metadata
license: mit
base_model: deepset/gelectra-large-germanquad
tags:
- generated_from_trainer
model-index:
- name: Finetuned_Question_Answering_Model
results: []
Finetuned_Question_Answering_Model
This model is a fine-tuned version of deepset/gelectra-large-germanquad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0090
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: 5
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7296 | 1.0 | 3 | 0.0478 |
| 0.9269 | 2.0 | 6 | 0.0365 |
| 0.1316 | 3.0 | 9 | 0.0271 |
| 0.08 | 4.0 | 12 | 0.0201 |
| 0.0648 | 5.0 | 15 | 0.0155 |
| 0.0185 | 6.0 | 18 | 0.0133 |
| 0.0024 | 7.0 | 21 | 0.0112 |
| 0.0087 | 8.0 | 24 | 0.0100 |
| 0.0586 | 9.0 | 27 | 0.0092 |
| 0.0039 | 10.0 | 30 | 0.0090 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2