metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_20_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_km_20_v2_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8158792975513233
- name: F1
type: f1
value: 0.7507032819825854
bert_base_km_20_v2_qqp
This model is a fine-tuned version of Hartunka/bert_base_km_20_v2 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3973
- Accuracy: 0.8159
- F1: 0.7507
- Combined Score: 0.7833
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.4797 | 1.0 | 1422 | 0.4332 | 0.7929 | 0.6880 | 0.7404 |
| 0.371 | 2.0 | 2844 | 0.3973 | 0.8159 | 0.7507 | 0.7833 |
| 0.2919 | 3.0 | 4266 | 0.4062 | 0.8167 | 0.7721 | 0.7944 |
| 0.2234 | 4.0 | 5688 | 0.4300 | 0.8318 | 0.7711 | 0.8015 |
| 0.1687 | 5.0 | 7110 | 0.4925 | 0.8354 | 0.7750 | 0.8052 |
| 0.1294 | 6.0 | 8532 | 0.5532 | 0.8354 | 0.7686 | 0.8020 |
| 0.1015 | 7.0 | 9954 | 0.6021 | 0.8350 | 0.7747 | 0.8049 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1