metadata
base_model: bert-base-uncased
library_name: transformers
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: Finetuning_BERT_BBCNews
results: []
Finetuning_BERT_BBCNews
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: 0.1125
- Accuracy: 0.9775
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 195 | 0.0810 | 0.9775 |
| No log | 2.0 | 390 | 0.1163 | 0.9730 |
| 0.1923 | 3.0 | 585 | 0.1213 | 0.9820 |
| 0.1923 | 4.0 | 780 | 0.0941 | 0.9775 |
| 0.1923 | 5.0 | 975 | 0.1148 | 0.9820 |
| 0.0098 | 6.0 | 1170 | 0.1389 | 0.9820 |
| 0.0098 | 7.0 | 1365 | 0.1032 | 0.9730 |
| 0.0044 | 8.0 | 1560 | 0.1165 | 0.9820 |
| 0.0044 | 9.0 | 1755 | 0.1126 | 0.9820 |
| 0.0044 | 10.0 | 1950 | 0.1125 | 0.9775 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0