Downloads · 30 days
35
11% of all-time downloads
turkish-electra-tquad
muratsimsek003/turkish-electra-tquad
turkish-electra-tquad is a question answering model from muratsimsek003. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
311
Public
Parameters
110M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors440 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- mit
- Model type
- electra
- Access
- Public
- Created
- Nov 8, 2024
- Updated
- Nov 20, 2024
- SHA
- d52fa6ed
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
turkish-electra-tquad
This model is a fine-tuned version of dbmdz/electra-base-turkish-cased-discriminator on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3721
- F1: 1.0225
- Exact Match: 0.0
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: 16
- eval_batch_size: 16
- seed: 42
- 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 | F1 | Exact Match |
|---|---|---|---|---|---|
| 1.6287 | 1.0 | 520 | 1.4853 | 0.8821 | 0.0 |
| 1.1809 | 2.0 | 1040 | 1.3662 | 0.9583 | 0.0 |
| 0.9459 | 3.0 | 1560 | 1.3721 | 1.0225 | 0.0 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.0
- Task
- Question Answering
- Library
- transformers
- Type
- electra
- License
- mit
- Created
- Nov 8, 2024
- Updated
- Nov 20, 2024