metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - shared-task
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bsc-bio-ehr-es-finetuned-ner-1
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: shared-task
          type: shared-task
          config: Shared
          split: validation
          args: Shared
        metrics:
          - name: Precision
            type: precision
            value: 0.28507462686567164
          - name: Recall
            type: recall
            value: 0.3560111835973905
          - name: F1
            type: f1
            value: 0.3166183174471612
          - name: Accuracy
            type: accuracy
            value: 0.8444321635810997

bsc-bio-ehr-es-finetuned-ner-1

This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the shared-task dataset. It achieves the following results on the evaluation set:

Loss: 0.6021
Precision: 0.2851
Recall: 0.3560
F1: 0.3166
Accuracy: 0.8444

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	59	0.6644	0.2234	0.2600	0.2403	0.8198
No log	2.0	118	0.5786	0.1997	0.2507	0.2223	0.8331
No log	3.0	177	0.6083	0.2732	0.3187	0.2942	0.8379
No log	4.0	236	0.6032	0.2855	0.3486	0.3139	0.8366
No log	5.0	295	0.6021	0.2851	0.3560	0.3166	0.8444

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3