estudiante_Swin3D_RLVS

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

• Loss: 0.0766
• Accuracy: 0.9816
• F1: 0.9816
• Precision: 0.9817
• Recall: 0.9816
• 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: 15
• eval_batch_size: 15
• 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: 318
• training_steps: 3180
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.2317	1.0160	159	0.1561	0.9412	0.9410	0.9453	0.9412	0.9878
0.1354	2.0321	318	0.0908	0.9652	0.9652	0.9654	0.9652	0.9939
0.0698	4.0142	477	0.1050	0.9679	0.9679	0.9688	0.9679	0.9952
0.0767	5.0302	636	0.0930	0.9759	0.9759	0.9761	0.9759	0.9972
0.0576	7.0123	795	0.0916	0.9786	0.9786	0.9787	0.9786	0.9975
0.0514	8.0283	954	0.0840	0.9813	0.9813	0.9814	0.9813	0.9985
0.0481	10.0104	1113	0.1026	0.9733	0.9733	0.9733	0.9733	0.9980
0.0257	11.0264	1272	0.1148	0.9813	0.9813	0.9814	0.9813	0.9966
0.03	13.0085	1431	0.1170	0.9759	0.9759	0.9761	0.9759	0.9981
0.0302	14.0245	1590	0.1537	0.9733	0.9733	0.9735	0.9733	0.9978
0.0414	16.0066	1749	0.1367	0.9786	0.9786	0.9787	0.9786	0.9981

Framework versions

• Transformers 4.46.3
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3