profesor_MViT_O_UCFCRIME

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

• Loss: 0.6919
• Accuracy: 0.5344
• F1: 0.5379
• Precision: 0.5482
• Recall: 0.5344
• Roc Auc: 0.5503

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: 20
• eval_batch_size: 20
• 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: 72
• training_steps: 720
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc
0.6883	2.0236	72	0.6839	0.5993	0.5953	0.6136	0.5993	0.6495
0.6687	5.0083	144	0.6742	0.5914	0.5807	0.6174	0.5914	0.7125
0.6698	7.0319	216	0.6704	0.5767	0.5587	0.6117	0.5767	0.7110
0.6401	10.0181	288	0.6626	0.5705	0.5488	0.6097	0.5705	0.7163

Framework versions

• Transformers 4.46.1
• Pytorch 2.0.1+cu118
• Datasets 3.0.2
• Tokenizers 0.20.1