metadata
license: llama3
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: llama3-ai-detector-v3-20k-32batch-512max-len
results: []
llama3-ai-detector-v3-20k-32batch-512max-len
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1170
- Accuracy: 0.9662
- Precision: 0.9865
- Recall: 0.9590
- F1: 0.9726
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 0.3286 | 1.0 | 625 | 0.1242 | 0.9502 | 0.9842 | 0.9353 | 0.9591 |
| 0.1012 | 2.0 | 1250 | 0.1170 | 0.9662 | 0.9865 | 0.9590 | 0.9726 |
| 0.0543 | 3.0 | 1875 | 0.1445 | 0.9688 | 0.9717 | 0.9785 | 0.9751 |
| 0.0082 | 4.0 | 2500 | 0.1693 | 0.9688 | 0.9802 | 0.9696 | 0.9749 |
| 0.0015 | 5.0 | 3125 | 0.1849 | 0.9702 | 0.9784 | 0.9737 | 0.9761 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1