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: 0.7005
- Matthews Correlation: 0.0
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 | 0.7005 | 0.0 |
| 0.6995 | 2.0 | 536 | 0.6960 | -0.0043 |
| 0.6995 | 3.0 | 804 | 0.6976 | -0.0057 |
| 0.6962 | 4.0 | 1072 | 0.6983 | -0.0123 |
| 0.6962 | 5.0 | 1340 | 0.6977 | -0.0529 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.