essay-detect-bert

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0166
• Accuracy: 0.9974

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: 5e-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
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1696	0.2856	500	0.0238	0.9940
0.0441	0.5711	1000	0.0341	0.9929
0.0294	0.8567	1500	0.0787	0.9860
0.0204	1.1422	2000	0.0112	0.9979
0.0148	1.4278	2500	0.0120	0.9981
0.0037	1.7133	3000	0.0188	0.9964
0.0098	1.9989	3500	0.0735	0.9874
0.0025	2.2844	4000	0.0075	0.9983
0.0008	2.5700	4500	0.0206	0.9967
0.0006	2.8555	5000	0.0168	0.9974

Framework versions

• Transformers 4.43.1
• Pytorch 2.2.2+cu121
• Tokenizers 0.19.1