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-v0.1
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: few_nerd
type: few_nerd
args: supervised
metrics:
- name: Precision
type: precision
value: 0.7377633209417596
- name: Recall
type: recall
value: 0.7817648386368765
- name: F1
type: f1
value: 0.7591269959856158
- name: Accuracy
type: accuracy
value: 0.9383331648547562
Cybonto-distilbert-base-uncased-finetuned-ner-v0.1
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: 0.1930
- Precision: 0.7378
- Recall: 0.7818
- F1: 0.7591
- Accuracy: 0.9383
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: 36
- eval_batch_size: 36
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2001 | 1.0 | 3661 | 0.1954 | 0.7244 | 0.7750 | 0.7488 | 0.9360 |
| 0.1717 | 2.0 | 7322 | 0.1898 | 0.7392 | 0.7767 | 0.7575 | 0.9384 |
| 0.1485 | 3.0 | 10983 | 0.1930 | 0.7378 | 0.7818 | 0.7591 | 0.9383 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6