metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-multilingual-cased-finetuned-en_de_pt
results: []
distilbert-base-multilingual-cased-finetuned-en_de_pt
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: 3.3271
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3969 | 1.0 | 67 | 3.6289 |
| 3.8957 | 2.0 | 134 | 3.7617 |
| 3.7469 | 3.0 | 201 | 3.4861 |
| 3.6244 | 4.0 | 268 | 3.5451 |
| 3.5513 | 5.0 | 335 | 3.2156 |
| 3.5667 | 6.0 | 402 | 3.3271 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1