--- license: apache-2.0 base_model: google-bert/bert-base-multilingual-cased tags: - generated_from_trainer metrics: - accuracy - recall - precision model-index: - name: content results: [] --- # content This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4643 - Accuracy: 0.7959 - F1-score: 0.7686 - Recall: 0.8062 - Precision: 0.7343 ## 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: 2.5e-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: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Recall | Precision | |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:------:|:---------:| | 0.5842 | 0.3814 | 500 | 0.5475 | 0.7275 | 0.7439 | 0.8704 | 0.6496 | | 0.5066 | 0.7628 | 1000 | 0.5066 | 0.7527 | 0.7544 | 0.8351 | 0.6879 | | 0.4702 | 1.1442 | 1500 | 0.5164 | 0.7524 | 0.7611 | 0.8672 | 0.6781 | | 0.4287 | 1.5256 | 2000 | 0.4908 | 0.7902 | 0.7760 | 0.7992 | 0.7542 | | 0.428 | 1.9069 | 2500 | 0.5179 | 0.7553 | 0.7643 | 0.8722 | 0.6801 | | 0.368 | 2.2883 | 3000 | 0.5774 | 0.7476 | 0.7377 | 0.7804 | 0.6994 | | 0.3507 | 2.6697 | 3500 | 0.5190 | 0.7770 | 0.7784 | 0.8609 | 0.7103 | | 0.3285 | 3.0511 | 4000 | 0.6028 | 0.7745 | 0.7684 | 0.8225 | 0.7209 | | 0.2697 | 3.4325 | 4500 | 0.5910 | 0.7725 | 0.7745 | 0.8590 | 0.7051 | | 0.2697 | 3.8139 | 5000 | 0.5870 | 0.7679 | 0.7554 | 0.7879 | 0.7254 | | 0.2274 | 4.1953 | 5500 | 0.7693 | 0.7690 | 0.7558 | 0.7860 | 0.7279 | | 0.2076 | 4.5767 | 6000 | 0.7267 | 0.7676 | 0.7535 | 0.7810 | 0.7279 | | 0.2057 | 4.9580 | 6500 | 0.7228 | 0.7653 | 0.7494 | 0.7716 | 0.7285 | ### Framework versions - Transformers 4.42.4 - Pytorch 2.3.1+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1