metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
base_model: distilbert-base-multilingual-cased
model-index:
- name: distilbertmultilang
results: []
distilbertmultilang
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5628
- Accuracy: 0.7527
- Precision: 0.7353
- Recall: 0.6867
- F1: 0.6967
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: 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: 999
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4753 | 1.0 | 761 | 0.5657 | 0.7471 | 0.7146 | 0.6782 | 0.6831 |
| 0.0881 | 2.0 | 1522 | 0.6042 | 0.7728 | 0.7387 | 0.7289 | 0.7329 |
| 0.2734 | 3.0 | 2283 | 0.6275 | 0.7757 | 0.7431 | 0.7504 | 0.7459 |
| 0.0468 | 4.0 | 3044 | 0.9842 | 0.7599 | 0.7362 | 0.7048 | 0.7140 |
| 0.0037 | 5.0 | 3805 | 1.0992 | 0.7715 | 0.7402 | 0.7364 | 0.7374 |
| 0.3644 | 6.0 | 4566 | 1.2696 | 0.7521 | 0.7460 | 0.6853 | 0.6928 |
| 0.0078 | 7.0 | 5327 | 1.3667 | 0.7646 | 0.7329 | 0.7273 | 0.7293 |
| 0.0021 | 8.0 | 6088 | 1.5628 | 0.7527 | 0.7353 | 0.6867 | 0.6967 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2