profesor_MViT_B_VIOPERU

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

• Loss: 0.5811
• Accuracy: 0.8393
• F1: 0.8385
• Precision: 0.8464
• Recall: 0.8393
• Roc Auc: 0.9232

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: 22
• eval_batch_size: 22
• 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: 90
• training_steps: 900
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.6576	7.0067	90	0.6648	0.6786	0.6719	0.6944	0.6786	0.7857
0.5634	14.0133	180	0.5872	0.75	0.7497	0.7513	0.75	0.8533
0.4258	22.0067	270	0.4743	0.875	0.8750	0.8755	0.875	0.9133
0.3059	29.0133	360	0.4014	0.8393	0.8392	0.8397	0.8393	0.9298
0.2045	37.0067	450	0.3394	0.8571	0.8570	0.8590	0.8571	0.9401
0.1448	44.0133	540	0.3734	0.8393	0.8392	0.8397	0.8393	0.9279
0.1082	52.0067	630	0.3368	0.8929	0.8916	0.9118	0.8929	0.9515
0.0912	59.0133	720	0.3935	0.8571	0.8564	0.8646	0.8571	0.9388
0.0736	67.0067	810	0.3789	0.8929	0.8916	0.9118	0.8929	0.9522
0.0615	74.0133	900	0.3806	0.8929	0.8916	0.9118	0.8929	0.9579

Framework versions

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