metadata
license: apache-2.0
base_model: distilbert-base-cased
tags:
- generated_from_trainer
datasets:
- bionlp2004
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-cased-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: bionlp2004
type: bionlp2004
config: bionlp2004
split: validation
args: bionlp2004
metrics:
- name: Precision
type: precision
value: 0.7436025257560651
- name: Recall
type: recall
value: 0.8058707005222402
- name: F1
type: f1
value: 0.7734854377322617
- name: Accuracy
type: accuracy
value: 0.9356447830424587
distilbert-base-cased-ner
This model is a fine-tuned version of distilbert-base-cased on the bionlp2004 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2048
- Precision: 0.7436
- Recall: 0.8059
- F1: 0.7735
- Accuracy: 0.9356
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2313 | 1.0 | 2078 | 0.2127 | 0.7120 | 0.7810 | 0.7449 | 0.9287 |
| 0.184 | 2.0 | 4156 | 0.1992 | 0.7258 | 0.7999 | 0.7611 | 0.9353 |
| 0.1471 | 3.0 | 6234 | 0.2048 | 0.7436 | 0.8059 | 0.7735 | 0.9356 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1