README.md

metadata

license: apache-2.0
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
tags:
  - token-classification
  - generated_from_trainer
datasets:
  - Rodrigo1771/multi-train-distemist-dev-ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: output
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: Rodrigo1771/multi-train-distemist-dev-ner
          type: Rodrigo1771/multi-train-distemist-dev-ner
          config: MultiTrainDisTEMISTDevNER
          split: validation
          args: MultiTrainDisTEMISTDevNER
        metrics:
          - name: Precision
            type: precision
            value: 0.32143181611701643
          - name: Recall
            type: recall
            value: 0.8277959756668226
          - name: F1
            type: f1
            value: 0.46305870034683594
          - name: Accuracy
            type: accuracy
            value: 0.8559776451929613

output

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

• Loss: 0.9499
• Precision: 0.3214
• Recall: 0.8278
• F1: 0.4631
• Accuracy: 0.8560

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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
0.2596	0.9997	1701	0.4319	0.2617	0.7866	0.3927	0.8359
0.1853	2.0	3403	0.3841	0.3142	0.7829	0.4485	0.8645
0.1254	2.9997	5104	0.6410	0.3055	0.8088	0.4435	0.8436
0.0823	4.0	6806	0.7242	0.2964	0.8074	0.4336	0.8436
0.0597	4.9997	8507	0.7756	0.3133	0.7948	0.4495	0.8502
0.0446	6.0	10209	0.8561	0.3137	0.8037	0.4513	0.8483
0.0325	6.9997	11910	0.9499	0.3214	0.8278	0.4631	0.8560
0.022	8.0	13612	1.0452	0.3129	0.8222	0.4533	0.8510
0.017	8.9997	15313	1.1025	0.3133	0.8180	0.4531	0.8524
0.0135	9.9971	17010	1.1188	0.3145	0.8224	0.4550	0.8526

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1