metadata
license: cc-by-4.0
base_model: dicta-il/dictabert
tags:
- generated_from_trainer
datasets:
- nemo_corpus
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: nemo_corpus
type: nemo_corpus
config: flat_token
split: validation
args: flat_token
metrics:
- name: Precision
type: precision
value: 0.8606811145510835
- name: Recall
type: recall
value: 0.852760736196319
- name: F1
type: f1
value: 0.8567026194144837
- name: Accuracy
type: accuracy
value: 0.9786301369863014
bert-finetuned-ner
This model is a fine-tuned version of dicta-il/dictabert on the nemo_corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.1102
- Precision: 0.8607
- Recall: 0.8528
- F1: 0.8567
- Accuracy: 0.9786
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 |
|---|---|---|---|---|---|---|---|
| 0.2884 | 1.0 | 618 | 0.1202 | 0.8182 | 0.8006 | 0.8093 | 0.9733 |
| 0.0896 | 2.0 | 1236 | 0.1081 | 0.8298 | 0.8374 | 0.8336 | 0.9771 |
| 0.0548 | 3.0 | 1854 | 0.1102 | 0.8607 | 0.8528 | 0.8567 | 0.9786 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cpu
- Datasets 2.15.0
- Tokenizers 0.15.0