metadata
license: mit
base_model: cointegrated/rubert-tiny2
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: rubert-tiny-two-example
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.6808952126871202
- name: Recall
type: recall
value: 0.7731403567822283
- name: F1
type: f1
value: 0.7240917329970842
- name: Accuracy
type: accuracy
value: 0.948779898526214
rubert-tiny-two-example
This model is a fine-tuned version of cointegrated/rubert-tiny2 on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1719
- Precision: 0.6809
- Recall: 0.7731
- F1: 0.7241
- Accuracy: 0.9488
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 |
|---|---|---|---|---|---|---|---|
| 0.2925 | 1.0 | 1756 | 0.2403 | 0.5587 | 0.6641 | 0.6068 | 0.9273 |
| 0.1975 | 2.0 | 3512 | 0.1833 | 0.6607 | 0.7526 | 0.7036 | 0.9457 |
| 0.1726 | 3.0 | 5268 | 0.1719 | 0.6809 | 0.7731 | 0.7241 | 0.9488 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cpu
- Datasets 2.19.2
- Tokenizers 0.19.1