train_run-SmolLM2-135M-Instruct-fadel-full-arabic-diacritization
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0470
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.134 | 0.0623 | 500 | 0.1328 |
| 0.0999 | 0.1247 | 1000 | 0.1022 |
| 0.081 | 0.1870 | 1500 | 0.0856 |
| 0.0691 | 0.2493 | 2000 | 0.0770 |
| 0.0668 | 0.3117 | 2500 | 0.0695 |
| 0.0642 | 0.3740 | 3000 | 0.0659 |
| 0.0605 | 0.4364 | 3500 | 0.0637 |
| 0.0586 | 0.4987 | 4000 | 0.0586 |
| 0.0539 | 0.5610 | 4500 | 0.0557 |
| 0.0545 | 0.6234 | 5000 | 0.0541 |
| 0.0517 | 0.6857 | 5500 | 0.0528 |
| 0.0503 | 0.7480 | 6000 | 0.0522 |
| 0.0467 | 0.8104 | 6500 | 0.0496 |
| 0.0474 | 0.8727 | 7000 | 0.0488 |
| 0.0434 | 0.9350 | 7500 | 0.0488 |
| 0.0473 | 0.9974 | 8000 | 0.0470 |
Framework versions
- PEFT 0.14.0
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0