metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - jxner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: medicine-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: jxner
          type: jxner
          config: wnut_17
          split: test
          args: wnut_17
        metrics:
          - name: Precision
            type: precision
            value: 0
          - name: Recall
            type: recall
            value: 0
          - name: F1
            type: f1
            value: 0
          - name: Accuracy
            type: accuracy
            value: 0.9

medicine-ner

This model is a fine-tuned version of distilbert-base-uncased on the jxner dataset. It achieves the following results on the evaluation set:

Loss: 0.5562
Precision: 0.0
Recall: 0.0
F1: 0.0
Accuracy: 0.9

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	1	1.7398	0.0370	0.125	0.0571	0.65
No log	2.0	2	1.5750	0.0	0.0	0.0	0.86
No log	3.0	3	1.4146	0.0	0.0	0.0	0.88
No log	4.0	4	1.2611	0.0	0.0	0.0	0.9
No log	5.0	5	1.1173	0.0	0.0	0.0	0.9
No log	6.0	6	0.9869	0.0	0.0	0.0	0.9
No log	7.0	7	0.8737	0.0	0.0	0.0	0.9
No log	8.0	8	0.7804	0.0	0.0	0.0	0.9
No log	9.0	9	0.7074	0.0	0.0	0.0	0.9
No log	10.0	10	0.6545	0.0	0.0	0.0	0.9
No log	11.0	11	0.6181	0.0	0.0	0.0	0.9
No log	12.0	12	0.5938	0.0	0.0	0.0	0.9
No log	13.0	13	0.5780	0.0	0.0	0.0	0.9
No log	14.0	14	0.5682	0.0	0.0	0.0	0.9
No log	15.0	15	0.5623	0.0	0.0	0.0	0.9
No log	16.0	16	0.5589	0.0	0.0	0.0	0.9
No log	17.0	17	0.5571	0.0	0.0	0.0	0.9
No log	18.0	18	0.5563	0.0	0.0	0.0	0.9
No log	19.0	19	0.5562	0.0	0.0	0.0	0.9
No log	20.0	20	0.5562	0.0	0.0	0.0	0.9

Framework versions

Transformers 4.27.3
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2