metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-3B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 22d51fb0-bed6-4c8d-8514-550e1b4ccbdf
results: []
22d51fb0-bed6-4c8d-8514-550e1b4ccbdf
This model is a fine-tuned version of unsloth/Llama-3.2-3B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5226
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: 0.000212
- 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 | 0.0002 | 1 | 1.0245 |
| 0.6082 | 0.0094 | 50 | 0.6099 |
| 0.477 | 0.0188 | 100 | 0.5924 |
| 0.4938 | 0.0282 | 150 | 0.5825 |
| 0.4835 | 0.0376 | 200 | 0.5645 |
| 0.4875 | 0.0470 | 250 | 0.5528 |
| 0.499 | 0.0564 | 300 | 0.5460 |
| 0.4577 | 0.0658 | 350 | 0.5349 |
| 0.4757 | 0.0752 | 400 | 0.5285 |
| 0.47 | 0.0846 | 450 | 0.5241 |
| 0.4403 | 0.0940 | 500 | 0.5226 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1