Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
prototype_multiple_question – AI Model by dflcmu | AlphaNeural AI
You can deploy this model and start earning money today!
dflcmu
/
prototype_multiple_question
like
0
transformers
pytorch
tensorboard
roberta
multiple-choice
generated_from_trainer
swag
cc-by-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
prototype_multiple_question
This model is a fine-tuned version of
deepset/roberta-base-squad2
on the swag dataset. It achieves the following results on the evaluation set:
Loss: 0.6287
Accuracy: 0.8095
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: 5e-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
Accuracy
0.8148
1.0
4597
0.6297
0.7594
0.5495
2.0
9194
0.5768
0.7927
0.2971
3.0
13791
0.6287
0.8095
Framework versions
Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3
