fine-tuned-smolLM2-360M-with-LoRA-on-camel-ai-physics
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-360M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7558
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7878 | 1.0 | 4000 | 0.8105 |
| 0.7877 | 2.0 | 8000 | 0.7847 |
| 0.7671 | 3.0 | 12000 | 0.7703 |
| 0.7233 | 4.0 | 16000 | 0.7630 |
| 0.7043 | 5.0 | 20000 | 0.7583 |
| 0.6809 | 6.0 | 24000 | 0.7562 |
| 0.6795 | 7.0 | 28000 | 0.7553 |
| 0.6832 | 8.0 | 32000 | 0.7558 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 13
Model tree for akhilfau/fine-tuned-smolLM2-360M-with-LoRA-on-camel-ai-physics
Base model
HuggingFaceTB/SmolLM2-360M