metadata
library_name: transformers
language:
- en
base_model: gokulsrinivasagan/bert_tiny_lda_50_v1_book
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_tiny_lda_50_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: 0.8727924808310661
- name: F1
type: f1
value: 0.8236584947711297
bert_tiny_lda_50_v1_book_qqp
This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_lda_50_v1_book on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3001
- Accuracy: 0.8728
- F1: 0.8237
- Combined Score: 0.8482
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 |
|---|---|---|---|---|---|---|
| 0.4008 | 1.0 | 1422 | 0.3670 | 0.8389 | 0.7596 | 0.7993 |
| 0.3043 | 2.0 | 2844 | 0.3162 | 0.8636 | 0.8129 | 0.8383 |
| 0.2505 | 3.0 | 4266 | 0.3001 | 0.8728 | 0.8237 | 0.8482 |
| 0.2074 | 4.0 | 5688 | 0.3213 | 0.8740 | 0.8186 | 0.8463 |
| 0.1699 | 5.0 | 7110 | 0.3346 | 0.8776 | 0.8287 | 0.8531 |
| 0.1392 | 6.0 | 8532 | 0.3586 | 0.8808 | 0.8395 | 0.8602 |
| 0.1151 | 7.0 | 9954 | 0.3763 | 0.8820 | 0.8390 | 0.8605 |
| 0.0954 | 8.0 | 11376 | 0.3984 | 0.8820 | 0.8376 | 0.8598 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3