metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: distilbert-base-uncased-finetuned-cola
results: []
distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7867
- Matthews Correlation: 0.5312
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: 1.2364553135564726e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 5
- 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 |
|---|---|---|---|---|
| 0.5405 | 1.0 | 2138 | 0.6268 | 0.4122 |
| 0.485 | 2.0 | 4276 | 0.7867 | 0.5312 |
| 0.3086 | 3.0 | 6414 | 0.9165 | 0.5238 |
| 0.2457 | 4.0 | 8552 | 1.0430 | 0.5136 |
| 0.2357 | 5.0 | 10690 | 1.1299 | 0.5252 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2