README.md

metadata

library_name: transformers
license: apache-2.0
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
tags:
  - token-classification
  - generated_from_trainer
datasets:
  - Rodrigo1771/drugtemist-fasttext-75-ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: output
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: Rodrigo1771/drugtemist-fasttext-75-ner
          type: Rodrigo1771/drugtemist-fasttext-75-ner
          config: DrugTEMIST NER
          split: validation
          args: DrugTEMIST NER
        metrics:
          - name: Precision
            type: precision
            value: 0.9447963800904977
          - name: Recall
            type: recall
            value: 0.9595588235294118
          - name: F1
            type: f1
            value: 0.9521203830369357
          - name: Accuracy
            type: accuracy
            value: 0.9991418018042759

output

This model is a fine-tuned version of PlanTL-GOB-ES/bsc-bio-ehr-es on the Rodrigo1771/drugtemist-fasttext-75-ner dataset. It achieves the following results on the evaluation set:

• Loss: 0.0044
• Precision: 0.9448
• Recall: 0.9596
• F1: 0.9521
• Accuracy: 0.9991

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: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	488	0.0039	0.9005	0.9733	0.9355	0.9988
0.0189	2.0	976	0.0032	0.9239	0.9596	0.9414	0.9989
0.0027	3.0	1464	0.0044	0.9192	0.9623	0.9403	0.9989
0.0015	4.0	1952	0.0036	0.9424	0.9467	0.9445	0.9991
0.0007	5.0	2440	0.0044	0.9448	0.9596	0.9521	0.9991
0.0004	6.0	2928	0.0055	0.9594	0.9338	0.9464	0.9990
0.0002	7.0	3416	0.0049	0.9397	0.9458	0.9427	0.9990
0.0002	8.0	3904	0.0053	0.9434	0.9504	0.9469	0.9991
0.0001	9.0	4392	0.0050	0.9434	0.9494	0.9464	0.9991
0.0001	10.0	4880	0.0052	0.9417	0.9494	0.9455	0.9991

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1