|
--- |
|
license: llama3 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: meta-llama/Meta-Llama-3-8B |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: LLAMA3_8b_LORA_FOR_CLASSIFICATION |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# LLAMA3_8b_LORA_FOR_CLASSIFICATION |
|
|
|
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6062 |
|
- Balanced Accuracy: 0.86 |
|
- Accuracy: 0.86 |
|
- Micro F1: 0.86 |
|
- Macro F1: 0.8600 |
|
- Weighted F1: 0.8600 |
|
- Classification Report: precision recall f1-score support |
|
|
|
0 0.86 0.85 0.86 200 |
|
1 0.86 0.86 0.86 200 |
|
|
|
accuracy 0.86 400 |
|
macro avg 0.86 0.86 0.86 400 |
|
weighted avg 0.86 0.86 0.86 400 |
|
|
|
|
|
## 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: 8 |
|
- 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 | Accuracy | Balanced Accuracy | Classification Report | Validation Loss | Macro F1 | Micro F1 | Weighted F1 | |
|
|:-------------:|:-----:|:----:|:--------:|:-----------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|:--------:|:--------:|:-----------:| |
|
| 0.5306 | 1.0 | 732 | 0.8125 | 0.8125 | precision recall f1-score support |
|
|
|
0 0.76 0.92 0.83 200 |
|
1 0.90 0.70 0.79 200 |
|
|
|
accuracy 0.81 400 |
|
macro avg 0.83 0.81 0.81 400 |
|
weighted avg 0.83 0.81 0.81 400 |
|
| 0.4840 | 0.8103 | 0.8125 | 0.8103 | |
|
| 0.4284 | 2.0 | 1464 | 0.4444 | 0.815 | 0.815 | 0.815 | 0.8147 | 0.8147 | precision recall f1-score support |
|
|
|
0 0.84 0.78 0.81 200 |
|
1 0.79 0.85 0.82 200 |
|
|
|
accuracy 0.81 400 |
|
macro avg 0.82 0.81 0.81 400 |
|
weighted avg 0.82 0.81 0.81 400 |
|
| |
|
| 0.3809 | 3.0 | 2196 | 0.4513 | 0.8475 | 0.8475 | 0.8475 | 0.8470 | 0.8470 | precision recall f1-score support |
|
|
|
0 0.81 0.91 0.86 200 |
|
1 0.89 0.79 0.84 200 |
|
|
|
accuracy 0.85 400 |
|
macro avg 0.85 0.85 0.85 400 |
|
weighted avg 0.85 0.85 0.85 400 |
|
| |
|
| 0.2413 | 4.0 | 2928 | 0.5228 | 0.87 | 0.87 | 0.87 | 0.8700 | 0.8700 | precision recall f1-score support |
|
|
|
0 0.87 0.86 0.87 200 |
|
1 0.87 0.88 0.87 200 |
|
|
|
accuracy 0.87 400 |
|
macro avg 0.87 0.87 0.87 400 |
|
weighted avg 0.87 0.87 0.87 400 |
|
| |
|
| 0.1499 | 5.0 | 3660 | 0.6062 | 0.86 | 0.86 | 0.86 | 0.8600 | 0.8600 | precision recall f1-score support |
|
|
|
0 0.86 0.85 0.86 200 |
|
1 0.86 0.86 0.86 200 |
|
|
|
accuracy 0.86 400 |
|
macro avg 0.86 0.86 0.86 400 |
|
weighted avg 0.86 0.86 0.86 400 |
|
| |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
