metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: output
results: []
output
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: 0.4129
- Accuracy: 0.918
- F1: 0.9180
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 | F1 |
|---|---|---|---|---|---|
| 0.314 | 1.0 | 500 | 0.2791 | 0.893 | 0.8926 |
| 0.1636 | 2.0 | 1000 | 0.2975 | 0.9095 | 0.9095 |
| 0.0832 | 3.0 | 1500 | 0.3482 | 0.915 | 0.9150 |
| 0.0483 | 4.0 | 2000 | 0.4060 | 0.919 | 0.9190 |
| 0.0329 | 5.0 | 2500 | 0.4129 | 0.918 | 0.9180 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0