Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
distil-roberta-qa – AI Model by vaibhav9 | AlphaNeural AI
You can deploy this model and start earning money today!
vaibhav9
/
distil-roberta-qa
like
0
transformers
pytorch
tensorboard
roberta
question-answering
generated_from_trainer
cc-by-4.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
distil-roberta-qa
This model is a fine-tuned version of
deepset/tinyroberta-squad2
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.5542
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: 32
eval_batch_size: 32
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
0.6017
1.0
1882
0.5264
0.4438
2.0
3764
0.5333
0.3427
3.0
5646
0.5542
Framework versions
Transformers 4.25.1
Pytorch 1.11.0+cu102
Datasets 2.8.0
Tokenizers 0.13.2
