t5-base-uzbek-grammar
This model is a fine-tuned version of google-t5/t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1399
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: 0.0003
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1322 | 1.0 | 400 | 0.1719 |
| 0.1526 | 2.0 | 800 | 0.1413 |
| 0.0676 | 3.0 | 1200 | 0.1377 |
| 0.0673 | 4.0 | 1600 | 0.1399 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1