profesor_MViT_O_VIOPERU

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

• Loss: 0.5344
• Accuracy: 0.8661
• F1: 0.8660
• Precision: 0.8671
• Recall: 0.8661
• Roc Auc: 0.9058

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
0.6682	7.0067	90	0.6678	0.6111	0.5504	0.7849	0.6111	0.8791
0.5925	14.0133	180	0.6043	0.8519	0.8519	0.8519	0.8519	0.875
0.4774	22.0067	270	0.5004	0.8889	0.8886	0.8907	0.8889	0.8929
0.3457	29.0133	360	0.4336	0.8704	0.8702	0.8707	0.8704	0.8929
0.221	37.0067	450	0.3516	0.8519	0.8519	0.8519	0.8519	0.8984
0.139	44.0133	540	0.3847	0.8704	0.8697	0.8745	0.8704	0.9080
0.0955	52.0067	630	0.3967	0.8704	0.8675	0.8963	0.8704	0.9121
0.0773	59.0133	720	0.4283	0.8704	0.8697	0.8745	0.8704	0.9032
0.0584	67.0067	810	0.3643	0.8889	0.8880	0.8971	0.8889	0.9114
0.0441	74.0133	900	0.4218	0.8519	0.8519	0.8519	0.8519	0.9100

Framework versions

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