metadata
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: 0.6088262979015748
longformer-base-4096-finetuned-cola
This model is a fine-tuned version of allenai/longformer-base-4096 on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5601
- Matthews Correlation: 0.6088
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 | 0.5854 | 0.4865 |
| 0.4087 | 2.0 | 536 | 0.4939 | 0.5495 |
| 0.4087 | 3.0 | 804 | 0.6292 | 0.5687 |
| 0.1978 | 4.0 | 1072 | 0.5601 | 0.6088 |
| 0.1978 | 5.0 | 1340 | 0.6785 | 0.5931 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1