estudiante_Swin3D_profesor_MViT_kl_VIOPERU

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

• Loss: 0.4829
• Accuracy: 0.7946
• F1: 0.7933
• Precision: 0.8025
• Recall: 0.7946
• Roc Auc: 0.8791

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: 66
• training_steps: 660
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.5625	1.0136	33	0.6570	0.6607	0.6580	0.6660	0.6607	0.8329
0.5146	2.0273	66	0.6185	0.6964	0.6916	0.7095	0.6964	0.8724
0.4598	4.0045	99	0.5806	0.7321	0.7300	0.7398	0.7321	0.8827
0.4104	5.0182	132	0.4956	0.8036	0.8020	0.8136	0.8036	0.9184
0.3357	6.0318	165	0.4244	0.8571	0.8571	0.8571	0.8571	0.9324
0.2828	8.0091	198	0.4226	0.8571	0.8571	0.8571	0.8571	0.9311
0.256	9.0227	231	0.3688	0.8571	0.8571	0.8571	0.8571	0.9324
0.2545	10.0364	264	0.3938	0.8036	0.8020	0.8136	0.8036	0.9196
0.2664	12.0136	297	0.3765	0.8036	0.8030	0.8071	0.8036	0.9184
0.2484	13.0273	330	0.3911	0.8393	0.8392	0.8397	0.8393	0.9235

Framework versions

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