estudiante_S3D_profesor_MViT_akl_RWF2000

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

• Loss: 0.3008
• Accuracy: 0.8988
• F1: 0.8987
• Precision: 0.8989
• Recall: 0.8988
• Roc Auc: 0.9450

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: 160
• training_steps: 1600
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
9.9187	1.025	80	0.4880	0.8025	0.7992	0.8235	0.8025	0.9107
6.1382	3.025	160	0.3472	0.86	0.8599	0.8606	0.86	0.9258
4.1216	5.025	240	0.3976	0.87	0.8694	0.8774	0.87	0.9304
3.2118	7.025	320	0.5049	0.86	0.8590	0.8707	0.86	0.9305
2.7679	9.025	400	0.4112	0.86	0.8591	0.8695	0.86	0.9304
2.2489	11.025	480	0.4092	0.8725	0.8721	0.8767	0.8725	0.9301
1.9282	13.025	560	0.3318	0.8825	0.8823	0.8847	0.8825	0.9321
1.7851	15.025	640	0.3461	0.9	0.9000	0.9002	0.9	0.9373
1.5879	17.025	720	0.3348	0.9	0.9	0.9	0.9	0.9398
1.6127	19.025	800	0.3177	0.895	0.8950	0.8950	0.895	0.9438
1.5788	21.025	880	0.3190	0.8975	0.8975	0.8976	0.8975	0.9453
1.3457	23.025	960	0.3099	0.8925	0.8925	0.8927	0.8925	0.9467
1.3701	25.025	1040	0.2855	0.89	0.8900	0.8904	0.89	0.9501

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.1.0
• Tokenizers 0.20.2