profesor_Swin3D_S_VIOPERU

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

• Loss: 0.4504
• Accuracy: 0.8661
• F1: 0.8658
• Precision: 0.8690
• Recall: 0.8661
• Roc Auc: 0.8801

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: 5e-06
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 84
• training_steps: 560
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
1.3468	2.0161	37	0.6550	0.7857	0.7832	0.7995	0.7857	0.7844
1.2606	5.0071	74	0.6209	0.75	0.7471	0.7620	0.75	0.8444
1.1865	7.0232	111	0.5585	0.8036	0.8035	0.8040	0.8036	0.8533
0.9207	10.0143	148	0.5006	0.8393	0.8392	0.8397	0.8393	0.8724
0.8035	13.0054	185	0.4414	0.875	0.8746	0.8794	0.875	0.8776
0.6533	15.0214	222	0.4137	0.8571	0.8564	0.8646	0.8571	0.875
0.3945	18.0125	259	0.4275	0.875	0.8746	0.8794	0.875	0.8724
0.3083	21.0036	296	0.4526	0.875	0.8746	0.8794	0.875	0.8839

Framework versions

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