metadata
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_km_5_v2_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8237447440019787
- name: F1
type: f1
value: 0.762450830055337
bert_base_km_5_v2_qqp
This model is a fine-tuned version of Hartunka/bert_base_km_5_v2 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3830
- Accuracy: 0.8237
- F1: 0.7625
- Combined Score: 0.7931
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 |
|---|---|---|---|---|---|---|
| 0.4655 | 1.0 | 1422 | 0.4296 | 0.7971 | 0.6871 | 0.7421 |
| 0.3502 | 2.0 | 2844 | 0.3830 | 0.8237 | 0.7625 | 0.7931 |
| 0.2673 | 3.0 | 4266 | 0.4028 | 0.8350 | 0.7760 | 0.8055 |
| 0.2003 | 4.0 | 5688 | 0.4558 | 0.8396 | 0.7713 | 0.8054 |
| 0.151 | 5.0 | 7110 | 0.4538 | 0.8437 | 0.7796 | 0.8117 |
| 0.1178 | 6.0 | 8532 | 0.5561 | 0.8424 | 0.7802 | 0.8113 |
| 0.0952 | 7.0 | 9954 | 0.5664 | 0.8406 | 0.7861 | 0.8134 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1