metadata
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: news-category-classifier-distilbert
results: []
news-category-classifier-distilbert
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1519
- Accuracy: 0.9513
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.4239 | 1.0 | 2289 | 0.9138 | 0.2604 |
| 0.3058 | 2.0 | 4578 | 0.9240 | 0.2384 |
| 0.3846 | 3.0 | 6867 | 0.9304 | 0.2280 |
| 0.138 | 4.0 | 9156 | 0.9333 | 0.2280 |
| 0.1904 | 5.0 | 11445 | 0.9468 | 0.1775 |
| 0.193 | 6.0 | 13734 | 0.9468 | 0.1775 |
| 0.0425 | 7.0 | 16023 | 0.9468 | 0.1775 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1