metadata

license: apache-2.0
base_model: Dr-BERT/DrBERT-7GB
tags:
  - generated_from_trainer
datasets:
  - quaero
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: drbert-7gb-finedtuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: quaero
          type: quaero
          config: medline
          split: validation
          args: medline
        metrics:
          - name: Precision
            type: precision
            value: 0.5218963439132182
          - name: Recall
            type: recall
            value: 0.5781041388518025
          - name: F1
            type: f1
            value: 0.5485641891891893
          - name: Accuracy
            type: accuracy
            value: 0.8009761388286334

drbert-7gb-finedtuned-ner

This model is a fine-tuned version of Dr-BERT/DrBERT-7GB on the quaero dataset. It achieves the following results on the evaluation set:

Loss: 1.4328
Precision: 0.5219
Recall: 0.5781
F1: 0.5486
Accuracy: 0.8010

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
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	105	0.7200	0.4493	0.4833	0.4657	0.7785
No log	2.0	210	0.7287	0.4381	0.5056	0.4694	0.7791
No log	3.0	315	0.8443	0.4635	0.5207	0.4905	0.7823
No log	4.0	420	1.0059	0.4780	0.5269	0.5013	0.7835
0.4225	5.0	525	0.9944	0.4688	0.5545	0.5081	0.7806
0.4225	6.0	630	1.0721	0.5104	0.5367	0.5232	0.7944
0.4225	7.0	735	1.1099	0.4829	0.5639	0.5202	0.7933
0.4225	8.0	840	1.2544	0.4814	0.5527	0.5146	0.7779
0.4225	9.0	945	1.2083	0.4823	0.5639	0.5199	0.7905
0.0481	10.0	1050	1.3132	0.4892	0.5621	0.5231	0.7924
0.0481	11.0	1155	1.3484	0.5040	0.5665	0.5334	0.7942
0.0481	12.0	1260	1.3297	0.5042	0.5585	0.5300	0.7989
0.0481	13.0	1365	1.3890	0.5023	0.5741	0.5358	0.7955
0.0481	14.0	1470	1.4140	0.5111	0.5639	0.5362	0.7985
0.009	15.0	1575	1.4130	0.5226	0.5550	0.5383	0.7996
0.009	16.0	1680	1.4197	0.5127	0.5639	0.5371	0.7964
0.009	17.0	1785	1.4166	0.5262	0.5723	0.5483	0.8015
0.009	18.0	1890	1.4257	0.5173	0.5781	0.5460	0.8004
0.009	19.0	1995	1.4318	0.5203	0.5817	0.5493	0.8011
0.0018	20.0	2100	1.4328	0.5219	0.5781	0.5486	0.8010

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2