metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- xglue
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-tiny-finetuned-xglue-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: xglue
type: xglue
config: ner
split: train
args: ner
metrics:
- name: Precision
type: precision
value: 0.630759453447728
- name: Recall
type: recall
value: 0.6681252103668799
- name: F1
type: f1
value: 0.6489048708728343
- name: Accuracy
type: accuracy
value: 0.9274310133922189
bert-tiny-finetuned-xglue-ner
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the xglue dataset. It achieves the following results on the evaluation set:
- Loss: 0.2489
- Precision: 0.6308
- Recall: 0.6681
- F1: 0.6489
- Accuracy: 0.9274
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 |
|---|---|---|---|---|---|---|---|
| 0.4082 | 1.0 | 1756 | 0.3326 | 0.5600 | 0.5798 | 0.5697 | 0.9118 |
| 0.2974 | 2.0 | 3512 | 0.2635 | 0.6143 | 0.6562 | 0.6346 | 0.9248 |
| 0.2741 | 3.0 | 5268 | 0.2489 | 0.6308 | 0.6681 | 0.6489 | 0.9274 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1