metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_base_lda_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_lda_5_v1_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.837867919861489
- name: F1
type: f1
value: 0.7795971890655996
bert_base_lda_5_v1_qqp
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_5_v1 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3662
- Accuracy: 0.8379
- F1: 0.7796
- Combined Score: 0.8087
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 |
|---|---|---|---|---|---|---|
| 0.449 | 1.0 | 1422 | 0.3986 | 0.8140 | 0.7293 | 0.7717 |
| 0.3328 | 2.0 | 2844 | 0.3662 | 0.8379 | 0.7796 | 0.8087 |
| 0.2532 | 3.0 | 4266 | 0.3697 | 0.8430 | 0.7975 | 0.8202 |
| 0.1908 | 4.0 | 5688 | 0.4016 | 0.8528 | 0.7973 | 0.8250 |
| 0.1448 | 5.0 | 7110 | 0.4637 | 0.8542 | 0.7932 | 0.8237 |
| 0.112 | 6.0 | 8532 | 0.4905 | 0.8572 | 0.8037 | 0.8304 |
| 0.0917 | 7.0 | 9954 | 0.5420 | 0.8560 | 0.8002 | 0.8281 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3