metadata
base_model: mor40/BulBERT-chitanka-model
tags:
- generated_from_trainer
datasets:
- bgglue
metrics:
- accuracy
model-index:
- name: BulBERT-fakenews-5epochs
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: bgglue
type: bgglue
config: fakenews
split: validation
args: fakenews
metrics:
- name: Accuracy
type: accuracy
value: 0.9049773755656109
BulBERT-fakenews-5epochs
This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the bgglue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3487
- Accuracy: 0.9050
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: 32
- eval_batch_size: 32
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 84 | 0.4732 | 0.7511 |
| No log | 2.0 | 168 | 0.3922 | 0.8552 |
| No log | 3.0 | 252 | 0.3230 | 0.8778 |
| No log | 4.0 | 336 | 0.3518 | 0.8959 |
| No log | 5.0 | 420 | 0.3487 | 0.9050 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1