---
tags:
- generated_from_trainer
datasets:
- ade_drug_effect_ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: electramed-small-ADE-DRUG-EFFECT-ner-v3
  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: 0.7436108821104699
    - name: Recall
      type: recall
      value: 0.6711309523809523
    - name: F1
      type: f1
      value: 0.7055142745404771
    - name: Accuracy
      type: accuracy
      value: 0.9334986406954859
---

<!-- 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-v3

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: 0.1626
- Precision: 0.7436
- Recall: 0.6711
- F1: 0.7055
- Accuracy: 0.9335

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.3393        | 1.0   | 336  | 0.3055          | 0.6126    | 0.6648 | 0.6376 | 0.9218   |
| 0.2503        | 2.0   | 672  | 0.2138          | 0.7025    | 0.6905 | 0.6964 | 0.9300   |
| 0.1494        | 3.0   | 1008 | 0.1879          | 0.7342    | 0.6555 | 0.6926 | 0.9326   |
| 0.1152        | 4.0   | 1344 | 0.1755          | 0.7323    | 0.6797 | 0.7050 | 0.9327   |
| 0.178         | 5.0   | 1680 | 0.1726          | 0.7279    | 0.6827 | 0.7045 | 0.9326   |
| 0.1814        | 6.0   | 2016 | 0.1654          | 0.7358    | 0.6734 | 0.7032 | 0.9332   |
| 0.1292        | 7.0   | 2352 | 0.1641          | 0.7332    | 0.6849 | 0.7082 | 0.9336   |
| 0.1107        | 8.0   | 2688 | 0.1638          | 0.7520    | 0.6522 | 0.6985 | 0.9337   |
| 0.1911        | 9.0   | 3024 | 0.1625          | 0.7503    | 0.6596 | 0.7020 | 0.9331   |
| 0.1517        | 10.0  | 3360 | 0.1626          | 0.7436    | 0.6711 | 0.7055 | 0.9335   |


### Framework versions

- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1