metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: results
results: []
results
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: 0.4465
- Accuracy: 0.8226
- F1: 0.8220
- Precision: 0.8231
- Recall: 0.8226
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: 4.993596574084884e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.0218 | 1.0 | 622 | 0.8816 | 0.5732 | 0.5732 | 0.5812 | 0.5732 |
| 0.8654 | 2.0 | 1244 | 0.7610 | 0.6600 | 0.6539 | 0.6620 | 0.6600 |
| 0.7534 | 3.0 | 1866 | 0.6904 | 0.6962 | 0.6912 | 0.7079 | 0.6962 |
| 0.6593 | 4.0 | 2488 | 0.6406 | 0.7342 | 0.7290 | 0.7454 | 0.7342 |
| 0.5278 | 5.0 | 3110 | 0.5557 | 0.7740 | 0.7732 | 0.7763 | 0.7740 |
| 0.4939 | 6.0 | 3732 | 0.5420 | 0.7776 | 0.7764 | 0.7819 | 0.7776 |
| 0.4585 | 7.0 | 4354 | 0.5258 | 0.7920 | 0.7899 | 0.7999 | 0.7920 |
| 0.4181 | 8.0 | 4976 | 0.5013 | 0.8029 | 0.8023 | 0.8046 | 0.8029 |
| 0.3804 | 9.0 | 5598 | 0.4922 | 0.8065 | 0.8053 | 0.8109 | 0.8065 |
| 0.3642 | 10.0 | 6220 | 0.4823 | 0.8065 | 0.8056 | 0.8085 | 0.8065 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1