metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: results
results: []
results
This model is a fine-tuned version of bert-base-uncased on an Kwaai/IMDB_Sentiment dataset. It achieves the following results on the evaluation set:
- Loss: 0.3875
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: 0.002
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5455 | 1.0 | 782 | 0.4385 |
| 0.4874 | 2.0 | 1564 | 0.4432 |
| 0.4862 | 3.0 | 2346 | 0.4612 |
| 0.4723 | 4.0 | 3128 | 0.4084 |
| 0.4641 | 5.0 | 3910 | 0.4454 |
| 0.4655 | 6.0 | 4692 | 0.3979 |
| 0.4609 | 7.0 | 5474 | 0.3867 |
| 0.4551 | 8.0 | 6256 | 0.3876 |
| 0.4546 | 9.0 | 7038 | 0.3835 |
| 0.4525 | 10.0 | 7820 | 0.3875 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1