profesor_Swin3D_O_RLVS

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

• Loss: 0.0660
• Accuracy: 0.9882
• F1: 0.9882
• Precision: 0.9882
• Recall: 0.9882
• Roc Auc: 0.9988

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: 1e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Use 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_steps: 477
• training_steps: 4770
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.0696	2.0329	477	0.0768	0.9732	0.9732	0.9734	0.9732	0.9980
0.0312	5.0323	954	0.1061	0.9786	0.9786	0.9788	0.9786	0.9984
0.0414	8.0317	1431	0.0981	0.9732	0.9732	0.9734	0.9732	0.9988
0.0005	11.0310	1908	0.0739	0.9866	0.9866	0.9866	0.9866	0.9986
0.0009	14.0304	2385	0.1144	0.9812	0.9812	0.9814	0.9812	0.9987
0.0015	17.0298	2862	0.2200	0.9705	0.9705	0.9712	0.9705	0.9964
0.0002	20.0291	3339	0.1794	0.9732	0.9732	0.9733	0.9732	0.9978

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.1