Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
RewardModel_RobertaBase – AI Model by RajuThesis | AlphaNeural AI
You can deploy this model and start earning money today!
RajuThesis
/
RewardModel_RobertaBase
like
0
transformers
tensorboard
safetensors
roberta
text-classification
generated_from_trainer
FacebookAI/roberta-base
finetune
mit
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
RewardModel_RobertaBase
This model is a fine-tuned version of
roberta-base
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.4742
F1: 0.7921
Roc Auc: 0.7917
Accuracy: 0.7897
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: 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
F1
Roc Auc
Accuracy
No log
1.0
93
0.6779
0.6257
0.625
0.6230
0.6429
2.0
186
0.4775
0.7833
0.7837
0.7817
0.5357
3.0
279
0.4742
0.7921
0.7917
0.7897
Framework versions
Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1
