Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
roberta-large-finetuned-GLUE-QNLI – AI Model by du33169 | AlphaNeural AI
You can deploy this model and start earning money today!
du33169
/
roberta-large-finetuned-GLUE-QNLI
like
0
safetensors
roberta
generated_from_trainer
en
glue
FacebookAI/roberta-large
finetune
model-index
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
QNLI
This model is a fine-tuned version of
FacebookAI/roberta-large
on the GLUE QNLI dataset. It achieves the following results on the evaluation set:
Loss: 0.2250
Accuracy: 0.9451
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: 64
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6.0
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.2269
1.0
1637
0.1639
0.9363
0.1637
2.0
3274
0.1718
0.9372
0.0977
3.0
4911
0.1788
0.9425
0.0672
4.0
6548
0.2250
0.9451
0.0437
5.0
8185
0.2863
0.9431
0.0289
6.0
9822
0.3216
0.9438
Framework versions
Transformers 4.43.3
Pytorch 1.11.0+cu113
Datasets 2.20.0
Tokenizers 0.19.1
