| | --- |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - ade_drug_dosage_ner |
| | metrics: |
| | - precision |
| | - recall |
| | - f1 |
| | - accuracy |
| | model-index: |
| | - name: electramed-small-ADE-DRUG-DOSAGE-ner |
| | results: |
| | - task: |
| | name: Token Classification |
| | type: token-classification |
| | dataset: |
| | name: ade_drug_dosage_ner |
| | type: ade_drug_dosage_ner |
| | config: ade |
| | split: train |
| | args: ade |
| | metrics: |
| | - name: Precision |
| | type: precision |
| | value: 0.0 |
| | - name: Recall |
| | type: recall |
| | value: 0.0 |
| | - name: F1 |
| | type: f1 |
| | value: 0.0 |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.8697318007662835 |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # electramed-small-ADE-DRUG-DOSAGE-ner |
| |
|
| | This model is a fine-tuned version of [giacomomiolo/electramed_small_scivocab](https://huggingface.co/giacomomiolo/electramed_small_scivocab) on the ade_drug_dosage_ner dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.6064 |
| | - Precision: 0.0 |
| | - Recall: 0.0 |
| | - F1: 0.0 |
| | - Accuracy: 0.8697 |
| | |
| | ## 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: 10 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | | 1.4165 | 1.0 | 14 | 1.3965 | 0.0255 | 0.0636 | 0.0365 | 0.7471 | |
| | | 1.2063 | 2.0 | 28 | 1.1702 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.9527 | 3.0 | 42 | 0.9342 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.8238 | 4.0 | 56 | 0.7775 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.7452 | 5.0 | 70 | 0.6945 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.6386 | 6.0 | 84 | 0.6519 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.6742 | 7.0 | 98 | 0.6294 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.6669 | 8.0 | 112 | 0.6162 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.6595 | 9.0 | 126 | 0.6090 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | | 0.6122 | 10.0 | 140 | 0.6064 | 0.0 | 0.0 | 0.0 | 0.8697 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.22.1 |
| | - Pytorch 1.12.1+cu113 |
| | - Datasets 2.4.0 |
| | - Tokenizers 0.12.1 |
| | |
