estudiante_S3D_profesor_MViT_akl_VIOPERU

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

• Loss: 0.5499
• Accuracy: 0.7411
• F1: 0.7363
• Precision: 0.7597
• Recall: 0.7411
• Roc Auc: 0.8501

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: 40
• eval_batch_size: 40
• 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: 40
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
2.7266	2.01	20	0.6842	0.5	0.3875	0.5	0.5	0.5459
2.137	4.02	40	0.6643	0.5893	0.5221	0.7041	0.5893	0.6480
1.6043	7.01	60	0.6242	0.6429	0.6111	0.7121	0.6429	0.7309
1.3277	9.02	80	0.6219	0.6964	0.6842	0.7323	0.6964	0.7704
1.03	12.01	100	0.5769	0.6964	0.6842	0.7323	0.6964	0.8010
0.8458	14.02	120	0.5795	0.6964	0.6884	0.7191	0.6964	0.8087
0.6449	17.01	140	0.5731	0.7143	0.7083	0.7333	0.7143	0.8189
0.5688	19.02	160	0.5663	0.7321	0.7300	0.7398	0.7321	0.8329
0.4625	22.01	180	0.5546	0.7143	0.7110	0.7246	0.7143	0.8380
0.4104	24.02	200	0.5407	0.7143	0.7110	0.7246	0.7143	0.8406
0.5655	27.01	220	0.5199	0.7143	0.7110	0.7246	0.7143	0.8393
0.4936	29.02	240	0.5060	0.6786	0.6748	0.6872	0.6786	0.8316
0.3731	32.01	260	0.5524	0.6964	0.6916	0.7095	0.6964	0.8355

Framework versions

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