| | --- |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - ade_drug_effect_ner |
| | metrics: |
| | - precision |
| | - recall |
| | - f1 |
| | - accuracy |
| | model-index: |
| | - name: electramed-small-ADE-DRUG-EFFECT-ner |
| | results: |
| | - task: |
| | name: Token Classification |
| | type: token-classification |
| | dataset: |
| | name: ade_drug_effect_ner |
| | type: ade_drug_effect_ner |
| | config: ade |
| | split: train |
| | args: ade |
| | metrics: |
| | - name: Precision |
| | type: precision |
| | value: 0.7745054945054946 |
| | - name: Recall |
| | type: recall |
| | value: 0.6555059523809523 |
| | - name: F1 |
| | type: f1 |
| | value: 0.7100544025790851 |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.9310355073540336 |
| | --- |
| | |
| | <!-- 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-EFFECT-ner |
| |
|
| | This model is a fine-tuned version of [giacomomiolo/electramed_small_scivocab](https://huggingface.co/giacomomiolo/electramed_small_scivocab) on the ade_drug_effect_ner dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.1630 |
| | - Precision: 0.7745 |
| | - Recall: 0.6555 |
| | - F1: 0.7101 |
| | - Accuracy: 0.9310 |
| | |
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | | 0.4498 | 1.0 | 336 | 0.3042 | 0.5423 | 0.6295 | 0.5826 | 0.9114 | |
| | | 0.2572 | 2.0 | 672 | 0.2146 | 0.7596 | 0.6194 | 0.6824 | 0.9276 | |
| | | 0.1542 | 3.0 | 1008 | 0.1894 | 0.7806 | 0.6168 | 0.6891 | 0.9299 | |
| | | 0.1525 | 4.0 | 1344 | 0.1771 | 0.7832 | 0.625 | 0.6952 | 0.9309 | |
| | | 0.1871 | 5.0 | 1680 | 0.1723 | 0.7271 | 0.6920 | 0.7091 | 0.9304 | |
| | | 0.1425 | 6.0 | 2016 | 0.1683 | 0.7300 | 0.6979 | 0.7136 | 0.9297 | |
| | | 0.1638 | 7.0 | 2352 | 0.1654 | 0.7432 | 0.6771 | 0.7086 | 0.9306 | |
| | | 0.1592 | 8.0 | 2688 | 0.1635 | 0.7613 | 0.6585 | 0.7062 | 0.9305 | |
| | | 0.1882 | 9.0 | 3024 | 0.1625 | 0.7858 | 0.6373 | 0.7038 | 0.9309 | |
| | | 0.1339 | 10.0 | 3360 | 0.1630 | 0.7745 | 0.6555 | 0.7101 | 0.9310 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.22.1 |
| | - Pytorch 1.12.1+cu113 |
| | - Datasets 2.4.0 |
| | - Tokenizers 0.12.1 |
| | |
