profesor_MViT_S_VIOPERU

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

• Loss: 0.2991
• Accuracy: 0.9107
• F1: 0.9107
• Precision: 0.9112
• Recall: 0.9107
• Roc Auc: 0.9576

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: 23
• eval_batch_size: 23
• 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: 81
• training_steps: 810
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.6473	6.0111	81	0.6350	0.75	0.7497	0.7513	0.75	0.8418
0.5438	13.0074	162	0.5559	0.7857	0.7857	0.7857	0.7857	0.8980
0.4124	20.0037	243	0.4445	0.8571	0.8564	0.8646	0.8571	0.9439
0.2958	26.0148	324	0.3501	0.8929	0.8927	0.8949	0.8929	0.9745
0.2126	33.0111	405	0.2827	0.8929	0.8927	0.8949	0.8929	0.9745
0.1469	40.0074	486	0.3615	0.875	0.8746	0.8794	0.875	0.9732
0.1063	47.0037	567	0.3208	0.8929	0.8927	0.8949	0.8929	0.9783
0.0883	53.0148	648	0.4270	0.875	0.8746	0.8794	0.875	0.9745
0.0631	60.0111	729	0.4191	0.8929	0.8927	0.8949	0.8929	0.9783

Framework versions

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