--- 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: 5.9825 ## 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: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 5.9707 | 0.09 | 5 | 6.0008 | | 5.9661 | 0.18 | 10 | 5.9998 | | 5.9659 | 0.27 | 15 | 5.9987 | | 5.9441 | 0.36 | 20 | 5.9974 | | 5.9937 | 0.45 | 25 | 5.9965 | | 5.9483 | 0.55 | 30 | 5.9953 | | 5.9214 | 0.64 | 35 | 5.9945 | | 5.9332 | 0.73 | 40 | 5.9937 | | 5.9383 | 0.82 | 45 | 5.9926 | | 5.9223 | 0.91 | 50 | 5.9919 | | 5.9233 | 1.0 | 55 | 5.9911 | | 5.8762 | 1.09 | 60 | 5.9905 | | 5.8967 | 1.18 | 65 | 5.9899 | | 5.9024 | 1.27 | 70 | 5.9891 | | 5.9122 | 1.36 | 75 | 5.9885 | | 5.902 | 1.45 | 80 | 5.9879 | | 5.874 | 1.55 | 85 | 5.9872 | | 5.8774 | 1.64 | 90 | 5.9867 | | 5.8782 | 1.73 | 95 | 5.9862 | | 5.8664 | 1.82 | 100 | 5.9857 | | 5.8833 | 1.91 | 105 | 5.9852 | | 5.8488 | 2.0 | 110 | 5.9848 | | 5.8747 | 2.09 | 115 | 5.9843 | | 5.8333 | 2.18 | 120 | 5.9840 | | 5.8573 | 2.27 | 125 | 5.9837 | | 5.8398 | 2.36 | 130 | 5.9834 | | 5.8371 | 2.45 | 135 | 5.9832 | | 5.8274 | 2.55 | 140 | 5.9831 | | 5.863 | 2.64 | 145 | 5.9829 | | 5.8183 | 2.73 | 150 | 5.9827 | | 5.8448 | 2.82 | 155 | 5.9826 | | 5.9111 | 2.91 | 160 | 5.9825 | | 5.8316 | 3.0 | 165 | 5.9825 | ### Framework versions - Transformers 4.34.1 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.14.1