bert-aihuman-classifier_teacher

Idiomcheng/bert-aihuman-classifier_teacher

bert-aihuman-classifier_teacher is a text classification model from Idiomcheng. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

25% of all-time downloads

All-time downloads

Public

Parameters

109M

1.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors438 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: apache-2.0
Model type: bert
Access: Public
Created: Dec 11, 2025
Updated: Dec 14, 2025
SHA: 0de403bc

Try a prompt

Base models

google-bert/bert-base-uncased

Model card

From the Hugging Face model README

bert-aihuman-classifier_teacher

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0519
Accuracy: 0.993
Auc: 0.9988
Precision: 0.9874
Recall: 0.9986
F1: 0.993
Human Precision: 0.9986
Human Recall: 0.9875
Human F1: 0.993
Ai Precision: 0.9874
Ai Recall: 0.9986
Ai F1: 0.993

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: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision	Recall	F1	Human Precision	Human Recall	Human F1	Ai Precision	Ai Recall	Ai F1
0.414	1.0	714	0.4553	0.8074	0.9658	0.7216	0.9958	0.8368	0.9933	0.6222	0.7652	0.7216	0.9958	0.8368
0.1949	2.0	1428	0.3726	0.8978	0.988	0.8306	0.9972	0.9063	0.9965	0.8	0.8875	0.8306	0.9972	0.9063
0.08	3.0	2142	0.1551	0.9643	0.9965	0.9351	0.9972	0.9651	0.997	0.9319	0.9634	0.9351	0.9972	0.9651
0.0281	4.0	2856	0.1369	0.9727	0.9957	0.9502	0.9972	0.9731	0.9971	0.9486	0.9722	0.9502	0.9972	0.9731
0.0194	5.0	3570	0.0770	0.9832	0.9987	0.9698	0.9972	0.9833	0.9971	0.9694	0.9831	0.9698	0.9972	0.9833
0.0137	6.0	4284	0.1049	0.9839	0.9988	0.9711	0.9972	0.984	0.9971	0.9708	0.9838	0.9711	0.9972	0.984
0.0065	7.0	4998	0.0550	0.9923	0.9988	0.9861	0.9986	0.9923	0.9986	0.9861	0.9923	0.9861	0.9986	0.9923
0.0053	8.0	5712	0.1434	0.9734	0.9987	0.9503	0.9986	0.9738	0.9985	0.9486	0.9729	0.9503	0.9986	0.9738
0.0025	9.0	6426	0.0477	0.993	0.9988	0.9874	0.9986	0.993	0.9986	0.9875	0.993	0.9874	0.9986	0.993
0.002	10.0	7140	0.0519	0.993	0.9988	0.9874	0.9986	0.993	0.9986	0.9875	0.993	0.9874	0.9986	0.993

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Task: Text Classification
Library: transformers
Type: bert
License: apache-2.0
Created: Dec 11, 2025
Updated: Dec 14, 2025