Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
roberta-base-squadv2 – AI Model by FredDYyy | AlphaNeural AI
You can deploy this model and start earning money today!
FredDYyy
/
roberta-base-squadv2
like
0
transformers
pytorch
tensorboard
roberta
question-answering
generated_from_trainer
squad_v2
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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
