metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: trained_slovak
results: []
trained_slovak
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1216
- Precision: 0.5864
- Recall: 0.4015
- F1: 0.4766
- Accuracy: 0.9679
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.99 | 33 | 0.1546 | 0.5429 | 0.0033 | 0.0065 | 0.9547 |
| No log | 1.98 | 66 | 0.1291 | 0.4814 | 0.3492 | 0.4048 | 0.9656 |
| No log | 2.98 | 99 | 0.1216 | 0.5864 | 0.4015 | 0.4766 | 0.9679 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2