ai-text-detector-deberta-v3-large-h2

This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6619
• Accuracy: 0.5009
• F1: 0.0

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: 8
• eval_batch_size: 16
• 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: cosine
• lr_scheduler_warmup_ratio: 0.08
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7014	0.0184	200	0.6942	0.5009	0.0
0.6947	0.0368	400	0.6927	0.4989	0.0969
0.6987	0.0552	600	0.6910	0.5383	0.1416
0.6937	0.0736	800	0.6957	0.4991	0.6658
0.6878	0.0920	1000	0.6669	0.5561	0.6894
0.6968	0.1103	1200	0.6806	0.5009	0.0025
0.6811	0.1287	1400	0.6619	0.5009	0.0

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1