metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1207
- Accuracy: 0.9755
- Precision: 0.7225
- Recall: 0.7652
- F1: 0.7432
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 204 | 0.0963 | 0.9710 | 0.6434 | 0.6814 | 0.6619 |
| No log | 2.0 | 408 | 0.0877 | 0.9742 | 0.6677 | 0.7389 | 0.7015 |
| 0.1244 | 3.0 | 612 | 0.0957 | 0.9723 | 0.7054 | 0.6880 | 0.6966 |
| 0.1244 | 4.0 | 816 | 0.0903 | 0.9759 | 0.7323 | 0.7635 | 0.7476 |
| 0.0318 | 5.0 | 1020 | 0.1059 | 0.9732 | 0.6986 | 0.7192 | 0.7087 |
| 0.0318 | 6.0 | 1224 | 0.1025 | 0.9758 | 0.7179 | 0.7438 | 0.7306 |
| 0.0318 | 7.0 | 1428 | 0.1177 | 0.9742 | 0.7072 | 0.7455 | 0.7258 |
| 0.0136 | 8.0 | 1632 | 0.1172 | 0.9754 | 0.7134 | 0.7603 | 0.7361 |
| 0.0136 | 9.0 | 1836 | 0.1199 | 0.9755 | 0.7229 | 0.7668 | 0.7442 |
| 0.009 | 10.0 | 2040 | 0.1207 | 0.9755 | 0.7225 | 0.7652 | 0.7432 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2