metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- data_set
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: data_set
type: data_set
config: conll2003
split: train
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.2080536912751678
- name: Recall
type: recall
value: 0.1949685534591195
- name: F1
type: f1
value: 0.20129870129870134
- name: Accuracy
type: accuracy
value: 0.9193947914574546
bert-finetuned-ner
This model is a fine-tuned version of bert-base-cased on the data_set dataset. It achieves the following results on the evaluation set:
- Loss: 0.3395
- Precision: 0.2081
- Recall: 0.1950
- F1: 0.2013
- Accuracy: 0.9194
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 | 100 | 0.3796 | 0.125 | 0.0755 | 0.0941 | 0.9152 |
| No log | 2.0 | 200 | 0.3512 | 0.2131 | 0.1635 | 0.1851 | 0.9208 |
| No log | 3.0 | 300 | 0.3395 | 0.2081 | 0.1950 | 0.2013 | 0.9194 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2