estudiante_Swin3D_VIOPERU

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

• Loss: 0.5108
• Accuracy: 0.8036
• F1: 0.8030
• Precision: 0.8071
• Recall: 0.8036
• Roc Auc: 0.8383

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: 20
• eval_batch_size: 20
• 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: 44
• training_steps: 440
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.6623	1.0227	22	0.6737	0.625	0.5960	0.6753	0.625	0.6186
0.6271	3.0182	44	0.6519	0.6786	0.6719	0.6944	0.6786	0.7066
0.5442	5.0136	66	0.6355	0.6964	0.6940	0.7029	0.6964	0.7309
0.5011	7.0091	88	0.5895	0.6607	0.6606	0.6609	0.6607	0.7577
0.4201	9.0045	110	0.5643	0.75	0.7487	0.7552	0.75	0.7806
0.3943	10.0273	132	0.5755	0.8036	0.8035	0.8040	0.8036	0.7857
0.3258	12.0227	154	0.6106	0.7679	0.7678	0.7682	0.7679	0.7870
0.2769	14.0182	176	0.5971	0.8036	0.8035	0.8040	0.8036	0.7959
0.2305	16.0136	198	0.5782	0.8036	0.8035	0.8040	0.8036	0.7997
0.2703	18.0091	220	0.6228	0.8036	0.8035	0.8040	0.8036	0.8099
0.1854	20.0045	242	0.7158	0.7679	0.7672	0.7710	0.7679	0.8278

Framework versions

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