--- license: apache-2.0 tags: - generated_from_trainer base_model: facebook/bart-large metrics: - accuracy - precision - recall model-index: - name: bart-large results: [] --- # bart-large This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.0027 - Accuracy: 0.7916 - Precision: 0.7858 - Recall: 0.7916 - Precision Macro: 0.7201 - Recall Macro: 0.7056 - Macro Fpr: 0.0201 - Weighted Fpr: 0.0195 - Weighted Specificity: 0.9714 - Macro Specificity: 0.9836 - Weighted Sensitivity: 0.7823 - Macro Sensitivity: 0.7056 - F1 Micro: 0.7823 - F1 Macro: 0.7080 - F1 Weighted: 0.7801 ## 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: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 30 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:| | 1.1685 | 1.0 | 2569 | 1.2587 | 0.6847 | 0.6360 | 0.6847 | 0.4176 | 0.4720 | 0.0331 | 0.0318 | 0.9550 | 0.9760 | 0.6847 | 0.4720 | 0.6847 | 0.4296 | 0.6471 | | 1.1965 | 2.0 | 5138 | 1.1623 | 0.6638 | 0.6943 | 0.6638 | 0.4564 | 0.4261 | 0.0342 | 0.0349 | 0.9654 | 0.9753 | 0.6638 | 0.4261 | 0.6638 | 0.3955 | 0.6468 | | 1.189 | 3.0 | 7707 | 1.3574 | 0.7235 | 0.7220 | 0.7235 | 0.5413 | 0.5528 | 0.0271 | 0.0266 | 0.9628 | 0.9791 | 0.7235 | 0.5528 | 0.7235 | 0.5196 | 0.7031 | | 1.0127 | 4.0 | 10276 | 1.4685 | 0.7668 | 0.7584 | 0.7668 | 0.6671 | 0.6202 | 0.0224 | 0.0213 | 0.9653 | 0.9821 | 0.7668 | 0.6202 | 0.7668 | 0.6233 | 0.7569 | | 1.0205 | 5.0 | 12845 | 1.4232 | 0.7668 | 0.7711 | 0.7668 | 0.6765 | 0.6872 | 0.0215 | 0.0213 | 0.9737 | 0.9827 | 0.7668 | 0.6872 | 0.7668 | 0.6732 | 0.7643 | | 0.7927 | 6.0 | 15414 | 1.5678 | 0.7428 | 0.7451 | 0.7428 | 0.6489 | 0.6333 | 0.0248 | 0.0241 | 0.9690 | 0.9808 | 0.7428 | 0.6333 | 0.7428 | 0.6108 | 0.7292 | | 0.7701 | 7.0 | 17983 | 1.7337 | 0.7467 | 0.7600 | 0.7467 | 0.6863 | 0.6536 | 0.0240 | 0.0237 | 0.9680 | 0.9810 | 0.7467 | 0.6536 | 0.7467 | 0.6584 | 0.7399 | | 0.584 | 8.0 | 20552 | 1.6188 | 0.7692 | 0.7766 | 0.7692 | 0.6979 | 0.7065 | 0.0214 | 0.0210 | 0.9706 | 0.9827 | 0.7692 | 0.7065 | 0.7692 | 0.6980 | 0.7683 | | 0.5659 | 9.0 | 23121 | 1.6983 | 0.7599 | 0.7665 | 0.7599 | 0.7000 | 0.6804 | 0.0227 | 0.0221 | 0.9695 | 0.9820 | 0.7599 | 0.6804 | 0.7599 | 0.6728 | 0.7542 | | 0.7021 | 10.0 | 25690 | 1.6445 | 0.7699 | 0.7656 | 0.7699 | 0.7144 | 0.6857 | 0.0223 | 0.0209 | 0.9608 | 0.9821 | 0.7699 | 0.6857 | 0.7699 | 0.6954 | 0.7634 | | 0.6216 | 11.0 | 28259 | 1.6562 | 0.7676 | 0.7634 | 0.7676 | 0.6856 | 0.6776 | 0.0223 | 0.0212 | 0.9640 | 0.9821 | 0.7676 | 0.6776 | 0.7676 | 0.6786 | 0.7624 | | 0.6408 | 12.0 | 30828 | 1.6682 | 0.7668 | 0.7629 | 0.7668 | 0.6706 | 0.6719 | 0.0223 | 0.0213 | 0.9666 | 0.9822 | 0.7668 | 0.6719 | 0.7668 | 0.6666 | 0.7608 | | 0.523 | 13.0 | 33397 | 1.7727 | 0.7653 | 0.7674 | 0.7653 | 0.8238 | 0.6934 | 0.0226 | 0.0214 | 0.9659 | 0.9821 | 0.7653 | 0.6934 | 0.7653 | 0.7066 | 0.7534 | | 0.3688 | 14.0 | 35966 | 1.8404 | 0.7792 | 0.7788 | 0.7792 | 0.7229 | 0.6921 | 0.0209 | 0.0198 | 0.9675 | 0.9831 | 0.7792 | 0.6921 | 0.7792 | 0.6960 | 0.7731 | | 0.2394 | 15.0 | 38535 | 1.7885 | 0.7816 | 0.7809 | 0.7816 | 0.7441 | 0.7115 | 0.0210 | 0.0196 | 0.9628 | 0.9830 | 0.7816 | 0.7115 | 0.7816 | 0.7230 | 0.7765 | | 0.2734 | 16.0 | 41104 | 1.8944 | 0.7777 | 0.7870 | 0.7777 | 0.7539 | 0.7265 | 0.0203 | 0.0200 | 0.9724 | 0.9833 | 0.7777 | 0.7265 | 0.7777 | 0.7295 | 0.7777 | | 0.4319 | 17.0 | 43673 | 1.7744 | 0.7885 | 0.7847 | 0.7885 | 0.7247 | 0.7320 | 0.0195 | 0.0188 | 0.9718 | 0.9840 | 0.7885 | 0.7320 | 0.7885 | 0.7269 | 0.7855 | | 0.2347 | 18.0 | 46242 | 2.0036 | 0.7413 | 0.7352 | 0.7413 | 0.6934 | 0.6799 | 0.0255 | 0.0243 | 0.9597 | 0.9801 | 0.7413 | 0.6799 | 0.7413 | 0.6825 | 0.7354 | | 0.1882 | 19.0 | 48811 | 1.9298 | 0.7816 | 0.7804 | 0.7816 | 0.7243 | 0.7262 | 0.0202 | 0.0196 | 0.9708 | 0.9835 | 0.7816 | 0.7262 | 0.7816 | 0.7225 | 0.7792 | | 0.1799 | 20.0 | 51380 | 1.9688 | 0.7792 | 0.7892 | 0.7792 | 0.7312 | 0.7343 | 0.0205 | 0.0198 | 0.9714 | 0.9834 | 0.7792 | 0.7343 | 0.7792 | 0.7242 | 0.7779 | | 0.1366 | 21.0 | 53949 | 1.9910 | 0.7847 | 0.7846 | 0.7847 | 0.7148 | 0.7455 | 0.0198 | 0.0192 | 0.9730 | 0.9838 | 0.7847 | 0.7455 | 0.7847 | 0.7265 | 0.7833 | | 0.1793 | 22.0 | 56518 | 2.2548 | 0.7630 | 0.7648 | 0.7630 | 0.7150 | 0.7273 | 0.0230 | 0.0217 | 0.9633 | 0.9818 | 0.7630 | 0.7273 | 0.7630 | 0.7150 | 0.7582 | | 0.1749 | 23.0 | 59087 | 2.1109 | 0.7816 | 0.7768 | 0.7816 | 0.7466 | 0.7230 | 0.0205 | 0.0196 | 0.9690 | 0.9834 | 0.7816 | 0.7230 | 0.7816 | 0.7289 | 0.7774 | | 0.1154 | 24.0 | 61656 | 2.0637 | 0.7878 | 0.7837 | 0.7878 | 0.7590 | 0.7269 | 0.0196 | 0.0189 | 0.9718 | 0.9840 | 0.7878 | 0.7269 | 0.7878 | 0.7331 | 0.7828 | | 0.1447 | 25.0 | 64225 | 2.0027 | 0.7916 | 0.7858 | 0.7916 | 0.7750 | 0.7299 | 0.0194 | 0.0185 | 0.9697 | 0.9841 | 0.7916 | 0.7299 | 0.7916 | 0.7408 | 0.7861 | | 0.0806 | 26.0 | 66794 | 2.0777 | 0.7885 | 0.7831 | 0.7885 | 0.7162 | 0.7134 | 0.0196 | 0.0188 | 0.9715 | 0.9840 | 0.7885 | 0.7134 | 0.7885 | 0.7118 | 0.7840 | | 0.0407 | 27.0 | 69363 | 2.1754 | 0.7885 | 0.7863 | 0.7885 | 0.7192 | 0.7080 | 0.0194 | 0.0188 | 0.9725 | 0.9841 | 0.7885 | 0.7080 | 0.7885 | 0.7105 | 0.7866 | | 0.0701 | 28.0 | 71932 | 2.1578 | 0.7823 | 0.7817 | 0.7823 | 0.7130 | 0.7097 | 0.0201 | 0.0195 | 0.9714 | 0.9836 | 0.7823 | 0.7097 | 0.7823 | 0.7066 | 0.7810 | | 0.1034 | 29.0 | 74501 | 2.2132 | 0.7800 | 0.7789 | 0.7800 | 0.7163 | 0.7044 | 0.0203 | 0.0197 | 0.9713 | 0.9834 | 0.7800 | 0.7044 | 0.7800 | 0.7064 | 0.7785 | | 0.0388 | 30.0 | 77070 | 2.1833 | 0.7823 | 0.7806 | 0.7823 | 0.7201 | 0.7056 | 0.0201 | 0.0195 | 0.9714 | 0.9836 | 0.7823 | 0.7056 | 0.7823 | 0.7080 | 0.7801 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.19.0 - Tokenizers 0.15.1