| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: j5ng/et5-typos-corrector |
| tags: |
| - generated_from_trainer |
| metrics: |
| - rouge |
| model-index: |
| - name: make_err_ft_results |
| 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. --> |
|
|
| # make_err_ft_results |
| |
| This model is a fine-tuned version of [j5ng/et5-typos-corrector](https://huggingface.co/j5ng/et5-typos-corrector) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7980 |
| - Rouge1: 0.0 |
| - Rouge2: 0.0 |
| - Rougel: 0.0 |
| - Rougelsum: 0.0 |
| - Gen Len: 12.393 |
| |
| ## 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: 2e-05 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 2 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
| | 2.6767 | 0.05 | 100 | 1.7986 | 0.0 | 0.0 | 0.0 | 0.0 | 11.7733 | |
| | 1.8043 | 0.1 | 200 | 1.5141 | 0.0 | 0.0 | 0.0 | 0.0 | 11.96 | |
| | 1.5302 | 0.15 | 300 | 1.3564 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1402 | |
| | 1.4056 | 0.2 | 400 | 1.2753 | 0.0 | 0.0 | 0.0 | 0.0 | 12.152 | |
| | 1.3319 | 0.25 | 500 | 1.1993 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1468 | |
| | 1.2765 | 0.3 | 600 | 1.1429 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1095 | |
| | 1.2172 | 0.35 | 700 | 1.1243 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1418 | |
| | 1.1631 | 0.4 | 800 | 1.0812 | 0.0 | 0.0 | 0.0 | 0.0 | 12.138 | |
| | 1.1409 | 0.45 | 900 | 1.0510 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1267 | |
| | 1.1012 | 0.5 | 1000 | 1.0116 | 0.0 | 0.0 | 0.0 | 0.0 | 12.2747 | |
| | 1.0973 | 0.55 | 1100 | 0.9905 | 0.0 | 0.0 | 0.0 | 0.0 | 12.358 | |
| | 1.0126 | 0.6 | 1200 | 0.9786 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3313 | |
| | 1.0697 | 0.65 | 1300 | 0.9535 | 0.0 | 0.0 | 0.0 | 0.0 | 12.252 | |
| | 1.0192 | 0.7 | 1400 | 0.9333 | 0.0 | 0.0 | 0.0 | 0.0 | 12.2155 | |
| | 1.0312 | 0.75 | 1500 | 0.9366 | 0.0 | 0.0 | 0.0 | 0.0 | 12.2265 | |
| | 0.9608 | 0.8 | 1600 | 0.9175 | 0.0 | 0.0 | 0.0 | 0.0 | 12.2825 | |
| | 1.0319 | 0.85 | 1700 | 0.8935 | 0.0 | 0.0 | 0.0 | 0.0 | 12.32 | |
| | 1.002 | 0.9 | 1800 | 0.8972 | 0.0 | 0.0 | 0.0 | 0.0 | 12.1375 | |
| | 0.9787 | 0.95 | 1900 | 0.8744 | 0.0 | 0.0 | 0.0 | 0.0 | 12.2127 | |
| | 0.973 | 1.0 | 2000 | 0.8654 | 0.0 | 0.0 | 0.0 | 0.0 | 12.377 | |
| | 0.7704 | 1.05 | 2100 | 0.8659 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4095 | |
| | 0.7728 | 1.1 | 2200 | 0.8607 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4428 | |
| | 0.7539 | 1.15 | 2300 | 0.8510 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4315 | |
| | 0.7358 | 1.2 | 2400 | 0.8562 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3308 | |
| | 0.7533 | 1.25 | 2500 | 0.8423 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4243 | |
| | 0.7437 | 1.3 | 2600 | 0.8412 | 0.0 | 0.0 | 0.0 | 0.0 | 12.395 | |
| | 0.7368 | 1.35 | 2700 | 0.8301 | 0.0 | 0.0 | 0.0 | 0.0 | 12.381 | |
| | 0.7089 | 1.4 | 2800 | 0.8304 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3552 | |
| | 0.7399 | 1.45 | 2900 | 0.8226 | 0.0 | 0.0 | 0.0 | 0.0 | 12.423 | |
| | 0.7027 | 1.5 | 3000 | 0.8255 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3588 | |
| | 0.6931 | 1.55 | 3100 | 0.8173 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4135 | |
| | 0.7254 | 1.6 | 3200 | 0.8141 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4155 | |
| | 0.7203 | 1.65 | 3300 | 0.8102 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4065 | |
| | 0.676 | 1.7 | 3400 | 0.8107 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3648 | |
| | 0.7369 | 1.75 | 3500 | 0.8021 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4313 | |
| | 0.6942 | 1.8 | 3600 | 0.8040 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3852 | |
| | 0.7023 | 1.85 | 3700 | 0.7997 | 0.0 | 0.0 | 0.0 | 0.0 | 12.4072 | |
| | 0.6866 | 1.9 | 3800 | 0.8003 | 0.0 | 0.0 | 0.0 | 0.0 | 12.3915 | |
| | 0.7067 | 1.95 | 3900 | 0.7985 | 0.0 | 0.0 | 0.0 | 0.0 | 12.398 | |
| | 0.7163 | 2.0 | 4000 | 0.7980 | 0.0 | 0.0 | 0.0 | 0.0 | 12.393 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.55.1 |
| - Pytorch 2.6.0+cu124 |
| - Datasets 4.0.0 |
| - Tokenizers 0.21.4 |
| |
