Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
roberta-fa-zwnj-base-finetuned-PQuAD-3epochs – AI Model by Z-Jafari | AlphaNeural AI
You can deploy this model and start earning money today!
Z-Jafari
/
roberta-fa-zwnj-base-finetuned-PQuAD-3epochs
like
0
transformers
tensorboard
safetensors
roberta
question-answering
generated_from_trainer
fa
Z-Jafari/PQuAD
HooshvareLab/roberta-fa-zwnj-base
finetune
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
roberta-fa-zwnj-base-finetuned-PQuAD-3epochs
This model is a fine-tuned version of
HooshvareLab/roberta-fa-zwnj-base
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 1.0544
{'exact': 69.28267933016745, 'f1': 82.1337789035037, 'total': 8002, 'HasAns_exact': 63.370565045992116, 'HasAns_f1': 80.26190847336343, 'HasAns_total': 6088, 'NoAns_exact': 88.08777429467085, 'NoAns_f1': 88.08777429467085, 'NoAns_total': 1914, 'best_exact': 69.28267933016745, 'best_exact_thresh': 0.0, 'best_f1': 82.13377890350401, 'best_f1_thresh': 0.0}
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.0485
1.0
4020
1.0218
0.733
2.0
8040
1.0029
0.5001
3.0
12060
1.0544
Framework versions
Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1
