metadata
license: apache-2.0
base_model: distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BERT_B08
results: []
BERT_B08
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: 0.3054
- Precision: 0.6335
- Recall: 0.6849
- F1: 0.6582
- Accuracy: 0.9094
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 |
|---|---|---|---|---|---|---|---|
| 0.3792 | 1.0 | 92 | 0.3446 | 0.6004 | 0.5913 | 0.5958 | 0.8982 |
| 0.2782 | 2.0 | 184 | 0.2911 | 0.6485 | 0.6664 | 0.6573 | 0.9110 |
| 0.1736 | 3.0 | 276 | 0.2886 | 0.6570 | 0.6730 | 0.6649 | 0.9123 |
| 0.1434 | 4.0 | 368 | 0.2974 | 0.6481 | 0.6763 | 0.6619 | 0.9109 |
| 0.1422 | 5.0 | 460 | 0.3054 | 0.6335 | 0.6849 | 0.6582 | 0.9094 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3