Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
fine-tuned-roberta-large-swag-peft – AI Model by amritpuhan | AlphaNeural AI
You can deploy this model and start earning money today!
amritpuhan
/
fine-tuned-roberta-large-swag-peft
like
0
peft
safetensors
generated_from_trainer
allenai/swag
FacebookAI/roberta-large
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
fine-tuned-roberta-large-swag-peft
This model is a fine-tuned version of
FacebookAI/roberta-large
on SWAG dataset. It achieves the following results on the evaluation set:
Loss: 0.3473
Accuracy: 0.8730
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: 1.5e-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: 4
Training results
Training Loss
Epoch
Step
Validation Loss
Accuracy
0.7002
1.0
4597
0.4130
0.8536
0.6414
2.0
9194
0.3676
0.8677
0.628
3.0
13791
0.3556
0.8703
0.6137
4.0
18388
0.3473
0.8730
Framework versions
PEFT 0.11.1
Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.19.2
Tokenizers 0.19.1
