estudiante_S3D_profesor_MViT_kl_RWF2000

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

• Loss: 0.2961
• Accuracy: 0.895
• F1: 0.8950
• Precision: 0.8952
• Recall: 0.895
• Roc Auc: 0.9467

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: 320
• training_steps: 3200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.5654	3.0125	160	0.3967	0.8225	0.8217	0.8285	0.8225	0.9237
0.3222	7.0125	320	0.3785	0.8325	0.8309	0.8456	0.8325	0.9408
0.2286	11.0125	480	0.3733	0.875	0.8746	0.8796	0.875	0.9448
0.181	15.0125	640	0.3435	0.8875	0.8874	0.8883	0.8875	0.9457
0.129	19.0125	800	0.2839	0.8875	0.8875	0.8875	0.8875	0.9508
0.1303	23.0125	960	0.3033	0.9	0.9000	0.9006	0.9	0.9503
0.1157	27.0125	1120	0.2834	0.8925	0.8924	0.8937	0.8925	0.9495
0.11	31.0125	1280	0.2883	0.9	0.9000	0.9004	0.9	0.9498
0.0951	35.0125	1440	0.2846	0.8975	0.8974	0.8983	0.8975	0.9487
0.0955	39.0125	1600	0.2967	0.8925	0.8924	0.8937	0.8925	0.9505
0.0995	43.0125	1760	0.3147	0.8975	0.8974	0.8983	0.8975	0.9486

Framework versions

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