--- tags: - generated_from_trainer model-index: - name: icdar23-entrydetector_labelledtext_breaks_indents_left_diff_right_ref results: [] --- # icdar23-entrydetector_labelledtext_breaks_indents_left_diff_right_ref This model is a fine-tuned version of [HueyNemud/das22-10-camembert_pretrained](https://huggingface.co/HueyNemud/das22-10-camembert_pretrained) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2515 - Act: {'precision': 0.8046783625730994, 'recall': 0.9017038007863696, 'f1': 0.8504326328800988, 'number': 1526} - Cardinal: {'precision': 0.9451428571428572, 'recall': 0.9538638985005767, 'f1': 0.9494833524684271, 'number': 2601} - Ebegin: {'precision': 0.9940431868950111, 'recall': 0.9910913140311804, 'f1': 0.9925650557620818, 'number': 2694} - Eend: {'precision': 0.9988751406074241, 'recall': 0.9859363434492968, 'f1': 0.9923635686347551, 'number': 2702} - Ft: {'precision': 0.2, 'recall': 0.2857142857142857, 'f1': 0.23529411764705882, 'number': 21} - Loc: {'precision': 0.9071332436069987, 'recall': 0.935072142064373, 'f1': 0.9208908320808854, 'number': 3604} - Per: {'precision': 0.9300651354130957, 'recall': 0.9345504650361695, 'f1': 0.9323024054982818, 'number': 2903} - Titre: {'precision': 0.5234042553191489, 'recall': 0.82, 'f1': 0.6389610389610388, 'number': 150} - Overall Precision: 0.9287 - Overall Recall: 0.9507 - Overall F1: 0.9396 - Overall Accuracy: 0.9459 ## 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: 0.0001 - 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 - training_steps: 7500 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 0.07 | 300 | 0.2219 | 0.8682 | 0.9280 | 0.8971 | 0.9525 | | 0.4302 | 0.14 | 600 | 0.1580 | 0.9429 | 0.9488 | 0.9458 | 0.9658 | | 0.4302 | 0.21 | 900 | 0.1575 | 0.9398 | 0.9429 | 0.9413 | 0.9597 | | 0.1819 | 0.29 | 1200 | 0.1236 | 0.9447 | 0.9542 | 0.9495 | 0.9686 | | 0.1537 | 0.36 | 1500 | 0.1312 | 0.9543 | 0.9486 | 0.9514 | 0.9670 | | 0.1537 | 0.43 | 1800 | 0.1337 | 0.9487 | 0.9559 | 0.9523 | 0.9679 | | 0.119 | 0.5 | 2100 | 0.1198 | 0.9554 | 0.9556 | 0.9555 | 0.9702 | | 0.119 | 0.57 | 2400 | 0.1128 | 0.9467 | 0.9641 | 0.9553 | 0.9707 | | 0.1098 | 0.64 | 2700 | 0.1215 | 0.9528 | 0.9607 | 0.9567 | 0.9713 | | 0.1118 | 0.72 | 3000 | 0.1099 | 0.9482 | 0.9635 | 0.9558 | 0.9711 | | 0.1118 | 0.79 | 3300 | 0.1140 | 0.9541 | 0.9684 | 0.9612 | 0.9727 | | 0.094 | 0.86 | 3600 | 0.0969 | 0.9581 | 0.9654 | 0.9617 | 0.9748 | | 0.094 | 0.93 | 3900 | 0.1089 | 0.9564 | 0.9664 | 0.9614 | 0.9755 | | 0.0895 | 1.0 | 4200 | 0.1158 | 0.9574 | 0.9662 | 0.9618 | 0.9746 | | 0.0626 | 1.07 | 4500 | 0.1072 | 0.9479 | 0.9709 | 0.9593 | 0.9747 | | 0.0626 | 1.14 | 4800 | 0.1060 | 0.9549 | 0.9682 | 0.9615 | 0.9735 | | 0.0474 | 1.22 | 5100 | 0.1172 | 0.9462 | 0.9718 | 0.9588 | 0.9723 | | 0.0474 | 1.29 | 5400 | 0.1019 | 0.9550 | 0.9698 | 0.9624 | 0.9764 | | 0.0554 | 1.36 | 5700 | 0.1086 | 0.9473 | 0.9700 | 0.9585 | 0.9737 | | 0.0416 | 1.43 | 6000 | 0.1175 | 0.9514 | 0.9714 | 0.9613 | 0.9737 | | 0.0416 | 1.5 | 6300 | 0.1143 | 0.9536 | 0.9718 | 0.9626 | 0.9742 | | 0.0514 | 1.57 | 6600 | 0.1113 | 0.9618 | 0.9679 | 0.9648 | 0.9749 | | 0.0514 | 1.65 | 6900 | 0.1084 | 0.9595 | 0.9709 | 0.9652 | 0.9762 | | 0.0377 | 1.72 | 7200 | 0.1102 | 0.9601 | 0.9706 | 0.9653 | 0.9759 | | 0.0437 | 1.79 | 7500 | 0.1123 | 0.9585 | 0.9710 | 0.9647 | 0.9757 | ### Framework versions - Transformers 4.26.1 - Pytorch 1.13.1+cu116 - Datasets 2.9.0 - Tokenizers 0.13.2