metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test_trainer
results: []
test_trainer
This model is a fine-tuned version of bert-base-cased on imdb dataset. It achieves the following results on the evaluation set:
- Loss: 0.6039
- Accuracy: 0.9038
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: 5e-05
- 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 | Accuracy |
|---|---|---|---|---|
| 0.4533 | 1.0 | 500 | 0.5298 | 0.802 |
| 0.2644 | 2.0 | 1000 | 0.4896 | 0.8852 |
| 0.1317 | 3.0 | 1500 | 0.4272 | 0.9015 |
| 0.0579 | 4.0 | 2000 | 0.5598 | 0.904 |
| 0.0177 | 5.0 | 2500 | 0.6039 | 0.9038 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1