|
--- |
|
language: |
|
- en |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: hBERTv2_data_aug_wnli |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE WNLI |
|
type: glue |
|
args: wnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.5633802816901409 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# hBERTv2_data_aug_wnli |
|
|
|
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE WNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6873 |
|
- Accuracy: 0.5634 |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.699 | 1.0 | 218 | 0.6895 | 0.5634 | |
|
| 0.6947 | 2.0 | 436 | 0.6886 | 0.5634 | |
|
| 0.6935 | 3.0 | 654 | 0.6873 | 0.5634 | |
|
| 0.6937 | 4.0 | 872 | 0.6921 | 0.5634 | |
|
| 0.6934 | 5.0 | 1090 | 0.6892 | 0.5634 | |
|
| 0.6932 | 6.0 | 1308 | 0.6911 | 0.5634 | |
|
| 0.6933 | 7.0 | 1526 | 0.6955 | 0.4366 | |
|
| 0.6931 | 8.0 | 1744 | 0.6908 | 0.5634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.14.0a0+410ce96 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
