metadata
license: apache-2.0
base_model: Dr-BERT/DrBERT-7GB
tags:
- generated_from_trainer
datasets:
- quaero
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: drbert-7gb-finedtuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: quaero
type: quaero
config: medline
split: validation
args: medline
metrics:
- name: Precision
type: precision
value: 0.5105965463108321
- name: Recall
type: recall
value: 0.5789942145082332
- name: F1
type: f1
value: 0.5426485922836287
- name: Accuracy
type: accuracy
value: 0.8011795010845987
drbert-7gb-finedtuned-ner
This model is a fine-tuned version of Dr-BERT/DrBERT-7GB on the quaero dataset. It achieves the following results on the evaluation set:
- Loss: 1.2226
- Precision: 0.5106
- Recall: 0.5790
- F1: 0.5426
- Accuracy: 0.8012
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 105 | 0.7160 | 0.4596 | 0.4713 | 0.4654 | 0.7764 |
No log | 2.0 | 210 | 0.6985 | 0.4484 | 0.5220 | 0.4824 | 0.7831 |
No log | 3.0 | 315 | 0.8448 | 0.4872 | 0.5234 | 0.5046 | 0.7881 |
No log | 4.0 | 420 | 0.9029 | 0.5231 | 0.5403 | 0.5315 | 0.8017 |
0.4116 | 5.0 | 525 | 1.0169 | 0.4813 | 0.5656 | 0.5200 | 0.7892 |
0.4116 | 6.0 | 630 | 1.0596 | 0.5150 | 0.5665 | 0.5395 | 0.7986 |
0.4116 | 7.0 | 735 | 1.1298 | 0.4954 | 0.5705 | 0.5303 | 0.8000 |
0.4116 | 8.0 | 840 | 1.1665 | 0.4949 | 0.5803 | 0.5342 | 0.7984 |
0.4116 | 9.0 | 945 | 1.2045 | 0.5135 | 0.5754 | 0.5427 | 0.8025 |
0.0254 | 10.0 | 1050 | 1.2226 | 0.5106 | 0.5790 | 0.5426 | 0.8012 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2