metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_B02
results: []
BERT_B02
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: 0.5303
- Precision: 0.5901
- Recall: 0.6373
- F1: 0.6128
- Accuracy: 0.8529
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: 4e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.8874 | 1.0 | 47 | 0.7667 | 0.4130 | 0.364 | 0.3870 | 0.7897 |
| 0.5169 | 2.0 | 94 | 0.5512 | 0.5390 | 0.608 | 0.5714 | 0.8469 |
| 0.3529 | 3.0 | 141 | 0.5238 | 0.5913 | 0.6173 | 0.6040 | 0.8542 |
| 0.2603 | 4.0 | 188 | 0.5243 | 0.5926 | 0.6227 | 0.6073 | 0.8521 |
| 0.2134 | 5.0 | 235 | 0.5303 | 0.5901 | 0.6373 | 0.6128 | 0.8529 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3