--- license: apache-2.0 base_model: bert-base-multilingual-cased tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: FrozenLAST-BERT-multilingual-finetuned-CEFR_ner-3000news results: [] --- # FrozenLAST-BERT-multilingual-finetuned-CEFR_ner-3000news This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5231 - Accuracy: 0.4029 - Precision: 0.4730 - Recall: 0.6519 - F1: 0.4491 ## 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: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 12 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| | No log | 1.0 | 132 | 0.6719 | 0.3466 | 0.5010 | 0.4385 | 0.3075 | | No log | 2.0 | 264 | 0.5498 | 0.3741 | 0.5375 | 0.5142 | 0.3600 | | No log | 3.0 | 396 | 0.4966 | 0.3872 | 0.4761 | 0.5740 | 0.3970 | | 0.6209 | 4.0 | 528 | 0.4753 | 0.3937 | 0.4654 | 0.5910 | 0.4146 | | 0.6209 | 5.0 | 660 | 0.4714 | 0.3952 | 0.4558 | 0.6100 | 0.4200 | | 0.6209 | 6.0 | 792 | 0.4684 | 0.3989 | 0.4640 | 0.6139 | 0.4275 | | 0.6209 | 7.0 | 924 | 0.4813 | 0.3994 | 0.4673 | 0.6276 | 0.4376 | | 0.2738 | 8.0 | 1056 | 0.4890 | 0.4015 | 0.4760 | 0.6404 | 0.4470 | | 0.2738 | 9.0 | 1188 | 0.5157 | 0.4013 | 0.4723 | 0.6386 | 0.4432 | | 0.2738 | 10.0 | 1320 | 0.5229 | 0.4019 | 0.4665 | 0.6498 | 0.4433 | | 0.2738 | 11.0 | 1452 | 0.5188 | 0.4024 | 0.4673 | 0.6529 | 0.4448 | | 0.1745 | 12.0 | 1584 | 0.5231 | 0.4029 | 0.4730 | 0.6519 | 0.4491 | ### Framework versions - Transformers 4.41.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1