metadata
library_name: transformers
license: apache-2.0
base_model: Lau123/distilbert-base-uncased-detect_ai_generated_text
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: ai-detect-4
results: []
ai-detect-4
This model is a fine-tuned version of Lau123/distilbert-base-uncased-detect_ai_generated_text on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3305
- Accuracy: 0.9392
- Precision: 0.9490
- Recall: 0.9541
- F1: 0.9516
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1925 | 1.0 | 6250 | 0.1812 | 0.9257 | 0.9280 | 0.9554 | 0.9415 |
| 0.1569 | 2.0 | 12500 | 0.3106 | 0.9074 | 0.8873 | 0.9760 | 0.9295 |
| 0.0781 | 3.0 | 18750 | 0.5252 | 0.8923 | 0.8619 | 0.9859 | 0.9197 |
| 0.1004 | 4.0 | 25000 | 0.3305 | 0.9392 | 0.9490 | 0.9541 | 0.9516 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1