metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- base_model:adapter:meta-llama/Llama-3.2-1B-Instruct
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: finetune
results: []
finetune
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: 0.3303
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0733 | 0.2 | 5 | 0.8342 |
| 0.5412 | 0.4 | 10 | 0.5452 |
| 0.482 | 0.6 | 15 | 0.4806 |
| 0.372 | 0.8 | 20 | 0.4173 |
| 0.3336 | 1.0 | 25 | 0.3932 |
| 0.3449 | 1.2 | 30 | 0.3777 |
| 0.3247 | 1.4 | 35 | 0.3705 |
| 0.3711 | 1.6 | 40 | 0.3568 |
| 0.2638 | 1.8 | 45 | 0.3480 |
| 0.2707 | 2.0 | 50 | 0.3436 |
| 0.2652 | 2.2 | 55 | 0.3407 |
| 0.2703 | 2.4 | 60 | 0.3369 |
| 0.2841 | 2.6 | 65 | 0.3350 |
| 0.2334 | 2.8 | 70 | 0.3302 |
| 0.2854 | 3.0 | 75 | 0.3303 |
Framework versions
- PEFT 0.17.1
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1