 2.13.1 |
| | - Tokenizers 0.13.3 |
| | |
