metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: hw1
results: []
hw1
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: 0.9151
- Matthews Correlation: 0.5294
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: 1.2246998000876558e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 6
- 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 |
|---|---|---|---|---|
| 0.4949 | 1.0 | 1069 | 0.4726 | 0.4647 |
| 0.3651 | 2.0 | 2138 | 0.5118 | 0.5239 |
| 0.2996 | 3.0 | 3207 | 0.7391 | 0.5299 |
| 0.2181 | 4.0 | 4276 | 0.8309 | 0.5139 |
| 0.1807 | 5.0 | 5345 | 0.9151 | 0.5294 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1