IndoT5-LoRA-R16-LR0.0001-Ep10
This model is a fine-tuned version of Wikidepia/IndoT5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5329
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- 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: constant
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9741 | 1.0 | 188 | 0.8986 |
| 0.8334 | 2.0 | 376 | 0.8524 |
| 0.8657 | 3.0 | 564 | 0.8229 |
| 0.7753 | 4.0 | 752 | 0.7942 |
| 0.6823 | 5.0 | 940 | 0.5941 |
| 0.5969 | 6.0 | 1128 | 0.5686 |
| 0.618 | 7.0 | 1316 | 0.5567 |
| 0.5726 | 8.0 | 1504 | 0.5419 |
| 0.5489 | 9.0 | 1692 | 0.5374 |
| 0.5392 | 10.0 | 1880 | 0.5329 |
Framework versions
- PEFT 0.18.1
- Transformers 4.57.6
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for raniaa17/IndoT5-LoRA-R16-LR0.0001-Ep10
Base model
Wikidepia/IndoT5-base