metadata
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-tiny-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.5147295742232451
- name: Recall
type: recall
value: 0.5003915426781519
- name: F1
type: f1
value: 0.5074593000170173
- name: Accuracy
type: accuracy
value: 0.8967226396810015
bert-tiny-finetuned-ner
This model is a fine-tuned version of prajjwal1/bert-tiny on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4053
- Precision: 0.5147
- Recall: 0.5004
- F1: 0.5075
- Accuracy: 0.8967
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 |
|---|---|---|---|---|---|---|---|
| 0.9306 | 1.0 | 878 | 0.5040 | 0.4321 | 0.4099 | 0.4207 | 0.8762 |
| 0.4777 | 2.0 | 1756 | 0.4240 | 0.4978 | 0.4851 | 0.4913 | 0.8926 |
| 0.4306 | 3.0 | 2634 | 0.4053 | 0.5147 | 0.5004 | 0.5075 | 0.8967 |
Framework versions
- Transformers 4.10.0
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3