metadata
language:
- en
license: mit
base_model: xlnet-base-cased
tags:
- low-resource NER
- token_classification
- biomedicine
- medical NER
- generated_from_trainer
datasets:
- medicine
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: Dagobert42/xlnet-base-cased-biored-finetuned
results: []
Dagobert42/xlnet-base-cased-biored-finetuned
This model is a fine-tuned version of xlnet-base-cased on the bigbio/biored dataset. It achieves the following results on the evaluation set:
- Loss: 0.7341
- Accuracy: 0.7714
- Precision: 0.5341
- Recall: 0.4169
- F1: 0.4594
- Weighted F1: 0.7495
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: 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Weighted F1 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 25 | 0.8831 | 0.7377 | 0.4536 | 0.2481 | 0.2822 | 0.6719 |
| No log | 2.0 | 50 | 0.8309 | 0.7542 | 0.6035 | 0.3177 | 0.3598 | 0.6933 |
| No log | 3.0 | 75 | 0.7695 | 0.7624 | 0.568 | 0.3566 | 0.409 | 0.7189 |
| No log | 4.0 | 100 | 0.7562 | 0.7676 | 0.5536 | 0.3886 | 0.4398 | 0.7343 |
| No log | 5.0 | 125 | 0.7540 | 0.7673 | 0.5711 | 0.4013 | 0.4474 | 0.7368 |
| No log | 6.0 | 150 | 0.7425 | 0.7754 | 0.5867 | 0.4398 | 0.4873 | 0.7514 |
| No log | 7.0 | 175 | 0.7806 | 0.7788 | 0.606 | 0.4235 | 0.473 | 0.7475 |
| No log | 8.0 | 200 | 0.7638 | 0.7785 | 0.558 | 0.4547 | 0.4871 | 0.7549 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.15.0