metadata
base_model: mor40/BulBERT-chitanka-model
tags:
- generated_from_trainer
datasets:
- bgglue
model-index:
- name: BulBERT-exams-5epochs
results: []
BulBERT-exams-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: 2.9622
- Acc: 0.2946
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Acc |
|---|---|---|---|---|
| 1.0207 | 1.0 | 2538 | 1.9309 | 0.3004 |
| 0.9505 | 2.0 | 5076 | 2.7472 | 0.2750 |
| 0.9552 | 3.0 | 7614 | 2.7331 | 0.2913 |
| 0.9126 | 4.0 | 10152 | 2.8254 | 0.2798 |
| 0.8957 | 5.0 | 12690 | 2.9622 | 0.2946 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1