electra-small-turkish-uncased-discriminator-finetuned_lr-2e-05_epochs-3
This model is a fine-tuned version of loodos/electra-small-turkish-uncased-discriminator on the Turkish squad dataset. It achieves the following results on the evaluation set:
- Loss: 2.1669
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 |
---|---|---|---|
2.5305 | 1.0 | 5818 | 2.4024 |
2.3264 | 2.0 | 11636 | 2.2298 |
2.1762 | 3.0 | 17454 | 2.1669 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
- Downloads last month
- 12
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.