|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/bert_uncased_L-2_H-128_A-2 |
|
model-index: |
|
- name: tiny-mlm-glue-qqp |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# tiny-mlm-glue-qqp |
|
|
|
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.5533 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- num_epochs: 200 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 4.313 | 0.4 | 500 | 3.8831 | |
|
| 4.1839 | 0.8 | 1000 | 3.7763 | |
|
| 4.0803 | 1.2 | 1500 | 3.6769 | |
|
| 3.9319 | 1.6 | 2000 | 3.6800 | |
|
| 3.8968 | 2.0 | 2500 | 3.6765 | |
|
| 3.8441 | 2.4 | 3000 | 3.5576 | |
|
| 3.7809 | 2.8 | 3500 | 3.6472 | |
|
| 3.8456 | 3.2 | 4000 | 3.5526 | |
|
| 3.682 | 3.6 | 4500 | 3.5926 | |
|
| 3.749 | 4.0 | 5000 | 3.5727 | |
|
| 3.6818 | 4.4 | 5500 | 3.5533 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
