metadata
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
metrics:
- accuracy
- precision
- recall
model-index:
- name: Llama3_less_data_SUPNT
results: []
Llama3_less_data_SUPNT
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9354
- Accuracy: 0.7867
- Precision: 0.7443
- Recall: 0.8733
- F1 score: 0.8037
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|---|---|---|
| 0.487 | 1.0 | 200 | 0.6341 | 0.7833 | 0.7640 | 0.82 | 0.7910 |
| 0.2565 | 2.0 | 400 | 0.7592 | 0.7833 | 0.7429 | 0.8667 | 0.8 |
| 0.1559 | 3.0 | 600 | 0.7008 | 0.79 | 0.7514 | 0.8667 | 0.8050 |
| 0.1054 | 4.0 | 800 | 0.8348 | 0.79 | 0.7486 | 0.8733 | 0.8062 |
| 0.051 | 5.0 | 1000 | 0.9354 | 0.7867 | 0.7443 | 0.8733 | 0.8037 |
Framework versions
- PEFT 0.11.1
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1