metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_20_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_lda_20_v1_book_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8944595597328716
- name: F1
type: f1
value: 0.8609327640713098
bert_base_lda_20_v1_book_qqp
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_20_v1_book on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2672
- Accuracy: 0.8945
- F1: 0.8609
- Combined Score: 0.8777
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 |
|---|---|---|---|---|---|---|
| 0.3572 | 1.0 | 1422 | 0.2867 | 0.8733 | 0.8318 | 0.8526 |
| 0.2449 | 2.0 | 2844 | 0.2800 | 0.8809 | 0.8501 | 0.8655 |
| 0.1784 | 3.0 | 4266 | 0.2672 | 0.8945 | 0.8609 | 0.8777 |
| 0.1265 | 4.0 | 5688 | 0.2889 | 0.8951 | 0.8612 | 0.8782 |
| 0.0934 | 5.0 | 7110 | 0.3325 | 0.8966 | 0.8566 | 0.8766 |
| 0.0723 | 6.0 | 8532 | 0.3647 | 0.8955 | 0.8605 | 0.8780 |
| 0.0576 | 7.0 | 9954 | 0.4287 | 0.8960 | 0.8634 | 0.8797 |
| 0.0486 | 8.0 | 11376 | 0.3932 | 0.8967 | 0.8600 | 0.8784 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3