Modesty_binary

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

• Loss: 0.7015
• Accuracy: 0.6800
• Precision: 0.6756
• Recall: 0.6908
• F1: 0.6831
• Auc: 0.7466

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: 32
• eval_batch_size: 32
• seed: 1234
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.06
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Auc
No log	1.0	118	0.6176	0.6600	0.6096	0.8878	0.7228	0.7586
No log	2.0	236	0.5801	0.6999	0.6533	0.8504	0.7389	0.7779
No log	3.0	354	0.6588	0.6750	0.6220	0.8903	0.7323	0.7726
No log	4.0	472	0.7015	0.6800	0.6756	0.6908	0.6831	0.7466

Framework versions

• Transformers 4.44.1
• Pytorch 1.11.0
• Datasets 2.12.0
• Tokenizers 0.19.1