metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: mymodel_2024
results: []
mymodel_2024
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: 0.8945
- Matthews Correlation: 0.5232
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: 9.899001593609293e-06
- train_batch_size: 8
- eval_batch_size: 16
- seed: 30
- 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 |
|---|---|---|---|---|
| 0.509 | 1.0 | 1069 | 0.5366 | 0.4025 |
| 0.3925 | 2.0 | 2138 | 0.6003 | 0.4916 |
| 0.2998 | 3.0 | 3207 | 0.6921 | 0.4865 |
| 0.2377 | 4.0 | 4276 | 0.8213 | 0.5235 |
| 0.2098 | 5.0 | 5345 | 0.8945 | 0.5232 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2