metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_5_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_5_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: 0.8787286668315607
- name: F1
type: f1
value: 0.8352652622383496
bert_tiny_lda_5_v1_book_qqp
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_5_v1_book on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2895
- Accuracy: 0.8787
- F1: 0.8353
- Combined Score: 0.8570
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 |
|---|---|---|---|---|---|---|
| 0.3935 | 1.0 | 1422 | 0.3346 | 0.8488 | 0.7845 | 0.8166 |
| 0.294 | 2.0 | 2844 | 0.2951 | 0.8698 | 0.8284 | 0.8491 |
| 0.2397 | 3.0 | 4266 | 0.2895 | 0.8787 | 0.8353 | 0.8570 |
| 0.1952 | 4.0 | 5688 | 0.3010 | 0.8811 | 0.8347 | 0.8579 |
| 0.1584 | 5.0 | 7110 | 0.3140 | 0.8839 | 0.8439 | 0.8639 |
| 0.128 | 6.0 | 8532 | 0.3402 | 0.8852 | 0.8485 | 0.8668 |
| 0.1045 | 7.0 | 9954 | 0.3547 | 0.8845 | 0.8442 | 0.8644 |
| 0.0881 | 8.0 | 11376 | 0.3848 | 0.8849 | 0.8479 | 0.8664 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3