metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-uncased-20-News-Group
results: []
bert-uncased-20-News-Group
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8676
- Balanced Accuracy: 0.7123
- Accuracy: 0.7324
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- 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 | Balanced Accuracy | Accuracy |
|---|---|---|---|---|---|
| 1.2155 | 1.0 | 25 | 0.8842 | 0.5767 | 0.6378 |
| 0.6571 | 2.0 | 50 | 0.7429 | 0.6312 | 0.6896 |
| 0.3757 | 3.0 | 75 | 0.7148 | 0.7222 | 0.7317 |
| 0.173 | 4.0 | 100 | 0.8154 | 0.7175 | 0.7347 |
| 0.0638 | 5.0 | 125 | 0.8676 | 0.7123 | 0.7324 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1