metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-3B
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 1c37c4f8-f9e0-419a-b93c-15b082bcf37d
results: []
1c37c4f8-f9e0-419a-b93c-15b082bcf37d
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: 0.5217
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: 0.000201
- 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 |
| 0.6084 | 0.0094 | 50 | 0.6058 |
| 0.4788 | 0.0188 | 100 | 0.5870 |
| 0.4938 | 0.0282 | 150 | 0.5855 |
| 0.4774 | 0.0376 | 200 | 0.5657 |
| 0.4842 | 0.0470 | 250 | 0.5510 |
| 0.4943 | 0.0564 | 300 | 0.5422 |
| 0.4577 | 0.0658 | 350 | 0.5332 |
| 0.4748 | 0.0752 | 400 | 0.5273 |
| 0.4693 | 0.0846 | 450 | 0.5230 |
| 0.4389 | 0.0940 | 500 | 0.5217 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1