# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("FredDYyy/roberta-base-squadv2")
model = AutoModelForQuestionAnswering.from_pretrained("FredDYyy/roberta-base-squadv2")Quick Links
roberta-base-squadv2
This model is a fine-tuned version of roberta-base on the squad_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6731
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|
| 1.1898 | 1.0 | 1221 | 1.5332 |
| 0.7719 | 2.0 | 2443 | 1.5191 |
| 0.5484 | 3.0 | 3663 | 1.6731 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="FredDYyy/roberta-base-squadv2")