distilbert-base-uncased-finetuned-sngp-for-qa-squad-seed-9990
This model is a fine-tuned version of distilbert-base-uncased on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.9271
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 |
|---|---|---|---|
| 2.4046 | 1.0 | 8248 | 2.0792 |
| 2.0132 | 2.0 | 16496 | 1.8262 |
| 1.7824 | 3.0 | 24744 | 1.9271 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 105
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.