metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_olda_book_10_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_olda_book_10_v1_qqp
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE QQP
type: glue
args: qqp
metrics:
- name: Accuracy
type: accuracy
value: 0.8799901063566659
- name: F1
type: f1
value: 0.841251145138071
bert_tiny_olda_book_10_v1_qqp
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_olda_book_10_v1 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2816
- Accuracy: 0.8800
- F1: 0.8413
- Combined Score: 0.8606
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 OptimizerNames.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 |
|---|---|---|---|---|---|---|
| 0.3941 | 1.0 | 1422 | 0.3365 | 0.8496 | 0.7836 | 0.8166 |
| 0.2912 | 2.0 | 2844 | 0.2905 | 0.8710 | 0.8323 | 0.8516 |
| 0.2365 | 3.0 | 4266 | 0.2816 | 0.8800 | 0.8413 | 0.8606 |
| 0.1917 | 4.0 | 5688 | 0.2965 | 0.8807 | 0.8349 | 0.8578 |
| 0.157 | 5.0 | 7110 | 0.3086 | 0.8831 | 0.8474 | 0.8653 |
| 0.1268 | 6.0 | 8532 | 0.3240 | 0.8849 | 0.8496 | 0.8672 |
| 0.1053 | 7.0 | 9954 | 0.3513 | 0.8878 | 0.8496 | 0.8687 |
| 0.0878 | 8.0 | 11376 | 0.3817 | 0.8864 | 0.8520 | 0.8692 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1