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: 0.7909
- Accuracy: 0.756
- Precision: 0.5226
- Recall: 0.3518
- F1: 0.4027
- Weighted F1: 0.7173
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 | 13 | 0.9045 | 0.7251 | 0.3378 | 0.1564 | 0.1457 | 0.6233 |
| No log | 2.0 | 26 | 0.8688 | 0.7336 | 0.5559 | 0.2281 | 0.2504 | 0.6453 |
| No log | 3.0 | 39 | 0.8579 | 0.7409 | 0.5851 | 0.2931 | 0.3179 | 0.6795 |
| No log | 4.0 | 52 | 0.7956 | 0.7507 | 0.5225 | 0.3443 | 0.3919 | 0.7017 |
| No log | 5.0 | 65 | 0.7947 | 0.7529 | 0.532 | 0.3535 | 0.4026 | 0.7093 |
| No log | 6.0 | 78 | 0.8063 | 0.7549 | 0.5502 | 0.3752 | 0.4191 | 0.7168 |
| No log | 7.0 | 91 | 0.8059 | 0.7599 | 0.5496 | 0.3764 | 0.4269 | 0.7227 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.15.0