metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- few_nerd
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Cybonto-distilbert-base-uncased-finetuned-ner-FewNerd
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: few_nerd
type: few_nerd
args: supervised
metrics:
- name: Precision
type: precision
value: 0.7422259388187705
- name: Recall
type: recall
value: 0.7830368683449253
- name: F1
type: f1
value: 0.7620854216169805
- name: Accuracy
type: accuracy
value: 0.9386106950200795
Cybonto-distilbert-base-uncased-finetuned-ner-FewNerd
This model is a fine-tuned version of distilbert-base-uncased on the few_nerd dataset. It achieves the following results on the evaluation set:
- Loss: 0.2091
- Precision: 0.7422
- Recall: 0.7830
- F1: 0.7621
- Accuracy: 0.9386
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1964 | 1.0 | 4118 | 0.1946 | 0.7302 | 0.7761 | 0.7525 | 0.9366 |
| 0.1685 | 2.0 | 8236 | 0.1907 | 0.7414 | 0.7776 | 0.7591 | 0.9384 |
| 0.145 | 3.0 | 12354 | 0.1967 | 0.7454 | 0.7816 | 0.7631 | 0.9388 |
| 0.1263 | 4.0 | 16472 | 0.2021 | 0.7402 | 0.7845 | 0.7617 | 0.9384 |
| 0.1114 | 5.0 | 20590 | 0.2091 | 0.7422 | 0.7830 | 0.7621 | 0.9386 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1