metadata
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM2-1.7B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 3b20ef7a-c5ff-44cc-8016-a647f7e78a5b
results: []
3b20ef7a-c5ff-44cc-8016-a647f7e78a5b
This model is a fine-tuned version of unsloth/SmolLM2-1.7B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1791
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: 0.000214
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0006 | 1 | 1.5136 |
| 1.4206 | 0.0284 | 50 | 1.3546 |
| 1.248 | 0.0568 | 100 | 1.2817 |
| 1.1673 | 0.0853 | 150 | 1.2531 |
| 1.2848 | 0.1137 | 200 | 1.2271 |
| 1.2348 | 0.1421 | 250 | 1.2059 |
| 1.3114 | 0.1705 | 300 | 1.1918 |
| 1.2413 | 0.1989 | 350 | 1.1818 |
| 1.2793 | 0.2273 | 400 | 1.1730 |
| 1.3291 | 0.2558 | 450 | 1.1837 |
| 1.262 | 0.2842 | 500 | 1.1791 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1