results

• Loss: 0.5635
• Accuracy: 0.7531
• Report: precision recall f1-score support
  absence 0.75 0.84 0.79 45 presence 0.77 0.64 0.70 36
  accuracy 0.75 81 macro avg 0.76 0.74 0.74 81 weighted avg 0.75 0.75 0.75 81

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• 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: linear
• num_epochs: 5

Training results

 absence       0.75      0.53      0.62        45
presence       0.57      0.78      0.66        36

accuracy                           0.64        81

 absence       0.75      0.84      0.79        45
presence       0.77      0.64      0.70        36

accuracy                           0.75        81

 absence       0.75      0.84      0.79        45
presence       0.77      0.64      0.70        36

accuracy                           0.75        81

 absence       0.75      0.84      0.79        45
presence       0.77      0.64      0.70        36

accuracy                           0.75        81

 absence       0.75      0.84      0.79        45
presence       0.77      0.64      0.70        36

accuracy                           0.75        81

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1