profesor_Swin3D_O_RWF2000

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

• Loss: 0.4342
• Accuracy: 0.8988
• F1: 0.8987
• Precision: 0.8991
• Recall: 0.8988
• Roc Auc: 0.9591

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: 450
• training_steps: 4500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.2087	2.0324	450	0.4338	0.8553	0.8532	0.8764	0.8553	0.9511
0.1662	5.0311	900	0.3895	0.9053	0.9053	0.9053	0.9053	0.9684
0.0927	8.0298	1350	0.5082	0.8921	0.8921	0.8921	0.8921	0.9706
0.0577	11.0284	1800	0.6253	0.9026	0.9026	0.9029	0.9026	0.9674
0.0418	14.0271	2250	0.6788	0.8974	0.8974	0.8976	0.8974	0.9667

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.0.2
• Tokenizers 0.20.1