metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/distilbert_lda_5_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert_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: 0.8923818946326985
- name: F1
type: f1
value: 0.8591772664012687
distilbert_lda_5_v1_book_qqp
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_5_v1_book on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.2694
- Accuracy: 0.8924
- F1: 0.8592
- Combined Score: 0.8758
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 |
|---|---|---|---|---|---|---|
| 0.3639 | 1.0 | 1422 | 0.2923 | 0.8723 | 0.8247 | 0.8485 |
| 0.2514 | 2.0 | 2844 | 0.2710 | 0.8812 | 0.8480 | 0.8646 |
| 0.1851 | 3.0 | 4266 | 0.2694 | 0.8924 | 0.8592 | 0.8758 |
| 0.134 | 4.0 | 5688 | 0.2956 | 0.8939 | 0.8562 | 0.8750 |
| 0.0985 | 5.0 | 7110 | 0.3307 | 0.8945 | 0.8562 | 0.8753 |
| 0.076 | 6.0 | 8532 | 0.3846 | 0.8946 | 0.8588 | 0.8767 |
| 0.0609 | 7.0 | 9954 | 0.3922 | 0.8930 | 0.8558 | 0.8744 |
| 0.0505 | 8.0 | 11376 | 0.4375 | 0.8933 | 0.8583 | 0.8758 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1