estudiante_S3D_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: 0.5112
• Accuracy: 0.7768
• F1: 0.7737
• Precision: 0.7926
• Recall: 0.7768
• Roc Auc: 0.8568

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
0.5176	4.02	40	0.6982	0.5357	0.4313	0.6346	0.5357	0.5472
0.3737	9.02	80	0.6248	0.7321	0.7214	0.7745	0.7321	0.7602
0.2609	14.02	120	0.5522	0.7143	0.7110	0.7246	0.7143	0.8253
0.2297	19.02	160	0.5293	0.7143	0.7110	0.7246	0.7143	0.8495
0.1643	24.02	200	0.5365	0.7679	0.7672	0.7710	0.7679	0.8533
0.1424	29.02	240	0.4691	0.7679	0.7672	0.7710	0.7679	0.8559
0.1415	34.02	280	0.4561	0.7143	0.7128	0.7188	0.7143	0.8367
0.1346	39.02	320	0.5279	0.7143	0.7128	0.7188	0.7143	0.8380
0.1223	44.02	360	0.5140	0.7143	0.7128	0.7188	0.7143	0.8380
0.1315	49.02	400	0.4849	0.6964	0.6940	0.7029	0.6964	0.8304

Framework versions

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