metadata
library_name: peft
license: apache-2.0
base_model: unsloth/SmolLM2-360M-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: cd44a030-ab30-45b1-86b9-18e220ba4b0a
results: []
cd44a030-ab30-45b1-86b9-18e220ba4b0a
This model is a fine-tuned version of unsloth/SmolLM2-360M-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7443
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: 0.000218
- 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 | 0.0000 | 1 | 2.5576 |
| 1.7941 | 0.0015 | 50 | 2.0143 |
| 1.5838 | 0.0029 | 100 | 1.9189 |
| 1.6309 | 0.0044 | 150 | 1.8461 |
| 1.5889 | 0.0059 | 200 | 1.8116 |
| 1.464 | 0.0073 | 250 | 1.7828 |
| 1.5213 | 0.0088 | 300 | 1.7800 |
| 1.5243 | 0.0103 | 350 | 1.7653 |
| 1.4979 | 0.0117 | 400 | 1.7514 |
| 1.6244 | 0.0132 | 450 | 1.7454 |
| 1.4191 | 0.0147 | 500 | 1.7443 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1