|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: tiny-mlm-glue-qnli-target-glue-mnli |
|
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-qnli-target-glue-mnli |
|
|
|
This model is a fine-tuned version of [muhtasham/tiny-mlm-glue-qnli](https://huggingface.co/muhtasham/tiny-mlm-glue-qnli) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7907 |
|
- Accuracy: 0.6507 |
|
|
|
## 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 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 1.0753 | 0.04 | 500 | 1.0327 | 0.4677 | |
|
| 1.0084 | 0.08 | 1000 | 0.9655 | 0.5434 | |
|
| 0.962 | 0.12 | 1500 | 0.9232 | 0.5779 | |
|
| 0.9358 | 0.16 | 2000 | 0.9087 | 0.5874 | |
|
| 0.9241 | 0.2 | 2500 | 0.8928 | 0.5963 | |
|
| 0.9157 | 0.24 | 3000 | 0.8772 | 0.5988 | |
|
| 0.8992 | 0.29 | 3500 | 0.8687 | 0.6088 | |
|
| 0.8928 | 0.33 | 4000 | 0.8571 | 0.6173 | |
|
| 0.8757 | 0.37 | 4500 | 0.8529 | 0.6164 | |
|
| 0.8774 | 0.41 | 5000 | 0.8438 | 0.6232 | |
|
| 0.8694 | 0.45 | 5500 | 0.8372 | 0.6246 | |
|
| 0.8653 | 0.49 | 6000 | 0.8350 | 0.6265 | |
|
| 0.8677 | 0.53 | 6500 | 0.8268 | 0.6292 | |
|
| 0.8584 | 0.57 | 7000 | 0.8270 | 0.6326 | |
|
| 0.8508 | 0.61 | 7500 | 0.8134 | 0.6391 | |
|
| 0.8521 | 0.65 | 8000 | 0.8110 | 0.6416 | |
|
| 0.8447 | 0.69 | 8500 | 0.8264 | 0.6323 | |
|
| 0.8466 | 0.73 | 9000 | 0.7951 | 0.6468 | |
|
| 0.8379 | 0.77 | 9500 | 0.8089 | 0.6401 | |
|
| 0.8277 | 0.81 | 10000 | 0.7941 | 0.6477 | |
|
| 0.8307 | 0.86 | 10500 | 0.7999 | 0.6437 | |
|
| 0.8289 | 0.9 | 11000 | 0.7874 | 0.6530 | |
|
| 0.8228 | 0.94 | 11500 | 0.7835 | 0.6524 | |
|
| 0.8228 | 0.98 | 12000 | 0.7851 | 0.6511 | |
|
| 0.8078 | 1.02 | 12500 | 0.7907 | 0.6507 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu116 |
|
- Datasets 2.8.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
