metadata
library_name: transformers
license: apache-2.0
base_model: ayakiri/sentence-correction
tags:
- generated_from_trainer
model-index:
- name: sentence-correction
results: []
sentence-correction
This model is a fine-tuned version of ayakiri/sentence-correction on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6802
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 374 | 0.6624 |
| 0.4455 | 2.0 | 748 | 0.6696 |
| 0.4284 | 3.0 | 1122 | 0.6677 |
| 0.4284 | 4.0 | 1496 | 0.6674 |
| 0.4049 | 5.0 | 1870 | 0.6714 |
| 0.3958 | 6.0 | 2244 | 0.6759 |
| 0.3905 | 7.0 | 2618 | 0.6770 |
| 0.3905 | 8.0 | 2992 | 0.6784 |
| 0.3825 | 9.0 | 3366 | 0.6785 |
| 0.3808 | 10.0 | 3740 | 0.6802 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0