context_based_qa
This model is a fine-tuned version of camembert-base on the squad_fr dataset. It achieves the following results on the evaluation set:
- Loss: 1.6218
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 |
|---|---|---|---|
| 1.8512 | 1.0 | 3829 | 1.7145 |
| 1.543 | 2.0 | 7658 | 1.6075 |
| 1.3907 | 3.0 | 11487 | 1.6218 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2+cpu
- Datasets 2.12.0
- Tokenizers 0.13.2
Dataset Usage
It used the squad_fr dataset from qwant.
- Downloads last month
- 23
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.
Model tree for cquentin48/context_based_qa
Base model
almanach/camembert-base