distilbert-base-multilingual-cased-finetuned-imdb-v2
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: 2.2042
- 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 |
|---|---|---|---|---|
| 2.6967 | 1.0 | 259 | 2.4319 | 0.0 |
| 2.5156 | 2.0 | 518 | 2.3565 | 0.0 |
| 2.4422 | 3.0 | 777 | 2.3096 | 0.0 |
| 2.4045 | 4.0 | 1036 | 2.2846 | 0.0 |
| 2.3612 | 5.0 | 1295 | 2.2520 | 0.0 |
| 2.3413 | 6.0 | 1554 | 2.2347 | 0.0 |
| 2.3211 | 7.0 | 1813 | 2.2225 | 0.0 |
| 2.3099 | 8.0 | 2072 | 2.2142 | 0.0 |
| 2.2957 | 9.0 | 2331 | 2.2033 | 0.0 |
| 2.2919 | 10.0 | 2590 | 2.1960 | 0.0 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0