distilled_alpaca_combined
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.0980
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1025 | 0.5722 | 500 | 0.1032 |
| 0.0955 | 1.1445 | 1000 | 0.1000 |
| 0.0934 | 1.7167 | 1500 | 0.0988 |
| 0.0906 | 2.2890 | 2000 | 0.0983 |
| 0.0911 | 2.8612 | 2500 | 0.0980 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1