custom_model

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0004
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 1.0

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.6805	0.5556	20	0.5965	0.7606	0	0.0	0
0.5306	1.1111	40	0.4812	0.7606	0	0.0	0
0.3863	1.6667	60	0.2857	0.7606	0	0.0	0
0.234	2.2222	80	0.1738	0.9437	1.0	0.7647	0.8667
0.0583	2.7778	100	0.0827	0.9859	1.0	0.9412	0.9697
0.0314	3.3333	120	0.0036	1.0	1.0	1.0	1.0
0.0926	3.8889	140	0.0873	0.9718	1.0	0.8824	0.9375
0.0019	4.4444	160	0.0007	1.0	1.0	1.0	1.0
0.0556	5.0	180	0.0009	1.0	1.0	1.0	1.0
0.0018	5.5556	200	0.0467	0.9859	1.0	0.9412	0.9697
0.0011	6.1111	220	0.0005	1.0	1.0	1.0	1.0
0.0012	6.6667	240	0.0004	1.0	1.0	1.0	1.0
0.0011	7.2222	260	0.0004	1.0	1.0	1.0	1.0
0.0012	7.7778	280	0.0004	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1