RALL_RGBCROP_5e6-poly_test_eval

This model is a fine-tuned version of TanAlexanderlz/RALL_RGBCROP_Aug16F-polynomial on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5478
• eval_model_preparation_time: 0.0065
• eval_accuracy: 0.8635
• eval_precision: 0.8494
• eval_recall: 0.8835
• eval_f1: 0.8661
• eval_auc_roc: 0.9269
• eval_specificity: 0.8434
• eval_sensitivity: 0.8835
• eval_runtime: 111.893
• eval_samples_per_second: 4.451
• eval_steps_per_second: 0.563
• step: 0

Confusion Matrix: Normal Shoplifting Normal 210 39 Shoplifting 29 220 ***** test metrics ***** eval_accuracy = 0.8635 eval_auc_roc = 0.9269 eval_f1 = 0.8661 eval_loss = 0.5478 eval_model_preparation_time = 0.0065 eval_precision = 0.8494 eval_recall = 0.8835 eval_runtime = 0:01:50.26 eval_samples_per_second = 4.516 eval_sensitivity = 0.8835 eval_specificity = 0.8434 eval_steps_per_second = 0.571

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 4320

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1