|
|
--- |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: hBERTv1_new_pretrain_mrpc |
|
|
results: |
|
|
- task: |
|
|
name: Text Classification |
|
|
type: text-classification |
|
|
dataset: |
|
|
name: GLUE MRPC |
|
|
type: glue |
|
|
config: mrpc |
|
|
split: validation |
|
|
args: mrpc |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.6838235294117647 |
|
|
- name: F1 |
|
|
type: f1 |
|
|
value: 0.8122270742358079 |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# hBERTv1_new_pretrain_mrpc |
|
|
|
|
|
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new) on the GLUE MRPC dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6018 |
|
|
- Accuracy: 0.6838 |
|
|
- F1: 0.8122 |
|
|
- Combined Score: 0.7480 |
|
|
|
|
|
## 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: 4e-05 |
|
|
- train_batch_size: 128 |
|
|
- eval_batch_size: 128 |
|
|
- 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 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:| |
|
|
| 0.6855 | 1.0 | 29 | 0.6255 | 0.6838 | 0.8122 | 0.7480 | |
|
|
| 0.647 | 2.0 | 58 | 0.6536 | 0.6838 | 0.8122 | 0.7480 | |
|
|
| 0.6336 | 3.0 | 87 | 0.6537 | 0.6838 | 0.8122 | 0.7480 | |
|
|
| 0.6007 | 4.0 | 116 | 0.6018 | 0.6838 | 0.8122 | 0.7480 | |
|
|
| 0.5196 | 5.0 | 145 | 0.6852 | 0.6544 | 0.7273 | 0.6908 | |
|
|
| 0.3703 | 6.0 | 174 | 0.7167 | 0.6838 | 0.7709 | 0.7273 | |
|
|
| 0.2697 | 7.0 | 203 | 0.9072 | 0.7010 | 0.7953 | 0.7481 | |
|
|
| 0.1997 | 8.0 | 232 | 1.0467 | 0.6765 | 0.7651 | 0.7208 | |
|
|
| 0.1629 | 9.0 | 261 | 1.0809 | 0.6593 | 0.7495 | 0.7044 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.29.2 |
|
|
- Pytorch 1.14.0a0+410ce96 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
