metadata

tags:
  - generated_from_trainer
datasets:
  - ade_drug_dosage_ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
base_model: giacomomiolo/electramed_small_scivocab
model-index:
  - name: electramed-small-ADE-DRUG-DOSAGE-ner
    results:
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: ade_drug_dosage_ner
          type: ade_drug_dosage_ner
          config: ade
          split: train
          args: ade
        metrics:
          - type: precision
            value: 0
            name: Precision
          - type: recall
            value: 0
            name: Recall
          - type: f1
            value: 0
            name: F1
          - type: accuracy
            value: 0.8697318007662835
            name: Accuracy

electramed-small-ADE-DRUG-DOSAGE-ner

This model is a fine-tuned version of 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