distilbert-base-multilingual-cased-finetuned-imdb-v1
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2385
- Model Preparation Time: 0.0
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: 64
- eval_batch_size: 64
- 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 | Model Preparation Time |
|---|---|---|---|---|
| 2.717 | 1.0 | 207 | 2.4718 | 0.0 |
| 2.535 | 2.0 | 414 | 2.3905 | 0.0 |
| 2.4733 | 3.0 | 621 | 2.3432 | 0.0 |
| 2.4287 | 4.0 | 828 | 2.3092 | 0.0 |
| 2.4045 | 5.0 | 1035 | 2.2898 | 0.0 |
| 2.3726 | 6.0 | 1242 | 2.2734 | 0.0 |
| 2.3534 | 7.0 | 1449 | 2.2569 | 0.0 |
| 2.3474 | 8.0 | 1656 | 2.2455 | 0.0 |
| 2.3307 | 9.0 | 1863 | 2.2463 | 0.0 |
| 2.3291 | 10.0 | 2070 | 2.2386 | 0.0 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0