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_serbian
results: []
trained_serbian
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: 0.0786
- Precision: 0.8138
- Recall: 0.8795
- F1: 0.8454
- Accuracy: 0.9774
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 | 1.0 | 104 | 0.1030 | 0.7317 | 0.7706 | 0.7507 | 0.9667 |
| No log | 2.0 | 208 | 0.0814 | 0.8001 | 0.8642 | 0.8309 | 0.9757 |
| No log | 3.0 | 312 | 0.0786 | 0.8138 | 0.8795 | 0.8454 | 0.9774 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2