--- license: apache-2.0 base_model: google-bert/bert-base-multilingual-cased tags: - generated_from_trainer metrics: - precision - recall - f1 - accuracy model-index: - name: bert-base-multilingual-cased-finetuned-ner-geocorpus results: [] --- # bert-base-multilingual-cased-finetuned-ner-geocorpus This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1098 - Precision: 0.8046 - Recall: 0.8681 - F1: 0.8352 - Accuracy: 0.9718 ## 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: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | No log | 1.0 | 276 | 0.1803 | 0.7390 | 0.6469 | 0.6899 | 0.9556 | | 0.2476 | 2.0 | 552 | 0.1196 | 0.8330 | 0.7767 | 0.8039 | 0.9699 | | 0.2476 | 3.0 | 828 | 0.1157 | 0.8719 | 0.7778 | 0.8222 | 0.9717 | | 0.0766 | 4.0 | 1104 | 0.1229 | 0.7866 | 0.8806 | 0.8310 | 0.9717 | | 0.0766 | 5.0 | 1380 | 0.1105 | 0.8567 | 0.8692 | 0.8629 | 0.9761 | | 0.0393 | 6.0 | 1656 | 0.1098 | 0.8046 | 0.8681 | 0.8352 | 0.9718 | | 0.0393 | 7.0 | 1932 | 0.1180 | 0.8663 | 0.8744 | 0.8703 | 0.9786 | | 0.0236 | 8.0 | 2208 | 0.1294 | 0.8293 | 0.8982 | 0.8624 | 0.9744 | | 0.0236 | 9.0 | 2484 | 0.1337 | 0.8864 | 0.8505 | 0.8680 | 0.9781 | ### Framework versions - Transformers 4.41.1 - Pytorch 2.1.2 - Datasets 2.19.1 - Tokenizers 0.19.1