|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- matthews_correlation |
|
model-index: |
|
- name: longformer-base-4096-finetuned-cola |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: glue |
|
type: glue |
|
args: cola |
|
metrics: |
|
- name: Matthews Correlation |
|
type: matthews_correlation |
|
value: 0.5912435391119252 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# longformer-base-4096-finetuned-cola |
|
|
|
This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the glue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5643 |
|
- Matthews Correlation: 0.5912 |
|
|
|
## 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: 2e-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: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------:| |
|
| No log | 1.0 | 268 | 0.4890 | 0.5080 | |
|
| 0.4099 | 2.0 | 536 | 0.4874 | 0.5312 | |
|
| 0.4099 | 3.0 | 804 | 0.5917 | 0.5733 | |
|
| 0.197 | 4.0 | 1072 | 0.5643 | 0.5912 | |
|
| 0.197 | 5.0 | 1340 | 0.6762 | 0.5863 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu102 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
