|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- en |
|
|
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: bert_tiny_lda_100_v1_qqp |
|
|
results: |
|
|
- task: |
|
|
name: Text Classification |
|
|
type: text-classification |
|
|
dataset: |
|
|
name: GLUE QQP |
|
|
type: glue |
|
|
args: qqp |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.8543408360128617 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.8063020096700984 |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# bert_tiny_lda_100_v1_qqp |
|
|
|
|
|
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE QQP dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3551 |
|
|
- Accuracy: 0.8543 |
|
|
- F1: 0.8063 |
|
|
- Combined Score: 0.8303 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:| |
|
|
| 0.4874 | 1.0 | 1422 | 0.4274 | 0.7980 | 0.7125 | 0.7553 | |
|
|
| 0.388 | 2.0 | 2844 | 0.3786 | 0.8224 | 0.7726 | 0.7975 | |
|
|
| 0.3354 | 3.0 | 4266 | 0.3613 | 0.8372 | 0.7899 | 0.8136 | |
|
|
| 0.2928 | 4.0 | 5688 | 0.3564 | 0.8447 | 0.7830 | 0.8139 | |
|
|
| 0.2583 | 5.0 | 7110 | 0.3614 | 0.8509 | 0.7997 | 0.8253 | |
|
|
| 0.2277 | 6.0 | 8532 | 0.3551 | 0.8543 | 0.8063 | 0.8303 | |
|
|
| 0.2014 | 7.0 | 9954 | 0.3854 | 0.8552 | 0.8093 | 0.8322 | |
|
|
| 0.1784 | 8.0 | 11376 | 0.3979 | 0.8545 | 0.8064 | 0.8305 | |
|
|
| 0.1578 | 9.0 | 12798 | 0.4261 | 0.8558 | 0.8102 | 0.8330 | |
|
|
| 0.1403 | 10.0 | 14220 | 0.4443 | 0.8588 | 0.8108 | 0.8348 | |
|
|
| 0.1246 | 11.0 | 15642 | 0.4678 | 0.8567 | 0.8093 | 0.8330 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.2.1+cu118 |
|
|
- Datasets 2.17.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
