metadata
license: mit
base_model: microsoft/deberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-base-clickbait-task1-post-para-title
results: []
deberta-base-clickbait-task1-post-para-title
This model is a fine-tuned version of microsoft/deberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7941
- Accuracy: 0.7675
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: 16
- eval_batch_size: 16
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 200 | 0.7693 | 0.65 |
| No log | 2.0 | 400 | 0.7033 | 0.7375 |
| 0.763 | 3.0 | 600 | 0.6864 | 0.7475 |
| 0.763 | 4.0 | 800 | 0.7415 | 0.76 |
| 0.3299 | 5.0 | 1000 | 0.7941 | 0.7675 |
Framework versions
- Transformers 4.44.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1