distilbert-base-multilingual-cased-sindhi-cpt
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1873
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- 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: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 12.3142 | 0.1423 | 3000 | 1.4516 |
| 11.3215 | 0.2846 | 6000 | 1.3460 |
| 10.7683 | 0.4269 | 9000 | 1.2617 |
| 10.4548 | 0.5691 | 12000 | 1.2410 |
| 10.1765 | 0.7114 | 15000 | 1.2041 |
| 10.0206 | 0.8537 | 18000 | 1.1939 |
| 9.9302 | 0.9960 | 21000 | 1.1875 |
| 9.9302 | 1.0 | 21085 | 1.1873 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.8.0+cu129
- Datasets 5.0.1
- Tokenizers 0.23.2