metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- few_nerd
metrics:
- precision
- recall
- f1
- accuracy
pipeline_tag: token-classification
base_model: distilbert-base-uncased
model-index:
- name: distilbert-base-uncased-finetuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: few_nerd
type: few_nerd
args: supervised
metrics:
- type: precision
value: 0.6424480067658478
name: Precision
- type: recall
value: 0.6854236732015421
name: Recall
- type: f1
value: 0.6632404008334158
name: F1
- type: accuracy
value: 0.9075199647113962
name: Accuracy
distilbert-base-uncased-finetuned-ner
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: 0.3136
- Precision: 0.6424
- Recall: 0.6854
- F1: 0.6632
- Accuracy: 0.9075
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.328 | 1.0 | 8236 | 0.3197 | 0.6274 | 0.6720 | 0.6489 | 0.9041 |
| 0.2776 | 2.0 | 16472 | 0.3111 | 0.6433 | 0.6759 | 0.6592 | 0.9069 |
| 0.241 | 3.0 | 24708 | 0.3136 | 0.6424 | 0.6854 | 0.6632 | 0.9075 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.1.0
- Tokenizers 0.12.1