metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- generated_from_trainer
model-index:
- name: test_tune
results: []
test_tune
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1745
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1701 | 4.1 | 50 | 2.2675 |
| 1.7542 | 9.1 | 100 | 2.1745 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.3.0+cu118
- Datasets 3.0.2
- Tokenizers 0.20.1