metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: ace
split: validation
args: ace
metrics:
- name: Precision
type: precision
value: 0.20394736842105263
- name: Recall
type: recall
value: 0.2897196261682243
- name: F1
type: f1
value: 0.23938223938223938
- name: Accuracy
type: accuracy
value: 0.817741935483871
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.6372
- Precision: 0.2039
- Recall: 0.2897
- F1: 0.2394
- Accuracy: 0.8177
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 13 | 0.7383 | 0.1463 | 0.1121 | 0.1270 | 0.7737 |
| No log | 2.0 | 26 | 0.6586 | 0.1618 | 0.2056 | 0.1811 | 0.8075 |
| No log | 3.0 | 39 | 0.6372 | 0.2039 | 0.2897 | 0.2394 | 0.8177 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3