--- license: mit base_model: emilyalsentzer/Bio_ClinicalBERT tags: - generated_from_trainer model-index: - name: CliBert-20 results: [] --- # CliBert-20 This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 5.8847 ## 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: 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: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 5.8842 | 0.09 | 5 | 5.9152 | | 5.7961 | 0.18 | 10 | 5.9106 | | 5.7777 | 0.27 | 15 | 5.9060 | | 5.7638 | 0.36 | 20 | 5.9016 | | 5.7282 | 0.45 | 25 | 5.8980 | | 5.6804 | 0.55 | 30 | 5.8942 | | 5.6095 | 0.64 | 35 | 5.8912 | | 5.5418 | 0.73 | 40 | 5.8890 | | 5.5853 | 0.82 | 45 | 5.8864 | | 5.55 | 0.91 | 50 | 5.8844 | | 5.5284 | 1.0 | 55 | 5.8828 | | 5.4085 | 1.09 | 60 | 5.8818 | | 5.368 | 1.18 | 65 | 5.8812 | | 5.4048 | 1.27 | 70 | 5.8807 | | 5.4172 | 1.36 | 75 | 5.8802 | | 5.4134 | 1.45 | 80 | 5.8796 | | 5.4728 | 1.55 | 85 | 5.8791 | | 5.3326 | 1.64 | 90 | 5.8787 | | 5.3464 | 1.73 | 95 | 5.8789 | | 5.3447 | 1.82 | 100 | 5.8791 | | 5.3264 | 1.91 | 105 | 5.8793 | | 5.2265 | 2.0 | 110 | 5.8797 | | 5.1223 | 2.09 | 115 | 5.8803 | | 5.232 | 2.18 | 120 | 5.8811 | | 5.3772 | 2.27 | 125 | 5.8815 | | 5.2502 | 2.36 | 130 | 5.8821 | | 5.2293 | 2.45 | 135 | 5.8825 | | 5.1182 | 2.55 | 140 | 5.8832 | | 5.0885 | 2.64 | 145 | 5.8839 | | 5.157 | 2.73 | 150 | 5.8844 | | 5.3388 | 2.82 | 155 | 5.8845 | | 5.2609 | 2.91 | 160 | 5.8846 | | 5.2008 | 3.0 | 165 | 5.8847 | ### Framework versions - Transformers 4.34.1 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.1