hausa_blend
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 9.6934
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: 0.002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 1652
- gradient_accumulation_steps: 5
- total_train_batch_size: 320
- 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
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 213.2576 | 1.0 | 201 | 22.5111 |
| 61.0713 | 2.0 | 402 | 11.1953 |
| 53.5773 | 3.0 | 603 | 10.4559 |
| 51.1444 | 4.0 | 804 | 10.0289 |
| 49.6945 | 5.0 | 1005 | 9.7750 |
| 48.9875 | 6.0 | 1206 | 9.6934 |
Framework versions
- PEFT 0.16.0
- Transformers 4.54.1
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2
- Downloads last month
- 5
Model tree for thiomajid/hausa_blend
Base model
HuggingFaceTB/SmolLM2-135M